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.1699276199.rhmmedcatt-proliant-ml350-gen10 b/.summary/0/events.out.tfevents.1699276199.rhmmedcatt-proliant-ml350-gen10 new file mode 100644 index 0000000000000000000000000000000000000000..230a59e35b532016d8d0d628b8d86c5f5fbc1513 --- /dev/null +++ b/.summary/0/events.out.tfevents.1699276199.rhmmedcatt-proliant-ml350-gen10 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e32522d3c547dfa8153b3fc97cdf6762ab478e66f974a16ce2705d0421a9214 +size 40 diff --git a/.summary/0/events.out.tfevents.1699279610.rhmmedcatt-proliant-ml350-gen10 b/.summary/0/events.out.tfevents.1699279610.rhmmedcatt-proliant-ml350-gen10 new file mode 100644 index 0000000000000000000000000000000000000000..30161c1ff810e676335ed1339e393c8dac8b566b --- /dev/null +++ b/.summary/0/events.out.tfevents.1699279610.rhmmedcatt-proliant-ml350-gen10 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:304f2be194674c64aed54a9d8f25d2df87cffd18b5ca7839867528d7120f4916 +size 86332506 diff --git a/.summary/1/events.out.tfevents.1699276199.rhmmedcatt-proliant-ml350-gen10 b/.summary/1/events.out.tfevents.1699276199.rhmmedcatt-proliant-ml350-gen10 new file mode 100644 index 0000000000000000000000000000000000000000..d445624f865f161379cef07d27f57cde27867289 --- /dev/null +++ b/.summary/1/events.out.tfevents.1699276199.rhmmedcatt-proliant-ml350-gen10 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41bc75c0902ab905046e771a3e315f749d1d9a5d72bf417701f936917747d4b4 +size 40 diff --git a/.summary/1/events.out.tfevents.1699279610.rhmmedcatt-proliant-ml350-gen10 b/.summary/1/events.out.tfevents.1699279610.rhmmedcatt-proliant-ml350-gen10 new file mode 100644 index 0000000000000000000000000000000000000000..9a3712706b490670ef20b42dc35bfff0d9fda9dd --- /dev/null +++ b/.summary/1/events.out.tfevents.1699279610.rhmmedcatt-proliant-ml350-gen10 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f0b1f243cfd11ee172f74489fae09df6ddded131bab1406de036b6f1cafd184 +size 45477613 diff --git a/README.md b/README.md index 96710fa530cf52037ea1aa6ace3f9cc75338b7eb..9fe70625dbd981bfcbd8079276757dbd29ab9e37 100644 --- a/README.md +++ b/README.md @@ -15,35 +15,39 @@ model-index: type: atari_hero metrics: - type: mean_reward - value: 35738.00 +/- 2517.72 + value: 44548.50 +/- 163.14 name: mean_reward verified: false --- -A(n) **APPO** model trained on the **atari_hero** environment. +## About the Project -This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory. -Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/ +This project is an attempt to maximise performance of high sample throughput APPO RL models in Atari environments in as carbon efficient a manner as possible using a single, not particularly high performance single machine. It is about demonstrating the generalisability of on-policy algorithms to create good performance quickly (by sacrificing sample efficiency) while also proving that this route to RL production is accessible to even hobbyists like me (I am a gastroenterologist not a computer scientist). +In terms of throughput I am managing to reach throughputs of 2,500 - 3,000 across both policies using sample factory using two Quadro P2200's (not particularly powerful GPUs) each loaded up about 60% (3GB). Previously using the stable baselines 3 (sb3) implementation of PPO it would take about a week to train an atari agent to 100 million timesteps synchronously. By comparison the sample factory async implementation takes only just over 2 hours to achieve the same result. That is about 84 times faster with only typically a 21 watt burn per GPU. I am thus very grateful to Alex Petrenko and all the sample factory team for their work on this. -## Downloading the model +## Project Aims -After installing Sample-Factory, download the model with: -``` -python -m sample_factory.huggingface.load_from_hub -r MattStammers/APPO-atari_hero -``` +This model as with all the others in the benchmarks was trained initially asynchronously un-seeded to 10 million steps for the purposes of setting a sample factory async baseline for this model on this environment but only 3/57 made it anywhere near sota performance. - -## About the Model +I then re-trained the models with 100 million timesteps- at this point 2 environments maxed out at sota performance (Pong and Freeway) with four approaching sota performance - (atlantis, boxing, tennis and fishingderby.) =6/57 near sota. + +The aim now is to try and reach state-of-the-art (SOTA) performance on a further block of atari environments using up to 1 billion training timesteps initially with appo. I will flag the models with SOTA when they reach at or near these levels. -This model as with all the others in the benchmarks was trained initially asynchronously un-seeded to 10 million steps for the purposes of setting a sample factory async baseline for this model on this environment but only 3/57 made it. +After this I will switch on V-Trace to see if the Impala variations perform any better with the same seed (I have seeded '1234') -The aim is to reach state-of-the-art (SOTA) performance on each atari environment. I will flag the models with SOTA when they reach at or near these levels. -The hyperparameters used in the model are the ones I have pushed to my fork of sample-factory: https://github.com/MattStammers/sample-factory. Given that https://huggingface.co/edbeeching has kindly shared his. -I saved time and energy by using many of his tuned hyperparameters to maximise performance. However, he used 2 billion training steps. I have started as explained above at 10 million then moved to 100m to see how performance goes: +## About the Model + +The hyperparameters used in the model are described in my shell script on my fork of sample-factory: https://github.com/MattStammers/sample-factory. Given that https://huggingface.co/edbeeching has kindly shared his parameters, I saved time and energy by using many of his tuned hyperparameters to reduce carbon inefficiency: ``` hyperparameters = { + "help": false, + "algo": "APPO", + "env": "atari_asteroid", + "experiment": "atari_asteroid_APPO", + "train_dir": "./train_atari", + "restart_behavior": "restart", "device": "gpu", "seed": 1234, "num_policies": 2, @@ -141,12 +145,28 @@ hyperparameters = { "env_gpu_observations": true, "env_frameskip": 4, "env_framestack": 4, - } + "pixel_format": "CHW" +} ``` +A(n) **APPO** model trained on the **atari_hero** environment. + +This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory. Sample factory is a +high throughput on-policy RL framework. I have been using +Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/ + + +## Downloading the model + +After installing Sample-Factory, download the model with: +``` +python -m sample_factory.huggingface.load_from_hub -r MattStammers/APPO-atari_hero +``` + + ## Using the model To run the model after download, use the `enjoy` script corresponding to this environment: diff --git a/checkpoint_p0/best_000888824_227540992_reward_110.540.pth b/checkpoint_p0/best_000888824_227540992_reward_110.540.pth new file mode 100644 index 0000000000000000000000000000000000000000..2774a614e3821358bc715b7d533ec568832294f3 --- /dev/null +++ b/checkpoint_p0/best_000888824_227540992_reward_110.540.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35a064cb1aba84c0b9683535bd07433a4326bd53ce36015be1831fe416bc6b9c +size 20795763 diff --git a/checkpoint_p0/checkpoint_001651576_422805504.pth b/checkpoint_p0/checkpoint_001651576_422805504.pth new file mode 100644 index 0000000000000000000000000000000000000000..08c01d8c17e3094d42bd605975856f96084c11b5 --- /dev/null +++ b/checkpoint_p0/checkpoint_001651576_422805504.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56680be284a2a6d38264c0322309464b070e72a283c85cc6fdfe2a9e60dfd087 +size 20796099 diff --git a/checkpoint_p0/checkpoint_001651928_422895616.pth b/checkpoint_p0/checkpoint_001651928_422895616.pth new file mode 100644 index 0000000000000000000000000000000000000000..c24285065cb859cf6b07f7f5fdd31ec0f49c21fc --- /dev/null +++ b/checkpoint_p0/checkpoint_001651928_422895616.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49b17b88847ea33dafe4b884f87d35196d1f09fc873a1c783d46277c7f4fbb2f +size 20796099 diff --git a/checkpoint_p0/milestones/checkpoint_000010848_2777088.pth b/checkpoint_p0/milestones/checkpoint_000010848_2777088.pth new file mode 100644 index 0000000000000000000000000000000000000000..26baa711e5d5d24332c4077dbed9eb4ea9f79d5d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000010848_2777088.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c97d5dd157dbe68b9c610ae181337c00de8c20b743378d6600e07de637b357e +size 20796955 diff --git a/checkpoint_p0/milestones/checkpoint_000022080_5652480.pth b/checkpoint_p0/milestones/checkpoint_000022080_5652480.pth new file mode 100644 index 0000000000000000000000000000000000000000..9023da47abca9ed388642a797342e661508af93d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000022080_5652480.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58cf6fd2fee6bf91da51447759eb6d37ef7df321901d3cbadecdc4325b72902b +size 20796955 diff --git a/checkpoint_p0/milestones/checkpoint_000033344_8536064.pth b/checkpoint_p0/milestones/checkpoint_000033344_8536064.pth new file mode 100644 index 0000000000000000000000000000000000000000..374ac26be261b91d81923e32c88c0a8215fb6d16 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000033344_8536064.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46b7b3184e153a331e2f09cc2ffaa6f78bdd4a20a6bfa743066854fb29111537 +size 20796955 diff --git a/checkpoint_p0/milestones/checkpoint_000044480_11386880.pth b/checkpoint_p0/milestones/checkpoint_000044480_11386880.pth new file mode 100644 index 0000000000000000000000000000000000000000..26dad8849f7b7c5bda952a2f86d80aa35480a8bb --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000044480_11386880.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:919cb5aa6644e63de79bdeb826b3f2fbe435789eff91c2f569ab23c36195d837 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000055584_14229504.pth b/checkpoint_p0/milestones/checkpoint_000055584_14229504.pth new file mode 100644 index 0000000000000000000000000000000000000000..4df513be008e58acb49fb0bd52326a6380b3fb40 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000055584_14229504.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:014221c08dba36029e49f973516a195e21ddd4e06dbd3fa025b2d996e3fc469c +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000066528_17031168.pth b/checkpoint_p0/milestones/checkpoint_000066528_17031168.pth new file mode 100644 index 0000000000000000000000000000000000000000..c6c1a37a70223975370cdb46681424b1b9ab29a7 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000066528_17031168.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:408807798ab874cb1aac876b758d3b012546d15bef28a31cfe483a85e3811733 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000077504_19841024.pth b/checkpoint_p0/milestones/checkpoint_000077504_19841024.pth new file mode 100644 index 0000000000000000000000000000000000000000..858487df5a1cfec6dfebd9b1f5bf11931e4e4256 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000077504_19841024.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8bbc24ed07141fc077848c88ea1c12600871afdfac19cca4b479fc0efc06675 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000088480_22650880.pth b/checkpoint_p0/milestones/checkpoint_000088480_22650880.pth new file mode 100644 index 0000000000000000000000000000000000000000..f239c16d3eedc71693d6f786e8ef36780b51b3de --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000088480_22650880.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c57b9c05eaf6ba30653a97a2dd5f3581e698c5d598d6038a26936012f201bca9 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000099392_25444352.pth b/checkpoint_p0/milestones/checkpoint_000099392_25444352.pth new file mode 100644 index 0000000000000000000000000000000000000000..184d373a3a037227a893988638016adc38ad3ce0 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000099392_25444352.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8a6785f92922ba33175116be4fb3c42e47abb59dce4a7fe713b695a0d6a4cb1 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000110560_28303360.pth b/checkpoint_p0/milestones/checkpoint_000110560_28303360.pth new file mode 100644 index 0000000000000000000000000000000000000000..e3708245d517d75d4cbeaad42783f5acd5c4e0de --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000110560_28303360.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcd65968ba6c2871cdca31fa69e3a76c885f951152b7a5dae471ae45828fb5b3 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000121472_31096832.pth b/checkpoint_p0/milestones/checkpoint_000121472_31096832.pth new file mode 100644 index 0000000000000000000000000000000000000000..c59683a73ece0baab17a8735e9be53dd1d412e55 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000121472_31096832.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ada9a8d4c6a7e5f121f2c31fcce5058fb71ced7cd4bcbe09795f95c3e2d425b +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000132512_33923072.pth b/checkpoint_p0/milestones/checkpoint_000132512_33923072.pth new file mode 100644 index 0000000000000000000000000000000000000000..44832e3219a2ac2d068805d93090965114058a5d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000132512_33923072.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cc8d12875235202507c54a68384a279744c78114ad5c24cda0d1cc918242952 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000143488_36732928.pth b/checkpoint_p0/milestones/checkpoint_000143488_36732928.pth new file mode 100644 index 0000000000000000000000000000000000000000..fe3b68852580234041b1e2e0e645bdafe8ac34a3 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000143488_36732928.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46e494c6443d612c4113521b29ff2b71cb5d3c4c53bfb7ecb50d7d9ec9f57d02 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000154304_39501824.pth b/checkpoint_p0/milestones/checkpoint_000154304_39501824.pth new file mode 100644 index 0000000000000000000000000000000000000000..23cfde750e59ca396f6cd29e1c97fee6f2a0e530 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000154304_39501824.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7c55fafb2b33d38f83dc4515de72189f807e900ddb364388fb1da0d6b0b49bb +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000165504_42369024.pth b/checkpoint_p0/milestones/checkpoint_000165504_42369024.pth new file mode 100644 index 0000000000000000000000000000000000000000..53356e2bab8a7c1aa81e632eee8418d9c40b75dd --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000165504_42369024.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9c7c8807e7d64ae3ded9b076ab2201279e9ca785c6cfee9f7c91a67457cb0b4 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000176768_45252608.pth b/checkpoint_p0/milestones/checkpoint_000176768_45252608.pth new file mode 100644 index 0000000000000000000000000000000000000000..1fb9aa4a1815018f1fd4c144b93c2970cb368ff7 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000176768_45252608.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cbb1b4d4f2bfc03a84b7cbe175d294cf44009b70c91cd4a52cb90006e271eaf +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000187968_48119808.pth b/checkpoint_p0/milestones/checkpoint_000187968_48119808.pth new file mode 100644 index 0000000000000000000000000000000000000000..cba5bb91b0c219dbe4a01fb7e3291226660768d2 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000187968_48119808.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5315499310872395923ac5f790ed2c64757bcbc35085a7a6d8ed813e7fbbd9c3 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000199200_50995200.pth b/checkpoint_p0/milestones/checkpoint_000199200_50995200.pth new file mode 100644 index 0000000000000000000000000000000000000000..0b141e26a4c9794d9f3768105907b28e291fab14 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000199200_50995200.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:370a4f07094e3b7380f066f23b848ef9d44792beb93d8d49a32c06ef90ac64da +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000210496_53886976.pth b/checkpoint_p0/milestones/checkpoint_000210496_53886976.pth new file mode 100644 index 0000000000000000000000000000000000000000..2346174f03668856c9ae00fa25ada6d35cd191aa --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000210496_53886976.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6de9a101e68abe2dc9596d8bba3e588041cc515d11f3dfb6f3edf3ac44a6103 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000221728_56762368.pth b/checkpoint_p0/milestones/checkpoint_000221728_56762368.pth new file mode 100644 index 0000000000000000000000000000000000000000..6a41cf0155596e6b11fba5ef2cae6e828f2a4bdd --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000221728_56762368.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c147878e82b38cda81e7971494a0127ab69740fb35e81730a7916216916ebefa +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000233024_59654144.pth b/checkpoint_p0/milestones/checkpoint_000233024_59654144.pth new file mode 100644 index 0000000000000000000000000000000000000000..093a731aae8fe28286fbb2b604aff3604764b94d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000233024_59654144.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e0d85990358f391ae2f449dc09db01e70ce686520526c11e938bbf29493698b +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000244256_62529536.pth b/checkpoint_p0/milestones/checkpoint_000244256_62529536.pth new file mode 100644 index 0000000000000000000000000000000000000000..fd0963b999ecd02488d97b514d3e342befe8fffa --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000244256_62529536.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c5a7ec4b5fe770d1d5de241e1b4f234877862087aef2811be68cc9b874273f6 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000255552_65421312.pth b/checkpoint_p0/milestones/checkpoint_000255552_65421312.pth new file mode 100644 index 0000000000000000000000000000000000000000..0becf01d4f8050d439f9828d8501f0b3c611b210 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000255552_65421312.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:560c696a5923930e93b4b1780c6f3c8d73d7213cbba90e400fa8d44544fee3a3 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000266848_68313088.pth b/checkpoint_p0/milestones/checkpoint_000266848_68313088.pth new file mode 100644 index 0000000000000000000000000000000000000000..0cb195b5cdda170e4c6ec5ba762377851c88f0c5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000266848_68313088.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:805ce2b5b039830c307fd50013f5a4928b67090a2330984f0c25829ee1323281 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000278176_71213056.pth b/checkpoint_p0/milestones/checkpoint_000278176_71213056.pth new file mode 100644 index 0000000000000000000000000000000000000000..eb76880aa0dfd1c55cc8f7cd444966a516582880 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000278176_71213056.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77f178a93bdae161a2ad8d8a6fdbd85795f362692ca2472ce5d450a1aa8b3aa1 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000289496_74113024.pth b/checkpoint_p0/milestones/checkpoint_000289496_74113024.pth new file mode 100644 index 0000000000000000000000000000000000000000..6a2b5e1b3822b3d04fde9f54c7de2ee742fcefba --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000289496_74113024.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:244312542720c609fe508a4a08f97d8d54c3110523a88f119cfff8fd71b3dd2c +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000300728_76988416.pth b/checkpoint_p0/milestones/checkpoint_000300728_76988416.pth new file mode 100644 index 0000000000000000000000000000000000000000..ee030c67d1f6276e754d505a48d645c9e0f8353b --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000300728_76988416.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e51190acb463331892a962f9d958df59d917ddef17de05c0e21ae7a472aea33a +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000311992_79872000.pth b/checkpoint_p0/milestones/checkpoint_000311992_79872000.pth new file mode 100644 index 0000000000000000000000000000000000000000..0c4c475190d6dc7e6d6f70e6d54ec251d85287a3 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000311992_79872000.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dccad2c8b6d4bbcbe31e30732294962eec148fcab36aaa374ebf94b0279903a +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000323192_82739200.pth b/checkpoint_p0/milestones/checkpoint_000323192_82739200.pth new file mode 100644 index 0000000000000000000000000000000000000000..45fd033e366993561510c133431030a0b31f2e87 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000323192_82739200.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f375eb078a4c4190a154d59e3e28fc261982bc08b8ea5b9fff7c7edc785f7693 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000334072_85524480.pth b/checkpoint_p0/milestones/checkpoint_000334072_85524480.pth new file mode 100644 index 0000000000000000000000000000000000000000..51bab4c06a9fb30c6c61b52640e5b80181cdc4a2 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000334072_85524480.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a024d57d30c8a848aee5e70e28adabf7d65d730495a3f6dbfb0444a7905fe1b +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000345176_88367104.pth b/checkpoint_p0/milestones/checkpoint_000345176_88367104.pth new file mode 100644 index 0000000000000000000000000000000000000000..ce57300d5249d7e8c2877ff0ffef4442b2c49b22 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000345176_88367104.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cfb95ce37f836421fb441cc4042f582a3bfedf910305cb0100e97016b3e04ca +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000356504_91267072.pth b/checkpoint_p0/milestones/checkpoint_000356504_91267072.pth new file mode 100644 index 0000000000000000000000000000000000000000..3788feead2f00895d33f9259b840d3d1717b8ef2 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000356504_91267072.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04dfe89f38a5bd98177a73c602e2d0982a383dbc49878ff93a959afd486c7b1e +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000367800_94158848.pth b/checkpoint_p0/milestones/checkpoint_000367800_94158848.pth new file mode 100644 index 0000000000000000000000000000000000000000..da20a90c94c58888fdf462bcdb9bbf041fbb3eaf --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000367800_94158848.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9203ecf799b562ea66b21a619cd252daac203c44adb4590623fb39cc2e552471 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000379096_97050624.pth b/checkpoint_p0/milestones/checkpoint_000379096_97050624.pth new file mode 100644 index 0000000000000000000000000000000000000000..62206e67b5d51299eec7bbe0b96187b9bcb22a51 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000379096_97050624.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb90bc14cbcf8e0dc59a4c39fce56ab6e5a6fcb40b9b7dab06dc582894a56b48 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000390456_99958784.pth b/checkpoint_p0/milestones/checkpoint_000390456_99958784.pth new file mode 100644 index 0000000000000000000000000000000000000000..57add362903f0302fd0568b3de1647971835b8ab --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000390456_99958784.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a80f06f7ca1489ff968d65fc7536e698a5e0bc1e5d5039435e64c231e776e86a +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000401784_102858752.pth b/checkpoint_p0/milestones/checkpoint_000401784_102858752.pth new file mode 100644 index 0000000000000000000000000000000000000000..3922795ad011c8b8a820e0b579d807204d81ee14 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000401784_102858752.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d09cefab4a6d9e2d3bfbb2e4d0c31d4b24b7eed165ccf8215cfa1d74c1b5e25d +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000413080_105750528.pth b/checkpoint_p0/milestones/checkpoint_000413080_105750528.pth new file mode 100644 index 0000000000000000000000000000000000000000..77c78650497ca2b8d3e00c2804bedab5f6972480 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000413080_105750528.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8387b73fbc412bbefdc289504c8a0c13bc898961c4de86b1cf8b991fbede8f44 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000424408_108650496.pth b/checkpoint_p0/milestones/checkpoint_000424408_108650496.pth new file mode 100644 index 0000000000000000000000000000000000000000..f60a0d3c99985062bf827891da22f6d4fcdb5f81 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000424408_108650496.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1f6c368de9f4cdfe7729be6dbdf986cd84e7d85038e52a8f14f10bfe124b687 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000435736_111550464.pth b/checkpoint_p0/milestones/checkpoint_000435736_111550464.pth new file mode 100644 index 0000000000000000000000000000000000000000..a18d9351bd229d19bfbfd5fc73d38500634fac28 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000435736_111550464.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4375f0020947ff1a781b3b93d85ee87f7d8e601264fcbaaa4a54dbbc45c0c02 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000447096_114458624.pth b/checkpoint_p0/milestones/checkpoint_000447096_114458624.pth new file mode 100644 index 0000000000000000000000000000000000000000..fc009d7ea11c0a25a832de142b94d47c9547b4e5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000447096_114458624.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1a111be455e43e479a632c12d9f17d150930a04b27fe3fdcde7aa6190110ecb +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000458456_117366784.pth b/checkpoint_p0/milestones/checkpoint_000458456_117366784.pth new file mode 100644 index 0000000000000000000000000000000000000000..b3941dd3e512d5981c9555f399d5ca8a4ed817d5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000458456_117366784.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:584d9edc35736b651205187a9004e253e5aa829501076d50b79d1281640797fc +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000469720_120250368.pth b/checkpoint_p0/milestones/checkpoint_000469720_120250368.pth new file mode 100644 index 0000000000000000000000000000000000000000..4cc95cdedcce7f1395a01534c0e7f74da50915c4 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000469720_120250368.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:867274d592d236ab8dfe9599d6424a041a10ef323e050bb47299ca2936c15d91 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000481048_123150336.pth b/checkpoint_p0/milestones/checkpoint_000481048_123150336.pth new file mode 100644 index 0000000000000000000000000000000000000000..dc3550011d34571292b3360d600a5a2d4cf62767 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000481048_123150336.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd4fb7aab5000129215080b81fbc797cee370f544a146d2bf2bf2fd35d2bafbd +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000492312_126033920.pth b/checkpoint_p0/milestones/checkpoint_000492312_126033920.pth new file mode 100644 index 0000000000000000000000000000000000000000..1014a270916819d1578f64e37d72cdc5cc493256 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000492312_126033920.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ab20596f71ce3490f21fb8158a62f2c1ea2c93dad00301fb45c5404ca804963 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000503640_128933888.pth b/checkpoint_p0/milestones/checkpoint_000503640_128933888.pth new file mode 100644 index 0000000000000000000000000000000000000000..38a28a05ef2a6bd7ec8a2adba391c76ce55eee85 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000503640_128933888.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a881b2835049e65c978c4257b7cfcd54e56fcd9ef41897f1ade0b1a3ef0a9409 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000514808_131792896.pth b/checkpoint_p0/milestones/checkpoint_000514808_131792896.pth new file mode 100644 index 0000000000000000000000000000000000000000..92cbe3815467ea5791578e78942d16c699a7a7d3 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000514808_131792896.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d05109046d10344e55f7cd35aa590fcaec7f5589b0f0d78df448f67b0002190 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000526040_134668288.pth b/checkpoint_p0/milestones/checkpoint_000526040_134668288.pth new file mode 100644 index 0000000000000000000000000000000000000000..b90ecc72e8b34d6aca8e4c6fff2d2809cc301dd6 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000526040_134668288.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22fcf70346ae386d08a4591d9ff942ba14c729c80fe860be764b569f0c5ed134 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000537336_137560064.pth b/checkpoint_p0/milestones/checkpoint_000537336_137560064.pth new file mode 100644 index 0000000000000000000000000000000000000000..a3817cabdad747c6e89242996b2c3fba19602d14 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000537336_137560064.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a7d511c555d18d10af2912a67adb6bf76af72f5a21239da8cd1ea182c1f515a +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000548760_140484608.pth b/checkpoint_p0/milestones/checkpoint_000548760_140484608.pth new file mode 100644 index 0000000000000000000000000000000000000000..accd6850516b308968e3214d8e6353e82c82b414 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000548760_140484608.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1d79ebbedd70488b1e7638260e6843a79623e416828b87034e0cb583055f766 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000560024_143368192.pth b/checkpoint_p0/milestones/checkpoint_000560024_143368192.pth new file mode 100644 index 0000000000000000000000000000000000000000..8c738a5205b078941daa3a816564b1a734b03545 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000560024_143368192.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66037b505c213226df1d0ac5098ca7ee6958ebd8f56564ff3689148d5f0c4e49 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000571288_146251776.pth b/checkpoint_p0/milestones/checkpoint_000571288_146251776.pth new file mode 100644 index 0000000000000000000000000000000000000000..624cc203556d62a3a5dba8bfba5572731d41e905 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000571288_146251776.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4619f17613642c068c77a572f93922a9110f495a07551e63d3ccfc35b1a05479 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000582648_149159936.pth b/checkpoint_p0/milestones/checkpoint_000582648_149159936.pth new file mode 100644 index 0000000000000000000000000000000000000000..04e23897e2768bd27e86d0723779723da0078e53 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000582648_149159936.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:013cdb4c922847fad613b0b46edbf26742f9b4bc75d0921588578fd56c1c42ff +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000593944_152051712.pth b/checkpoint_p0/milestones/checkpoint_000593944_152051712.pth new file mode 100644 index 0000000000000000000000000000000000000000..bf1c30fe127129440f84c51a4f84dcdb8bcf13ec --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000593944_152051712.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f1023b18ec65a17ce0994a26c46af3758a6e546084c45a02968c6adc9c02f0a +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000605272_154951680.pth b/checkpoint_p0/milestones/checkpoint_000605272_154951680.pth new file mode 100644 index 0000000000000000000000000000000000000000..0b6473c67522cfe91889b987ed5554fa8e912536 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000605272_154951680.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2c1bc9f951096e9936c8e8ef7b893c9bff26e74cc0612b96ff31bdfa5e51dba +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000616536_157835264.pth b/checkpoint_p0/milestones/checkpoint_000616536_157835264.pth new file mode 100644 index 0000000000000000000000000000000000000000..9f58b189839c4c965ebc0b9cca322d544675dd9d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000616536_157835264.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:456611d8c33f47b044525ddbf730141ed639b06601c66c9d83850b1d6bb15f2c +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000627896_160743424.pth b/checkpoint_p0/milestones/checkpoint_000627896_160743424.pth new file mode 100644 index 0000000000000000000000000000000000000000..f61a2e87bd6b251f8fa966a9f414cbf6b20b036c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000627896_160743424.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79cf1060070614e5cfd6a1f7ae5c86d6f088cd4188179987a0bde42073122f8c +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000639160_163627008.pth b/checkpoint_p0/milestones/checkpoint_000639160_163627008.pth new file mode 100644 index 0000000000000000000000000000000000000000..a086700d79ffdb90a6305e2da9177fe8b161a239 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000639160_163627008.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a801eebb5082675adb177bf0d2c16a8cb6345743398772e9d68ad358d0d32a76 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000650520_166535168.pth b/checkpoint_p0/milestones/checkpoint_000650520_166535168.pth new file mode 100644 index 0000000000000000000000000000000000000000..c2af0b6e2fb49ab6712431b652d7db62b3a65c2a --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000650520_166535168.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db26a0ebd766c6aec9a72553cf220a1f4e91e1c2ecf2c770274b1cd3f35536e5 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000661816_169426944.pth b/checkpoint_p0/milestones/checkpoint_000661816_169426944.pth new file mode 100644 index 0000000000000000000000000000000000000000..9457dd4aae9196336dda58ea2fc04d5418c9e3cb --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000661816_169426944.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fdfb19a3eb1e95ac012038b5e860f3f1e7b0fbaecc02a7d0335719b1afcd945 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000673080_172310528.pth b/checkpoint_p0/milestones/checkpoint_000673080_172310528.pth new file mode 100644 index 0000000000000000000000000000000000000000..ca593f46b2d4a0667aec26abee9d36a6e4dcebe9 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000673080_172310528.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:149ce6d81820ab8889386d4dfff2e44a21071010d41de79d66498a3d5c18f485 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000684504_175235072.pth b/checkpoint_p0/milestones/checkpoint_000684504_175235072.pth new file mode 100644 index 0000000000000000000000000000000000000000..bca6aa39e7e55142a5d038c52e3744519e7f43fc --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000684504_175235072.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:272591643c6282bc1661f834626f17b006858ce9d94545432a9e273d017b536c +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000695864_178143232.pth b/checkpoint_p0/milestones/checkpoint_000695864_178143232.pth new file mode 100644 index 0000000000000000000000000000000000000000..c29863cd95c224161dc51cabdedac62983c7d334 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000695864_178143232.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9d8db9e6918fbde8806a9e54ed6d53a43856b0b3608a2fce6751ca51ebead02 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000707160_181035008.pth b/checkpoint_p0/milestones/checkpoint_000707160_181035008.pth new file mode 100644 index 0000000000000000000000000000000000000000..9f78205fd37d044925f86c1f6ef9abd55c8ad51e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000707160_181035008.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7455decf11012f8086688dad28ab5ac8fca6eb3f66596532c637ba606cac7528 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000718168_183853056.pth b/checkpoint_p0/milestones/checkpoint_000718168_183853056.pth new file mode 100644 index 0000000000000000000000000000000000000000..9dcd091ae8de59bf0606347863120424412f1e0f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000718168_183853056.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37630f1a6ae9daa0225a7c136d2cfbdf4df3ec30bfac823ae01a5e79d73adc54 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000728664_186540032.pth b/checkpoint_p0/milestones/checkpoint_000728664_186540032.pth new file mode 100644 index 0000000000000000000000000000000000000000..64f22c36fbfd3efc7b0130b288a9fbadf85ad34d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000728664_186540032.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:926d6a5551ec2cd12a90ab519db260f8092a19eb5f9e80b91f34ac1e75927f4f +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000739096_189210624.pth b/checkpoint_p0/milestones/checkpoint_000739096_189210624.pth new file mode 100644 index 0000000000000000000000000000000000000000..4eba675035c5b94196cd6216daf78500fd0f3817 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000739096_189210624.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d32033694345bc30b0a8c3abf02fc2ca6cc694753d3b47a1ac87b12501bb9040 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000749656_191913984.pth b/checkpoint_p0/milestones/checkpoint_000749656_191913984.pth new file mode 100644 index 0000000000000000000000000000000000000000..0cfeffab19b79e46866d5f021d8057da3021f86b --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000749656_191913984.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13d30d42bde665e864045001cbfec8870a4337033192e37246f23ffb222c9cd7 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000760824_194772992.pth b/checkpoint_p0/milestones/checkpoint_000760824_194772992.pth new file mode 100644 index 0000000000000000000000000000000000000000..18dc0661585682a8ea036717e4a8344489402008 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000760824_194772992.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:825dccb274d2c3f424d7e1a9a2cf4c0e162ec330f999ed30470c9e88fa23a626 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000772152_197672960.pth b/checkpoint_p0/milestones/checkpoint_000772152_197672960.pth new file mode 100644 index 0000000000000000000000000000000000000000..32b1e176d9691091f3320771151672e6854662ea --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000772152_197672960.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:131efb894e6b593f8a86cea4c184a2ae415eeba5f0a5ed5759d93c4f6dcc2eda +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000783544_200589312.pth b/checkpoint_p0/milestones/checkpoint_000783544_200589312.pth new file mode 100644 index 0000000000000000000000000000000000000000..74fd3ce5c62393452edf1313a1aabc917d89cd8e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000783544_200589312.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c90a38c09a8e5068e984fee1355a5aa53f07c1267bb35ab2273238712fb19db +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000794936_203505664.pth b/checkpoint_p0/milestones/checkpoint_000794936_203505664.pth new file mode 100644 index 0000000000000000000000000000000000000000..dbceab015ab8332f93eb6026cedac6e91294b51b --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000794936_203505664.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d640d834babfd7583ee6b290542375fac69ff1d51e938547d99b4610c126ac5f +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000806328_206422016.pth b/checkpoint_p0/milestones/checkpoint_000806328_206422016.pth new file mode 100644 index 0000000000000000000000000000000000000000..8e458730a67b44dc3c4a246c36c3d1feca7b8cd6 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000806328_206422016.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79d664cdc6a93bdb74aba6f261c7fd285678f71dbbb18666ba0658a3b0101550 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000817688_209330176.pth b/checkpoint_p0/milestones/checkpoint_000817688_209330176.pth new file mode 100644 index 0000000000000000000000000000000000000000..db86830ec46e55b3b6413ca010b716679a7e3309 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000817688_209330176.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4f39e5c1be37dad581459adb78db2fb50293d9c04d0e1136a55681f2933abd7 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000829016_212230144.pth b/checkpoint_p0/milestones/checkpoint_000829016_212230144.pth new file mode 100644 index 0000000000000000000000000000000000000000..cfa71b465f24597e136856f8d28579bcf62d05d4 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000829016_212230144.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecd8a4fdf6029a66f84f41766c34800a34904910d41ecd709e15e8739850096a +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000840376_215138304.pth b/checkpoint_p0/milestones/checkpoint_000840376_215138304.pth new file mode 100644 index 0000000000000000000000000000000000000000..061b65cea3c6a782cdd68e6363291b2700d7177d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000840376_215138304.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb7fdde6253f3c4f6e26ae055150fef91403308ba0c63155a39b9a27e507b418 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000851736_218046464.pth b/checkpoint_p0/milestones/checkpoint_000851736_218046464.pth new file mode 100644 index 0000000000000000000000000000000000000000..42c4aeb787bdb5b33b1de1d4b4dc0d6af05280c7 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000851736_218046464.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:892811f0d5a1db892695a35db50d932d798bbd8036859400b7edd12e2369aef3 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000863064_220946432.pth b/checkpoint_p0/milestones/checkpoint_000863064_220946432.pth new file mode 100644 index 0000000000000000000000000000000000000000..7226a1560d719441c70c6f9b4345db48d5430eb4 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000863064_220946432.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec3b1cfd90fa466960e2a625835e417f683523dcc322233f2c47506beaef00a5 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000874360_223838208.pth b/checkpoint_p0/milestones/checkpoint_000874360_223838208.pth new file mode 100644 index 0000000000000000000000000000000000000000..5cfca367f20cc84c1b0b37233297a213e9dbdf4b --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000874360_223838208.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86f290eb0c70605442f350a5646658184fdfb2fb33ad134cd4cd6e589539190b +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000885720_226746368.pth b/checkpoint_p0/milestones/checkpoint_000885720_226746368.pth new file mode 100644 index 0000000000000000000000000000000000000000..1726b13bd8a56877937f3b6e0b6e44727d4dc9d4 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000885720_226746368.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:516ff1f15bf19f61a12e3face5547dd93d4bf8da1d613dc07cfaabf54b0201ac +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000897048_229646336.pth b/checkpoint_p0/milestones/checkpoint_000897048_229646336.pth new file mode 100644 index 0000000000000000000000000000000000000000..c295500591a79db0ca3b65700c865249f6a419e9 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000897048_229646336.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:952dd7a7ff836eb0294121c83a9eff57cc934b07d503463c47d68a596aec64c2 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000908440_232562688.pth b/checkpoint_p0/milestones/checkpoint_000908440_232562688.pth new file mode 100644 index 0000000000000000000000000000000000000000..0dd0478ff59f084379208018f8026aed409b6fe0 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000908440_232562688.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93b36d82fe11c1778ed3feeca865ee38fe1983ee283d57f835dd202a2dbde023 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000919736_235454464.pth b/checkpoint_p0/milestones/checkpoint_000919736_235454464.pth new file mode 100644 index 0000000000000000000000000000000000000000..78ce6a72127b76e1257e6d68e8621926d6fdc9e0 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000919736_235454464.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f92c9d496e1164aeca211a8b6e14bacd5fe4428b7b807cb22c8344c5d6ad86f7 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000931032_238346240.pth b/checkpoint_p0/milestones/checkpoint_000931032_238346240.pth new file mode 100644 index 0000000000000000000000000000000000000000..a9c01cbac60b32b61dd8b269b170b260cf8e263c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000931032_238346240.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ef5f570d7a30527f8e69d39f412e1e76caee86f45e872e035bacd9385ccb018 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000942136_241188864.pth b/checkpoint_p0/milestones/checkpoint_000942136_241188864.pth new file mode 100644 index 0000000000000000000000000000000000000000..990c6710b71a42e9071e5e63271a1950a65e7d3c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000942136_241188864.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf51c0d7b9bc352fcd9901881bdb5f288e50cda8d6518ef62f6d6a52ee71c27d +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000953336_244056064.pth b/checkpoint_p0/milestones/checkpoint_000953336_244056064.pth new file mode 100644 index 0000000000000000000000000000000000000000..e04efefd5cb9f3050c5dd4688b53f4a73999646b --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000953336_244056064.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ea270c6351266f1d849208eb4a43ffcd01f7d6d3c914c8ae9c39a47aa0bdc1e +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000964568_246931456.pth b/checkpoint_p0/milestones/checkpoint_000964568_246931456.pth new file mode 100644 index 0000000000000000000000000000000000000000..31cd5f290138ed7fbd214792b06879e3710f9053 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000964568_246931456.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b9593d6c270ea1e8dc56c199bf9bb8dc33a5225f146e6b476ce8e7b66f90926 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000975768_249798656.pth b/checkpoint_p0/milestones/checkpoint_000975768_249798656.pth new file mode 100644 index 0000000000000000000000000000000000000000..d3e21c702bd969336815f82ce1f35aa2b5807341 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000975768_249798656.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:649568c54c79320194c3eb4cb86246ef72e8ada47d878cb84920c38388f9d896 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000986776_252616704.pth b/checkpoint_p0/milestones/checkpoint_000986776_252616704.pth new file mode 100644 index 0000000000000000000000000000000000000000..2d832a5693346f92ff0b2c6d18259ff4e4a438b4 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000986776_252616704.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a40a18ee846c07823e3c031600ba1fdbb61719bb39541244754984d176966436 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000997976_255483904.pth b/checkpoint_p0/milestones/checkpoint_000997976_255483904.pth new file mode 100644 index 0000000000000000000000000000000000000000..a5d76888724435e03b941425b3eca6c2642aa53c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000997976_255483904.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd7d32911488be9e696eddb9120c94c29bd754c38f57c311aec66ae47013856c +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001009048_258318336.pth b/checkpoint_p0/milestones/checkpoint_001009048_258318336.pth new file mode 100644 index 0000000000000000000000000000000000000000..b2bd897226662c63766a529b5e492c2607c2be98 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001009048_258318336.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec499884fbb24bb744fe3499d2763e77010d02bca0d81a5beaeb9b166233f07f +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001020376_261218304.pth b/checkpoint_p0/milestones/checkpoint_001020376_261218304.pth new file mode 100644 index 0000000000000000000000000000000000000000..0c24a891e9c0bf995e5d03536a441b6b3de211b4 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001020376_261218304.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0209999c02e1344d114639cfa7f17b0c41472bd7acbee4825bbe6f8cb7af7027 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001031576_264085504.pth b/checkpoint_p0/milestones/checkpoint_001031576_264085504.pth new file mode 100644 index 0000000000000000000000000000000000000000..7b9951abdcd23f3cdc446df8e3f82199eddc8012 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001031576_264085504.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6f1bca39ae58193ffa5cb1c9373fa99ecd7a01d190c07982216eed2b69cef4c +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001042872_266977280.pth b/checkpoint_p0/milestones/checkpoint_001042872_266977280.pth new file mode 100644 index 0000000000000000000000000000000000000000..9953dab81309fafbb731350d59e001c368a95f4a --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001042872_266977280.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2878c1ded0050c71bce816006f8c18d1dbc2d1accea43e94d77930825f421294 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001054232_269885440.pth b/checkpoint_p0/milestones/checkpoint_001054232_269885440.pth new file mode 100644 index 0000000000000000000000000000000000000000..bd4a682ed36cbd6739ad5d2121efdfc0b31b717d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001054232_269885440.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d35cb0fdb679af8af44c61eba0cd013c0a13218e1b3e75f2d8c8bcf95703445 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001065592_272793600.pth b/checkpoint_p0/milestones/checkpoint_001065592_272793600.pth new file mode 100644 index 0000000000000000000000000000000000000000..e05a1996a41ec24ef6a2e73fdb4ed02d1e05a0f6 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001065592_272793600.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d95e26d73015a58d7886f7ad2c56664902bfd6eee94427f544a1584691f3b33b +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001076888_275685376.pth b/checkpoint_p0/milestones/checkpoint_001076888_275685376.pth new file mode 100644 index 0000000000000000000000000000000000000000..8a8a3dbb17d197b6499f12de8e03d9d6b1b6526c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001076888_275685376.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed683bff5ff6d6a965eee96a292eeced11f2c990f3851f213706caf944a33025 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001088312_278609920.pth b/checkpoint_p0/milestones/checkpoint_001088312_278609920.pth new file mode 100644 index 0000000000000000000000000000000000000000..0c869136ff7855934dfffe37c6b48e83afde4130 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001088312_278609920.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe1f50dcf924ba9e02296b0fcdc8c09a55d4c323f7d7cd645f8dcf545ff81862 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001099672_281518080.pth b/checkpoint_p0/milestones/checkpoint_001099672_281518080.pth new file mode 100644 index 0000000000000000000000000000000000000000..fde9a182fb3f9e8bdb3fef7704c8b971dd1d582c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001099672_281518080.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:988bcb19d9c800c44b0a77b006bc2ac06d7f08bbb4544c3f0f9b8dc344df7ebf +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001111032_284426240.pth b/checkpoint_p0/milestones/checkpoint_001111032_284426240.pth new file mode 100644 index 0000000000000000000000000000000000000000..cf2968fcea157319b8a4c8930a066f438f16197e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001111032_284426240.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7208ea76c7c432485dfc8937c3161684f7972d33a33000edda6894e69d023f67 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001122360_287326208.pth b/checkpoint_p0/milestones/checkpoint_001122360_287326208.pth new file mode 100644 index 0000000000000000000000000000000000000000..d6e62177a7e3427fe0c0a82950b319df094e76c4 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001122360_287326208.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1182cad9418b1bd4b0e014d5fba7cbc1270fe7855d7f5a20e407287739a3961 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001133752_290242560.pth b/checkpoint_p0/milestones/checkpoint_001133752_290242560.pth new file mode 100644 index 0000000000000000000000000000000000000000..df4db621c0a60ca6d644e9f09674d14be239c724 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001133752_290242560.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e83bbad226115f32318b4f54fdd73ec248fcfb94ec0ddb27883413b3c4a2194f +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001144856_293085184.pth b/checkpoint_p0/milestones/checkpoint_001144856_293085184.pth new file mode 100644 index 0000000000000000000000000000000000000000..11fff726a2a1a5dfb2e12a1d7f03264bb01d3884 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001144856_293085184.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7b429217d32396d98e5eb0bfd394b98ea27c4ebb71a0202f7ee2b4751c899a9 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001156088_295960576.pth b/checkpoint_p0/milestones/checkpoint_001156088_295960576.pth new file mode 100644 index 0000000000000000000000000000000000000000..7a6ca2c3b6713c4fb81c5da86ea5b6dbbf38e5b7 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001156088_295960576.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5812ac01f32bbfbe9558a497f59e26254b316f402327f7c75ba6f9a94a1df64 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001167512_298885120.pth b/checkpoint_p0/milestones/checkpoint_001167512_298885120.pth new file mode 100644 index 0000000000000000000000000000000000000000..c6dcc9921011ef6ee4241e9fa82a66c8d308d50c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001167512_298885120.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaa2d146f33cbce63d5f236047b081649a0b68e4fba3bc619937c0529c360f05 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001178840_301785088.pth b/checkpoint_p0/milestones/checkpoint_001178840_301785088.pth new file mode 100644 index 0000000000000000000000000000000000000000..b1c63dc98aa2e050371627febd8150bcdc2bedf2 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001178840_301785088.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5295c48b0ddf08235c08eb2a4608c1851e4f57e1d4e2fabe3c0b786c8a58b74c +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001190264_304709632.pth b/checkpoint_p0/milestones/checkpoint_001190264_304709632.pth new file mode 100644 index 0000000000000000000000000000000000000000..229058393986bc3142c2a522fe2bbb8f208824ad --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001190264_304709632.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6ceb2107a55f3919c606bc7ead9b03452151a343c6672114b505e63a63766b0 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001201592_307609600.pth b/checkpoint_p0/milestones/checkpoint_001201592_307609600.pth new file mode 100644 index 0000000000000000000000000000000000000000..bb3b6f426bc5e1bed8798c2cb5fa5cb82a606000 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001201592_307609600.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dd9108c82f518c4d78be7ce060834d534cbae81812e9b3a15897b87985f4b43 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001213016_310534144.pth b/checkpoint_p0/milestones/checkpoint_001213016_310534144.pth new file mode 100644 index 0000000000000000000000000000000000000000..edb62f012a92455f1f7b6ddb5d81783b7bc7aa02 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001213016_310534144.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e361161786fc156ca3d55042b8db68c2858699463adfe3f7ff1b0dbcb0981d7d +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001224376_313442304.pth b/checkpoint_p0/milestones/checkpoint_001224376_313442304.pth new file mode 100644 index 0000000000000000000000000000000000000000..71e13058b17d435fdbb4cddcaf81d75c3572dc0c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001224376_313442304.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3336bc9d3861a1ab4b4a407bc7db6c57956ca598e9bfe017d421a4d22e627ea1 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001235736_316350464.pth b/checkpoint_p0/milestones/checkpoint_001235736_316350464.pth new file mode 100644 index 0000000000000000000000000000000000000000..99d8714bd18a5b1620a77419397295ee877fdbe5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001235736_316350464.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aebbddcf09a45e510b79ad27c15d3c5a556cff6106916bf4550e36e416c5c553 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001247128_319266816.pth b/checkpoint_p0/milestones/checkpoint_001247128_319266816.pth new file mode 100644 index 0000000000000000000000000000000000000000..ce324e913f4f191799c3fbf1f5d90d4a7d58189c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001247128_319266816.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01e80bb12cdcc4a36cab96162b9529980d5ee0e611b397f4f24ebca72989b172 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001258552_322191360.pth b/checkpoint_p0/milestones/checkpoint_001258552_322191360.pth new file mode 100644 index 0000000000000000000000000000000000000000..bd12fed65efe4644feca600ef26dd073066a2a3c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001258552_322191360.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a08b14bac91d8bc530b67615f7c4a6f3f93b2f3cc8a2624b0c57b111fada37b +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001269944_325107712.pth b/checkpoint_p0/milestones/checkpoint_001269944_325107712.pth new file mode 100644 index 0000000000000000000000000000000000000000..785417f8b8b1d96a5aa865c1c961d3664f08e8ec --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001269944_325107712.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f384fa61b0d7e00cb144550a11eb7fee4c8f8a51c3e2303800ef1b311f7f7843 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001281304_328015872.pth b/checkpoint_p0/milestones/checkpoint_001281304_328015872.pth new file mode 100644 index 0000000000000000000000000000000000000000..a5487dd3e2ccf512ec532c333631b6b4e3384aa9 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001281304_328015872.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5fdcdba6e1cbc0d5e777c3bb638ce06be1b486f7fde9991e457634e33a4fcd7 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001292568_330899456.pth b/checkpoint_p0/milestones/checkpoint_001292568_330899456.pth new file mode 100644 index 0000000000000000000000000000000000000000..98b0982ccbafe86467b20172a8b13ae005fcf3fd --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001292568_330899456.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5431ab2c0a01a57a994ec5d21281604a91c528c2afe0e64c30e2de3981d3b486 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001303896_333799424.pth b/checkpoint_p0/milestones/checkpoint_001303896_333799424.pth new file mode 100644 index 0000000000000000000000000000000000000000..0dd28dd9209ed99b4a25009907bcfb1a5dab9c1a --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001303896_333799424.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb088042355c476a9af378f973599301956968ce6615fcbf049dd47995b6a6aa +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001315224_336699392.pth b/checkpoint_p0/milestones/checkpoint_001315224_336699392.pth new file mode 100644 index 0000000000000000000000000000000000000000..ec0895447068cfeec12c96dab8b16e0b544a4bd0 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001315224_336699392.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c5dd2a56376807b449096bad02c7be8b075abf35b9606c5b27661d2bf3e5ddc +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001326584_339607552.pth b/checkpoint_p0/milestones/checkpoint_001326584_339607552.pth new file mode 100644 index 0000000000000000000000000000000000000000..7e37f036b3e2e963940af020291f6ddb5ef62571 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001326584_339607552.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83244eff0df23613e493de17e60a8d36693edae8b7d61518f685606b6cb7aaf1 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001337976_342523904.pth b/checkpoint_p0/milestones/checkpoint_001337976_342523904.pth new file mode 100644 index 0000000000000000000000000000000000000000..3b9c65d1f6c7c259120f4c207f61ab3df562a176 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001337976_342523904.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b92eb2409c1bef16783ff843d1e85cb48673be2b65fe9198a804dd2f79abe1a3 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001349272_345415680.pth b/checkpoint_p0/milestones/checkpoint_001349272_345415680.pth new file mode 100644 index 0000000000000000000000000000000000000000..1d1e29bccf79258ba8429494ac651b60e416edbf --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001349272_345415680.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f51108e6c0464317d6f66786e22bbe121bd2d1a4a0eb528e9a5221c4d6e30960 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001360600_348315648.pth b/checkpoint_p0/milestones/checkpoint_001360600_348315648.pth new file mode 100644 index 0000000000000000000000000000000000000000..f36d9c8c0a0f54fbe87e668541d67720a2836f59 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001360600_348315648.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb34986a907d96418aba3cec34cc7e7d18c2f3cc8d95086533837279c2511527 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001371896_351207424.pth b/checkpoint_p0/milestones/checkpoint_001371896_351207424.pth new file mode 100644 index 0000000000000000000000000000000000000000..767f49a5e02e895b92e91b23d3fc7d08397a78a5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001371896_351207424.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b48cdc158b1092dec85cd305c8a7d6bbe54bd7950f24c62888c09ff50f6b43c7 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001383256_354115584.pth b/checkpoint_p0/milestones/checkpoint_001383256_354115584.pth new file mode 100644 index 0000000000000000000000000000000000000000..f11c55f784e43587190806b7b39802ab79e4afc8 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001383256_354115584.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2303d0f31d6759d51eb98c00c2c408d85a8d13b4a0fe385375e799d5d0842ad9 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001394648_357031936.pth b/checkpoint_p0/milestones/checkpoint_001394648_357031936.pth new file mode 100644 index 0000000000000000000000000000000000000000..2fa20bb25e766ec1d1fda75a879052b59a043107 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001394648_357031936.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82aa7920f5fbf311a341fad3db19b5594f11061e3c54182782b490c309e48ce8 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001405944_359923712.pth b/checkpoint_p0/milestones/checkpoint_001405944_359923712.pth new file mode 100644 index 0000000000000000000000000000000000000000..f9b430db1d8acbc8db80cd868ce0af7a0fe43ffb --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001405944_359923712.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f0b9d92a4d4d54b74b11b5b9025e18342d3f093b8de9faccf41617c02a60498 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001417272_362823680.pth b/checkpoint_p0/milestones/checkpoint_001417272_362823680.pth new file mode 100644 index 0000000000000000000000000000000000000000..1e99cc39327a0b4b48ec9b919e31b3ea7f4def48 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001417272_362823680.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27832774acf994032ae6939ff38b3e1f4b1da50e824249226f32d8f48998f3ae +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001428632_365731840.pth b/checkpoint_p0/milestones/checkpoint_001428632_365731840.pth new file mode 100644 index 0000000000000000000000000000000000000000..3ff426cbda921a8df4ed2f25b7e56edef49638bd --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001428632_365731840.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b46d9b451298085cbb34e33483997e1273b9d2f176250507f8637f2f7520ef25 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001439928_368623616.pth b/checkpoint_p0/milestones/checkpoint_001439928_368623616.pth new file mode 100644 index 0000000000000000000000000000000000000000..cc9cbdc5f1a128035fbf6828b6ea5cbaea757dfc --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001439928_368623616.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb328541aa30ffc623cf6180801766bd034925a68b7248aae4ea2363ec19e2cf +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001451192_371507200.pth b/checkpoint_p0/milestones/checkpoint_001451192_371507200.pth new file mode 100644 index 0000000000000000000000000000000000000000..fdfeba516719a90a9a7b3680a8ffe55a2e7c3ee5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001451192_371507200.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e498f8eb0a7f3b60d1a9bc37a9a830fe2296b22be8c2ede50c9690dcc540d1c6 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001462488_374398976.pth b/checkpoint_p0/milestones/checkpoint_001462488_374398976.pth new file mode 100644 index 0000000000000000000000000000000000000000..c70ab9135ba8894619fe8ded04b75ae7675e67e9 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001462488_374398976.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6dd0e7d521de354e532c4ee3ad8b296e4b22da4c7f7d31f279551b464a27b4c +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001473816_377298944.pth b/checkpoint_p0/milestones/checkpoint_001473816_377298944.pth new file mode 100644 index 0000000000000000000000000000000000000000..92259ac80752d1044d6432780f2f7ffdfb6a8b3b --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001473816_377298944.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaff031d805ff39851552437dc9aed9b5925bc366ee0cc6f7e615d3dd49b8cb9 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001485176_380207104.pth b/checkpoint_p0/milestones/checkpoint_001485176_380207104.pth new file mode 100644 index 0000000000000000000000000000000000000000..94fc43b6430ae62fbdefdbae27f9afd17e0b3120 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001485176_380207104.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac967a9871c2a48b6c9aa25b9709a33a4f7b1e1e6b0eb59e728672def045691f +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001496504_383107072.pth b/checkpoint_p0/milestones/checkpoint_001496504_383107072.pth new file mode 100644 index 0000000000000000000000000000000000000000..7609504270a88564a6694b2a17831bd89ea5ec36 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001496504_383107072.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7c4b013de02f4040f15cb4075ece3577d9117128dfbc94fe0860722f651860a +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001507768_385990656.pth b/checkpoint_p0/milestones/checkpoint_001507768_385990656.pth new file mode 100644 index 0000000000000000000000000000000000000000..6aa25f2af0e810017b689677e62a16629136dc91 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001507768_385990656.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b2ce6b4ce344827f30afa06b1b15ffbed89fba44a5e1dbe00135ba324ce391e +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001519096_388890624.pth b/checkpoint_p0/milestones/checkpoint_001519096_388890624.pth new file mode 100644 index 0000000000000000000000000000000000000000..e9af12a250d56f7f4aadbaf4742d97d8a614cd7c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001519096_388890624.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a13c3b70eb747a840b8bce5a3e7116a98ce376c4695aa23531f0ec41e8fd3190 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001530360_391774208.pth b/checkpoint_p0/milestones/checkpoint_001530360_391774208.pth new file mode 100644 index 0000000000000000000000000000000000000000..b9f6a2c087b62d1895fc5efa79852b1d683a444f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001530360_391774208.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a413a9ca12407ad2c6c4dd9e763062c846cfc8daef75c6301c0a6cde202a8d23 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001541752_394690560.pth b/checkpoint_p0/milestones/checkpoint_001541752_394690560.pth new file mode 100644 index 0000000000000000000000000000000000000000..d2af1b7ca81b4cbd3f2e9b15f5b2a11e6ea736d4 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001541752_394690560.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:919c8dda9bc9c21c0ba98423155de02d498a401d744217db429e506384feaf6c +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001553080_397590528.pth b/checkpoint_p0/milestones/checkpoint_001553080_397590528.pth new file mode 100644 index 0000000000000000000000000000000000000000..3e5be2c92782f8d646e2713161ef7abf3513a2bb --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001553080_397590528.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60d662b2f3e92467e1b8287542f0e454a315e4bc5fa44d3a25b079663a2c94f7 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001564440_400498688.pth b/checkpoint_p0/milestones/checkpoint_001564440_400498688.pth new file mode 100644 index 0000000000000000000000000000000000000000..1f04f209d634563a440f273894a24e1f37d1612c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001564440_400498688.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:401997d1197d09d4a2d97522d4561b70205d34da9aee243bd1d8e9f47f09da8a +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001575672_403374080.pth b/checkpoint_p0/milestones/checkpoint_001575672_403374080.pth new file mode 100644 index 0000000000000000000000000000000000000000..d5a9ed7bfc25d992131b00433b2758175d85d466 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001575672_403374080.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d48ddee069ac957bf761c725e788cef7fd827f6e275de235e7d9533d2e37c9e +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001587032_406282240.pth b/checkpoint_p0/milestones/checkpoint_001587032_406282240.pth new file mode 100644 index 0000000000000000000000000000000000000000..c29736194137e5478119f1bb05348a9d1da901a2 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001587032_406282240.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c54952ee08891c8f9f0329ab6257bc1a194f404a285e22dd48f2f65fc1d77937 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001598360_409182208.pth b/checkpoint_p0/milestones/checkpoint_001598360_409182208.pth new file mode 100644 index 0000000000000000000000000000000000000000..57d678d6572e4c07a2cc66f03242c88ac561120f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001598360_409182208.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:395d62b1bc5249aa39a3d7e6780c5437a90ff3338684334fa6186c1f570aae5b +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001609688_412082176.pth b/checkpoint_p0/milestones/checkpoint_001609688_412082176.pth new file mode 100644 index 0000000000000000000000000000000000000000..fa550a2914272758000eb886e48ec4bdf9ea5f76 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001609688_412082176.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90604107da9d7086dff197a292b83fd557db3d5cfc1fce1405c3c6e342ee4760 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001621016_414982144.pth b/checkpoint_p0/milestones/checkpoint_001621016_414982144.pth new file mode 100644 index 0000000000000000000000000000000000000000..ef5139ae4e8eeab230d4cf407550637874a935ad --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001621016_414982144.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f3a3d22cfe5c3ca48741642f7f751082c113e5dfe2b264f4fbe6fc5c6c86bcd +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001632344_417882112.pth b/checkpoint_p0/milestones/checkpoint_001632344_417882112.pth new file mode 100644 index 0000000000000000000000000000000000000000..919f5da11e882a409c720baa2f17dd1261310883 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001632344_417882112.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14e27b205838f598b820161407a3fa629c9b81ce3d940c3a3c44ebeb99863204 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001643640_420773888.pth b/checkpoint_p0/milestones/checkpoint_001643640_420773888.pth new file mode 100644 index 0000000000000000000000000000000000000000..df7cc4cc6c7eeca312f0093150077343da56f8de --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001643640_420773888.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d813b1fde3eef9e7f2f055c24ff2cd63e1445eb11e4e8a9b2f3eaba7ba5dea2b +size 20797067 diff --git a/checkpoint_p1/best_000461600_118169600_reward_103.180.pth b/checkpoint_p1/best_000461600_118169600_reward_103.180.pth new file mode 100644 index 0000000000000000000000000000000000000000..18044b51ba24f2b1edf7ee449bbdf0e1966c9ca5 --- /dev/null +++ b/checkpoint_p1/best_000461600_118169600_reward_103.180.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7936c8cf6f238f9e6066679905894e26d70f6e60982009542405885d0c3c82d6 +size 20795763 diff --git a/checkpoint_p1/checkpoint_001627872_416735232.pth b/checkpoint_p1/checkpoint_001627872_416735232.pth new file mode 100644 index 0000000000000000000000000000000000000000..bb326abad2a5f91f1252ee260f6e0417bd9a4f5d --- /dev/null +++ b/checkpoint_p1/checkpoint_001627872_416735232.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c58a01a87ca23701609fae5d102aa5072fe2263a5b28e7eb493665e5d3a94274 +size 20796099 diff --git a/checkpoint_p1/checkpoint_001628192_416817152.pth b/checkpoint_p1/checkpoint_001628192_416817152.pth new file mode 100644 index 0000000000000000000000000000000000000000..e3adaa6ed1d1166be0f1bcb587e004d7c8df0796 --- /dev/null +++ b/checkpoint_p1/checkpoint_001628192_416817152.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62359c8beb6b0de29606a33445cb7e3220ab5c86434b75ef80ddefeb0a108f66 +size 20796099 diff --git a/checkpoint_p1/milestones/checkpoint_000010720_2744320.pth b/checkpoint_p1/milestones/checkpoint_000010720_2744320.pth new file mode 100644 index 0000000000000000000000000000000000000000..a4d1a24f518c6ea0395a733e0a8f9916abea95e8 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000010720_2744320.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb164d62edad14aa7105a682bea30c4721091d14b60f1228acad91a3e5351656 +size 20796955 diff --git a/checkpoint_p1/milestones/checkpoint_000021792_5578752.pth b/checkpoint_p1/milestones/checkpoint_000021792_5578752.pth new file mode 100644 index 0000000000000000000000000000000000000000..f083dde1a88c70c2600f3415c22be3dfc63259e8 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000021792_5578752.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:189407d9471870223aaae684ee44e43fd948086bf21b9be7ee14deb0c4851d93 +size 20796955 diff --git a/checkpoint_p1/milestones/checkpoint_000032832_8404992.pth b/checkpoint_p1/milestones/checkpoint_000032832_8404992.pth new file mode 100644 index 0000000000000000000000000000000000000000..b6dceb041820e014cf9229dffb6f36df8e770d6e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000032832_8404992.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:581c60159d0f22cd8f980b05b79876805b1726877349fc3b9b6d226f8c63ad1d +size 20796955 diff --git a/checkpoint_p1/milestones/checkpoint_000043872_11231232.pth b/checkpoint_p1/milestones/checkpoint_000043872_11231232.pth new file mode 100644 index 0000000000000000000000000000000000000000..074a2b4fc02fb4357763571634e1c32e6ca7c7e1 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000043872_11231232.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40eb79c18131df973aee005a25168503638355b894846766dba76d6675f3436c +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000054912_14057472.pth b/checkpoint_p1/milestones/checkpoint_000054912_14057472.pth new file mode 100644 index 0000000000000000000000000000000000000000..342083a10de1634194585b570dfbab9ed9f597e3 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000054912_14057472.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53cadc35526b7984447a210ebca5f06b623c0cee3d5aa094a44f2c7468969bc5 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000065728_16826368.pth b/checkpoint_p1/milestones/checkpoint_000065728_16826368.pth new file mode 100644 index 0000000000000000000000000000000000000000..b8f1adadbe9869f2558a8f6caae0aad8e2513846 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000065728_16826368.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c6ab4836779a1b8bd6cc80e028cfc126e3d12aadd5bff535c119ff8f430e81a +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000076512_19587072.pth b/checkpoint_p1/milestones/checkpoint_000076512_19587072.pth new file mode 100644 index 0000000000000000000000000000000000000000..a4fcb2e1f08ba87d0a6e810b4a68cf8817ab5091 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000076512_19587072.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17b56ed6380b134637f3ad177bea0876b688054d4c874cc882a3d7548159325b +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000087392_22372352.pth b/checkpoint_p1/milestones/checkpoint_000087392_22372352.pth new file mode 100644 index 0000000000000000000000000000000000000000..acd73025842c436f89d5636760f1eb50ed5b0ad5 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000087392_22372352.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6cacf52eca90fdae06aa36c111f01ee2c637239d658b687500ad35613e34038 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000098240_25149440.pth b/checkpoint_p1/milestones/checkpoint_000098240_25149440.pth new file mode 100644 index 0000000000000000000000000000000000000000..c9ef0a7352553d118098bd28403cac947b0b1b6b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000098240_25149440.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00511801f9d5254ad2b47e720b57f5030ad796a463eaee79cb8e07457beb8ea7 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000109248_27967488.pth b/checkpoint_p1/milestones/checkpoint_000109248_27967488.pth new file mode 100644 index 0000000000000000000000000000000000000000..75ba270a8c626b66f435502bd80ba9c37c6151a4 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000109248_27967488.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6622957bde8cbd1658f284d4ad7700b6e8d8df2fa0c653f0333d563df097388c +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000120064_30736384.pth b/checkpoint_p1/milestones/checkpoint_000120064_30736384.pth new file mode 100644 index 0000000000000000000000000000000000000000..b462e744b4b067ff5b81d162fc6bc24f2dc4406a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000120064_30736384.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56f234df1cd833af466e1e24ecbe6e9026325f72d04b46b02df45a612281e0c4 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000130976_33529856.pth b/checkpoint_p1/milestones/checkpoint_000130976_33529856.pth new file mode 100644 index 0000000000000000000000000000000000000000..200dc37d1c01ab23ddf9f068def9eebf5de92143 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000130976_33529856.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:914fe29a17ecbbdb7082152eb8fec77bc65882b48fe6e34b4d0ec55dac443904 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000141952_36339712.pth b/checkpoint_p1/milestones/checkpoint_000141952_36339712.pth new file mode 100644 index 0000000000000000000000000000000000000000..c9a47a5a9397808f8f894e8df8536f92f1bbb05f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000141952_36339712.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f7327c9690d5dbe9112103122bccac11d17bac1c38687fba605ee6cd6ce8248 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000152640_39075840.pth b/checkpoint_p1/milestones/checkpoint_000152640_39075840.pth new file mode 100644 index 0000000000000000000000000000000000000000..78fee3ead50fbc33d333a5fba970703f21ee9185 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000152640_39075840.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d202782151cc8e87bcd8f64d296f363b794b4450f6b4ab362c4be017159f583 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000163776_41926656.pth b/checkpoint_p1/milestones/checkpoint_000163776_41926656.pth new file mode 100644 index 0000000000000000000000000000000000000000..538e64e90cc6d1f661487d32bca8b83c83c22284 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000163776_41926656.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e18fc9279ae0f5aba29378a5c9137f8ca7190cb8eb3be5fb1644bd2239ff85fe +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000174848_44761088.pth b/checkpoint_p1/milestones/checkpoint_000174848_44761088.pth new file mode 100644 index 0000000000000000000000000000000000000000..ec7249e14bbb3893ad985aef01c660935156876b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000174848_44761088.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e6d6ff7cb2ab4a67af506d4a7c58f4cd44942518fedbd02743d43781789eaff +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000185952_47603712.pth b/checkpoint_p1/milestones/checkpoint_000185952_47603712.pth new file mode 100644 index 0000000000000000000000000000000000000000..de049e1f9382f495ee31cff47ae95f1b9954091c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000185952_47603712.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9978bbfcc8c191fcdbfcc11620ef7935a1cff4c76c0e2154e6652df6152ed3b6 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000197088_50454528.pth b/checkpoint_p1/milestones/checkpoint_000197088_50454528.pth new file mode 100644 index 0000000000000000000000000000000000000000..251a49b525ecaa8e4fe517eceffc3915968fb3ff --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000197088_50454528.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21f9baed7341ee37730c262720a4d796376ea139270d73b718f84ae9c14d3a64 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000208224_53305344.pth b/checkpoint_p1/milestones/checkpoint_000208224_53305344.pth new file mode 100644 index 0000000000000000000000000000000000000000..8ce3b3f95e8e3b829c36a144d7c0634a5a85fb5d --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000208224_53305344.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c96102be0d2baaacfc0f2c63d0a86a231ad980d4c955759fd7954610cf2f36e +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000219424_56172544.pth b/checkpoint_p1/milestones/checkpoint_000219424_56172544.pth new file mode 100644 index 0000000000000000000000000000000000000000..025c3c6477e41eceff4be12309ee5d7ccdb2548f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000219424_56172544.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f41c890ccbf6cb46914cc4b487b89f2b4f4c0e0a00e3c36c3636dd6c0680bb5e +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000230592_59031552.pth b/checkpoint_p1/milestones/checkpoint_000230592_59031552.pth new file mode 100644 index 0000000000000000000000000000000000000000..5987630d083e1143a73643206dfe3f25bf4a5ad1 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000230592_59031552.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70a811776878ec4e89a64b4b78459f0b8460680386e97314b3dafceb9805cda9 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000241728_61882368.pth b/checkpoint_p1/milestones/checkpoint_000241728_61882368.pth new file mode 100644 index 0000000000000000000000000000000000000000..a36ca2a8bad4f91eaba9248dd3e90988a413debd --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000241728_61882368.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3de96618aa1eacf275ff7819c0019eecef0799b97241efff1d186da4436275b6 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000252832_64724992.pth b/checkpoint_p1/milestones/checkpoint_000252832_64724992.pth new file mode 100644 index 0000000000000000000000000000000000000000..01b445143a943c1df0392680a07f3d40cf592051 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000252832_64724992.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84e6e3b4478f840499e04e7962804a84a8fb51097a94035bff3207f86e276fde +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000263904_67559424.pth b/checkpoint_p1/milestones/checkpoint_000263904_67559424.pth new file mode 100644 index 0000000000000000000000000000000000000000..fdfe3fe125e16b3c5b5dc362db6db2c196dba924 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000263904_67559424.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0eab9a2f39e4ef1b9c4b041c66bb6c018571b20863f0cb18f942987a7981784 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000274976_70393856.pth b/checkpoint_p1/milestones/checkpoint_000274976_70393856.pth new file mode 100644 index 0000000000000000000000000000000000000000..a6d68945de4017f0ee17ec9bbce5ef049ad9607e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000274976_70393856.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05bd2bd7d2659df9c686948b46e8fc84ec0f96a6f4c502465a1afc0d51034bd8 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000286144_73252864.pth b/checkpoint_p1/milestones/checkpoint_000286144_73252864.pth new file mode 100644 index 0000000000000000000000000000000000000000..0d6da90e1fbe7fa425cbabe933a0d53a5ecd4926 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000286144_73252864.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:709703cafa4584d6b993dd227ed8fd64c432a4e4a3303ffdf3f571c3e9228652 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000297280_76103680.pth b/checkpoint_p1/milestones/checkpoint_000297280_76103680.pth new file mode 100644 index 0000000000000000000000000000000000000000..03eed8935481f7bc2ce65ec62ee86e69a84ff6cb --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000297280_76103680.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f270979d196f8fca2f366644230d4d6329a88658d0bb95c31855723e10dbe7e +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000308448_78962688.pth b/checkpoint_p1/milestones/checkpoint_000308448_78962688.pth new file mode 100644 index 0000000000000000000000000000000000000000..bbadc172e13f77e8be89db94cc719590ea9cfe3e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000308448_78962688.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8388ac88aaeb654fe6d7eff0d3cfa5b7343a95259eb29bb39c0f17707a12581 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000319616_81821696.pth b/checkpoint_p1/milestones/checkpoint_000319616_81821696.pth new file mode 100644 index 0000000000000000000000000000000000000000..7f128569579960dabfa6c5ec5793804a12d750af --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000319616_81821696.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9c7a57f3aa18e78d7b1853105cebbd0e8bf33dad121dd775aeffcc4d35d70e1 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000330368_84574208.pth b/checkpoint_p1/milestones/checkpoint_000330368_84574208.pth new file mode 100644 index 0000000000000000000000000000000000000000..cdce85cbdeff6b79ab8dd1aeb970986ea99d3ab5 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000330368_84574208.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e1fa52921c1ebf7532730e9617be60ab08095dcf55404e8a3f50385cfa4ef49 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000341408_87400448.pth b/checkpoint_p1/milestones/checkpoint_000341408_87400448.pth new file mode 100644 index 0000000000000000000000000000000000000000..b625e771a5f0891d2c3a9be564315f24df4d2a80 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000341408_87400448.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c54bc7bd777b90d6888df1a90318448ffc01d3aa9bf317a5e9caadd341bc55b +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000352608_90267648.pth b/checkpoint_p1/milestones/checkpoint_000352608_90267648.pth new file mode 100644 index 0000000000000000000000000000000000000000..cda205c8bcf08cd0a24e8842681011642bbc3dae --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000352608_90267648.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84d46e09841a46913a10989c0fd916eba8767c28458d8d327e96a1a8148029d6 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000363712_93110272.pth b/checkpoint_p1/milestones/checkpoint_000363712_93110272.pth new file mode 100644 index 0000000000000000000000000000000000000000..e15fda6bf3fe77a181e7fd6db7ef95ec4ae2304f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000363712_93110272.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf51b826c94fed44e12904fb035a7c69f7d9d2ddf4fb39338215c5e60d254b8f +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000374880_95969280.pth b/checkpoint_p1/milestones/checkpoint_000374880_95969280.pth new file mode 100644 index 0000000000000000000000000000000000000000..733b760499c363658eb85a01dd67645535da91cb --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000374880_95969280.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78261c1e6113abaae1148a70298f57cd21a8948a64eabdcf55d7a9af68b115c5 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000385984_98811904.pth b/checkpoint_p1/milestones/checkpoint_000385984_98811904.pth new file mode 100644 index 0000000000000000000000000000000000000000..d4a8aac6f0f7b54a590f9eca432353b112bf5877 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000385984_98811904.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cb947d052005c7d175b1bc047075cc6d4d7136128c46597906b7fb2382dd089 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000397152_101670912.pth b/checkpoint_p1/milestones/checkpoint_000397152_101670912.pth new file mode 100644 index 0000000000000000000000000000000000000000..2511aa2bef15f03de0f4afc379729f02a76ef1e8 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000397152_101670912.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24ed6f3355d9e58deaca8742c32f09d8055cd45a31c3d652b0e25967ac4a7fa5 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000408224_104505344.pth b/checkpoint_p1/milestones/checkpoint_000408224_104505344.pth new file mode 100644 index 0000000000000000000000000000000000000000..0047e778cfda7abda4a201e2a159c37bb4577cfb --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000408224_104505344.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e70696b6836f9c2b77c988b50020e338277ff682e2ed9abb6cf058ef6cd03dc +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000419424_107372544.pth b/checkpoint_p1/milestones/checkpoint_000419424_107372544.pth new file mode 100644 index 0000000000000000000000000000000000000000..30665706b2421260f1f77fc4605848d44dad1bd5 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000419424_107372544.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7858a248b57e47283b9e42e79a1f4390a60a1bb9e5b6b5ac3a564faeb3d918ec +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000430528_110215168.pth b/checkpoint_p1/milestones/checkpoint_000430528_110215168.pth new file mode 100644 index 0000000000000000000000000000000000000000..58b472e99518c8cb178438d481d0616b6b53ed8a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000430528_110215168.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21c71fef60f110c3034f87f12af5522cd49d08a0718a5f920369369d91f04007 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000441664_113065984.pth b/checkpoint_p1/milestones/checkpoint_000441664_113065984.pth new file mode 100644 index 0000000000000000000000000000000000000000..bbfd465b3fb38624e238f01d7a8e3cbccd2d5658 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000441664_113065984.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fda3177f2a53fdcb450068846f482551492d19f8781ad2f09e8ec9401ee37ec +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000452832_115924992.pth b/checkpoint_p1/milestones/checkpoint_000452832_115924992.pth new file mode 100644 index 0000000000000000000000000000000000000000..e07a04c3b39ef83eab37fd222b311c0d730553bd --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000452832_115924992.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee02b9afbb114b5d8f830c868fd5c900cbb9af220018ec8b54be08343dc85370 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000464032_118792192.pth b/checkpoint_p1/milestones/checkpoint_000464032_118792192.pth new file mode 100644 index 0000000000000000000000000000000000000000..d05351f0783e44d4539d0e81eb2a2362633579ae --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000464032_118792192.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6862b82640c0c546a7c7726d1bbfa3626be08f907e5c39bc784e450f8aeba7f4 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000475200_121651200.pth b/checkpoint_p1/milestones/checkpoint_000475200_121651200.pth new file mode 100644 index 0000000000000000000000000000000000000000..0b7f65d16e263a656d01fae32cc0d69c3ae335da --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000475200_121651200.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11844e9e37b3d9c997b89976e94944f848763d18f683eae9a3d075d6003f9ca6 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000486400_124518400.pth b/checkpoint_p1/milestones/checkpoint_000486400_124518400.pth new file mode 100644 index 0000000000000000000000000000000000000000..5cbfeb1a7125c86d14b6f3cb5dda68c6bd83b94c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000486400_124518400.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1c33a3618f66de07778fc1eb27c2186d1fbd677a9facd897f93f4b579f60bc7 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000497728_127418368.pth b/checkpoint_p1/milestones/checkpoint_000497728_127418368.pth new file mode 100644 index 0000000000000000000000000000000000000000..7e260df4b316f4e68e93bb89372038782514dba2 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000497728_127418368.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a788dca793c3b82783c15f251025893955c0b7b24b12547fb1cfebf4076e9db9 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000508992_130301952.pth b/checkpoint_p1/milestones/checkpoint_000508992_130301952.pth new file mode 100644 index 0000000000000000000000000000000000000000..6758b0bc27f778e0bdd0fa00c3c497679e12cc4d --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000508992_130301952.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd36f59f7c17143cbf6ee8e8c919ef523de3f9ac3879e2d513d3a578563f210e +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000520192_133169152.pth b/checkpoint_p1/milestones/checkpoint_000520192_133169152.pth new file mode 100644 index 0000000000000000000000000000000000000000..ea2cbb75c721c653b5c228b5d410bbf0e63caffe --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000520192_133169152.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08d92fe6b109ae327db5f7514a44084ae990b07607d76fd38511ea64149510ed +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000531424_136044544.pth b/checkpoint_p1/milestones/checkpoint_000531424_136044544.pth new file mode 100644 index 0000000000000000000000000000000000000000..b3e189a299bbcc576f4342cc3bfe3580267dd859 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000531424_136044544.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:321c9a8218e06fc868c46493040ca7c9b373c4ff1e225860da36ec9de611a27b +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000542656_138919936.pth b/checkpoint_p1/milestones/checkpoint_000542656_138919936.pth new file mode 100644 index 0000000000000000000000000000000000000000..9e7507f64f1ed270dd12d39109b84c647894fb87 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000542656_138919936.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fc7ac913a0ae0b4c37850f81e58c5cabbc45a41e1eaddef067a79183f6e72c7 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000553888_141795328.pth b/checkpoint_p1/milestones/checkpoint_000553888_141795328.pth new file mode 100644 index 0000000000000000000000000000000000000000..1f61482e8e79e556be2e7b1fe4caf4b64c3a4e29 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000553888_141795328.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdc7307ff9fbbb9d731881254e58b96b0a17c064919ca49346f7895bc39ba5d6 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000565088_144662528.pth b/checkpoint_p1/milestones/checkpoint_000565088_144662528.pth new file mode 100644 index 0000000000000000000000000000000000000000..e5fcc816dad4dd9a440122d45de0f8bccc8a4b5a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000565088_144662528.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c4de6271d3eb559a2be0d3694c927189aac3c48d0344bfcca7af999d2a9a68c +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000576256_147521536.pth b/checkpoint_p1/milestones/checkpoint_000576256_147521536.pth new file mode 100644 index 0000000000000000000000000000000000000000..49db9eec61ce27f0aaa46277a0e842549fc292b6 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000576256_147521536.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:630ccbc995229835a30a10c6e3fb50819934148404c73097d06bd8e215961a99 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000587424_150380544.pth b/checkpoint_p1/milestones/checkpoint_000587424_150380544.pth new file mode 100644 index 0000000000000000000000000000000000000000..ef2ff29ee2ed45a984f91b36d1423c7494519c48 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000587424_150380544.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35a1a47591da19199de2f9110fe66b61ebf1d86762296697589e26e01c0087de +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000598624_153247744.pth b/checkpoint_p1/milestones/checkpoint_000598624_153247744.pth new file mode 100644 index 0000000000000000000000000000000000000000..3537f63d0de6d3d38e167a275daa1ae03abcba71 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000598624_153247744.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b540f5e1802d439f619f9f8c7e3915e137345d413acf62a75bba35375071ee10 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000609792_156106752.pth b/checkpoint_p1/milestones/checkpoint_000609792_156106752.pth new file mode 100644 index 0000000000000000000000000000000000000000..91814b7d35c894f02c5e08969893138c3387979a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000609792_156106752.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95edd0ee633fe0be1f3c5438c50041aea17c9dc2bd56f2db3ca201aa09e3d7c3 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000621024_158982144.pth b/checkpoint_p1/milestones/checkpoint_000621024_158982144.pth new file mode 100644 index 0000000000000000000000000000000000000000..d303e191c0b64588b4a39935f83bd317cf534d1b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000621024_158982144.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4db2b61d2651a41a3a75812d4930a9af91be2b89973013a4f9bdc2d5e4907ed3 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000632192_161841152.pth b/checkpoint_p1/milestones/checkpoint_000632192_161841152.pth new file mode 100644 index 0000000000000000000000000000000000000000..162961eabf0ee93b5477e6491868afc28181212e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000632192_161841152.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:623d0aafe4a8733c4bc900f4e5da94b574aaa25d1b0ffb5778496257abe5dad2 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000643392_164708352.pth b/checkpoint_p1/milestones/checkpoint_000643392_164708352.pth new file mode 100644 index 0000000000000000000000000000000000000000..267a43586593240b0e6f238be4061b3e7b57ff44 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000643392_164708352.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7253e6714f0efc6d47863936df07dd2b9fee489bf81f5485bc901f15948a5e42 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000654496_167550976.pth b/checkpoint_p1/milestones/checkpoint_000654496_167550976.pth new file mode 100644 index 0000000000000000000000000000000000000000..9327ce715834e9a10a4dc7b8e09217b0301271aa --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000654496_167550976.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9302f760c22556abff6c40bbd330ecfdb22a0756f4c4ed6fe99cd0abb4d7deb +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000665632_170401792.pth b/checkpoint_p1/milestones/checkpoint_000665632_170401792.pth new file mode 100644 index 0000000000000000000000000000000000000000..605934f8a434693b346cf7c1a0363ca4c1d64916 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000665632_170401792.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6893ca43ea506b2572b085cb6965bf6079d9849addf9155bf9b8a332c4e7e7c +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000676768_173252608.pth b/checkpoint_p1/milestones/checkpoint_000676768_173252608.pth new file mode 100644 index 0000000000000000000000000000000000000000..c434ac142d54c4a4394f6ea867ead82eb0597834 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000676768_173252608.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6357d68d7f025e860f11bc66cd4ad1ec27d3062faa8775040e82ebdf6aa82fb6 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000687904_176103424.pth b/checkpoint_p1/milestones/checkpoint_000687904_176103424.pth new file mode 100644 index 0000000000000000000000000000000000000000..3866f84f3eb7ffbc08aa6fe903ac6798c682cd51 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000687904_176103424.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f22dde8c95b32baaef9a47d8e420f64704c920cb00bcaa2c513a3835238dbe9 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000699072_178962432.pth b/checkpoint_p1/milestones/checkpoint_000699072_178962432.pth new file mode 100644 index 0000000000000000000000000000000000000000..e876023d6d175b03e316d196c52ec06b8728476c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000699072_178962432.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb61e1f5970145579901a42313a4e5f5b1d757bc87937e9e6c92f4a6f87bd6c9 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000709952_181747712.pth b/checkpoint_p1/milestones/checkpoint_000709952_181747712.pth new file mode 100644 index 0000000000000000000000000000000000000000..50513b79f358d0915298fa1ab918cc73ba7b8495 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000709952_181747712.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0985a1b83860bcae33aa4c98979d617daa37d9079337214c825dfcc2a4260d92 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000720288_184393728.pth b/checkpoint_p1/milestones/checkpoint_000720288_184393728.pth new file mode 100644 index 0000000000000000000000000000000000000000..da52c260afc405f2b73b1eb7a968104569ccccf5 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000720288_184393728.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb7e853cb5aba8d331c218945d46b7d87027603f599fb4279a050cadfe877ac2 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000730624_187039744.pth b/checkpoint_p1/milestones/checkpoint_000730624_187039744.pth new file mode 100644 index 0000000000000000000000000000000000000000..ed7164ee175761aee01762e8cd4fa89e7a20be7c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000730624_187039744.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1bc340b945e89e7b7636749a558d0fefc976b1ab1d7f2f47fb6b2c29fed0719 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000741120_189726720.pth b/checkpoint_p1/milestones/checkpoint_000741120_189726720.pth new file mode 100644 index 0000000000000000000000000000000000000000..1c59c134c8dd4630fdae06877837f77647528f2a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000741120_189726720.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fce029b0404c40b25800b5fae97724df0d31ca461319bc89321aeeada630c95f +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000752128_192544768.pth b/checkpoint_p1/milestones/checkpoint_000752128_192544768.pth new file mode 100644 index 0000000000000000000000000000000000000000..abfde895954544c3790085e64f97c4324448b207 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000752128_192544768.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d67bca7f37405522fda32a508637704dc66b0291860c570935352dac3539fed +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000763296_195403776.pth b/checkpoint_p1/milestones/checkpoint_000763296_195403776.pth new file mode 100644 index 0000000000000000000000000000000000000000..be2ceba25cf754a7d264605649d78c41ad81581f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000763296_195403776.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c2622106715e79d5078afc31ba1f87031827562ce0dd14500736040aa8e7687 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000774464_198262784.pth b/checkpoint_p1/milestones/checkpoint_000774464_198262784.pth new file mode 100644 index 0000000000000000000000000000000000000000..89f9aa74d4efade283bbf12e1616b0b66141373e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000774464_198262784.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef15a7afdf91bc75f25f7859a135d18f1e8f57f686ca95904fcbda47a1f93a55 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000785632_201121792.pth b/checkpoint_p1/milestones/checkpoint_000785632_201121792.pth new file mode 100644 index 0000000000000000000000000000000000000000..5b7d676ed6addcd9513db0b25d56bff547739ed9 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000785632_201121792.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f016c14eeec179d72332fc04dbd8597dae539625746585d82ca575567443bff +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000796768_203972608.pth b/checkpoint_p1/milestones/checkpoint_000796768_203972608.pth new file mode 100644 index 0000000000000000000000000000000000000000..48960b6ed6fe3da9cd2d5960982ab90cc88e9520 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000796768_203972608.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64c9ffc235bff09e3bc06ef16bb50e0436ac2d06b31ac379c4ddc0478adffc23 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000807936_206831616.pth b/checkpoint_p1/milestones/checkpoint_000807936_206831616.pth new file mode 100644 index 0000000000000000000000000000000000000000..6bfb9e5c41e16892136332e221510cd895ca7b71 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000807936_206831616.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66d30c8ef4e98bdaef1e6033de77dcbfde9ba16ef1bdc6fed0207aad865a4f2d +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000819104_209690624.pth b/checkpoint_p1/milestones/checkpoint_000819104_209690624.pth new file mode 100644 index 0000000000000000000000000000000000000000..6ecfc919a2eb5a5187283eef549e96515c77cb65 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000819104_209690624.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41c4b06f2375c171f72440bbfa1edff7929136d6672901e1f24d2500700030ad +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000830176_212525056.pth b/checkpoint_p1/milestones/checkpoint_000830176_212525056.pth new file mode 100644 index 0000000000000000000000000000000000000000..5893c176b69d13ae4e3d987d2c31cedae968cf58 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000830176_212525056.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33d1d11c34a751f160bef9d9a552edbe14ae0790085ad7928fe21b414c9d4c25 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000841344_215384064.pth b/checkpoint_p1/milestones/checkpoint_000841344_215384064.pth new file mode 100644 index 0000000000000000000000000000000000000000..fe2efe6cbdab9097a5dcd68e46d810dea88b54c7 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000841344_215384064.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03f00f83cbf81e004c0cf9cc66106d13d3e94318217785946099a6b6973cc53a +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000852416_218218496.pth b/checkpoint_p1/milestones/checkpoint_000852416_218218496.pth new file mode 100644 index 0000000000000000000000000000000000000000..540d3cf661c3339b435f2078a2672f6516fb9d2f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000852416_218218496.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb51d7285517227854b3072cd28ceeb4c3a8fefa64dbd4c59b64ea230d43a2e4 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000863488_221052928.pth b/checkpoint_p1/milestones/checkpoint_000863488_221052928.pth new file mode 100644 index 0000000000000000000000000000000000000000..c280b16445bbd5b3377f3977ebe074031f04cf12 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000863488_221052928.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0db4b0ad72f944c91e189b060eaaa3f93647368987d4892a31ab03b55a9a05cd +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000874656_223911936.pth b/checkpoint_p1/milestones/checkpoint_000874656_223911936.pth new file mode 100644 index 0000000000000000000000000000000000000000..cdb27feea3df5489fadc727b4ab48eff44218e45 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000874656_223911936.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4debfeb3d6a4ff6bc4d64815c92bd4895699bee5841dfdb22b80e70e52ce63d1 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000885792_226762752.pth b/checkpoint_p1/milestones/checkpoint_000885792_226762752.pth new file mode 100644 index 0000000000000000000000000000000000000000..b44f13a4a5289ae667a0988c8e4a5d4705e15feb --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000885792_226762752.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07207ced2dac5c91877cac2fbb7c1519712b30e9d13d5bbc9079f6ba3026bf3d +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000896896_229605376.pth b/checkpoint_p1/milestones/checkpoint_000896896_229605376.pth new file mode 100644 index 0000000000000000000000000000000000000000..5e15f0f348661fb8ab8288bd192d4ea773e7e0f5 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000896896_229605376.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98821020a3d1637ba0a9745f384b3c805731326cd25946f3ff2e1abe2c311bca +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000907968_232439808.pth b/checkpoint_p1/milestones/checkpoint_000907968_232439808.pth new file mode 100644 index 0000000000000000000000000000000000000000..9105dd5ccbfd7df88c5ae46ee314ebdacf94edf7 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000907968_232439808.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ab1915da7c001bcb2b9c3f27157be96fda2d2158382581ddb639c3d5d62a2cf +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000918976_235257856.pth b/checkpoint_p1/milestones/checkpoint_000918976_235257856.pth new file mode 100644 index 0000000000000000000000000000000000000000..d9228f342458ec5d4f9d9a517d3ebbb05fa2bad4 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000918976_235257856.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a2fac51d45010f48ea843ac4db031b4dfc6ae2b2661fae06a8e77c3db805e18 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000929888_238051328.pth b/checkpoint_p1/milestones/checkpoint_000929888_238051328.pth new file mode 100644 index 0000000000000000000000000000000000000000..36508ce0f55d7f85381a429ae8174723024abb04 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000929888_238051328.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd8e0749d4d97f3f213e61d672b22df5d32fc4a4c02fe580629ecd3db88f75a7 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000940864_240861184.pth b/checkpoint_p1/milestones/checkpoint_000940864_240861184.pth new file mode 100644 index 0000000000000000000000000000000000000000..c175c8a4fb04e828692554a1816f94bd5f80a7a1 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000940864_240861184.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c4be807d3261ca0be024455565ea5b461fa42f669ca25fa267b875b1e701557 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000951776_243654656.pth b/checkpoint_p1/milestones/checkpoint_000951776_243654656.pth new file mode 100644 index 0000000000000000000000000000000000000000..5d15ca4f25746c694fb1118d126e6e469aedfa85 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000951776_243654656.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29016f62cff6ebf143190b71bed52a3a748dc62012624b3614842752452d1786 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000962784_246472704.pth b/checkpoint_p1/milestones/checkpoint_000962784_246472704.pth new file mode 100644 index 0000000000000000000000000000000000000000..163a8fc0c04a65e87742b9a5d0b2abebbfbc2513 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000962784_246472704.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:825dc63079e6e9b88a5011fcab194298a3147e47958ed4409bdd3d09aaeb3088 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000973536_249225216.pth b/checkpoint_p1/milestones/checkpoint_000973536_249225216.pth new file mode 100644 index 0000000000000000000000000000000000000000..d6b6199f361ba6237668dc3f4ce3b04af8c8db47 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000973536_249225216.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d45c89f284b58eb522ea53b3f3ce0171780820cfdf6508e528df659049ad3fee +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000984544_252043264.pth b/checkpoint_p1/milestones/checkpoint_000984544_252043264.pth new file mode 100644 index 0000000000000000000000000000000000000000..12c2db4456a894ce2bb596877dc554b961cb8edc --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000984544_252043264.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d23e8258cfa849a1840437f3cd5e99f8f705f6785fe7ef5b9ee2d2272a92b52 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000995456_254836736.pth b/checkpoint_p1/milestones/checkpoint_000995456_254836736.pth new file mode 100644 index 0000000000000000000000000000000000000000..0c84939e81c47e694f10ea5c55bfe31f233e6095 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000995456_254836736.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:271a3b718954c290674714c7e3610fccbc38355df9b5a60a3edfc3176535264b +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001006464_257654784.pth b/checkpoint_p1/milestones/checkpoint_001006464_257654784.pth new file mode 100644 index 0000000000000000000000000000000000000000..2cf279e23b5ffee1d7b9d8f19af8f72569d9a554 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001006464_257654784.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be0759fc1a2c3768cc66bedf1cd85dd2b7e401d755c1719bfc75fbd012b75e7f +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001017600_260505600.pth b/checkpoint_p1/milestones/checkpoint_001017600_260505600.pth new file mode 100644 index 0000000000000000000000000000000000000000..7fa123e5d61141fc39a515c58a624d4bf1aa211d --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001017600_260505600.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fe69dc6e2f87023d6905ec493c2bf7a6eefb0db7d066cb847656b6f4ae39f24 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001028736_263356416.pth b/checkpoint_p1/milestones/checkpoint_001028736_263356416.pth new file mode 100644 index 0000000000000000000000000000000000000000..44a5daa1f2925ebc1013df71bc16942a9bc61551 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001028736_263356416.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd5646efea8f2b6220ac92972cf51759481a5d64207c74432c37582d3e5b7045 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001039808_266190848.pth b/checkpoint_p1/milestones/checkpoint_001039808_266190848.pth new file mode 100644 index 0000000000000000000000000000000000000000..1b5841b9fcee44453542d2fc35e9cf92896e1bd5 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001039808_266190848.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccb8db2745268a8c060b4b03e2f2e1c09bbc2bb599c09770ca4b75c2c4a9b509 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001050912_269033472.pth b/checkpoint_p1/milestones/checkpoint_001050912_269033472.pth new file mode 100644 index 0000000000000000000000000000000000000000..b370c2b174f909930da184103c657438abcae43f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001050912_269033472.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99cdeaccdaf92b5cadf2e0548bae67e08977a3e22e3c2658773a745def723b90 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001062016_271876096.pth b/checkpoint_p1/milestones/checkpoint_001062016_271876096.pth new file mode 100644 index 0000000000000000000000000000000000000000..afb6931b4afe7945fe92233ea893a8c0639a931a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001062016_271876096.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07db6766ed4f0a66f659589ea723e0fbda7b7d7c88a476f80791d0934edddc37 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001073088_274710528.pth b/checkpoint_p1/milestones/checkpoint_001073088_274710528.pth new file mode 100644 index 0000000000000000000000000000000000000000..9464a2c5b774f0da963b44bccdb873346a1e449b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001073088_274710528.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf2a0c4ecddfab20d81f88a08e80d2f111b91ac1b8b02517b66f919e981783be +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001084256_277569536.pth b/checkpoint_p1/milestones/checkpoint_001084256_277569536.pth new file mode 100644 index 0000000000000000000000000000000000000000..d9fc9afc4f1ca873903d58259c28b3c6381e2168 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001084256_277569536.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6750c9b0d2aefb2e8bc6c5fce3403c6a45d2c4eda9df1a0635b0a8fe13a02b06 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001095392_280420352.pth b/checkpoint_p1/milestones/checkpoint_001095392_280420352.pth new file mode 100644 index 0000000000000000000000000000000000000000..29e318b009639819fffef596e024237a84435f8d --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001095392_280420352.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20c7f2577468310e8768b2ba69ce436dda5c6d29ef75a56480c4f99c275986a2 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001106528_283271168.pth b/checkpoint_p1/milestones/checkpoint_001106528_283271168.pth new file mode 100644 index 0000000000000000000000000000000000000000..d6b9aac3c917769fdfa0197d8bc7bc30ce3cd745 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001106528_283271168.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1931ba4b3e91c6015ced97516133ed72787b7942f972ca046636c198fb39b4ec +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001117728_286138368.pth b/checkpoint_p1/milestones/checkpoint_001117728_286138368.pth new file mode 100644 index 0000000000000000000000000000000000000000..e50fe9ad09916ac577b98d3634090421adaecbdd --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001117728_286138368.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05ed53d71730d1071efe8bbb7be6efbab10d5521393a16ce035a1d704ed5d7a2 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001128704_288948224.pth b/checkpoint_p1/milestones/checkpoint_001128704_288948224.pth new file mode 100644 index 0000000000000000000000000000000000000000..ac39f866665b2dc8c011e1a38fbd51c25b76fd41 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001128704_288948224.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d206706a6f4c99b1a366876e438b4561f2f7d44b3f4159637ca3058775020b2f +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001139776_291782656.pth b/checkpoint_p1/milestones/checkpoint_001139776_291782656.pth new file mode 100644 index 0000000000000000000000000000000000000000..cc587ed01e4de8a7065885b263259e8dd39714a8 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001139776_291782656.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9009e232fc2fba31199cd032aab3052c528d4b662ab66642dcd9e79197d3cb85 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001150944_294641664.pth b/checkpoint_p1/milestones/checkpoint_001150944_294641664.pth new file mode 100644 index 0000000000000000000000000000000000000000..1c09c5b81911f8e0ac052f87396371a1411f63de --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001150944_294641664.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a621b7c2ccaea4f0c51114423e9a33a0dca4118d3a78fe154b9d009132c692f +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001162112_297500672.pth b/checkpoint_p1/milestones/checkpoint_001162112_297500672.pth new file mode 100644 index 0000000000000000000000000000000000000000..1cce415a7e31f3832a7e174462345ad3bf53c911 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001162112_297500672.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0df5252d5b887fd3ff45ce8c50ed54800f8d332b9af686b8ededf4f6628e079 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001173344_300376064.pth b/checkpoint_p1/milestones/checkpoint_001173344_300376064.pth new file mode 100644 index 0000000000000000000000000000000000000000..f4501fbb28b3dd09c577bbe2f07bef92ce1c1cb5 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001173344_300376064.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5823ffdec75df6b4f992fea29282f29f20c6c38f844811983c8d287c670bac5 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001184576_303251456.pth b/checkpoint_p1/milestones/checkpoint_001184576_303251456.pth new file mode 100644 index 0000000000000000000000000000000000000000..dded01d321a6666e6745b938f0f6e0117ec3313b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001184576_303251456.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdecfb7fe16f7ecefa4847223123e3ba9f85fc0491ab74624966e301e2c10b58 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001195808_306126848.pth b/checkpoint_p1/milestones/checkpoint_001195808_306126848.pth new file mode 100644 index 0000000000000000000000000000000000000000..1cc826e9441966458e349cbbe8b44d45026d8382 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001195808_306126848.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8dd031eadd3fae2926cae271eb077e94e38b20606ea8126dd1d8c724981b1f5 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001207008_308994048.pth b/checkpoint_p1/milestones/checkpoint_001207008_308994048.pth new file mode 100644 index 0000000000000000000000000000000000000000..0d0db7169eec31a5ace0481ca5b166cc9f00e8e0 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001207008_308994048.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23914d7775ad092045d845ca82933f6fa7489bcf7b47a5bbcdabaad98d9ed3e7 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001218144_311844864.pth b/checkpoint_p1/milestones/checkpoint_001218144_311844864.pth new file mode 100644 index 0000000000000000000000000000000000000000..387e4f0f0b83f57511ba7546fd94dbf25f641d6b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001218144_311844864.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc073f8f11ad1b99e0f123ae5e32dc19c8f6baa874152987965f39e78a0ec5cd +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001229312_314703872.pth b/checkpoint_p1/milestones/checkpoint_001229312_314703872.pth new file mode 100644 index 0000000000000000000000000000000000000000..142fdf4dc071da74bf3b59b639d00155f6b75e4b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001229312_314703872.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc31c5290936c50eae74f3f5a04979b3260921014ee7bb677bb534ca474cdbed +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001240480_317562880.pth b/checkpoint_p1/milestones/checkpoint_001240480_317562880.pth new file mode 100644 index 0000000000000000000000000000000000000000..ea05fb5863131545b3dc10cff308582bc2b908fa --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001240480_317562880.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4d60a543b819ff05b5d06fe1a63b924928e58d0cf37872375d27993f85b73c1 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001251616_320413696.pth b/checkpoint_p1/milestones/checkpoint_001251616_320413696.pth new file mode 100644 index 0000000000000000000000000000000000000000..5db510e23096b8a06facf7a0a988dfe5e8ff5fec --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001251616_320413696.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09f0903d33f62947ff9790e72b1b1880282459ee03d6eb88d4c1d2918043fb94 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001262784_323272704.pth b/checkpoint_p1/milestones/checkpoint_001262784_323272704.pth new file mode 100644 index 0000000000000000000000000000000000000000..421d0fe7c3b6f860761af0af67491d7587be69ef --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001262784_323272704.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4b0f36b525021ae6b2e77f5a6e4c6c3909ade2b172bea108430a48985aa50bd +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001273952_326131712.pth b/checkpoint_p1/milestones/checkpoint_001273952_326131712.pth new file mode 100644 index 0000000000000000000000000000000000000000..308b155b50a9ebf7bb65c7437fd8286f8236d2e6 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001273952_326131712.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c24549ca8b82ead5bb017c0c96663d471ef8ba333b9ea06d6a98a4eaad3854f +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001285120_328990720.pth b/checkpoint_p1/milestones/checkpoint_001285120_328990720.pth new file mode 100644 index 0000000000000000000000000000000000000000..93fe53d2d1e020a3522064c74de5be5bb8c1c3fb --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001285120_328990720.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34b344936214b831173754dc0300d8c2ea7527339d82a9514510b663a801482e +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001296320_331857920.pth b/checkpoint_p1/milestones/checkpoint_001296320_331857920.pth new file mode 100644 index 0000000000000000000000000000000000000000..19816cca5dc8723dc5e6d9667d6ec1e7835a4374 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001296320_331857920.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcd1876bd984655c46572f083ff48a9a7d6474db6f9a0ee762578488e3108d44 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001307456_334708736.pth b/checkpoint_p1/milestones/checkpoint_001307456_334708736.pth new file mode 100644 index 0000000000000000000000000000000000000000..ee8d32f1ea4d754b3993367ba0e6a6a3170dc173 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001307456_334708736.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:672162099bd2889b6916693a1e5ebd5801e144916d2d8aebef41bba898401c28 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001318592_337559552.pth b/checkpoint_p1/milestones/checkpoint_001318592_337559552.pth new file mode 100644 index 0000000000000000000000000000000000000000..b9caddf68d5bb37e898452bde22152512607937a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001318592_337559552.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f4fa25495577db45d1a018819999724a8718aae97f605126b95485b63caae08 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001329824_340434944.pth b/checkpoint_p1/milestones/checkpoint_001329824_340434944.pth new file mode 100644 index 0000000000000000000000000000000000000000..a430aaae54e270a6af97f816dd1a234864560fa5 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001329824_340434944.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:866e23ecacc47f6f8ab9f379975c53edc07e13f5079ee94c8bdd5b0fc729af28 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001341088_343318528.pth b/checkpoint_p1/milestones/checkpoint_001341088_343318528.pth new file mode 100644 index 0000000000000000000000000000000000000000..53fe4f40c26edde5086f6a57efd7e6f214d464e1 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001341088_343318528.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0366a20ceac1b03866631071528d530816638433c86e60ced38273d1693812d0 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001352224_346169344.pth b/checkpoint_p1/milestones/checkpoint_001352224_346169344.pth new file mode 100644 index 0000000000000000000000000000000000000000..9a7585b6ee7a884683f9647dda2394f1649a0211 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001352224_346169344.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82013ac8266ff1e2b0ecede7876001679d8f74955a3f9a369e62df8a2632631d +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001363424_349036544.pth b/checkpoint_p1/milestones/checkpoint_001363424_349036544.pth new file mode 100644 index 0000000000000000000000000000000000000000..3b84a5208471e3ff4f245262561be88fdebcac5e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001363424_349036544.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e844b097c56fcfdc7ac9b358624dbfcfcdd76c1fa7a12a9d27fd124aa4111187 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001374592_351895552.pth b/checkpoint_p1/milestones/checkpoint_001374592_351895552.pth new file mode 100644 index 0000000000000000000000000000000000000000..46fe9f2ebb0034bd4b840a2650474ebcdb0f6c5c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001374592_351895552.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afc305cd83b38ba7e7f66f6312f168e9421dffcddb3bcbf770b7be2eeb8cc14f +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001385760_354754560.pth b/checkpoint_p1/milestones/checkpoint_001385760_354754560.pth new file mode 100644 index 0000000000000000000000000000000000000000..4d142007e1ae3011ea3d4bcb859d68683ff00990 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001385760_354754560.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa35539d7c3bd3589d7314d23a642256b859135314447163eb4be0f5ac84ca44 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001396928_357613568.pth b/checkpoint_p1/milestones/checkpoint_001396928_357613568.pth new file mode 100644 index 0000000000000000000000000000000000000000..0a87eb5ce5b7526a8ce3fc6e409772f894a65d27 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001396928_357613568.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db6cf23b50920c96d0fad776b4b34938221c81f1e166946be74ed7f2427a0522 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001408192_360497152.pth b/checkpoint_p1/milestones/checkpoint_001408192_360497152.pth new file mode 100644 index 0000000000000000000000000000000000000000..f96797bd27dbd186ed2da423a2562802146a1dad --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001408192_360497152.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c50572055ffeb2f5788f7fa03623cdb669c12335d76661164c8b52f71e427b9 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001419328_363347968.pth b/checkpoint_p1/milestones/checkpoint_001419328_363347968.pth new file mode 100644 index 0000000000000000000000000000000000000000..722dc192f2771dea91b51b121e5204e5d5dd75e7 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001419328_363347968.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f87b1a697718e47868b50507e23c2a0688a963962ad8f2bba766495688114076 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001430464_366198784.pth b/checkpoint_p1/milestones/checkpoint_001430464_366198784.pth new file mode 100644 index 0000000000000000000000000000000000000000..d90b7d920e45c40e24930877a0a61267553c88c0 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001430464_366198784.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:deb0d576a55877d7de98f761fa27bf8531bf3492a5a92088bfec4e6771c66a32 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001441568_369041408.pth b/checkpoint_p1/milestones/checkpoint_001441568_369041408.pth new file mode 100644 index 0000000000000000000000000000000000000000..5c876208bdb72953dec581a9b712d3952d609024 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001441568_369041408.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f93eb62de5865f59b98074111671fe0429b0035493f5172589274e4a57de2a08 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001452768_371908608.pth b/checkpoint_p1/milestones/checkpoint_001452768_371908608.pth new file mode 100644 index 0000000000000000000000000000000000000000..883298d0a0ba0749824b79463591b2a8cd8abef0 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001452768_371908608.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2782fb5b64b55e1bddb30080385b6dbe673bc381d2c3c46635fec05c9b7c0d0d +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001463872_374751232.pth b/checkpoint_p1/milestones/checkpoint_001463872_374751232.pth new file mode 100644 index 0000000000000000000000000000000000000000..5424cba55d7417a3483c53acae016fe2450984c8 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001463872_374751232.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc6c90445d198cc15513c313951afb62b663f2ad5d01c612f784640c2de4b394 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001475040_377610240.pth b/checkpoint_p1/milestones/checkpoint_001475040_377610240.pth new file mode 100644 index 0000000000000000000000000000000000000000..2570114af21863b2d8865c2890cb564ec3f3687f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001475040_377610240.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9a9471758a7ec94c4db10d481782aec9846869f0dffa95422eecf8c5a68e8e +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001486176_380461056.pth b/checkpoint_p1/milestones/checkpoint_001486176_380461056.pth new file mode 100644 index 0000000000000000000000000000000000000000..3e49ca4d215a95b33afd262e97e914058c1f30f0 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001486176_380461056.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e55350442e711d3c08a0f12f28841d9713ada52c8bbc844542514ce7b206f95e +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001497344_383320064.pth b/checkpoint_p1/milestones/checkpoint_001497344_383320064.pth new file mode 100644 index 0000000000000000000000000000000000000000..cda11e374acc84e82d799891011d459ef4604f68 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001497344_383320064.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ed709c4562c8794e6e07b0dace1b59fb6baab89126173d8755690be8834b055 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001508512_386179072.pth b/checkpoint_p1/milestones/checkpoint_001508512_386179072.pth new file mode 100644 index 0000000000000000000000000000000000000000..8fd88677495329844a3b57521eed37b38d59e3ca --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001508512_386179072.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbb11420904d4f10be60eeb580ee6e540d5a8ad09235a42ac87d158ee7a0bea5 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001519712_389046272.pth b/checkpoint_p1/milestones/checkpoint_001519712_389046272.pth new file mode 100644 index 0000000000000000000000000000000000000000..c93613f7ddd52116daf3fd26001f54e5c82b1e60 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001519712_389046272.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f3924a2af5ea96245b3c67fa6d91f525afbc9b1311443e665c346111edcb654 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001530880_391905280.pth b/checkpoint_p1/milestones/checkpoint_001530880_391905280.pth new file mode 100644 index 0000000000000000000000000000000000000000..6f924fe54823c88586a1c0b183cd128e5ed0e238 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001530880_391905280.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff47de041b1b958a60f9ae50f3a0037e41bb21970f78579d372b8dc4373b055c +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001541984_394747904.pth b/checkpoint_p1/milestones/checkpoint_001541984_394747904.pth new file mode 100644 index 0000000000000000000000000000000000000000..23cc0428a7b8fa92089e33cdd8dbf92bbba10c8a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001541984_394747904.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc7112a9740c6ba55713dd163f4d070b299fb9e1aed867acebeff2681c99d836 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001553120_397598720.pth b/checkpoint_p1/milestones/checkpoint_001553120_397598720.pth new file mode 100644 index 0000000000000000000000000000000000000000..e7c42f5ee8562246e30aeb91e762239ef1e237bb --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001553120_397598720.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcacf7ec567445218484844892c3f822628aefb1c5367a014151686acd32178b +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001564224_400441344.pth b/checkpoint_p1/milestones/checkpoint_001564224_400441344.pth new file mode 100644 index 0000000000000000000000000000000000000000..88b9a5e6c653d34826c0138f226bb6842df3c711 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001564224_400441344.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0efa3bc06eee726d1efff97da2c6dabd387f06cb4c07cd6be949daf63c70008c +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001575424_403308544.pth b/checkpoint_p1/milestones/checkpoint_001575424_403308544.pth new file mode 100644 index 0000000000000000000000000000000000000000..ad1a656205f02931148cb3596a09db1816e997e2 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001575424_403308544.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:892172c796f6789d365b5719af12fe6692081c6d9dcc4f8cdcfb0f86184b6dff +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001586624_406175744.pth b/checkpoint_p1/milestones/checkpoint_001586624_406175744.pth new file mode 100644 index 0000000000000000000000000000000000000000..f6418427de54f5b08ab93a84126a673bfc330d52 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001586624_406175744.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23871906593e1022556793fdeefd53b4cd5a496ecc38991d6c486b118c8e5dbb +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001597728_409018368.pth b/checkpoint_p1/milestones/checkpoint_001597728_409018368.pth new file mode 100644 index 0000000000000000000000000000000000000000..3a5a2d994afd3aee984f323ee63b85a763073a1c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001597728_409018368.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:444df964e3ffb1393ed3a07c0af1ce441e733d35d9960fcc7982683ecd99f5eb +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001608832_411860992.pth b/checkpoint_p1/milestones/checkpoint_001608832_411860992.pth new file mode 100644 index 0000000000000000000000000000000000000000..053e54fe8f86f5c9c74887859dbe4cb997d1140f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001608832_411860992.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19a8c0d235b066f506e0ed8d742e93e146c383dc1a3e84a31cf53fb404b2b949 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001620096_414744576.pth b/checkpoint_p1/milestones/checkpoint_001620096_414744576.pth new file mode 100644 index 0000000000000000000000000000000000000000..d2842cffae24374c4aba180792b8b814df334ba4 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001620096_414744576.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95ea0343a08bd4af43c6f312c2afbf4b7e9391ef7fb742c05db7cd6e7aebeb40 +size 20797067 diff --git a/config.json b/config.json index bb883848858010177293c432e24ea5e4530abd91..8eca21de7dfcae0cccbe75997742b8abfa06144c 100644 --- a/config.json +++ b/config.json @@ -4,7 +4,7 @@ "env": "atari_hero", "experiment": "atari_hero_APPO", "train_dir": "./train_atari", - "restart_behavior": "restart", + "restart_behavior": "resume", "device": "gpu", "seed": 1234, "num_policies": 2, @@ -12,11 +12,11 @@ "serial_mode": false, "batched_sampling": true, "num_batches_to_accumulate": 2, - "worker_num_splits": 1, + "worker_num_splits": 2, "policy_workers_per_policy": 1, "max_policy_lag": 1000, "num_workers": 16, - "num_envs_per_worker": 2, + "num_envs_per_worker": 8, "batch_size": 1024, "num_batches_per_epoch": 8, "num_epochs": 4, @@ -64,10 +64,10 @@ "experiment_summaries_interval": 3, "flush_summaries_interval": 30, "stats_avg": 100, - "summaries_use_frameskip": true, + "summaries_use_frameskip": false, "heartbeat_interval": 10, "heartbeat_reporting_interval": 60, - "train_for_env_steps": 100000000, + "train_for_env_steps": 500000000, "train_for_seconds": 10000000000, "save_every_sec": 120, "keep_checkpoints": 2, @@ -124,28 +124,30 @@ "pbt_target_objective": "true_objective", "pbt_perturb_min": 1.1, "pbt_perturb_max": 1.5, - "command_line": "--algo=APPO --env=atari_hero --experiment=atari_hero_APPO --num_policies=2 --restart_behavior=restart --train_dir=./train_atari --train_for_env_steps=100000000 --seed=1234 --num_workers=16 --num_envs_per_worker=2 --num_batches_per_epoch=8 --async_rl=true --batched_sampling=true --batch_size=1024 --max_grad_norm=0 --learning_rate=0.0003033891184 --heartbeat_interval=10 --heartbeat_reporting_interval=60 --save_milestones_sec=1200 --num_epochs=4 --exploration_loss_coeff=0.0004677351413 --with_wandb=true --wandb_user=matt-stammers --wandb_project=atari_APPO --wandb_group=atari_hero --wandb_job_type=SF --wandb_tags=atari", + "command_line": "--algo=APPO --env=atari_hero --experiment=atari_hero_APPO --num_policies=2 --restart_behavior=resume --train_dir=./train_atari --train_for_env_steps=500000000 --seed=1234 --num_workers=16 --num_envs_per_worker=8 --num_batches_per_epoch=8 --worker_num_splits=2 --async_rl=true --batched_sampling=true --batch_size=1024 --max_grad_norm=0 --learning_rate=0.0003033891184 --heartbeat_interval=10 --heartbeat_reporting_interval=60 --save_milestones_sec=1200 --num_epochs=4 --exploration_loss_coeff=0.0004677351413 --summaries_use_frameskip=False --with_wandb=true --wandb_user=matt-stammers --wandb_project=atari_APPO --wandb_group=atari_hero --wandb_job_type=SF --wandb_tags=atari", "cli_args": { "algo": "APPO", "env": "atari_hero", "experiment": "atari_hero_APPO", "train_dir": "./train_atari", - "restart_behavior": "restart", + "restart_behavior": "resume", "seed": 1234, "num_policies": 2, "async_rl": true, "batched_sampling": true, + "worker_num_splits": 2, "num_workers": 16, - "num_envs_per_worker": 2, + "num_envs_per_worker": 8, "batch_size": 1024, "num_batches_per_epoch": 8, "num_epochs": 4, "exploration_loss_coeff": 0.0004677351413, "max_grad_norm": 0.0, "learning_rate": 0.0003033891184, + "summaries_use_frameskip": false, "heartbeat_interval": 10, "heartbeat_reporting_interval": 60, - "train_for_env_steps": 100000000, + "train_for_env_steps": 500000000, "save_milestones_sec": 1200, "with_wandb": true, "wandb_user": "matt-stammers", @@ -158,5 +160,5 @@ }, "git_hash": "5fff97c2f535da5987d358cdbe6927cccd43621e", "git_repo_name": "not a git repository", - "wandb_unique_id": "atari_hero_APPO_20231012_030307_335840" + "wandb_unique_id": "atari_hero_APPO_20231106_140647_610567" } \ No newline at end of file diff --git a/git.diff b/git.diff index 960bf7b013feefe7b56842bffdcf222f0bdf7dbd..f2014ff0d08b4ad19d4c267f4668e0df6f312c93 100644 --- a/git.diff +++ b/git.diff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:3357904f421d3f4924836316b1741bf64d5dd0e807d5e80ac07059b4c52a7008 -size 14426734 +oid sha256:de4fecb91705490b8f6f89418f0c59ae52b7bc523a512f22d64b0d2006864d31 +size 380928 diff --git a/replay.mp4 b/replay.mp4 index 41456f9e66c6f698a7ee3d1c6ddb7b35448d73f4..2b768afd89751a431d9b5dbd81c0902df1ed6d18 100644 --- a/replay.mp4 +++ b/replay.mp4 @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:c312d0e49540460529c9859af71cb7eead600c5ca46be56ba97dda0a101ed909 -size 4224392 +oid sha256:b0664279fc87edbade329b509d38347b17a96adaedd07a7e024188b2471e41fc +size 8003471 diff --git a/sf_log.txt b/sf_log.txt index d8c95c33e00257099c047c6e1ec19ed0178f2d4a..c06396409e531cd2e3f0d4d678d8efa082724b69 100644 --- a/sf_log.txt +++ b/sf_log.txt @@ -1,26922 +1,3 @@ -[2023-10-12 03:03:14,073][77203] Saving configuration to ./train_atari/atari_hero_APPO/config.json... -[2023-10-12 03:03:14,390][77203] Rollout worker 0 uses device cpu -[2023-10-12 03:03:14,391][77203] Rollout worker 1 uses device cpu -[2023-10-12 03:03:14,392][77203] Rollout worker 2 uses device cpu -[2023-10-12 03:03:14,392][77203] Rollout worker 3 uses device cpu -[2023-10-12 03:03:14,393][77203] Rollout worker 4 uses device cpu -[2023-10-12 03:03:14,394][77203] Rollout worker 5 uses device cpu -[2023-10-12 03:03:14,394][77203] Rollout worker 6 uses device cpu -[2023-10-12 03:03:14,395][77203] Rollout worker 7 uses device cpu -[2023-10-12 03:03:14,395][77203] Rollout worker 8 uses device cpu -[2023-10-12 03:03:14,396][77203] Rollout worker 9 uses device cpu -[2023-10-12 03:03:14,396][77203] Rollout worker 10 uses device cpu -[2023-10-12 03:03:14,396][77203] Rollout worker 11 uses device cpu -[2023-10-12 03:03:14,397][77203] Rollout worker 12 uses device cpu -[2023-10-12 03:03:14,397][77203] Rollout worker 13 uses device cpu -[2023-10-12 03:03:14,398][77203] Rollout worker 14 uses device cpu -[2023-10-12 03:03:14,398][77203] Rollout worker 15 uses device cpu -[2023-10-12 03:03:14,694][77203] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-10-12 03:03:14,695][77203] InferenceWorker_p0-w0: min num requests: 2 -[2023-10-12 03:03:14,698][77203] Using GPUs [1] for process 1 (actually maps to GPUs [1]) -[2023-10-12 03:03:14,698][77203] InferenceWorker_p1-w0: min num requests: 2 -[2023-10-12 03:03:14,746][77203] Starting all processes... -[2023-10-12 03:03:14,746][77203] Starting process learner_proc0 -[2023-10-12 03:03:16,403][77203] Starting process learner_proc1 -[2023-10-12 03:03:16,408][77792] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-10-12 03:03:16,408][77792] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 -[2023-10-12 03:03:16,427][77792] Num visible devices: 1 -[2023-10-12 03:03:16,444][77792] Setting fixed seed 1234 -[2023-10-12 03:03:16,445][77792] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-10-12 03:03:16,445][77792] Initializing actor-critic model on device cuda:0 -[2023-10-12 03:03:16,445][77792] RunningMeanStd input shape: (4, 84, 84) -[2023-10-12 03:03:16,446][77792] RunningMeanStd input shape: (1,) -[2023-10-12 03:03:16,457][77792] ConvEncoder: input_channels=4 -[2023-10-12 03:03:16,610][77792] Conv encoder output size: 512 -[2023-10-12 03:03:16,612][77792] Created Actor Critic model with architecture: -[2023-10-12 03:03:16,612][77792] 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=18, bias=True) - ) -) -[2023-10-12 03:03:17,175][77792] Using optimizer -[2023-10-12 03:03:17,175][77792] No checkpoints found -[2023-10-12 03:03:17,176][77792] Did not load from checkpoint, starting from scratch! -[2023-10-12 03:03:17,176][77792] Initialized policy 0 weights for model version 0 -[2023-10-12 03:03:17,177][77792] LearnerWorker_p0 finished initialization! -[2023-10-12 03:03:17,178][77792] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-10-12 03:03:18,165][77203] Starting all processes... -[2023-10-12 03:03:18,168][77950] Using GPUs [1] for process 1 (actually maps to GPUs [1]) -[2023-10-12 03:03:18,169][77950] Set environment var CUDA_VISIBLE_DEVICES to '1' (GPU indices [1]) for learning process 1 -[2023-10-12 03:03:18,174][77203] Starting process inference_proc0-0 -[2023-10-12 03:03:18,174][77203] Starting process inference_proc1-0 -[2023-10-12 03:03:18,174][77203] Starting process rollout_proc0 -[2023-10-12 03:03:18,187][77950] Num visible devices: 1 -[2023-10-12 03:03:18,174][77203] Starting process rollout_proc1 -[2023-10-12 03:03:18,175][77203] Starting process rollout_proc2 -[2023-10-12 03:03:18,175][77203] Starting process rollout_proc3 -[2023-10-12 03:03:18,211][77950] Setting fixed seed 1234 -[2023-10-12 03:03:18,180][77203] Starting process rollout_proc4 -[2023-10-12 03:03:18,213][77950] Using GPUs [0] for process 1 (actually maps to GPUs [1]) -[2023-10-12 03:03:18,213][77950] Initializing actor-critic model on device cuda:0 -[2023-10-12 03:03:18,213][77950] RunningMeanStd input shape: (4, 84, 84) -[2023-10-12 03:03:18,214][77950] RunningMeanStd input shape: (1,) -[2023-10-12 03:03:18,181][77203] Starting process rollout_proc5 -[2023-10-12 03:03:18,182][77203] Starting process rollout_proc6 -[2023-10-12 03:03:18,186][77203] Starting process rollout_proc7 -[2023-10-12 03:03:18,187][77203] Starting process rollout_proc8 -[2023-10-12 03:03:18,226][77950] ConvEncoder: input_channels=4 -[2023-10-12 03:03:18,203][77203] Starting process rollout_proc9 -[2023-10-12 03:03:18,203][77203] Starting process rollout_proc10 -[2023-10-12 03:03:18,204][77203] Starting process rollout_proc11 -[2023-10-12 03:03:18,208][77203] Starting process rollout_proc12 -[2023-10-12 03:03:18,208][77203] Starting process rollout_proc13 -[2023-10-12 03:03:18,737][77950] Conv encoder output size: 512 -[2023-10-12 03:03:18,739][77950] Created Actor Critic model with architecture: -[2023-10-12 03:03:18,739][77950] 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=18, bias=True) - ) -) -[2023-10-12 03:03:19,371][77950] Using optimizer -[2023-10-12 03:03:19,372][77950] No checkpoints found -[2023-10-12 03:03:19,372][77950] Did not load from checkpoint, starting from scratch! -[2023-10-12 03:03:19,372][77950] Initialized policy 1 weights for model version 0 -[2023-10-12 03:03:19,373][77950] LearnerWorker_p1 finished initialization! -[2023-10-12 03:03:19,374][77950] Using GPUs [0] for process 1 (actually maps to GPUs [1]) -[2023-10-12 03:03:20,417][77203] Starting process rollout_proc14 -[2023-10-12 03:03:20,421][78127] Worker 3 uses CPU cores [6, 7] -[2023-10-12 03:03:20,445][77203] Starting process rollout_proc15 -[2023-10-12 03:03:20,451][78135] Worker 11 uses CPU cores [22, 23] -[2023-10-12 03:03:20,531][78128] Worker 2 uses CPU cores [4, 5] -[2023-10-12 03:03:20,658][78124] Worker 0 uses CPU cores [0, 1] -[2023-10-12 03:03:20,793][78130] Worker 5 uses CPU cores [10, 11] -[2023-10-12 03:03:20,803][78123] Using GPUs [1] for process 1 (actually maps to GPUs [1]) -[2023-10-12 03:03:20,803][78123] Set environment var CUDA_VISIBLE_DEVICES to '1' (GPU indices [1]) for inference process 1 -[2023-10-12 03:03:20,823][78123] Num visible devices: 1 -[2023-10-12 03:03:20,879][78129] Worker 4 uses CPU cores [8, 9] -[2023-10-12 03:03:20,889][78137] Worker 12 uses CPU cores [24, 25] -[2023-10-12 03:03:20,895][78136] Worker 10 uses CPU cores [20, 21] -[2023-10-12 03:03:20,919][78138] Worker 13 uses CPU cores [26, 27] -[2023-10-12 03:03:20,932][78134] Worker 9 uses CPU cores [18, 19] -[2023-10-12 03:03:20,941][78133] Worker 8 uses CPU cores [16, 17] -[2023-10-12 03:03:20,959][78091] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-10-12 03:03:20,959][78091] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 -[2023-10-12 03:03:20,977][78091] Num visible devices: 1 -[2023-10-12 03:03:21,100][78132] Worker 7 uses CPU cores [14, 15] -[2023-10-12 03:03:21,112][78131] Worker 6 uses CPU cores [12, 13] -[2023-10-12 03:03:21,335][78125] Worker 1 uses CPU cores [2, 3] -[2023-10-12 03:03:21,536][78123] RunningMeanStd input shape: (4, 84, 84) -[2023-10-12 03:03:21,536][78123] RunningMeanStd input shape: (1,) -[2023-10-12 03:03:21,548][78123] ConvEncoder: input_channels=4 -[2023-10-12 03:03:21,602][78091] RunningMeanStd input shape: (4, 84, 84) -[2023-10-12 03:03:21,602][78091] RunningMeanStd input shape: (1,) -[2023-10-12 03:03:21,613][78091] ConvEncoder: input_channels=4 -[2023-10-12 03:03:21,651][78123] Conv encoder output size: 512 -[2023-10-12 03:03:21,715][78091] Conv encoder output size: 512 -[2023-10-12 03:03:22,351][78759] Worker 15 uses CPU cores [30, 31] -[2023-10-12 03:03:22,406][77203] Inference worker 1-0 is ready! -[2023-10-12 03:03:22,407][77203] Inference worker 0-0 is ready! -[2023-10-12 03:03:22,408][78725] Worker 14 uses CPU cores [28, 29] -[2023-10-12 03:03:22,408][77203] All inference workers are ready! Signal rollout workers to start! -[2023-10-12 03:03:22,409][78130] EnvRunner 5-0 uses policy 1 -[2023-10-12 03:03:22,409][78132] EnvRunner 7-0 uses policy 1 -[2023-10-12 03:03:22,409][78134] EnvRunner 9-0 uses policy 1 -[2023-10-12 03:03:22,409][78136] EnvRunner 10-0 uses policy 0 -[2023-10-12 03:03:22,409][78131] EnvRunner 6-0 uses policy 0 -[2023-10-12 03:03:22,409][78133] EnvRunner 8-0 uses policy 0 -[2023-10-12 03:03:22,409][78138] EnvRunner 13-0 uses policy 1 -[2023-10-12 03:03:22,409][78128] EnvRunner 2-0 uses policy 0 -[2023-10-12 03:03:22,410][78129] EnvRunner 4-0 uses policy 0 -[2023-10-12 03:03:22,410][78127] EnvRunner 3-0 uses policy 1 -[2023-10-12 03:03:22,410][78137] EnvRunner 12-0 uses policy 0 -[2023-10-12 03:03:22,409][77203] 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) -[2023-10-12 03:03:22,410][78125] EnvRunner 1-0 uses policy 1 -[2023-10-12 03:03:22,410][78135] EnvRunner 11-0 uses policy 1 -[2023-10-12 03:03:22,410][78124] EnvRunner 0-0 uses policy 0 -[2023-10-12 03:03:22,536][78725] EnvRunner 14-0 uses policy 0 -[2023-10-12 03:03:22,548][78759] EnvRunner 15-0 uses policy 1 -[2023-10-12 03:03:24,682][77203] Heartbeat connected on Batcher_0 -[2023-10-12 03:03:24,685][77203] Heartbeat connected on LearnerWorker_p0 -[2023-10-12 03:03:24,688][77203] Heartbeat connected on Batcher_1 -[2023-10-12 03:03:24,690][77203] Heartbeat connected on LearnerWorker_p1 -[2023-10-12 03:03:24,702][77203] Heartbeat connected on InferenceWorker_p0-w0 -[2023-10-12 03:03:24,703][77203] Heartbeat connected on RolloutWorker_w0 -[2023-10-12 03:03:24,706][77203] Heartbeat connected on InferenceWorker_p1-w0 -[2023-10-12 03:03:24,708][77203] Heartbeat connected on RolloutWorker_w2 -[2023-10-12 03:03:24,709][77203] Heartbeat connected on RolloutWorker_w1 -[2023-10-12 03:03:24,714][77203] Heartbeat connected on RolloutWorker_w3 -[2023-10-12 03:03:24,716][77203] Heartbeat connected on RolloutWorker_w5 -[2023-10-12 03:03:24,718][77203] Heartbeat connected on RolloutWorker_w6 -[2023-10-12 03:03:24,719][77203] Heartbeat connected on RolloutWorker_w4 -[2023-10-12 03:03:24,721][77203] Heartbeat connected on RolloutWorker_w7 -[2023-10-12 03:03:24,727][77203] Heartbeat connected on RolloutWorker_w9 -[2023-10-12 03:03:24,729][77203] Heartbeat connected on RolloutWorker_w8 -[2023-10-12 03:03:24,730][77203] Heartbeat connected on RolloutWorker_w10 -[2023-10-12 03:03:24,732][77203] Heartbeat connected on RolloutWorker_w11 -[2023-10-12 03:03:24,737][77203] Heartbeat connected on RolloutWorker_w12 -[2023-10-12 03:03:24,741][77203] Heartbeat connected on RolloutWorker_w13 -[2023-10-12 03:03:24,744][77203] Heartbeat connected on RolloutWorker_w14 -[2023-10-12 03:03:24,750][77203] Heartbeat connected on RolloutWorker_w15 -[2023-10-12 03:03:25,201][77203] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 460.6, 1: 470.0. Samples: 2598. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) -[2023-10-12 03:03:25,203][77203] Avg episode reward: [(0, '0.353'), (1, '0.263')] -[2023-10-12 03:03:30,201][77203] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 855.3, 1: 848.9. Samples: 13278. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) -[2023-10-12 03:03:30,201][77203] Avg episode reward: [(0, '0.188'), (1, '0.180')] -[2023-10-12 03:03:33,009][78091] Updated weights for policy 0, policy_version 10 (0.0008) -[2023-10-12 03:03:33,339][78123] Updated weights for policy 1, policy_version 10 (0.0009) -[2023-10-12 03:03:33,376][78091] Updated weights for policy 0, policy_version 20 (0.0007) -[2023-10-12 03:03:33,701][78123] Updated weights for policy 1, policy_version 20 (0.0008) -[2023-10-12 03:03:33,754][78091] Updated weights for policy 0, policy_version 30 (0.0008) -[2023-10-12 03:03:34,058][78123] Updated weights for policy 1, policy_version 30 (0.0008) -[2023-10-12 03:03:35,201][77203] Fps is (10 sec: 6553.9, 60 sec: 5123.5, 300 sec: 5123.5). Total num frames: 65536. Throughput: 0: 1128.1, 1: 1151.9. Samples: 29164. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-12 03:03:35,201][77203] Avg episode reward: [(0, '0.430'), (1, '0.170')] -[2023-10-12 03:03:36,656][78123] Updated weights for policy 1, policy_version 40 (0.0009) -[2023-10-12 03:03:36,746][78091] Updated weights for policy 0, policy_version 40 (0.0009) -[2023-10-12 03:03:37,023][78123] Updated weights for policy 1, policy_version 50 (0.0011) -[2023-10-12 03:03:37,118][78091] Updated weights for policy 0, policy_version 50 (0.0010) -[2023-10-12 03:03:37,391][78123] Updated weights for policy 1, policy_version 60 (0.0007) -[2023-10-12 03:03:37,492][78091] Updated weights for policy 0, policy_version 60 (0.0009) -[2023-10-12 03:03:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 7367.2, 300 sec: 7367.2). Total num frames: 131072. Throughput: 0: 1344.6, 1: 1356.2. Samples: 48050. Policy #0 lag: (min: 33.0, avg: 33.0, max: 33.0) -[2023-10-12 03:03:40,201][77203] Avg episode reward: [(0, '1.060'), (1, '2.110')] -[2023-10-12 03:03:41,201][78123] Updated weights for policy 1, policy_version 70 (0.0009) -[2023-10-12 03:03:41,349][78091] Updated weights for policy 0, policy_version 70 (0.0008) -[2023-10-12 03:03:41,565][78123] Updated weights for policy 1, policy_version 80 (0.0008) -[2023-10-12 03:03:41,721][78091] Updated weights for policy 0, policy_version 80 (0.0009) -[2023-10-12 03:03:41,923][78123] Updated weights for policy 1, policy_version 90 (0.0009) -[2023-10-12 03:03:42,098][78091] Updated weights for policy 0, policy_version 90 (0.0008) -[2023-10-12 03:03:45,201][77203] Fps is (10 sec: 13106.7, 60 sec: 8626.3, 300 sec: 8626.3). Total num frames: 196608. Throughput: 0: 1233.9, 1: 1247.0. Samples: 56544. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 03:03:45,202][77203] Avg episode reward: [(0, '2.990'), (1, '3.380')] -[2023-10-12 03:03:45,976][78091] Updated weights for policy 0, policy_version 100 (0.0008) -[2023-10-12 03:03:46,038][78123] Updated weights for policy 1, policy_version 100 (0.0009) -[2023-10-12 03:03:46,348][78091] Updated weights for policy 0, policy_version 110 (0.0010) -[2023-10-12 03:03:46,405][78123] Updated weights for policy 1, policy_version 110 (0.0007) -[2023-10-12 03:03:46,708][78091] Updated weights for policy 0, policy_version 120 (0.0009) -[2023-10-12 03:03:46,770][78123] Updated weights for policy 1, policy_version 120 (0.0008) -[2023-10-12 03:03:50,201][77203] Fps is (10 sec: 13106.9, 60 sec: 9432.5, 300 sec: 9432.5). Total num frames: 262144. Throughput: 0: 1364.4, 1: 1361.5. Samples: 75758. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-12 03:03:50,202][77203] Avg episode reward: [(0, '5.270'), (1, '7.300')] -[2023-10-12 03:03:50,204][77792] Saving new best policy, reward=5.270! -[2023-10-12 03:03:50,204][77950] Saving new best policy, reward=7.300! -[2023-10-12 03:03:51,166][78123] Updated weights for policy 1, policy_version 130 (0.0008) -[2023-10-12 03:03:51,223][78091] Updated weights for policy 0, policy_version 130 (0.0011) -[2023-10-12 03:03:51,524][78123] Updated weights for policy 1, policy_version 140 (0.0007) -[2023-10-12 03:03:51,594][78091] Updated weights for policy 0, policy_version 140 (0.0009) -[2023-10-12 03:03:51,877][78123] Updated weights for policy 1, policy_version 150 (0.0008) -[2023-10-12 03:03:51,950][78091] Updated weights for policy 0, policy_version 150 (0.0008) -[2023-10-12 03:03:52,244][78123] Updated weights for policy 1, policy_version 160 (0.0009) -[2023-10-12 03:03:52,324][78091] Updated weights for policy 0, policy_version 160 (0.0009) -[2023-10-12 03:03:55,201][77203] Fps is (10 sec: 13107.4, 60 sec: 9992.8, 300 sec: 9992.8). Total num frames: 327680. Throughput: 0: 1452.9, 1: 1441.7. Samples: 94918. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 03:03:55,202][77203] Avg episode reward: [(0, '6.420'), (1, '8.450')] -[2023-10-12 03:03:55,209][77792] Saving new best policy, reward=6.420! -[2023-10-12 03:03:55,210][77950] Saving new best policy, reward=8.450! -[2023-10-12 03:03:56,626][78091] Updated weights for policy 0, policy_version 170 (0.0008) -[2023-10-12 03:03:56,840][78123] Updated weights for policy 1, policy_version 170 (0.0008) -[2023-10-12 03:03:56,997][78091] Updated weights for policy 0, policy_version 180 (0.0007) -[2023-10-12 03:03:57,196][78123] Updated weights for policy 1, policy_version 180 (0.0009) -[2023-10-12 03:03:57,370][78091] Updated weights for policy 0, policy_version 190 (0.0008) -[2023-10-12 03:03:57,561][78123] Updated weights for policy 1, policy_version 190 (0.0008) -[2023-10-12 03:04:00,201][77203] Fps is (10 sec: 13107.4, 60 sec: 10404.9, 300 sec: 10404.9). Total num frames: 393216. Throughput: 0: 1373.7, 1: 1360.0. Samples: 103312. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) -[2023-10-12 03:04:00,202][77203] Avg episode reward: [(0, '8.070'), (1, '7.380')] -[2023-10-12 03:04:00,203][77792] Saving new best policy, reward=8.070! -[2023-10-12 03:04:01,778][78091] Updated weights for policy 0, policy_version 200 (0.0008) -[2023-10-12 03:04:01,960][78123] Updated weights for policy 1, policy_version 200 (0.0007) -[2023-10-12 03:04:02,144][78091] Updated weights for policy 0, policy_version 210 (0.0007) -[2023-10-12 03:04:02,320][78123] Updated weights for policy 1, policy_version 210 (0.0007) -[2023-10-12 03:04:02,516][78091] Updated weights for policy 0, policy_version 220 (0.0010) -[2023-10-12 03:04:02,686][78123] Updated weights for policy 1, policy_version 220 (0.0007) -[2023-10-12 03:04:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 10720.6, 300 sec: 10720.6). Total num frames: 458752. Throughput: 0: 1439.2, 1: 1425.3. Samples: 122576. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:04:05,202][77203] Avg episode reward: [(0, '7.570'), (1, '8.810')] -[2023-10-12 03:04:05,204][77950] Saving new best policy, reward=8.810! -[2023-10-12 03:04:06,904][78091] Updated weights for policy 0, policy_version 230 (0.0009) -[2023-10-12 03:04:07,211][78123] Updated weights for policy 1, policy_version 230 (0.0009) -[2023-10-12 03:04:07,265][78091] Updated weights for policy 0, policy_version 240 (0.0008) -[2023-10-12 03:04:07,564][78123] Updated weights for policy 1, policy_version 240 (0.0008) -[2023-10-12 03:04:07,625][78091] Updated weights for policy 0, policy_version 250 (0.0009) -[2023-10-12 03:04:07,929][78123] Updated weights for policy 1, policy_version 250 (0.0008) -[2023-10-12 03:04:10,201][77203] Fps is (10 sec: 13107.5, 60 sec: 10970.4, 300 sec: 10970.4). Total num frames: 524288. Throughput: 0: 1554.6, 1: 1539.3. Samples: 141818. Policy #0 lag: (min: 4.0, avg: 6.4, max: 36.0) -[2023-10-12 03:04:10,201][77203] Avg episode reward: [(0, '8.060'), (1, '8.480')] -[2023-10-12 03:04:11,965][78091] Updated weights for policy 0, policy_version 260 (0.0007) -[2023-10-12 03:04:12,185][78123] Updated weights for policy 1, policy_version 260 (0.0009) -[2023-10-12 03:04:12,334][78091] Updated weights for policy 0, policy_version 270 (0.0007) -[2023-10-12 03:04:12,545][78123] Updated weights for policy 1, policy_version 270 (0.0008) -[2023-10-12 03:04:12,704][78091] Updated weights for policy 0, policy_version 280 (0.0009) -[2023-10-12 03:04:12,909][78123] Updated weights for policy 1, policy_version 280 (0.0009) -[2023-10-12 03:04:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 11172.7, 300 sec: 11172.7). Total num frames: 589824. Throughput: 0: 1535.0, 1: 1527.9. Samples: 151110. Policy #0 lag: (min: 31.0, avg: 36.2, max: 63.0) -[2023-10-12 03:04:15,202][77203] Avg episode reward: [(0, '9.830'), (1, '9.830')] -[2023-10-12 03:04:15,204][77950] Saving new best policy, reward=9.830! -[2023-10-12 03:04:15,204][77792] Saving new best policy, reward=9.830! -[2023-10-12 03:04:17,042][78091] Updated weights for policy 0, policy_version 290 (0.0007) -[2023-10-12 03:04:17,153][78123] Updated weights for policy 1, policy_version 290 (0.0008) -[2023-10-12 03:04:17,421][78091] Updated weights for policy 0, policy_version 300 (0.0007) -[2023-10-12 03:04:17,515][78123] Updated weights for policy 1, policy_version 300 (0.0008) -[2023-10-12 03:04:17,792][78091] Updated weights for policy 0, policy_version 310 (0.0009) -[2023-10-12 03:04:17,881][78123] Updated weights for policy 1, policy_version 310 (0.0008) -[2023-10-12 03:04:18,155][78091] Updated weights for policy 0, policy_version 320 (0.0008) -[2023-10-12 03:04:18,246][78123] Updated weights for policy 1, policy_version 320 (0.0007) -[2023-10-12 03:04:20,201][77203] Fps is (10 sec: 13106.9, 60 sec: 11340.1, 300 sec: 11340.1). Total num frames: 655360. Throughput: 0: 1570.4, 1: 1554.4. Samples: 169780. Policy #0 lag: (min: 31.0, avg: 40.9, max: 63.0) -[2023-10-12 03:04:20,202][77203] Avg episode reward: [(0, '10.800'), (1, '10.470')] -[2023-10-12 03:04:20,203][77792] Saving new best policy, reward=10.800! -[2023-10-12 03:04:20,203][77950] Saving new best policy, reward=10.470! -[2023-10-12 03:04:22,484][78091] Updated weights for policy 0, policy_version 330 (0.0009) -[2023-10-12 03:04:22,646][78123] Updated weights for policy 1, policy_version 330 (0.0008) -[2023-10-12 03:04:22,852][78091] Updated weights for policy 0, policy_version 340 (0.0009) -[2023-10-12 03:04:22,998][78123] Updated weights for policy 1, policy_version 340 (0.0008) -[2023-10-12 03:04:23,219][78091] Updated weights for policy 0, policy_version 350 (0.0007) -[2023-10-12 03:04:23,366][78123] Updated weights for policy 1, policy_version 350 (0.0008) -[2023-10-12 03:04:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12015.0, 300 sec: 11480.8). Total num frames: 720896. Throughput: 0: 1574.0, 1: 1557.3. Samples: 188956. Policy #0 lag: (min: 26.0, avg: 26.6, max: 43.0) -[2023-10-12 03:04:25,202][77203] Avg episode reward: [(0, '10.700'), (1, '11.030')] -[2023-10-12 03:04:25,215][77950] Saving new best policy, reward=11.030! -[2023-10-12 03:04:27,566][78091] Updated weights for policy 0, policy_version 360 (0.0007) -[2023-10-12 03:04:27,684][78123] Updated weights for policy 1, policy_version 360 (0.0007) -[2023-10-12 03:04:27,930][78091] Updated weights for policy 0, policy_version 370 (0.0007) -[2023-10-12 03:04:28,053][78123] Updated weights for policy 1, policy_version 370 (0.0007) -[2023-10-12 03:04:28,292][78091] Updated weights for policy 0, policy_version 380 (0.0007) -[2023-10-12 03:04:28,415][78123] Updated weights for policy 1, policy_version 380 (0.0007) -[2023-10-12 03:04:30,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 11600.8). Total num frames: 786432. Throughput: 0: 1592.2, 1: 1576.6. Samples: 199142. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) -[2023-10-12 03:04:30,201][77203] Avg episode reward: [(0, '10.780'), (1, '10.130')] -[2023-10-12 03:04:32,608][78091] Updated weights for policy 0, policy_version 390 (0.0008) -[2023-10-12 03:04:32,657][78123] Updated weights for policy 1, policy_version 390 (0.0007) -[2023-10-12 03:04:32,973][78091] Updated weights for policy 0, policy_version 400 (0.0008) -[2023-10-12 03:04:33,022][78123] Updated weights for policy 1, policy_version 400 (0.0008) -[2023-10-12 03:04:33,347][78091] Updated weights for policy 0, policy_version 410 (0.0008) -[2023-10-12 03:04:33,380][78123] Updated weights for policy 1, policy_version 410 (0.0008) -[2023-10-12 03:04:35,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.1, 300 sec: 11704.2). Total num frames: 851968. Throughput: 0: 1574.4, 1: 1568.6. Samples: 217194. Policy #0 lag: (min: 22.0, avg: 26.3, max: 54.0) -[2023-10-12 03:04:35,202][77203] Avg episode reward: [(0, '11.090'), (1, '10.440')] -[2023-10-12 03:04:35,203][77792] Saving new best policy, reward=11.090! -[2023-10-12 03:04:37,750][78091] Updated weights for policy 0, policy_version 420 (0.0007) -[2023-10-12 03:04:38,007][78123] Updated weights for policy 1, policy_version 420 (0.0008) -[2023-10-12 03:04:38,119][78091] Updated weights for policy 0, policy_version 430 (0.0009) -[2023-10-12 03:04:38,380][78123] Updated weights for policy 1, policy_version 430 (0.0008) -[2023-10-12 03:04:38,488][78091] Updated weights for policy 0, policy_version 440 (0.0007) -[2023-10-12 03:04:38,745][78123] Updated weights for policy 1, policy_version 440 (0.0010) -[2023-10-12 03:04:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 11794.4). Total num frames: 917504. Throughput: 0: 1571.9, 1: 1571.1. Samples: 236352. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 03:04:40,202][77203] Avg episode reward: [(0, '10.760'), (1, '11.110')] -[2023-10-12 03:04:40,210][77950] Saving new best policy, reward=11.110! -[2023-10-12 03:04:42,822][78091] Updated weights for policy 0, policy_version 450 (0.0007) -[2023-10-12 03:04:42,982][78123] Updated weights for policy 1, policy_version 450 (0.0009) -[2023-10-12 03:04:43,189][78091] Updated weights for policy 0, policy_version 460 (0.0007) -[2023-10-12 03:04:43,349][78123] Updated weights for policy 1, policy_version 460 (0.0010) -[2023-10-12 03:04:43,565][78091] Updated weights for policy 0, policy_version 470 (0.0007) -[2023-10-12 03:04:43,713][78123] Updated weights for policy 1, policy_version 470 (0.0008) -[2023-10-12 03:04:43,926][78091] Updated weights for policy 0, policy_version 480 (0.0009) -[2023-10-12 03:04:44,064][78123] Updated weights for policy 1, policy_version 480 (0.0008) -[2023-10-12 03:04:45,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.3, 300 sec: 11873.7). Total num frames: 983040. Throughput: 0: 1596.4, 1: 1599.8. Samples: 247138. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-10-12 03:04:45,202][77203] Avg episode reward: [(0, '9.920'), (1, '10.930')] -[2023-10-12 03:04:48,220][78091] Updated weights for policy 0, policy_version 490 (0.0007) -[2023-10-12 03:04:48,508][78123] Updated weights for policy 1, policy_version 490 (0.0008) -[2023-10-12 03:04:48,592][78091] Updated weights for policy 0, policy_version 500 (0.0009) -[2023-10-12 03:04:48,869][78123] Updated weights for policy 1, policy_version 500 (0.0008) -[2023-10-12 03:04:48,965][78091] Updated weights for policy 0, policy_version 510 (0.0009) -[2023-10-12 03:04:49,242][78123] Updated weights for policy 1, policy_version 510 (0.0007) -[2023-10-12 03:04:50,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 11943.9). Total num frames: 1048576. Throughput: 0: 1580.7, 1: 1587.9. Samples: 265162. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-12 03:04:50,202][77203] Avg episode reward: [(0, '12.180'), (1, '10.590')] -[2023-10-12 03:04:50,203][77792] Saving new best policy, reward=12.180! -[2023-10-12 03:04:53,305][78091] Updated weights for policy 0, policy_version 520 (0.0008) -[2023-10-12 03:04:53,547][78123] Updated weights for policy 1, policy_version 520 (0.0008) -[2023-10-12 03:04:53,662][78091] Updated weights for policy 0, policy_version 530 (0.0007) -[2023-10-12 03:04:53,917][78123] Updated weights for policy 1, policy_version 530 (0.0009) -[2023-10-12 03:04:54,028][78091] Updated weights for policy 0, policy_version 540 (0.0010) -[2023-10-12 03:04:54,281][78123] Updated weights for policy 1, policy_version 540 (0.0007) -[2023-10-12 03:04:55,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12006.6). Total num frames: 1114112. Throughput: 0: 1576.8, 1: 1574.5. Samples: 283628. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:04:55,202][77203] Avg episode reward: [(0, '11.920'), (1, '10.190')] -[2023-10-12 03:04:58,404][78091] Updated weights for policy 0, policy_version 550 (0.0009) -[2023-10-12 03:04:58,556][78123] Updated weights for policy 1, policy_version 550 (0.0008) -[2023-10-12 03:04:58,770][78091] Updated weights for policy 0, policy_version 560 (0.0010) -[2023-10-12 03:04:58,927][78123] Updated weights for policy 1, policy_version 560 (0.0008) -[2023-10-12 03:04:59,142][78091] Updated weights for policy 0, policy_version 570 (0.0008) -[2023-10-12 03:04:59,285][78123] Updated weights for policy 1, policy_version 570 (0.0009) -[2023-10-12 03:05:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12062.9). Total num frames: 1179648. Throughput: 0: 1592.8, 1: 1589.8. Samples: 294328. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-12 03:05:00,202][77203] Avg episode reward: [(0, '10.290'), (1, '11.070')] -[2023-10-12 03:05:03,511][78091] Updated weights for policy 0, policy_version 580 (0.0008) -[2023-10-12 03:05:03,605][78123] Updated weights for policy 1, policy_version 580 (0.0009) -[2023-10-12 03:05:03,874][78091] Updated weights for policy 0, policy_version 590 (0.0009) -[2023-10-12 03:05:03,972][78123] Updated weights for policy 1, policy_version 590 (0.0008) -[2023-10-12 03:05:04,245][78091] Updated weights for policy 0, policy_version 600 (0.0009) -[2023-10-12 03:05:04,338][78123] Updated weights for policy 1, policy_version 600 (0.0008) -[2023-10-12 03:05:05,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12113.7). Total num frames: 1245184. Throughput: 0: 1590.5, 1: 1597.7. Samples: 313250. Policy #0 lag: (min: 17.0, avg: 17.9, max: 39.0) -[2023-10-12 03:05:05,202][77203] Avg episode reward: [(0, '9.390'), (1, '11.060')] -[2023-10-12 03:05:08,732][78091] Updated weights for policy 0, policy_version 610 (0.0007) -[2023-10-12 03:05:08,800][78123] Updated weights for policy 1, policy_version 610 (0.0009) -[2023-10-12 03:05:09,131][78091] Updated weights for policy 0, policy_version 620 (0.0009) -[2023-10-12 03:05:09,202][78123] Updated weights for policy 1, policy_version 620 (0.0009) -[2023-10-12 03:05:09,495][78091] Updated weights for policy 0, policy_version 630 (0.0007) -[2023-10-12 03:05:09,561][78123] Updated weights for policy 1, policy_version 630 (0.0008) -[2023-10-12 03:05:09,865][78091] Updated weights for policy 0, policy_version 640 (0.0009) -[2023-10-12 03:05:09,925][78123] Updated weights for policy 1, policy_version 640 (0.0007) -[2023-10-12 03:05:10,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12159.8). Total num frames: 1310720. Throughput: 0: 1575.1, 1: 1588.0. Samples: 331296. Policy #0 lag: (min: 28.0, avg: 38.3, max: 60.0) -[2023-10-12 03:05:10,201][77203] Avg episode reward: [(0, '9.400'), (1, '11.480')] -[2023-10-12 03:05:10,209][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000000640_655360.pth... -[2023-10-12 03:05:10,209][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000000640_655360.pth... -[2023-10-12 03:05:10,238][77950] Saving new best policy, reward=11.480! -[2023-10-12 03:05:14,256][78123] Updated weights for policy 1, policy_version 650 (0.0008) -[2023-10-12 03:05:14,316][78091] Updated weights for policy 0, policy_version 650 (0.0008) -[2023-10-12 03:05:14,617][78123] Updated weights for policy 1, policy_version 660 (0.0009) -[2023-10-12 03:05:14,691][78091] Updated weights for policy 0, policy_version 660 (0.0008) -[2023-10-12 03:05:14,990][78123] Updated weights for policy 1, policy_version 670 (0.0008) -[2023-10-12 03:05:15,065][78091] Updated weights for policy 0, policy_version 670 (0.0007) -[2023-10-12 03:05:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12201.8). Total num frames: 1376256. Throughput: 0: 1585.0, 1: 1586.4. Samples: 341856. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:05:15,202][77203] Avg episode reward: [(0, '11.260'), (1, '11.310')] -[2023-10-12 03:05:19,336][78123] Updated weights for policy 1, policy_version 680 (0.0008) -[2023-10-12 03:05:19,382][78091] Updated weights for policy 0, policy_version 680 (0.0007) -[2023-10-12 03:05:19,706][78123] Updated weights for policy 1, policy_version 690 (0.0007) -[2023-10-12 03:05:19,763][78091] Updated weights for policy 0, policy_version 690 (0.0007) -[2023-10-12 03:05:20,078][78123] Updated weights for policy 1, policy_version 700 (0.0008) -[2023-10-12 03:05:20,132][78091] Updated weights for policy 0, policy_version 700 (0.0007) -[2023-10-12 03:05:20,201][77203] Fps is (10 sec: 6553.5, 60 sec: 12014.9, 300 sec: 11683.8). Total num frames: 1376256. Throughput: 0: 1600.8, 1: 1602.9. Samples: 361364. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:05:20,202][77203] Avg episode reward: [(0, '13.780'), (1, '12.240')] -[2023-10-12 03:05:20,218][77950] Saving new best policy, reward=12.240! -[2023-10-12 03:05:20,277][77792] Saving new best policy, reward=13.780! -[2023-10-12 03:05:24,418][78091] Updated weights for policy 0, policy_version 710 (0.0008) -[2023-10-12 03:05:24,649][78123] Updated weights for policy 1, policy_version 710 (0.0007) -[2023-10-12 03:05:24,793][78091] Updated weights for policy 0, policy_version 720 (0.0009) -[2023-10-12 03:05:25,012][78123] Updated weights for policy 1, policy_version 720 (0.0007) -[2023-10-12 03:05:25,155][78091] Updated weights for policy 0, policy_version 730 (0.0009) -[2023-10-12 03:05:25,201][77203] Fps is (10 sec: 6553.7, 60 sec: 12015.0, 300 sec: 11741.8). Total num frames: 1441792. Throughput: 0: 1593.6, 1: 1598.9. Samples: 380014. Policy #0 lag: (min: 15.0, avg: 21.0, max: 47.0) -[2023-10-12 03:05:25,201][77203] Avg episode reward: [(0, '11.070'), (1, '11.360')] -[2023-10-12 03:05:25,379][78123] Updated weights for policy 1, policy_version 730 (0.0007) -[2023-10-12 03:05:29,434][78091] Updated weights for policy 0, policy_version 740 (0.0007) -[2023-10-12 03:05:29,650][78123] Updated weights for policy 1, policy_version 740 (0.0009) -[2023-10-12 03:05:29,805][78091] Updated weights for policy 0, policy_version 750 (0.0008) -[2023-10-12 03:05:30,022][78123] Updated weights for policy 1, policy_version 750 (0.0008) -[2023-10-12 03:05:30,176][78091] Updated weights for policy 0, policy_version 760 (0.0008) -[2023-10-12 03:05:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 11795.2). Total num frames: 1507328. Throughput: 0: 1578.4, 1: 1580.6. Samples: 389294. Policy #0 lag: (min: 4.0, avg: 4.0, max: 5.0) -[2023-10-12 03:05:30,202][77203] Avg episode reward: [(0, '12.470'), (1, '11.350')] -[2023-10-12 03:05:30,389][78123] Updated weights for policy 1, policy_version 760 (0.0008) -[2023-10-12 03:05:34,504][78091] Updated weights for policy 0, policy_version 770 (0.0009) -[2023-10-12 03:05:34,769][78123] Updated weights for policy 1, policy_version 770 (0.0008) -[2023-10-12 03:05:34,872][78091] Updated weights for policy 0, policy_version 780 (0.0008) -[2023-10-12 03:05:35,131][78123] Updated weights for policy 1, policy_version 780 (0.0009) -[2023-10-12 03:05:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12015.0, 300 sec: 11844.6). Total num frames: 1572864. Throughput: 0: 1596.9, 1: 1596.1. Samples: 408848. Policy #0 lag: (min: 31.0, avg: 31.6, max: 49.0) -[2023-10-12 03:05:35,201][77203] Avg episode reward: [(0, '12.000'), (1, '11.930')] -[2023-10-12 03:05:35,248][78091] Updated weights for policy 0, policy_version 790 (0.0007) -[2023-10-12 03:05:35,501][78123] Updated weights for policy 1, policy_version 790 (0.0008) -[2023-10-12 03:05:35,610][78091] Updated weights for policy 0, policy_version 800 (0.0009) -[2023-10-12 03:05:35,871][78123] Updated weights for policy 1, policy_version 800 (0.0007) -[2023-10-12 03:05:39,868][78091] Updated weights for policy 0, policy_version 810 (0.0007) -[2023-10-12 03:05:40,106][78123] Updated weights for policy 1, policy_version 810 (0.0008) -[2023-10-12 03:05:40,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12014.9, 300 sec: 11890.4). Total num frames: 1638400. Throughput: 0: 1593.3, 1: 1611.8. Samples: 427858. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-12 03:05:40,201][77203] Avg episode reward: [(0, '11.030'), (1, '11.880')] -[2023-10-12 03:05:40,245][78091] Updated weights for policy 0, policy_version 820 (0.0007) -[2023-10-12 03:05:40,464][78123] Updated weights for policy 1, policy_version 820 (0.0009) -[2023-10-12 03:05:40,613][78091] Updated weights for policy 0, policy_version 830 (0.0008) -[2023-10-12 03:05:40,838][78123] Updated weights for policy 1, policy_version 830 (0.0007) -[2023-10-12 03:05:45,065][78091] Updated weights for policy 0, policy_version 840 (0.0008) -[2023-10-12 03:05:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 11933.0). Total num frames: 1703936. Throughput: 0: 1580.7, 1: 1584.3. Samples: 436750. Policy #0 lag: (min: 12.0, avg: 18.0, max: 44.0) -[2023-10-12 03:05:45,202][77203] Avg episode reward: [(0, '12.150'), (1, '11.960')] -[2023-10-12 03:05:45,320][78123] Updated weights for policy 1, policy_version 840 (0.0009) -[2023-10-12 03:05:45,434][78091] Updated weights for policy 0, policy_version 850 (0.0009) -[2023-10-12 03:05:45,691][78123] Updated weights for policy 1, policy_version 850 (0.0009) -[2023-10-12 03:05:45,803][78091] Updated weights for policy 0, policy_version 860 (0.0009) -[2023-10-12 03:05:46,061][78123] Updated weights for policy 1, policy_version 860 (0.0009) -[2023-10-12 03:05:50,065][78091] Updated weights for policy 0, policy_version 870 (0.0009) -[2023-10-12 03:05:50,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12015.0, 300 sec: 11972.8). Total num frames: 1769472. Throughput: 0: 1591.2, 1: 1583.3. Samples: 456100. Policy #0 lag: (min: 8.0, avg: 22.5, max: 40.0) -[2023-10-12 03:05:50,201][77203] Avg episode reward: [(0, '11.440'), (1, '13.740')] -[2023-10-12 03:05:50,370][78123] Updated weights for policy 1, policy_version 870 (0.0007) -[2023-10-12 03:05:50,433][78091] Updated weights for policy 0, policy_version 880 (0.0007) -[2023-10-12 03:05:50,744][78123] Updated weights for policy 1, policy_version 880 (0.0007) -[2023-10-12 03:05:50,810][78091] Updated weights for policy 0, policy_version 890 (0.0009) -[2023-10-12 03:05:51,114][78123] Updated weights for policy 1, policy_version 890 (0.0007) -[2023-10-12 03:05:51,330][77950] Saving new best policy, reward=13.740! -[2023-10-12 03:05:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12015.0, 300 sec: 12009.9). Total num frames: 1835008. Throughput: 0: 1605.0, 1: 1599.3. Samples: 475492. Policy #0 lag: (min: 16.0, avg: 38.4, max: 48.0) -[2023-10-12 03:05:55,201][77203] Avg episode reward: [(0, '12.820'), (1, '12.830')] -[2023-10-12 03:05:55,291][78091] Updated weights for policy 0, policy_version 900 (0.0010) -[2023-10-12 03:05:55,441][78123] Updated weights for policy 1, policy_version 900 (0.0009) -[2023-10-12 03:05:55,671][78091] Updated weights for policy 0, policy_version 910 (0.0007) -[2023-10-12 03:05:55,834][78123] Updated weights for policy 1, policy_version 910 (0.0008) -[2023-10-12 03:05:56,050][78091] Updated weights for policy 0, policy_version 920 (0.0008) -[2023-10-12 03:05:56,192][78123] Updated weights for policy 1, policy_version 920 (0.0008) -[2023-10-12 03:06:00,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12014.9, 300 sec: 12044.7). Total num frames: 1900544. Throughput: 0: 1575.8, 1: 1576.5. Samples: 483712. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:06:00,202][77203] Avg episode reward: [(0, '12.960'), (1, '11.500')] -[2023-10-12 03:06:00,498][78091] Updated weights for policy 0, policy_version 930 (0.0011) -[2023-10-12 03:06:00,696][78123] Updated weights for policy 1, policy_version 930 (0.0009) -[2023-10-12 03:06:00,870][78091] Updated weights for policy 0, policy_version 940 (0.0007) -[2023-10-12 03:06:01,060][78123] Updated weights for policy 1, policy_version 940 (0.0007) -[2023-10-12 03:06:01,234][78091] Updated weights for policy 0, policy_version 950 (0.0009) -[2023-10-12 03:06:01,417][78123] Updated weights for policy 1, policy_version 950 (0.0008) -[2023-10-12 03:06:01,609][78091] Updated weights for policy 0, policy_version 960 (0.0009) -[2023-10-12 03:06:01,792][78123] Updated weights for policy 1, policy_version 960 (0.0012) -[2023-10-12 03:06:05,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12014.9, 300 sec: 12077.3). Total num frames: 1966080. Throughput: 0: 1575.3, 1: 1573.3. Samples: 503052. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) -[2023-10-12 03:06:05,202][77203] Avg episode reward: [(0, '12.460'), (1, '12.050')] -[2023-10-12 03:06:05,835][78091] Updated weights for policy 0, policy_version 970 (0.0010) -[2023-10-12 03:06:06,200][78091] Updated weights for policy 0, policy_version 980 (0.0009) -[2023-10-12 03:06:06,298][78123] Updated weights for policy 1, policy_version 970 (0.0008) -[2023-10-12 03:06:06,574][78091] Updated weights for policy 0, policy_version 990 (0.0007) -[2023-10-12 03:06:06,661][78123] Updated weights for policy 1, policy_version 980 (0.0009) -[2023-10-12 03:06:07,028][78123] Updated weights for policy 1, policy_version 990 (0.0009) -[2023-10-12 03:06:10,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12014.9, 300 sec: 12108.0). Total num frames: 2031616. Throughput: 0: 1586.3, 1: 1581.3. Samples: 522558. Policy #0 lag: (min: 21.0, avg: 23.5, max: 53.0) -[2023-10-12 03:06:10,202][77203] Avg episode reward: [(0, '13.860'), (1, '12.510')] -[2023-10-12 03:06:10,211][77792] Saving new best policy, reward=13.860! -[2023-10-12 03:06:10,863][78091] Updated weights for policy 0, policy_version 1000 (0.0007) -[2023-10-12 03:06:11,236][78091] Updated weights for policy 0, policy_version 1010 (0.0008) -[2023-10-12 03:06:11,390][78123] Updated weights for policy 1, policy_version 1000 (0.0007) -[2023-10-12 03:06:11,614][78091] Updated weights for policy 0, policy_version 1020 (0.0007) -[2023-10-12 03:06:11,752][78123] Updated weights for policy 1, policy_version 1010 (0.0007) -[2023-10-12 03:06:12,128][78123] Updated weights for policy 1, policy_version 1020 (0.0009) -[2023-10-12 03:06:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 12136.9). Total num frames: 2097152. Throughput: 0: 1578.1, 1: 1576.7. Samples: 531258. Policy #0 lag: (min: 13.0, avg: 16.3, max: 45.0) -[2023-10-12 03:06:15,202][77203] Avg episode reward: [(0, '14.100'), (1, '12.150')] -[2023-10-12 03:06:15,203][77792] Saving new best policy, reward=14.100! -[2023-10-12 03:06:15,931][78091] Updated weights for policy 0, policy_version 1030 (0.0008) -[2023-10-12 03:06:16,226][78123] Updated weights for policy 1, policy_version 1030 (0.0009) -[2023-10-12 03:06:16,305][78091] Updated weights for policy 0, policy_version 1040 (0.0008) -[2023-10-12 03:06:16,588][78123] Updated weights for policy 1, policy_version 1040 (0.0008) -[2023-10-12 03:06:16,675][78091] Updated weights for policy 0, policy_version 1050 (0.0009) -[2023-10-12 03:06:16,953][78123] Updated weights for policy 1, policy_version 1050 (0.0009) -[2023-10-12 03:06:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12164.2). Total num frames: 2162688. Throughput: 0: 1574.1, 1: 1575.6. Samples: 550584. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-12 03:06:20,202][77203] Avg episode reward: [(0, '13.600'), (1, '12.550')] -[2023-10-12 03:06:21,060][78091] Updated weights for policy 0, policy_version 1060 (0.0008) -[2023-10-12 03:06:21,345][78123] Updated weights for policy 1, policy_version 1060 (0.0008) -[2023-10-12 03:06:21,428][78091] Updated weights for policy 0, policy_version 1070 (0.0007) -[2023-10-12 03:06:21,702][78123] Updated weights for policy 1, policy_version 1070 (0.0007) -[2023-10-12 03:06:21,795][78091] Updated weights for policy 0, policy_version 1080 (0.0008) -[2023-10-12 03:06:22,062][78123] Updated weights for policy 1, policy_version 1080 (0.0007) -[2023-10-12 03:06:25,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12190.0). Total num frames: 2228224. Throughput: 0: 1586.6, 1: 1576.0. Samples: 570176. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:06:25,201][77203] Avg episode reward: [(0, '11.650'), (1, '11.640')] -[2023-10-12 03:06:26,087][78091] Updated weights for policy 0, policy_version 1090 (0.0007) -[2023-10-12 03:06:26,207][78123] Updated weights for policy 1, policy_version 1090 (0.0009) -[2023-10-12 03:06:26,464][78091] Updated weights for policy 0, policy_version 1100 (0.0008) -[2023-10-12 03:06:26,587][78123] Updated weights for policy 1, policy_version 1100 (0.0007) -[2023-10-12 03:06:26,836][78091] Updated weights for policy 0, policy_version 1110 (0.0008) -[2023-10-12 03:06:26,947][78123] Updated weights for policy 1, policy_version 1110 (0.0009) -[2023-10-12 03:06:27,210][78091] Updated weights for policy 0, policy_version 1120 (0.0007) -[2023-10-12 03:06:27,307][78123] Updated weights for policy 1, policy_version 1120 (0.0009) -[2023-10-12 03:06:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12214.4). Total num frames: 2293760. Throughput: 0: 1580.2, 1: 1576.0. Samples: 578780. Policy #0 lag: (min: 6.0, avg: 13.3, max: 38.0) -[2023-10-12 03:06:30,201][77203] Avg episode reward: [(0, '11.370'), (1, '12.060')] -[2023-10-12 03:06:31,522][78091] Updated weights for policy 0, policy_version 1130 (0.0007) -[2023-10-12 03:06:31,757][78123] Updated weights for policy 1, policy_version 1130 (0.0008) -[2023-10-12 03:06:31,893][78091] Updated weights for policy 0, policy_version 1140 (0.0008) -[2023-10-12 03:06:32,126][78123] Updated weights for policy 1, policy_version 1140 (0.0007) -[2023-10-12 03:06:32,266][78091] Updated weights for policy 0, policy_version 1150 (0.0008) -[2023-10-12 03:06:32,490][78123] Updated weights for policy 1, policy_version 1150 (0.0009) -[2023-10-12 03:06:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12237.6). Total num frames: 2359296. Throughput: 0: 1582.7, 1: 1577.9. Samples: 598328. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:06:35,201][77203] Avg episode reward: [(0, '13.440'), (1, '11.680')] -[2023-10-12 03:06:36,639][78091] Updated weights for policy 0, policy_version 1160 (0.0009) -[2023-10-12 03:06:36,988][78123] Updated weights for policy 1, policy_version 1160 (0.0009) -[2023-10-12 03:06:37,002][78091] Updated weights for policy 0, policy_version 1170 (0.0008) -[2023-10-12 03:06:37,361][78123] Updated weights for policy 1, policy_version 1170 (0.0008) -[2023-10-12 03:06:37,373][78091] Updated weights for policy 0, policy_version 1180 (0.0009) -[2023-10-12 03:06:37,727][78123] Updated weights for policy 1, policy_version 1180 (0.0008) -[2023-10-12 03:06:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12259.5). Total num frames: 2424832. Throughput: 0: 1584.4, 1: 1579.2. Samples: 617852. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-12 03:06:40,202][77203] Avg episode reward: [(0, '12.860'), (1, '12.570')] -[2023-10-12 03:06:41,708][78091] Updated weights for policy 0, policy_version 1190 (0.0008) -[2023-10-12 03:06:42,019][78123] Updated weights for policy 1, policy_version 1190 (0.0008) -[2023-10-12 03:06:42,095][78091] Updated weights for policy 0, policy_version 1200 (0.0009) -[2023-10-12 03:06:42,404][78123] Updated weights for policy 1, policy_version 1200 (0.0007) -[2023-10-12 03:06:42,469][78091] Updated weights for policy 0, policy_version 1210 (0.0009) -[2023-10-12 03:06:42,768][78123] Updated weights for policy 1, policy_version 1210 (0.0007) -[2023-10-12 03:06:45,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12280.4). Total num frames: 2490368. Throughput: 0: 1585.6, 1: 1590.6. Samples: 626642. Policy #0 lag: (min: 31.0, avg: 35.5, max: 63.0) -[2023-10-12 03:06:45,201][77203] Avg episode reward: [(0, '14.850'), (1, '12.160')] -[2023-10-12 03:06:45,202][77792] Saving new best policy, reward=14.850! -[2023-10-12 03:06:46,681][78091] Updated weights for policy 0, policy_version 1220 (0.0009) -[2023-10-12 03:06:47,059][78091] Updated weights for policy 0, policy_version 1230 (0.0008) -[2023-10-12 03:06:47,151][78123] Updated weights for policy 1, policy_version 1220 (0.0009) -[2023-10-12 03:06:47,420][78091] Updated weights for policy 0, policy_version 1240 (0.0009) -[2023-10-12 03:06:47,505][78123] Updated weights for policy 1, policy_version 1230 (0.0008) -[2023-10-12 03:06:47,867][78123] Updated weights for policy 1, policy_version 1240 (0.0010) -[2023-10-12 03:06:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12300.3). Total num frames: 2555904. Throughput: 0: 1586.8, 1: 1587.2. Samples: 645880. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-10-12 03:06:50,202][77203] Avg episode reward: [(0, '13.560'), (1, '11.570')] -[2023-10-12 03:06:51,841][78091] Updated weights for policy 0, policy_version 1250 (0.0008) -[2023-10-12 03:06:52,218][78091] Updated weights for policy 0, policy_version 1260 (0.0007) -[2023-10-12 03:06:52,320][78123] Updated weights for policy 1, policy_version 1250 (0.0008) -[2023-10-12 03:06:52,578][78091] Updated weights for policy 0, policy_version 1270 (0.0007) -[2023-10-12 03:06:52,688][78123] Updated weights for policy 1, policy_version 1260 (0.0009) -[2023-10-12 03:06:52,951][78091] Updated weights for policy 0, policy_version 1280 (0.0007) -[2023-10-12 03:06:53,050][78123] Updated weights for policy 1, policy_version 1270 (0.0008) -[2023-10-12 03:06:53,420][78123] Updated weights for policy 1, policy_version 1280 (0.0010) -[2023-10-12 03:06:55,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12319.3). Total num frames: 2621440. Throughput: 0: 1584.0, 1: 1587.7. Samples: 665286. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-12 03:06:55,202][77203] Avg episode reward: [(0, '12.100'), (1, '11.950')] -[2023-10-12 03:06:57,361][78091] Updated weights for policy 0, policy_version 1290 (0.0009) -[2023-10-12 03:06:57,728][78091] Updated weights for policy 0, policy_version 1300 (0.0010) -[2023-10-12 03:06:57,730][78123] Updated weights for policy 1, policy_version 1290 (0.0008) -[2023-10-12 03:06:58,089][78123] Updated weights for policy 1, policy_version 1300 (0.0007) -[2023-10-12 03:06:58,104][78091] Updated weights for policy 0, policy_version 1310 (0.0009) -[2023-10-12 03:06:58,464][78123] Updated weights for policy 1, policy_version 1310 (0.0007) -[2023-10-12 03:07:00,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12337.4). Total num frames: 2686976. Throughput: 0: 1594.7, 1: 1602.0. Samples: 675108. Policy #0 lag: (min: 26.0, avg: 28.7, max: 58.0) -[2023-10-12 03:07:00,201][77203] Avg episode reward: [(0, '12.740'), (1, '12.180')] -[2023-10-12 03:07:02,530][78091] Updated weights for policy 0, policy_version 1320 (0.0009) -[2023-10-12 03:07:02,814][78123] Updated weights for policy 1, policy_version 1320 (0.0010) -[2023-10-12 03:07:02,896][78091] Updated weights for policy 0, policy_version 1330 (0.0008) -[2023-10-12 03:07:03,186][78123] Updated weights for policy 1, policy_version 1330 (0.0007) -[2023-10-12 03:07:03,255][78091] Updated weights for policy 0, policy_version 1340 (0.0008) -[2023-10-12 03:07:03,551][78123] Updated weights for policy 1, policy_version 1340 (0.0007) -[2023-10-12 03:07:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12354.7). Total num frames: 2752512. Throughput: 0: 1584.1, 1: 1584.8. Samples: 693188. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-12 03:07:05,202][77203] Avg episode reward: [(0, '12.930'), (1, '12.110')] -[2023-10-12 03:07:07,833][78123] Updated weights for policy 1, policy_version 1350 (0.0009) -[2023-10-12 03:07:07,851][78091] Updated weights for policy 0, policy_version 1350 (0.0007) -[2023-10-12 03:07:08,194][78123] Updated weights for policy 1, policy_version 1360 (0.0009) -[2023-10-12 03:07:08,214][78091] Updated weights for policy 0, policy_version 1360 (0.0007) -[2023-10-12 03:07:08,567][78123] Updated weights for policy 1, policy_version 1370 (0.0009) -[2023-10-12 03:07:08,590][78091] Updated weights for policy 0, policy_version 1370 (0.0009) -[2023-10-12 03:07:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12371.2). Total num frames: 2818048. Throughput: 0: 1577.2, 1: 1587.9. Samples: 712604. Policy #0 lag: (min: 10.0, avg: 10.5, max: 25.0) -[2023-10-12 03:07:10,201][77203] Avg episode reward: [(0, '13.540'), (1, '13.150')] -[2023-10-12 03:07:10,209][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000001376_1409024.pth... -[2023-10-12 03:07:10,210][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000001376_1409024.pth... -[2023-10-12 03:07:12,892][78091] Updated weights for policy 0, policy_version 1380 (0.0009) -[2023-10-12 03:07:12,904][78123] Updated weights for policy 1, policy_version 1380 (0.0007) -[2023-10-12 03:07:13,260][78091] Updated weights for policy 0, policy_version 1390 (0.0007) -[2023-10-12 03:07:13,271][78123] Updated weights for policy 1, policy_version 1390 (0.0008) -[2023-10-12 03:07:13,633][78091] Updated weights for policy 0, policy_version 1400 (0.0008) -[2023-10-12 03:07:13,644][78123] Updated weights for policy 1, policy_version 1400 (0.0008) -[2023-10-12 03:07:15,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12387.0). Total num frames: 2883584. Throughput: 0: 1600.4, 1: 1614.1. Samples: 723432. Policy #0 lag: (min: 10.0, avg: 10.2, max: 19.0) -[2023-10-12 03:07:15,202][77203] Avg episode reward: [(0, '17.430'), (1, '12.920')] -[2023-10-12 03:07:15,202][77792] Saving new best policy, reward=17.430! -[2023-10-12 03:07:17,949][78123] Updated weights for policy 1, policy_version 1410 (0.0009) -[2023-10-12 03:07:17,965][78091] Updated weights for policy 0, policy_version 1410 (0.0009) -[2023-10-12 03:07:18,317][78123] Updated weights for policy 1, policy_version 1420 (0.0009) -[2023-10-12 03:07:18,322][78091] Updated weights for policy 0, policy_version 1420 (0.0007) -[2023-10-12 03:07:18,682][78123] Updated weights for policy 1, policy_version 1430 (0.0008) -[2023-10-12 03:07:18,684][78091] Updated weights for policy 0, policy_version 1430 (0.0009) -[2023-10-12 03:07:19,055][78091] Updated weights for policy 0, policy_version 1440 (0.0008) -[2023-10-12 03:07:19,056][78123] Updated weights for policy 1, policy_version 1440 (0.0008) -[2023-10-12 03:07:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12402.1). Total num frames: 2949120. Throughput: 0: 1579.6, 1: 1596.5. Samples: 741254. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-12 03:07:20,201][77203] Avg episode reward: [(0, '14.680'), (1, '12.300')] -[2023-10-12 03:07:23,276][78091] Updated weights for policy 0, policy_version 1450 (0.0009) -[2023-10-12 03:07:23,353][78123] Updated weights for policy 1, policy_version 1450 (0.0009) -[2023-10-12 03:07:23,654][78091] Updated weights for policy 0, policy_version 1460 (0.0009) -[2023-10-12 03:07:23,720][78123] Updated weights for policy 1, policy_version 1460 (0.0008) -[2023-10-12 03:07:24,027][78091] Updated weights for policy 0, policy_version 1470 (0.0008) -[2023-10-12 03:07:24,082][78123] Updated weights for policy 1, policy_version 1470 (0.0009) -[2023-10-12 03:07:25,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12416.7). Total num frames: 3014656. Throughput: 0: 1577.2, 1: 1583.6. Samples: 760090. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:07:25,201][77203] Avg episode reward: [(0, '13.850'), (1, '11.890')] -[2023-10-12 03:07:28,315][78091] Updated weights for policy 0, policy_version 1480 (0.0007) -[2023-10-12 03:07:28,589][78123] Updated weights for policy 1, policy_version 1480 (0.0009) -[2023-10-12 03:07:28,700][78091] Updated weights for policy 0, policy_version 1490 (0.0008) -[2023-10-12 03:07:28,959][78123] Updated weights for policy 1, policy_version 1490 (0.0008) -[2023-10-12 03:07:29,071][78091] Updated weights for policy 0, policy_version 1500 (0.0010) -[2023-10-12 03:07:29,329][78123] Updated weights for policy 1, policy_version 1500 (0.0008) -[2023-10-12 03:07:30,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12430.6). Total num frames: 3080192. Throughput: 0: 1606.0, 1: 1601.4. Samples: 770974. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) -[2023-10-12 03:07:30,202][77203] Avg episode reward: [(0, '13.830'), (1, '13.330')] -[2023-10-12 03:07:33,356][78091] Updated weights for policy 0, policy_version 1510 (0.0008) -[2023-10-12 03:07:33,513][78123] Updated weights for policy 1, policy_version 1510 (0.0007) -[2023-10-12 03:07:33,728][78091] Updated weights for policy 0, policy_version 1520 (0.0007) -[2023-10-12 03:07:33,881][78123] Updated weights for policy 1, policy_version 1520 (0.0007) -[2023-10-12 03:07:34,093][78091] Updated weights for policy 0, policy_version 1530 (0.0007) -[2023-10-12 03:07:34,240][78123] Updated weights for policy 1, policy_version 1530 (0.0007) -[2023-10-12 03:07:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12444.0). Total num frames: 3145728. Throughput: 0: 1590.2, 1: 1597.8. Samples: 789338. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-12 03:07:35,201][77203] Avg episode reward: [(0, '13.690'), (1, '13.330')] -[2023-10-12 03:07:38,484][78091] Updated weights for policy 0, policy_version 1540 (0.0008) -[2023-10-12 03:07:38,797][78123] Updated weights for policy 1, policy_version 1540 (0.0007) -[2023-10-12 03:07:38,852][78091] Updated weights for policy 0, policy_version 1550 (0.0010) -[2023-10-12 03:07:39,167][78123] Updated weights for policy 1, policy_version 1550 (0.0010) -[2023-10-12 03:07:39,233][78091] Updated weights for policy 0, policy_version 1560 (0.0009) -[2023-10-12 03:07:39,530][78123] Updated weights for policy 1, policy_version 1560 (0.0010) -[2023-10-12 03:07:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12456.8). Total num frames: 3211264. Throughput: 0: 1584.0, 1: 1580.8. Samples: 807700. Policy #0 lag: (min: 17.0, avg: 24.4, max: 49.0) -[2023-10-12 03:07:40,202][77203] Avg episode reward: [(0, '14.210'), (1, '14.290')] -[2023-10-12 03:07:40,208][77950] Saving new best policy, reward=14.290! -[2023-10-12 03:07:43,607][78091] Updated weights for policy 0, policy_version 1570 (0.0008) -[2023-10-12 03:07:43,707][78123] Updated weights for policy 1, policy_version 1570 (0.0011) -[2023-10-12 03:07:43,967][78091] Updated weights for policy 0, policy_version 1580 (0.0009) -[2023-10-12 03:07:44,079][78123] Updated weights for policy 1, policy_version 1580 (0.0007) -[2023-10-12 03:07:44,342][78091] Updated weights for policy 0, policy_version 1590 (0.0008) -[2023-10-12 03:07:44,446][78123] Updated weights for policy 1, policy_version 1590 (0.0007) -[2023-10-12 03:07:44,713][78091] Updated weights for policy 0, policy_version 1600 (0.0008) -[2023-10-12 03:07:44,812][78123] Updated weights for policy 1, policy_version 1600 (0.0007) -[2023-10-12 03:07:45,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12469.2). Total num frames: 3276800. Throughput: 0: 1597.6, 1: 1585.6. Samples: 818352. Policy #0 lag: (min: 30.0, avg: 36.4, max: 62.0) -[2023-10-12 03:07:45,202][77203] Avg episode reward: [(0, '16.130'), (1, '14.500')] -[2023-10-12 03:07:45,204][77950] Saving new best policy, reward=14.500! -[2023-10-12 03:07:49,112][78091] Updated weights for policy 0, policy_version 1610 (0.0008) -[2023-10-12 03:07:49,206][78123] Updated weights for policy 1, policy_version 1610 (0.0009) -[2023-10-12 03:07:49,486][78091] Updated weights for policy 0, policy_version 1620 (0.0007) -[2023-10-12 03:07:49,575][78123] Updated weights for policy 1, policy_version 1620 (0.0008) -[2023-10-12 03:07:49,864][78091] Updated weights for policy 0, policy_version 1630 (0.0008) -[2023-10-12 03:07:49,935][78123] Updated weights for policy 1, policy_version 1630 (0.0010) -[2023-10-12 03:07:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12481.1). Total num frames: 3342336. Throughput: 0: 1607.8, 1: 1607.4. Samples: 837872. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-12 03:07:50,202][77203] Avg episode reward: [(0, '14.850'), (1, '14.320')] -[2023-10-12 03:07:54,327][78091] Updated weights for policy 0, policy_version 1640 (0.0009) -[2023-10-12 03:07:54,338][78123] Updated weights for policy 1, policy_version 1640 (0.0008) -[2023-10-12 03:07:54,701][78123] Updated weights for policy 1, policy_version 1650 (0.0007) -[2023-10-12 03:07:54,704][78091] Updated weights for policy 0, policy_version 1650 (0.0009) -[2023-10-12 03:07:55,074][78091] Updated weights for policy 0, policy_version 1660 (0.0009) -[2023-10-12 03:07:55,076][78123] Updated weights for policy 1, policy_version 1660 (0.0009) -[2023-10-12 03:07:55,201][77203] Fps is (10 sec: 6553.7, 60 sec: 12015.0, 300 sec: 12252.4). Total num frames: 3342336. Throughput: 0: 1594.8, 1: 1584.0. Samples: 855646. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-12 03:07:55,201][77203] Avg episode reward: [(0, '18.280'), (1, '14.870')] -[2023-10-12 03:07:55,215][77950] Saving new best policy, reward=14.870! -[2023-10-12 03:07:55,226][77792] Saving new best policy, reward=18.280! -[2023-10-12 03:07:59,491][78091] Updated weights for policy 0, policy_version 1670 (0.0008) -[2023-10-12 03:07:59,550][78123] Updated weights for policy 1, policy_version 1670 (0.0009) -[2023-10-12 03:07:59,849][78091] Updated weights for policy 0, policy_version 1680 (0.0008) -[2023-10-12 03:07:59,915][78123] Updated weights for policy 1, policy_version 1680 (0.0008) -[2023-10-12 03:08:00,201][77203] Fps is (10 sec: 6553.6, 60 sec: 12014.9, 300 sec: 12267.7). Total num frames: 3407872. Throughput: 0: 1586.0, 1: 1571.5. Samples: 865516. Policy #0 lag: (min: 4.0, avg: 6.1, max: 35.0) -[2023-10-12 03:08:00,201][77203] Avg episode reward: [(0, '18.750'), (1, '15.070')] -[2023-10-12 03:08:00,223][78091] Updated weights for policy 0, policy_version 1690 (0.0009) -[2023-10-12 03:08:00,290][78123] Updated weights for policy 1, policy_version 1690 (0.0008) -[2023-10-12 03:08:00,437][77792] Saving new best policy, reward=18.750! -[2023-10-12 03:08:00,509][77950] Saving new best policy, reward=15.070! -[2023-10-12 03:08:04,473][78091] Updated weights for policy 0, policy_version 1700 (0.0008) -[2023-10-12 03:08:04,689][78123] Updated weights for policy 1, policy_version 1700 (0.0008) -[2023-10-12 03:08:04,836][78091] Updated weights for policy 0, policy_version 1710 (0.0008) -[2023-10-12 03:08:05,053][78123] Updated weights for policy 1, policy_version 1710 (0.0009) -[2023-10-12 03:08:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12015.0, 300 sec: 12282.6). Total num frames: 3473408. Throughput: 0: 1605.7, 1: 1588.0. Samples: 884970. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-10-12 03:08:05,201][77203] Avg episode reward: [(0, '17.010'), (1, '15.710')] -[2023-10-12 03:08:05,207][78091] Updated weights for policy 0, policy_version 1720 (0.0009) -[2023-10-12 03:08:05,411][78123] Updated weights for policy 1, policy_version 1720 (0.0008) -[2023-10-12 03:08:05,708][77950] Saving new best policy, reward=15.710! -[2023-10-12 03:08:09,493][78091] Updated weights for policy 0, policy_version 1730 (0.0008) -[2023-10-12 03:08:09,861][78091] Updated weights for policy 0, policy_version 1740 (0.0008) -[2023-10-12 03:08:09,944][78123] Updated weights for policy 1, policy_version 1730 (0.0008) -[2023-10-12 03:08:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 12296.9). Total num frames: 3538944. Throughput: 0: 1599.3, 1: 1592.3. Samples: 903714. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:08:10,201][77203] Avg episode reward: [(0, '18.940'), (1, '14.100')] -[2023-10-12 03:08:10,238][78091] Updated weights for policy 0, policy_version 1750 (0.0009) -[2023-10-12 03:08:10,308][78123] Updated weights for policy 1, policy_version 1740 (0.0007) -[2023-10-12 03:08:10,596][77792] Saving new best policy, reward=18.940! -[2023-10-12 03:08:10,597][78091] Updated weights for policy 0, policy_version 1760 (0.0007) -[2023-10-12 03:08:10,671][78123] Updated weights for policy 1, policy_version 1750 (0.0007) -[2023-10-12 03:08:11,039][78123] Updated weights for policy 1, policy_version 1760 (0.0007) -[2023-10-12 03:08:14,792][78091] Updated weights for policy 0, policy_version 1770 (0.0009) -[2023-10-12 03:08:15,169][78091] Updated weights for policy 0, policy_version 1780 (0.0008) -[2023-10-12 03:08:15,201][77203] Fps is (10 sec: 13106.8, 60 sec: 12014.9, 300 sec: 12310.7). Total num frames: 3604480. Throughput: 0: 1581.9, 1: 1570.4. Samples: 912824. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-12 03:08:15,202][77203] Avg episode reward: [(0, '19.160'), (1, '16.480')] -[2023-10-12 03:08:15,377][78123] Updated weights for policy 1, policy_version 1770 (0.0007) -[2023-10-12 03:08:15,530][78091] Updated weights for policy 0, policy_version 1790 (0.0007) -[2023-10-12 03:08:15,601][77792] Saving new best policy, reward=19.160! -[2023-10-12 03:08:15,739][78123] Updated weights for policy 1, policy_version 1780 (0.0009) -[2023-10-12 03:08:16,117][78123] Updated weights for policy 1, policy_version 1790 (0.0009) -[2023-10-12 03:08:16,180][77950] Saving new best policy, reward=16.480! -[2023-10-12 03:08:20,045][78091] Updated weights for policy 0, policy_version 1800 (0.0007) -[2023-10-12 03:08:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 12440.8). Total num frames: 3670016. Throughput: 0: 1593.3, 1: 1575.5. Samples: 931934. Policy #0 lag: (min: 8.0, avg: 35.6, max: 40.0) -[2023-10-12 03:08:20,201][77203] Avg episode reward: [(0, '17.650'), (1, '15.960')] -[2023-10-12 03:08:20,330][78123] Updated weights for policy 1, policy_version 1800 (0.0009) -[2023-10-12 03:08:20,412][78091] Updated weights for policy 0, policy_version 1810 (0.0008) -[2023-10-12 03:08:20,703][78123] Updated weights for policy 1, policy_version 1810 (0.0008) -[2023-10-12 03:08:20,788][78091] Updated weights for policy 0, policy_version 1820 (0.0008) -[2023-10-12 03:08:21,069][78123] Updated weights for policy 1, policy_version 1820 (0.0007) -[2023-10-12 03:08:25,112][78091] Updated weights for policy 0, policy_version 1830 (0.0008) -[2023-10-12 03:08:25,201][77203] Fps is (10 sec: 13107.6, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 3735552. Throughput: 0: 1596.0, 1: 1593.2. Samples: 951210. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:08:25,201][77203] Avg episode reward: [(0, '17.440'), (1, '17.120')] -[2023-10-12 03:08:25,209][77950] Saving new best policy, reward=17.120! -[2023-10-12 03:08:25,479][78091] Updated weights for policy 0, policy_version 1840 (0.0007) -[2023-10-12 03:08:25,589][78123] Updated weights for policy 1, policy_version 1830 (0.0008) -[2023-10-12 03:08:25,843][78091] Updated weights for policy 0, policy_version 1850 (0.0007) -[2023-10-12 03:08:25,968][78123] Updated weights for policy 1, policy_version 1840 (0.0009) -[2023-10-12 03:08:26,343][78123] Updated weights for policy 1, policy_version 1850 (0.0009) -[2023-10-12 03:08:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 3801088. Throughput: 0: 1568.6, 1: 1572.8. Samples: 959714. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:08:30,202][77203] Avg episode reward: [(0, '18.870'), (1, '17.760')] -[2023-10-12 03:08:30,203][77950] Saving new best policy, reward=17.760! -[2023-10-12 03:08:30,361][78091] Updated weights for policy 0, policy_version 1860 (0.0008) -[2023-10-12 03:08:30,701][78123] Updated weights for policy 1, policy_version 1860 (0.0009) -[2023-10-12 03:08:30,727][78091] Updated weights for policy 0, policy_version 1870 (0.0008) -[2023-10-12 03:08:31,074][78123] Updated weights for policy 1, policy_version 1870 (0.0009) -[2023-10-12 03:08:31,101][78091] Updated weights for policy 0, policy_version 1880 (0.0010) -[2023-10-12 03:08:31,444][78123] Updated weights for policy 1, policy_version 1880 (0.0008) -[2023-10-12 03:08:35,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 3866624. Throughput: 0: 1573.8, 1: 1570.3. Samples: 979358. Policy #0 lag: (min: 26.0, avg: 26.4, max: 40.0) -[2023-10-12 03:08:35,202][77203] Avg episode reward: [(0, '17.670'), (1, '17.290')] -[2023-10-12 03:08:35,407][78091] Updated weights for policy 0, policy_version 1890 (0.0009) -[2023-10-12 03:08:35,674][78123] Updated weights for policy 1, policy_version 1890 (0.0008) -[2023-10-12 03:08:35,776][78091] Updated weights for policy 0, policy_version 1900 (0.0009) -[2023-10-12 03:08:36,044][78123] Updated weights for policy 1, policy_version 1900 (0.0009) -[2023-10-12 03:08:36,144][78091] Updated weights for policy 0, policy_version 1910 (0.0008) -[2023-10-12 03:08:36,411][78123] Updated weights for policy 1, policy_version 1910 (0.0008) -[2023-10-12 03:08:36,520][78091] Updated weights for policy 0, policy_version 1920 (0.0007) -[2023-10-12 03:08:36,779][78123] Updated weights for policy 1, policy_version 1920 (0.0008) -[2023-10-12 03:08:40,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 3932160. Throughput: 0: 1589.0, 1: 1590.8. Samples: 998738. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:08:40,201][77203] Avg episode reward: [(0, '19.540'), (1, '17.640')] -[2023-10-12 03:08:40,208][77792] Saving new best policy, reward=19.540! -[2023-10-12 03:08:40,934][78123] Updated weights for policy 1, policy_version 1930 (0.0009) -[2023-10-12 03:08:41,018][78091] Updated weights for policy 0, policy_version 1930 (0.0009) -[2023-10-12 03:08:41,310][78123] Updated weights for policy 1, policy_version 1940 (0.0008) -[2023-10-12 03:08:41,388][78091] Updated weights for policy 0, policy_version 1940 (0.0008) -[2023-10-12 03:08:41,681][78123] Updated weights for policy 1, policy_version 1950 (0.0007) -[2023-10-12 03:08:41,755][78091] Updated weights for policy 0, policy_version 1950 (0.0009) -[2023-10-12 03:08:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 3997696. Throughput: 0: 1571.7, 1: 1578.4. Samples: 1007274. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:08:45,202][77203] Avg episode reward: [(0, '19.810'), (1, '18.160')] -[2023-10-12 03:08:45,203][77792] Saving new best policy, reward=19.810! -[2023-10-12 03:08:45,203][77950] Saving new best policy, reward=18.160! -[2023-10-12 03:08:46,026][78123] Updated weights for policy 1, policy_version 1960 (0.0008) -[2023-10-12 03:08:46,091][78091] Updated weights for policy 0, policy_version 1960 (0.0008) -[2023-10-12 03:08:46,387][78123] Updated weights for policy 1, policy_version 1970 (0.0009) -[2023-10-12 03:08:46,455][78091] Updated weights for policy 0, policy_version 1970 (0.0009) -[2023-10-12 03:08:46,761][78123] Updated weights for policy 1, policy_version 1980 (0.0009) -[2023-10-12 03:08:46,820][78091] Updated weights for policy 0, policy_version 1980 (0.0007) -[2023-10-12 03:08:50,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 4063232. Throughput: 0: 1568.9, 1: 1576.7. Samples: 1026522. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-12 03:08:50,202][77203] Avg episode reward: [(0, '21.150'), (1, '17.460')] -[2023-10-12 03:08:50,204][77792] Saving new best policy, reward=21.150! -[2023-10-12 03:08:51,179][78091] Updated weights for policy 0, policy_version 1990 (0.0009) -[2023-10-12 03:08:51,251][78123] Updated weights for policy 1, policy_version 1990 (0.0007) -[2023-10-12 03:08:51,542][78091] Updated weights for policy 0, policy_version 2000 (0.0009) -[2023-10-12 03:08:51,618][78123] Updated weights for policy 1, policy_version 2000 (0.0007) -[2023-10-12 03:08:51,914][78091] Updated weights for policy 0, policy_version 2010 (0.0007) -[2023-10-12 03:08:51,982][78123] Updated weights for policy 1, policy_version 2010 (0.0007) -[2023-10-12 03:08:55,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 4128768. Throughput: 0: 1576.8, 1: 1583.3. Samples: 1045918. Policy #0 lag: (min: 1.0, avg: 11.0, max: 33.0) -[2023-10-12 03:08:55,201][77203] Avg episode reward: [(0, '22.100'), (1, '16.650')] -[2023-10-12 03:08:55,210][77792] Saving new best policy, reward=22.100! -[2023-10-12 03:08:56,252][78123] Updated weights for policy 1, policy_version 2020 (0.0007) -[2023-10-12 03:08:56,382][78091] Updated weights for policy 0, policy_version 2020 (0.0009) -[2023-10-12 03:08:56,613][78123] Updated weights for policy 1, policy_version 2030 (0.0007) -[2023-10-12 03:08:56,758][78091] Updated weights for policy 0, policy_version 2030 (0.0009) -[2023-10-12 03:08:56,978][78123] Updated weights for policy 1, policy_version 2040 (0.0007) -[2023-10-12 03:08:57,117][78091] Updated weights for policy 0, policy_version 2040 (0.0009) -[2023-10-12 03:09:00,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 4194304. Throughput: 0: 1564.0, 1: 1579.4. Samples: 1054276. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-12 03:09:00,201][77203] Avg episode reward: [(0, '21.140'), (1, '19.120')] -[2023-10-12 03:09:00,202][77950] Saving new best policy, reward=19.120! -[2023-10-12 03:09:01,357][78123] Updated weights for policy 1, policy_version 2050 (0.0007) -[2023-10-12 03:09:01,394][78091] Updated weights for policy 0, policy_version 2050 (0.0010) -[2023-10-12 03:09:01,725][78123] Updated weights for policy 1, policy_version 2060 (0.0007) -[2023-10-12 03:09:01,768][78091] Updated weights for policy 0, policy_version 2060 (0.0009) -[2023-10-12 03:09:02,092][78123] Updated weights for policy 1, policy_version 2070 (0.0008) -[2023-10-12 03:09:02,148][78091] Updated weights for policy 0, policy_version 2070 (0.0010) -[2023-10-12 03:09:02,461][78123] Updated weights for policy 1, policy_version 2080 (0.0008) -[2023-10-12 03:09:02,513][78091] Updated weights for policy 0, policy_version 2080 (0.0010) -[2023-10-12 03:09:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 4259840. Throughput: 0: 1569.0, 1: 1583.6. Samples: 1073804. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:09:05,202][77203] Avg episode reward: [(0, '22.540'), (1, '18.540')] -[2023-10-12 03:09:05,203][77792] Saving new best policy, reward=22.540! -[2023-10-12 03:09:06,660][78091] Updated weights for policy 0, policy_version 2090 (0.0008) -[2023-10-12 03:09:06,952][78123] Updated weights for policy 1, policy_version 2090 (0.0007) -[2023-10-12 03:09:07,024][78091] Updated weights for policy 0, policy_version 2100 (0.0008) -[2023-10-12 03:09:07,305][78123] Updated weights for policy 1, policy_version 2100 (0.0009) -[2023-10-12 03:09:07,396][78091] Updated weights for policy 0, policy_version 2110 (0.0010) -[2023-10-12 03:09:07,676][78123] Updated weights for policy 1, policy_version 2110 (0.0010) -[2023-10-12 03:09:10,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 4325376. Throughput: 0: 1575.7, 1: 1578.0. Samples: 1093126. Policy #0 lag: (min: 26.0, avg: 31.1, max: 58.0) -[2023-10-12 03:09:10,202][77203] Avg episode reward: [(0, '20.640'), (1, '19.020')] -[2023-10-12 03:09:10,210][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000002112_2162688.pth... -[2023-10-12 03:09:10,210][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000002112_2162688.pth... -[2023-10-12 03:09:10,240][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000000640_655360.pth -[2023-10-12 03:09:10,255][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000000640_655360.pth -[2023-10-12 03:09:11,776][78091] Updated weights for policy 0, policy_version 2120 (0.0011) -[2023-10-12 03:09:12,136][78091] Updated weights for policy 0, policy_version 2130 (0.0009) -[2023-10-12 03:09:12,253][78123] Updated weights for policy 1, policy_version 2120 (0.0008) -[2023-10-12 03:09:12,507][78091] Updated weights for policy 0, policy_version 2140 (0.0009) -[2023-10-12 03:09:12,626][78123] Updated weights for policy 1, policy_version 2130 (0.0007) -[2023-10-12 03:09:12,992][78123] Updated weights for policy 1, policy_version 2140 (0.0009) -[2023-10-12 03:09:15,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 4390912. Throughput: 0: 1580.2, 1: 1584.2. Samples: 1102112. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:09:15,202][77203] Avg episode reward: [(0, '21.480'), (1, '17.850')] -[2023-10-12 03:09:16,712][78091] Updated weights for policy 0, policy_version 2150 (0.0009) -[2023-10-12 03:09:17,075][78091] Updated weights for policy 0, policy_version 2160 (0.0008) -[2023-10-12 03:09:17,148][78123] Updated weights for policy 1, policy_version 2150 (0.0009) -[2023-10-12 03:09:17,443][78091] Updated weights for policy 0, policy_version 2170 (0.0007) -[2023-10-12 03:09:17,513][78123] Updated weights for policy 1, policy_version 2160 (0.0009) -[2023-10-12 03:09:17,885][78123] Updated weights for policy 1, policy_version 2170 (0.0010) -[2023-10-12 03:09:20,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 4456448. Throughput: 0: 1579.2, 1: 1575.3. Samples: 1121312. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:09:20,201][77203] Avg episode reward: [(0, '21.240'), (1, '19.320')] -[2023-10-12 03:09:20,202][77950] Saving new best policy, reward=19.320! -[2023-10-12 03:09:21,934][78091] Updated weights for policy 0, policy_version 2180 (0.0007) -[2023-10-12 03:09:22,134][78123] Updated weights for policy 1, policy_version 2180 (0.0010) -[2023-10-12 03:09:22,298][78091] Updated weights for policy 0, policy_version 2190 (0.0008) -[2023-10-12 03:09:22,498][78123] Updated weights for policy 1, policy_version 2190 (0.0009) -[2023-10-12 03:09:22,676][78091] Updated weights for policy 0, policy_version 2200 (0.0009) -[2023-10-12 03:09:22,873][78123] Updated weights for policy 1, policy_version 2200 (0.0009) -[2023-10-12 03:09:25,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 4521984. Throughput: 0: 1582.7, 1: 1575.9. Samples: 1140874. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:09:25,201][77203] Avg episode reward: [(0, '22.200'), (1, '22.970')] -[2023-10-12 03:09:25,208][77950] Saving new best policy, reward=22.970! -[2023-10-12 03:09:26,639][78091] Updated weights for policy 0, policy_version 2210 (0.0008) -[2023-10-12 03:09:27,002][78091] Updated weights for policy 0, policy_version 2220 (0.0010) -[2023-10-12 03:09:27,195][78123] Updated weights for policy 1, policy_version 2210 (0.0009) -[2023-10-12 03:09:27,377][78091] Updated weights for policy 0, policy_version 2230 (0.0009) -[2023-10-12 03:09:27,569][78123] Updated weights for policy 1, policy_version 2220 (0.0009) -[2023-10-12 03:09:27,748][78091] Updated weights for policy 0, policy_version 2240 (0.0008) -[2023-10-12 03:09:27,942][78123] Updated weights for policy 1, policy_version 2230 (0.0009) -[2023-10-12 03:09:28,321][78123] Updated weights for policy 1, policy_version 2240 (0.0008) -[2023-10-12 03:09:30,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 4587520. Throughput: 0: 1586.4, 1: 1591.6. Samples: 1150284. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:09:30,202][77203] Avg episode reward: [(0, '23.380'), (1, '21.900')] -[2023-10-12 03:09:30,203][77792] Saving new best policy, reward=23.380! -[2023-10-12 03:09:32,099][78091] Updated weights for policy 0, policy_version 2250 (0.0007) -[2023-10-12 03:09:32,474][78091] Updated weights for policy 0, policy_version 2260 (0.0008) -[2023-10-12 03:09:32,670][78123] Updated weights for policy 1, policy_version 2250 (0.0010) -[2023-10-12 03:09:32,837][78091] Updated weights for policy 0, policy_version 2270 (0.0007) -[2023-10-12 03:09:33,033][78123] Updated weights for policy 1, policy_version 2260 (0.0009) -[2023-10-12 03:09:33,399][78123] Updated weights for policy 1, policy_version 2270 (0.0008) -[2023-10-12 03:09:35,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 4653056. Throughput: 0: 1591.8, 1: 1579.3. Samples: 1169222. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:09:35,201][77203] Avg episode reward: [(0, '21.340'), (1, '20.670')] -[2023-10-12 03:09:37,326][78091] Updated weights for policy 0, policy_version 2280 (0.0007) -[2023-10-12 03:09:37,672][78123] Updated weights for policy 1, policy_version 2280 (0.0008) -[2023-10-12 03:09:37,694][78091] Updated weights for policy 0, policy_version 2290 (0.0010) -[2023-10-12 03:09:38,045][78123] Updated weights for policy 1, policy_version 2290 (0.0009) -[2023-10-12 03:09:38,070][78091] Updated weights for policy 0, policy_version 2300 (0.0008) -[2023-10-12 03:09:38,417][78123] Updated weights for policy 1, policy_version 2300 (0.0009) -[2023-10-12 03:09:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.1, 300 sec: 12662.9). Total num frames: 4718592. Throughput: 0: 1589.9, 1: 1579.3. Samples: 1188534. Policy #0 lag: (min: 9.0, avg: 13.3, max: 41.0) -[2023-10-12 03:09:40,202][77203] Avg episode reward: [(0, '20.120'), (1, '21.070')] -[2023-10-12 03:09:42,638][78091] Updated weights for policy 0, policy_version 2310 (0.0008) -[2023-10-12 03:09:42,848][78123] Updated weights for policy 1, policy_version 2310 (0.0008) -[2023-10-12 03:09:43,002][78091] Updated weights for policy 0, policy_version 2320 (0.0008) -[2023-10-12 03:09:43,208][78123] Updated weights for policy 1, policy_version 2320 (0.0007) -[2023-10-12 03:09:43,369][78091] Updated weights for policy 0, policy_version 2330 (0.0008) -[2023-10-12 03:09:43,582][78123] Updated weights for policy 1, policy_version 2330 (0.0008) -[2023-10-12 03:09:45,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 4784128. Throughput: 0: 1608.4, 1: 1607.0. Samples: 1198968. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:09:45,202][77203] Avg episode reward: [(0, '22.120'), (1, '20.720')] -[2023-10-12 03:09:47,577][78091] Updated weights for policy 0, policy_version 2340 (0.0008) -[2023-10-12 03:09:47,951][78091] Updated weights for policy 0, policy_version 2350 (0.0007) -[2023-10-12 03:09:48,053][78123] Updated weights for policy 1, policy_version 2340 (0.0009) -[2023-10-12 03:09:48,322][78091] Updated weights for policy 0, policy_version 2360 (0.0009) -[2023-10-12 03:09:48,458][78123] Updated weights for policy 1, policy_version 2350 (0.0008) -[2023-10-12 03:09:48,821][78123] Updated weights for policy 1, policy_version 2360 (0.0008) -[2023-10-12 03:09:50,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 4849664. Throughput: 0: 1589.6, 1: 1585.7. Samples: 1216694. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-12 03:09:50,201][77203] Avg episode reward: [(0, '24.420'), (1, '21.340')] -[2023-10-12 03:09:50,202][77792] Saving new best policy, reward=24.420! -[2023-10-12 03:09:52,666][78091] Updated weights for policy 0, policy_version 2370 (0.0009) -[2023-10-12 03:09:52,896][78123] Updated weights for policy 1, policy_version 2370 (0.0008) -[2023-10-12 03:09:53,082][78091] Updated weights for policy 0, policy_version 2380 (0.0007) -[2023-10-12 03:09:53,257][78123] Updated weights for policy 1, policy_version 2380 (0.0007) -[2023-10-12 03:09:53,454][78091] Updated weights for policy 0, policy_version 2390 (0.0009) -[2023-10-12 03:09:53,633][78123] Updated weights for policy 1, policy_version 2390 (0.0009) -[2023-10-12 03:09:53,827][78091] Updated weights for policy 0, policy_version 2400 (0.0007) -[2023-10-12 03:09:53,996][78123] Updated weights for policy 1, policy_version 2400 (0.0007) -[2023-10-12 03:09:55,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 4915200. Throughput: 0: 1584.8, 1: 1581.9. Samples: 1235628. Policy #0 lag: (min: 31.0, avg: 31.8, max: 51.0) -[2023-10-12 03:09:55,201][77203] Avg episode reward: [(0, '23.090'), (1, '21.580')] -[2023-10-12 03:09:58,331][78091] Updated weights for policy 0, policy_version 2410 (0.0008) -[2023-10-12 03:09:58,417][78123] Updated weights for policy 1, policy_version 2410 (0.0007) -[2023-10-12 03:09:58,701][78091] Updated weights for policy 0, policy_version 2420 (0.0007) -[2023-10-12 03:09:58,785][78123] Updated weights for policy 1, policy_version 2420 (0.0009) -[2023-10-12 03:09:59,061][78091] Updated weights for policy 0, policy_version 2430 (0.0007) -[2023-10-12 03:09:59,149][78123] Updated weights for policy 1, policy_version 2430 (0.0007) -[2023-10-12 03:10:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 4980736. Throughput: 0: 1611.1, 1: 1598.0. Samples: 1246522. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-12 03:10:00,201][77203] Avg episode reward: [(0, '21.340'), (1, '21.290')] -[2023-10-12 03:10:03,091][78091] Updated weights for policy 0, policy_version 2440 (0.0008) -[2023-10-12 03:10:03,454][78123] Updated weights for policy 1, policy_version 2440 (0.0008) -[2023-10-12 03:10:03,473][78091] Updated weights for policy 0, policy_version 2450 (0.0008) -[2023-10-12 03:10:03,821][78123] Updated weights for policy 1, policy_version 2450 (0.0009) -[2023-10-12 03:10:03,850][78091] Updated weights for policy 0, policy_version 2460 (0.0010) -[2023-10-12 03:10:04,185][78123] Updated weights for policy 1, policy_version 2460 (0.0009) -[2023-10-12 03:10:05,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 5046272. Throughput: 0: 1592.4, 1: 1595.1. Samples: 1264754. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-12 03:10:05,202][77203] Avg episode reward: [(0, '21.810'), (1, '22.980')] -[2023-10-12 03:10:05,204][77950] Saving new best policy, reward=22.980! -[2023-10-12 03:10:08,307][78091] Updated weights for policy 0, policy_version 2470 (0.0008) -[2023-10-12 03:10:08,492][78123] Updated weights for policy 1, policy_version 2470 (0.0007) -[2023-10-12 03:10:08,675][78091] Updated weights for policy 0, policy_version 2480 (0.0008) -[2023-10-12 03:10:08,863][78123] Updated weights for policy 1, policy_version 2480 (0.0008) -[2023-10-12 03:10:09,055][78091] Updated weights for policy 0, policy_version 2490 (0.0010) -[2023-10-12 03:10:09,226][78123] Updated weights for policy 1, policy_version 2490 (0.0007) -[2023-10-12 03:10:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 5111808. Throughput: 0: 1585.1, 1: 1579.5. Samples: 1283282. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-12 03:10:10,202][77203] Avg episode reward: [(0, '24.630'), (1, '22.730')] -[2023-10-12 03:10:10,210][77792] Saving new best policy, reward=24.630! -[2023-10-12 03:10:13,549][78091] Updated weights for policy 0, policy_version 2500 (0.0009) -[2023-10-12 03:10:13,652][78123] Updated weights for policy 1, policy_version 2500 (0.0008) -[2023-10-12 03:10:13,913][78091] Updated weights for policy 0, policy_version 2510 (0.0008) -[2023-10-12 03:10:14,016][78123] Updated weights for policy 1, policy_version 2510 (0.0008) -[2023-10-12 03:10:14,288][78091] Updated weights for policy 0, policy_version 2520 (0.0008) -[2023-10-12 03:10:14,383][78123] Updated weights for policy 1, policy_version 2520 (0.0009) -[2023-10-12 03:10:15,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.3, 300 sec: 12885.0). Total num frames: 5177344. Throughput: 0: 1607.4, 1: 1590.6. Samples: 1294194. Policy #0 lag: (min: 18.0, avg: 20.0, max: 49.0) -[2023-10-12 03:10:15,201][77203] Avg episode reward: [(0, '24.280'), (1, '19.470')] -[2023-10-12 03:10:18,647][78091] Updated weights for policy 0, policy_version 2530 (0.0010) -[2023-10-12 03:10:18,841][78123] Updated weights for policy 1, policy_version 2530 (0.0009) -[2023-10-12 03:10:19,012][78091] Updated weights for policy 0, policy_version 2540 (0.0009) -[2023-10-12 03:10:19,208][78123] Updated weights for policy 1, policy_version 2540 (0.0008) -[2023-10-12 03:10:19,371][78091] Updated weights for policy 0, policy_version 2550 (0.0008) -[2023-10-12 03:10:19,578][78123] Updated weights for policy 1, policy_version 2550 (0.0009) -[2023-10-12 03:10:19,742][78091] Updated weights for policy 0, policy_version 2560 (0.0009) -[2023-10-12 03:10:19,939][78123] Updated weights for policy 1, policy_version 2560 (0.0009) -[2023-10-12 03:10:20,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 5242880. Throughput: 0: 1597.4, 1: 1604.1. Samples: 1313292. Policy #0 lag: (min: 31.0, avg: 32.8, max: 60.0) -[2023-10-12 03:10:20,202][77203] Avg episode reward: [(0, '22.350'), (1, '21.700')] -[2023-10-12 03:10:24,051][78091] Updated weights for policy 0, policy_version 2570 (0.0008) -[2023-10-12 03:10:24,311][78123] Updated weights for policy 1, policy_version 2570 (0.0010) -[2023-10-12 03:10:24,416][78091] Updated weights for policy 0, policy_version 2580 (0.0009) -[2023-10-12 03:10:24,684][78123] Updated weights for policy 1, policy_version 2580 (0.0009) -[2023-10-12 03:10:24,786][78091] Updated weights for policy 0, policy_version 2590 (0.0007) -[2023-10-12 03:10:25,049][78123] Updated weights for policy 1, policy_version 2590 (0.0009) -[2023-10-12 03:10:25,201][77203] Fps is (10 sec: 13106.7, 60 sec: 13107.1, 300 sec: 12885.0). Total num frames: 5308416. Throughput: 0: 1582.8, 1: 1583.5. Samples: 1331016. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:10:25,203][77203] Avg episode reward: [(0, '21.370'), (1, '25.100')] -[2023-10-12 03:10:25,213][77950] Saving new best policy, reward=25.100! -[2023-10-12 03:10:29,097][78091] Updated weights for policy 0, policy_version 2600 (0.0008) -[2023-10-12 03:10:29,341][78123] Updated weights for policy 1, policy_version 2600 (0.0009) -[2023-10-12 03:10:29,469][78091] Updated weights for policy 0, policy_version 2610 (0.0008) -[2023-10-12 03:10:29,717][78123] Updated weights for policy 1, policy_version 2610 (0.0008) -[2023-10-12 03:10:29,835][78091] Updated weights for policy 0, policy_version 2620 (0.0009) -[2023-10-12 03:10:30,085][78123] Updated weights for policy 1, policy_version 2620 (0.0007) -[2023-10-12 03:10:30,201][77203] Fps is (10 sec: 9830.6, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 5341184. Throughput: 0: 1590.5, 1: 1572.5. Samples: 1341306. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-12 03:10:30,201][77203] Avg episode reward: [(0, '23.350'), (1, '23.780')] -[2023-10-12 03:10:33,905][78091] Updated weights for policy 0, policy_version 2630 (0.0009) -[2023-10-12 03:10:34,276][78091] Updated weights for policy 0, policy_version 2640 (0.0007) -[2023-10-12 03:10:34,576][78123] Updated weights for policy 1, policy_version 2630 (0.0008) -[2023-10-12 03:10:34,650][78091] Updated weights for policy 0, policy_version 2650 (0.0007) -[2023-10-12 03:10:34,957][78123] Updated weights for policy 1, policy_version 2640 (0.0008) -[2023-10-12 03:10:35,201][77203] Fps is (10 sec: 9830.7, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 5406720. Throughput: 0: 1604.4, 1: 1590.6. Samples: 1360468. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-12 03:10:35,201][77203] Avg episode reward: [(0, '23.970'), (1, '21.690')] -[2023-10-12 03:10:35,319][78123] Updated weights for policy 1, policy_version 2650 (0.0010) -[2023-10-12 03:10:39,061][78091] Updated weights for policy 0, policy_version 2660 (0.0008) -[2023-10-12 03:10:39,436][78091] Updated weights for policy 0, policy_version 2670 (0.0010) -[2023-10-12 03:10:39,730][78123] Updated weights for policy 1, policy_version 2660 (0.0008) -[2023-10-12 03:10:39,813][78091] Updated weights for policy 0, policy_version 2680 (0.0009) -[2023-10-12 03:10:40,094][78123] Updated weights for policy 1, policy_version 2670 (0.0008) -[2023-10-12 03:10:40,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 5472256. Throughput: 0: 1589.4, 1: 1588.4. Samples: 1378632. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-12 03:10:40,202][77203] Avg episode reward: [(0, '22.060'), (1, '21.720')] -[2023-10-12 03:10:40,467][78123] Updated weights for policy 1, policy_version 2680 (0.0008) -[2023-10-12 03:10:43,915][78091] Updated weights for policy 0, policy_version 2690 (0.0009) -[2023-10-12 03:10:44,286][78091] Updated weights for policy 0, policy_version 2700 (0.0008) -[2023-10-12 03:10:44,670][78091] Updated weights for policy 0, policy_version 2710 (0.0008) -[2023-10-12 03:10:44,828][78123] Updated weights for policy 1, policy_version 2690 (0.0008) -[2023-10-12 03:10:45,036][78091] Updated weights for policy 0, policy_version 2720 (0.0008) -[2023-10-12 03:10:45,197][78123] Updated weights for policy 1, policy_version 2700 (0.0008) -[2023-10-12 03:10:45,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 5537792. Throughput: 0: 1581.5, 1: 1567.8. Samples: 1388238. Policy #0 lag: (min: 14.0, avg: 17.4, max: 46.0) -[2023-10-12 03:10:45,201][77203] Avg episode reward: [(0, '22.430'), (1, '23.800')] -[2023-10-12 03:10:45,572][78123] Updated weights for policy 1, policy_version 2710 (0.0009) -[2023-10-12 03:10:45,941][78123] Updated weights for policy 1, policy_version 2720 (0.0007) -[2023-10-12 03:10:49,399][78091] Updated weights for policy 0, policy_version 2730 (0.0008) -[2023-10-12 03:10:49,765][78091] Updated weights for policy 0, policy_version 2740 (0.0009) -[2023-10-12 03:10:50,144][78091] Updated weights for policy 0, policy_version 2750 (0.0008) -[2023-10-12 03:10:50,201][77203] Fps is (10 sec: 9830.6, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 5570560. Throughput: 0: 1599.2, 1: 1576.9. Samples: 1407680. Policy #0 lag: (min: 14.0, avg: 17.4, max: 46.0) -[2023-10-12 03:10:50,201][77203] Avg episode reward: [(0, '22.940'), (1, '24.310')] -[2023-10-12 03:10:50,270][78123] Updated weights for policy 1, policy_version 2730 (0.0009) -[2023-10-12 03:10:50,634][78123] Updated weights for policy 1, policy_version 2740 (0.0009) -[2023-10-12 03:10:51,006][78123] Updated weights for policy 1, policy_version 2750 (0.0008) -[2023-10-12 03:10:54,367][78091] Updated weights for policy 0, policy_version 2760 (0.0008) -[2023-10-12 03:10:54,743][78091] Updated weights for policy 0, policy_version 2770 (0.0010) -[2023-10-12 03:10:55,119][78091] Updated weights for policy 0, policy_version 2780 (0.0007) -[2023-10-12 03:10:55,201][77203] Fps is (10 sec: 9830.2, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 5636096. Throughput: 0: 1595.9, 1: 1588.7. Samples: 1426590. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-12 03:10:55,202][77203] Avg episode reward: [(0, '22.360'), (1, '23.310')] -[2023-10-12 03:10:55,423][78123] Updated weights for policy 1, policy_version 2760 (0.0007) -[2023-10-12 03:10:55,804][78123] Updated weights for policy 1, policy_version 2770 (0.0008) -[2023-10-12 03:10:56,179][78123] Updated weights for policy 1, policy_version 2780 (0.0008) -[2023-10-12 03:10:59,624][78091] Updated weights for policy 0, policy_version 2790 (0.0007) -[2023-10-12 03:11:00,005][78091] Updated weights for policy 0, policy_version 2800 (0.0011) -[2023-10-12 03:11:00,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 5701632. Throughput: 0: 1586.8, 1: 1557.6. Samples: 1435690. Policy #0 lag: (min: 25.0, avg: 28.7, max: 57.0) -[2023-10-12 03:11:00,201][77203] Avg episode reward: [(0, '23.700'), (1, '22.520')] -[2023-10-12 03:11:00,374][78091] Updated weights for policy 0, policy_version 2810 (0.0008) -[2023-10-12 03:11:00,710][78123] Updated weights for policy 1, policy_version 2790 (0.0007) -[2023-10-12 03:11:01,082][78123] Updated weights for policy 1, policy_version 2800 (0.0007) -[2023-10-12 03:11:01,459][78123] Updated weights for policy 1, policy_version 2810 (0.0007) -[2023-10-12 03:11:04,648][78091] Updated weights for policy 0, policy_version 2820 (0.0008) -[2023-10-12 03:11:05,019][78091] Updated weights for policy 0, policy_version 2830 (0.0009) -[2023-10-12 03:11:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 5767168. Throughput: 0: 1591.5, 1: 1557.6. Samples: 1455000. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-12 03:11:05,201][77203] Avg episode reward: [(0, '22.530'), (1, '24.740')] -[2023-10-12 03:11:05,402][78091] Updated weights for policy 0, policy_version 2840 (0.0010) -[2023-10-12 03:11:05,722][78123] Updated weights for policy 1, policy_version 2820 (0.0008) -[2023-10-12 03:11:06,103][78123] Updated weights for policy 1, policy_version 2830 (0.0008) -[2023-10-12 03:11:06,469][78123] Updated weights for policy 1, policy_version 2840 (0.0010) -[2023-10-12 03:11:09,649][78091] Updated weights for policy 0, policy_version 2850 (0.0009) -[2023-10-12 03:11:10,016][78091] Updated weights for policy 0, policy_version 2860 (0.0009) -[2023-10-12 03:11:10,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 5832704. Throughput: 0: 1606.9, 1: 1573.0. Samples: 1474110. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-12 03:11:10,202][77203] Avg episode reward: [(0, '22.530'), (1, '23.410')] -[2023-10-12 03:11:10,210][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000002848_2916352.pth... -[2023-10-12 03:11:10,240][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000001376_1409024.pth -[2023-10-12 03:11:10,390][78091] Updated weights for policy 0, policy_version 2870 (0.0008) -[2023-10-12 03:11:10,755][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000002880_2949120.pth... -[2023-10-12 03:11:10,761][78091] Updated weights for policy 0, policy_version 2880 (0.0007) -[2023-10-12 03:11:10,784][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000001376_1409024.pth -[2023-10-12 03:11:11,057][78123] Updated weights for policy 1, policy_version 2850 (0.0009) -[2023-10-12 03:11:11,420][78123] Updated weights for policy 1, policy_version 2860 (0.0007) -[2023-10-12 03:11:11,793][78123] Updated weights for policy 1, policy_version 2870 (0.0010) -[2023-10-12 03:11:12,154][78123] Updated weights for policy 1, policy_version 2880 (0.0011) -[2023-10-12 03:11:15,135][78091] Updated weights for policy 0, policy_version 2890 (0.0010) -[2023-10-12 03:11:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 5898240. Throughput: 0: 1588.9, 1: 1555.5. Samples: 1482808. Policy #0 lag: (min: 16.0, avg: 39.5, max: 48.0) -[2023-10-12 03:11:15,202][77203] Avg episode reward: [(0, '21.910'), (1, '22.490')] -[2023-10-12 03:11:15,510][78091] Updated weights for policy 0, policy_version 2900 (0.0010) -[2023-10-12 03:11:15,884][78091] Updated weights for policy 0, policy_version 2910 (0.0011) -[2023-10-12 03:11:16,568][78123] Updated weights for policy 1, policy_version 2890 (0.0009) -[2023-10-12 03:11:16,934][78123] Updated weights for policy 1, policy_version 2900 (0.0007) -[2023-10-12 03:11:17,305][78123] Updated weights for policy 1, policy_version 2910 (0.0007) -[2023-10-12 03:11:20,201][77203] Fps is (10 sec: 13107.6, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 5963776. Throughput: 0: 1590.0, 1: 1553.9. Samples: 1501944. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-12 03:11:20,201][77203] Avg episode reward: [(0, '23.360'), (1, '23.450')] -[2023-10-12 03:11:20,364][78091] Updated weights for policy 0, policy_version 2920 (0.0009) -[2023-10-12 03:11:20,738][78091] Updated weights for policy 0, policy_version 2930 (0.0008) -[2023-10-12 03:11:21,110][78091] Updated weights for policy 0, policy_version 2940 (0.0009) -[2023-10-12 03:11:21,655][78123] Updated weights for policy 1, policy_version 2920 (0.0009) -[2023-10-12 03:11:22,025][78123] Updated weights for policy 1, policy_version 2930 (0.0009) -[2023-10-12 03:11:22,396][78123] Updated weights for policy 1, policy_version 2940 (0.0010) -[2023-10-12 03:11:25,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 6029312. Throughput: 0: 1609.6, 1: 1564.1. Samples: 1521450. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-12 03:11:25,201][77203] Avg episode reward: [(0, '24.050'), (1, '22.590')] -[2023-10-12 03:11:25,621][78091] Updated weights for policy 0, policy_version 2950 (0.0008) -[2023-10-12 03:11:26,002][78091] Updated weights for policy 0, policy_version 2960 (0.0010) -[2023-10-12 03:11:26,385][78091] Updated weights for policy 0, policy_version 2970 (0.0009) -[2023-10-12 03:11:26,740][78123] Updated weights for policy 1, policy_version 2950 (0.0009) -[2023-10-12 03:11:27,110][78123] Updated weights for policy 1, policy_version 2960 (0.0007) -[2023-10-12 03:11:27,474][78123] Updated weights for policy 1, policy_version 2970 (0.0009) -[2023-10-12 03:11:30,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 6094848. Throughput: 0: 1585.6, 1: 1563.9. Samples: 1529966. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-12 03:11:30,202][77203] Avg episode reward: [(0, '22.190'), (1, '21.190')] -[2023-10-12 03:11:30,755][78091] Updated weights for policy 0, policy_version 2980 (0.0009) -[2023-10-12 03:11:31,119][78091] Updated weights for policy 0, policy_version 2990 (0.0007) -[2023-10-12 03:11:31,487][78091] Updated weights for policy 0, policy_version 3000 (0.0007) -[2023-10-12 03:11:31,811][78123] Updated weights for policy 1, policy_version 2980 (0.0008) -[2023-10-12 03:11:32,178][78123] Updated weights for policy 1, policy_version 2990 (0.0008) -[2023-10-12 03:11:32,549][78123] Updated weights for policy 1, policy_version 3000 (0.0010) -[2023-10-12 03:11:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 6160384. Throughput: 0: 1587.7, 1: 1564.1. Samples: 1549512. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:11:35,202][77203] Avg episode reward: [(0, '22.450'), (1, '22.620')] -[2023-10-12 03:11:35,762][78091] Updated weights for policy 0, policy_version 3010 (0.0007) -[2023-10-12 03:11:36,134][78091] Updated weights for policy 0, policy_version 3020 (0.0007) -[2023-10-12 03:11:36,498][78091] Updated weights for policy 0, policy_version 3030 (0.0008) -[2023-10-12 03:11:36,853][78123] Updated weights for policy 1, policy_version 3010 (0.0010) -[2023-10-12 03:11:36,873][78091] Updated weights for policy 0, policy_version 3040 (0.0008) -[2023-10-12 03:11:37,223][78123] Updated weights for policy 1, policy_version 3020 (0.0008) -[2023-10-12 03:11:37,586][78123] Updated weights for policy 1, policy_version 3030 (0.0008) -[2023-10-12 03:11:37,955][78123] Updated weights for policy 1, policy_version 3040 (0.0007) -[2023-10-12 03:11:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 6225920. Throughput: 0: 1598.5, 1: 1567.3. Samples: 1569052. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-12 03:11:40,205][77203] Avg episode reward: [(0, '23.450'), (1, '23.170')] -[2023-10-12 03:11:41,214][78091] Updated weights for policy 0, policy_version 3050 (0.0009) -[2023-10-12 03:11:41,592][78091] Updated weights for policy 0, policy_version 3060 (0.0009) -[2023-10-12 03:11:41,957][78091] Updated weights for policy 0, policy_version 3070 (0.0007) -[2023-10-12 03:11:42,457][78123] Updated weights for policy 1, policy_version 3050 (0.0010) -[2023-10-12 03:11:42,821][78123] Updated weights for policy 1, policy_version 3060 (0.0010) -[2023-10-12 03:11:43,184][78123] Updated weights for policy 1, policy_version 3070 (0.0010) -[2023-10-12 03:11:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 6291456. Throughput: 0: 1581.4, 1: 1580.5. Samples: 1577976. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:11:45,201][77203] Avg episode reward: [(0, '23.510'), (1, '23.880')] -[2023-10-12 03:11:46,306][78091] Updated weights for policy 0, policy_version 3080 (0.0007) -[2023-10-12 03:11:46,675][78091] Updated weights for policy 0, policy_version 3090 (0.0007) -[2023-10-12 03:11:47,058][78091] Updated weights for policy 0, policy_version 3100 (0.0008) -[2023-10-12 03:11:47,576][78123] Updated weights for policy 1, policy_version 3080 (0.0009) -[2023-10-12 03:11:47,948][78123] Updated weights for policy 1, policy_version 3090 (0.0007) -[2023-10-12 03:11:48,307][78123] Updated weights for policy 1, policy_version 3100 (0.0008) -[2023-10-12 03:11:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 6356992. Throughput: 0: 1586.5, 1: 1567.7. Samples: 1596942. Policy #0 lag: (min: 3.0, avg: 5.9, max: 33.0) -[2023-10-12 03:11:50,201][77203] Avg episode reward: [(0, '22.620'), (1, '22.120')] -[2023-10-12 03:11:51,381][78091] Updated weights for policy 0, policy_version 3110 (0.0007) -[2023-10-12 03:11:51,755][78091] Updated weights for policy 0, policy_version 3120 (0.0008) -[2023-10-12 03:11:52,116][78091] Updated weights for policy 0, policy_version 3130 (0.0007) -[2023-10-12 03:11:52,639][78123] Updated weights for policy 1, policy_version 3110 (0.0008) -[2023-10-12 03:11:53,006][78123] Updated weights for policy 1, policy_version 3120 (0.0009) -[2023-10-12 03:11:53,377][78123] Updated weights for policy 1, policy_version 3130 (0.0010) -[2023-10-12 03:11:55,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 6422528. Throughput: 0: 1588.7, 1: 1571.8. Samples: 1616330. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-12 03:11:55,202][77203] Avg episode reward: [(0, '22.260'), (1, '23.000')] -[2023-10-12 03:11:56,251][78091] Updated weights for policy 0, policy_version 3140 (0.0008) -[2023-10-12 03:11:56,629][78091] Updated weights for policy 0, policy_version 3150 (0.0008) -[2023-10-12 03:11:56,994][78091] Updated weights for policy 0, policy_version 3160 (0.0009) -[2023-10-12 03:11:57,744][78123] Updated weights for policy 1, policy_version 3140 (0.0010) -[2023-10-12 03:11:58,101][78123] Updated weights for policy 1, policy_version 3150 (0.0009) -[2023-10-12 03:11:58,475][78123] Updated weights for policy 1, policy_version 3160 (0.0008) -[2023-10-12 03:12:00,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 6488064. Throughput: 0: 1584.4, 1: 1597.1. Samples: 1625978. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-12 03:12:00,202][77203] Avg episode reward: [(0, '23.530'), (1, '25.320')] -[2023-10-12 03:12:00,203][77950] Saving new best policy, reward=25.320! -[2023-10-12 03:12:01,485][78091] Updated weights for policy 0, policy_version 3170 (0.0011) -[2023-10-12 03:12:01,863][78091] Updated weights for policy 0, policy_version 3180 (0.0010) -[2023-10-12 03:12:02,238][78091] Updated weights for policy 0, policy_version 3190 (0.0010) -[2023-10-12 03:12:02,610][78091] Updated weights for policy 0, policy_version 3200 (0.0008) -[2023-10-12 03:12:02,875][78123] Updated weights for policy 1, policy_version 3170 (0.0008) -[2023-10-12 03:12:03,241][78123] Updated weights for policy 1, policy_version 3180 (0.0010) -[2023-10-12 03:12:03,609][78123] Updated weights for policy 1, policy_version 3190 (0.0009) -[2023-10-12 03:12:03,984][78123] Updated weights for policy 1, policy_version 3200 (0.0009) -[2023-10-12 03:12:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 6553600. Throughput: 0: 1587.4, 1: 1585.8. Samples: 1644738. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 03:12:05,202][77203] Avg episode reward: [(0, '24.440'), (1, '22.390')] -[2023-10-12 03:12:06,814][78091] Updated weights for policy 0, policy_version 3210 (0.0010) -[2023-10-12 03:12:07,197][78091] Updated weights for policy 0, policy_version 3220 (0.0009) -[2023-10-12 03:12:07,556][78091] Updated weights for policy 0, policy_version 3230 (0.0009) -[2023-10-12 03:12:08,319][78123] Updated weights for policy 1, policy_version 3210 (0.0007) -[2023-10-12 03:12:08,688][78123] Updated weights for policy 1, policy_version 3220 (0.0009) -[2023-10-12 03:12:09,064][78123] Updated weights for policy 1, policy_version 3230 (0.0008) -[2023-10-12 03:12:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 6619136. Throughput: 0: 1585.6, 1: 1579.0. Samples: 1663860. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:12:10,202][77203] Avg episode reward: [(0, '22.650'), (1, '21.280')] -[2023-10-12 03:12:11,929][78091] Updated weights for policy 0, policy_version 3240 (0.0009) -[2023-10-12 03:12:12,303][78091] Updated weights for policy 0, policy_version 3250 (0.0009) -[2023-10-12 03:12:12,674][78091] Updated weights for policy 0, policy_version 3260 (0.0010) -[2023-10-12 03:12:13,226][78123] Updated weights for policy 1, policy_version 3240 (0.0010) -[2023-10-12 03:12:13,601][78123] Updated weights for policy 1, policy_version 3250 (0.0007) -[2023-10-12 03:12:13,971][78123] Updated weights for policy 1, policy_version 3260 (0.0008) -[2023-10-12 03:12:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 6684672. Throughput: 0: 1585.3, 1: 1605.4. Samples: 1673546. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-12 03:12:15,202][77203] Avg episode reward: [(0, '21.300'), (1, '22.830')] -[2023-10-12 03:12:17,055][78091] Updated weights for policy 0, policy_version 3270 (0.0008) -[2023-10-12 03:12:17,434][78091] Updated weights for policy 0, policy_version 3280 (0.0010) -[2023-10-12 03:12:17,803][78091] Updated weights for policy 0, policy_version 3290 (0.0010) -[2023-10-12 03:12:18,220][78123] Updated weights for policy 1, policy_version 3270 (0.0007) -[2023-10-12 03:12:18,591][78123] Updated weights for policy 1, policy_version 3280 (0.0009) -[2023-10-12 03:12:18,960][78123] Updated weights for policy 1, policy_version 3290 (0.0008) -[2023-10-12 03:12:20,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 6750208. Throughput: 0: 1578.3, 1: 1591.6. Samples: 1692160. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:12:20,201][77203] Avg episode reward: [(0, '22.690'), (1, '23.340')] -[2023-10-12 03:12:22,264][78091] Updated weights for policy 0, policy_version 3300 (0.0008) -[2023-10-12 03:12:22,627][78091] Updated weights for policy 0, policy_version 3310 (0.0007) -[2023-10-12 03:12:22,998][78091] Updated weights for policy 0, policy_version 3320 (0.0008) -[2023-10-12 03:12:23,276][78123] Updated weights for policy 1, policy_version 3300 (0.0008) -[2023-10-12 03:12:23,635][78123] Updated weights for policy 1, policy_version 3310 (0.0009) -[2023-10-12 03:12:23,998][78123] Updated weights for policy 1, policy_version 3320 (0.0007) -[2023-10-12 03:12:25,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 6815744. Throughput: 0: 1573.2, 1: 1584.2. Samples: 1711134. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:12:25,201][77203] Avg episode reward: [(0, '22.730'), (1, '21.890')] -[2023-10-12 03:12:27,408][78091] Updated weights for policy 0, policy_version 3330 (0.0008) -[2023-10-12 03:12:27,779][78091] Updated weights for policy 0, policy_version 3340 (0.0010) -[2023-10-12 03:12:28,152][78091] Updated weights for policy 0, policy_version 3350 (0.0008) -[2023-10-12 03:12:28,514][78123] Updated weights for policy 1, policy_version 3330 (0.0008) -[2023-10-12 03:12:28,520][78091] Updated weights for policy 0, policy_version 3360 (0.0007) -[2023-10-12 03:12:28,881][78123] Updated weights for policy 1, policy_version 3340 (0.0009) -[2023-10-12 03:12:29,260][78123] Updated weights for policy 1, policy_version 3350 (0.0008) -[2023-10-12 03:12:29,624][78123] Updated weights for policy 1, policy_version 3360 (0.0007) -[2023-10-12 03:12:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 6881280. Throughput: 0: 1591.1, 1: 1601.0. Samples: 1721618. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-12 03:12:30,202][77203] Avg episode reward: [(0, '22.240'), (1, '21.830')] -[2023-10-12 03:12:32,837][78091] Updated weights for policy 0, policy_version 3370 (0.0007) -[2023-10-12 03:12:33,209][78091] Updated weights for policy 0, policy_version 3380 (0.0008) -[2023-10-12 03:12:33,580][78091] Updated weights for policy 0, policy_version 3390 (0.0010) -[2023-10-12 03:12:34,044][78123] Updated weights for policy 1, policy_version 3370 (0.0010) -[2023-10-12 03:12:34,413][78123] Updated weights for policy 1, policy_version 3380 (0.0008) -[2023-10-12 03:12:34,795][78123] Updated weights for policy 1, policy_version 3390 (0.0010) -[2023-10-12 03:12:35,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 6946816. Throughput: 0: 1570.3, 1: 1611.5. Samples: 1740126. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:12:35,202][77203] Avg episode reward: [(0, '22.690'), (1, '20.990')] -[2023-10-12 03:12:37,938][78091] Updated weights for policy 0, policy_version 3400 (0.0009) -[2023-10-12 03:12:38,302][78091] Updated weights for policy 0, policy_version 3410 (0.0009) -[2023-10-12 03:12:38,674][78091] Updated weights for policy 0, policy_version 3420 (0.0009) -[2023-10-12 03:12:39,127][78123] Updated weights for policy 1, policy_version 3400 (0.0008) -[2023-10-12 03:12:39,504][78123] Updated weights for policy 1, policy_version 3410 (0.0010) -[2023-10-12 03:12:39,875][78123] Updated weights for policy 1, policy_version 3420 (0.0009) -[2023-10-12 03:12:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 7012352. Throughput: 0: 1571.3, 1: 1591.5. Samples: 1758654. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) -[2023-10-12 03:12:40,202][77203] Avg episode reward: [(0, '23.050'), (1, '22.690')] -[2023-10-12 03:12:42,974][78091] Updated weights for policy 0, policy_version 3430 (0.0009) -[2023-10-12 03:12:43,350][78091] Updated weights for policy 0, policy_version 3440 (0.0011) -[2023-10-12 03:12:43,716][78091] Updated weights for policy 0, policy_version 3450 (0.0011) -[2023-10-12 03:12:44,273][78123] Updated weights for policy 1, policy_version 3430 (0.0010) -[2023-10-12 03:12:44,650][78123] Updated weights for policy 1, policy_version 3440 (0.0007) -[2023-10-12 03:12:45,014][78123] Updated weights for policy 1, policy_version 3450 (0.0008) -[2023-10-12 03:12:45,201][77203] Fps is (10 sec: 9830.6, 60 sec: 12561.1, 300 sec: 12551.8). Total num frames: 7045120. Throughput: 0: 1593.2, 1: 1586.0. Samples: 1769044. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) -[2023-10-12 03:12:45,201][77203] Avg episode reward: [(0, '23.100'), (1, '22.100')] -[2023-10-12 03:12:47,903][78091] Updated weights for policy 0, policy_version 3460 (0.0008) -[2023-10-12 03:12:48,271][78091] Updated weights for policy 0, policy_version 3470 (0.0007) -[2023-10-12 03:12:48,649][78091] Updated weights for policy 0, policy_version 3480 (0.0009) -[2023-10-12 03:12:49,371][78123] Updated weights for policy 1, policy_version 3460 (0.0010) -[2023-10-12 03:12:49,735][78123] Updated weights for policy 1, policy_version 3470 (0.0008) -[2023-10-12 03:12:50,115][78123] Updated weights for policy 1, policy_version 3480 (0.0009) -[2023-10-12 03:12:50,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 7110656. Throughput: 0: 1581.9, 1: 1599.0. Samples: 1787876. Policy #0 lag: (min: 7.0, avg: 10.8, max: 39.0) -[2023-10-12 03:12:50,201][77203] Avg episode reward: [(0, '24.000'), (1, '20.720')] -[2023-10-12 03:12:52,996][78091] Updated weights for policy 0, policy_version 3490 (0.0010) -[2023-10-12 03:12:53,374][78091] Updated weights for policy 0, policy_version 3500 (0.0009) -[2023-10-12 03:12:53,750][78091] Updated weights for policy 0, policy_version 3510 (0.0009) -[2023-10-12 03:12:54,119][78091] Updated weights for policy 0, policy_version 3520 (0.0008) -[2023-10-12 03:12:54,399][78123] Updated weights for policy 1, policy_version 3490 (0.0008) -[2023-10-12 03:12:54,795][78123] Updated weights for policy 1, policy_version 3500 (0.0008) -[2023-10-12 03:12:55,163][78123] Updated weights for policy 1, policy_version 3510 (0.0008) -[2023-10-12 03:12:55,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 7176192. Throughput: 0: 1579.3, 1: 1596.0. Samples: 1806748. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:12:55,202][77203] Avg episode reward: [(0, '23.660'), (1, '21.350')] -[2023-10-12 03:12:55,526][78123] Updated weights for policy 1, policy_version 3520 (0.0007) -[2023-10-12 03:12:58,520][78091] Updated weights for policy 0, policy_version 3530 (0.0008) -[2023-10-12 03:12:58,896][78091] Updated weights for policy 0, policy_version 3540 (0.0008) -[2023-10-12 03:12:59,264][78091] Updated weights for policy 0, policy_version 3550 (0.0008) -[2023-10-12 03:12:59,745][78123] Updated weights for policy 1, policy_version 3530 (0.0008) -[2023-10-12 03:13:00,127][78123] Updated weights for policy 1, policy_version 3540 (0.0009) -[2023-10-12 03:13:00,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 7241728. Throughput: 0: 1613.2, 1: 1576.2. Samples: 1817068. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:13:00,202][77203] Avg episode reward: [(0, '21.810'), (1, '21.770')] -[2023-10-12 03:13:00,490][78123] Updated weights for policy 1, policy_version 3550 (0.0009) -[2023-10-12 03:13:03,403][78091] Updated weights for policy 0, policy_version 3560 (0.0008) -[2023-10-12 03:13:03,767][78091] Updated weights for policy 0, policy_version 3570 (0.0010) -[2023-10-12 03:13:04,145][78091] Updated weights for policy 0, policy_version 3580 (0.0009) -[2023-10-12 03:13:05,010][78123] Updated weights for policy 1, policy_version 3560 (0.0010) -[2023-10-12 03:13:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 7307264. Throughput: 0: 1600.3, 1: 1593.5. Samples: 1835880. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:13:05,202][77203] Avg episode reward: [(0, '23.660'), (1, '20.120')] -[2023-10-12 03:13:05,385][78123] Updated weights for policy 1, policy_version 3570 (0.0010) -[2023-10-12 03:13:05,748][78123] Updated weights for policy 1, policy_version 3580 (0.0009) -[2023-10-12 03:13:08,442][78091] Updated weights for policy 0, policy_version 3590 (0.0008) -[2023-10-12 03:13:08,802][78091] Updated weights for policy 0, policy_version 3600 (0.0007) -[2023-10-12 03:13:09,176][78091] Updated weights for policy 0, policy_version 3610 (0.0007) -[2023-10-12 03:13:10,136][78123] Updated weights for policy 1, policy_version 3590 (0.0009) -[2023-10-12 03:13:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 7372800. Throughput: 0: 1595.0, 1: 1597.0. Samples: 1854774. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:13:10,201][77203] Avg episode reward: [(0, '25.100'), (1, '21.940')] -[2023-10-12 03:13:10,209][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000003616_3702784.pth... -[2023-10-12 03:13:10,244][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000002112_2162688.pth -[2023-10-12 03:13:10,248][77792] Saving new best policy, reward=25.100! -[2023-10-12 03:13:10,500][78123] Updated weights for policy 1, policy_version 3600 (0.0010) -[2023-10-12 03:13:10,871][78123] Updated weights for policy 1, policy_version 3610 (0.0008) -[2023-10-12 03:13:11,086][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000003616_3702784.pth... -[2023-10-12 03:13:11,127][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000002112_2162688.pth -[2023-10-12 03:13:13,390][78091] Updated weights for policy 0, policy_version 3620 (0.0008) -[2023-10-12 03:13:13,761][78091] Updated weights for policy 0, policy_version 3630 (0.0008) -[2023-10-12 03:13:14,132][78091] Updated weights for policy 0, policy_version 3640 (0.0009) -[2023-10-12 03:13:15,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 7438336. Throughput: 0: 1607.3, 1: 1568.4. Samples: 1864524. Policy #0 lag: (min: 31.0, avg: 31.2, max: 41.0) -[2023-10-12 03:13:15,201][77203] Avg episode reward: [(0, '21.830'), (1, '22.170')] -[2023-10-12 03:13:15,353][78123] Updated weights for policy 1, policy_version 3620 (0.0008) -[2023-10-12 03:13:15,708][78123] Updated weights for policy 1, policy_version 3630 (0.0008) -[2023-10-12 03:13:16,076][78123] Updated weights for policy 1, policy_version 3640 (0.0010) -[2023-10-12 03:13:18,524][78091] Updated weights for policy 0, policy_version 3650 (0.0008) -[2023-10-12 03:13:18,891][78091] Updated weights for policy 0, policy_version 3660 (0.0010) -[2023-10-12 03:13:19,269][78091] Updated weights for policy 0, policy_version 3670 (0.0009) -[2023-10-12 03:13:19,641][78091] Updated weights for policy 0, policy_version 3680 (0.0009) -[2023-10-12 03:13:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 7503872. Throughput: 0: 1617.7, 1: 1569.8. Samples: 1883564. Policy #0 lag: (min: 31.0, avg: 31.2, max: 41.0) -[2023-10-12 03:13:20,202][77203] Avg episode reward: [(0, '21.180'), (1, '22.460')] -[2023-10-12 03:13:20,438][78123] Updated weights for policy 1, policy_version 3650 (0.0008) -[2023-10-12 03:13:20,815][78123] Updated weights for policy 1, policy_version 3660 (0.0008) -[2023-10-12 03:13:21,178][78123] Updated weights for policy 1, policy_version 3670 (0.0008) -[2023-10-12 03:13:21,559][78123] Updated weights for policy 1, policy_version 3680 (0.0010) -[2023-10-12 03:13:23,935][78091] Updated weights for policy 0, policy_version 3690 (0.0009) -[2023-10-12 03:13:24,302][78091] Updated weights for policy 0, policy_version 3700 (0.0009) -[2023-10-12 03:13:24,680][78091] Updated weights for policy 0, policy_version 3710 (0.0008) -[2023-10-12 03:13:25,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 7569408. Throughput: 0: 1602.8, 1: 1591.4. Samples: 1902394. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:13:25,202][77203] Avg episode reward: [(0, '22.940'), (1, '23.530')] -[2023-10-12 03:13:25,860][78123] Updated weights for policy 1, policy_version 3690 (0.0008) -[2023-10-12 03:13:26,235][78123] Updated weights for policy 1, policy_version 3700 (0.0008) -[2023-10-12 03:13:26,598][78123] Updated weights for policy 1, policy_version 3710 (0.0007) -[2023-10-12 03:13:28,825][78091] Updated weights for policy 0, policy_version 3720 (0.0009) -[2023-10-12 03:13:29,194][78091] Updated weights for policy 0, policy_version 3730 (0.0010) -[2023-10-12 03:13:29,569][78091] Updated weights for policy 0, policy_version 3740 (0.0009) -[2023-10-12 03:13:30,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 7634944. Throughput: 0: 1605.6, 1: 1575.4. Samples: 1912186. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:13:30,201][77203] Avg episode reward: [(0, '24.680'), (1, '22.510')] -[2023-10-12 03:13:31,003][78123] Updated weights for policy 1, policy_version 3720 (0.0010) -[2023-10-12 03:13:31,368][78123] Updated weights for policy 1, policy_version 3730 (0.0009) -[2023-10-12 03:13:31,729][78123] Updated weights for policy 1, policy_version 3740 (0.0007) -[2023-10-12 03:13:33,811][78091] Updated weights for policy 0, policy_version 3750 (0.0009) -[2023-10-12 03:13:34,185][78091] Updated weights for policy 0, policy_version 3760 (0.0010) -[2023-10-12 03:13:34,563][78091] Updated weights for policy 0, policy_version 3770 (0.0008) -[2023-10-12 03:13:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 7700480. Throughput: 0: 1613.3, 1: 1576.8. Samples: 1931432. Policy #0 lag: (min: 16.0, avg: 26.1, max: 48.0) -[2023-10-12 03:13:35,202][77203] Avg episode reward: [(0, '23.820'), (1, '21.180')] -[2023-10-12 03:13:36,220][78123] Updated weights for policy 1, policy_version 3750 (0.0008) -[2023-10-12 03:13:36,595][78123] Updated weights for policy 1, policy_version 3760 (0.0008) -[2023-10-12 03:13:36,965][78123] Updated weights for policy 1, policy_version 3770 (0.0009) -[2023-10-12 03:13:38,888][78091] Updated weights for policy 0, policy_version 3780 (0.0009) -[2023-10-12 03:13:39,264][78091] Updated weights for policy 0, policy_version 3790 (0.0008) -[2023-10-12 03:13:39,642][78091] Updated weights for policy 0, policy_version 3800 (0.0010) -[2023-10-12 03:13:40,201][77203] Fps is (10 sec: 13106.7, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 7766016. Throughput: 0: 1602.6, 1: 1586.2. Samples: 1950242. Policy #0 lag: (min: 31.0, avg: 31.5, max: 47.0) -[2023-10-12 03:13:40,202][77203] Avg episode reward: [(0, '21.820'), (1, '24.900')] -[2023-10-12 03:13:41,283][78123] Updated weights for policy 1, policy_version 3780 (0.0007) -[2023-10-12 03:13:41,689][78123] Updated weights for policy 1, policy_version 3790 (0.0008) -[2023-10-12 03:13:42,056][78123] Updated weights for policy 1, policy_version 3800 (0.0007) -[2023-10-12 03:13:44,051][78091] Updated weights for policy 0, policy_version 3810 (0.0009) -[2023-10-12 03:13:44,458][78091] Updated weights for policy 0, policy_version 3820 (0.0010) -[2023-10-12 03:13:44,832][78091] Updated weights for policy 0, policy_version 3830 (0.0008) -[2023-10-12 03:13:45,201][77203] Fps is (10 sec: 9830.6, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 7798784. Throughput: 0: 1595.4, 1: 1574.4. Samples: 1959708. Policy #0 lag: (min: 31.0, avg: 31.5, max: 47.0) -[2023-10-12 03:13:45,202][77203] Avg episode reward: [(0, '21.330'), (1, '21.680')] -[2023-10-12 03:13:45,207][78091] Updated weights for policy 0, policy_version 3840 (0.0007) -[2023-10-12 03:13:46,269][78123] Updated weights for policy 1, policy_version 3810 (0.0008) -[2023-10-12 03:13:46,646][78123] Updated weights for policy 1, policy_version 3820 (0.0010) -[2023-10-12 03:13:47,006][78123] Updated weights for policy 1, policy_version 3830 (0.0007) -[2023-10-12 03:13:47,377][78123] Updated weights for policy 1, policy_version 3840 (0.0009) -[2023-10-12 03:13:49,500][78091] Updated weights for policy 0, policy_version 3850 (0.0009) -[2023-10-12 03:13:49,871][78091] Updated weights for policy 0, policy_version 3860 (0.0009) -[2023-10-12 03:13:50,201][77203] Fps is (10 sec: 9830.6, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 7864320. Throughput: 0: 1613.7, 1: 1570.3. Samples: 1979160. Policy #0 lag: (min: 31.0, avg: 31.5, max: 47.0) -[2023-10-12 03:13:50,202][77203] Avg episode reward: [(0, '22.670'), (1, '21.590')] -[2023-10-12 03:13:50,244][78091] Updated weights for policy 0, policy_version 3870 (0.0008) -[2023-10-12 03:13:51,767][78123] Updated weights for policy 1, policy_version 3850 (0.0007) -[2023-10-12 03:13:52,139][78123] Updated weights for policy 1, policy_version 3860 (0.0007) -[2023-10-12 03:13:52,501][78123] Updated weights for policy 1, policy_version 3870 (0.0011) -[2023-10-12 03:13:54,552][78091] Updated weights for policy 0, policy_version 3880 (0.0008) -[2023-10-12 03:13:54,927][78091] Updated weights for policy 0, policy_version 3890 (0.0008) -[2023-10-12 03:13:55,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 7929856. Throughput: 0: 1612.3, 1: 1573.1. Samples: 1998118. Policy #0 lag: (min: 17.0, avg: 26.9, max: 49.0) -[2023-10-12 03:13:55,201][77203] Avg episode reward: [(0, '25.560'), (1, '22.590')] -[2023-10-12 03:13:55,297][78091] Updated weights for policy 0, policy_version 3900 (0.0010) -[2023-10-12 03:13:55,443][77792] Saving new best policy, reward=25.560! -[2023-10-12 03:13:56,932][78123] Updated weights for policy 1, policy_version 3880 (0.0008) -[2023-10-12 03:13:57,291][78123] Updated weights for policy 1, policy_version 3890 (0.0009) -[2023-10-12 03:13:57,660][78123] Updated weights for policy 1, policy_version 3900 (0.0008) -[2023-10-12 03:13:59,587][78091] Updated weights for policy 0, policy_version 3910 (0.0008) -[2023-10-12 03:13:59,954][78091] Updated weights for policy 0, policy_version 3920 (0.0008) -[2023-10-12 03:14:00,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 7995392. Throughput: 0: 1596.4, 1: 1581.1. Samples: 2007510. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:14:00,201][77203] Avg episode reward: [(0, '22.210'), (1, '24.100')] -[2023-10-12 03:14:00,320][78091] Updated weights for policy 0, policy_version 3930 (0.0009) -[2023-10-12 03:14:01,826][78123] Updated weights for policy 1, policy_version 3910 (0.0007) -[2023-10-12 03:14:02,192][78123] Updated weights for policy 1, policy_version 3920 (0.0007) -[2023-10-12 03:14:02,562][78123] Updated weights for policy 1, policy_version 3930 (0.0010) -[2023-10-12 03:14:04,548][78091] Updated weights for policy 0, policy_version 3940 (0.0008) -[2023-10-12 03:14:04,919][78091] Updated weights for policy 0, policy_version 3950 (0.0008) -[2023-10-12 03:14:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 8060928. Throughput: 0: 1606.2, 1: 1580.7. Samples: 2026974. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:14:05,201][77203] Avg episode reward: [(0, '21.260'), (1, '21.640')] -[2023-10-12 03:14:05,294][78091] Updated weights for policy 0, policy_version 3960 (0.0009) -[2023-10-12 03:14:06,890][78123] Updated weights for policy 1, policy_version 3940 (0.0008) -[2023-10-12 03:14:07,256][78123] Updated weights for policy 1, policy_version 3950 (0.0008) -[2023-10-12 03:14:07,618][78123] Updated weights for policy 1, policy_version 3960 (0.0010) -[2023-10-12 03:14:09,538][78091] Updated weights for policy 0, policy_version 3970 (0.0007) -[2023-10-12 03:14:09,911][78091] Updated weights for policy 0, policy_version 3980 (0.0007) -[2023-10-12 03:14:10,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 8126464. Throughput: 0: 1614.6, 1: 1581.6. Samples: 2046220. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:14:10,201][77203] Avg episode reward: [(0, '23.450'), (1, '22.480')] -[2023-10-12 03:14:10,289][78091] Updated weights for policy 0, policy_version 3990 (0.0009) -[2023-10-12 03:14:10,656][78091] Updated weights for policy 0, policy_version 4000 (0.0009) -[2023-10-12 03:14:11,831][78123] Updated weights for policy 1, policy_version 3970 (0.0010) -[2023-10-12 03:14:12,204][78123] Updated weights for policy 1, policy_version 3980 (0.0009) -[2023-10-12 03:14:12,571][78123] Updated weights for policy 1, policy_version 3990 (0.0009) -[2023-10-12 03:14:12,934][78123] Updated weights for policy 1, policy_version 4000 (0.0008) -[2023-10-12 03:14:14,922][78091] Updated weights for policy 0, policy_version 4010 (0.0009) -[2023-10-12 03:14:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 8192000. Throughput: 0: 1596.6, 1: 1587.4. Samples: 2055468. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:14:15,202][77203] Avg episode reward: [(0, '24.550'), (1, '23.880')] -[2023-10-12 03:14:15,291][78091] Updated weights for policy 0, policy_version 4020 (0.0008) -[2023-10-12 03:14:15,661][78091] Updated weights for policy 0, policy_version 4030 (0.0008) -[2023-10-12 03:14:17,348][78123] Updated weights for policy 1, policy_version 4010 (0.0007) -[2023-10-12 03:14:17,727][78123] Updated weights for policy 1, policy_version 4020 (0.0007) -[2023-10-12 03:14:18,103][78123] Updated weights for policy 1, policy_version 4030 (0.0008) -[2023-10-12 03:14:20,078][78091] Updated weights for policy 0, policy_version 4040 (0.0007) -[2023-10-12 03:14:20,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 8257536. Throughput: 0: 1600.2, 1: 1584.1. Samples: 2074728. Policy #0 lag: (min: 31.0, avg: 32.6, max: 58.0) -[2023-10-12 03:14:20,202][77203] Avg episode reward: [(0, '23.250'), (1, '22.240')] -[2023-10-12 03:14:20,444][78091] Updated weights for policy 0, policy_version 4050 (0.0007) -[2023-10-12 03:14:20,820][78091] Updated weights for policy 0, policy_version 4060 (0.0007) -[2023-10-12 03:14:22,392][78123] Updated weights for policy 1, policy_version 4040 (0.0008) -[2023-10-12 03:14:22,762][78123] Updated weights for policy 1, policy_version 4050 (0.0009) -[2023-10-12 03:14:23,132][78123] Updated weights for policy 1, policy_version 4060 (0.0008) -[2023-10-12 03:14:25,188][78091] Updated weights for policy 0, policy_version 4070 (0.0009) -[2023-10-12 03:14:25,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 8323072. Throughput: 0: 1614.0, 1: 1587.0. Samples: 2094284. Policy #0 lag: (min: 31.0, avg: 32.6, max: 58.0) -[2023-10-12 03:14:25,201][77203] Avg episode reward: [(0, '22.690'), (1, '24.970')] -[2023-10-12 03:14:25,557][78091] Updated weights for policy 0, policy_version 4080 (0.0008) -[2023-10-12 03:14:25,929][78091] Updated weights for policy 0, policy_version 4090 (0.0009) -[2023-10-12 03:14:27,625][78123] Updated weights for policy 1, policy_version 4070 (0.0008) -[2023-10-12 03:14:28,005][78123] Updated weights for policy 1, policy_version 4080 (0.0009) -[2023-10-12 03:14:28,379][78123] Updated weights for policy 1, policy_version 4090 (0.0007) -[2023-10-12 03:14:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 8388608. Throughput: 0: 1591.0, 1: 1607.1. Samples: 2103624. Policy #0 lag: (min: 2.0, avg: 3.2, max: 24.0) -[2023-10-12 03:14:30,202][77203] Avg episode reward: [(0, '24.010'), (1, '21.290')] -[2023-10-12 03:14:30,362][78091] Updated weights for policy 0, policy_version 4100 (0.0009) -[2023-10-12 03:14:30,757][78091] Updated weights for policy 0, policy_version 4110 (0.0010) -[2023-10-12 03:14:31,128][78091] Updated weights for policy 0, policy_version 4120 (0.0009) -[2023-10-12 03:14:32,778][78123] Updated weights for policy 1, policy_version 4100 (0.0009) -[2023-10-12 03:14:33,148][78123] Updated weights for policy 1, policy_version 4110 (0.0010) -[2023-10-12 03:14:33,510][78123] Updated weights for policy 1, policy_version 4120 (0.0007) -[2023-10-12 03:14:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 8454144. Throughput: 0: 1588.4, 1: 1590.6. Samples: 2122216. Policy #0 lag: (min: 7.0, avg: 12.4, max: 39.0) -[2023-10-12 03:14:35,201][77203] Avg episode reward: [(0, '21.870'), (1, '20.880')] -[2023-10-12 03:14:35,390][78091] Updated weights for policy 0, policy_version 4130 (0.0008) -[2023-10-12 03:14:35,766][78091] Updated weights for policy 0, policy_version 4140 (0.0007) -[2023-10-12 03:14:36,133][78091] Updated weights for policy 0, policy_version 4150 (0.0007) -[2023-10-12 03:14:36,510][78091] Updated weights for policy 0, policy_version 4160 (0.0007) -[2023-10-12 03:14:37,817][78123] Updated weights for policy 1, policy_version 4130 (0.0009) -[2023-10-12 03:14:38,192][78123] Updated weights for policy 1, policy_version 4140 (0.0007) -[2023-10-12 03:14:38,568][78123] Updated weights for policy 1, policy_version 4150 (0.0008) -[2023-10-12 03:14:38,935][78123] Updated weights for policy 1, policy_version 4160 (0.0007) -[2023-10-12 03:14:40,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 8519680. Throughput: 0: 1592.5, 1: 1589.7. Samples: 2141318. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:14:40,201][77203] Avg episode reward: [(0, '23.220'), (1, '24.220')] -[2023-10-12 03:14:41,146][78091] Updated weights for policy 0, policy_version 4170 (0.0007) -[2023-10-12 03:14:41,514][78091] Updated weights for policy 0, policy_version 4180 (0.0010) -[2023-10-12 03:14:41,889][78091] Updated weights for policy 0, policy_version 4190 (0.0009) -[2023-10-12 03:14:43,196][78123] Updated weights for policy 1, policy_version 4170 (0.0010) -[2023-10-12 03:14:43,566][78123] Updated weights for policy 1, policy_version 4180 (0.0008) -[2023-10-12 03:14:43,935][78123] Updated weights for policy 1, policy_version 4190 (0.0007) -[2023-10-12 03:14:45,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 8585216. Throughput: 0: 1576.8, 1: 1610.5. Samples: 2150938. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:14:45,202][77203] Avg episode reward: [(0, '23.130'), (1, '22.050')] -[2023-10-12 03:14:45,956][78091] Updated weights for policy 0, policy_version 4200 (0.0010) -[2023-10-12 03:14:46,336][78091] Updated weights for policy 0, policy_version 4210 (0.0007) -[2023-10-12 03:14:46,704][78091] Updated weights for policy 0, policy_version 4220 (0.0008) -[2023-10-12 03:14:48,331][78123] Updated weights for policy 1, policy_version 4200 (0.0007) -[2023-10-12 03:14:48,698][78123] Updated weights for policy 1, policy_version 4210 (0.0007) -[2023-10-12 03:14:49,064][78123] Updated weights for policy 1, policy_version 4220 (0.0008) -[2023-10-12 03:14:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 8650752. Throughput: 0: 1580.6, 1: 1594.5. Samples: 2169854. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:14:50,205][77203] Avg episode reward: [(0, '23.220'), (1, '21.420')] -[2023-10-12 03:14:50,967][78091] Updated weights for policy 0, policy_version 4230 (0.0010) -[2023-10-12 03:14:51,332][78091] Updated weights for policy 0, policy_version 4240 (0.0010) -[2023-10-12 03:14:51,704][78091] Updated weights for policy 0, policy_version 4250 (0.0009) -[2023-10-12 03:14:53,302][78123] Updated weights for policy 1, policy_version 4230 (0.0009) -[2023-10-12 03:14:53,666][78123] Updated weights for policy 1, policy_version 4240 (0.0007) -[2023-10-12 03:14:54,032][78123] Updated weights for policy 1, policy_version 4250 (0.0009) -[2023-10-12 03:14:55,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 8716288. Throughput: 0: 1584.7, 1: 1582.3. Samples: 2188734. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:14:55,201][77203] Avg episode reward: [(0, '23.170'), (1, '22.260')] -[2023-10-12 03:14:56,010][78091] Updated weights for policy 0, policy_version 4260 (0.0008) -[2023-10-12 03:14:56,374][78091] Updated weights for policy 0, policy_version 4270 (0.0008) -[2023-10-12 03:14:56,754][78091] Updated weights for policy 0, policy_version 4280 (0.0008) -[2023-10-12 03:14:58,474][78123] Updated weights for policy 1, policy_version 4260 (0.0010) -[2023-10-12 03:14:58,845][78123] Updated weights for policy 1, policy_version 4270 (0.0009) -[2023-10-12 03:14:59,207][78123] Updated weights for policy 1, policy_version 4280 (0.0010) -[2023-10-12 03:15:00,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 8781824. Throughput: 0: 1580.3, 1: 1603.2. Samples: 2198726. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:15:00,202][77203] Avg episode reward: [(0, '22.770'), (1, '25.110')] -[2023-10-12 03:15:00,961][78091] Updated weights for policy 0, policy_version 4290 (0.0009) -[2023-10-12 03:15:01,333][78091] Updated weights for policy 0, policy_version 4300 (0.0009) -[2023-10-12 03:15:01,705][78091] Updated weights for policy 0, policy_version 4310 (0.0008) -[2023-10-12 03:15:02,069][78091] Updated weights for policy 0, policy_version 4320 (0.0007) -[2023-10-12 03:15:03,624][78123] Updated weights for policy 1, policy_version 4290 (0.0010) -[2023-10-12 03:15:03,988][78123] Updated weights for policy 1, policy_version 4300 (0.0008) -[2023-10-12 03:15:04,352][78123] Updated weights for policy 1, policy_version 4310 (0.0007) -[2023-10-12 03:15:04,723][78123] Updated weights for policy 1, policy_version 4320 (0.0008) -[2023-10-12 03:15:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 8847360. Throughput: 0: 1586.9, 1: 1600.2. Samples: 2218150. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:15:05,201][77203] Avg episode reward: [(0, '23.660'), (1, '20.540')] -[2023-10-12 03:15:06,211][78091] Updated weights for policy 0, policy_version 4330 (0.0007) -[2023-10-12 03:15:06,583][78091] Updated weights for policy 0, policy_version 4340 (0.0011) -[2023-10-12 03:15:06,946][78091] Updated weights for policy 0, policy_version 4350 (0.0008) -[2023-10-12 03:15:09,177][78123] Updated weights for policy 1, policy_version 4330 (0.0008) -[2023-10-12 03:15:09,548][78123] Updated weights for policy 1, policy_version 4340 (0.0009) -[2023-10-12 03:15:09,911][78123] Updated weights for policy 1, policy_version 4350 (0.0008) -[2023-10-12 03:15:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 8912896. Throughput: 0: 1593.8, 1: 1582.6. Samples: 2237224. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:15:10,201][77203] Avg episode reward: [(0, '22.660'), (1, '27.040')] -[2023-10-12 03:15:10,212][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000004352_4456448.pth... -[2023-10-12 03:15:10,213][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000004352_4456448.pth... -[2023-10-12 03:15:10,246][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000002848_2916352.pth -[2023-10-12 03:15:10,250][77950] Saving new best policy, reward=27.040! -[2023-10-12 03:15:10,257][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000002880_2949120.pth -[2023-10-12 03:15:11,260][78091] Updated weights for policy 0, policy_version 4360 (0.0007) -[2023-10-12 03:15:11,624][78091] Updated weights for policy 0, policy_version 4370 (0.0007) -[2023-10-12 03:15:12,000][78091] Updated weights for policy 0, policy_version 4380 (0.0008) -[2023-10-12 03:15:14,221][78123] Updated weights for policy 1, policy_version 4360 (0.0008) -[2023-10-12 03:15:14,592][78123] Updated weights for policy 1, policy_version 4370 (0.0007) -[2023-10-12 03:15:14,965][78123] Updated weights for policy 1, policy_version 4380 (0.0010) -[2023-10-12 03:15:15,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 8978432. Throughput: 0: 1591.5, 1: 1588.3. Samples: 2246714. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:15:15,202][77203] Avg episode reward: [(0, '23.120'), (1, '22.410')] -[2023-10-12 03:15:16,289][78091] Updated weights for policy 0, policy_version 4390 (0.0011) -[2023-10-12 03:15:16,655][78091] Updated weights for policy 0, policy_version 4400 (0.0010) -[2023-10-12 03:15:17,021][78091] Updated weights for policy 0, policy_version 4410 (0.0008) -[2023-10-12 03:15:19,118][78123] Updated weights for policy 1, policy_version 4390 (0.0007) -[2023-10-12 03:15:19,488][78123] Updated weights for policy 1, policy_version 4400 (0.0008) -[2023-10-12 03:15:19,849][78123] Updated weights for policy 1, policy_version 4410 (0.0008) -[2023-10-12 03:15:20,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 9043968. Throughput: 0: 1597.0, 1: 1601.9. Samples: 2266164. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-10-12 03:15:20,201][77203] Avg episode reward: [(0, '22.640'), (1, '23.850')] -[2023-10-12 03:15:21,363][78091] Updated weights for policy 0, policy_version 4420 (0.0008) -[2023-10-12 03:15:21,733][78091] Updated weights for policy 0, policy_version 4430 (0.0009) -[2023-10-12 03:15:22,100][78091] Updated weights for policy 0, policy_version 4440 (0.0008) -[2023-10-12 03:15:24,303][78123] Updated weights for policy 1, policy_version 4420 (0.0008) -[2023-10-12 03:15:24,665][78123] Updated weights for policy 1, policy_version 4430 (0.0009) -[2023-10-12 03:15:25,034][78123] Updated weights for policy 1, policy_version 4440 (0.0009) -[2023-10-12 03:15:25,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 9076736. Throughput: 0: 1602.8, 1: 1590.7. Samples: 2285030. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-10-12 03:15:25,202][77203] Avg episode reward: [(0, '23.570'), (1, '24.610')] -[2023-10-12 03:15:26,418][78091] Updated weights for policy 0, policy_version 4450 (0.0007) -[2023-10-12 03:15:26,793][78091] Updated weights for policy 0, policy_version 4460 (0.0007) -[2023-10-12 03:15:27,157][78091] Updated weights for policy 0, policy_version 4470 (0.0008) -[2023-10-12 03:15:27,528][78091] Updated weights for policy 0, policy_version 4480 (0.0008) -[2023-10-12 03:15:29,454][78123] Updated weights for policy 1, policy_version 4450 (0.0007) -[2023-10-12 03:15:29,823][78123] Updated weights for policy 1, policy_version 4460 (0.0009) -[2023-10-12 03:15:30,201][78123] Updated weights for policy 1, policy_version 4470 (0.0009) -[2023-10-12 03:15:30,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 9142272. Throughput: 0: 1606.3, 1: 1578.4. Samples: 2294250. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:15:30,201][77203] Avg episode reward: [(0, '22.340'), (1, '21.320')] -[2023-10-12 03:15:30,563][78123] Updated weights for policy 1, policy_version 4480 (0.0009) -[2023-10-12 03:15:31,887][78091] Updated weights for policy 0, policy_version 4490 (0.0007) -[2023-10-12 03:15:32,268][78091] Updated weights for policy 0, policy_version 4500 (0.0009) -[2023-10-12 03:15:32,643][78091] Updated weights for policy 0, policy_version 4510 (0.0008) -[2023-10-12 03:15:34,902][78123] Updated weights for policy 1, policy_version 4490 (0.0009) -[2023-10-12 03:15:35,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 9207808. Throughput: 0: 1600.5, 1: 1598.2. Samples: 2313794. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:15:35,202][77203] Avg episode reward: [(0, '22.290'), (1, '24.580')] -[2023-10-12 03:15:35,262][78123] Updated weights for policy 1, policy_version 4500 (0.0009) -[2023-10-12 03:15:35,627][78123] Updated weights for policy 1, policy_version 4510 (0.0009) -[2023-10-12 03:15:36,767][78091] Updated weights for policy 0, policy_version 4520 (0.0009) -[2023-10-12 03:15:37,142][78091] Updated weights for policy 0, policy_version 4530 (0.0010) -[2023-10-12 03:15:37,505][78091] Updated weights for policy 0, policy_version 4540 (0.0009) -[2023-10-12 03:15:39,904][78123] Updated weights for policy 1, policy_version 4520 (0.0009) -[2023-10-12 03:15:40,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 9273344. Throughput: 0: 1605.0, 1: 1607.8. Samples: 2333312. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:15:40,202][77203] Avg episode reward: [(0, '22.680'), (1, '25.410')] -[2023-10-12 03:15:40,270][78123] Updated weights for policy 1, policy_version 4530 (0.0009) -[2023-10-12 03:15:40,631][78123] Updated weights for policy 1, policy_version 4540 (0.0011) -[2023-10-12 03:15:42,197][78091] Updated weights for policy 0, policy_version 4550 (0.0008) -[2023-10-12 03:15:42,566][78091] Updated weights for policy 0, policy_version 4560 (0.0007) -[2023-10-12 03:15:42,937][78091] Updated weights for policy 0, policy_version 4570 (0.0007) -[2023-10-12 03:15:44,883][78123] Updated weights for policy 1, policy_version 4550 (0.0009) -[2023-10-12 03:15:45,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 9338880. Throughput: 0: 1612.3, 1: 1582.2. Samples: 2342476. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:15:45,202][77203] Avg episode reward: [(0, '23.720'), (1, '18.740')] -[2023-10-12 03:15:45,263][78123] Updated weights for policy 1, policy_version 4560 (0.0009) -[2023-10-12 03:15:45,632][78123] Updated weights for policy 1, policy_version 4570 (0.0010) -[2023-10-12 03:15:47,292][78091] Updated weights for policy 0, policy_version 4580 (0.0007) -[2023-10-12 03:15:47,666][78091] Updated weights for policy 0, policy_version 4590 (0.0007) -[2023-10-12 03:15:48,034][78091] Updated weights for policy 0, policy_version 4600 (0.0007) -[2023-10-12 03:15:49,994][78123] Updated weights for policy 1, policy_version 4580 (0.0009) -[2023-10-12 03:15:50,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 9404416. Throughput: 0: 1598.4, 1: 1590.7. Samples: 2361660. Policy #0 lag: (min: 10.0, avg: 12.0, max: 34.0) -[2023-10-12 03:15:50,201][77203] Avg episode reward: [(0, '22.290'), (1, '25.000')] -[2023-10-12 03:15:50,357][78123] Updated weights for policy 1, policy_version 4590 (0.0010) -[2023-10-12 03:15:50,730][78123] Updated weights for policy 1, policy_version 4600 (0.0008) -[2023-10-12 03:15:52,363][78091] Updated weights for policy 0, policy_version 4610 (0.0009) -[2023-10-12 03:15:52,736][78091] Updated weights for policy 0, policy_version 4620 (0.0008) -[2023-10-12 03:15:53,113][78091] Updated weights for policy 0, policy_version 4630 (0.0008) -[2023-10-12 03:15:53,484][78091] Updated weights for policy 0, policy_version 4640 (0.0007) -[2023-10-12 03:15:55,118][78123] Updated weights for policy 1, policy_version 4610 (0.0008) -[2023-10-12 03:15:55,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 9469952. Throughput: 0: 1589.4, 1: 1607.4. Samples: 2381082. Policy #0 lag: (min: 31.0, avg: 32.5, max: 58.0) -[2023-10-12 03:15:55,202][77203] Avg episode reward: [(0, '21.250'), (1, '25.030')] -[2023-10-12 03:15:55,488][78123] Updated weights for policy 1, policy_version 4620 (0.0009) -[2023-10-12 03:15:55,844][78123] Updated weights for policy 1, policy_version 4630 (0.0009) -[2023-10-12 03:15:56,206][78123] Updated weights for policy 1, policy_version 4640 (0.0008) -[2023-10-12 03:15:57,905][78091] Updated weights for policy 0, policy_version 4650 (0.0009) -[2023-10-12 03:15:58,280][78091] Updated weights for policy 0, policy_version 4660 (0.0010) -[2023-10-12 03:15:58,653][78091] Updated weights for policy 0, policy_version 4670 (0.0010) -[2023-10-12 03:16:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 9535488. Throughput: 0: 1611.3, 1: 1583.1. Samples: 2390458. Policy #0 lag: (min: 31.0, avg: 32.5, max: 58.0) -[2023-10-12 03:16:00,201][77203] Avg episode reward: [(0, '22.580'), (1, '23.510')] -[2023-10-12 03:16:00,572][78123] Updated weights for policy 1, policy_version 4650 (0.0010) -[2023-10-12 03:16:00,942][78123] Updated weights for policy 1, policy_version 4660 (0.0008) -[2023-10-12 03:16:01,306][78123] Updated weights for policy 1, policy_version 4670 (0.0007) -[2023-10-12 03:16:03,075][78091] Updated weights for policy 0, policy_version 4680 (0.0008) -[2023-10-12 03:16:03,443][78091] Updated weights for policy 0, policy_version 4690 (0.0008) -[2023-10-12 03:16:03,808][78091] Updated weights for policy 0, policy_version 4700 (0.0010) -[2023-10-12 03:16:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 9601024. Throughput: 0: 1590.7, 1: 1589.5. Samples: 2409272. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-12 03:16:05,202][77203] Avg episode reward: [(0, '23.550'), (1, '23.010')] -[2023-10-12 03:16:05,611][78123] Updated weights for policy 1, policy_version 4680 (0.0008) -[2023-10-12 03:16:05,978][78123] Updated weights for policy 1, policy_version 4690 (0.0008) -[2023-10-12 03:16:06,351][78123] Updated weights for policy 1, policy_version 4700 (0.0009) -[2023-10-12 03:16:08,045][78091] Updated weights for policy 0, policy_version 4710 (0.0009) -[2023-10-12 03:16:08,422][78091] Updated weights for policy 0, policy_version 4720 (0.0009) -[2023-10-12 03:16:08,786][78091] Updated weights for policy 0, policy_version 4730 (0.0010) -[2023-10-12 03:16:10,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 9666560. Throughput: 0: 1582.1, 1: 1606.0. Samples: 2428496. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-12 03:16:10,201][77203] Avg episode reward: [(0, '23.980'), (1, '20.150')] -[2023-10-12 03:16:10,617][78123] Updated weights for policy 1, policy_version 4710 (0.0008) -[2023-10-12 03:16:10,999][78123] Updated weights for policy 1, policy_version 4720 (0.0009) -[2023-10-12 03:16:11,364][78123] Updated weights for policy 1, policy_version 4730 (0.0009) -[2023-10-12 03:16:13,148][78091] Updated weights for policy 0, policy_version 4740 (0.0009) -[2023-10-12 03:16:13,516][78091] Updated weights for policy 0, policy_version 4750 (0.0007) -[2023-10-12 03:16:13,887][78091] Updated weights for policy 0, policy_version 4760 (0.0009) -[2023-10-12 03:16:15,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 9732096. Throughput: 0: 1607.3, 1: 1591.3. Samples: 2438188. Policy #0 lag: (min: 13.0, avg: 30.5, max: 32.0) -[2023-10-12 03:16:15,202][77203] Avg episode reward: [(0, '22.670'), (1, '24.490')] -[2023-10-12 03:16:15,677][78123] Updated weights for policy 1, policy_version 4740 (0.0009) -[2023-10-12 03:16:16,051][78123] Updated weights for policy 1, policy_version 4750 (0.0007) -[2023-10-12 03:16:16,423][78123] Updated weights for policy 1, policy_version 4760 (0.0007) -[2023-10-12 03:16:18,296][78091] Updated weights for policy 0, policy_version 4770 (0.0008) -[2023-10-12 03:16:18,674][78091] Updated weights for policy 0, policy_version 4780 (0.0008) -[2023-10-12 03:16:19,048][78091] Updated weights for policy 0, policy_version 4790 (0.0007) -[2023-10-12 03:16:19,414][78091] Updated weights for policy 0, policy_version 4800 (0.0008) -[2023-10-12 03:16:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 9797632. Throughput: 0: 1590.6, 1: 1592.7. Samples: 2457044. Policy #0 lag: (min: 7.0, avg: 14.3, max: 39.0) -[2023-10-12 03:16:20,202][77203] Avg episode reward: [(0, '22.760'), (1, '24.080')] -[2023-10-12 03:16:20,687][78123] Updated weights for policy 1, policy_version 4770 (0.0007) -[2023-10-12 03:16:21,048][78123] Updated weights for policy 1, policy_version 4780 (0.0008) -[2023-10-12 03:16:21,417][78123] Updated weights for policy 1, policy_version 4790 (0.0007) -[2023-10-12 03:16:21,784][78123] Updated weights for policy 1, policy_version 4800 (0.0007) -[2023-10-12 03:16:23,706][78091] Updated weights for policy 0, policy_version 4810 (0.0009) -[2023-10-12 03:16:24,077][78091] Updated weights for policy 0, policy_version 4820 (0.0009) -[2023-10-12 03:16:24,442][78091] Updated weights for policy 0, policy_version 4830 (0.0010) -[2023-10-12 03:16:25,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 9863168. Throughput: 0: 1577.2, 1: 1594.3. Samples: 2476030. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:16:25,202][77203] Avg episode reward: [(0, '23.350'), (1, '22.530')] -[2023-10-12 03:16:25,923][78123] Updated weights for policy 1, policy_version 4810 (0.0007) -[2023-10-12 03:16:26,287][78123] Updated weights for policy 1, policy_version 4820 (0.0008) -[2023-10-12 03:16:26,659][78123] Updated weights for policy 1, policy_version 4830 (0.0008) -[2023-10-12 03:16:28,698][78091] Updated weights for policy 0, policy_version 4840 (0.0008) -[2023-10-12 03:16:29,068][78091] Updated weights for policy 0, policy_version 4850 (0.0008) -[2023-10-12 03:16:29,431][78091] Updated weights for policy 0, policy_version 4860 (0.0010) -[2023-10-12 03:16:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 9928704. Throughput: 0: 1594.3, 1: 1593.5. Samples: 2485926. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:16:30,201][77203] Avg episode reward: [(0, '24.170'), (1, '25.720')] -[2023-10-12 03:16:30,931][78123] Updated weights for policy 1, policy_version 4840 (0.0009) -[2023-10-12 03:16:31,304][78123] Updated weights for policy 1, policy_version 4850 (0.0007) -[2023-10-12 03:16:31,667][78123] Updated weights for policy 1, policy_version 4860 (0.0007) -[2023-10-12 03:16:33,811][78091] Updated weights for policy 0, policy_version 4870 (0.0009) -[2023-10-12 03:16:34,177][78091] Updated weights for policy 0, policy_version 4880 (0.0010) -[2023-10-12 03:16:34,552][78091] Updated weights for policy 0, policy_version 4890 (0.0009) -[2023-10-12 03:16:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 9994240. Throughput: 0: 1600.3, 1: 1595.2. Samples: 2505456. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:16:35,202][77203] Avg episode reward: [(0, '23.230'), (1, '21.640')] -[2023-10-12 03:16:35,903][78123] Updated weights for policy 1, policy_version 4870 (0.0007) -[2023-10-12 03:16:36,279][78123] Updated weights for policy 1, policy_version 4880 (0.0008) -[2023-10-12 03:16:36,648][78123] Updated weights for policy 1, policy_version 4890 (0.0010) -[2023-10-12 03:16:38,827][78091] Updated weights for policy 0, policy_version 4900 (0.0009) -[2023-10-12 03:16:39,206][78091] Updated weights for policy 0, policy_version 4910 (0.0010) -[2023-10-12 03:16:39,577][78091] Updated weights for policy 0, policy_version 4920 (0.0009) -[2023-10-12 03:16:40,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 12774.0). Total num frames: 10059776. Throughput: 0: 1588.0, 1: 1593.7. Samples: 2524254. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:16:40,201][77203] Avg episode reward: [(0, '23.330'), (1, '25.850')] -[2023-10-12 03:16:41,079][78123] Updated weights for policy 1, policy_version 4900 (0.0010) -[2023-10-12 03:16:41,445][78123] Updated weights for policy 1, policy_version 4910 (0.0008) -[2023-10-12 03:16:41,812][78123] Updated weights for policy 1, policy_version 4920 (0.0007) -[2023-10-12 03:16:43,895][78091] Updated weights for policy 0, policy_version 4930 (0.0009) -[2023-10-12 03:16:44,259][78091] Updated weights for policy 0, policy_version 4940 (0.0009) -[2023-10-12 03:16:44,639][78091] Updated weights for policy 0, policy_version 4950 (0.0009) -[2023-10-12 03:16:45,017][78091] Updated weights for policy 0, policy_version 4960 (0.0009) -[2023-10-12 03:16:45,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.3, 300 sec: 12774.0). Total num frames: 10125312. Throughput: 0: 1593.3, 1: 1595.2. Samples: 2533940. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-12 03:16:45,201][77203] Avg episode reward: [(0, '22.800'), (1, '24.270')] -[2023-10-12 03:16:46,136][78123] Updated weights for policy 1, policy_version 4930 (0.0011) -[2023-10-12 03:16:46,509][78123] Updated weights for policy 1, policy_version 4940 (0.0009) -[2023-10-12 03:16:46,881][78123] Updated weights for policy 1, policy_version 4950 (0.0010) -[2023-10-12 03:16:47,246][78123] Updated weights for policy 1, policy_version 4960 (0.0007) -[2023-10-12 03:16:49,431][78091] Updated weights for policy 0, policy_version 4970 (0.0009) -[2023-10-12 03:16:49,808][78091] Updated weights for policy 0, policy_version 4980 (0.0009) -[2023-10-12 03:16:50,169][78091] Updated weights for policy 0, policy_version 4990 (0.0009) -[2023-10-12 03:16:50,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 10158080. Throughput: 0: 1607.2, 1: 1591.1. Samples: 2553196. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-12 03:16:50,201][77203] Avg episode reward: [(0, '22.760'), (1, '24.720')] -[2023-10-12 03:16:51,718][78123] Updated weights for policy 1, policy_version 4970 (0.0008) -[2023-10-12 03:16:52,093][78123] Updated weights for policy 1, policy_version 4980 (0.0009) -[2023-10-12 03:16:52,459][78123] Updated weights for policy 1, policy_version 4990 (0.0009) -[2023-10-12 03:16:54,413][78091] Updated weights for policy 0, policy_version 5000 (0.0007) -[2023-10-12 03:16:54,776][78091] Updated weights for policy 0, policy_version 5010 (0.0008) -[2023-10-12 03:16:55,156][78091] Updated weights for policy 0, policy_version 5020 (0.0008) -[2023-10-12 03:16:55,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 10223616. Throughput: 0: 1604.7, 1: 1586.4. Samples: 2572096. Policy #0 lag: (min: 8.0, avg: 33.1, max: 40.0) -[2023-10-12 03:16:55,202][77203] Avg episode reward: [(0, '22.790'), (1, '24.620')] -[2023-10-12 03:16:56,838][78123] Updated weights for policy 1, policy_version 5000 (0.0007) -[2023-10-12 03:16:57,201][78123] Updated weights for policy 1, policy_version 5010 (0.0008) -[2023-10-12 03:16:57,571][78123] Updated weights for policy 1, policy_version 5020 (0.0008) -[2023-10-12 03:16:59,190][78091] Updated weights for policy 0, policy_version 5030 (0.0008) -[2023-10-12 03:16:59,560][78091] Updated weights for policy 0, policy_version 5040 (0.0010) -[2023-10-12 03:16:59,938][78091] Updated weights for policy 0, policy_version 5050 (0.0011) -[2023-10-12 03:17:00,201][77203] Fps is (10 sec: 16383.9, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 10321920. Throughput: 0: 1597.1, 1: 1586.1. Samples: 2581434. Policy #0 lag: (min: 27.0, avg: 34.3, max: 59.0) -[2023-10-12 03:17:00,201][77203] Avg episode reward: [(0, '22.820'), (1, '25.800')] -[2023-10-12 03:17:01,930][78123] Updated weights for policy 1, policy_version 5030 (0.0007) -[2023-10-12 03:17:02,304][78123] Updated weights for policy 1, policy_version 5040 (0.0010) -[2023-10-12 03:17:02,679][78123] Updated weights for policy 1, policy_version 5050 (0.0010) -[2023-10-12 03:17:04,204][78091] Updated weights for policy 0, policy_version 5060 (0.0008) -[2023-10-12 03:17:04,572][78091] Updated weights for policy 0, policy_version 5070 (0.0010) -[2023-10-12 03:17:04,944][78091] Updated weights for policy 0, policy_version 5080 (0.0009) -[2023-10-12 03:17:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 10354688. Throughput: 0: 1616.0, 1: 1582.1. Samples: 2600958. Policy #0 lag: (min: 27.0, avg: 34.3, max: 59.0) -[2023-10-12 03:17:05,202][77203] Avg episode reward: [(0, '24.180'), (1, '25.050')] -[2023-10-12 03:17:06,901][78123] Updated weights for policy 1, policy_version 5060 (0.0007) -[2023-10-12 03:17:07,274][78123] Updated weights for policy 1, policy_version 5070 (0.0010) -[2023-10-12 03:17:07,654][78123] Updated weights for policy 1, policy_version 5080 (0.0010) -[2023-10-12 03:17:09,209][78091] Updated weights for policy 0, policy_version 5090 (0.0009) -[2023-10-12 03:17:09,590][78091] Updated weights for policy 0, policy_version 5100 (0.0009) -[2023-10-12 03:17:09,959][78091] Updated weights for policy 0, policy_version 5110 (0.0008) -[2023-10-12 03:17:10,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 10420224. Throughput: 0: 1615.6, 1: 1581.9. Samples: 2619918. Policy #0 lag: (min: 27.0, avg: 34.3, max: 59.0) -[2023-10-12 03:17:10,202][77203] Avg episode reward: [(0, '24.070'), (1, '25.370')] -[2023-10-12 03:17:10,210][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000005088_5210112.pth... -[2023-10-12 03:17:10,247][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000003616_3702784.pth -[2023-10-12 03:17:10,330][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000005120_5242880.pth... -[2023-10-12 03:17:10,331][78091] Updated weights for policy 0, policy_version 5120 (0.0009) -[2023-10-12 03:17:10,359][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000003616_3702784.pth -[2023-10-12 03:17:12,156][78123] Updated weights for policy 1, policy_version 5090 (0.0011) -[2023-10-12 03:17:12,523][78123] Updated weights for policy 1, policy_version 5100 (0.0009) -[2023-10-12 03:17:12,894][78123] Updated weights for policy 1, policy_version 5110 (0.0009) -[2023-10-12 03:17:13,263][78123] Updated weights for policy 1, policy_version 5120 (0.0010) -[2023-10-12 03:17:14,510][78091] Updated weights for policy 0, policy_version 5130 (0.0007) -[2023-10-12 03:17:14,884][78091] Updated weights for policy 0, policy_version 5140 (0.0009) -[2023-10-12 03:17:15,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 10485760. Throughput: 0: 1606.0, 1: 1589.9. Samples: 2629742. Policy #0 lag: (min: 31.0, avg: 31.0, max: 36.0) -[2023-10-12 03:17:15,201][77203] Avg episode reward: [(0, '22.160'), (1, '27.280')] -[2023-10-12 03:17:15,202][77950] Saving new best policy, reward=27.280! -[2023-10-12 03:17:15,261][78091] Updated weights for policy 0, policy_version 5150 (0.0010) -[2023-10-12 03:17:17,463][78123] Updated weights for policy 1, policy_version 5130 (0.0009) -[2023-10-12 03:17:17,837][78123] Updated weights for policy 1, policy_version 5140 (0.0008) -[2023-10-12 03:17:18,216][78123] Updated weights for policy 1, policy_version 5150 (0.0007) -[2023-10-12 03:17:19,533][78091] Updated weights for policy 0, policy_version 5160 (0.0009) -[2023-10-12 03:17:19,910][78091] Updated weights for policy 0, policy_version 5170 (0.0009) -[2023-10-12 03:17:20,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 10551296. Throughput: 0: 1612.2, 1: 1577.0. Samples: 2648970. Policy #0 lag: (min: 31.0, avg: 31.0, max: 36.0) -[2023-10-12 03:17:20,202][77203] Avg episode reward: [(0, '23.490'), (1, '24.870')] -[2023-10-12 03:17:20,288][78091] Updated weights for policy 0, policy_version 5180 (0.0010) -[2023-10-12 03:17:22,631][78123] Updated weights for policy 1, policy_version 5160 (0.0010) -[2023-10-12 03:17:22,996][78123] Updated weights for policy 1, policy_version 5170 (0.0008) -[2023-10-12 03:17:23,361][78123] Updated weights for policy 1, policy_version 5180 (0.0010) -[2023-10-12 03:17:24,532][78091] Updated weights for policy 0, policy_version 5190 (0.0008) -[2023-10-12 03:17:24,896][78091] Updated weights for policy 0, policy_version 5200 (0.0008) -[2023-10-12 03:17:25,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 10616832. Throughput: 0: 1617.7, 1: 1573.2. Samples: 2667848. Policy #0 lag: (min: 26.0, avg: 29.7, max: 58.0) -[2023-10-12 03:17:25,201][77203] Avg episode reward: [(0, '24.910'), (1, '25.690')] -[2023-10-12 03:17:25,266][78091] Updated weights for policy 0, policy_version 5210 (0.0008) -[2023-10-12 03:17:27,698][78123] Updated weights for policy 1, policy_version 5190 (0.0008) -[2023-10-12 03:17:28,063][78123] Updated weights for policy 1, policy_version 5200 (0.0007) -[2023-10-12 03:17:28,425][78123] Updated weights for policy 1, policy_version 5210 (0.0007) -[2023-10-12 03:17:29,661][78091] Updated weights for policy 0, policy_version 5220 (0.0008) -[2023-10-12 03:17:30,040][78091] Updated weights for policy 0, policy_version 5230 (0.0007) -[2023-10-12 03:17:30,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 10682368. Throughput: 0: 1603.0, 1: 1595.3. Samples: 2677864. Policy #0 lag: (min: 26.0, avg: 29.7, max: 58.0) -[2023-10-12 03:17:30,202][77203] Avg episode reward: [(0, '24.060'), (1, '24.460')] -[2023-10-12 03:17:30,412][78091] Updated weights for policy 0, policy_version 5240 (0.0007) -[2023-10-12 03:17:32,618][78123] Updated weights for policy 1, policy_version 5220 (0.0008) -[2023-10-12 03:17:32,983][78123] Updated weights for policy 1, policy_version 5230 (0.0007) -[2023-10-12 03:17:33,360][78123] Updated weights for policy 1, policy_version 5240 (0.0009) -[2023-10-12 03:17:34,762][78091] Updated weights for policy 0, policy_version 5250 (0.0007) -[2023-10-12 03:17:35,174][78091] Updated weights for policy 0, policy_version 5260 (0.0009) -[2023-10-12 03:17:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 10747904. Throughput: 0: 1605.7, 1: 1574.3. Samples: 2696298. Policy #0 lag: (min: 1.0, avg: 3.9, max: 33.0) -[2023-10-12 03:17:35,201][77203] Avg episode reward: [(0, '22.110'), (1, '27.090')] -[2023-10-12 03:17:35,533][78091] Updated weights for policy 0, policy_version 5270 (0.0010) -[2023-10-12 03:17:35,907][78091] Updated weights for policy 0, policy_version 5280 (0.0008) -[2023-10-12 03:17:37,946][78123] Updated weights for policy 1, policy_version 5250 (0.0010) -[2023-10-12 03:17:38,357][78123] Updated weights for policy 1, policy_version 5260 (0.0008) -[2023-10-12 03:17:38,724][78123] Updated weights for policy 1, policy_version 5270 (0.0008) -[2023-10-12 03:17:39,088][78123] Updated weights for policy 1, policy_version 5280 (0.0008) -[2023-10-12 03:17:39,993][78091] Updated weights for policy 0, policy_version 5290 (0.0007) -[2023-10-12 03:17:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 10813440. Throughput: 0: 1618.4, 1: 1571.8. Samples: 2715656. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-12 03:17:40,201][77203] Avg episode reward: [(0, '22.050'), (1, '27.490')] -[2023-10-12 03:17:40,209][77950] Saving new best policy, reward=27.490! -[2023-10-12 03:17:40,365][78091] Updated weights for policy 0, policy_version 5300 (0.0009) -[2023-10-12 03:17:40,732][78091] Updated weights for policy 0, policy_version 5310 (0.0009) -[2023-10-12 03:17:43,419][78123] Updated weights for policy 1, policy_version 5290 (0.0007) -[2023-10-12 03:17:43,782][78123] Updated weights for policy 1, policy_version 5300 (0.0010) -[2023-10-12 03:17:44,153][78123] Updated weights for policy 1, policy_version 5310 (0.0007) -[2023-10-12 03:17:45,178][78091] Updated weights for policy 0, policy_version 5320 (0.0011) -[2023-10-12 03:17:45,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 10878976. Throughput: 0: 1601.6, 1: 1598.0. Samples: 2725416. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-12 03:17:45,201][77203] Avg episode reward: [(0, '24.050'), (1, '27.240')] -[2023-10-12 03:17:45,560][78091] Updated weights for policy 0, policy_version 5330 (0.0007) -[2023-10-12 03:17:45,926][78091] Updated weights for policy 0, policy_version 5340 (0.0007) -[2023-10-12 03:17:48,571][78123] Updated weights for policy 1, policy_version 5320 (0.0009) -[2023-10-12 03:17:48,929][78123] Updated weights for policy 1, policy_version 5330 (0.0008) -[2023-10-12 03:17:49,298][78123] Updated weights for policy 1, policy_version 5340 (0.0008) -[2023-10-12 03:17:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 10944512. Throughput: 0: 1596.0, 1: 1591.0. Samples: 2744374. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-12 03:17:50,201][77203] Avg episode reward: [(0, '22.840'), (1, '27.040')] -[2023-10-12 03:17:50,305][78091] Updated weights for policy 0, policy_version 5350 (0.0010) -[2023-10-12 03:17:50,671][78091] Updated weights for policy 0, policy_version 5360 (0.0008) -[2023-10-12 03:17:51,054][78091] Updated weights for policy 0, policy_version 5370 (0.0009) -[2023-10-12 03:17:53,497][78123] Updated weights for policy 1, policy_version 5350 (0.0008) -[2023-10-12 03:17:53,872][78123] Updated weights for policy 1, policy_version 5360 (0.0010) -[2023-10-12 03:17:54,234][78123] Updated weights for policy 1, policy_version 5370 (0.0008) -[2023-10-12 03:17:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 11010048. Throughput: 0: 1611.2, 1: 1574.8. Samples: 2763292. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-12 03:17:55,201][77203] Avg episode reward: [(0, '22.600'), (1, '30.960')] -[2023-10-12 03:17:55,210][77950] Saving new best policy, reward=30.960! -[2023-10-12 03:17:55,379][78091] Updated weights for policy 0, policy_version 5380 (0.0008) -[2023-10-12 03:17:55,753][78091] Updated weights for policy 0, policy_version 5390 (0.0007) -[2023-10-12 03:17:56,122][78091] Updated weights for policy 0, policy_version 5400 (0.0009) -[2023-10-12 03:17:58,584][78123] Updated weights for policy 1, policy_version 5380 (0.0009) -[2023-10-12 03:17:58,953][78123] Updated weights for policy 1, policy_version 5390 (0.0008) -[2023-10-12 03:17:59,315][78123] Updated weights for policy 1, policy_version 5400 (0.0009) -[2023-10-12 03:18:00,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 11075584. Throughput: 0: 1594.1, 1: 1591.6. Samples: 2773098. Policy #0 lag: (min: 3.0, avg: 9.3, max: 35.0) -[2023-10-12 03:18:00,202][77203] Avg episode reward: [(0, '24.090'), (1, '29.180')] -[2023-10-12 03:18:00,394][78091] Updated weights for policy 0, policy_version 5410 (0.0009) -[2023-10-12 03:18:00,759][78091] Updated weights for policy 0, policy_version 5420 (0.0009) -[2023-10-12 03:18:01,132][78091] Updated weights for policy 0, policy_version 5430 (0.0009) -[2023-10-12 03:18:01,499][78091] Updated weights for policy 0, policy_version 5440 (0.0009) -[2023-10-12 03:18:03,715][78123] Updated weights for policy 1, policy_version 5410 (0.0007) -[2023-10-12 03:18:04,079][78123] Updated weights for policy 1, policy_version 5420 (0.0008) -[2023-10-12 03:18:04,465][78123] Updated weights for policy 1, policy_version 5430 (0.0008) -[2023-10-12 03:18:04,831][78123] Updated weights for policy 1, policy_version 5440 (0.0009) -[2023-10-12 03:18:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 11141120. Throughput: 0: 1590.6, 1: 1602.8. Samples: 2792670. Policy #0 lag: (min: 3.0, avg: 9.3, max: 35.0) -[2023-10-12 03:18:05,201][77203] Avg episode reward: [(0, '23.800'), (1, '32.930')] -[2023-10-12 03:18:05,202][77950] Saving new best policy, reward=32.930! -[2023-10-12 03:18:05,833][78091] Updated weights for policy 0, policy_version 5450 (0.0010) -[2023-10-12 03:18:06,205][78091] Updated weights for policy 0, policy_version 5460 (0.0009) -[2023-10-12 03:18:06,578][78091] Updated weights for policy 0, policy_version 5470 (0.0009) -[2023-10-12 03:18:09,039][78123] Updated weights for policy 1, policy_version 5450 (0.0011) -[2023-10-12 03:18:09,407][78123] Updated weights for policy 1, policy_version 5460 (0.0010) -[2023-10-12 03:18:09,783][78123] Updated weights for policy 1, policy_version 5470 (0.0008) -[2023-10-12 03:18:10,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 11206656. Throughput: 0: 1599.3, 1: 1587.0. Samples: 2811232. Policy #0 lag: (min: 31.0, avg: 45.3, max: 63.0) -[2023-10-12 03:18:10,201][77203] Avg episode reward: [(0, '22.230'), (1, '29.380')] -[2023-10-12 03:18:11,010][78091] Updated weights for policy 0, policy_version 5480 (0.0010) -[2023-10-12 03:18:11,388][78091] Updated weights for policy 0, policy_version 5490 (0.0010) -[2023-10-12 03:18:11,763][78091] Updated weights for policy 0, policy_version 5500 (0.0010) -[2023-10-12 03:18:14,120][78123] Updated weights for policy 1, policy_version 5480 (0.0009) -[2023-10-12 03:18:14,490][78123] Updated weights for policy 1, policy_version 5490 (0.0009) -[2023-10-12 03:18:14,858][78123] Updated weights for policy 1, policy_version 5500 (0.0008) -[2023-10-12 03:18:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 11272192. Throughput: 0: 1587.1, 1: 1587.5. Samples: 2820722. Policy #0 lag: (min: 31.0, avg: 45.3, max: 63.0) -[2023-10-12 03:18:15,201][77203] Avg episode reward: [(0, '22.750'), (1, '28.170')] -[2023-10-12 03:18:15,985][78091] Updated weights for policy 0, policy_version 5510 (0.0008) -[2023-10-12 03:18:16,352][78091] Updated weights for policy 0, policy_version 5520 (0.0009) -[2023-10-12 03:18:16,726][78091] Updated weights for policy 0, policy_version 5530 (0.0008) -[2023-10-12 03:18:19,325][78123] Updated weights for policy 1, policy_version 5510 (0.0009) -[2023-10-12 03:18:19,693][78123] Updated weights for policy 1, policy_version 5520 (0.0010) -[2023-10-12 03:18:20,047][78123] Updated weights for policy 1, policy_version 5530 (0.0007) -[2023-10-12 03:18:20,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 11304960. Throughput: 0: 1591.2, 1: 1607.3. Samples: 2840230. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:18:20,202][77203] Avg episode reward: [(0, '22.290'), (1, '24.780')] -[2023-10-12 03:18:21,042][78091] Updated weights for policy 0, policy_version 5540 (0.0009) -[2023-10-12 03:18:21,423][78091] Updated weights for policy 0, policy_version 5550 (0.0010) -[2023-10-12 03:18:21,801][78091] Updated weights for policy 0, policy_version 5560 (0.0010) -[2023-10-12 03:18:24,593][78123] Updated weights for policy 1, policy_version 5540 (0.0008) -[2023-10-12 03:18:24,988][78123] Updated weights for policy 1, policy_version 5550 (0.0008) -[2023-10-12 03:18:25,201][77203] Fps is (10 sec: 9830.2, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 11370496. Throughput: 0: 1582.2, 1: 1604.0. Samples: 2859036. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:18:25,202][77203] Avg episode reward: [(0, '23.220'), (1, '27.500')] -[2023-10-12 03:18:25,352][78123] Updated weights for policy 1, policy_version 5560 (0.0007) -[2023-10-12 03:18:25,999][78091] Updated weights for policy 0, policy_version 5570 (0.0009) -[2023-10-12 03:18:26,376][78091] Updated weights for policy 0, policy_version 5580 (0.0007) -[2023-10-12 03:18:26,742][78091] Updated weights for policy 0, policy_version 5590 (0.0010) -[2023-10-12 03:18:27,119][78091] Updated weights for policy 0, policy_version 5600 (0.0009) -[2023-10-12 03:18:29,776][78123] Updated weights for policy 1, policy_version 5570 (0.0009) -[2023-10-12 03:18:30,144][78123] Updated weights for policy 1, policy_version 5580 (0.0009) -[2023-10-12 03:18:30,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 11436032. Throughput: 0: 1583.0, 1: 1582.5. Samples: 2867864. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:18:30,201][77203] Avg episode reward: [(0, '23.690'), (1, '25.740')] -[2023-10-12 03:18:30,512][78123] Updated weights for policy 1, policy_version 5590 (0.0009) -[2023-10-12 03:18:30,871][78123] Updated weights for policy 1, policy_version 5600 (0.0008) -[2023-10-12 03:18:31,308][78091] Updated weights for policy 0, policy_version 5610 (0.0008) -[2023-10-12 03:18:31,675][78091] Updated weights for policy 0, policy_version 5620 (0.0008) -[2023-10-12 03:18:32,050][78091] Updated weights for policy 0, policy_version 5630 (0.0007) -[2023-10-12 03:18:35,093][78123] Updated weights for policy 1, policy_version 5610 (0.0007) -[2023-10-12 03:18:35,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 11501568. Throughput: 0: 1586.0, 1: 1593.1. Samples: 2887436. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:18:35,201][77203] Avg episode reward: [(0, '22.760'), (1, '28.760')] -[2023-10-12 03:18:35,461][78123] Updated weights for policy 1, policy_version 5620 (0.0008) -[2023-10-12 03:18:35,820][78123] Updated weights for policy 1, policy_version 5630 (0.0007) -[2023-10-12 03:18:36,396][78091] Updated weights for policy 0, policy_version 5640 (0.0007) -[2023-10-12 03:18:36,768][78091] Updated weights for policy 0, policy_version 5650 (0.0008) -[2023-10-12 03:18:37,141][78091] Updated weights for policy 0, policy_version 5660 (0.0008) -[2023-10-12 03:18:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 11567104. Throughput: 0: 1592.8, 1: 1603.1. Samples: 2907106. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:18:40,201][77203] Avg episode reward: [(0, '22.380'), (1, '28.510')] -[2023-10-12 03:18:40,301][78123] Updated weights for policy 1, policy_version 5640 (0.0009) -[2023-10-12 03:18:40,667][78123] Updated weights for policy 1, policy_version 5650 (0.0010) -[2023-10-12 03:18:41,033][78123] Updated weights for policy 1, policy_version 5660 (0.0009) -[2023-10-12 03:18:41,300][78091] Updated weights for policy 0, policy_version 5670 (0.0007) -[2023-10-12 03:18:41,676][78091] Updated weights for policy 0, policy_version 5680 (0.0007) -[2023-10-12 03:18:42,052][78091] Updated weights for policy 0, policy_version 5690 (0.0010) -[2023-10-12 03:18:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 11632640. Throughput: 0: 1594.6, 1: 1578.4. Samples: 2915884. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:18:45,201][77203] Avg episode reward: [(0, '22.320'), (1, '32.000')] -[2023-10-12 03:18:45,430][78123] Updated weights for policy 1, policy_version 5670 (0.0007) -[2023-10-12 03:18:45,796][78123] Updated weights for policy 1, policy_version 5680 (0.0008) -[2023-10-12 03:18:46,170][78123] Updated weights for policy 1, policy_version 5690 (0.0009) -[2023-10-12 03:18:46,230][78091] Updated weights for policy 0, policy_version 5700 (0.0009) -[2023-10-12 03:18:46,596][78091] Updated weights for policy 0, policy_version 5710 (0.0009) -[2023-10-12 03:18:46,972][78091] Updated weights for policy 0, policy_version 5720 (0.0008) -[2023-10-12 03:18:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 11698176. Throughput: 0: 1593.0, 1: 1575.3. Samples: 2935244. Policy #0 lag: (min: 1.0, avg: 1.1, max: 5.0) -[2023-10-12 03:18:50,201][77203] Avg episode reward: [(0, '22.810'), (1, '29.600')] -[2023-10-12 03:18:50,424][78123] Updated weights for policy 1, policy_version 5700 (0.0007) -[2023-10-12 03:18:50,787][78123] Updated weights for policy 1, policy_version 5710 (0.0007) -[2023-10-12 03:18:51,157][78123] Updated weights for policy 1, policy_version 5720 (0.0008) -[2023-10-12 03:18:51,473][78091] Updated weights for policy 0, policy_version 5730 (0.0010) -[2023-10-12 03:18:51,843][78091] Updated weights for policy 0, policy_version 5740 (0.0010) -[2023-10-12 03:18:52,204][78091] Updated weights for policy 0, policy_version 5750 (0.0009) -[2023-10-12 03:18:52,576][78091] Updated weights for policy 0, policy_version 5760 (0.0009) -[2023-10-12 03:18:55,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 11763712. Throughput: 0: 1591.0, 1: 1592.6. Samples: 2954492. Policy #0 lag: (min: 1.0, avg: 1.1, max: 5.0) -[2023-10-12 03:18:55,202][77203] Avg episode reward: [(0, '23.090'), (1, '29.110')] -[2023-10-12 03:18:55,600][78123] Updated weights for policy 1, policy_version 5730 (0.0009) -[2023-10-12 03:18:55,964][78123] Updated weights for policy 1, policy_version 5740 (0.0010) -[2023-10-12 03:18:56,333][78123] Updated weights for policy 1, policy_version 5750 (0.0009) -[2023-10-12 03:18:56,702][78123] Updated weights for policy 1, policy_version 5760 (0.0009) -[2023-10-12 03:18:56,901][78091] Updated weights for policy 0, policy_version 5770 (0.0007) -[2023-10-12 03:18:57,284][78091] Updated weights for policy 0, policy_version 5780 (0.0007) -[2023-10-12 03:18:57,654][78091] Updated weights for policy 0, policy_version 5790 (0.0009) -[2023-10-12 03:19:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 11829248. Throughput: 0: 1596.2, 1: 1567.5. Samples: 2963090. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:19:00,201][77203] Avg episode reward: [(0, '24.030'), (1, '28.920')] -[2023-10-12 03:19:01,001][78123] Updated weights for policy 1, policy_version 5770 (0.0008) -[2023-10-12 03:19:01,362][78123] Updated weights for policy 1, policy_version 5780 (0.0010) -[2023-10-12 03:19:01,734][78123] Updated weights for policy 1, policy_version 5790 (0.0008) -[2023-10-12 03:19:02,176][78091] Updated weights for policy 0, policy_version 5800 (0.0009) -[2023-10-12 03:19:02,553][78091] Updated weights for policy 0, policy_version 5810 (0.0010) -[2023-10-12 03:19:02,928][78091] Updated weights for policy 0, policy_version 5820 (0.0008) -[2023-10-12 03:19:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 11894784. Throughput: 0: 1589.6, 1: 1572.4. Samples: 2982518. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:19:05,202][77203] Avg episode reward: [(0, '21.780'), (1, '28.280')] -[2023-10-12 03:19:05,890][78123] Updated weights for policy 1, policy_version 5800 (0.0010) -[2023-10-12 03:19:06,267][78123] Updated weights for policy 1, policy_version 5810 (0.0010) -[2023-10-12 03:19:06,627][78123] Updated weights for policy 1, policy_version 5820 (0.0007) -[2023-10-12 03:19:07,202][78091] Updated weights for policy 0, policy_version 5830 (0.0010) -[2023-10-12 03:19:07,585][78091] Updated weights for policy 0, policy_version 5840 (0.0007) -[2023-10-12 03:19:07,960][78091] Updated weights for policy 0, policy_version 5850 (0.0008) -[2023-10-12 03:19:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 11960320. Throughput: 0: 1595.7, 1: 1580.1. Samples: 3001946. Policy #0 lag: (min: 17.0, avg: 27.5, max: 49.0) -[2023-10-12 03:19:10,201][77203] Avg episode reward: [(0, '21.670'), (1, '27.710')] -[2023-10-12 03:19:10,210][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000005824_5963776.pth... -[2023-10-12 03:19:10,210][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000005856_5996544.pth... -[2023-10-12 03:19:10,251][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000004352_4456448.pth -[2023-10-12 03:19:10,252][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000004352_4456448.pth -[2023-10-12 03:19:11,133][78123] Updated weights for policy 1, policy_version 5830 (0.0008) -[2023-10-12 03:19:11,513][78123] Updated weights for policy 1, policy_version 5840 (0.0009) -[2023-10-12 03:19:11,884][78123] Updated weights for policy 1, policy_version 5850 (0.0010) -[2023-10-12 03:19:12,320][78091] Updated weights for policy 0, policy_version 5860 (0.0008) -[2023-10-12 03:19:12,697][78091] Updated weights for policy 0, policy_version 5870 (0.0008) -[2023-10-12 03:19:13,074][78091] Updated weights for policy 0, policy_version 5880 (0.0007) -[2023-10-12 03:19:15,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 12025856. Throughput: 0: 1606.5, 1: 1575.4. Samples: 3011050. Policy #0 lag: (min: 17.0, avg: 27.5, max: 49.0) -[2023-10-12 03:19:15,203][77203] Avg episode reward: [(0, '25.930'), (1, '25.180')] -[2023-10-12 03:19:15,204][77792] Saving new best policy, reward=25.930! -[2023-10-12 03:19:16,358][78123] Updated weights for policy 1, policy_version 5860 (0.0010) -[2023-10-12 03:19:16,723][78123] Updated weights for policy 1, policy_version 5870 (0.0011) -[2023-10-12 03:19:17,090][78123] Updated weights for policy 1, policy_version 5880 (0.0011) -[2023-10-12 03:19:17,471][78091] Updated weights for policy 0, policy_version 5890 (0.0008) -[2023-10-12 03:19:17,844][78091] Updated weights for policy 0, policy_version 5900 (0.0008) -[2023-10-12 03:19:18,218][78091] Updated weights for policy 0, policy_version 5910 (0.0007) -[2023-10-12 03:19:18,592][78091] Updated weights for policy 0, policy_version 5920 (0.0008) -[2023-10-12 03:19:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 12091392. Throughput: 0: 1591.6, 1: 1570.6. Samples: 3029734. Policy #0 lag: (min: 7.0, avg: 7.1, max: 13.0) -[2023-10-12 03:19:20,201][77203] Avg episode reward: [(0, '22.300'), (1, '30.950')] -[2023-10-12 03:19:21,531][78123] Updated weights for policy 1, policy_version 5890 (0.0009) -[2023-10-12 03:19:21,902][78123] Updated weights for policy 1, policy_version 5900 (0.0007) -[2023-10-12 03:19:22,271][78123] Updated weights for policy 1, policy_version 5910 (0.0010) -[2023-10-12 03:19:22,638][78123] Updated weights for policy 1, policy_version 5920 (0.0009) -[2023-10-12 03:19:22,894][78091] Updated weights for policy 0, policy_version 5930 (0.0008) -[2023-10-12 03:19:23,271][78091] Updated weights for policy 0, policy_version 5940 (0.0009) -[2023-10-12 03:19:23,642][78091] Updated weights for policy 0, policy_version 5950 (0.0009) -[2023-10-12 03:19:25,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 12156928. Throughput: 0: 1582.3, 1: 1575.6. Samples: 3049214. Policy #0 lag: (min: 7.0, avg: 7.1, max: 13.0) -[2023-10-12 03:19:25,202][77203] Avg episode reward: [(0, '22.420'), (1, '26.290')] -[2023-10-12 03:19:26,894][78123] Updated weights for policy 1, policy_version 5930 (0.0009) -[2023-10-12 03:19:27,263][78123] Updated weights for policy 1, policy_version 5940 (0.0007) -[2023-10-12 03:19:27,647][78123] Updated weights for policy 1, policy_version 5950 (0.0009) -[2023-10-12 03:19:28,042][78091] Updated weights for policy 0, policy_version 5960 (0.0008) -[2023-10-12 03:19:28,419][78091] Updated weights for policy 0, policy_version 5970 (0.0009) -[2023-10-12 03:19:28,799][78091] Updated weights for policy 0, policy_version 5980 (0.0008) -[2023-10-12 03:19:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 12222464. Throughput: 0: 1604.1, 1: 1575.5. Samples: 3058964. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:19:30,201][77203] Avg episode reward: [(0, '23.610'), (1, '29.130')] -[2023-10-12 03:19:32,042][78123] Updated weights for policy 1, policy_version 5960 (0.0008) -[2023-10-12 03:19:32,410][78123] Updated weights for policy 1, policy_version 5970 (0.0008) -[2023-10-12 03:19:32,774][78123] Updated weights for policy 1, policy_version 5980 (0.0009) -[2023-10-12 03:19:33,080][78091] Updated weights for policy 0, policy_version 5990 (0.0007) -[2023-10-12 03:19:33,454][78091] Updated weights for policy 0, policy_version 6000 (0.0008) -[2023-10-12 03:19:33,829][78091] Updated weights for policy 0, policy_version 6010 (0.0008) -[2023-10-12 03:19:35,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 12288000. Throughput: 0: 1589.6, 1: 1579.7. Samples: 3077864. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:19:35,202][77203] Avg episode reward: [(0, '23.260'), (1, '28.230')] -[2023-10-12 03:19:37,022][78123] Updated weights for policy 1, policy_version 5990 (0.0009) -[2023-10-12 03:19:37,385][78123] Updated weights for policy 1, policy_version 6000 (0.0008) -[2023-10-12 03:19:37,749][78123] Updated weights for policy 1, policy_version 6010 (0.0010) -[2023-10-12 03:19:38,004][78091] Updated weights for policy 0, policy_version 6020 (0.0008) -[2023-10-12 03:19:38,387][78091] Updated weights for policy 0, policy_version 6030 (0.0008) -[2023-10-12 03:19:38,754][78091] Updated weights for policy 0, policy_version 6040 (0.0008) -[2023-10-12 03:19:40,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 12353536. Throughput: 0: 1588.9, 1: 1580.9. Samples: 3097134. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 03:19:40,202][77203] Avg episode reward: [(0, '24.630'), (1, '27.570')] -[2023-10-12 03:19:42,211][78123] Updated weights for policy 1, policy_version 6020 (0.0008) -[2023-10-12 03:19:42,579][78123] Updated weights for policy 1, policy_version 6030 (0.0008) -[2023-10-12 03:19:42,953][78123] Updated weights for policy 1, policy_version 6040 (0.0007) -[2023-10-12 03:19:43,042][78091] Updated weights for policy 0, policy_version 6050 (0.0009) -[2023-10-12 03:19:43,403][78091] Updated weights for policy 0, policy_version 6060 (0.0007) -[2023-10-12 03:19:43,786][78091] Updated weights for policy 0, policy_version 6070 (0.0008) -[2023-10-12 03:19:44,154][78091] Updated weights for policy 0, policy_version 6080 (0.0009) -[2023-10-12 03:19:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 12419072. Throughput: 0: 1613.3, 1: 1594.0. Samples: 3107420. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 03:19:45,201][77203] Avg episode reward: [(0, '22.310'), (1, '26.800')] -[2023-10-12 03:19:47,370][78123] Updated weights for policy 1, policy_version 6050 (0.0007) -[2023-10-12 03:19:47,742][78123] Updated weights for policy 1, policy_version 6060 (0.0008) -[2023-10-12 03:19:48,107][78123] Updated weights for policy 1, policy_version 6070 (0.0008) -[2023-10-12 03:19:48,295][78091] Updated weights for policy 0, policy_version 6090 (0.0008) -[2023-10-12 03:19:48,472][78123] Updated weights for policy 1, policy_version 6080 (0.0007) -[2023-10-12 03:19:48,667][78091] Updated weights for policy 0, policy_version 6100 (0.0007) -[2023-10-12 03:19:49,050][78091] Updated weights for policy 0, policy_version 6110 (0.0009) -[2023-10-12 03:19:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 12484608. Throughput: 0: 1599.5, 1: 1579.1. Samples: 3125556. Policy #0 lag: (min: 24.0, avg: 48.4, max: 56.0) -[2023-10-12 03:19:50,202][77203] Avg episode reward: [(0, '23.130'), (1, '27.260')] -[2023-10-12 03:19:52,800][78123] Updated weights for policy 1, policy_version 6090 (0.0009) -[2023-10-12 03:19:53,178][78123] Updated weights for policy 1, policy_version 6100 (0.0008) -[2023-10-12 03:19:53,539][78123] Updated weights for policy 1, policy_version 6110 (0.0009) -[2023-10-12 03:19:53,630][78091] Updated weights for policy 0, policy_version 6120 (0.0008) -[2023-10-12 03:19:53,996][78091] Updated weights for policy 0, policy_version 6130 (0.0008) -[2023-10-12 03:19:54,371][78091] Updated weights for policy 0, policy_version 6140 (0.0007) -[2023-10-12 03:19:55,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 12774.0). Total num frames: 12550144. Throughput: 0: 1590.4, 1: 1579.4. Samples: 3144586. Policy #0 lag: (min: 24.0, avg: 48.4, max: 56.0) -[2023-10-12 03:19:55,201][77203] Avg episode reward: [(0, '22.720'), (1, '31.600')] -[2023-10-12 03:19:57,744][78123] Updated weights for policy 1, policy_version 6120 (0.0009) -[2023-10-12 03:19:58,105][78123] Updated weights for policy 1, policy_version 6130 (0.0007) -[2023-10-12 03:19:58,468][78123] Updated weights for policy 1, policy_version 6140 (0.0007) -[2023-10-12 03:19:58,506][78091] Updated weights for policy 0, policy_version 6150 (0.0009) -[2023-10-12 03:19:58,873][78091] Updated weights for policy 0, policy_version 6160 (0.0008) -[2023-10-12 03:19:59,241][78091] Updated weights for policy 0, policy_version 6170 (0.0007) -[2023-10-12 03:20:00,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 12615680. Throughput: 0: 1603.7, 1: 1596.9. Samples: 3155078. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:20:00,202][77203] Avg episode reward: [(0, '22.750'), (1, '26.000')] -[2023-10-12 03:20:02,781][78123] Updated weights for policy 1, policy_version 6150 (0.0008) -[2023-10-12 03:20:03,137][78123] Updated weights for policy 1, policy_version 6160 (0.0008) -[2023-10-12 03:20:03,510][78123] Updated weights for policy 1, policy_version 6170 (0.0007) -[2023-10-12 03:20:03,587][78091] Updated weights for policy 0, policy_version 6180 (0.0009) -[2023-10-12 03:20:03,965][78091] Updated weights for policy 0, policy_version 6190 (0.0008) -[2023-10-12 03:20:04,331][78091] Updated weights for policy 0, policy_version 6200 (0.0008) -[2023-10-12 03:20:05,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 12681216. Throughput: 0: 1614.5, 1: 1581.9. Samples: 3173574. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:20:05,202][77203] Avg episode reward: [(0, '23.070'), (1, '27.950')] -[2023-10-12 03:20:07,776][78123] Updated weights for policy 1, policy_version 6180 (0.0008) -[2023-10-12 03:20:08,144][78123] Updated weights for policy 1, policy_version 6190 (0.0007) -[2023-10-12 03:20:08,516][78123] Updated weights for policy 1, policy_version 6200 (0.0008) -[2023-10-12 03:20:08,612][78091] Updated weights for policy 0, policy_version 6210 (0.0008) -[2023-10-12 03:20:08,983][78091] Updated weights for policy 0, policy_version 6220 (0.0009) -[2023-10-12 03:20:09,352][78091] Updated weights for policy 0, policy_version 6230 (0.0010) -[2023-10-12 03:20:09,724][78091] Updated weights for policy 0, policy_version 6240 (0.0008) -[2023-10-12 03:20:10,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 12746752. Throughput: 0: 1592.4, 1: 1583.4. Samples: 3192124. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:20:10,203][77203] Avg episode reward: [(0, '23.210'), (1, '28.650')] -[2023-10-12 03:20:12,831][78123] Updated weights for policy 1, policy_version 6210 (0.0009) -[2023-10-12 03:20:13,207][78123] Updated weights for policy 1, policy_version 6220 (0.0008) -[2023-10-12 03:20:13,577][78123] Updated weights for policy 1, policy_version 6230 (0.0007) -[2023-10-12 03:20:13,954][78123] Updated weights for policy 1, policy_version 6240 (0.0007) -[2023-10-12 03:20:14,024][78091] Updated weights for policy 0, policy_version 6250 (0.0008) -[2023-10-12 03:20:14,381][78091] Updated weights for policy 0, policy_version 6260 (0.0008) -[2023-10-12 03:20:14,754][78091] Updated weights for policy 0, policy_version 6270 (0.0009) -[2023-10-12 03:20:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 12812288. Throughput: 0: 1597.8, 1: 1606.7. Samples: 3203164. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:20:15,202][77203] Avg episode reward: [(0, '22.670'), (1, '28.030')] -[2023-10-12 03:20:18,290][78123] Updated weights for policy 1, policy_version 6250 (0.0010) -[2023-10-12 03:20:18,659][78123] Updated weights for policy 1, policy_version 6260 (0.0008) -[2023-10-12 03:20:19,024][78123] Updated weights for policy 1, policy_version 6270 (0.0008) -[2023-10-12 03:20:19,102][78091] Updated weights for policy 0, policy_version 6280 (0.0007) -[2023-10-12 03:20:19,470][78091] Updated weights for policy 0, policy_version 6290 (0.0008) -[2023-10-12 03:20:19,842][78091] Updated weights for policy 0, policy_version 6300 (0.0010) -[2023-10-12 03:20:20,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.1, 300 sec: 12885.0). Total num frames: 12877824. Throughput: 0: 1615.2, 1: 1583.8. Samples: 3221820. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-12 03:20:20,202][77203] Avg episode reward: [(0, '23.090'), (1, '30.740')] -[2023-10-12 03:20:23,407][78123] Updated weights for policy 1, policy_version 6280 (0.0009) -[2023-10-12 03:20:23,774][78123] Updated weights for policy 1, policy_version 6290 (0.0010) -[2023-10-12 03:20:24,055][78091] Updated weights for policy 0, policy_version 6310 (0.0009) -[2023-10-12 03:20:24,139][78123] Updated weights for policy 1, policy_version 6300 (0.0008) -[2023-10-12 03:20:24,425][78091] Updated weights for policy 0, policy_version 6320 (0.0009) -[2023-10-12 03:20:24,794][78091] Updated weights for policy 0, policy_version 6330 (0.0007) -[2023-10-12 03:20:25,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 12943360. Throughput: 0: 1600.4, 1: 1577.3. Samples: 3240128. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-12 03:20:25,202][77203] Avg episode reward: [(0, '23.740'), (1, '30.610')] -[2023-10-12 03:20:28,544][78123] Updated weights for policy 1, policy_version 6310 (0.0008) -[2023-10-12 03:20:28,907][78123] Updated weights for policy 1, policy_version 6320 (0.0008) -[2023-10-12 03:20:29,125][78091] Updated weights for policy 0, policy_version 6340 (0.0010) -[2023-10-12 03:20:29,276][78123] Updated weights for policy 1, policy_version 6330 (0.0009) -[2023-10-12 03:20:29,494][78091] Updated weights for policy 0, policy_version 6350 (0.0010) -[2023-10-12 03:20:29,869][78091] Updated weights for policy 0, policy_version 6360 (0.0009) -[2023-10-12 03:20:30,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 13008896. Throughput: 0: 1594.0, 1: 1591.8. Samples: 3250784. Policy #0 lag: (min: 6.0, avg: 8.7, max: 38.0) -[2023-10-12 03:20:30,201][77203] Avg episode reward: [(0, '22.810'), (1, '28.280')] -[2023-10-12 03:20:33,540][78123] Updated weights for policy 1, policy_version 6340 (0.0009) -[2023-10-12 03:20:33,908][78123] Updated weights for policy 1, policy_version 6350 (0.0010) -[2023-10-12 03:20:34,268][78091] Updated weights for policy 0, policy_version 6370 (0.0010) -[2023-10-12 03:20:34,281][78123] Updated weights for policy 1, policy_version 6360 (0.0010) -[2023-10-12 03:20:34,636][78091] Updated weights for policy 0, policy_version 6380 (0.0010) -[2023-10-12 03:20:35,010][78091] Updated weights for policy 0, policy_version 6390 (0.0009) -[2023-10-12 03:20:35,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 13041664. Throughput: 0: 1609.4, 1: 1600.3. Samples: 3269994. Policy #0 lag: (min: 6.0, avg: 8.7, max: 38.0) -[2023-10-12 03:20:35,202][77203] Avg episode reward: [(0, '23.250'), (1, '32.220')] -[2023-10-12 03:20:35,373][78091] Updated weights for policy 0, policy_version 6400 (0.0008) -[2023-10-12 03:20:38,629][78123] Updated weights for policy 1, policy_version 6370 (0.0009) -[2023-10-12 03:20:38,995][78123] Updated weights for policy 1, policy_version 6380 (0.0011) -[2023-10-12 03:20:39,368][78123] Updated weights for policy 1, policy_version 6390 (0.0010) -[2023-10-12 03:20:39,728][78123] Updated weights for policy 1, policy_version 6400 (0.0009) -[2023-10-12 03:20:39,741][78091] Updated weights for policy 0, policy_version 6410 (0.0007) -[2023-10-12 03:20:40,110][78091] Updated weights for policy 0, policy_version 6420 (0.0010) -[2023-10-12 03:20:40,201][77203] Fps is (10 sec: 9830.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 13107200. Throughput: 0: 1610.3, 1: 1581.3. Samples: 3288208. Policy #0 lag: (min: 6.0, avg: 8.7, max: 38.0) -[2023-10-12 03:20:40,202][77203] Avg episode reward: [(0, '20.970'), (1, '27.620')] -[2023-10-12 03:20:40,485][78091] Updated weights for policy 0, policy_version 6430 (0.0008) -[2023-10-12 03:20:44,194][78123] Updated weights for policy 1, policy_version 6410 (0.0010) -[2023-10-12 03:20:44,557][78123] Updated weights for policy 1, policy_version 6420 (0.0009) -[2023-10-12 03:20:44,850][78091] Updated weights for policy 0, policy_version 6440 (0.0008) -[2023-10-12 03:20:44,932][78123] Updated weights for policy 1, policy_version 6430 (0.0008) -[2023-10-12 03:20:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 13172736. Throughput: 0: 1592.7, 1: 1589.7. Samples: 3298286. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-10-12 03:20:45,201][77203] Avg episode reward: [(0, '24.180'), (1, '29.880')] -[2023-10-12 03:20:45,220][78091] Updated weights for policy 0, policy_version 6450 (0.0007) -[2023-10-12 03:20:45,592][78091] Updated weights for policy 0, policy_version 6460 (0.0010) -[2023-10-12 03:20:49,355][78123] Updated weights for policy 1, policy_version 6440 (0.0008) -[2023-10-12 03:20:49,721][78123] Updated weights for policy 1, policy_version 6450 (0.0008) -[2023-10-12 03:20:49,885][78091] Updated weights for policy 0, policy_version 6470 (0.0009) -[2023-10-12 03:20:50,093][78123] Updated weights for policy 1, policy_version 6460 (0.0007) -[2023-10-12 03:20:50,201][77203] Fps is (10 sec: 9830.6, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 13205504. Throughput: 0: 1595.7, 1: 1605.4. Samples: 3317622. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-10-12 03:20:50,201][77203] Avg episode reward: [(0, '23.700'), (1, '27.280')] -[2023-10-12 03:20:50,260][78091] Updated weights for policy 0, policy_version 6480 (0.0007) -[2023-10-12 03:20:50,640][78091] Updated weights for policy 0, policy_version 6490 (0.0007) -[2023-10-12 03:20:54,311][78123] Updated weights for policy 1, policy_version 6470 (0.0009) -[2023-10-12 03:20:54,678][78123] Updated weights for policy 1, policy_version 6480 (0.0010) -[2023-10-12 03:20:54,850][78091] Updated weights for policy 0, policy_version 6500 (0.0009) -[2023-10-12 03:20:55,047][78123] Updated weights for policy 1, policy_version 6490 (0.0007) -[2023-10-12 03:20:55,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 13271040. Throughput: 0: 1615.7, 1: 1592.6. Samples: 3336500. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) -[2023-10-12 03:20:55,202][77203] Avg episode reward: [(0, '22.740'), (1, '29.170')] -[2023-10-12 03:20:55,208][78091] Updated weights for policy 0, policy_version 6510 (0.0007) -[2023-10-12 03:20:55,589][78091] Updated weights for policy 0, policy_version 6520 (0.0007) -[2023-10-12 03:20:59,481][78123] Updated weights for policy 1, policy_version 6500 (0.0007) -[2023-10-12 03:20:59,835][78091] Updated weights for policy 0, policy_version 6530 (0.0007) -[2023-10-12 03:20:59,858][78123] Updated weights for policy 1, policy_version 6510 (0.0009) -[2023-10-12 03:21:00,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 13336576. Throughput: 0: 1593.7, 1: 1577.2. Samples: 3345852. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) -[2023-10-12 03:21:00,201][77203] Avg episode reward: [(0, '23.330'), (1, '26.550')] -[2023-10-12 03:21:00,210][78091] Updated weights for policy 0, policy_version 6540 (0.0010) -[2023-10-12 03:21:00,213][78123] Updated weights for policy 1, policy_version 6520 (0.0009) -[2023-10-12 03:21:00,578][78091] Updated weights for policy 0, policy_version 6550 (0.0008) -[2023-10-12 03:21:00,955][78091] Updated weights for policy 0, policy_version 6560 (0.0010) -[2023-10-12 03:21:04,537][78123] Updated weights for policy 1, policy_version 6530 (0.0009) -[2023-10-12 03:21:04,911][78123] Updated weights for policy 1, policy_version 6540 (0.0008) -[2023-10-12 03:21:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 13402112. Throughput: 0: 1594.1, 1: 1599.6. Samples: 3365538. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:21:05,202][77203] Avg episode reward: [(0, '21.480'), (1, '28.750')] -[2023-10-12 03:21:05,214][78091] Updated weights for policy 0, policy_version 6570 (0.0008) -[2023-10-12 03:21:05,280][78123] Updated weights for policy 1, policy_version 6550 (0.0007) -[2023-10-12 03:21:05,596][78091] Updated weights for policy 0, policy_version 6580 (0.0008) -[2023-10-12 03:21:05,642][78123] Updated weights for policy 1, policy_version 6560 (0.0007) -[2023-10-12 03:21:05,956][78091] Updated weights for policy 0, policy_version 6590 (0.0007) -[2023-10-12 03:21:10,109][78123] Updated weights for policy 1, policy_version 6570 (0.0010) -[2023-10-12 03:21:10,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 13467648. Throughput: 0: 1610.8, 1: 1602.9. Samples: 3384746. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:21:10,201][77203] Avg episode reward: [(0, '23.250'), (1, '26.490')] -[2023-10-12 03:21:10,430][78091] Updated weights for policy 0, policy_version 6600 (0.0008) -[2023-10-12 03:21:10,476][78123] Updated weights for policy 1, policy_version 6580 (0.0010) -[2023-10-12 03:21:10,812][78091] Updated weights for policy 0, policy_version 6610 (0.0007) -[2023-10-12 03:21:10,831][78123] Updated weights for policy 1, policy_version 6590 (0.0010) -[2023-10-12 03:21:10,905][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000006592_6750208.pth... -[2023-10-12 03:21:10,943][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000005088_5210112.pth -[2023-10-12 03:21:11,169][78091] Updated weights for policy 0, policy_version 6620 (0.0008) -[2023-10-12 03:21:11,316][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000006624_6782976.pth... -[2023-10-12 03:21:11,356][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000005120_5242880.pth -[2023-10-12 03:21:15,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 13533184. Throughput: 0: 1591.3, 1: 1579.9. Samples: 3393488. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-12 03:21:15,201][77203] Avg episode reward: [(0, '23.390'), (1, '29.070')] -[2023-10-12 03:21:15,272][78123] Updated weights for policy 1, policy_version 6600 (0.0009) -[2023-10-12 03:21:15,422][78091] Updated weights for policy 0, policy_version 6630 (0.0009) -[2023-10-12 03:21:15,640][78123] Updated weights for policy 1, policy_version 6610 (0.0009) -[2023-10-12 03:21:15,789][78091] Updated weights for policy 0, policy_version 6640 (0.0009) -[2023-10-12 03:21:16,009][78123] Updated weights for policy 1, policy_version 6620 (0.0008) -[2023-10-12 03:21:16,156][78091] Updated weights for policy 0, policy_version 6650 (0.0010) -[2023-10-12 03:21:20,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 13598720. Throughput: 0: 1591.7, 1: 1585.7. Samples: 3412978. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-12 03:21:20,202][77203] Avg episode reward: [(0, '23.900'), (1, '29.310')] -[2023-10-12 03:21:20,343][78123] Updated weights for policy 1, policy_version 6630 (0.0009) -[2023-10-12 03:21:20,555][78091] Updated weights for policy 0, policy_version 6660 (0.0009) -[2023-10-12 03:21:20,721][78123] Updated weights for policy 1, policy_version 6640 (0.0008) -[2023-10-12 03:21:20,923][78091] Updated weights for policy 0, policy_version 6670 (0.0008) -[2023-10-12 03:21:21,082][78123] Updated weights for policy 1, policy_version 6650 (0.0007) -[2023-10-12 03:21:21,294][78091] Updated weights for policy 0, policy_version 6680 (0.0008) -[2023-10-12 03:21:25,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 13664256. Throughput: 0: 1602.5, 1: 1601.5. Samples: 3432390. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-12 03:21:25,202][77203] Avg episode reward: [(0, '23.350'), (1, '27.790')] -[2023-10-12 03:21:25,294][78123] Updated weights for policy 1, policy_version 6660 (0.0009) -[2023-10-12 03:21:25,663][78123] Updated weights for policy 1, policy_version 6670 (0.0008) -[2023-10-12 03:21:25,745][78091] Updated weights for policy 0, policy_version 6690 (0.0008) -[2023-10-12 03:21:26,029][78123] Updated weights for policy 1, policy_version 6680 (0.0008) -[2023-10-12 03:21:26,156][78091] Updated weights for policy 0, policy_version 6700 (0.0009) -[2023-10-12 03:21:26,523][78091] Updated weights for policy 0, policy_version 6710 (0.0008) -[2023-10-12 03:21:26,897][78091] Updated weights for policy 0, policy_version 6720 (0.0009) -[2023-10-12 03:21:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 13729792. Throughput: 0: 1590.7, 1: 1578.1. Samples: 3440884. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-12 03:21:30,202][77203] Avg episode reward: [(0, '22.750'), (1, '29.500')] -[2023-10-12 03:21:30,456][78123] Updated weights for policy 1, policy_version 6690 (0.0010) -[2023-10-12 03:21:30,862][78123] Updated weights for policy 1, policy_version 6700 (0.0007) -[2023-10-12 03:21:31,224][78123] Updated weights for policy 1, policy_version 6710 (0.0009) -[2023-10-12 03:21:31,268][78091] Updated weights for policy 0, policy_version 6730 (0.0008) -[2023-10-12 03:21:31,594][78123] Updated weights for policy 1, policy_version 6720 (0.0009) -[2023-10-12 03:21:31,645][78091] Updated weights for policy 0, policy_version 6740 (0.0010) -[2023-10-12 03:21:32,015][78091] Updated weights for policy 0, policy_version 6750 (0.0009) -[2023-10-12 03:21:35,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 13795328. Throughput: 0: 1589.9, 1: 1578.8. Samples: 3460214. Policy #0 lag: (min: 6.0, avg: 8.7, max: 38.0) -[2023-10-12 03:21:35,201][77203] Avg episode reward: [(0, '24.270'), (1, '30.660')] -[2023-10-12 03:21:36,029][78123] Updated weights for policy 1, policy_version 6730 (0.0007) -[2023-10-12 03:21:36,359][78091] Updated weights for policy 0, policy_version 6760 (0.0008) -[2023-10-12 03:21:36,402][78123] Updated weights for policy 1, policy_version 6740 (0.0007) -[2023-10-12 03:21:36,730][78091] Updated weights for policy 0, policy_version 6770 (0.0007) -[2023-10-12 03:21:36,770][78123] Updated weights for policy 1, policy_version 6750 (0.0008) -[2023-10-12 03:21:37,096][78091] Updated weights for policy 0, policy_version 6780 (0.0007) -[2023-10-12 03:21:40,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 13860864. Throughput: 0: 1595.2, 1: 1587.3. Samples: 3479712. Policy #0 lag: (min: 6.0, avg: 8.7, max: 38.0) -[2023-10-12 03:21:40,201][77203] Avg episode reward: [(0, '22.550'), (1, '27.660')] -[2023-10-12 03:21:41,172][78123] Updated weights for policy 1, policy_version 6760 (0.0008) -[2023-10-12 03:21:41,395][78091] Updated weights for policy 0, policy_version 6790 (0.0007) -[2023-10-12 03:21:41,531][78123] Updated weights for policy 1, policy_version 6770 (0.0008) -[2023-10-12 03:21:41,753][78091] Updated weights for policy 0, policy_version 6800 (0.0009) -[2023-10-12 03:21:41,893][78123] Updated weights for policy 1, policy_version 6780 (0.0008) -[2023-10-12 03:21:42,118][78091] Updated weights for policy 0, policy_version 6810 (0.0007) -[2023-10-12 03:21:45,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 13926400. Throughput: 0: 1585.2, 1: 1577.3. Samples: 3488168. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 03:21:45,202][77203] Avg episode reward: [(0, '22.350'), (1, '28.110')] -[2023-10-12 03:21:46,192][78123] Updated weights for policy 1, policy_version 6790 (0.0008) -[2023-10-12 03:21:46,555][78123] Updated weights for policy 1, policy_version 6800 (0.0009) -[2023-10-12 03:21:46,568][78091] Updated weights for policy 0, policy_version 6820 (0.0009) -[2023-10-12 03:21:46,917][78123] Updated weights for policy 1, policy_version 6810 (0.0009) -[2023-10-12 03:21:46,941][78091] Updated weights for policy 0, policy_version 6830 (0.0008) -[2023-10-12 03:21:47,310][78091] Updated weights for policy 0, policy_version 6840 (0.0009) -[2023-10-12 03:21:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 13991936. Throughput: 0: 1581.9, 1: 1577.6. Samples: 3507716. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 03:21:50,201][77203] Avg episode reward: [(0, '24.320'), (1, '28.640')] -[2023-10-12 03:21:51,480][78123] Updated weights for policy 1, policy_version 6820 (0.0008) -[2023-10-12 03:21:51,585][78091] Updated weights for policy 0, policy_version 6850 (0.0009) -[2023-10-12 03:21:51,857][78123] Updated weights for policy 1, policy_version 6830 (0.0009) -[2023-10-12 03:21:51,951][78091] Updated weights for policy 0, policy_version 6860 (0.0008) -[2023-10-12 03:21:52,229][78123] Updated weights for policy 1, policy_version 6840 (0.0009) -[2023-10-12 03:21:52,323][78091] Updated weights for policy 0, policy_version 6870 (0.0009) -[2023-10-12 03:21:52,692][78091] Updated weights for policy 0, policy_version 6880 (0.0008) -[2023-10-12 03:21:55,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 14057472. Throughput: 0: 1584.9, 1: 1574.1. Samples: 3526900. Policy #0 lag: (min: 8.0, avg: 24.3, max: 40.0) -[2023-10-12 03:21:55,201][77203] Avg episode reward: [(0, '23.420'), (1, '30.800')] -[2023-10-12 03:21:56,647][78123] Updated weights for policy 1, policy_version 6850 (0.0008) -[2023-10-12 03:21:56,953][78091] Updated weights for policy 0, policy_version 6890 (0.0009) -[2023-10-12 03:21:57,019][78123] Updated weights for policy 1, policy_version 6860 (0.0008) -[2023-10-12 03:21:57,322][78091] Updated weights for policy 0, policy_version 6900 (0.0009) -[2023-10-12 03:21:57,395][78123] Updated weights for policy 1, policy_version 6870 (0.0009) -[2023-10-12 03:21:57,699][78091] Updated weights for policy 0, policy_version 6910 (0.0009) -[2023-10-12 03:21:57,752][78123] Updated weights for policy 1, policy_version 6880 (0.0008) -[2023-10-12 03:22:00,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 14123008. Throughput: 0: 1584.4, 1: 1573.5. Samples: 3535594. Policy #0 lag: (min: 8.0, avg: 24.3, max: 40.0) -[2023-10-12 03:22:00,202][77203] Avg episode reward: [(0, '22.400'), (1, '30.970')] -[2023-10-12 03:22:02,093][78091] Updated weights for policy 0, policy_version 6920 (0.0008) -[2023-10-12 03:22:02,165][78123] Updated weights for policy 1, policy_version 6890 (0.0008) -[2023-10-12 03:22:02,465][78091] Updated weights for policy 0, policy_version 6930 (0.0009) -[2023-10-12 03:22:02,529][78123] Updated weights for policy 1, policy_version 6900 (0.0008) -[2023-10-12 03:22:02,831][78091] Updated weights for policy 0, policy_version 6940 (0.0009) -[2023-10-12 03:22:02,897][78123] Updated weights for policy 1, policy_version 6910 (0.0008) -[2023-10-12 03:22:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 14188544. Throughput: 0: 1581.0, 1: 1567.9. Samples: 3554678. Policy #0 lag: (min: 11.0, avg: 19.0, max: 43.0) -[2023-10-12 03:22:05,202][77203] Avg episode reward: [(0, '21.420'), (1, '29.010')] -[2023-10-12 03:22:07,072][78091] Updated weights for policy 0, policy_version 6950 (0.0008) -[2023-10-12 03:22:07,173][78123] Updated weights for policy 1, policy_version 6920 (0.0007) -[2023-10-12 03:22:07,442][78091] Updated weights for policy 0, policy_version 6960 (0.0009) -[2023-10-12 03:22:07,534][78123] Updated weights for policy 1, policy_version 6930 (0.0010) -[2023-10-12 03:22:07,815][78091] Updated weights for policy 0, policy_version 6970 (0.0007) -[2023-10-12 03:22:07,896][78123] Updated weights for policy 1, policy_version 6940 (0.0007) -[2023-10-12 03:22:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 14254080. Throughput: 0: 1580.6, 1: 1568.8. Samples: 3574110. Policy #0 lag: (min: 11.0, avg: 19.0, max: 43.0) -[2023-10-12 03:22:10,201][77203] Avg episode reward: [(0, '24.750'), (1, '33.250')] -[2023-10-12 03:22:10,213][77950] Saving new best policy, reward=33.250! -[2023-10-12 03:22:12,164][78123] Updated weights for policy 1, policy_version 6950 (0.0007) -[2023-10-12 03:22:12,219][78091] Updated weights for policy 0, policy_version 6980 (0.0007) -[2023-10-12 03:22:12,540][78123] Updated weights for policy 1, policy_version 6960 (0.0009) -[2023-10-12 03:22:12,621][78091] Updated weights for policy 0, policy_version 6990 (0.0009) -[2023-10-12 03:22:12,906][78123] Updated weights for policy 1, policy_version 6970 (0.0009) -[2023-10-12 03:22:12,991][78091] Updated weights for policy 0, policy_version 7000 (0.0008) -[2023-10-12 03:22:15,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 14319616. Throughput: 0: 1592.6, 1: 1574.6. Samples: 3583406. Policy #0 lag: (min: 31.0, avg: 32.2, max: 57.0) -[2023-10-12 03:22:15,202][77203] Avg episode reward: [(0, '22.960'), (1, '29.690')] -[2023-10-12 03:22:17,320][78091] Updated weights for policy 0, policy_version 7010 (0.0009) -[2023-10-12 03:22:17,357][78123] Updated weights for policy 1, policy_version 6980 (0.0009) -[2023-10-12 03:22:17,689][78091] Updated weights for policy 0, policy_version 7020 (0.0008) -[2023-10-12 03:22:17,722][78123] Updated weights for policy 1, policy_version 6990 (0.0010) -[2023-10-12 03:22:18,056][78091] Updated weights for policy 0, policy_version 7030 (0.0007) -[2023-10-12 03:22:18,086][78123] Updated weights for policy 1, policy_version 7000 (0.0007) -[2023-10-12 03:22:18,431][78091] Updated weights for policy 0, policy_version 7040 (0.0007) -[2023-10-12 03:22:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 14385152. Throughput: 0: 1580.2, 1: 1563.6. Samples: 3601684. Policy #0 lag: (min: 31.0, avg: 32.2, max: 57.0) -[2023-10-12 03:22:20,202][77203] Avg episode reward: [(0, '22.370'), (1, '33.380')] -[2023-10-12 03:22:20,202][77950] Saving new best policy, reward=33.380! -[2023-10-12 03:22:22,494][78123] Updated weights for policy 1, policy_version 7010 (0.0007) -[2023-10-12 03:22:22,682][78091] Updated weights for policy 0, policy_version 7050 (0.0008) -[2023-10-12 03:22:22,896][78123] Updated weights for policy 1, policy_version 7020 (0.0008) -[2023-10-12 03:22:23,048][78091] Updated weights for policy 0, policy_version 7060 (0.0007) -[2023-10-12 03:22:23,265][78123] Updated weights for policy 1, policy_version 7030 (0.0007) -[2023-10-12 03:22:23,411][78091] Updated weights for policy 0, policy_version 7070 (0.0008) -[2023-10-12 03:22:23,636][78123] Updated weights for policy 1, policy_version 7040 (0.0009) -[2023-10-12 03:22:25,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 14450688. Throughput: 0: 1579.5, 1: 1559.3. Samples: 3620958. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-12 03:22:25,201][77203] Avg episode reward: [(0, '25.250'), (1, '30.390')] -[2023-10-12 03:22:27,570][78091] Updated weights for policy 0, policy_version 7080 (0.0009) -[2023-10-12 03:22:27,949][78091] Updated weights for policy 0, policy_version 7090 (0.0007) -[2023-10-12 03:22:27,992][78123] Updated weights for policy 1, policy_version 7050 (0.0008) -[2023-10-12 03:22:28,330][78091] Updated weights for policy 0, policy_version 7100 (0.0008) -[2023-10-12 03:22:28,365][78123] Updated weights for policy 1, policy_version 7060 (0.0009) -[2023-10-12 03:22:28,742][78123] Updated weights for policy 1, policy_version 7070 (0.0009) -[2023-10-12 03:22:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 14516224. Throughput: 0: 1601.0, 1: 1583.2. Samples: 3631456. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-12 03:22:30,202][77203] Avg episode reward: [(0, '23.880'), (1, '35.390')] -[2023-10-12 03:22:30,203][77950] Saving new best policy, reward=35.390! -[2023-10-12 03:22:32,632][78091] Updated weights for policy 0, policy_version 7110 (0.0007) -[2023-10-12 03:22:33,007][78091] Updated weights for policy 0, policy_version 7120 (0.0008) -[2023-10-12 03:22:33,206][78123] Updated weights for policy 1, policy_version 7080 (0.0007) -[2023-10-12 03:22:33,387][78091] Updated weights for policy 0, policy_version 7130 (0.0008) -[2023-10-12 03:22:33,574][78123] Updated weights for policy 1, policy_version 7090 (0.0008) -[2023-10-12 03:22:33,943][78123] Updated weights for policy 1, policy_version 7100 (0.0009) -[2023-10-12 03:22:35,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 14581760. Throughput: 0: 1586.6, 1: 1563.8. Samples: 3649482. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:22:35,202][77203] Avg episode reward: [(0, '23.410'), (1, '30.900')] -[2023-10-12 03:22:37,578][78091] Updated weights for policy 0, policy_version 7140 (0.0007) -[2023-10-12 03:22:37,947][78091] Updated weights for policy 0, policy_version 7150 (0.0007) -[2023-10-12 03:22:38,090][78123] Updated weights for policy 1, policy_version 7110 (0.0009) -[2023-10-12 03:22:38,320][78091] Updated weights for policy 0, policy_version 7160 (0.0008) -[2023-10-12 03:22:38,456][78123] Updated weights for policy 1, policy_version 7120 (0.0007) -[2023-10-12 03:22:38,819][78123] Updated weights for policy 1, policy_version 7130 (0.0009) -[2023-10-12 03:22:40,201][77203] Fps is (10 sec: 13106.7, 60 sec: 13107.1, 300 sec: 12773.9). Total num frames: 14647296. Throughput: 0: 1585.6, 1: 1568.0. Samples: 3668816. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:22:40,203][77203] Avg episode reward: [(0, '22.790'), (1, '33.330')] -[2023-10-12 03:22:42,607][78091] Updated weights for policy 0, policy_version 7170 (0.0008) -[2023-10-12 03:22:42,975][78091] Updated weights for policy 0, policy_version 7180 (0.0009) -[2023-10-12 03:22:43,175][78123] Updated weights for policy 1, policy_version 7140 (0.0010) -[2023-10-12 03:22:43,340][78091] Updated weights for policy 0, policy_version 7190 (0.0008) -[2023-10-12 03:22:43,538][78123] Updated weights for policy 1, policy_version 7150 (0.0008) -[2023-10-12 03:22:43,713][78091] Updated weights for policy 0, policy_version 7200 (0.0007) -[2023-10-12 03:22:43,902][78123] Updated weights for policy 1, policy_version 7160 (0.0010) -[2023-10-12 03:22:45,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 14712832. Throughput: 0: 1605.9, 1: 1589.6. Samples: 3679392. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:22:45,201][77203] Avg episode reward: [(0, '23.880'), (1, '33.230')] -[2023-10-12 03:22:48,168][78091] Updated weights for policy 0, policy_version 7210 (0.0009) -[2023-10-12 03:22:48,358][78123] Updated weights for policy 1, policy_version 7170 (0.0009) -[2023-10-12 03:22:48,545][78091] Updated weights for policy 0, policy_version 7220 (0.0009) -[2023-10-12 03:22:48,724][78123] Updated weights for policy 1, policy_version 7180 (0.0008) -[2023-10-12 03:22:48,908][78091] Updated weights for policy 0, policy_version 7230 (0.0009) -[2023-10-12 03:22:49,085][78123] Updated weights for policy 1, policy_version 7190 (0.0010) -[2023-10-12 03:22:49,458][78123] Updated weights for policy 1, policy_version 7200 (0.0010) -[2023-10-12 03:22:50,201][77203] Fps is (10 sec: 13107.8, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 14778368. Throughput: 0: 1596.9, 1: 1580.6. Samples: 3697664. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:22:50,201][77203] Avg episode reward: [(0, '23.590'), (1, '31.680')] -[2023-10-12 03:22:53,310][78091] Updated weights for policy 0, policy_version 7240 (0.0008) -[2023-10-12 03:22:53,690][78091] Updated weights for policy 0, policy_version 7250 (0.0007) -[2023-10-12 03:22:53,889][78123] Updated weights for policy 1, policy_version 7210 (0.0008) -[2023-10-12 03:22:54,056][78091] Updated weights for policy 0, policy_version 7260 (0.0008) -[2023-10-12 03:22:54,259][78123] Updated weights for policy 1, policy_version 7220 (0.0009) -[2023-10-12 03:22:54,628][78123] Updated weights for policy 1, policy_version 7230 (0.0012) -[2023-10-12 03:22:55,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 14843904. Throughput: 0: 1590.6, 1: 1563.2. Samples: 3716032. Policy #0 lag: (min: 9.0, avg: 16.4, max: 41.0) -[2023-10-12 03:22:55,202][77203] Avg episode reward: [(0, '22.990'), (1, '30.130')] -[2023-10-12 03:22:58,252][78091] Updated weights for policy 0, policy_version 7270 (0.0009) -[2023-10-12 03:22:58,636][78091] Updated weights for policy 0, policy_version 7280 (0.0009) -[2023-10-12 03:22:58,998][78091] Updated weights for policy 0, policy_version 7290 (0.0010) -[2023-10-12 03:22:59,107][78123] Updated weights for policy 1, policy_version 7240 (0.0009) -[2023-10-12 03:22:59,470][78123] Updated weights for policy 1, policy_version 7250 (0.0009) -[2023-10-12 03:22:59,838][78123] Updated weights for policy 1, policy_version 7260 (0.0009) -[2023-10-12 03:23:00,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 14909440. Throughput: 0: 1612.8, 1: 1579.0. Samples: 3727036. Policy #0 lag: (min: 9.0, avg: 16.4, max: 41.0) -[2023-10-12 03:23:00,202][77203] Avg episode reward: [(0, '24.820'), (1, '32.430')] -[2023-10-12 03:23:03,221][78091] Updated weights for policy 0, policy_version 7300 (0.0009) -[2023-10-12 03:23:03,591][78091] Updated weights for policy 0, policy_version 7310 (0.0007) -[2023-10-12 03:23:03,966][78091] Updated weights for policy 0, policy_version 7320 (0.0009) -[2023-10-12 03:23:04,192][78123] Updated weights for policy 1, policy_version 7270 (0.0009) -[2023-10-12 03:23:04,563][78123] Updated weights for policy 1, policy_version 7280 (0.0010) -[2023-10-12 03:23:04,931][78123] Updated weights for policy 1, policy_version 7290 (0.0010) -[2023-10-12 03:23:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 14974976. Throughput: 0: 1612.4, 1: 1592.5. Samples: 3745906. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-12 03:23:05,202][77203] Avg episode reward: [(0, '23.080'), (1, '30.750')] -[2023-10-12 03:23:08,216][78091] Updated weights for policy 0, policy_version 7330 (0.0009) -[2023-10-12 03:23:08,585][78091] Updated weights for policy 0, policy_version 7340 (0.0010) -[2023-10-12 03:23:08,962][78091] Updated weights for policy 0, policy_version 7350 (0.0008) -[2023-10-12 03:23:09,316][78123] Updated weights for policy 1, policy_version 7300 (0.0009) -[2023-10-12 03:23:09,337][78091] Updated weights for policy 0, policy_version 7360 (0.0009) -[2023-10-12 03:23:09,688][78123] Updated weights for policy 1, policy_version 7310 (0.0007) -[2023-10-12 03:23:10,065][78123] Updated weights for policy 1, policy_version 7320 (0.0007) -[2023-10-12 03:23:10,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 15007744. Throughput: 0: 1601.4, 1: 1588.4. Samples: 3764498. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-12 03:23:10,201][77203] Avg episode reward: [(0, '23.160'), (1, '32.540')] -[2023-10-12 03:23:10,209][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000007360_7536640.pth... -[2023-10-12 03:23:10,252][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000005856_5996544.pth -[2023-10-12 03:23:10,258][77792] Saving a milestone ./train_atari/atari_hero_APPO/checkpoint_p0/milestones/checkpoint_000007360_7536640.pth -[2023-10-12 03:23:10,352][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000007328_7503872.pth... -[2023-10-12 03:23:10,389][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000005824_5963776.pth -[2023-10-12 03:23:10,395][77950] Saving a milestone ./train_atari/atari_hero_APPO/checkpoint_p1/milestones/checkpoint_000007328_7503872.pth -[2023-10-12 03:23:13,681][78091] Updated weights for policy 0, policy_version 7370 (0.0007) -[2023-10-12 03:23:14,039][78091] Updated weights for policy 0, policy_version 7380 (0.0009) -[2023-10-12 03:23:14,242][78123] Updated weights for policy 1, policy_version 7330 (0.0009) -[2023-10-12 03:23:14,411][78091] Updated weights for policy 0, policy_version 7390 (0.0008) -[2023-10-12 03:23:14,611][78123] Updated weights for policy 1, policy_version 7340 (0.0009) -[2023-10-12 03:23:14,980][78123] Updated weights for policy 1, policy_version 7350 (0.0010) -[2023-10-12 03:23:15,201][77203] Fps is (10 sec: 9830.6, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 15073280. Throughput: 0: 1611.0, 1: 1575.6. Samples: 3774854. Policy #0 lag: (min: 28.0, avg: 36.1, max: 60.0) -[2023-10-12 03:23:15,201][77203] Avg episode reward: [(0, '22.270'), (1, '31.640')] -[2023-10-12 03:23:15,356][78123] Updated weights for policy 1, policy_version 7360 (0.0011) -[2023-10-12 03:23:18,680][78091] Updated weights for policy 0, policy_version 7400 (0.0007) -[2023-10-12 03:23:19,044][78091] Updated weights for policy 0, policy_version 7410 (0.0009) -[2023-10-12 03:23:19,425][78091] Updated weights for policy 0, policy_version 7420 (0.0009) -[2023-10-12 03:23:19,769][78123] Updated weights for policy 1, policy_version 7370 (0.0008) -[2023-10-12 03:23:20,136][78123] Updated weights for policy 1, policy_version 7380 (0.0007) -[2023-10-12 03:23:20,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 15138816. Throughput: 0: 1619.2, 1: 1593.4. Samples: 3794048. Policy #0 lag: (min: 28.0, avg: 36.1, max: 60.0) -[2023-10-12 03:23:20,202][77203] Avg episode reward: [(0, '23.910'), (1, '33.590')] -[2023-10-12 03:23:20,506][78123] Updated weights for policy 1, policy_version 7390 (0.0007) -[2023-10-12 03:23:23,748][78091] Updated weights for policy 0, policy_version 7430 (0.0010) -[2023-10-12 03:23:24,119][78091] Updated weights for policy 0, policy_version 7440 (0.0009) -[2023-10-12 03:23:24,485][78091] Updated weights for policy 0, policy_version 7450 (0.0008) -[2023-10-12 03:23:24,743][78123] Updated weights for policy 1, policy_version 7400 (0.0009) -[2023-10-12 03:23:25,105][78123] Updated weights for policy 1, policy_version 7410 (0.0008) -[2023-10-12 03:23:25,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 15204352. Throughput: 0: 1601.2, 1: 1592.5. Samples: 3812534. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:23:25,202][77203] Avg episode reward: [(0, '25.050'), (1, '31.990')] -[2023-10-12 03:23:25,473][78123] Updated weights for policy 1, policy_version 7420 (0.0008) -[2023-10-12 03:23:28,635][78091] Updated weights for policy 0, policy_version 7460 (0.0009) -[2023-10-12 03:23:29,009][78091] Updated weights for policy 0, policy_version 7470 (0.0008) -[2023-10-12 03:23:29,380][78091] Updated weights for policy 0, policy_version 7480 (0.0008) -[2023-10-12 03:23:29,763][78123] Updated weights for policy 1, policy_version 7430 (0.0008) -[2023-10-12 03:23:30,126][78123] Updated weights for policy 1, policy_version 7440 (0.0009) -[2023-10-12 03:23:30,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 15269888. Throughput: 0: 1608.3, 1: 1576.2. Samples: 3822692. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:23:30,202][77203] Avg episode reward: [(0, '22.180'), (1, '32.020')] -[2023-10-12 03:23:30,485][78123] Updated weights for policy 1, policy_version 7450 (0.0008) -[2023-10-12 03:23:33,559][78091] Updated weights for policy 0, policy_version 7490 (0.0008) -[2023-10-12 03:23:33,942][78091] Updated weights for policy 0, policy_version 7500 (0.0008) -[2023-10-12 03:23:34,302][78091] Updated weights for policy 0, policy_version 7510 (0.0009) -[2023-10-12 03:23:34,680][78091] Updated weights for policy 0, policy_version 7520 (0.0009) -[2023-10-12 03:23:34,864][78123] Updated weights for policy 1, policy_version 7460 (0.0010) -[2023-10-12 03:23:35,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 15335424. Throughput: 0: 1617.2, 1: 1586.9. Samples: 3841850. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-12 03:23:35,201][77203] Avg episode reward: [(0, '24.550'), (1, '31.920')] -[2023-10-12 03:23:35,229][78123] Updated weights for policy 1, policy_version 7470 (0.0010) -[2023-10-12 03:23:35,590][78123] Updated weights for policy 1, policy_version 7480 (0.0009) -[2023-10-12 03:23:39,046][78091] Updated weights for policy 0, policy_version 7530 (0.0008) -[2023-10-12 03:23:39,413][78091] Updated weights for policy 0, policy_version 7540 (0.0009) -[2023-10-12 03:23:39,775][78091] Updated weights for policy 0, policy_version 7550 (0.0008) -[2023-10-12 03:23:39,870][78123] Updated weights for policy 1, policy_version 7490 (0.0008) -[2023-10-12 03:23:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 15400960. Throughput: 0: 1602.9, 1: 1608.7. Samples: 3860556. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-12 03:23:40,201][77203] Avg episode reward: [(0, '23.590'), (1, '31.220')] -[2023-10-12 03:23:40,229][78123] Updated weights for policy 1, policy_version 7500 (0.0009) -[2023-10-12 03:23:40,595][78123] Updated weights for policy 1, policy_version 7510 (0.0008) -[2023-10-12 03:23:40,961][78123] Updated weights for policy 1, policy_version 7520 (0.0007) -[2023-10-12 03:23:44,212][78091] Updated weights for policy 0, policy_version 7560 (0.0008) -[2023-10-12 03:23:44,575][78091] Updated weights for policy 0, policy_version 7570 (0.0008) -[2023-10-12 03:23:44,942][78091] Updated weights for policy 0, policy_version 7580 (0.0007) -[2023-10-12 03:23:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 15466496. Throughput: 0: 1597.4, 1: 1582.1. Samples: 3870112. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:23:45,201][77203] Avg episode reward: [(0, '24.060'), (1, '31.430')] -[2023-10-12 03:23:45,359][78123] Updated weights for policy 1, policy_version 7530 (0.0008) -[2023-10-12 03:23:45,722][78123] Updated weights for policy 1, policy_version 7540 (0.0007) -[2023-10-12 03:23:46,085][78123] Updated weights for policy 1, policy_version 7550 (0.0008) -[2023-10-12 03:23:49,333][78091] Updated weights for policy 0, policy_version 7590 (0.0007) -[2023-10-12 03:23:49,703][78091] Updated weights for policy 0, policy_version 7600 (0.0010) -[2023-10-12 03:23:50,083][78091] Updated weights for policy 0, policy_version 7610 (0.0009) -[2023-10-12 03:23:50,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 15499264. Throughput: 0: 1610.5, 1: 1580.8. Samples: 3889512. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:23:50,202][77203] Avg episode reward: [(0, '23.530'), (1, '32.940')] -[2023-10-12 03:23:50,589][78123] Updated weights for policy 1, policy_version 7560 (0.0009) -[2023-10-12 03:23:50,954][78123] Updated weights for policy 1, policy_version 7570 (0.0007) -[2023-10-12 03:23:51,311][78123] Updated weights for policy 1, policy_version 7580 (0.0009) -[2023-10-12 03:23:54,546][78091] Updated weights for policy 0, policy_version 7620 (0.0009) -[2023-10-12 03:23:54,919][78091] Updated weights for policy 0, policy_version 7630 (0.0009) -[2023-10-12 03:23:55,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 15564800. Throughput: 0: 1609.2, 1: 1589.6. Samples: 3908444. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:23:55,202][77203] Avg episode reward: [(0, '24.010'), (1, '32.860')] -[2023-10-12 03:23:55,289][78091] Updated weights for policy 0, policy_version 7640 (0.0010) -[2023-10-12 03:23:55,914][78123] Updated weights for policy 1, policy_version 7590 (0.0009) -[2023-10-12 03:23:56,290][78123] Updated weights for policy 1, policy_version 7600 (0.0007) -[2023-10-12 03:23:56,657][78123] Updated weights for policy 1, policy_version 7610 (0.0009) -[2023-10-12 03:23:59,454][78091] Updated weights for policy 0, policy_version 7650 (0.0010) -[2023-10-12 03:23:59,829][78091] Updated weights for policy 0, policy_version 7660 (0.0008) -[2023-10-12 03:24:00,192][78091] Updated weights for policy 0, policy_version 7670 (0.0008) -[2023-10-12 03:24:00,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 15630336. Throughput: 0: 1590.5, 1: 1577.2. Samples: 3917402. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:24:00,201][77203] Avg episode reward: [(0, '23.450'), (1, '34.320')] -[2023-10-12 03:24:00,568][78091] Updated weights for policy 0, policy_version 7680 (0.0011) -[2023-10-12 03:24:01,045][78123] Updated weights for policy 1, policy_version 7620 (0.0008) -[2023-10-12 03:24:01,411][78123] Updated weights for policy 1, policy_version 7630 (0.0008) -[2023-10-12 03:24:01,773][78123] Updated weights for policy 1, policy_version 7640 (0.0010) -[2023-10-12 03:24:04,870][78091] Updated weights for policy 0, policy_version 7690 (0.0008) -[2023-10-12 03:24:05,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 15695872. Throughput: 0: 1599.5, 1: 1574.1. Samples: 3936858. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:24:05,202][77203] Avg episode reward: [(0, '22.240'), (1, '29.570')] -[2023-10-12 03:24:05,249][78091] Updated weights for policy 0, policy_version 7700 (0.0007) -[2023-10-12 03:24:05,619][78091] Updated weights for policy 0, policy_version 7710 (0.0011) -[2023-10-12 03:24:06,251][78123] Updated weights for policy 1, policy_version 7650 (0.0010) -[2023-10-12 03:24:06,631][78123] Updated weights for policy 1, policy_version 7660 (0.0011) -[2023-10-12 03:24:07,003][78123] Updated weights for policy 1, policy_version 7670 (0.0009) -[2023-10-12 03:24:07,367][78123] Updated weights for policy 1, policy_version 7680 (0.0010) -[2023-10-12 03:24:10,050][78091] Updated weights for policy 0, policy_version 7720 (0.0007) -[2023-10-12 03:24:10,201][77203] Fps is (10 sec: 13106.8, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 15761408. Throughput: 0: 1614.2, 1: 1577.6. Samples: 3956168. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-12 03:24:10,202][77203] Avg episode reward: [(0, '25.800'), (1, '31.460')] -[2023-10-12 03:24:10,433][78091] Updated weights for policy 0, policy_version 7730 (0.0009) -[2023-10-12 03:24:10,804][78091] Updated weights for policy 0, policy_version 7740 (0.0009) -[2023-10-12 03:24:11,648][78123] Updated weights for policy 1, policy_version 7690 (0.0009) -[2023-10-12 03:24:12,016][78123] Updated weights for policy 1, policy_version 7700 (0.0008) -[2023-10-12 03:24:12,383][78123] Updated weights for policy 1, policy_version 7710 (0.0007) -[2023-10-12 03:24:15,158][78091] Updated weights for policy 0, policy_version 7750 (0.0009) -[2023-10-12 03:24:15,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 15826944. Throughput: 0: 1587.8, 1: 1570.6. Samples: 3964820. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-12 03:24:15,202][77203] Avg episode reward: [(0, '24.920'), (1, '32.750')] -[2023-10-12 03:24:15,524][78091] Updated weights for policy 0, policy_version 7760 (0.0009) -[2023-10-12 03:24:15,896][78091] Updated weights for policy 0, policy_version 7770 (0.0008) -[2023-10-12 03:24:16,953][78123] Updated weights for policy 1, policy_version 7720 (0.0009) -[2023-10-12 03:24:17,311][78123] Updated weights for policy 1, policy_version 7730 (0.0009) -[2023-10-12 03:24:17,689][78123] Updated weights for policy 1, policy_version 7740 (0.0008) -[2023-10-12 03:24:20,086][78091] Updated weights for policy 0, policy_version 7780 (0.0009) -[2023-10-12 03:24:20,201][77203] Fps is (10 sec: 13107.6, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 15892480. Throughput: 0: 1593.1, 1: 1569.0. Samples: 3984146. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:24:20,201][77203] Avg episode reward: [(0, '25.540'), (1, '30.670')] -[2023-10-12 03:24:20,452][78091] Updated weights for policy 0, policy_version 7790 (0.0009) -[2023-10-12 03:24:20,829][78091] Updated weights for policy 0, policy_version 7800 (0.0007) -[2023-10-12 03:24:21,926][78123] Updated weights for policy 1, policy_version 7750 (0.0010) -[2023-10-12 03:24:22,295][78123] Updated weights for policy 1, policy_version 7760 (0.0008) -[2023-10-12 03:24:22,661][78123] Updated weights for policy 1, policy_version 7770 (0.0011) -[2023-10-12 03:24:25,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 15958016. Throughput: 0: 1616.4, 1: 1566.4. Samples: 4003782. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:24:25,202][77203] Avg episode reward: [(0, '25.350'), (1, '33.260')] -[2023-10-12 03:24:25,254][78091] Updated weights for policy 0, policy_version 7810 (0.0009) -[2023-10-12 03:24:25,622][78091] Updated weights for policy 0, policy_version 7820 (0.0008) -[2023-10-12 03:24:25,998][78091] Updated weights for policy 0, policy_version 7830 (0.0010) -[2023-10-12 03:24:26,380][78091] Updated weights for policy 0, policy_version 7840 (0.0009) -[2023-10-12 03:24:26,928][78123] Updated weights for policy 1, policy_version 7780 (0.0009) -[2023-10-12 03:24:27,294][78123] Updated weights for policy 1, policy_version 7790 (0.0007) -[2023-10-12 03:24:27,655][78123] Updated weights for policy 1, policy_version 7800 (0.0008) -[2023-10-12 03:24:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 16023552. Throughput: 0: 1590.3, 1: 1575.8. Samples: 4012586. Policy #0 lag: (min: 23.0, avg: 27.7, max: 55.0) -[2023-10-12 03:24:30,201][77203] Avg episode reward: [(0, '24.410'), (1, '30.690')] -[2023-10-12 03:24:30,822][78091] Updated weights for policy 0, policy_version 7850 (0.0009) -[2023-10-12 03:24:31,203][78091] Updated weights for policy 0, policy_version 7860 (0.0008) -[2023-10-12 03:24:31,578][78091] Updated weights for policy 0, policy_version 7870 (0.0009) -[2023-10-12 03:24:32,168][78123] Updated weights for policy 1, policy_version 7810 (0.0009) -[2023-10-12 03:24:32,540][78123] Updated weights for policy 1, policy_version 7820 (0.0010) -[2023-10-12 03:24:32,913][78123] Updated weights for policy 1, policy_version 7830 (0.0010) -[2023-10-12 03:24:33,288][78123] Updated weights for policy 1, policy_version 7840 (0.0007) -[2023-10-12 03:24:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 16089088. Throughput: 0: 1588.2, 1: 1564.2. Samples: 4031368. Policy #0 lag: (min: 23.0, avg: 27.7, max: 55.0) -[2023-10-12 03:24:35,202][77203] Avg episode reward: [(0, '24.610'), (1, '32.730')] -[2023-10-12 03:24:35,878][78091] Updated weights for policy 0, policy_version 7880 (0.0008) -[2023-10-12 03:24:36,256][78091] Updated weights for policy 0, policy_version 7890 (0.0007) -[2023-10-12 03:24:36,626][78091] Updated weights for policy 0, policy_version 7900 (0.0007) -[2023-10-12 03:24:37,825][78123] Updated weights for policy 1, policy_version 7850 (0.0009) -[2023-10-12 03:24:38,193][78123] Updated weights for policy 1, policy_version 7860 (0.0008) -[2023-10-12 03:24:38,559][78123] Updated weights for policy 1, policy_version 7870 (0.0008) -[2023-10-12 03:24:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 16154624. Throughput: 0: 1600.0, 1: 1559.7. Samples: 4050630. Policy #0 lag: (min: 31.0, avg: 32.0, max: 54.0) -[2023-10-12 03:24:40,201][77203] Avg episode reward: [(0, '22.380'), (1, '31.790')] -[2023-10-12 03:24:40,896][78091] Updated weights for policy 0, policy_version 7910 (0.0007) -[2023-10-12 03:24:41,277][78091] Updated weights for policy 0, policy_version 7920 (0.0007) -[2023-10-12 03:24:41,645][78091] Updated weights for policy 0, policy_version 7930 (0.0007) -[2023-10-12 03:24:42,984][78123] Updated weights for policy 1, policy_version 7880 (0.0010) -[2023-10-12 03:24:43,369][78123] Updated weights for policy 1, policy_version 7890 (0.0010) -[2023-10-12 03:24:43,731][78123] Updated weights for policy 1, policy_version 7900 (0.0008) -[2023-10-12 03:24:45,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 16220160. Throughput: 0: 1590.5, 1: 1589.4. Samples: 4060498. Policy #0 lag: (min: 31.0, avg: 32.0, max: 54.0) -[2023-10-12 03:24:45,201][77203] Avg episode reward: [(0, '23.510'), (1, '31.580')] -[2023-10-12 03:24:45,819][78091] Updated weights for policy 0, policy_version 7940 (0.0008) -[2023-10-12 03:24:46,193][78091] Updated weights for policy 0, policy_version 7950 (0.0009) -[2023-10-12 03:24:46,570][78091] Updated weights for policy 0, policy_version 7960 (0.0010) -[2023-10-12 03:24:48,083][78123] Updated weights for policy 1, policy_version 7910 (0.0010) -[2023-10-12 03:24:48,452][78123] Updated weights for policy 1, policy_version 7920 (0.0008) -[2023-10-12 03:24:48,810][78123] Updated weights for policy 1, policy_version 7930 (0.0010) -[2023-10-12 03:24:50,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 16285696. Throughput: 0: 1589.7, 1: 1573.2. Samples: 4079186. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 03:24:50,202][77203] Avg episode reward: [(0, '26.250'), (1, '32.220')] -[2023-10-12 03:24:50,202][77792] Saving new best policy, reward=26.250! -[2023-10-12 03:24:50,764][78091] Updated weights for policy 0, policy_version 7970 (0.0008) -[2023-10-12 03:24:51,132][78091] Updated weights for policy 0, policy_version 7980 (0.0007) -[2023-10-12 03:24:51,505][78091] Updated weights for policy 0, policy_version 7990 (0.0007) -[2023-10-12 03:24:51,877][78091] Updated weights for policy 0, policy_version 8000 (0.0009) -[2023-10-12 03:24:53,180][78123] Updated weights for policy 1, policy_version 7940 (0.0009) -[2023-10-12 03:24:53,554][78123] Updated weights for policy 1, policy_version 7950 (0.0007) -[2023-10-12 03:24:53,922][78123] Updated weights for policy 1, policy_version 7960 (0.0008) -[2023-10-12 03:24:55,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 16351232. Throughput: 0: 1592.9, 1: 1567.6. Samples: 4098392. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 03:24:55,202][77203] Avg episode reward: [(0, '23.740'), (1, '33.110')] -[2023-10-12 03:24:56,279][78091] Updated weights for policy 0, policy_version 8010 (0.0007) -[2023-10-12 03:24:56,651][78091] Updated weights for policy 0, policy_version 8020 (0.0009) -[2023-10-12 03:24:57,029][78091] Updated weights for policy 0, policy_version 8030 (0.0009) -[2023-10-12 03:24:58,183][78123] Updated weights for policy 1, policy_version 7970 (0.0008) -[2023-10-12 03:24:58,540][78123] Updated weights for policy 1, policy_version 7980 (0.0008) -[2023-10-12 03:24:58,916][78123] Updated weights for policy 1, policy_version 7990 (0.0009) -[2023-10-12 03:24:59,284][78123] Updated weights for policy 1, policy_version 8000 (0.0010) -[2023-10-12 03:25:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 16416768. Throughput: 0: 1589.7, 1: 1594.7. Samples: 4108118. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-12 03:25:00,201][77203] Avg episode reward: [(0, '24.210'), (1, '34.810')] -[2023-10-12 03:25:01,304][78091] Updated weights for policy 0, policy_version 8040 (0.0010) -[2023-10-12 03:25:01,672][78091] Updated weights for policy 0, policy_version 8050 (0.0010) -[2023-10-12 03:25:02,046][78091] Updated weights for policy 0, policy_version 8060 (0.0011) -[2023-10-12 03:25:03,545][78123] Updated weights for policy 1, policy_version 8010 (0.0011) -[2023-10-12 03:25:03,907][78123] Updated weights for policy 1, policy_version 8020 (0.0007) -[2023-10-12 03:25:04,269][78123] Updated weights for policy 1, policy_version 8030 (0.0009) -[2023-10-12 03:25:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 16482304. Throughput: 0: 1581.5, 1: 1588.7. Samples: 4126806. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-12 03:25:05,202][77203] Avg episode reward: [(0, '25.560'), (1, '33.370')] -[2023-10-12 03:25:06,406][78091] Updated weights for policy 0, policy_version 8070 (0.0010) -[2023-10-12 03:25:06,789][78091] Updated weights for policy 0, policy_version 8080 (0.0010) -[2023-10-12 03:25:07,163][78091] Updated weights for policy 0, policy_version 8090 (0.0010) -[2023-10-12 03:25:08,543][78123] Updated weights for policy 1, policy_version 8040 (0.0009) -[2023-10-12 03:25:08,915][78123] Updated weights for policy 1, policy_version 8050 (0.0009) -[2023-10-12 03:25:09,291][78123] Updated weights for policy 1, policy_version 8060 (0.0011) -[2023-10-12 03:25:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 16547840. Throughput: 0: 1575.2, 1: 1575.4. Samples: 4145558. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:25:10,202][77203] Avg episode reward: [(0, '25.090'), (1, '34.360')] -[2023-10-12 03:25:10,211][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000008096_8290304.pth... -[2023-10-12 03:25:10,211][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000008064_8257536.pth... -[2023-10-12 03:25:10,245][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000006592_6750208.pth -[2023-10-12 03:25:10,253][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000006624_6782976.pth -[2023-10-12 03:25:11,459][78091] Updated weights for policy 0, policy_version 8100 (0.0010) -[2023-10-12 03:25:11,822][78091] Updated weights for policy 0, policy_version 8110 (0.0008) -[2023-10-12 03:25:12,203][78091] Updated weights for policy 0, policy_version 8120 (0.0007) -[2023-10-12 03:25:13,671][78123] Updated weights for policy 1, policy_version 8070 (0.0009) -[2023-10-12 03:25:14,044][78123] Updated weights for policy 1, policy_version 8080 (0.0009) -[2023-10-12 03:25:14,418][78123] Updated weights for policy 1, policy_version 8090 (0.0008) -[2023-10-12 03:25:15,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 16613376. Throughput: 0: 1577.5, 1: 1593.2. Samples: 4155266. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:25:15,202][77203] Avg episode reward: [(0, '24.890'), (1, '33.190')] -[2023-10-12 03:25:16,540][78091] Updated weights for policy 0, policy_version 8130 (0.0009) -[2023-10-12 03:25:16,916][78091] Updated weights for policy 0, policy_version 8140 (0.0008) -[2023-10-12 03:25:17,293][78091] Updated weights for policy 0, policy_version 8150 (0.0007) -[2023-10-12 03:25:17,661][78091] Updated weights for policy 0, policy_version 8160 (0.0008) -[2023-10-12 03:25:18,697][78123] Updated weights for policy 1, policy_version 8100 (0.0007) -[2023-10-12 03:25:19,070][78123] Updated weights for policy 1, policy_version 8110 (0.0007) -[2023-10-12 03:25:19,435][78123] Updated weights for policy 1, policy_version 8120 (0.0009) -[2023-10-12 03:25:20,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.1, 300 sec: 12662.9). Total num frames: 16678912. Throughput: 0: 1584.1, 1: 1602.0. Samples: 4174742. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:25:20,202][77203] Avg episode reward: [(0, '25.010'), (1, '35.230')] -[2023-10-12 03:25:22,061][78091] Updated weights for policy 0, policy_version 8170 (0.0010) -[2023-10-12 03:25:22,441][78091] Updated weights for policy 0, policy_version 8180 (0.0008) -[2023-10-12 03:25:22,813][78091] Updated weights for policy 0, policy_version 8190 (0.0008) -[2023-10-12 03:25:23,642][78123] Updated weights for policy 1, policy_version 8130 (0.0009) -[2023-10-12 03:25:24,006][78123] Updated weights for policy 1, policy_version 8140 (0.0010) -[2023-10-12 03:25:24,375][78123] Updated weights for policy 1, policy_version 8150 (0.0010) -[2023-10-12 03:25:24,745][78123] Updated weights for policy 1, policy_version 8160 (0.0008) -[2023-10-12 03:25:25,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 16744448. Throughput: 0: 1579.5, 1: 1589.2. Samples: 4193222. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:25:25,202][77203] Avg episode reward: [(0, '24.960'), (1, '32.190')] -[2023-10-12 03:25:27,039][78091] Updated weights for policy 0, policy_version 8200 (0.0008) -[2023-10-12 03:25:27,408][78091] Updated weights for policy 0, policy_version 8210 (0.0009) -[2023-10-12 03:25:27,770][78091] Updated weights for policy 0, policy_version 8220 (0.0010) -[2023-10-12 03:25:29,109][78123] Updated weights for policy 1, policy_version 8170 (0.0010) -[2023-10-12 03:25:29,474][78123] Updated weights for policy 1, policy_version 8180 (0.0009) -[2023-10-12 03:25:29,840][78123] Updated weights for policy 1, policy_version 8190 (0.0010) -[2023-10-12 03:25:30,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 16809984. Throughput: 0: 1580.5, 1: 1589.8. Samples: 4203160. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-12 03:25:30,202][77203] Avg episode reward: [(0, '23.940'), (1, '35.310')] -[2023-10-12 03:25:32,002][78091] Updated weights for policy 0, policy_version 8230 (0.0008) -[2023-10-12 03:25:32,372][78091] Updated weights for policy 0, policy_version 8240 (0.0009) -[2023-10-12 03:25:32,736][78091] Updated weights for policy 0, policy_version 8250 (0.0010) -[2023-10-12 03:25:34,251][78123] Updated weights for policy 1, policy_version 8200 (0.0008) -[2023-10-12 03:25:34,624][78123] Updated weights for policy 1, policy_version 8210 (0.0008) -[2023-10-12 03:25:34,996][78123] Updated weights for policy 1, policy_version 8220 (0.0010) -[2023-10-12 03:25:35,201][77203] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 16875520. Throughput: 0: 1580.8, 1: 1600.5. Samples: 4222342. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-12 03:25:35,201][77203] Avg episode reward: [(0, '23.340'), (1, '31.840')] -[2023-10-12 03:25:37,066][78091] Updated weights for policy 0, policy_version 8260 (0.0008) -[2023-10-12 03:25:37,443][78091] Updated weights for policy 0, policy_version 8270 (0.0010) -[2023-10-12 03:25:37,822][78091] Updated weights for policy 0, policy_version 8280 (0.0010) -[2023-10-12 03:25:39,360][78123] Updated weights for policy 1, policy_version 8230 (0.0009) -[2023-10-12 03:25:39,737][78123] Updated weights for policy 1, policy_version 8240 (0.0009) -[2023-10-12 03:25:40,108][78123] Updated weights for policy 1, policy_version 8250 (0.0010) -[2023-10-12 03:25:40,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 16908288. Throughput: 0: 1584.0, 1: 1595.6. Samples: 4241472. Policy #0 lag: (min: 8.0, avg: 23.8, max: 40.0) -[2023-10-12 03:25:40,202][77203] Avg episode reward: [(0, '25.620'), (1, '36.150')] -[2023-10-12 03:25:40,319][77950] Saving new best policy, reward=36.150! -[2023-10-12 03:25:42,115][78091] Updated weights for policy 0, policy_version 8290 (0.0011) -[2023-10-12 03:25:42,470][78091] Updated weights for policy 0, policy_version 8300 (0.0009) -[2023-10-12 03:25:42,836][78091] Updated weights for policy 0, policy_version 8310 (0.0009) -[2023-10-12 03:25:43,206][78091] Updated weights for policy 0, policy_version 8320 (0.0009) -[2023-10-12 03:25:44,602][78123] Updated weights for policy 1, policy_version 8260 (0.0010) -[2023-10-12 03:25:44,986][78123] Updated weights for policy 1, policy_version 8270 (0.0010) -[2023-10-12 03:25:45,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 16973824. Throughput: 0: 1595.5, 1: 1577.7. Samples: 4250912. Policy #0 lag: (min: 8.0, avg: 23.8, max: 40.0) -[2023-10-12 03:25:45,201][77203] Avg episode reward: [(0, '23.280'), (1, '32.310')] -[2023-10-12 03:25:45,358][78123] Updated weights for policy 1, policy_version 8280 (0.0009) -[2023-10-12 03:25:47,515][78091] Updated weights for policy 0, policy_version 8330 (0.0009) -[2023-10-12 03:25:47,882][78091] Updated weights for policy 0, policy_version 8340 (0.0010) -[2023-10-12 03:25:48,253][78091] Updated weights for policy 0, policy_version 8350 (0.0008) -[2023-10-12 03:25:49,479][78123] Updated weights for policy 1, policy_version 8290 (0.0007) -[2023-10-12 03:25:49,851][78123] Updated weights for policy 1, policy_version 8300 (0.0007) -[2023-10-12 03:25:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 17039360. Throughput: 0: 1589.3, 1: 1592.4. Samples: 4269980. Policy #0 lag: (min: 31.0, avg: 31.7, max: 51.0) -[2023-10-12 03:25:50,201][77203] Avg episode reward: [(0, '24.370'), (1, '35.770')] -[2023-10-12 03:25:50,221][78123] Updated weights for policy 1, policy_version 8310 (0.0008) -[2023-10-12 03:25:50,579][78123] Updated weights for policy 1, policy_version 8320 (0.0007) -[2023-10-12 03:25:52,596][78091] Updated weights for policy 0, policy_version 8360 (0.0008) -[2023-10-12 03:25:52,967][78091] Updated weights for policy 0, policy_version 8370 (0.0009) -[2023-10-12 03:25:53,334][78091] Updated weights for policy 0, policy_version 8380 (0.0009) -[2023-10-12 03:25:54,797][78123] Updated weights for policy 1, policy_version 8330 (0.0007) -[2023-10-12 03:25:55,164][78123] Updated weights for policy 1, policy_version 8340 (0.0008) -[2023-10-12 03:25:55,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 17104896. Throughput: 0: 1593.5, 1: 1605.1. Samples: 4289496. Policy #0 lag: (min: 31.0, avg: 31.7, max: 51.0) -[2023-10-12 03:25:55,202][77203] Avg episode reward: [(0, '25.490'), (1, '31.000')] -[2023-10-12 03:25:55,530][78123] Updated weights for policy 1, policy_version 8350 (0.0007) -[2023-10-12 03:25:57,794][78091] Updated weights for policy 0, policy_version 8390 (0.0010) -[2023-10-12 03:25:58,161][78091] Updated weights for policy 0, policy_version 8400 (0.0008) -[2023-10-12 03:25:58,536][78091] Updated weights for policy 0, policy_version 8410 (0.0008) -[2023-10-12 03:26:00,102][78123] Updated weights for policy 1, policy_version 8360 (0.0007) -[2023-10-12 03:26:00,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 17170432. Throughput: 0: 1613.2, 1: 1590.2. Samples: 4299416. Policy #0 lag: (min: 0.0, avg: 23.5, max: 32.0) -[2023-10-12 03:26:00,202][77203] Avg episode reward: [(0, '23.500'), (1, '34.410')] -[2023-10-12 03:26:00,476][78123] Updated weights for policy 1, policy_version 8370 (0.0008) -[2023-10-12 03:26:00,847][78123] Updated weights for policy 1, policy_version 8380 (0.0008) -[2023-10-12 03:26:02,731][78091] Updated weights for policy 0, policy_version 8420 (0.0009) -[2023-10-12 03:26:03,094][78091] Updated weights for policy 0, policy_version 8430 (0.0009) -[2023-10-12 03:26:03,468][78091] Updated weights for policy 0, policy_version 8440 (0.0008) -[2023-10-12 03:26:04,945][78123] Updated weights for policy 1, policy_version 8390 (0.0007) -[2023-10-12 03:26:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 17235968. Throughput: 0: 1592.6, 1: 1597.6. Samples: 4318298. Policy #0 lag: (min: 0.0, avg: 23.5, max: 32.0) -[2023-10-12 03:26:05,202][77203] Avg episode reward: [(0, '24.800'), (1, '30.390')] -[2023-10-12 03:26:05,315][78123] Updated weights for policy 1, policy_version 8400 (0.0007) -[2023-10-12 03:26:05,671][78123] Updated weights for policy 1, policy_version 8410 (0.0008) -[2023-10-12 03:26:07,914][78091] Updated weights for policy 0, policy_version 8450 (0.0007) -[2023-10-12 03:26:08,317][78091] Updated weights for policy 0, policy_version 8460 (0.0007) -[2023-10-12 03:26:08,684][78091] Updated weights for policy 0, policy_version 8470 (0.0007) -[2023-10-12 03:26:09,056][78091] Updated weights for policy 0, policy_version 8480 (0.0011) -[2023-10-12 03:26:09,970][78123] Updated weights for policy 1, policy_version 8420 (0.0009) -[2023-10-12 03:26:10,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 17301504. Throughput: 0: 1593.4, 1: 1617.6. Samples: 4337714. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:26:10,202][77203] Avg episode reward: [(0, '25.410'), (1, '34.490')] -[2023-10-12 03:26:10,345][78123] Updated weights for policy 1, policy_version 8430 (0.0009) -[2023-10-12 03:26:10,710][78123] Updated weights for policy 1, policy_version 8440 (0.0007) -[2023-10-12 03:26:13,343][78091] Updated weights for policy 0, policy_version 8490 (0.0007) -[2023-10-12 03:26:13,714][78091] Updated weights for policy 0, policy_version 8500 (0.0009) -[2023-10-12 03:26:14,079][78091] Updated weights for policy 0, policy_version 8510 (0.0008) -[2023-10-12 03:26:15,000][78123] Updated weights for policy 1, policy_version 8450 (0.0007) -[2023-10-12 03:26:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 17367040. Throughput: 0: 1618.8, 1: 1590.4. Samples: 4347576. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:26:15,201][77203] Avg episode reward: [(0, '24.770'), (1, '30.940')] -[2023-10-12 03:26:15,372][78123] Updated weights for policy 1, policy_version 8460 (0.0008) -[2023-10-12 03:26:15,740][78123] Updated weights for policy 1, policy_version 8470 (0.0009) -[2023-10-12 03:26:16,104][78123] Updated weights for policy 1, policy_version 8480 (0.0009) -[2023-10-12 03:26:18,573][78091] Updated weights for policy 0, policy_version 8520 (0.0009) -[2023-10-12 03:26:18,942][78091] Updated weights for policy 0, policy_version 8530 (0.0008) -[2023-10-12 03:26:19,313][78091] Updated weights for policy 0, policy_version 8540 (0.0007) -[2023-10-12 03:26:20,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 17432576. Throughput: 0: 1602.8, 1: 1600.0. Samples: 4366468. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 03:26:20,202][77203] Avg episode reward: [(0, '24.680'), (1, '33.260')] -[2023-10-12 03:26:20,350][78123] Updated weights for policy 1, policy_version 8490 (0.0011) -[2023-10-12 03:26:20,715][78123] Updated weights for policy 1, policy_version 8500 (0.0009) -[2023-10-12 03:26:21,076][78123] Updated weights for policy 1, policy_version 8510 (0.0009) -[2023-10-12 03:26:23,587][78091] Updated weights for policy 0, policy_version 8550 (0.0010) -[2023-10-12 03:26:23,954][78091] Updated weights for policy 0, policy_version 8560 (0.0008) -[2023-10-12 03:26:24,329][78091] Updated weights for policy 0, policy_version 8570 (0.0010) -[2023-10-12 03:26:25,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 17498112. Throughput: 0: 1587.0, 1: 1610.9. Samples: 4385380. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 03:26:25,202][77203] Avg episode reward: [(0, '25.610'), (1, '33.080')] -[2023-10-12 03:26:25,544][78123] Updated weights for policy 1, policy_version 8520 (0.0008) -[2023-10-12 03:26:25,910][78123] Updated weights for policy 1, policy_version 8530 (0.0009) -[2023-10-12 03:26:26,285][78123] Updated weights for policy 1, policy_version 8540 (0.0009) -[2023-10-12 03:26:28,614][78091] Updated weights for policy 0, policy_version 8580 (0.0008) -[2023-10-12 03:26:28,983][78091] Updated weights for policy 0, policy_version 8590 (0.0007) -[2023-10-12 03:26:29,360][78091] Updated weights for policy 0, policy_version 8600 (0.0008) -[2023-10-12 03:26:30,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 17563648. Throughput: 0: 1605.5, 1: 1600.2. Samples: 4395166. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:26:30,202][77203] Avg episode reward: [(0, '24.880'), (1, '33.040')] -[2023-10-12 03:26:30,580][78123] Updated weights for policy 1, policy_version 8550 (0.0009) -[2023-10-12 03:26:30,937][78123] Updated weights for policy 1, policy_version 8560 (0.0009) -[2023-10-12 03:26:31,312][78123] Updated weights for policy 1, policy_version 8570 (0.0010) -[2023-10-12 03:26:33,694][78091] Updated weights for policy 0, policy_version 8610 (0.0009) -[2023-10-12 03:26:34,055][78091] Updated weights for policy 0, policy_version 8620 (0.0011) -[2023-10-12 03:26:34,424][78091] Updated weights for policy 0, policy_version 8630 (0.0011) -[2023-10-12 03:26:34,791][78091] Updated weights for policy 0, policy_version 8640 (0.0010) -[2023-10-12 03:26:35,201][77203] Fps is (10 sec: 13107.6, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 17629184. Throughput: 0: 1615.5, 1: 1595.3. Samples: 4414466. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:26:35,202][77203] Avg episode reward: [(0, '25.720'), (1, '34.550')] -[2023-10-12 03:26:35,616][78123] Updated weights for policy 1, policy_version 8580 (0.0009) -[2023-10-12 03:26:35,987][78123] Updated weights for policy 1, policy_version 8590 (0.0007) -[2023-10-12 03:26:36,356][78123] Updated weights for policy 1, policy_version 8600 (0.0007) -[2023-10-12 03:26:39,052][78091] Updated weights for policy 0, policy_version 8650 (0.0008) -[2023-10-12 03:26:39,425][78091] Updated weights for policy 0, policy_version 8660 (0.0008) -[2023-10-12 03:26:39,811][78091] Updated weights for policy 0, policy_version 8670 (0.0009) -[2023-10-12 03:26:40,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 17694720. Throughput: 0: 1593.9, 1: 1598.6. Samples: 4433158. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-12 03:26:40,202][77203] Avg episode reward: [(0, '24.640'), (1, '32.490')] -[2023-10-12 03:26:40,695][78123] Updated weights for policy 1, policy_version 8610 (0.0009) -[2023-10-12 03:26:41,066][78123] Updated weights for policy 1, policy_version 8620 (0.0007) -[2023-10-12 03:26:41,425][78123] Updated weights for policy 1, policy_version 8630 (0.0008) -[2023-10-12 03:26:41,794][78123] Updated weights for policy 1, policy_version 8640 (0.0008) -[2023-10-12 03:26:44,180][78091] Updated weights for policy 0, policy_version 8680 (0.0010) -[2023-10-12 03:26:44,553][78091] Updated weights for policy 0, policy_version 8690 (0.0009) -[2023-10-12 03:26:44,930][78091] Updated weights for policy 0, policy_version 8700 (0.0009) -[2023-10-12 03:26:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 17760256. Throughput: 0: 1596.9, 1: 1589.1. Samples: 4442784. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-12 03:26:45,201][77203] Avg episode reward: [(0, '24.940'), (1, '31.480')] -[2023-10-12 03:26:46,038][78123] Updated weights for policy 1, policy_version 8650 (0.0009) -[2023-10-12 03:26:46,399][78123] Updated weights for policy 1, policy_version 8660 (0.0009) -[2023-10-12 03:26:46,770][78123] Updated weights for policy 1, policy_version 8670 (0.0010) -[2023-10-12 03:26:49,245][78091] Updated weights for policy 0, policy_version 8710 (0.0008) -[2023-10-12 03:26:49,615][78091] Updated weights for policy 0, policy_version 8720 (0.0010) -[2023-10-12 03:26:49,996][78091] Updated weights for policy 0, policy_version 8730 (0.0009) -[2023-10-12 03:26:50,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 17793024. Throughput: 0: 1613.2, 1: 1587.1. Samples: 4462310. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-12 03:26:50,202][77203] Avg episode reward: [(0, '26.010'), (1, '33.370')] -[2023-10-12 03:26:51,284][78123] Updated weights for policy 1, policy_version 8680 (0.0008) -[2023-10-12 03:26:51,648][78123] Updated weights for policy 1, policy_version 8690 (0.0007) -[2023-10-12 03:26:52,018][78123] Updated weights for policy 1, policy_version 8700 (0.0007) -[2023-10-12 03:26:54,384][78091] Updated weights for policy 0, policy_version 8740 (0.0011) -[2023-10-12 03:26:54,771][78091] Updated weights for policy 0, policy_version 8750 (0.0008) -[2023-10-12 03:26:55,148][78091] Updated weights for policy 0, policy_version 8760 (0.0007) -[2023-10-12 03:26:55,201][77203] Fps is (10 sec: 9830.1, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 17858560. Throughput: 0: 1600.6, 1: 1585.8. Samples: 4481102. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:26:55,203][77203] Avg episode reward: [(0, '24.850'), (1, '32.770')] -[2023-10-12 03:26:56,303][78123] Updated weights for policy 1, policy_version 8710 (0.0009) -[2023-10-12 03:26:56,669][78123] Updated weights for policy 1, policy_version 8720 (0.0011) -[2023-10-12 03:26:57,038][78123] Updated weights for policy 1, policy_version 8730 (0.0010) -[2023-10-12 03:26:59,400][78091] Updated weights for policy 0, policy_version 8770 (0.0008) -[2023-10-12 03:26:59,768][78091] Updated weights for policy 0, policy_version 8780 (0.0008) -[2023-10-12 03:27:00,135][78091] Updated weights for policy 0, policy_version 8790 (0.0009) -[2023-10-12 03:27:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 17924096. Throughput: 0: 1585.7, 1: 1582.8. Samples: 4490158. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:27:00,201][77203] Avg episode reward: [(0, '25.950'), (1, '33.200')] -[2023-10-12 03:27:00,506][78091] Updated weights for policy 0, policy_version 8800 (0.0007) -[2023-10-12 03:27:01,672][78123] Updated weights for policy 1, policy_version 8740 (0.0009) -[2023-10-12 03:27:02,061][78123] Updated weights for policy 1, policy_version 8750 (0.0007) -[2023-10-12 03:27:02,427][78123] Updated weights for policy 1, policy_version 8760 (0.0010) -[2023-10-12 03:27:04,819][78091] Updated weights for policy 0, policy_version 8810 (0.0009) -[2023-10-12 03:27:05,184][78091] Updated weights for policy 0, policy_version 8820 (0.0009) -[2023-10-12 03:27:05,201][77203] Fps is (10 sec: 13107.7, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 17989632. Throughput: 0: 1602.8, 1: 1575.9. Samples: 4509506. Policy #0 lag: (min: 10.0, avg: 11.0, max: 32.0) -[2023-10-12 03:27:05,201][77203] Avg episode reward: [(0, '24.860'), (1, '35.190')] -[2023-10-12 03:27:05,554][78091] Updated weights for policy 0, policy_version 8830 (0.0009) -[2023-10-12 03:27:06,720][78123] Updated weights for policy 1, policy_version 8770 (0.0009) -[2023-10-12 03:27:07,091][78123] Updated weights for policy 1, policy_version 8780 (0.0007) -[2023-10-12 03:27:07,468][78123] Updated weights for policy 1, policy_version 8790 (0.0008) -[2023-10-12 03:27:07,833][78123] Updated weights for policy 1, policy_version 8800 (0.0007) -[2023-10-12 03:27:09,942][78091] Updated weights for policy 0, policy_version 8840 (0.0007) -[2023-10-12 03:27:10,201][77203] Fps is (10 sec: 13106.5, 60 sec: 12560.9, 300 sec: 12662.9). Total num frames: 18055168. Throughput: 0: 1609.6, 1: 1574.7. Samples: 4528674. Policy #0 lag: (min: 10.0, avg: 11.0, max: 32.0) -[2023-10-12 03:27:10,203][77203] Avg episode reward: [(0, '25.000'), (1, '33.700')] -[2023-10-12 03:27:10,214][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000008800_9011200.pth... -[2023-10-12 03:27:10,255][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000007328_7503872.pth -[2023-10-12 03:27:10,311][78091] Updated weights for policy 0, policy_version 8850 (0.0009) -[2023-10-12 03:27:10,690][78091] Updated weights for policy 0, policy_version 8860 (0.0010) -[2023-10-12 03:27:10,839][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000008864_9076736.pth... -[2023-10-12 03:27:10,878][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000007360_7536640.pth -[2023-10-12 03:27:12,007][78123] Updated weights for policy 1, policy_version 8810 (0.0009) -[2023-10-12 03:27:12,372][78123] Updated weights for policy 1, policy_version 8820 (0.0011) -[2023-10-12 03:27:12,740][78123] Updated weights for policy 1, policy_version 8830 (0.0011) -[2023-10-12 03:27:14,968][78091] Updated weights for policy 0, policy_version 8870 (0.0008) -[2023-10-12 03:27:15,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 18120704. Throughput: 0: 1585.4, 1: 1580.9. Samples: 4537652. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:27:15,202][77203] Avg episode reward: [(0, '24.590'), (1, '33.530')] -[2023-10-12 03:27:15,346][78091] Updated weights for policy 0, policy_version 8880 (0.0007) -[2023-10-12 03:27:15,716][78091] Updated weights for policy 0, policy_version 8890 (0.0007) -[2023-10-12 03:27:17,440][78123] Updated weights for policy 1, policy_version 8840 (0.0008) -[2023-10-12 03:27:17,798][78123] Updated weights for policy 1, policy_version 8850 (0.0007) -[2023-10-12 03:27:18,162][78123] Updated weights for policy 1, policy_version 8860 (0.0007) -[2023-10-12 03:27:20,012][78091] Updated weights for policy 0, policy_version 8900 (0.0007) -[2023-10-12 03:27:20,201][77203] Fps is (10 sec: 13108.0, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 18186240. Throughput: 0: 1589.6, 1: 1577.0. Samples: 4556964. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:27:20,201][77203] Avg episode reward: [(0, '24.700'), (1, '34.740')] -[2023-10-12 03:27:20,388][78091] Updated weights for policy 0, policy_version 8910 (0.0009) -[2023-10-12 03:27:20,758][78091] Updated weights for policy 0, policy_version 8920 (0.0007) -[2023-10-12 03:27:22,297][78123] Updated weights for policy 1, policy_version 8870 (0.0009) -[2023-10-12 03:27:22,674][78123] Updated weights for policy 1, policy_version 8880 (0.0011) -[2023-10-12 03:27:23,052][78123] Updated weights for policy 1, policy_version 8890 (0.0010) -[2023-10-12 03:27:25,092][78091] Updated weights for policy 0, policy_version 8930 (0.0010) -[2023-10-12 03:27:25,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 18251776. Throughput: 0: 1610.2, 1: 1574.2. Samples: 4576458. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 03:27:25,201][77203] Avg episode reward: [(0, '25.220'), (1, '35.460')] -[2023-10-12 03:27:25,460][78091] Updated weights for policy 0, policy_version 8940 (0.0011) -[2023-10-12 03:27:25,835][78091] Updated weights for policy 0, policy_version 8950 (0.0009) -[2023-10-12 03:27:26,203][78091] Updated weights for policy 0, policy_version 8960 (0.0010) -[2023-10-12 03:27:27,389][78123] Updated weights for policy 1, policy_version 8900 (0.0008) -[2023-10-12 03:27:27,750][78123] Updated weights for policy 1, policy_version 8910 (0.0007) -[2023-10-12 03:27:28,110][78123] Updated weights for policy 1, policy_version 8920 (0.0007) -[2023-10-12 03:27:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 18317312. Throughput: 0: 1583.3, 1: 1593.9. Samples: 4585758. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 03:27:30,202][77203] Avg episode reward: [(0, '24.760'), (1, '31.650')] -[2023-10-12 03:27:30,612][78091] Updated weights for policy 0, policy_version 8970 (0.0009) -[2023-10-12 03:27:30,995][78091] Updated weights for policy 0, policy_version 8980 (0.0010) -[2023-10-12 03:27:31,372][78091] Updated weights for policy 0, policy_version 8990 (0.0007) -[2023-10-12 03:27:32,572][78123] Updated weights for policy 1, policy_version 8930 (0.0007) -[2023-10-12 03:27:32,955][78123] Updated weights for policy 1, policy_version 8940 (0.0010) -[2023-10-12 03:27:33,333][78123] Updated weights for policy 1, policy_version 8950 (0.0010) -[2023-10-12 03:27:33,694][78123] Updated weights for policy 1, policy_version 8960 (0.0009) -[2023-10-12 03:27:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 18382848. Throughput: 0: 1588.7, 1: 1575.3. Samples: 4604688. Policy #0 lag: (min: 12.0, avg: 20.8, max: 44.0) -[2023-10-12 03:27:35,201][77203] Avg episode reward: [(0, '25.290'), (1, '30.800')] -[2023-10-12 03:27:35,491][78091] Updated weights for policy 0, policy_version 9000 (0.0009) -[2023-10-12 03:27:35,863][78091] Updated weights for policy 0, policy_version 9010 (0.0008) -[2023-10-12 03:27:36,227][78091] Updated weights for policy 0, policy_version 9020 (0.0008) -[2023-10-12 03:27:38,155][78123] Updated weights for policy 1, policy_version 8970 (0.0008) -[2023-10-12 03:27:38,522][78123] Updated weights for policy 1, policy_version 8980 (0.0009) -[2023-10-12 03:27:38,891][78123] Updated weights for policy 1, policy_version 8990 (0.0010) -[2023-10-12 03:27:40,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 18448384. Throughput: 0: 1602.2, 1: 1571.1. Samples: 4623902. Policy #0 lag: (min: 12.0, avg: 20.8, max: 44.0) -[2023-10-12 03:27:40,202][77203] Avg episode reward: [(0, '25.100'), (1, '31.540')] -[2023-10-12 03:27:40,514][78091] Updated weights for policy 0, policy_version 9030 (0.0008) -[2023-10-12 03:27:40,884][78091] Updated weights for policy 0, policy_version 9040 (0.0009) -[2023-10-12 03:27:41,254][78091] Updated weights for policy 0, policy_version 9050 (0.0010) -[2023-10-12 03:27:43,083][78123] Updated weights for policy 1, policy_version 9000 (0.0009) -[2023-10-12 03:27:43,461][78123] Updated weights for policy 1, policy_version 9010 (0.0009) -[2023-10-12 03:27:43,826][78123] Updated weights for policy 1, policy_version 9020 (0.0008) -[2023-10-12 03:27:45,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 18513920. Throughput: 0: 1587.3, 1: 1603.8. Samples: 4633758. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-12 03:27:45,202][77203] Avg episode reward: [(0, '24.040'), (1, '31.500')] -[2023-10-12 03:27:45,634][78091] Updated weights for policy 0, policy_version 9060 (0.0009) -[2023-10-12 03:27:46,009][78091] Updated weights for policy 0, policy_version 9070 (0.0007) -[2023-10-12 03:27:46,379][78091] Updated weights for policy 0, policy_version 9080 (0.0007) -[2023-10-12 03:27:48,016][78123] Updated weights for policy 1, policy_version 9030 (0.0009) -[2023-10-12 03:27:48,390][78123] Updated weights for policy 1, policy_version 9040 (0.0008) -[2023-10-12 03:27:48,760][78123] Updated weights for policy 1, policy_version 9050 (0.0009) -[2023-10-12 03:27:50,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 18579456. Throughput: 0: 1584.3, 1: 1586.6. Samples: 4652196. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-12 03:27:50,201][77203] Avg episode reward: [(0, '26.080'), (1, '32.030')] -[2023-10-12 03:27:50,792][78091] Updated weights for policy 0, policy_version 9090 (0.0009) -[2023-10-12 03:27:51,166][78091] Updated weights for policy 0, policy_version 9100 (0.0007) -[2023-10-12 03:27:51,541][78091] Updated weights for policy 0, policy_version 9110 (0.0008) -[2023-10-12 03:27:51,915][78091] Updated weights for policy 0, policy_version 9120 (0.0007) -[2023-10-12 03:27:53,106][78123] Updated weights for policy 1, policy_version 9060 (0.0008) -[2023-10-12 03:27:53,467][78123] Updated weights for policy 1, policy_version 9070 (0.0007) -[2023-10-12 03:27:53,839][78123] Updated weights for policy 1, policy_version 9080 (0.0008) -[2023-10-12 03:27:55,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 18644992. Throughput: 0: 1586.5, 1: 1584.0. Samples: 4671346. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:27:55,202][77203] Avg episode reward: [(0, '25.440'), (1, '32.200')] -[2023-10-12 03:27:56,261][78091] Updated weights for policy 0, policy_version 9130 (0.0010) -[2023-10-12 03:27:56,633][78091] Updated weights for policy 0, policy_version 9140 (0.0010) -[2023-10-12 03:27:57,011][78091] Updated weights for policy 0, policy_version 9150 (0.0009) -[2023-10-12 03:27:58,166][78123] Updated weights for policy 1, policy_version 9090 (0.0009) -[2023-10-12 03:27:58,534][78123] Updated weights for policy 1, policy_version 9100 (0.0008) -[2023-10-12 03:27:58,904][78123] Updated weights for policy 1, policy_version 9110 (0.0009) -[2023-10-12 03:27:59,272][78123] Updated weights for policy 1, policy_version 9120 (0.0010) -[2023-10-12 03:28:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 18710528. Throughput: 0: 1582.4, 1: 1602.9. Samples: 4680992. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:28:00,201][77203] Avg episode reward: [(0, '26.550'), (1, '33.390')] -[2023-10-12 03:28:00,202][77792] Saving new best policy, reward=26.550! -[2023-10-12 03:28:01,344][78091] Updated weights for policy 0, policy_version 9160 (0.0007) -[2023-10-12 03:28:01,727][78091] Updated weights for policy 0, policy_version 9170 (0.0009) -[2023-10-12 03:28:02,098][78091] Updated weights for policy 0, policy_version 9180 (0.0009) -[2023-10-12 03:28:03,738][78123] Updated weights for policy 1, policy_version 9130 (0.0008) -[2023-10-12 03:28:04,105][78123] Updated weights for policy 1, policy_version 9140 (0.0010) -[2023-10-12 03:28:04,476][78123] Updated weights for policy 1, policy_version 9150 (0.0009) -[2023-10-12 03:28:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 18776064. Throughput: 0: 1582.3, 1: 1597.9. Samples: 4700072. Policy #0 lag: (min: 17.0, avg: 21.8, max: 49.0) -[2023-10-12 03:28:05,202][77203] Avg episode reward: [(0, '25.040'), (1, '34.220')] -[2023-10-12 03:28:06,572][78091] Updated weights for policy 0, policy_version 9190 (0.0010) -[2023-10-12 03:28:06,945][78091] Updated weights for policy 0, policy_version 9200 (0.0010) -[2023-10-12 03:28:07,323][78091] Updated weights for policy 0, policy_version 9210 (0.0009) -[2023-10-12 03:28:08,789][78123] Updated weights for policy 1, policy_version 9160 (0.0009) -[2023-10-12 03:28:09,164][78123] Updated weights for policy 1, policy_version 9170 (0.0007) -[2023-10-12 03:28:09,534][78123] Updated weights for policy 1, policy_version 9180 (0.0009) -[2023-10-12 03:28:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 12774.0). Total num frames: 18841600. Throughput: 0: 1578.6, 1: 1582.7. Samples: 4718714. Policy #0 lag: (min: 17.0, avg: 21.8, max: 49.0) -[2023-10-12 03:28:10,201][77203] Avg episode reward: [(0, '26.030'), (1, '35.690')] -[2023-10-12 03:28:11,730][78091] Updated weights for policy 0, policy_version 9220 (0.0008) -[2023-10-12 03:28:12,109][78091] Updated weights for policy 0, policy_version 9230 (0.0007) -[2023-10-12 03:28:12,474][78091] Updated weights for policy 0, policy_version 9240 (0.0009) -[2023-10-12 03:28:14,018][78123] Updated weights for policy 1, policy_version 9190 (0.0009) -[2023-10-12 03:28:14,378][78123] Updated weights for policy 1, policy_version 9200 (0.0007) -[2023-10-12 03:28:14,760][78123] Updated weights for policy 1, policy_version 9210 (0.0009) -[2023-10-12 03:28:15,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 18907136. Throughput: 0: 1580.4, 1: 1589.2. Samples: 4728392. Policy #0 lag: (min: 31.0, avg: 33.0, max: 63.0) -[2023-10-12 03:28:15,202][77203] Avg episode reward: [(0, '26.570'), (1, '34.580')] -[2023-10-12 03:28:15,204][77792] Saving new best policy, reward=26.570! -[2023-10-12 03:28:16,689][78091] Updated weights for policy 0, policy_version 9250 (0.0009) -[2023-10-12 03:28:17,053][78091] Updated weights for policy 0, policy_version 9260 (0.0010) -[2023-10-12 03:28:17,425][78091] Updated weights for policy 0, policy_version 9270 (0.0008) -[2023-10-12 03:28:17,791][78091] Updated weights for policy 0, policy_version 9280 (0.0007) -[2023-10-12 03:28:19,022][78123] Updated weights for policy 1, policy_version 9220 (0.0008) -[2023-10-12 03:28:19,390][78123] Updated weights for policy 1, policy_version 9230 (0.0010) -[2023-10-12 03:28:19,762][78123] Updated weights for policy 1, policy_version 9240 (0.0011) -[2023-10-12 03:28:20,201][77203] Fps is (10 sec: 13106.7, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 18972672. Throughput: 0: 1574.7, 1: 1605.5. Samples: 4747796. Policy #0 lag: (min: 31.0, avg: 33.0, max: 63.0) -[2023-10-12 03:28:20,202][77203] Avg episode reward: [(0, '27.190'), (1, '34.940')] -[2023-10-12 03:28:20,204][77792] Saving new best policy, reward=27.190! -[2023-10-12 03:28:21,927][78091] Updated weights for policy 0, policy_version 9290 (0.0008) -[2023-10-12 03:28:22,302][78091] Updated weights for policy 0, policy_version 9300 (0.0008) -[2023-10-12 03:28:22,667][78091] Updated weights for policy 0, policy_version 9310 (0.0007) -[2023-10-12 03:28:24,156][78123] Updated weights for policy 1, policy_version 9250 (0.0008) -[2023-10-12 03:28:24,528][78123] Updated weights for policy 1, policy_version 9260 (0.0008) -[2023-10-12 03:28:24,897][78123] Updated weights for policy 1, policy_version 9270 (0.0009) -[2023-10-12 03:28:25,201][77203] Fps is (10 sec: 9830.7, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 19005440. Throughput: 0: 1581.2, 1: 1596.9. Samples: 4766914. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-12 03:28:25,201][77203] Avg episode reward: [(0, '28.150'), (1, '32.110')] -[2023-10-12 03:28:25,211][77792] Saving new best policy, reward=28.150! -[2023-10-12 03:28:25,261][78123] Updated weights for policy 1, policy_version 9280 (0.0007) -[2023-10-12 03:28:27,105][78091] Updated weights for policy 0, policy_version 9320 (0.0007) -[2023-10-12 03:28:27,485][78091] Updated weights for policy 0, policy_version 9330 (0.0009) -[2023-10-12 03:28:27,860][78091] Updated weights for policy 0, policy_version 9340 (0.0009) -[2023-10-12 03:28:29,779][78123] Updated weights for policy 1, policy_version 9290 (0.0009) -[2023-10-12 03:28:30,154][78123] Updated weights for policy 1, policy_version 9300 (0.0008) -[2023-10-12 03:28:30,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 19070976. Throughput: 0: 1592.4, 1: 1577.4. Samples: 4776402. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-12 03:28:30,202][77203] Avg episode reward: [(0, '26.360'), (1, '33.270')] -[2023-10-12 03:28:30,519][78123] Updated weights for policy 1, policy_version 9310 (0.0007) -[2023-10-12 03:28:32,202][78091] Updated weights for policy 0, policy_version 9350 (0.0008) -[2023-10-12 03:28:32,579][78091] Updated weights for policy 0, policy_version 9360 (0.0009) -[2023-10-12 03:28:32,951][78091] Updated weights for policy 0, policy_version 9370 (0.0007) -[2023-10-12 03:28:34,900][78123] Updated weights for policy 1, policy_version 9320 (0.0010) -[2023-10-12 03:28:35,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 19136512. Throughput: 0: 1589.1, 1: 1597.6. Samples: 4795602. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:28:35,202][77203] Avg episode reward: [(0, '25.150'), (1, '31.750')] -[2023-10-12 03:28:35,272][78123] Updated weights for policy 1, policy_version 9330 (0.0009) -[2023-10-12 03:28:35,648][78123] Updated weights for policy 1, policy_version 9340 (0.0008) -[2023-10-12 03:28:37,282][78091] Updated weights for policy 0, policy_version 9380 (0.0008) -[2023-10-12 03:28:37,650][78091] Updated weights for policy 0, policy_version 9390 (0.0008) -[2023-10-12 03:28:38,039][78091] Updated weights for policy 0, policy_version 9400 (0.0009) -[2023-10-12 03:28:40,030][78123] Updated weights for policy 1, policy_version 9350 (0.0010) -[2023-10-12 03:28:40,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 19202048. Throughput: 0: 1591.9, 1: 1599.4. Samples: 4814954. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:28:40,202][77203] Avg episode reward: [(0, '25.880'), (1, '34.740')] -[2023-10-12 03:28:40,403][78123] Updated weights for policy 1, policy_version 9360 (0.0009) -[2023-10-12 03:28:40,778][78123] Updated weights for policy 1, policy_version 9370 (0.0010) -[2023-10-12 03:28:42,295][78091] Updated weights for policy 0, policy_version 9410 (0.0010) -[2023-10-12 03:28:42,668][78091] Updated weights for policy 0, policy_version 9420 (0.0010) -[2023-10-12 03:28:43,051][78091] Updated weights for policy 0, policy_version 9430 (0.0010) -[2023-10-12 03:28:43,427][78091] Updated weights for policy 0, policy_version 9440 (0.0011) -[2023-10-12 03:28:45,188][78123] Updated weights for policy 1, policy_version 9380 (0.0009) -[2023-10-12 03:28:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 19267584. Throughput: 0: 1607.6, 1: 1574.4. Samples: 4824186. Policy #0 lag: (min: 31.0, avg: 32.3, max: 55.0) -[2023-10-12 03:28:45,202][77203] Avg episode reward: [(0, '25.610'), (1, '33.700')] -[2023-10-12 03:28:45,551][78123] Updated weights for policy 1, policy_version 9390 (0.0008) -[2023-10-12 03:28:45,927][78123] Updated weights for policy 1, policy_version 9400 (0.0008) -[2023-10-12 03:28:47,733][78091] Updated weights for policy 0, policy_version 9450 (0.0009) -[2023-10-12 03:28:48,105][78091] Updated weights for policy 0, policy_version 9460 (0.0008) -[2023-10-12 03:28:48,469][78091] Updated weights for policy 0, policy_version 9470 (0.0008) -[2023-10-12 03:28:50,179][78123] Updated weights for policy 1, policy_version 9410 (0.0008) -[2023-10-12 03:28:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 19333120. Throughput: 0: 1592.3, 1: 1584.6. Samples: 4843034. Policy #0 lag: (min: 31.0, avg: 32.3, max: 55.0) -[2023-10-12 03:28:50,201][77203] Avg episode reward: [(0, '26.160'), (1, '34.890')] -[2023-10-12 03:28:50,541][78123] Updated weights for policy 1, policy_version 9420 (0.0008) -[2023-10-12 03:28:50,905][78123] Updated weights for policy 1, policy_version 9430 (0.0007) -[2023-10-12 03:28:51,275][78123] Updated weights for policy 1, policy_version 9440 (0.0007) -[2023-10-12 03:28:52,733][78091] Updated weights for policy 0, policy_version 9480 (0.0008) -[2023-10-12 03:28:53,107][78091] Updated weights for policy 0, policy_version 9490 (0.0007) -[2023-10-12 03:28:53,483][78091] Updated weights for policy 0, policy_version 9500 (0.0007) -[2023-10-12 03:28:55,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 19398656. Throughput: 0: 1597.4, 1: 1602.2. Samples: 4862694. Policy #0 lag: (min: 21.0, avg: 29.1, max: 53.0) -[2023-10-12 03:28:55,202][77203] Avg episode reward: [(0, '26.980'), (1, '32.070')] -[2023-10-12 03:28:55,517][78123] Updated weights for policy 1, policy_version 9450 (0.0007) -[2023-10-12 03:28:55,892][78123] Updated weights for policy 1, policy_version 9460 (0.0007) -[2023-10-12 03:28:56,261][78123] Updated weights for policy 1, policy_version 9470 (0.0008) -[2023-10-12 03:28:57,725][78091] Updated weights for policy 0, policy_version 9510 (0.0007) -[2023-10-12 03:28:58,095][78091] Updated weights for policy 0, policy_version 9520 (0.0007) -[2023-10-12 03:28:58,463][78091] Updated weights for policy 0, policy_version 9530 (0.0008) -[2023-10-12 03:29:00,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 19464192. Throughput: 0: 1619.1, 1: 1575.7. Samples: 4872158. Policy #0 lag: (min: 21.0, avg: 29.1, max: 53.0) -[2023-10-12 03:29:00,202][77203] Avg episode reward: [(0, '24.760'), (1, '32.460')] -[2023-10-12 03:29:00,426][78123] Updated weights for policy 1, policy_version 9480 (0.0007) -[2023-10-12 03:29:00,805][78123] Updated weights for policy 1, policy_version 9490 (0.0007) -[2023-10-12 03:29:01,186][78123] Updated weights for policy 1, policy_version 9500 (0.0008) -[2023-10-12 03:29:02,855][78091] Updated weights for policy 0, policy_version 9540 (0.0008) -[2023-10-12 03:29:03,223][78091] Updated weights for policy 0, policy_version 9550 (0.0007) -[2023-10-12 03:29:03,597][78091] Updated weights for policy 0, policy_version 9560 (0.0007) -[2023-10-12 03:29:05,201][77203] Fps is (10 sec: 13107.7, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 19529728. Throughput: 0: 1602.7, 1: 1580.3. Samples: 4891028. Policy #0 lag: (min: 18.0, avg: 27.2, max: 50.0) -[2023-10-12 03:29:05,201][77203] Avg episode reward: [(0, '27.100'), (1, '32.430')] -[2023-10-12 03:29:05,390][78123] Updated weights for policy 1, policy_version 9510 (0.0009) -[2023-10-12 03:29:05,756][78123] Updated weights for policy 1, policy_version 9520 (0.0007) -[2023-10-12 03:29:06,125][78123] Updated weights for policy 1, policy_version 9530 (0.0007) -[2023-10-12 03:29:07,781][78091] Updated weights for policy 0, policy_version 9570 (0.0008) -[2023-10-12 03:29:08,154][78091] Updated weights for policy 0, policy_version 9580 (0.0008) -[2023-10-12 03:29:08,532][78091] Updated weights for policy 0, policy_version 9590 (0.0010) -[2023-10-12 03:29:08,901][78091] Updated weights for policy 0, policy_version 9600 (0.0010) -[2023-10-12 03:29:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 19595264. Throughput: 0: 1592.6, 1: 1592.5. Samples: 4910244. Policy #0 lag: (min: 18.0, avg: 27.2, max: 50.0) -[2023-10-12 03:29:10,202][77203] Avg episode reward: [(0, '26.750'), (1, '30.980')] -[2023-10-12 03:29:10,208][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000009536_9764864.pth... -[2023-10-12 03:29:10,209][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000009600_9830400.pth... -[2023-10-12 03:29:10,248][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000008064_8257536.pth -[2023-10-12 03:29:10,255][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000008096_8290304.pth -[2023-10-12 03:29:10,548][78123] Updated weights for policy 1, policy_version 9540 (0.0007) -[2023-10-12 03:29:10,914][78123] Updated weights for policy 1, policy_version 9550 (0.0007) -[2023-10-12 03:29:11,285][78123] Updated weights for policy 1, policy_version 9560 (0.0008) -[2023-10-12 03:29:13,171][78091] Updated weights for policy 0, policy_version 9610 (0.0008) -[2023-10-12 03:29:13,541][78091] Updated weights for policy 0, policy_version 9620 (0.0009) -[2023-10-12 03:29:13,913][78091] Updated weights for policy 0, policy_version 9630 (0.0009) -[2023-10-12 03:29:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 19660800. Throughput: 0: 1612.0, 1: 1578.9. Samples: 4919988. Policy #0 lag: (min: 14.0, avg: 21.6, max: 46.0) -[2023-10-12 03:29:15,202][77203] Avg episode reward: [(0, '28.180'), (1, '34.170')] -[2023-10-12 03:29:15,203][77792] Saving new best policy, reward=28.180! -[2023-10-12 03:29:15,623][78123] Updated weights for policy 1, policy_version 9570 (0.0007) -[2023-10-12 03:29:15,997][78123] Updated weights for policy 1, policy_version 9580 (0.0010) -[2023-10-12 03:29:16,368][78123] Updated weights for policy 1, policy_version 9590 (0.0009) -[2023-10-12 03:29:16,731][78123] Updated weights for policy 1, policy_version 9600 (0.0010) -[2023-10-12 03:29:18,267][78091] Updated weights for policy 0, policy_version 9640 (0.0010) -[2023-10-12 03:29:18,636][78091] Updated weights for policy 0, policy_version 9650 (0.0010) -[2023-10-12 03:29:19,005][78091] Updated weights for policy 0, policy_version 9660 (0.0009) -[2023-10-12 03:29:20,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 19726336. Throughput: 0: 1597.0, 1: 1584.1. Samples: 4938750. Policy #0 lag: (min: 14.0, avg: 21.6, max: 46.0) -[2023-10-12 03:29:20,201][77203] Avg episode reward: [(0, '28.460'), (1, '32.520')] -[2023-10-12 03:29:20,202][77792] Saving new best policy, reward=28.460! -[2023-10-12 03:29:21,230][78123] Updated weights for policy 1, policy_version 9610 (0.0009) -[2023-10-12 03:29:21,602][78123] Updated weights for policy 1, policy_version 9620 (0.0009) -[2023-10-12 03:29:21,960][78123] Updated weights for policy 1, policy_version 9630 (0.0008) -[2023-10-12 03:29:23,309][78091] Updated weights for policy 0, policy_version 9670 (0.0009) -[2023-10-12 03:29:23,684][78091] Updated weights for policy 0, policy_version 9680 (0.0008) -[2023-10-12 03:29:24,054][78091] Updated weights for policy 0, policy_version 9690 (0.0011) -[2023-10-12 03:29:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 19791872. Throughput: 0: 1586.3, 1: 1585.3. Samples: 4957674. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 03:29:25,202][77203] Avg episode reward: [(0, '25.970'), (1, '33.280')] -[2023-10-12 03:29:26,305][78123] Updated weights for policy 1, policy_version 9640 (0.0008) -[2023-10-12 03:29:26,671][78123] Updated weights for policy 1, policy_version 9650 (0.0009) -[2023-10-12 03:29:27,047][78123] Updated weights for policy 1, policy_version 9660 (0.0008) -[2023-10-12 03:29:28,324][78091] Updated weights for policy 0, policy_version 9700 (0.0009) -[2023-10-12 03:29:28,697][78091] Updated weights for policy 0, policy_version 9710 (0.0010) -[2023-10-12 03:29:29,065][78091] Updated weights for policy 0, policy_version 9720 (0.0008) -[2023-10-12 03:29:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 19857408. Throughput: 0: 1599.3, 1: 1588.0. Samples: 4967614. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 03:29:30,202][77203] Avg episode reward: [(0, '26.960'), (1, '31.790')] -[2023-10-12 03:29:31,169][78123] Updated weights for policy 1, policy_version 9670 (0.0008) -[2023-10-12 03:29:31,538][78123] Updated weights for policy 1, policy_version 9680 (0.0008) -[2023-10-12 03:29:31,908][78123] Updated weights for policy 1, policy_version 9690 (0.0007) -[2023-10-12 03:29:33,393][78091] Updated weights for policy 0, policy_version 9730 (0.0008) -[2023-10-12 03:29:33,763][78091] Updated weights for policy 0, policy_version 9740 (0.0010) -[2023-10-12 03:29:34,134][78091] Updated weights for policy 0, policy_version 9750 (0.0010) -[2023-10-12 03:29:34,518][78091] Updated weights for policy 0, policy_version 9760 (0.0011) -[2023-10-12 03:29:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 19922944. Throughput: 0: 1603.7, 1: 1590.3. Samples: 4986766. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:29:35,201][77203] Avg episode reward: [(0, '26.580'), (1, '35.320')] -[2023-10-12 03:29:36,198][78123] Updated weights for policy 1, policy_version 9700 (0.0009) -[2023-10-12 03:29:36,574][78123] Updated weights for policy 1, policy_version 9710 (0.0007) -[2023-10-12 03:29:36,938][78123] Updated weights for policy 1, policy_version 9720 (0.0008) -[2023-10-12 03:29:38,840][78091] Updated weights for policy 0, policy_version 9770 (0.0009) -[2023-10-12 03:29:39,219][78091] Updated weights for policy 0, policy_version 9780 (0.0010) -[2023-10-12 03:29:39,582][78091] Updated weights for policy 0, policy_version 9790 (0.0010) -[2023-10-12 03:29:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 19988480. Throughput: 0: 1585.3, 1: 1586.1. Samples: 5005404. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:29:40,202][77203] Avg episode reward: [(0, '28.350'), (1, '33.900')] -[2023-10-12 03:29:41,241][78123] Updated weights for policy 1, policy_version 9730 (0.0009) -[2023-10-12 03:29:41,608][78123] Updated weights for policy 1, policy_version 9740 (0.0010) -[2023-10-12 03:29:41,982][78123] Updated weights for policy 1, policy_version 9750 (0.0008) -[2023-10-12 03:29:42,360][78123] Updated weights for policy 1, policy_version 9760 (0.0008) -[2023-10-12 03:29:43,987][78091] Updated weights for policy 0, policy_version 9800 (0.0008) -[2023-10-12 03:29:44,368][78091] Updated weights for policy 0, policy_version 9810 (0.0007) -[2023-10-12 03:29:44,743][78091] Updated weights for policy 0, policy_version 9820 (0.0007) -[2023-10-12 03:29:45,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 20054016. Throughput: 0: 1589.2, 1: 1586.4. Samples: 5015058. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-12 03:29:45,202][77203] Avg episode reward: [(0, '29.260'), (1, '36.870')] -[2023-10-12 03:29:45,203][77950] Saving new best policy, reward=36.870! -[2023-10-12 03:29:45,203][77792] Saving new best policy, reward=29.260! -[2023-10-12 03:29:46,933][78123] Updated weights for policy 1, policy_version 9770 (0.0009) -[2023-10-12 03:29:47,310][78123] Updated weights for policy 1, policy_version 9780 (0.0008) -[2023-10-12 03:29:47,672][78123] Updated weights for policy 1, policy_version 9790 (0.0007) -[2023-10-12 03:29:49,091][78091] Updated weights for policy 0, policy_version 9830 (0.0009) -[2023-10-12 03:29:49,459][78091] Updated weights for policy 0, policy_version 9840 (0.0009) -[2023-10-12 03:29:49,834][78091] Updated weights for policy 0, policy_version 9850 (0.0007) -[2023-10-12 03:29:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 20119552. Throughput: 0: 1604.8, 1: 1583.3. Samples: 5034492. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-12 03:29:50,201][77203] Avg episode reward: [(0, '29.260'), (1, '31.900')] -[2023-10-12 03:29:52,032][78123] Updated weights for policy 1, policy_version 9800 (0.0007) -[2023-10-12 03:29:52,399][78123] Updated weights for policy 1, policy_version 9810 (0.0007) -[2023-10-12 03:29:52,774][78123] Updated weights for policy 1, policy_version 9820 (0.0010) -[2023-10-12 03:29:54,239][78091] Updated weights for policy 0, policy_version 9860 (0.0008) -[2023-10-12 03:29:54,617][78091] Updated weights for policy 0, policy_version 9870 (0.0008) -[2023-10-12 03:29:54,992][78091] Updated weights for policy 0, policy_version 9880 (0.0009) -[2023-10-12 03:29:55,201][77203] Fps is (10 sec: 9830.6, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 20152320. Throughput: 0: 1591.8, 1: 1582.5. Samples: 5053088. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-12 03:29:55,201][77203] Avg episode reward: [(0, '27.070'), (1, '36.450')] -[2023-10-12 03:29:57,229][78123] Updated weights for policy 1, policy_version 9830 (0.0009) -[2023-10-12 03:29:57,599][78123] Updated weights for policy 1, policy_version 9840 (0.0009) -[2023-10-12 03:29:57,962][78123] Updated weights for policy 1, policy_version 9850 (0.0011) -[2023-10-12 03:29:59,378][78091] Updated weights for policy 0, policy_version 9890 (0.0007) -[2023-10-12 03:29:59,783][78091] Updated weights for policy 0, policy_version 9900 (0.0007) -[2023-10-12 03:30:00,155][78091] Updated weights for policy 0, policy_version 9910 (0.0008) -[2023-10-12 03:30:00,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 20217856. Throughput: 0: 1581.2, 1: 1595.2. Samples: 5062930. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-12 03:30:00,201][77203] Avg episode reward: [(0, '26.540'), (1, '31.010')] -[2023-10-12 03:30:00,519][78091] Updated weights for policy 0, policy_version 9920 (0.0007) -[2023-10-12 03:30:02,326][78123] Updated weights for policy 1, policy_version 9860 (0.0010) -[2023-10-12 03:30:02,709][78123] Updated weights for policy 1, policy_version 9870 (0.0007) -[2023-10-12 03:30:03,083][78123] Updated weights for policy 1, policy_version 9880 (0.0010) -[2023-10-12 03:30:04,644][78091] Updated weights for policy 0, policy_version 9930 (0.0008) -[2023-10-12 03:30:05,005][78091] Updated weights for policy 0, policy_version 9940 (0.0009) -[2023-10-12 03:30:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 20283392. Throughput: 0: 1603.9, 1: 1582.2. Samples: 5082124. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-12 03:30:05,201][77203] Avg episode reward: [(0, '27.610'), (1, '36.580')] -[2023-10-12 03:30:05,369][78091] Updated weights for policy 0, policy_version 9950 (0.0008) -[2023-10-12 03:30:07,524][78123] Updated weights for policy 1, policy_version 9890 (0.0009) -[2023-10-12 03:30:07,956][78123] Updated weights for policy 1, policy_version 9900 (0.0010) -[2023-10-12 03:30:08,326][78123] Updated weights for policy 1, policy_version 9910 (0.0010) -[2023-10-12 03:30:08,683][78123] Updated weights for policy 1, policy_version 9920 (0.0008) -[2023-10-12 03:30:09,761][78091] Updated weights for policy 0, policy_version 9960 (0.0011) -[2023-10-12 03:30:10,127][78091] Updated weights for policy 0, policy_version 9970 (0.0008) -[2023-10-12 03:30:10,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 20348928. Throughput: 0: 1606.9, 1: 1579.6. Samples: 5101068. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:30:10,202][77203] Avg episode reward: [(0, '28.590'), (1, '30.880')] -[2023-10-12 03:30:10,502][78091] Updated weights for policy 0, policy_version 9980 (0.0011) -[2023-10-12 03:30:13,077][78123] Updated weights for policy 1, policy_version 9930 (0.0009) -[2023-10-12 03:30:13,458][78123] Updated weights for policy 1, policy_version 9940 (0.0009) -[2023-10-12 03:30:13,827][78123] Updated weights for policy 1, policy_version 9950 (0.0008) -[2023-10-12 03:30:14,594][78091] Updated weights for policy 0, policy_version 9990 (0.0009) -[2023-10-12 03:30:14,973][78091] Updated weights for policy 0, policy_version 10000 (0.0009) -[2023-10-12 03:30:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 20414464. Throughput: 0: 1586.1, 1: 1602.4. Samples: 5111098. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:30:15,201][77203] Avg episode reward: [(0, '26.870'), (1, '35.710')] -[2023-10-12 03:30:15,355][78091] Updated weights for policy 0, policy_version 10010 (0.0010) -[2023-10-12 03:30:17,781][78123] Updated weights for policy 1, policy_version 9960 (0.0010) -[2023-10-12 03:30:18,149][78123] Updated weights for policy 1, policy_version 9970 (0.0007) -[2023-10-12 03:30:18,517][78123] Updated weights for policy 1, policy_version 9980 (0.0009) -[2023-10-12 03:30:19,826][78091] Updated weights for policy 0, policy_version 10020 (0.0007) -[2023-10-12 03:30:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 20480000. Throughput: 0: 1599.4, 1: 1575.3. Samples: 5129628. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-12 03:30:20,202][77203] Avg episode reward: [(0, '26.110'), (1, '30.430')] -[2023-10-12 03:30:20,203][78091] Updated weights for policy 0, policy_version 10030 (0.0011) -[2023-10-12 03:30:20,577][78091] Updated weights for policy 0, policy_version 10040 (0.0007) -[2023-10-12 03:30:22,721][78123] Updated weights for policy 1, policy_version 9990 (0.0007) -[2023-10-12 03:30:23,095][78123] Updated weights for policy 1, policy_version 10000 (0.0007) -[2023-10-12 03:30:23,470][78123] Updated weights for policy 1, policy_version 10010 (0.0008) -[2023-10-12 03:30:24,874][78091] Updated weights for policy 0, policy_version 10050 (0.0008) -[2023-10-12 03:30:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 20545536. Throughput: 0: 1614.1, 1: 1576.5. Samples: 5148982. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-12 03:30:25,201][77203] Avg episode reward: [(0, '24.770'), (1, '32.810')] -[2023-10-12 03:30:25,245][78091] Updated weights for policy 0, policy_version 10060 (0.0007) -[2023-10-12 03:30:25,615][78091] Updated weights for policy 0, policy_version 10070 (0.0007) -[2023-10-12 03:30:25,985][78091] Updated weights for policy 0, policy_version 10080 (0.0007) -[2023-10-12 03:30:27,776][78123] Updated weights for policy 1, policy_version 10020 (0.0008) -[2023-10-12 03:30:28,139][78123] Updated weights for policy 1, policy_version 10030 (0.0009) -[2023-10-12 03:30:28,502][78123] Updated weights for policy 1, policy_version 10040 (0.0011) -[2023-10-12 03:30:30,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 20611072. Throughput: 0: 1590.6, 1: 1601.5. Samples: 5158702. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-12 03:30:30,201][77203] Avg episode reward: [(0, '26.570'), (1, '30.770')] -[2023-10-12 03:30:30,381][78091] Updated weights for policy 0, policy_version 10090 (0.0011) -[2023-10-12 03:30:30,747][78091] Updated weights for policy 0, policy_version 10100 (0.0009) -[2023-10-12 03:30:31,132][78091] Updated weights for policy 0, policy_version 10110 (0.0008) -[2023-10-12 03:30:33,062][78123] Updated weights for policy 1, policy_version 10050 (0.0008) -[2023-10-12 03:30:33,443][78123] Updated weights for policy 1, policy_version 10060 (0.0010) -[2023-10-12 03:30:33,807][78123] Updated weights for policy 1, policy_version 10070 (0.0008) -[2023-10-12 03:30:34,171][78123] Updated weights for policy 1, policy_version 10080 (0.0009) -[2023-10-12 03:30:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 20676608. Throughput: 0: 1593.1, 1: 1585.9. Samples: 5177548. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-12 03:30:35,201][77203] Avg episode reward: [(0, '27.460'), (1, '32.270')] -[2023-10-12 03:30:35,509][78091] Updated weights for policy 0, policy_version 10120 (0.0007) -[2023-10-12 03:30:35,894][78091] Updated weights for policy 0, policy_version 10130 (0.0007) -[2023-10-12 03:30:36,268][78091] Updated weights for policy 0, policy_version 10140 (0.0007) -[2023-10-12 03:30:38,628][78123] Updated weights for policy 1, policy_version 10090 (0.0007) -[2023-10-12 03:30:38,995][78123] Updated weights for policy 1, policy_version 10100 (0.0009) -[2023-10-12 03:30:39,358][78123] Updated weights for policy 1, policy_version 10110 (0.0008) -[2023-10-12 03:30:40,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 20742144. Throughput: 0: 1610.2, 1: 1576.0. Samples: 5196468. Policy #0 lag: (min: 9.0, avg: 16.4, max: 41.0) -[2023-10-12 03:30:40,202][77203] Avg episode reward: [(0, '23.620'), (1, '36.060')] -[2023-10-12 03:30:40,637][78091] Updated weights for policy 0, policy_version 10150 (0.0008) -[2023-10-12 03:30:40,997][78091] Updated weights for policy 0, policy_version 10160 (0.0008) -[2023-10-12 03:30:41,382][78091] Updated weights for policy 0, policy_version 10170 (0.0009) -[2023-10-12 03:30:43,873][78123] Updated weights for policy 1, policy_version 10120 (0.0009) -[2023-10-12 03:30:44,239][78123] Updated weights for policy 1, policy_version 10130 (0.0010) -[2023-10-12 03:30:44,618][78123] Updated weights for policy 1, policy_version 10140 (0.0007) -[2023-10-12 03:30:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 20807680. Throughput: 0: 1592.1, 1: 1589.5. Samples: 5206100. Policy #0 lag: (min: 9.0, avg: 16.4, max: 41.0) -[2023-10-12 03:30:45,201][77203] Avg episode reward: [(0, '30.690'), (1, '30.880')] -[2023-10-12 03:30:45,202][77792] Saving new best policy, reward=30.690! -[2023-10-12 03:30:45,773][78091] Updated weights for policy 0, policy_version 10180 (0.0007) -[2023-10-12 03:30:46,150][78091] Updated weights for policy 0, policy_version 10190 (0.0009) -[2023-10-12 03:30:46,522][78091] Updated weights for policy 0, policy_version 10200 (0.0010) -[2023-10-12 03:30:49,021][78123] Updated weights for policy 1, policy_version 10150 (0.0009) -[2023-10-12 03:30:49,386][78123] Updated weights for policy 1, policy_version 10160 (0.0009) -[2023-10-12 03:30:49,765][78123] Updated weights for policy 1, policy_version 10170 (0.0008) -[2023-10-12 03:30:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 20873216. Throughput: 0: 1586.7, 1: 1599.1. Samples: 5225486. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 03:30:50,201][77203] Avg episode reward: [(0, '27.340'), (1, '32.720')] -[2023-10-12 03:30:50,842][78091] Updated weights for policy 0, policy_version 10210 (0.0008) -[2023-10-12 03:30:51,217][78091] Updated weights for policy 0, policy_version 10220 (0.0007) -[2023-10-12 03:30:51,593][78091] Updated weights for policy 0, policy_version 10230 (0.0010) -[2023-10-12 03:30:51,947][78091] Updated weights for policy 0, policy_version 10240 (0.0007) -[2023-10-12 03:30:54,045][78123] Updated weights for policy 1, policy_version 10180 (0.0009) -[2023-10-12 03:30:54,438][78123] Updated weights for policy 1, policy_version 10190 (0.0010) -[2023-10-12 03:30:54,807][78123] Updated weights for policy 1, policy_version 10200 (0.0007) -[2023-10-12 03:30:55,201][77203] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 20938752. Throughput: 0: 1592.6, 1: 1585.9. Samples: 5244102. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 03:30:55,202][77203] Avg episode reward: [(0, '32.570'), (1, '32.410')] -[2023-10-12 03:30:55,214][77792] Saving new best policy, reward=32.570! -[2023-10-12 03:30:56,325][78091] Updated weights for policy 0, policy_version 10250 (0.0009) -[2023-10-12 03:30:56,694][78091] Updated weights for policy 0, policy_version 10260 (0.0010) -[2023-10-12 03:30:57,074][78091] Updated weights for policy 0, policy_version 10270 (0.0008) -[2023-10-12 03:30:59,200][78123] Updated weights for policy 1, policy_version 10210 (0.0007) -[2023-10-12 03:30:59,571][78123] Updated weights for policy 1, policy_version 10220 (0.0007) -[2023-10-12 03:30:59,928][78123] Updated weights for policy 1, policy_version 10230 (0.0007) -[2023-10-12 03:31:00,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 20971520. Throughput: 0: 1583.6, 1: 1579.0. Samples: 5253412. Policy #0 lag: (min: 10.0, avg: 20.0, max: 42.0) -[2023-10-12 03:31:00,202][77203] Avg episode reward: [(0, '28.730'), (1, '33.970')] -[2023-10-12 03:31:00,300][78123] Updated weights for policy 1, policy_version 10240 (0.0008) -[2023-10-12 03:31:01,242][78091] Updated weights for policy 0, policy_version 10280 (0.0009) -[2023-10-12 03:31:01,620][78091] Updated weights for policy 0, policy_version 10290 (0.0008) -[2023-10-12 03:31:01,996][78091] Updated weights for policy 0, policy_version 10300 (0.0007) -[2023-10-12 03:31:04,753][78123] Updated weights for policy 1, policy_version 10250 (0.0008) -[2023-10-12 03:31:05,118][78123] Updated weights for policy 1, policy_version 10260 (0.0008) -[2023-10-12 03:31:05,201][77203] Fps is (10 sec: 9830.6, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 21037056. Throughput: 0: 1585.3, 1: 1601.4. Samples: 5273030. Policy #0 lag: (min: 10.0, avg: 20.0, max: 42.0) -[2023-10-12 03:31:05,202][77203] Avg episode reward: [(0, '31.650'), (1, '29.170')] -[2023-10-12 03:31:05,488][78123] Updated weights for policy 1, policy_version 10270 (0.0008) -[2023-10-12 03:31:06,237][78091] Updated weights for policy 0, policy_version 10310 (0.0007) -[2023-10-12 03:31:06,617][78091] Updated weights for policy 0, policy_version 10320 (0.0008) -[2023-10-12 03:31:06,989][78091] Updated weights for policy 0, policy_version 10330 (0.0008) -[2023-10-12 03:31:09,749][78123] Updated weights for policy 1, policy_version 10280 (0.0007) -[2023-10-12 03:31:10,116][78123] Updated weights for policy 1, policy_version 10290 (0.0007) -[2023-10-12 03:31:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 21102592. Throughput: 0: 1594.3, 1: 1596.6. Samples: 5292572. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:31:10,201][77203] Avg episode reward: [(0, '29.130'), (1, '34.020')] -[2023-10-12 03:31:10,209][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000010336_10584064.pth... -[2023-10-12 03:31:10,244][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000008864_9076736.pth -[2023-10-12 03:31:10,482][78123] Updated weights for policy 1, policy_version 10300 (0.0010) -[2023-10-12 03:31:10,626][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000010304_10551296.pth... -[2023-10-12 03:31:10,667][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000008800_9011200.pth -[2023-10-12 03:31:11,196][78091] Updated weights for policy 0, policy_version 10340 (0.0007) -[2023-10-12 03:31:11,566][78091] Updated weights for policy 0, policy_version 10350 (0.0008) -[2023-10-12 03:31:11,929][78091] Updated weights for policy 0, policy_version 10360 (0.0011) -[2023-10-12 03:31:14,625][78123] Updated weights for policy 1, policy_version 10310 (0.0009) -[2023-10-12 03:31:14,990][78123] Updated weights for policy 1, policy_version 10320 (0.0008) -[2023-10-12 03:31:15,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 21168128. Throughput: 0: 1591.8, 1: 1579.2. Samples: 5301400. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:31:15,201][77203] Avg episode reward: [(0, '31.410'), (1, '30.100')] -[2023-10-12 03:31:15,360][78123] Updated weights for policy 1, policy_version 10330 (0.0007) -[2023-10-12 03:31:16,274][78091] Updated weights for policy 0, policy_version 10370 (0.0010) -[2023-10-12 03:31:16,651][78091] Updated weights for policy 0, policy_version 10380 (0.0007) -[2023-10-12 03:31:17,018][78091] Updated weights for policy 0, policy_version 10390 (0.0008) -[2023-10-12 03:31:17,389][78091] Updated weights for policy 0, policy_version 10400 (0.0008) -[2023-10-12 03:31:19,658][78123] Updated weights for policy 1, policy_version 10340 (0.0007) -[2023-10-12 03:31:20,035][78123] Updated weights for policy 1, policy_version 10350 (0.0009) -[2023-10-12 03:31:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 21233664. Throughput: 0: 1595.2, 1: 1595.5. Samples: 5321128. Policy #0 lag: (min: 26.0, avg: 34.0, max: 58.0) -[2023-10-12 03:31:20,201][77203] Avg episode reward: [(0, '30.270'), (1, '33.450')] -[2023-10-12 03:31:20,396][78123] Updated weights for policy 1, policy_version 10360 (0.0010) -[2023-10-12 03:31:21,504][78091] Updated weights for policy 0, policy_version 10410 (0.0007) -[2023-10-12 03:31:21,877][78091] Updated weights for policy 0, policy_version 10420 (0.0007) -[2023-10-12 03:31:22,248][78091] Updated weights for policy 0, policy_version 10430 (0.0007) -[2023-10-12 03:31:24,751][78123] Updated weights for policy 1, policy_version 10370 (0.0009) -[2023-10-12 03:31:25,120][78123] Updated weights for policy 1, policy_version 10380 (0.0011) -[2023-10-12 03:31:25,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 21299200. Throughput: 0: 1599.5, 1: 1607.5. Samples: 5340780. Policy #0 lag: (min: 26.0, avg: 34.0, max: 58.0) -[2023-10-12 03:31:25,201][77203] Avg episode reward: [(0, '29.630'), (1, '33.920')] -[2023-10-12 03:31:25,491][78123] Updated weights for policy 1, policy_version 10390 (0.0010) -[2023-10-12 03:31:25,849][78123] Updated weights for policy 1, policy_version 10400 (0.0009) -[2023-10-12 03:31:26,327][78091] Updated weights for policy 0, policy_version 10440 (0.0007) -[2023-10-12 03:31:26,699][78091] Updated weights for policy 0, policy_version 10450 (0.0008) -[2023-10-12 03:31:27,081][78091] Updated weights for policy 0, policy_version 10460 (0.0007) -[2023-10-12 03:31:30,092][78123] Updated weights for policy 1, policy_version 10410 (0.0007) -[2023-10-12 03:31:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 21364736. Throughput: 0: 1603.0, 1: 1586.4. Samples: 5349624. Policy #0 lag: (min: 20.0, avg: 27.9, max: 52.0) -[2023-10-12 03:31:30,201][77203] Avg episode reward: [(0, '30.370'), (1, '32.470')] -[2023-10-12 03:31:30,465][78123] Updated weights for policy 1, policy_version 10420 (0.0008) -[2023-10-12 03:31:30,829][78123] Updated weights for policy 1, policy_version 10430 (0.0007) -[2023-10-12 03:31:31,276][78091] Updated weights for policy 0, policy_version 10470 (0.0008) -[2023-10-12 03:31:31,649][78091] Updated weights for policy 0, policy_version 10480 (0.0007) -[2023-10-12 03:31:32,021][78091] Updated weights for policy 0, policy_version 10490 (0.0008) -[2023-10-12 03:31:35,156][78123] Updated weights for policy 1, policy_version 10440 (0.0007) -[2023-10-12 03:31:35,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 21430272. Throughput: 0: 1607.6, 1: 1589.7. Samples: 5369368. Policy #0 lag: (min: 20.0, avg: 27.9, max: 52.0) -[2023-10-12 03:31:35,201][77203] Avg episode reward: [(0, '32.530'), (1, '33.490')] -[2023-10-12 03:31:35,526][78123] Updated weights for policy 1, policy_version 10450 (0.0008) -[2023-10-12 03:31:35,888][78123] Updated weights for policy 1, policy_version 10460 (0.0007) -[2023-10-12 03:31:36,533][78091] Updated weights for policy 0, policy_version 10500 (0.0010) -[2023-10-12 03:31:36,912][78091] Updated weights for policy 0, policy_version 10510 (0.0010) -[2023-10-12 03:31:37,294][78091] Updated weights for policy 0, policy_version 10520 (0.0007) -[2023-10-12 03:31:40,145][78123] Updated weights for policy 1, policy_version 10470 (0.0009) -[2023-10-12 03:31:40,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 21495808. Throughput: 0: 1607.2, 1: 1608.9. Samples: 5388828. Policy #0 lag: (min: 11.0, avg: 11.4, max: 25.0) -[2023-10-12 03:31:40,202][77203] Avg episode reward: [(0, '31.200'), (1, '31.820')] -[2023-10-12 03:31:40,529][78123] Updated weights for policy 1, policy_version 10480 (0.0007) -[2023-10-12 03:31:40,906][78123] Updated weights for policy 1, policy_version 10490 (0.0008) -[2023-10-12 03:31:41,543][78091] Updated weights for policy 0, policy_version 10530 (0.0008) -[2023-10-12 03:31:41,907][78091] Updated weights for policy 0, policy_version 10540 (0.0007) -[2023-10-12 03:31:42,271][78091] Updated weights for policy 0, policy_version 10550 (0.0007) -[2023-10-12 03:31:42,647][78091] Updated weights for policy 0, policy_version 10560 (0.0007) -[2023-10-12 03:31:45,183][78123] Updated weights for policy 1, policy_version 10500 (0.0008) -[2023-10-12 03:31:45,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 21561344. Throughput: 0: 1611.2, 1: 1589.2. Samples: 5397426. Policy #0 lag: (min: 11.0, avg: 11.4, max: 25.0) -[2023-10-12 03:31:45,202][77203] Avg episode reward: [(0, '27.330'), (1, '35.630')] -[2023-10-12 03:31:45,559][78123] Updated weights for policy 1, policy_version 10510 (0.0010) -[2023-10-12 03:31:45,932][78123] Updated weights for policy 1, policy_version 10520 (0.0010) -[2023-10-12 03:31:46,792][78091] Updated weights for policy 0, policy_version 10570 (0.0008) -[2023-10-12 03:31:47,176][78091] Updated weights for policy 0, policy_version 10580 (0.0007) -[2023-10-12 03:31:47,546][78091] Updated weights for policy 0, policy_version 10590 (0.0010) -[2023-10-12 03:31:50,201][77203] Fps is (10 sec: 13107.6, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 21626880. Throughput: 0: 1611.6, 1: 1587.5. Samples: 5416992. Policy #0 lag: (min: 25.0, avg: 29.6, max: 57.0) -[2023-10-12 03:31:50,201][77203] Avg episode reward: [(0, '29.370'), (1, '31.010')] -[2023-10-12 03:31:50,442][78123] Updated weights for policy 1, policy_version 10530 (0.0008) -[2023-10-12 03:31:50,815][78123] Updated weights for policy 1, policy_version 10540 (0.0007) -[2023-10-12 03:31:51,176][78123] Updated weights for policy 1, policy_version 10550 (0.0008) -[2023-10-12 03:31:51,546][78123] Updated weights for policy 1, policy_version 10560 (0.0007) -[2023-10-12 03:31:51,838][78091] Updated weights for policy 0, policy_version 10600 (0.0008) -[2023-10-12 03:31:52,205][78091] Updated weights for policy 0, policy_version 10610 (0.0007) -[2023-10-12 03:31:52,572][78091] Updated weights for policy 0, policy_version 10620 (0.0008) -[2023-10-12 03:31:55,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 21692416. Throughput: 0: 1607.4, 1: 1593.3. Samples: 5436606. Policy #0 lag: (min: 25.0, avg: 29.6, max: 57.0) -[2023-10-12 03:31:55,201][77203] Avg episode reward: [(0, '29.660'), (1, '36.420')] -[2023-10-12 03:31:55,968][78123] Updated weights for policy 1, policy_version 10570 (0.0009) -[2023-10-12 03:31:56,342][78123] Updated weights for policy 1, policy_version 10580 (0.0008) -[2023-10-12 03:31:56,708][78123] Updated weights for policy 1, policy_version 10590 (0.0008) -[2023-10-12 03:31:56,817][78091] Updated weights for policy 0, policy_version 10630 (0.0007) -[2023-10-12 03:31:57,192][78091] Updated weights for policy 0, policy_version 10640 (0.0008) -[2023-10-12 03:31:57,563][78091] Updated weights for policy 0, policy_version 10650 (0.0009) -[2023-10-12 03:32:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 21757952. Throughput: 0: 1611.6, 1: 1585.3. Samples: 5445258. Policy #0 lag: (min: 19.0, avg: 21.9, max: 51.0) -[2023-10-12 03:32:00,201][77203] Avg episode reward: [(0, '29.970'), (1, '32.460')] -[2023-10-12 03:32:01,072][78123] Updated weights for policy 1, policy_version 10600 (0.0008) -[2023-10-12 03:32:01,433][78123] Updated weights for policy 1, policy_version 10610 (0.0009) -[2023-10-12 03:32:01,808][78123] Updated weights for policy 1, policy_version 10620 (0.0009) -[2023-10-12 03:32:01,990][78091] Updated weights for policy 0, policy_version 10660 (0.0008) -[2023-10-12 03:32:02,352][78091] Updated weights for policy 0, policy_version 10670 (0.0009) -[2023-10-12 03:32:02,725][78091] Updated weights for policy 0, policy_version 10680 (0.0008) -[2023-10-12 03:32:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 21823488. Throughput: 0: 1607.6, 1: 1581.3. Samples: 5464630. Policy #0 lag: (min: 19.0, avg: 21.9, max: 51.0) -[2023-10-12 03:32:05,201][77203] Avg episode reward: [(0, '31.010'), (1, '37.670')] -[2023-10-12 03:32:05,202][77950] Saving new best policy, reward=37.670! -[2023-10-12 03:32:06,267][78123] Updated weights for policy 1, policy_version 10630 (0.0007) -[2023-10-12 03:32:06,634][78123] Updated weights for policy 1, policy_version 10640 (0.0008) -[2023-10-12 03:32:07,007][78123] Updated weights for policy 1, policy_version 10650 (0.0008) -[2023-10-12 03:32:07,164][78091] Updated weights for policy 0, policy_version 10690 (0.0009) -[2023-10-12 03:32:07,535][78091] Updated weights for policy 0, policy_version 10700 (0.0007) -[2023-10-12 03:32:07,902][78091] Updated weights for policy 0, policy_version 10710 (0.0007) -[2023-10-12 03:32:08,276][78091] Updated weights for policy 0, policy_version 10720 (0.0007) -[2023-10-12 03:32:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 21889024. Throughput: 0: 1604.0, 1: 1578.7. Samples: 5484004. Policy #0 lag: (min: 24.0, avg: 44.7, max: 48.0) -[2023-10-12 03:32:10,201][77203] Avg episode reward: [(0, '30.170'), (1, '32.410')] -[2023-10-12 03:32:11,380][78123] Updated weights for policy 1, policy_version 10660 (0.0007) -[2023-10-12 03:32:11,742][78123] Updated weights for policy 1, policy_version 10670 (0.0008) -[2023-10-12 03:32:12,108][78123] Updated weights for policy 1, policy_version 10680 (0.0009) -[2023-10-12 03:32:12,446][78091] Updated weights for policy 0, policy_version 10730 (0.0010) -[2023-10-12 03:32:12,822][78091] Updated weights for policy 0, policy_version 10740 (0.0008) -[2023-10-12 03:32:13,190][78091] Updated weights for policy 0, policy_version 10750 (0.0008) -[2023-10-12 03:32:15,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 21954560. Throughput: 0: 1615.6, 1: 1575.1. Samples: 5493208. Policy #0 lag: (min: 24.0, avg: 44.7, max: 48.0) -[2023-10-12 03:32:15,202][77203] Avg episode reward: [(0, '31.050'), (1, '36.110')] -[2023-10-12 03:32:16,579][78123] Updated weights for policy 1, policy_version 10690 (0.0009) -[2023-10-12 03:32:16,959][78123] Updated weights for policy 1, policy_version 10700 (0.0010) -[2023-10-12 03:32:17,338][78123] Updated weights for policy 1, policy_version 10710 (0.0008) -[2023-10-12 03:32:17,538][78091] Updated weights for policy 0, policy_version 10760 (0.0008) -[2023-10-12 03:32:17,692][78123] Updated weights for policy 1, policy_version 10720 (0.0007) -[2023-10-12 03:32:17,908][78091] Updated weights for policy 0, policy_version 10770 (0.0008) -[2023-10-12 03:32:18,277][78091] Updated weights for policy 0, policy_version 10780 (0.0007) -[2023-10-12 03:32:20,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 22020096. Throughput: 0: 1605.3, 1: 1573.4. Samples: 5512408. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-12 03:32:20,202][77203] Avg episode reward: [(0, '29.790'), (1, '32.980')] -[2023-10-12 03:32:21,899][78123] Updated weights for policy 1, policy_version 10730 (0.0010) -[2023-10-12 03:32:22,268][78123] Updated weights for policy 1, policy_version 10740 (0.0010) -[2023-10-12 03:32:22,575][78091] Updated weights for policy 0, policy_version 10790 (0.0008) -[2023-10-12 03:32:22,633][78123] Updated weights for policy 1, policy_version 10750 (0.0009) -[2023-10-12 03:32:22,954][78091] Updated weights for policy 0, policy_version 10800 (0.0008) -[2023-10-12 03:32:23,324][78091] Updated weights for policy 0, policy_version 10810 (0.0008) -[2023-10-12 03:32:25,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 22085632. Throughput: 0: 1606.0, 1: 1574.4. Samples: 5531950. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-12 03:32:25,202][77203] Avg episode reward: [(0, '31.440'), (1, '34.820')] -[2023-10-12 03:32:27,029][78123] Updated weights for policy 1, policy_version 10760 (0.0009) -[2023-10-12 03:32:27,409][78123] Updated weights for policy 1, policy_version 10770 (0.0010) -[2023-10-12 03:32:27,528][78091] Updated weights for policy 0, policy_version 10820 (0.0008) -[2023-10-12 03:32:27,780][78123] Updated weights for policy 1, policy_version 10780 (0.0008) -[2023-10-12 03:32:27,894][78091] Updated weights for policy 0, policy_version 10830 (0.0008) -[2023-10-12 03:32:28,266][78091] Updated weights for policy 0, policy_version 10840 (0.0008) -[2023-10-12 03:32:30,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 22151168. Throughput: 0: 1624.7, 1: 1577.9. Samples: 5541544. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-12 03:32:30,202][77203] Avg episode reward: [(0, '29.870'), (1, '32.010')] -[2023-10-12 03:32:32,050][78123] Updated weights for policy 1, policy_version 10790 (0.0009) -[2023-10-12 03:32:32,413][78123] Updated weights for policy 1, policy_version 10800 (0.0009) -[2023-10-12 03:32:32,486][78091] Updated weights for policy 0, policy_version 10850 (0.0009) -[2023-10-12 03:32:32,785][78123] Updated weights for policy 1, policy_version 10810 (0.0008) -[2023-10-12 03:32:32,850][78091] Updated weights for policy 0, policy_version 10860 (0.0008) -[2023-10-12 03:32:33,222][78091] Updated weights for policy 0, policy_version 10870 (0.0010) -[2023-10-12 03:32:33,595][78091] Updated weights for policy 0, policy_version 10880 (0.0008) -[2023-10-12 03:32:35,201][77203] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 22216704. Throughput: 0: 1605.6, 1: 1576.1. Samples: 5560168. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-12 03:32:35,201][77203] Avg episode reward: [(0, '33.230'), (1, '33.570')] -[2023-10-12 03:32:35,202][77792] Saving new best policy, reward=33.230! -[2023-10-12 03:32:37,215][78123] Updated weights for policy 1, policy_version 10820 (0.0009) -[2023-10-12 03:32:37,582][78123] Updated weights for policy 1, policy_version 10830 (0.0010) -[2023-10-12 03:32:37,945][78123] Updated weights for policy 1, policy_version 10840 (0.0009) -[2023-10-12 03:32:37,961][78091] Updated weights for policy 0, policy_version 10890 (0.0008) -[2023-10-12 03:32:38,334][78091] Updated weights for policy 0, policy_version 10900 (0.0008) -[2023-10-12 03:32:38,705][78091] Updated weights for policy 0, policy_version 10910 (0.0009) -[2023-10-12 03:32:40,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 22282240. Throughput: 0: 1602.0, 1: 1571.2. Samples: 5579404. Policy #0 lag: (min: 2.0, avg: 9.1, max: 34.0) -[2023-10-12 03:32:40,202][77203] Avg episode reward: [(0, '30.380'), (1, '37.120')] -[2023-10-12 03:32:42,367][78123] Updated weights for policy 1, policy_version 10850 (0.0009) -[2023-10-12 03:32:42,732][78123] Updated weights for policy 1, policy_version 10860 (0.0007) -[2023-10-12 03:32:42,926][78091] Updated weights for policy 0, policy_version 10920 (0.0008) -[2023-10-12 03:32:43,101][78123] Updated weights for policy 1, policy_version 10870 (0.0009) -[2023-10-12 03:32:43,304][78091] Updated weights for policy 0, policy_version 10930 (0.0008) -[2023-10-12 03:32:43,465][78123] Updated weights for policy 1, policy_version 10880 (0.0008) -[2023-10-12 03:32:43,688][78091] Updated weights for policy 0, policy_version 10940 (0.0007) -[2023-10-12 03:32:45,201][77203] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 22347776. Throughput: 0: 1622.7, 1: 1589.0. Samples: 5589786. Policy #0 lag: (min: 2.0, avg: 9.1, max: 34.0) -[2023-10-12 03:32:45,202][77203] Avg episode reward: [(0, '30.930'), (1, '36.680')] -[2023-10-12 03:32:47,713][78123] Updated weights for policy 1, policy_version 10890 (0.0011) -[2023-10-12 03:32:48,069][78123] Updated weights for policy 1, policy_version 10900 (0.0007) -[2023-10-12 03:32:48,081][78091] Updated weights for policy 0, policy_version 10950 (0.0008) -[2023-10-12 03:32:48,433][78123] Updated weights for policy 1, policy_version 10910 (0.0008) -[2023-10-12 03:32:48,455][78091] Updated weights for policy 0, policy_version 10960 (0.0009) -[2023-10-12 03:32:48,818][78091] Updated weights for policy 0, policy_version 10970 (0.0008) -[2023-10-12 03:32:50,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 22413312. Throughput: 0: 1604.7, 1: 1577.7. Samples: 5607838. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-12 03:32:50,202][77203] Avg episode reward: [(0, '30.130'), (1, '37.890')] -[2023-10-12 03:32:50,203][77950] Saving new best policy, reward=37.890! -[2023-10-12 03:32:52,714][78123] Updated weights for policy 1, policy_version 10920 (0.0009) -[2023-10-12 03:32:53,079][78123] Updated weights for policy 1, policy_version 10930 (0.0007) -[2023-10-12 03:32:53,120][78091] Updated weights for policy 0, policy_version 10980 (0.0008) -[2023-10-12 03:32:53,448][78123] Updated weights for policy 1, policy_version 10940 (0.0009) -[2023-10-12 03:32:53,504][78091] Updated weights for policy 0, policy_version 10990 (0.0008) -[2023-10-12 03:32:53,867][78091] Updated weights for policy 0, policy_version 11000 (0.0009) -[2023-10-12 03:32:55,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 22478848. Throughput: 0: 1597.5, 1: 1582.0. Samples: 5627082. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-12 03:32:55,202][77203] Avg episode reward: [(0, '32.930'), (1, '35.200')] -[2023-10-12 03:32:57,710][78123] Updated weights for policy 1, policy_version 10950 (0.0008) -[2023-10-12 03:32:58,079][78123] Updated weights for policy 1, policy_version 10960 (0.0008) -[2023-10-12 03:32:58,088][78091] Updated weights for policy 0, policy_version 11010 (0.0009) -[2023-10-12 03:32:58,448][78123] Updated weights for policy 1, policy_version 10970 (0.0010) -[2023-10-12 03:32:58,448][78091] Updated weights for policy 0, policy_version 11020 (0.0007) -[2023-10-12 03:32:58,823][78091] Updated weights for policy 0, policy_version 11030 (0.0008) -[2023-10-12 03:32:59,191][78091] Updated weights for policy 0, policy_version 11040 (0.0010) -[2023-10-12 03:33:00,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 22544384. Throughput: 0: 1611.2, 1: 1602.5. Samples: 5637824. Policy #0 lag: (min: 26.0, avg: 33.6, max: 58.0) -[2023-10-12 03:33:00,202][77203] Avg episode reward: [(0, '28.440'), (1, '35.200')] -[2023-10-12 03:33:02,949][78123] Updated weights for policy 1, policy_version 10980 (0.0010) -[2023-10-12 03:33:03,328][78123] Updated weights for policy 1, policy_version 10990 (0.0010) -[2023-10-12 03:33:03,514][78091] Updated weights for policy 0, policy_version 11050 (0.0007) -[2023-10-12 03:33:03,695][78123] Updated weights for policy 1, policy_version 11000 (0.0008) -[2023-10-12 03:33:03,891][78091] Updated weights for policy 0, policy_version 11060 (0.0009) -[2023-10-12 03:33:04,264][78091] Updated weights for policy 0, policy_version 11070 (0.0009) -[2023-10-12 03:33:05,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 22609920. Throughput: 0: 1604.5, 1: 1584.1. Samples: 5655896. Policy #0 lag: (min: 26.0, avg: 33.6, max: 58.0) -[2023-10-12 03:33:05,201][77203] Avg episode reward: [(0, '32.870'), (1, '34.720')] -[2023-10-12 03:33:07,874][78123] Updated weights for policy 1, policy_version 11010 (0.0009) -[2023-10-12 03:33:08,232][78123] Updated weights for policy 1, policy_version 11020 (0.0010) -[2023-10-12 03:33:08,603][78123] Updated weights for policy 1, policy_version 11030 (0.0007) -[2023-10-12 03:33:08,633][78091] Updated weights for policy 0, policy_version 11080 (0.0010) -[2023-10-12 03:33:08,977][78123] Updated weights for policy 1, policy_version 11040 (0.0007) -[2023-10-12 03:33:09,004][78091] Updated weights for policy 0, policy_version 11090 (0.0008) -[2023-10-12 03:33:09,369][78091] Updated weights for policy 0, policy_version 11100 (0.0009) -[2023-10-12 03:33:10,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 22675456. Throughput: 0: 1591.4, 1: 1572.4. Samples: 5674322. Policy #0 lag: (min: 0.0, avg: 21.4, max: 32.0) -[2023-10-12 03:33:10,202][77203] Avg episode reward: [(0, '32.150'), (1, '34.750')] -[2023-10-12 03:33:10,209][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000011104_11370496.pth... -[2023-10-12 03:33:10,209][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000011040_11304960.pth... -[2023-10-12 03:33:10,249][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000009536_9764864.pth -[2023-10-12 03:33:10,250][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000009600_9830400.pth -[2023-10-12 03:33:13,383][78123] Updated weights for policy 1, policy_version 11050 (0.0009) -[2023-10-12 03:33:13,756][78123] Updated weights for policy 1, policy_version 11060 (0.0008) -[2023-10-12 03:33:13,830][78091] Updated weights for policy 0, policy_version 11110 (0.0009) -[2023-10-12 03:33:14,126][78123] Updated weights for policy 1, policy_version 11070 (0.0009) -[2023-10-12 03:33:14,201][78091] Updated weights for policy 0, policy_version 11120 (0.0009) -[2023-10-12 03:33:14,573][78091] Updated weights for policy 0, policy_version 11130 (0.0011) -[2023-10-12 03:33:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 22740992. Throughput: 0: 1594.1, 1: 1604.1. Samples: 5685466. Policy #0 lag: (min: 0.0, avg: 21.4, max: 32.0) -[2023-10-12 03:33:15,201][77203] Avg episode reward: [(0, '31.280'), (1, '35.230')] -[2023-10-12 03:33:18,340][78123] Updated weights for policy 1, policy_version 11080 (0.0009) -[2023-10-12 03:33:18,701][78123] Updated weights for policy 1, policy_version 11090 (0.0007) -[2023-10-12 03:33:18,819][78091] Updated weights for policy 0, policy_version 11140 (0.0010) -[2023-10-12 03:33:19,074][78123] Updated weights for policy 1, policy_version 11100 (0.0009) -[2023-10-12 03:33:19,185][78091] Updated weights for policy 0, policy_version 11150 (0.0007) -[2023-10-12 03:33:19,565][78091] Updated weights for policy 0, policy_version 11160 (0.0009) -[2023-10-12 03:33:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 22806528. Throughput: 0: 1605.2, 1: 1597.6. Samples: 5704294. Policy #0 lag: (min: 29.0, avg: 31.8, max: 61.0) -[2023-10-12 03:33:20,202][77203] Avg episode reward: [(0, '29.320'), (1, '36.330')] -[2023-10-12 03:33:23,369][78123] Updated weights for policy 1, policy_version 11110 (0.0011) -[2023-10-12 03:33:23,724][78091] Updated weights for policy 0, policy_version 11170 (0.0010) -[2023-10-12 03:33:23,736][78123] Updated weights for policy 1, policy_version 11120 (0.0009) -[2023-10-12 03:33:24,091][78091] Updated weights for policy 0, policy_version 11180 (0.0009) -[2023-10-12 03:33:24,102][78123] Updated weights for policy 1, policy_version 11130 (0.0008) -[2023-10-12 03:33:24,461][78091] Updated weights for policy 0, policy_version 11190 (0.0007) -[2023-10-12 03:33:24,834][78091] Updated weights for policy 0, policy_version 11200 (0.0009) -[2023-10-12 03:33:25,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 22872064. Throughput: 0: 1587.3, 1: 1589.2. Samples: 5722346. Policy #0 lag: (min: 29.0, avg: 31.8, max: 61.0) -[2023-10-12 03:33:25,202][77203] Avg episode reward: [(0, '31.230'), (1, '35.810')] -[2023-10-12 03:33:28,513][78123] Updated weights for policy 1, policy_version 11140 (0.0008) -[2023-10-12 03:33:28,873][78123] Updated weights for policy 1, policy_version 11150 (0.0008) -[2023-10-12 03:33:29,148][78091] Updated weights for policy 0, policy_version 11210 (0.0009) -[2023-10-12 03:33:29,248][78123] Updated weights for policy 1, policy_version 11160 (0.0008) -[2023-10-12 03:33:29,516][78091] Updated weights for policy 0, policy_version 11220 (0.0009) -[2023-10-12 03:33:29,884][78091] Updated weights for policy 0, policy_version 11230 (0.0008) -[2023-10-12 03:33:30,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 22937600. Throughput: 0: 1585.7, 1: 1599.6. Samples: 5733124. Policy #0 lag: (min: 17.0, avg: 23.3, max: 49.0) -[2023-10-12 03:33:30,201][77203] Avg episode reward: [(0, '33.240'), (1, '35.820')] -[2023-10-12 03:33:30,202][77792] Saving new best policy, reward=33.240! -[2023-10-12 03:33:33,653][78123] Updated weights for policy 1, policy_version 11170 (0.0008) -[2023-10-12 03:33:34,008][78123] Updated weights for policy 1, policy_version 11180 (0.0009) -[2023-10-12 03:33:34,135][78091] Updated weights for policy 0, policy_version 11240 (0.0009) -[2023-10-12 03:33:34,376][78123] Updated weights for policy 1, policy_version 11190 (0.0008) -[2023-10-12 03:33:34,499][78091] Updated weights for policy 0, policy_version 11250 (0.0008) -[2023-10-12 03:33:34,755][78123] Updated weights for policy 1, policy_version 11200 (0.0007) -[2023-10-12 03:33:34,877][78091] Updated weights for policy 0, policy_version 11260 (0.0007) -[2023-10-12 03:33:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 23003136. Throughput: 0: 1607.1, 1: 1609.1. Samples: 5752566. Policy #0 lag: (min: 17.0, avg: 23.3, max: 49.0) -[2023-10-12 03:33:35,202][77203] Avg episode reward: [(0, '30.370'), (1, '33.990')] -[2023-10-12 03:33:39,097][78091] Updated weights for policy 0, policy_version 11270 (0.0007) -[2023-10-12 03:33:39,296][78123] Updated weights for policy 1, policy_version 11210 (0.0010) -[2023-10-12 03:33:39,469][78091] Updated weights for policy 0, policy_version 11280 (0.0010) -[2023-10-12 03:33:39,669][78123] Updated weights for policy 1, policy_version 11220 (0.0007) -[2023-10-12 03:33:39,845][78091] Updated weights for policy 0, policy_version 11290 (0.0007) -[2023-10-12 03:33:40,037][78123] Updated weights for policy 1, policy_version 11230 (0.0007) -[2023-10-12 03:33:40,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 23068672. Throughput: 0: 1597.7, 1: 1593.7. Samples: 5770694. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:33:40,202][77203] Avg episode reward: [(0, '34.940'), (1, '39.620')] -[2023-10-12 03:33:40,218][77950] Saving new best policy, reward=39.620! -[2023-10-12 03:33:40,218][77792] Saving new best policy, reward=34.940! -[2023-10-12 03:33:44,220][78091] Updated weights for policy 0, policy_version 11300 (0.0008) -[2023-10-12 03:33:44,340][78123] Updated weights for policy 1, policy_version 11240 (0.0008) -[2023-10-12 03:33:44,589][78091] Updated weights for policy 0, policy_version 11310 (0.0009) -[2023-10-12 03:33:44,712][78123] Updated weights for policy 1, policy_version 11250 (0.0011) -[2023-10-12 03:33:44,961][78091] Updated weights for policy 0, policy_version 11320 (0.0007) -[2023-10-12 03:33:45,089][78123] Updated weights for policy 1, policy_version 11260 (0.0007) -[2023-10-12 03:33:45,201][77203] Fps is (10 sec: 6553.6, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 23068672. Throughput: 0: 1588.1, 1: 1589.5. Samples: 5780816. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:33:45,202][77203] Avg episode reward: [(0, '29.670'), (1, '33.400')] -[2023-10-12 03:33:49,352][78123] Updated weights for policy 1, policy_version 11270 (0.0009) -[2023-10-12 03:33:49,432][78091] Updated weights for policy 0, policy_version 11330 (0.0008) -[2023-10-12 03:33:49,722][78123] Updated weights for policy 1, policy_version 11280 (0.0009) -[2023-10-12 03:33:49,804][78091] Updated weights for policy 0, policy_version 11340 (0.0010) -[2023-10-12 03:33:50,079][78123] Updated weights for policy 1, policy_version 11290 (0.0008) -[2023-10-12 03:33:50,171][78091] Updated weights for policy 0, policy_version 11350 (0.0009) -[2023-10-12 03:33:50,201][77203] Fps is (10 sec: 6553.7, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 23134208. Throughput: 0: 1599.2, 1: 1609.0. Samples: 5800266. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:33:50,202][77203] Avg episode reward: [(0, '33.620'), (1, '35.910')] -[2023-10-12 03:33:50,548][78091] Updated weights for policy 0, policy_version 11360 (0.0007) -[2023-10-12 03:33:54,242][78123] Updated weights for policy 1, policy_version 11300 (0.0009) -[2023-10-12 03:33:54,604][78123] Updated weights for policy 1, policy_version 11310 (0.0007) -[2023-10-12 03:33:54,775][78091] Updated weights for policy 0, policy_version 11370 (0.0009) -[2023-10-12 03:33:54,975][78123] Updated weights for policy 1, policy_version 11320 (0.0007) -[2023-10-12 03:33:55,147][78091] Updated weights for policy 0, policy_version 11380 (0.0007) -[2023-10-12 03:33:55,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 23199744. Throughput: 0: 1608.3, 1: 1604.4. Samples: 5818896. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-12 03:33:55,201][77203] Avg episode reward: [(0, '31.300'), (1, '33.640')] -[2023-10-12 03:33:55,518][78091] Updated weights for policy 0, policy_version 11390 (0.0007) -[2023-10-12 03:33:59,282][78123] Updated weights for policy 1, policy_version 11330 (0.0008) -[2023-10-12 03:33:59,683][78123] Updated weights for policy 1, policy_version 11340 (0.0007) -[2023-10-12 03:33:59,991][78091] Updated weights for policy 0, policy_version 11400 (0.0007) -[2023-10-12 03:34:00,038][78123] Updated weights for policy 1, policy_version 11350 (0.0010) -[2023-10-12 03:34:00,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 23265280. Throughput: 0: 1592.8, 1: 1586.6. Samples: 5828540. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-12 03:34:00,201][77203] Avg episode reward: [(0, '35.870'), (1, '35.340')] -[2023-10-12 03:34:00,362][78091] Updated weights for policy 0, policy_version 11410 (0.0008) -[2023-10-12 03:34:00,409][78123] Updated weights for policy 1, policy_version 11360 (0.0008) -[2023-10-12 03:34:00,733][78091] Updated weights for policy 0, policy_version 11420 (0.0009) -[2023-10-12 03:34:00,880][77792] Saving new best policy, reward=35.870! -[2023-10-12 03:34:04,632][78123] Updated weights for policy 1, policy_version 11370 (0.0009) -[2023-10-12 03:34:04,919][78091] Updated weights for policy 0, policy_version 11430 (0.0009) -[2023-10-12 03:34:04,994][78123] Updated weights for policy 1, policy_version 11380 (0.0009) -[2023-10-12 03:34:05,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 23330816. Throughput: 0: 1601.6, 1: 1598.9. Samples: 5848318. Policy #0 lag: (min: 24.0, avg: 50.3, max: 56.0) -[2023-10-12 03:34:05,201][77203] Avg episode reward: [(0, '32.850'), (1, '35.280')] -[2023-10-12 03:34:05,290][78091] Updated weights for policy 0, policy_version 11440 (0.0009) -[2023-10-12 03:34:05,369][78123] Updated weights for policy 1, policy_version 11390 (0.0009) -[2023-10-12 03:34:05,672][78091] Updated weights for policy 0, policy_version 11450 (0.0008) -[2023-10-12 03:34:09,690][78123] Updated weights for policy 1, policy_version 11400 (0.0008) -[2023-10-12 03:34:09,764][78091] Updated weights for policy 0, policy_version 11460 (0.0008) -[2023-10-12 03:34:10,061][78123] Updated weights for policy 1, policy_version 11410 (0.0009) -[2023-10-12 03:34:10,138][78091] Updated weights for policy 0, policy_version 11470 (0.0009) -[2023-10-12 03:34:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 23396352. Throughput: 0: 1619.1, 1: 1605.4. Samples: 5867446. Policy #0 lag: (min: 24.0, avg: 50.3, max: 56.0) -[2023-10-12 03:34:10,201][77203] Avg episode reward: [(0, '31.970'), (1, '36.400')] -[2023-10-12 03:34:10,429][78123] Updated weights for policy 1, policy_version 11420 (0.0008) -[2023-10-12 03:34:10,517][78091] Updated weights for policy 0, policy_version 11480 (0.0008) -[2023-10-12 03:34:14,898][78123] Updated weights for policy 1, policy_version 11430 (0.0007) -[2023-10-12 03:34:14,947][78091] Updated weights for policy 0, policy_version 11490 (0.0008) -[2023-10-12 03:34:15,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 23461888. Throughput: 0: 1600.5, 1: 1586.4. Samples: 5876536. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:34:15,202][77203] Avg episode reward: [(0, '32.120'), (1, '36.730')] -[2023-10-12 03:34:15,257][78123] Updated weights for policy 1, policy_version 11440 (0.0007) -[2023-10-12 03:34:15,324][78091] Updated weights for policy 0, policy_version 11500 (0.0008) -[2023-10-12 03:34:15,618][78123] Updated weights for policy 1, policy_version 11450 (0.0010) -[2023-10-12 03:34:15,700][78091] Updated weights for policy 0, policy_version 11510 (0.0008) -[2023-10-12 03:34:16,064][78091] Updated weights for policy 0, policy_version 11520 (0.0008) -[2023-10-12 03:34:19,905][78123] Updated weights for policy 1, policy_version 11460 (0.0008) -[2023-10-12 03:34:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 23527424. Throughput: 0: 1601.0, 1: 1588.7. Samples: 5896102. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:34:20,201][77203] Avg episode reward: [(0, '32.850'), (1, '33.360')] -[2023-10-12 03:34:20,272][78123] Updated weights for policy 1, policy_version 11470 (0.0008) -[2023-10-12 03:34:20,404][78091] Updated weights for policy 0, policy_version 11530 (0.0007) -[2023-10-12 03:34:20,634][78123] Updated weights for policy 1, policy_version 11480 (0.0008) -[2023-10-12 03:34:20,772][78091] Updated weights for policy 0, policy_version 11540 (0.0007) -[2023-10-12 03:34:21,149][78091] Updated weights for policy 0, policy_version 11550 (0.0010) -[2023-10-12 03:34:25,010][78123] Updated weights for policy 1, policy_version 11490 (0.0008) -[2023-10-12 03:34:25,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 23592960. Throughput: 0: 1615.9, 1: 1603.4. Samples: 5915560. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:34:25,202][77203] Avg episode reward: [(0, '32.690'), (1, '36.720')] -[2023-10-12 03:34:25,374][78123] Updated weights for policy 1, policy_version 11500 (0.0007) -[2023-10-12 03:34:25,481][78091] Updated weights for policy 0, policy_version 11560 (0.0009) -[2023-10-12 03:34:25,738][78123] Updated weights for policy 1, policy_version 11510 (0.0008) -[2023-10-12 03:34:25,856][78091] Updated weights for policy 0, policy_version 11570 (0.0007) -[2023-10-12 03:34:26,108][78123] Updated weights for policy 1, policy_version 11520 (0.0007) -[2023-10-12 03:34:26,230][78091] Updated weights for policy 0, policy_version 11580 (0.0008) -[2023-10-12 03:34:30,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 23658496. Throughput: 0: 1600.7, 1: 1586.9. Samples: 5924256. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:34:30,202][77203] Avg episode reward: [(0, '33.350'), (1, '34.160')] -[2023-10-12 03:34:30,488][78123] Updated weights for policy 1, policy_version 11530 (0.0008) -[2023-10-12 03:34:30,529][78091] Updated weights for policy 0, policy_version 11590 (0.0009) -[2023-10-12 03:34:30,861][78123] Updated weights for policy 1, policy_version 11540 (0.0007) -[2023-10-12 03:34:30,905][78091] Updated weights for policy 0, policy_version 11600 (0.0008) -[2023-10-12 03:34:31,219][78123] Updated weights for policy 1, policy_version 11550 (0.0008) -[2023-10-12 03:34:31,276][78091] Updated weights for policy 0, policy_version 11610 (0.0009) -[2023-10-12 03:34:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 23724032. Throughput: 0: 1607.0, 1: 1585.5. Samples: 5943928. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-12 03:34:35,202][77203] Avg episode reward: [(0, '32.320'), (1, '36.000')] -[2023-10-12 03:34:35,569][78123] Updated weights for policy 1, policy_version 11560 (0.0009) -[2023-10-12 03:34:35,580][78091] Updated weights for policy 0, policy_version 11620 (0.0010) -[2023-10-12 03:34:35,932][78123] Updated weights for policy 1, policy_version 11570 (0.0008) -[2023-10-12 03:34:35,957][78091] Updated weights for policy 0, policy_version 11630 (0.0009) -[2023-10-12 03:34:36,291][78123] Updated weights for policy 1, policy_version 11580 (0.0009) -[2023-10-12 03:34:36,327][78091] Updated weights for policy 0, policy_version 11640 (0.0008) -[2023-10-12 03:34:40,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 23789568. Throughput: 0: 1605.7, 1: 1599.6. Samples: 5963134. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-12 03:34:40,201][77203] Avg episode reward: [(0, '33.130'), (1, '37.000')] -[2023-10-12 03:34:40,742][78091] Updated weights for policy 0, policy_version 11650 (0.0008) -[2023-10-12 03:34:40,795][78123] Updated weights for policy 1, policy_version 11590 (0.0010) -[2023-10-12 03:34:41,163][78091] Updated weights for policy 0, policy_version 11660 (0.0009) -[2023-10-12 03:34:41,167][78123] Updated weights for policy 1, policy_version 11600 (0.0007) -[2023-10-12 03:34:41,526][78123] Updated weights for policy 1, policy_version 11610 (0.0007) -[2023-10-12 03:34:41,530][78091] Updated weights for policy 0, policy_version 11670 (0.0008) -[2023-10-12 03:34:41,897][78091] Updated weights for policy 0, policy_version 11680 (0.0010) -[2023-10-12 03:34:45,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 23855104. Throughput: 0: 1594.6, 1: 1583.1. Samples: 5971536. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:34:45,202][77203] Avg episode reward: [(0, '31.580'), (1, '35.720')] -[2023-10-12 03:34:46,178][78123] Updated weights for policy 1, policy_version 11620 (0.0008) -[2023-10-12 03:34:46,194][78091] Updated weights for policy 0, policy_version 11690 (0.0009) -[2023-10-12 03:34:46,548][78123] Updated weights for policy 1, policy_version 11630 (0.0009) -[2023-10-12 03:34:46,569][78091] Updated weights for policy 0, policy_version 11700 (0.0009) -[2023-10-12 03:34:46,911][78123] Updated weights for policy 1, policy_version 11640 (0.0010) -[2023-10-12 03:34:46,935][78091] Updated weights for policy 0, policy_version 11710 (0.0009) -[2023-10-12 03:34:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 23920640. Throughput: 0: 1585.7, 1: 1574.0. Samples: 5990504. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:34:50,201][77203] Avg episode reward: [(0, '34.870'), (1, '32.890')] -[2023-10-12 03:34:51,197][78091] Updated weights for policy 0, policy_version 11720 (0.0008) -[2023-10-12 03:34:51,306][78123] Updated weights for policy 1, policy_version 11650 (0.0008) -[2023-10-12 03:34:51,573][78091] Updated weights for policy 0, policy_version 11730 (0.0010) -[2023-10-12 03:34:51,673][78123] Updated weights for policy 1, policy_version 11660 (0.0008) -[2023-10-12 03:34:51,932][78091] Updated weights for policy 0, policy_version 11740 (0.0009) -[2023-10-12 03:34:52,043][78123] Updated weights for policy 1, policy_version 11670 (0.0007) -[2023-10-12 03:34:52,417][78123] Updated weights for policy 1, policy_version 11680 (0.0008) -[2023-10-12 03:34:55,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 23986176. Throughput: 0: 1586.2, 1: 1579.1. Samples: 6009882. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:34:55,202][77203] Avg episode reward: [(0, '31.550'), (1, '37.760')] -[2023-10-12 03:34:56,279][78091] Updated weights for policy 0, policy_version 11750 (0.0008) -[2023-10-12 03:34:56,655][78091] Updated weights for policy 0, policy_version 11760 (0.0010) -[2023-10-12 03:34:56,727][78123] Updated weights for policy 1, policy_version 11690 (0.0009) -[2023-10-12 03:34:57,018][78091] Updated weights for policy 0, policy_version 11770 (0.0010) -[2023-10-12 03:34:57,082][78123] Updated weights for policy 1, policy_version 11700 (0.0007) -[2023-10-12 03:34:57,444][78123] Updated weights for policy 1, policy_version 11710 (0.0008) -[2023-10-12 03:35:00,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 24051712. Throughput: 0: 1580.9, 1: 1571.2. Samples: 6018384. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:35:00,202][77203] Avg episode reward: [(0, '34.320'), (1, '35.270')] -[2023-10-12 03:35:01,423][78091] Updated weights for policy 0, policy_version 11780 (0.0008) -[2023-10-12 03:35:01,743][78123] Updated weights for policy 1, policy_version 11720 (0.0007) -[2023-10-12 03:35:01,790][78091] Updated weights for policy 0, policy_version 11790 (0.0008) -[2023-10-12 03:35:02,102][78123] Updated weights for policy 1, policy_version 11730 (0.0008) -[2023-10-12 03:35:02,166][78091] Updated weights for policy 0, policy_version 11800 (0.0007) -[2023-10-12 03:35:02,479][78123] Updated weights for policy 1, policy_version 11740 (0.0009) -[2023-10-12 03:35:05,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 24117248. Throughput: 0: 1583.6, 1: 1563.3. Samples: 6037712. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:35:05,201][77203] Avg episode reward: [(0, '29.540'), (1, '36.230')] -[2023-10-12 03:35:06,275][78091] Updated weights for policy 0, policy_version 11810 (0.0008) -[2023-10-12 03:35:06,643][78091] Updated weights for policy 0, policy_version 11820 (0.0008) -[2023-10-12 03:35:07,014][78091] Updated weights for policy 0, policy_version 11830 (0.0008) -[2023-10-12 03:35:07,034][78123] Updated weights for policy 1, policy_version 11750 (0.0009) -[2023-10-12 03:35:07,390][78091] Updated weights for policy 0, policy_version 11840 (0.0007) -[2023-10-12 03:35:07,398][78123] Updated weights for policy 1, policy_version 11760 (0.0009) -[2023-10-12 03:35:07,761][78123] Updated weights for policy 1, policy_version 11770 (0.0009) -[2023-10-12 03:35:10,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 24182784. Throughput: 0: 1586.9, 1: 1559.8. Samples: 6057160. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:35:10,202][77203] Avg episode reward: [(0, '30.440'), (1, '38.140')] -[2023-10-12 03:35:10,211][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000011840_12124160.pth... -[2023-10-12 03:35:10,210][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000011776_12058624.pth... -[2023-10-12 03:35:10,245][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000010304_10551296.pth -[2023-10-12 03:35:10,250][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000010336_10584064.pth -[2023-10-12 03:35:11,726][78091] Updated weights for policy 0, policy_version 11850 (0.0007) -[2023-10-12 03:35:12,096][78123] Updated weights for policy 1, policy_version 11780 (0.0008) -[2023-10-12 03:35:12,102][78091] Updated weights for policy 0, policy_version 11860 (0.0009) -[2023-10-12 03:35:12,459][78123] Updated weights for policy 1, policy_version 11790 (0.0007) -[2023-10-12 03:35:12,468][78091] Updated weights for policy 0, policy_version 11870 (0.0008) -[2023-10-12 03:35:12,819][78123] Updated weights for policy 1, policy_version 11800 (0.0009) -[2023-10-12 03:35:15,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 24248320. Throughput: 0: 1583.7, 1: 1571.0. Samples: 6066220. Policy #0 lag: (min: 26.0, avg: 28.9, max: 58.0) -[2023-10-12 03:35:15,202][77203] Avg episode reward: [(0, '31.890'), (1, '35.380')] -[2023-10-12 03:35:16,744][78091] Updated weights for policy 0, policy_version 11880 (0.0009) -[2023-10-12 03:35:17,102][78123] Updated weights for policy 1, policy_version 11810 (0.0009) -[2023-10-12 03:35:17,119][78091] Updated weights for policy 0, policy_version 11890 (0.0010) -[2023-10-12 03:35:17,474][78123] Updated weights for policy 1, policy_version 11820 (0.0009) -[2023-10-12 03:35:17,487][78091] Updated weights for policy 0, policy_version 11900 (0.0007) -[2023-10-12 03:35:17,840][78123] Updated weights for policy 1, policy_version 11830 (0.0009) -[2023-10-12 03:35:18,203][78123] Updated weights for policy 1, policy_version 11840 (0.0009) -[2023-10-12 03:35:20,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 24313856. Throughput: 0: 1583.1, 1: 1559.2. Samples: 6085334. Policy #0 lag: (min: 26.0, avg: 28.9, max: 58.0) -[2023-10-12 03:35:20,202][77203] Avg episode reward: [(0, '28.060'), (1, '34.870')] -[2023-10-12 03:35:21,949][78091] Updated weights for policy 0, policy_version 11910 (0.0007) -[2023-10-12 03:35:22,328][78091] Updated weights for policy 0, policy_version 11920 (0.0007) -[2023-10-12 03:35:22,695][78091] Updated weights for policy 0, policy_version 11930 (0.0007) -[2023-10-12 03:35:22,708][78123] Updated weights for policy 1, policy_version 11850 (0.0009) -[2023-10-12 03:35:23,069][78123] Updated weights for policy 1, policy_version 11860 (0.0007) -[2023-10-12 03:35:23,442][78123] Updated weights for policy 1, policy_version 11870 (0.0007) -[2023-10-12 03:35:25,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 24379392. Throughput: 0: 1587.8, 1: 1551.2. Samples: 6104392. Policy #0 lag: (min: 1.0, avg: 3.9, max: 33.0) -[2023-10-12 03:35:25,202][77203] Avg episode reward: [(0, '32.240'), (1, '34.050')] -[2023-10-12 03:35:26,720][78091] Updated weights for policy 0, policy_version 11940 (0.0008) -[2023-10-12 03:35:27,090][78091] Updated weights for policy 0, policy_version 11950 (0.0009) -[2023-10-12 03:35:27,459][78091] Updated weights for policy 0, policy_version 11960 (0.0008) -[2023-10-12 03:35:27,951][78123] Updated weights for policy 1, policy_version 11880 (0.0009) -[2023-10-12 03:35:28,318][78123] Updated weights for policy 1, policy_version 11890 (0.0007) -[2023-10-12 03:35:28,689][78123] Updated weights for policy 1, policy_version 11900 (0.0008) -[2023-10-12 03:35:30,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 24444928. Throughput: 0: 1596.4, 1: 1577.1. Samples: 6114342. Policy #0 lag: (min: 1.0, avg: 3.9, max: 33.0) -[2023-10-12 03:35:30,201][77203] Avg episode reward: [(0, '32.630'), (1, '37.580')] -[2023-10-12 03:35:31,840][78091] Updated weights for policy 0, policy_version 11970 (0.0008) -[2023-10-12 03:35:32,219][78091] Updated weights for policy 0, policy_version 11980 (0.0007) -[2023-10-12 03:35:32,583][78091] Updated weights for policy 0, policy_version 11990 (0.0010) -[2023-10-12 03:35:32,958][78091] Updated weights for policy 0, policy_version 12000 (0.0008) -[2023-10-12 03:35:33,189][78123] Updated weights for policy 1, policy_version 11910 (0.0009) -[2023-10-12 03:35:33,563][78123] Updated weights for policy 1, policy_version 11920 (0.0008) -[2023-10-12 03:35:33,931][78123] Updated weights for policy 1, policy_version 11930 (0.0007) -[2023-10-12 03:35:35,201][77203] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 24510464. Throughput: 0: 1599.3, 1: 1567.6. Samples: 6133018. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:35:35,201][77203] Avg episode reward: [(0, '31.530'), (1, '36.140')] -[2023-10-12 03:35:37,283][78091] Updated weights for policy 0, policy_version 12010 (0.0009) -[2023-10-12 03:35:37,658][78091] Updated weights for policy 0, policy_version 12020 (0.0009) -[2023-10-12 03:35:38,027][78091] Updated weights for policy 0, policy_version 12030 (0.0007) -[2023-10-12 03:35:38,067][78123] Updated weights for policy 1, policy_version 11940 (0.0009) -[2023-10-12 03:35:38,433][78123] Updated weights for policy 1, policy_version 11950 (0.0011) -[2023-10-12 03:35:38,809][78123] Updated weights for policy 1, policy_version 11960 (0.0008) -[2023-10-12 03:35:40,201][77203] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 24576000. Throughput: 0: 1602.1, 1: 1562.2. Samples: 6152276. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:35:40,202][77203] Avg episode reward: [(0, '35.290'), (1, '38.790')] -[2023-10-12 03:35:42,414][78091] Updated weights for policy 0, policy_version 12040 (0.0008) -[2023-10-12 03:35:42,777][78091] Updated weights for policy 0, policy_version 12050 (0.0010) -[2023-10-12 03:35:43,115][78123] Updated weights for policy 1, policy_version 11970 (0.0007) -[2023-10-12 03:35:43,158][78091] Updated weights for policy 0, policy_version 12060 (0.0008) -[2023-10-12 03:35:43,483][78123] Updated weights for policy 1, policy_version 11980 (0.0007) -[2023-10-12 03:35:43,843][78123] Updated weights for policy 1, policy_version 11990 (0.0008) -[2023-10-12 03:35:44,216][78123] Updated weights for policy 1, policy_version 12000 (0.0008) -[2023-10-12 03:35:45,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 24641536. Throughput: 0: 1616.3, 1: 1589.8. Samples: 6162656. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-12 03:35:45,202][77203] Avg episode reward: [(0, '32.840'), (1, '36.860')] -[2023-10-12 03:35:47,485][78091] Updated weights for policy 0, policy_version 12070 (0.0009) -[2023-10-12 03:35:47,851][78091] Updated weights for policy 0, policy_version 12080 (0.0010) -[2023-10-12 03:35:48,225][78091] Updated weights for policy 0, policy_version 12090 (0.0010) -[2023-10-12 03:35:48,508][78123] Updated weights for policy 1, policy_version 12010 (0.0009) -[2023-10-12 03:35:48,873][78123] Updated weights for policy 1, policy_version 12020 (0.0010) -[2023-10-12 03:35:49,235][78123] Updated weights for policy 1, policy_version 12030 (0.0009) -[2023-10-12 03:35:50,201][77203] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 24707072. Throughput: 0: 1600.2, 1: 1588.8. Samples: 6181218. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-12 03:35:50,201][77203] Avg episode reward: [(0, '33.660'), (1, '36.560')] -[2023-10-12 03:35:52,528][78091] Updated weights for policy 0, policy_version 12100 (0.0010) -[2023-10-12 03:35:52,911][78091] Updated weights for policy 0, policy_version 12110 (0.0010) -[2023-10-12 03:35:53,278][78091] Updated weights for policy 0, policy_version 12120 (0.0010) -[2023-10-12 03:35:53,649][78123] Updated weights for policy 1, policy_version 12040 (0.0007) -[2023-10-12 03:35:54,015][78123] Updated weights for policy 1, policy_version 12050 (0.0009) -[2023-10-12 03:35:54,384][78123] Updated weights for policy 1, policy_version 12060 (0.0008) -[2023-10-12 03:35:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 24772608. Throughput: 0: 1596.6, 1: 1582.1. Samples: 6200200. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:35:55,202][77203] Avg episode reward: [(0, '33.940'), (1, '39.720')] -[2023-10-12 03:35:55,210][77950] Saving new best policy, reward=39.720! -[2023-10-12 03:35:57,555][78091] Updated weights for policy 0, policy_version 12130 (0.0008) -[2023-10-12 03:35:57,916][78091] Updated weights for policy 0, policy_version 12140 (0.0009) -[2023-10-12 03:35:58,287][78091] Updated weights for policy 0, policy_version 12150 (0.0008) -[2023-10-12 03:35:58,665][78091] Updated weights for policy 0, policy_version 12160 (0.0007) -[2023-10-12 03:35:58,687][78123] Updated weights for policy 1, policy_version 12070 (0.0007) -[2023-10-12 03:35:59,059][78123] Updated weights for policy 1, policy_version 12080 (0.0010) -[2023-10-12 03:35:59,432][78123] Updated weights for policy 1, policy_version 12090 (0.0011) -[2023-10-12 03:36:00,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 24838144. Throughput: 0: 1616.3, 1: 1597.4. Samples: 6210836. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:36:00,202][77203] Avg episode reward: [(0, '30.650'), (1, '36.410')] -[2023-10-12 03:36:02,922][78091] Updated weights for policy 0, policy_version 12170 (0.0010) -[2023-10-12 03:36:03,306][78091] Updated weights for policy 0, policy_version 12180 (0.0010) -[2023-10-12 03:36:03,673][78091] Updated weights for policy 0, policy_version 12190 (0.0010) -[2023-10-12 03:36:03,729][78123] Updated weights for policy 1, policy_version 12100 (0.0009) -[2023-10-12 03:36:04,094][78123] Updated weights for policy 1, policy_version 12110 (0.0011) -[2023-10-12 03:36:04,468][78123] Updated weights for policy 1, policy_version 12120 (0.0008) -[2023-10-12 03:36:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 24903680. Throughput: 0: 1594.0, 1: 1603.6. Samples: 6229226. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:36:05,202][77203] Avg episode reward: [(0, '31.070'), (1, '37.390')] -[2023-10-12 03:36:08,004][78091] Updated weights for policy 0, policy_version 12200 (0.0008) -[2023-10-12 03:36:08,382][78091] Updated weights for policy 0, policy_version 12210 (0.0009) -[2023-10-12 03:36:08,764][78091] Updated weights for policy 0, policy_version 12220 (0.0008) -[2023-10-12 03:36:08,819][78123] Updated weights for policy 1, policy_version 12130 (0.0009) -[2023-10-12 03:36:09,178][78123] Updated weights for policy 1, policy_version 12140 (0.0008) -[2023-10-12 03:36:09,547][78123] Updated weights for policy 1, policy_version 12150 (0.0011) -[2023-10-12 03:36:09,907][78123] Updated weights for policy 1, policy_version 12160 (0.0007) -[2023-10-12 03:36:10,201][77203] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 24969216. Throughput: 0: 1599.3, 1: 1592.5. Samples: 6248024. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-12 03:36:10,202][77203] Avg episode reward: [(0, '30.050'), (1, '38.470')] -[2023-10-12 03:36:13,109][78091] Updated weights for policy 0, policy_version 12230 (0.0009) -[2023-10-12 03:36:13,486][78091] Updated weights for policy 0, policy_version 12240 (0.0008) -[2023-10-12 03:36:13,859][78091] Updated weights for policy 0, policy_version 12250 (0.0008) -[2023-10-12 03:36:14,123][78123] Updated weights for policy 1, policy_version 12170 (0.0009) -[2023-10-12 03:36:14,492][78123] Updated weights for policy 1, policy_version 12180 (0.0007) -[2023-10-12 03:36:14,861][78123] Updated weights for policy 1, policy_version 12190 (0.0009) -[2023-10-12 03:36:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 25034752. Throughput: 0: 1621.8, 1: 1591.6. Samples: 6258946. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-12 03:36:15,202][77203] Avg episode reward: [(0, '32.170'), (1, '36.460')] -[2023-10-12 03:36:18,158][78091] Updated weights for policy 0, policy_version 12260 (0.0009) -[2023-10-12 03:36:18,517][78091] Updated weights for policy 0, policy_version 12270 (0.0008) -[2023-10-12 03:36:18,900][78091] Updated weights for policy 0, policy_version 12280 (0.0010) -[2023-10-12 03:36:19,280][78123] Updated weights for policy 1, policy_version 12200 (0.0009) -[2023-10-12 03:36:19,655][78123] Updated weights for policy 1, policy_version 12210 (0.0009) -[2023-10-12 03:36:20,028][78123] Updated weights for policy 1, policy_version 12220 (0.0008) -[2023-10-12 03:36:20,201][77203] Fps is (10 sec: 13107.7, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 25100288. Throughput: 0: 1605.6, 1: 1606.7. Samples: 6277570. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:36:20,201][77203] Avg episode reward: [(0, '31.480'), (1, '34.160')] -[2023-10-12 03:36:23,209][78091] Updated weights for policy 0, policy_version 12290 (0.0008) -[2023-10-12 03:36:23,584][78091] Updated weights for policy 0, policy_version 12300 (0.0007) -[2023-10-12 03:36:23,950][78091] Updated weights for policy 0, policy_version 12310 (0.0010) -[2023-10-12 03:36:24,320][78091] Updated weights for policy 0, policy_version 12320 (0.0008) -[2023-10-12 03:36:24,335][78123] Updated weights for policy 1, policy_version 12230 (0.0010) -[2023-10-12 03:36:24,699][78123] Updated weights for policy 1, policy_version 12240 (0.0011) -[2023-10-12 03:36:25,066][78123] Updated weights for policy 1, policy_version 12250 (0.0010) -[2023-10-12 03:36:25,201][77203] Fps is (10 sec: 9830.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 25133056. Throughput: 0: 1597.2, 1: 1602.8. Samples: 6296280. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:36:25,202][77203] Avg episode reward: [(0, '31.590'), (1, '40.540')] -[2023-10-12 03:36:25,288][77950] Saving new best policy, reward=40.540! -[2023-10-12 03:36:28,632][78091] Updated weights for policy 0, policy_version 12330 (0.0007) -[2023-10-12 03:36:29,009][78091] Updated weights for policy 0, policy_version 12340 (0.0008) -[2023-10-12 03:36:29,361][78123] Updated weights for policy 1, policy_version 12260 (0.0009) -[2023-10-12 03:36:29,376][78091] Updated weights for policy 0, policy_version 12350 (0.0009) -[2023-10-12 03:36:29,738][78123] Updated weights for policy 1, policy_version 12270 (0.0008) -[2023-10-12 03:36:30,105][78123] Updated weights for policy 1, policy_version 12280 (0.0008) -[2023-10-12 03:36:30,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 25198592. Throughput: 0: 1610.7, 1: 1588.9. Samples: 6306636. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:36:30,201][77203] Avg episode reward: [(0, '34.170'), (1, '37.160')] -[2023-10-12 03:36:33,665][78091] Updated weights for policy 0, policy_version 12360 (0.0009) -[2023-10-12 03:36:34,031][78091] Updated weights for policy 0, policy_version 12370 (0.0009) -[2023-10-12 03:36:34,325][78123] Updated weights for policy 1, policy_version 12290 (0.0010) -[2023-10-12 03:36:34,396][78091] Updated weights for policy 0, policy_version 12380 (0.0009) -[2023-10-12 03:36:34,691][78123] Updated weights for policy 1, policy_version 12300 (0.0007) -[2023-10-12 03:36:35,051][78123] Updated weights for policy 1, policy_version 12310 (0.0009) -[2023-10-12 03:36:35,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 25264128. Throughput: 0: 1612.2, 1: 1604.7. Samples: 6325980. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:36:35,202][77203] Avg episode reward: [(0, '34.570'), (1, '35.770')] -[2023-10-12 03:36:35,425][78123] Updated weights for policy 1, policy_version 12320 (0.0008) -[2023-10-12 03:36:38,755][78091] Updated weights for policy 0, policy_version 12390 (0.0008) -[2023-10-12 03:36:39,121][78091] Updated weights for policy 0, policy_version 12400 (0.0010) -[2023-10-12 03:36:39,499][78091] Updated weights for policy 0, policy_version 12410 (0.0009) -[2023-10-12 03:36:39,901][78123] Updated weights for policy 1, policy_version 12330 (0.0008) -[2023-10-12 03:36:40,201][77203] Fps is (10 sec: 13106.6, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 25329664. Throughput: 0: 1595.8, 1: 1607.6. Samples: 6344356. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:36:40,202][77203] Avg episode reward: [(0, '36.190'), (1, '41.810')] -[2023-10-12 03:36:40,209][77792] Saving new best policy, reward=36.190! -[2023-10-12 03:36:40,261][78123] Updated weights for policy 1, policy_version 12340 (0.0007) -[2023-10-12 03:36:40,629][78123] Updated weights for policy 1, policy_version 12350 (0.0007) -[2023-10-12 03:36:40,701][77950] Saving new best policy, reward=41.810! -[2023-10-12 03:36:43,751][78091] Updated weights for policy 0, policy_version 12420 (0.0007) -[2023-10-12 03:36:44,128][78091] Updated weights for policy 0, policy_version 12430 (0.0011) -[2023-10-12 03:36:44,498][78091] Updated weights for policy 0, policy_version 12440 (0.0008) -[2023-10-12 03:36:45,044][78123] Updated weights for policy 1, policy_version 12360 (0.0009) -[2023-10-12 03:36:45,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 25395200. Throughput: 0: 1605.2, 1: 1582.8. Samples: 6354296. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:36:45,202][77203] Avg episode reward: [(0, '34.270'), (1, '35.580')] -[2023-10-12 03:36:45,411][78123] Updated weights for policy 1, policy_version 12370 (0.0010) -[2023-10-12 03:36:45,781][78123] Updated weights for policy 1, policy_version 12380 (0.0011) -[2023-10-12 03:36:48,723][78091] Updated weights for policy 0, policy_version 12450 (0.0009) -[2023-10-12 03:36:49,096][78091] Updated weights for policy 0, policy_version 12460 (0.0008) -[2023-10-12 03:36:49,461][78091] Updated weights for policy 0, policy_version 12470 (0.0008) -[2023-10-12 03:36:49,832][78091] Updated weights for policy 0, policy_version 12480 (0.0008) -[2023-10-12 03:36:49,982][78123] Updated weights for policy 1, policy_version 12390 (0.0009) -[2023-10-12 03:36:50,201][77203] Fps is (10 sec: 13107.7, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 25460736. Throughput: 0: 1620.4, 1: 1589.6. Samples: 6373676. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:36:50,202][77203] Avg episode reward: [(0, '36.030'), (1, '39.830')] -[2023-10-12 03:36:50,362][78123] Updated weights for policy 1, policy_version 12400 (0.0008) -[2023-10-12 03:36:50,726][78123] Updated weights for policy 1, policy_version 12410 (0.0008) -[2023-10-12 03:36:54,238][78091] Updated weights for policy 0, policy_version 12490 (0.0008) -[2023-10-12 03:36:54,618][78091] Updated weights for policy 0, policy_version 12500 (0.0008) -[2023-10-12 03:36:54,995][78091] Updated weights for policy 0, policy_version 12510 (0.0009) -[2023-10-12 03:36:55,005][78123] Updated weights for policy 1, policy_version 12420 (0.0007) -[2023-10-12 03:36:55,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 25526272. Throughput: 0: 1596.4, 1: 1612.2. Samples: 6392410. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:36:55,201][77203] Avg episode reward: [(0, '34.770'), (1, '34.490')] -[2023-10-12 03:36:55,380][78123] Updated weights for policy 1, policy_version 12430 (0.0007) -[2023-10-12 03:36:55,739][78123] Updated weights for policy 1, policy_version 12440 (0.0007) -[2023-10-12 03:36:59,621][78091] Updated weights for policy 0, policy_version 12520 (0.0008) -[2023-10-12 03:36:59,998][78091] Updated weights for policy 0, policy_version 12530 (0.0007) -[2023-10-12 03:37:00,100][78123] Updated weights for policy 1, policy_version 12450 (0.0008) -[2023-10-12 03:37:00,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 25559040. Throughput: 0: 1585.1, 1: 1588.7. Samples: 6401764. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:37:00,201][77203] Avg episode reward: [(0, '34.050'), (1, '39.870')] -[2023-10-12 03:37:00,371][78091] Updated weights for policy 0, policy_version 12540 (0.0008) -[2023-10-12 03:37:00,453][78123] Updated weights for policy 1, policy_version 12460 (0.0008) -[2023-10-12 03:37:00,834][78123] Updated weights for policy 1, policy_version 12470 (0.0008) -[2023-10-12 03:37:01,196][78123] Updated weights for policy 1, policy_version 12480 (0.0008) -[2023-10-12 03:37:04,486][78091] Updated weights for policy 0, policy_version 12550 (0.0008) -[2023-10-12 03:37:04,861][78091] Updated weights for policy 0, policy_version 12560 (0.0008) -[2023-10-12 03:37:05,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 25624576. Throughput: 0: 1598.2, 1: 1592.7. Samples: 6421160. Policy #0 lag: (min: 17.0, avg: 27.6, max: 49.0) -[2023-10-12 03:37:05,201][77203] Avg episode reward: [(0, '36.180'), (1, '38.900')] -[2023-10-12 03:37:05,231][78091] Updated weights for policy 0, policy_version 12570 (0.0009) -[2023-10-12 03:37:05,399][78123] Updated weights for policy 1, policy_version 12490 (0.0009) -[2023-10-12 03:37:05,772][78123] Updated weights for policy 1, policy_version 12500 (0.0008) -[2023-10-12 03:37:06,140][78123] Updated weights for policy 1, policy_version 12510 (0.0007) -[2023-10-12 03:37:09,605][78091] Updated weights for policy 0, policy_version 12580 (0.0009) -[2023-10-12 03:37:09,982][78091] Updated weights for policy 0, policy_version 12590 (0.0010) -[2023-10-12 03:37:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 25690112. Throughput: 0: 1595.9, 1: 1602.0. Samples: 6440186. Policy #0 lag: (min: 17.0, avg: 27.6, max: 49.0) -[2023-10-12 03:37:10,201][77203] Avg episode reward: [(0, '35.080'), (1, '39.390')] -[2023-10-12 03:37:10,358][78091] Updated weights for policy 0, policy_version 12600 (0.0009) -[2023-10-12 03:37:10,570][78123] Updated weights for policy 1, policy_version 12520 (0.0007) -[2023-10-12 03:37:10,648][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000012608_12910592.pth... -[2023-10-12 03:37:10,682][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000011104_11370496.pth -[2023-10-12 03:37:10,938][78123] Updated weights for policy 1, policy_version 12530 (0.0007) -[2023-10-12 03:37:11,297][78123] Updated weights for policy 1, policy_version 12540 (0.0009) -[2023-10-12 03:37:11,434][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000012544_12845056.pth... -[2023-10-12 03:37:11,462][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000011040_11304960.pth -[2023-10-12 03:37:14,625][78091] Updated weights for policy 0, policy_version 12610 (0.0008) -[2023-10-12 03:37:14,991][78091] Updated weights for policy 0, policy_version 12620 (0.0008) -[2023-10-12 03:37:15,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 25755648. Throughput: 0: 1575.5, 1: 1586.0. Samples: 6448902. Policy #0 lag: (min: 9.0, avg: 17.0, max: 41.0) -[2023-10-12 03:37:15,202][77203] Avg episode reward: [(0, '32.980'), (1, '41.200')] -[2023-10-12 03:37:15,367][78091] Updated weights for policy 0, policy_version 12630 (0.0009) -[2023-10-12 03:37:15,736][78091] Updated weights for policy 0, policy_version 12640 (0.0007) -[2023-10-12 03:37:15,739][78123] Updated weights for policy 1, policy_version 12550 (0.0009) -[2023-10-12 03:37:16,106][78123] Updated weights for policy 1, policy_version 12560 (0.0008) -[2023-10-12 03:37:16,466][78123] Updated weights for policy 1, policy_version 12570 (0.0007) -[2023-10-12 03:37:20,079][78091] Updated weights for policy 0, policy_version 12650 (0.0009) -[2023-10-12 03:37:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 25821184. Throughput: 0: 1585.8, 1: 1578.8. Samples: 6468388. Policy #0 lag: (min: 9.0, avg: 17.0, max: 41.0) -[2023-10-12 03:37:20,201][77203] Avg episode reward: [(0, '35.460'), (1, '38.650')] -[2023-10-12 03:37:20,447][78091] Updated weights for policy 0, policy_version 12660 (0.0009) -[2023-10-12 03:37:20,824][78091] Updated weights for policy 0, policy_version 12670 (0.0008) -[2023-10-12 03:37:20,867][78123] Updated weights for policy 1, policy_version 12580 (0.0009) -[2023-10-12 03:37:21,236][78123] Updated weights for policy 1, policy_version 12590 (0.0008) -[2023-10-12 03:37:21,605][78123] Updated weights for policy 1, policy_version 12600 (0.0011) -[2023-10-12 03:37:25,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 25886720. Throughput: 0: 1604.0, 1: 1584.3. Samples: 6487826. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:37:25,201][77203] Avg episode reward: [(0, '34.090'), (1, '42.580')] -[2023-10-12 03:37:25,208][77950] Saving new best policy, reward=42.580! -[2023-10-12 03:37:25,276][78091] Updated weights for policy 0, policy_version 12680 (0.0009) -[2023-10-12 03:37:25,654][78091] Updated weights for policy 0, policy_version 12690 (0.0009) -[2023-10-12 03:37:25,973][78123] Updated weights for policy 1, policy_version 12610 (0.0009) -[2023-10-12 03:37:26,032][78091] Updated weights for policy 0, policy_version 12700 (0.0008) -[2023-10-12 03:37:26,348][78123] Updated weights for policy 1, policy_version 12620 (0.0010) -[2023-10-12 03:37:26,722][78123] Updated weights for policy 1, policy_version 12630 (0.0010) -[2023-10-12 03:37:27,089][78123] Updated weights for policy 1, policy_version 12640 (0.0008) -[2023-10-12 03:37:30,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 25952256. Throughput: 0: 1573.0, 1: 1583.7. Samples: 6496344. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:37:30,201][77203] Avg episode reward: [(0, '33.840'), (1, '41.460')] -[2023-10-12 03:37:30,460][78091] Updated weights for policy 0, policy_version 12710 (0.0009) -[2023-10-12 03:37:30,817][78091] Updated weights for policy 0, policy_version 12720 (0.0010) -[2023-10-12 03:37:31,192][78091] Updated weights for policy 0, policy_version 12730 (0.0008) -[2023-10-12 03:37:31,349][78123] Updated weights for policy 1, policy_version 12650 (0.0009) -[2023-10-12 03:37:31,725][78123] Updated weights for policy 1, policy_version 12660 (0.0008) -[2023-10-12 03:37:32,094][78123] Updated weights for policy 1, policy_version 12670 (0.0008) -[2023-10-12 03:37:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 26017792. Throughput: 0: 1576.4, 1: 1586.1. Samples: 6515986. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:37:35,201][77203] Avg episode reward: [(0, '32.800'), (1, '42.160')] -[2023-10-12 03:37:35,445][78091] Updated weights for policy 0, policy_version 12740 (0.0010) -[2023-10-12 03:37:35,822][78091] Updated weights for policy 0, policy_version 12750 (0.0009) -[2023-10-12 03:37:36,180][78091] Updated weights for policy 0, policy_version 12760 (0.0007) -[2023-10-12 03:37:36,316][78123] Updated weights for policy 1, policy_version 12680 (0.0008) -[2023-10-12 03:37:36,688][78123] Updated weights for policy 1, policy_version 12690 (0.0008) -[2023-10-12 03:37:37,057][78123] Updated weights for policy 1, policy_version 12700 (0.0008) -[2023-10-12 03:37:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.2, 300 sec: 12662.9). Total num frames: 26083328. Throughput: 0: 1595.3, 1: 1584.4. Samples: 6535498. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-12 03:37:40,201][77203] Avg episode reward: [(0, '34.770'), (1, '43.800')] -[2023-10-12 03:37:40,211][77950] Saving new best policy, reward=43.800! -[2023-10-12 03:37:40,691][78091] Updated weights for policy 0, policy_version 12770 (0.0008) -[2023-10-12 03:37:41,070][78091] Updated weights for policy 0, policy_version 12780 (0.0008) -[2023-10-12 03:37:41,385][78123] Updated weights for policy 1, policy_version 12710 (0.0009) -[2023-10-12 03:37:41,432][78091] Updated weights for policy 0, policy_version 12790 (0.0008) -[2023-10-12 03:37:41,746][78123] Updated weights for policy 1, policy_version 12720 (0.0007) -[2023-10-12 03:37:41,807][78091] Updated weights for policy 0, policy_version 12800 (0.0007) -[2023-10-12 03:37:42,111][78123] Updated weights for policy 1, policy_version 12730 (0.0011) -[2023-10-12 03:37:45,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 26148864. Throughput: 0: 1574.7, 1: 1583.6. Samples: 6543886. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-12 03:37:45,202][77203] Avg episode reward: [(0, '36.120'), (1, '36.910')] -[2023-10-12 03:37:46,041][78091] Updated weights for policy 0, policy_version 12810 (0.0009) -[2023-10-12 03:37:46,402][78091] Updated weights for policy 0, policy_version 12820 (0.0007) -[2023-10-12 03:37:46,436][78123] Updated weights for policy 1, policy_version 12740 (0.0009) -[2023-10-12 03:37:46,772][78091] Updated weights for policy 0, policy_version 12830 (0.0008) -[2023-10-12 03:37:46,808][78123] Updated weights for policy 1, policy_version 12750 (0.0007) -[2023-10-12 03:37:47,175][78123] Updated weights for policy 1, policy_version 12760 (0.0007) -[2023-10-12 03:37:50,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 26214400. Throughput: 0: 1575.9, 1: 1584.8. Samples: 6563392. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-12 03:37:50,205][77203] Avg episode reward: [(0, '32.380'), (1, '41.030')] -[2023-10-12 03:37:51,036][78091] Updated weights for policy 0, policy_version 12840 (0.0010) -[2023-10-12 03:37:51,404][78091] Updated weights for policy 0, policy_version 12850 (0.0010) -[2023-10-12 03:37:51,558][78123] Updated weights for policy 1, policy_version 12770 (0.0008) -[2023-10-12 03:37:51,782][78091] Updated weights for policy 0, policy_version 12860 (0.0009) -[2023-10-12 03:37:51,962][78123] Updated weights for policy 1, policy_version 12780 (0.0009) -[2023-10-12 03:37:52,325][78123] Updated weights for policy 1, policy_version 12790 (0.0009) -[2023-10-12 03:37:52,694][78123] Updated weights for policy 1, policy_version 12800 (0.0007) -[2023-10-12 03:37:55,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 26279936. Throughput: 0: 1589.9, 1: 1588.5. Samples: 6583214. Policy #0 lag: (min: 24.0, avg: 41.1, max: 56.0) -[2023-10-12 03:37:55,201][77203] Avg episode reward: [(0, '36.660'), (1, '37.510')] -[2023-10-12 03:37:55,214][77792] Saving new best policy, reward=36.660! -[2023-10-12 03:37:56,091][78091] Updated weights for policy 0, policy_version 12870 (0.0009) -[2023-10-12 03:37:56,463][78091] Updated weights for policy 0, policy_version 12880 (0.0010) -[2023-10-12 03:37:56,836][78091] Updated weights for policy 0, policy_version 12890 (0.0008) -[2023-10-12 03:37:56,870][78123] Updated weights for policy 1, policy_version 12810 (0.0007) -[2023-10-12 03:37:57,241][78123] Updated weights for policy 1, policy_version 12820 (0.0009) -[2023-10-12 03:37:57,600][78123] Updated weights for policy 1, policy_version 12830 (0.0010) -[2023-10-12 03:38:00,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 26345472. Throughput: 0: 1583.4, 1: 1593.8. Samples: 6591878. Policy #0 lag: (min: 24.0, avg: 41.1, max: 56.0) -[2023-10-12 03:38:00,201][77203] Avg episode reward: [(0, '32.790'), (1, '41.550')] -[2023-10-12 03:38:01,074][78091] Updated weights for policy 0, policy_version 12900 (0.0009) -[2023-10-12 03:38:01,453][78091] Updated weights for policy 0, policy_version 12910 (0.0008) -[2023-10-12 03:38:01,831][78091] Updated weights for policy 0, policy_version 12920 (0.0008) -[2023-10-12 03:38:02,006][78123] Updated weights for policy 1, policy_version 12840 (0.0009) -[2023-10-12 03:38:02,378][78123] Updated weights for policy 1, policy_version 12850 (0.0010) -[2023-10-12 03:38:02,748][78123] Updated weights for policy 1, policy_version 12860 (0.0009) -[2023-10-12 03:38:05,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 26411008. Throughput: 0: 1591.3, 1: 1593.6. Samples: 6611712. Policy #0 lag: (min: 24.0, avg: 41.1, max: 56.0) -[2023-10-12 03:38:05,201][77203] Avg episode reward: [(0, '36.150'), (1, '44.650')] -[2023-10-12 03:38:05,202][77950] Saving new best policy, reward=44.650! -[2023-10-12 03:38:05,992][78091] Updated weights for policy 0, policy_version 12930 (0.0009) -[2023-10-12 03:38:06,351][78091] Updated weights for policy 0, policy_version 12940 (0.0011) -[2023-10-12 03:38:06,717][78091] Updated weights for policy 0, policy_version 12950 (0.0010) -[2023-10-12 03:38:07,082][78123] Updated weights for policy 1, policy_version 12870 (0.0008) -[2023-10-12 03:38:07,095][78091] Updated weights for policy 0, policy_version 12960 (0.0009) -[2023-10-12 03:38:07,454][78123] Updated weights for policy 1, policy_version 12880 (0.0008) -[2023-10-12 03:38:07,825][78123] Updated weights for policy 1, policy_version 12890 (0.0008) -[2023-10-12 03:38:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 26476544. Throughput: 0: 1591.8, 1: 1594.6. Samples: 6631216. Policy #0 lag: (min: 1.0, avg: 19.8, max: 33.0) -[2023-10-12 03:38:10,202][77203] Avg episode reward: [(0, '32.360'), (1, '39.570')] -[2023-10-12 03:38:11,549][78091] Updated weights for policy 0, policy_version 12970 (0.0008) -[2023-10-12 03:38:11,920][78091] Updated weights for policy 0, policy_version 12980 (0.0008) -[2023-10-12 03:38:12,029][78123] Updated weights for policy 1, policy_version 12900 (0.0008) -[2023-10-12 03:38:12,286][78091] Updated weights for policy 0, policy_version 12990 (0.0007) -[2023-10-12 03:38:12,392][78123] Updated weights for policy 1, policy_version 12910 (0.0008) -[2023-10-12 03:38:12,757][78123] Updated weights for policy 1, policy_version 12920 (0.0009) -[2023-10-12 03:38:15,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 26542080. Throughput: 0: 1593.5, 1: 1604.5. Samples: 6640256. Policy #0 lag: (min: 1.0, avg: 19.8, max: 33.0) -[2023-10-12 03:38:15,202][77203] Avg episode reward: [(0, '33.610'), (1, '43.950')] -[2023-10-12 03:38:16,570][78091] Updated weights for policy 0, policy_version 13000 (0.0010) -[2023-10-12 03:38:16,939][78091] Updated weights for policy 0, policy_version 13010 (0.0011) -[2023-10-12 03:38:17,312][78123] Updated weights for policy 1, policy_version 12930 (0.0007) -[2023-10-12 03:38:17,316][78091] Updated weights for policy 0, policy_version 13020 (0.0009) -[2023-10-12 03:38:17,686][78123] Updated weights for policy 1, policy_version 12940 (0.0007) -[2023-10-12 03:38:18,042][78123] Updated weights for policy 1, policy_version 12950 (0.0010) -[2023-10-12 03:38:18,407][78123] Updated weights for policy 1, policy_version 12960 (0.0009) -[2023-10-12 03:38:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 26607616. Throughput: 0: 1595.4, 1: 1589.9. Samples: 6659324. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:38:20,201][77203] Avg episode reward: [(0, '34.690'), (1, '41.360')] -[2023-10-12 03:38:21,650][78091] Updated weights for policy 0, policy_version 13030 (0.0008) -[2023-10-12 03:38:22,012][78091] Updated weights for policy 0, policy_version 13040 (0.0007) -[2023-10-12 03:38:22,392][78091] Updated weights for policy 0, policy_version 13050 (0.0008) -[2023-10-12 03:38:22,620][78123] Updated weights for policy 1, policy_version 12970 (0.0010) -[2023-10-12 03:38:22,993][78123] Updated weights for policy 1, policy_version 12980 (0.0010) -[2023-10-12 03:38:23,365][78123] Updated weights for policy 1, policy_version 12990 (0.0009) -[2023-10-12 03:38:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.1, 300 sec: 12662.9). Total num frames: 26673152. Throughput: 0: 1599.5, 1: 1586.3. Samples: 6678858. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:38:25,202][77203] Avg episode reward: [(0, '38.220'), (1, '39.460')] -[2023-10-12 03:38:25,212][77792] Saving new best policy, reward=38.220! -[2023-10-12 03:38:26,755][78091] Updated weights for policy 0, policy_version 13060 (0.0009) -[2023-10-12 03:38:27,120][78091] Updated weights for policy 0, policy_version 13070 (0.0010) -[2023-10-12 03:38:27,497][78091] Updated weights for policy 0, policy_version 13080 (0.0008) -[2023-10-12 03:38:27,670][78123] Updated weights for policy 1, policy_version 13000 (0.0008) -[2023-10-12 03:38:28,044][78123] Updated weights for policy 1, policy_version 13010 (0.0007) -[2023-10-12 03:38:28,407][78123] Updated weights for policy 1, policy_version 13020 (0.0007) -[2023-10-12 03:38:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 26738688. Throughput: 0: 1604.3, 1: 1608.2. Samples: 6688446. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:38:30,201][77203] Avg episode reward: [(0, '37.240'), (1, '40.460')] -[2023-10-12 03:38:31,792][78091] Updated weights for policy 0, policy_version 13090 (0.0008) -[2023-10-12 03:38:32,201][78091] Updated weights for policy 0, policy_version 13100 (0.0008) -[2023-10-12 03:38:32,563][78091] Updated weights for policy 0, policy_version 13110 (0.0010) -[2023-10-12 03:38:32,717][78123] Updated weights for policy 1, policy_version 13030 (0.0007) -[2023-10-12 03:38:32,939][78091] Updated weights for policy 0, policy_version 13120 (0.0007) -[2023-10-12 03:38:33,086][78123] Updated weights for policy 1, policy_version 13040 (0.0009) -[2023-10-12 03:38:33,451][78123] Updated weights for policy 1, policy_version 13050 (0.0010) -[2023-10-12 03:38:35,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 26804224. Throughput: 0: 1605.1, 1: 1587.8. Samples: 6707072. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:38:35,201][77203] Avg episode reward: [(0, '33.950'), (1, '34.680')] -[2023-10-12 03:38:36,900][78091] Updated weights for policy 0, policy_version 13130 (0.0009) -[2023-10-12 03:38:37,266][78091] Updated weights for policy 0, policy_version 13140 (0.0007) -[2023-10-12 03:38:37,632][78091] Updated weights for policy 0, policy_version 13150 (0.0008) -[2023-10-12 03:38:37,983][78123] Updated weights for policy 1, policy_version 13060 (0.0010) -[2023-10-12 03:38:38,382][78123] Updated weights for policy 1, policy_version 13070 (0.0010) -[2023-10-12 03:38:38,753][78123] Updated weights for policy 1, policy_version 13080 (0.0010) -[2023-10-12 03:38:40,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 12885.0). Total num frames: 26869760. Throughput: 0: 1606.7, 1: 1583.0. Samples: 6726752. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:38:40,202][77203] Avg episode reward: [(0, '35.200'), (1, '40.250')] -[2023-10-12 03:38:41,815][78091] Updated weights for policy 0, policy_version 13160 (0.0008) -[2023-10-12 03:38:42,180][78091] Updated weights for policy 0, policy_version 13170 (0.0008) -[2023-10-12 03:38:42,546][78091] Updated weights for policy 0, policy_version 13180 (0.0008) -[2023-10-12 03:38:43,177][78123] Updated weights for policy 1, policy_version 13090 (0.0009) -[2023-10-12 03:38:43,547][78123] Updated weights for policy 1, policy_version 13100 (0.0008) -[2023-10-12 03:38:43,908][78123] Updated weights for policy 1, policy_version 13110 (0.0009) -[2023-10-12 03:38:44,271][78123] Updated weights for policy 1, policy_version 13120 (0.0010) -[2023-10-12 03:38:45,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 26935296. Throughput: 0: 1610.0, 1: 1604.5. Samples: 6736532. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:38:45,202][77203] Avg episode reward: [(0, '34.930'), (1, '38.310')] -[2023-10-12 03:38:46,895][78091] Updated weights for policy 0, policy_version 13190 (0.0008) -[2023-10-12 03:38:47,271][78091] Updated weights for policy 0, policy_version 13200 (0.0009) -[2023-10-12 03:38:47,644][78091] Updated weights for policy 0, policy_version 13210 (0.0007) -[2023-10-12 03:38:48,543][78123] Updated weights for policy 1, policy_version 13130 (0.0008) -[2023-10-12 03:38:48,910][78123] Updated weights for policy 1, policy_version 13140 (0.0009) -[2023-10-12 03:38:49,288][78123] Updated weights for policy 1, policy_version 13150 (0.0010) -[2023-10-12 03:38:50,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 27000832. Throughput: 0: 1600.9, 1: 1594.7. Samples: 6755512. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-12 03:38:50,202][77203] Avg episode reward: [(0, '33.510'), (1, '41.460')] -[2023-10-12 03:38:51,950][78091] Updated weights for policy 0, policy_version 13220 (0.0011) -[2023-10-12 03:38:52,319][78091] Updated weights for policy 0, policy_version 13230 (0.0008) -[2023-10-12 03:38:52,684][78091] Updated weights for policy 0, policy_version 13240 (0.0010) -[2023-10-12 03:38:53,663][78123] Updated weights for policy 1, policy_version 13160 (0.0009) -[2023-10-12 03:38:54,026][78123] Updated weights for policy 1, policy_version 13170 (0.0011) -[2023-10-12 03:38:54,406][78123] Updated weights for policy 1, policy_version 13180 (0.0011) -[2023-10-12 03:38:55,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.1, 300 sec: 12885.0). Total num frames: 27066368. Throughput: 0: 1602.6, 1: 1583.4. Samples: 6774586. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-12 03:38:55,202][77203] Avg episode reward: [(0, '32.130'), (1, '43.160')] -[2023-10-12 03:38:56,919][78091] Updated weights for policy 0, policy_version 13250 (0.0010) -[2023-10-12 03:38:57,295][78091] Updated weights for policy 0, policy_version 13260 (0.0009) -[2023-10-12 03:38:57,661][78091] Updated weights for policy 0, policy_version 13270 (0.0010) -[2023-10-12 03:38:58,034][78091] Updated weights for policy 0, policy_version 13280 (0.0008) -[2023-10-12 03:38:58,361][78123] Updated weights for policy 1, policy_version 13190 (0.0009) -[2023-10-12 03:38:58,721][78123] Updated weights for policy 1, policy_version 13200 (0.0009) -[2023-10-12 03:38:59,095][78123] Updated weights for policy 1, policy_version 13210 (0.0008) -[2023-10-12 03:39:00,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 27131904. Throughput: 0: 1606.5, 1: 1600.9. Samples: 6784588. Policy #0 lag: (min: 8.0, avg: 31.3, max: 40.0) -[2023-10-12 03:39:00,201][77203] Avg episode reward: [(0, '35.910'), (1, '43.830')] -[2023-10-12 03:39:02,460][78091] Updated weights for policy 0, policy_version 13290 (0.0007) -[2023-10-12 03:39:02,833][78091] Updated weights for policy 0, policy_version 13300 (0.0007) -[2023-10-12 03:39:03,200][78091] Updated weights for policy 0, policy_version 13310 (0.0008) -[2023-10-12 03:39:03,317][78123] Updated weights for policy 1, policy_version 13220 (0.0008) -[2023-10-12 03:39:03,670][78123] Updated weights for policy 1, policy_version 13230 (0.0007) -[2023-10-12 03:39:04,036][78123] Updated weights for policy 1, policy_version 13240 (0.0007) -[2023-10-12 03:39:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 27197440. Throughput: 0: 1597.9, 1: 1602.2. Samples: 6803332. Policy #0 lag: (min: 8.0, avg: 31.3, max: 40.0) -[2023-10-12 03:39:05,202][77203] Avg episode reward: [(0, '34.400'), (1, '42.100')] -[2023-10-12 03:39:07,562][78091] Updated weights for policy 0, policy_version 13320 (0.0007) -[2023-10-12 03:39:07,931][78091] Updated weights for policy 0, policy_version 13330 (0.0010) -[2023-10-12 03:39:08,305][78091] Updated weights for policy 0, policy_version 13340 (0.0008) -[2023-10-12 03:39:08,460][78123] Updated weights for policy 1, policy_version 13250 (0.0007) -[2023-10-12 03:39:08,826][78123] Updated weights for policy 1, policy_version 13260 (0.0009) -[2023-10-12 03:39:09,201][78123] Updated weights for policy 1, policy_version 13270 (0.0008) -[2023-10-12 03:39:09,564][78123] Updated weights for policy 1, policy_version 13280 (0.0009) -[2023-10-12 03:39:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 27262976. Throughput: 0: 1598.1, 1: 1585.7. Samples: 6822128. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:39:10,201][77203] Avg episode reward: [(0, '35.960'), (1, '40.860')] -[2023-10-12 03:39:10,209][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000013344_13664256.pth... -[2023-10-12 03:39:10,209][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000013280_13598720.pth... -[2023-10-12 03:39:10,249][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000011776_12058624.pth -[2023-10-12 03:39:10,250][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000011840_12124160.pth -[2023-10-12 03:39:12,580][78091] Updated weights for policy 0, policy_version 13350 (0.0008) -[2023-10-12 03:39:12,956][78091] Updated weights for policy 0, policy_version 13360 (0.0010) -[2023-10-12 03:39:13,328][78091] Updated weights for policy 0, policy_version 13370 (0.0009) -[2023-10-12 03:39:13,939][78123] Updated weights for policy 1, policy_version 13290 (0.0010) -[2023-10-12 03:39:14,309][78123] Updated weights for policy 1, policy_version 13300 (0.0008) -[2023-10-12 03:39:14,679][78123] Updated weights for policy 1, policy_version 13310 (0.0007) -[2023-10-12 03:39:15,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 27328512. Throughput: 0: 1612.6, 1: 1591.3. Samples: 6832622. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:39:15,202][77203] Avg episode reward: [(0, '36.800'), (1, '39.620')] -[2023-10-12 03:39:17,630][78091] Updated weights for policy 0, policy_version 13380 (0.0010) -[2023-10-12 03:39:17,999][78091] Updated weights for policy 0, policy_version 13390 (0.0007) -[2023-10-12 03:39:18,381][78091] Updated weights for policy 0, policy_version 13400 (0.0009) -[2023-10-12 03:39:19,281][78123] Updated weights for policy 1, policy_version 13320 (0.0008) -[2023-10-12 03:39:19,660][78123] Updated weights for policy 1, policy_version 13330 (0.0011) -[2023-10-12 03:39:20,024][78123] Updated weights for policy 1, policy_version 13340 (0.0009) -[2023-10-12 03:39:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 27394048. Throughput: 0: 1597.8, 1: 1606.4. Samples: 6851264. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:39:20,201][77203] Avg episode reward: [(0, '36.460'), (1, '40.170')] -[2023-10-12 03:39:22,631][78091] Updated weights for policy 0, policy_version 13410 (0.0008) -[2023-10-12 03:39:23,034][78091] Updated weights for policy 0, policy_version 13420 (0.0008) -[2023-10-12 03:39:23,412][78091] Updated weights for policy 0, policy_version 13430 (0.0007) -[2023-10-12 03:39:23,781][78091] Updated weights for policy 0, policy_version 13440 (0.0007) -[2023-10-12 03:39:24,299][78123] Updated weights for policy 1, policy_version 13350 (0.0008) -[2023-10-12 03:39:24,676][78123] Updated weights for policy 1, policy_version 13360 (0.0010) -[2023-10-12 03:39:25,043][78123] Updated weights for policy 1, policy_version 13370 (0.0010) -[2023-10-12 03:39:25,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 27426816. Throughput: 0: 1591.5, 1: 1592.1. Samples: 6870016. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:39:25,202][77203] Avg episode reward: [(0, '36.470'), (1, '38.160')] -[2023-10-12 03:39:28,143][78091] Updated weights for policy 0, policy_version 13450 (0.0007) -[2023-10-12 03:39:28,515][78091] Updated weights for policy 0, policy_version 13460 (0.0010) -[2023-10-12 03:39:28,878][78091] Updated weights for policy 0, policy_version 13470 (0.0008) -[2023-10-12 03:39:29,430][78123] Updated weights for policy 1, policy_version 13380 (0.0009) -[2023-10-12 03:39:29,794][78123] Updated weights for policy 1, policy_version 13390 (0.0010) -[2023-10-12 03:39:30,163][78123] Updated weights for policy 1, policy_version 13400 (0.0009) -[2023-10-12 03:39:30,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 27492352. Throughput: 0: 1614.9, 1: 1581.8. Samples: 6880384. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:39:30,202][77203] Avg episode reward: [(0, '36.450'), (1, '38.620')] -[2023-10-12 03:39:33,108][78091] Updated weights for policy 0, policy_version 13480 (0.0010) -[2023-10-12 03:39:33,473][78091] Updated weights for policy 0, policy_version 13490 (0.0009) -[2023-10-12 03:39:33,847][78091] Updated weights for policy 0, policy_version 13500 (0.0008) -[2023-10-12 03:39:34,439][78123] Updated weights for policy 1, policy_version 13410 (0.0010) -[2023-10-12 03:39:34,804][78123] Updated weights for policy 1, policy_version 13420 (0.0008) -[2023-10-12 03:39:35,170][78123] Updated weights for policy 1, policy_version 13430 (0.0010) -[2023-10-12 03:39:35,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 27557888. Throughput: 0: 1596.5, 1: 1599.0. Samples: 6899310. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:39:35,201][77203] Avg episode reward: [(0, '35.870'), (1, '40.630')] -[2023-10-12 03:39:35,535][78123] Updated weights for policy 1, policy_version 13440 (0.0009) -[2023-10-12 03:39:38,194][78091] Updated weights for policy 0, policy_version 13510 (0.0007) -[2023-10-12 03:39:38,569][78091] Updated weights for policy 0, policy_version 13520 (0.0008) -[2023-10-12 03:39:38,947][78091] Updated weights for policy 0, policy_version 13530 (0.0010) -[2023-10-12 03:39:39,878][78123] Updated weights for policy 1, policy_version 13450 (0.0011) -[2023-10-12 03:39:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 27623424. Throughput: 0: 1588.0, 1: 1602.6. Samples: 6918160. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:39:40,202][77203] Avg episode reward: [(0, '35.880'), (1, '38.310')] -[2023-10-12 03:39:40,240][78123] Updated weights for policy 1, policy_version 13460 (0.0010) -[2023-10-12 03:39:40,612][78123] Updated weights for policy 1, policy_version 13470 (0.0010) -[2023-10-12 03:39:43,224][78091] Updated weights for policy 0, policy_version 13540 (0.0008) -[2023-10-12 03:39:43,595][78091] Updated weights for policy 0, policy_version 13550 (0.0008) -[2023-10-12 03:39:43,970][78091] Updated weights for policy 0, policy_version 13560 (0.0009) -[2023-10-12 03:39:45,147][78123] Updated weights for policy 1, policy_version 13480 (0.0008) -[2023-10-12 03:39:45,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 27688960. Throughput: 0: 1612.5, 1: 1576.5. Samples: 6928096. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:39:45,202][77203] Avg episode reward: [(0, '35.970'), (1, '41.670')] -[2023-10-12 03:39:45,522][78123] Updated weights for policy 1, policy_version 13490 (0.0007) -[2023-10-12 03:39:45,889][78123] Updated weights for policy 1, policy_version 13500 (0.0009) -[2023-10-12 03:39:48,249][78091] Updated weights for policy 0, policy_version 13570 (0.0008) -[2023-10-12 03:39:48,628][78091] Updated weights for policy 0, policy_version 13580 (0.0008) -[2023-10-12 03:39:48,991][78091] Updated weights for policy 0, policy_version 13590 (0.0009) -[2023-10-12 03:39:49,366][78091] Updated weights for policy 0, policy_version 13600 (0.0009) -[2023-10-12 03:39:50,198][78123] Updated weights for policy 1, policy_version 13510 (0.0008) -[2023-10-12 03:39:50,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 27754496. Throughput: 0: 1607.9, 1: 1583.3. Samples: 6946938. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:39:50,201][77203] Avg episode reward: [(0, '34.040'), (1, '39.040')] -[2023-10-12 03:39:50,566][78123] Updated weights for policy 1, policy_version 13520 (0.0007) -[2023-10-12 03:39:50,935][78123] Updated weights for policy 1, policy_version 13530 (0.0009) -[2023-10-12 03:39:53,564][78091] Updated weights for policy 0, policy_version 13610 (0.0008) -[2023-10-12 03:39:53,936][78091] Updated weights for policy 0, policy_version 13620 (0.0010) -[2023-10-12 03:39:54,308][78091] Updated weights for policy 0, policy_version 13630 (0.0009) -[2023-10-12 03:39:55,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 27820032. Throughput: 0: 1596.2, 1: 1600.7. Samples: 6965988. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-12 03:39:55,202][77203] Avg episode reward: [(0, '38.770'), (1, '41.560')] -[2023-10-12 03:39:55,212][77792] Saving new best policy, reward=38.770! -[2023-10-12 03:39:55,355][78123] Updated weights for policy 1, policy_version 13540 (0.0010) -[2023-10-12 03:39:55,718][78123] Updated weights for policy 1, policy_version 13550 (0.0009) -[2023-10-12 03:39:56,084][78123] Updated weights for policy 1, policy_version 13560 (0.0008) -[2023-10-12 03:39:58,612][78091] Updated weights for policy 0, policy_version 13640 (0.0008) -[2023-10-12 03:39:58,996][78091] Updated weights for policy 0, policy_version 13650 (0.0009) -[2023-10-12 03:39:59,370][78091] Updated weights for policy 0, policy_version 13660 (0.0008) -[2023-10-12 03:40:00,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 27885568. Throughput: 0: 1608.1, 1: 1572.3. Samples: 6975740. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-12 03:40:00,201][77203] Avg episode reward: [(0, '34.400'), (1, '37.780')] -[2023-10-12 03:40:00,401][78123] Updated weights for policy 1, policy_version 13570 (0.0008) -[2023-10-12 03:40:00,771][78123] Updated weights for policy 1, policy_version 13580 (0.0008) -[2023-10-12 03:40:01,146][78123] Updated weights for policy 1, policy_version 13590 (0.0010) -[2023-10-12 03:40:01,520][78123] Updated weights for policy 1, policy_version 13600 (0.0009) -[2023-10-12 03:40:03,564][78091] Updated weights for policy 0, policy_version 13670 (0.0009) -[2023-10-12 03:40:03,933][78091] Updated weights for policy 0, policy_version 13680 (0.0008) -[2023-10-12 03:40:04,310][78091] Updated weights for policy 0, policy_version 13690 (0.0010) -[2023-10-12 03:40:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 27951104. Throughput: 0: 1617.6, 1: 1577.1. Samples: 6995024. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-12 03:40:05,202][77203] Avg episode reward: [(0, '37.170'), (1, '36.080')] -[2023-10-12 03:40:05,861][78123] Updated weights for policy 1, policy_version 13610 (0.0009) -[2023-10-12 03:40:06,224][78123] Updated weights for policy 1, policy_version 13620 (0.0009) -[2023-10-12 03:40:06,586][78123] Updated weights for policy 1, policy_version 13630 (0.0007) -[2023-10-12 03:40:08,641][78091] Updated weights for policy 0, policy_version 13700 (0.0007) -[2023-10-12 03:40:09,028][78091] Updated weights for policy 0, policy_version 13710 (0.0010) -[2023-10-12 03:40:09,404][78091] Updated weights for policy 0, policy_version 13720 (0.0010) -[2023-10-12 03:40:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 28016640. Throughput: 0: 1597.9, 1: 1594.5. Samples: 7013674. Policy #0 lag: (min: 2.0, avg: 4.1, max: 34.0) -[2023-10-12 03:40:10,201][77203] Avg episode reward: [(0, '35.820'), (1, '41.000')] -[2023-10-12 03:40:11,076][78123] Updated weights for policy 1, policy_version 13640 (0.0010) -[2023-10-12 03:40:11,461][78123] Updated weights for policy 1, policy_version 13650 (0.0010) -[2023-10-12 03:40:11,830][78123] Updated weights for policy 1, policy_version 13660 (0.0010) -[2023-10-12 03:40:13,683][78091] Updated weights for policy 0, policy_version 13730 (0.0009) -[2023-10-12 03:40:14,046][78091] Updated weights for policy 0, policy_version 13740 (0.0008) -[2023-10-12 03:40:14,427][78091] Updated weights for policy 0, policy_version 13750 (0.0009) -[2023-10-12 03:40:14,802][78091] Updated weights for policy 0, policy_version 13760 (0.0009) -[2023-10-12 03:40:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 28082176. Throughput: 0: 1602.6, 1: 1577.0. Samples: 7023466. Policy #0 lag: (min: 2.0, avg: 4.1, max: 34.0) -[2023-10-12 03:40:15,202][77203] Avg episode reward: [(0, '38.860'), (1, '40.270')] -[2023-10-12 03:40:15,203][77792] Saving new best policy, reward=38.860! -[2023-10-12 03:40:15,955][78123] Updated weights for policy 1, policy_version 13670 (0.0009) -[2023-10-12 03:40:16,326][78123] Updated weights for policy 1, policy_version 13680 (0.0010) -[2023-10-12 03:40:16,692][78123] Updated weights for policy 1, policy_version 13690 (0.0007) -[2023-10-12 03:40:19,130][78091] Updated weights for policy 0, policy_version 13770 (0.0009) -[2023-10-12 03:40:19,499][78091] Updated weights for policy 0, policy_version 13780 (0.0008) -[2023-10-12 03:40:19,871][78091] Updated weights for policy 0, policy_version 13790 (0.0010) -[2023-10-12 03:40:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 28147712. Throughput: 0: 1623.7, 1: 1571.6. Samples: 7043098. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:40:20,201][77203] Avg episode reward: [(0, '32.970'), (1, '40.070')] -[2023-10-12 03:40:20,998][78123] Updated weights for policy 1, policy_version 13700 (0.0007) -[2023-10-12 03:40:21,372][78123] Updated weights for policy 1, policy_version 13710 (0.0008) -[2023-10-12 03:40:21,747][78123] Updated weights for policy 1, policy_version 13720 (0.0009) -[2023-10-12 03:40:24,155][78091] Updated weights for policy 0, policy_version 13800 (0.0008) -[2023-10-12 03:40:24,522][78091] Updated weights for policy 0, policy_version 13810 (0.0007) -[2023-10-12 03:40:24,898][78091] Updated weights for policy 0, policy_version 13820 (0.0007) -[2023-10-12 03:40:25,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 28213248. Throughput: 0: 1614.1, 1: 1577.8. Samples: 7061798. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:40:25,201][77203] Avg episode reward: [(0, '40.150'), (1, '40.230')] -[2023-10-12 03:40:25,208][77792] Saving new best policy, reward=40.150! -[2023-10-12 03:40:26,225][78123] Updated weights for policy 1, policy_version 13730 (0.0010) -[2023-10-12 03:40:26,595][78123] Updated weights for policy 1, policy_version 13740 (0.0008) -[2023-10-12 03:40:26,953][78123] Updated weights for policy 1, policy_version 13750 (0.0007) -[2023-10-12 03:40:27,315][78123] Updated weights for policy 1, policy_version 13760 (0.0007) -[2023-10-12 03:40:29,231][78091] Updated weights for policy 0, policy_version 13830 (0.0009) -[2023-10-12 03:40:29,610][78091] Updated weights for policy 0, policy_version 13840 (0.0010) -[2023-10-12 03:40:29,977][78091] Updated weights for policy 0, policy_version 13850 (0.0008) -[2023-10-12 03:40:30,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 28278784. Throughput: 0: 1604.1, 1: 1575.2. Samples: 7071168. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:40:30,201][77203] Avg episode reward: [(0, '35.540'), (1, '39.380')] -[2023-10-12 03:40:31,527][78123] Updated weights for policy 1, policy_version 13770 (0.0007) -[2023-10-12 03:40:31,896][78123] Updated weights for policy 1, policy_version 13780 (0.0007) -[2023-10-12 03:40:32,271][78123] Updated weights for policy 1, policy_version 13790 (0.0008) -[2023-10-12 03:40:34,197][78091] Updated weights for policy 0, policy_version 13860 (0.0010) -[2023-10-12 03:40:34,576][78091] Updated weights for policy 0, policy_version 13870 (0.0007) -[2023-10-12 03:40:34,947][78091] Updated weights for policy 0, policy_version 13880 (0.0007) -[2023-10-12 03:40:35,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 28311552. Throughput: 0: 1616.1, 1: 1578.9. Samples: 7090714. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:40:35,202][77203] Avg episode reward: [(0, '38.330'), (1, '39.110')] -[2023-10-12 03:40:36,681][78123] Updated weights for policy 1, policy_version 13800 (0.0008) -[2023-10-12 03:40:37,040][78123] Updated weights for policy 1, policy_version 13810 (0.0010) -[2023-10-12 03:40:37,415][78123] Updated weights for policy 1, policy_version 13820 (0.0009) -[2023-10-12 03:40:39,333][78091] Updated weights for policy 0, policy_version 13890 (0.0010) -[2023-10-12 03:40:39,708][78091] Updated weights for policy 0, policy_version 13900 (0.0008) -[2023-10-12 03:40:40,081][78091] Updated weights for policy 0, policy_version 13910 (0.0009) -[2023-10-12 03:40:40,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 28377088. Throughput: 0: 1615.8, 1: 1578.0. Samples: 7109706. Policy #0 lag: (min: 18.0, avg: 29.7, max: 50.0) -[2023-10-12 03:40:40,201][77203] Avg episode reward: [(0, '34.530'), (1, '42.220')] -[2023-10-12 03:40:40,441][78091] Updated weights for policy 0, policy_version 13920 (0.0009) -[2023-10-12 03:40:41,722][78123] Updated weights for policy 1, policy_version 13830 (0.0008) -[2023-10-12 03:40:42,100][78123] Updated weights for policy 1, policy_version 13840 (0.0007) -[2023-10-12 03:40:42,459][78123] Updated weights for policy 1, policy_version 13850 (0.0008) -[2023-10-12 03:40:44,824][78091] Updated weights for policy 0, policy_version 13930 (0.0010) -[2023-10-12 03:40:45,184][78091] Updated weights for policy 0, policy_version 13940 (0.0010) -[2023-10-12 03:40:45,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 28442624. Throughput: 0: 1599.7, 1: 1581.4. Samples: 7118888. Policy #0 lag: (min: 18.0, avg: 29.7, max: 50.0) -[2023-10-12 03:40:45,201][77203] Avg episode reward: [(0, '39.880'), (1, '35.020')] -[2023-10-12 03:40:45,552][78091] Updated weights for policy 0, policy_version 13950 (0.0010) -[2023-10-12 03:40:46,937][78123] Updated weights for policy 1, policy_version 13860 (0.0010) -[2023-10-12 03:40:47,302][78123] Updated weights for policy 1, policy_version 13870 (0.0010) -[2023-10-12 03:40:47,673][78123] Updated weights for policy 1, policy_version 13880 (0.0010) -[2023-10-12 03:40:49,867][78091] Updated weights for policy 0, policy_version 13960 (0.0009) -[2023-10-12 03:40:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 28508160. Throughput: 0: 1608.0, 1: 1576.0. Samples: 7138300. Policy #0 lag: (min: 18.0, avg: 29.7, max: 50.0) -[2023-10-12 03:40:50,201][77203] Avg episode reward: [(0, '35.080'), (1, '36.590')] -[2023-10-12 03:40:50,245][78091] Updated weights for policy 0, policy_version 13970 (0.0010) -[2023-10-12 03:40:50,624][78091] Updated weights for policy 0, policy_version 13980 (0.0010) -[2023-10-12 03:40:52,101][78123] Updated weights for policy 1, policy_version 13890 (0.0010) -[2023-10-12 03:40:52,455][78123] Updated weights for policy 1, policy_version 13900 (0.0007) -[2023-10-12 03:40:52,820][78123] Updated weights for policy 1, policy_version 13910 (0.0008) -[2023-10-12 03:40:53,184][78123] Updated weights for policy 1, policy_version 13920 (0.0009) -[2023-10-12 03:40:54,930][78091] Updated weights for policy 0, policy_version 13990 (0.0007) -[2023-10-12 03:40:55,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 28573696. Throughput: 0: 1625.4, 1: 1578.2. Samples: 7157836. Policy #0 lag: (min: 37.0, avg: 54.4, max: 56.0) -[2023-10-12 03:40:55,202][77203] Avg episode reward: [(0, '38.810'), (1, '39.290')] -[2023-10-12 03:40:55,318][78091] Updated weights for policy 0, policy_version 14000 (0.0009) -[2023-10-12 03:40:55,698][78091] Updated weights for policy 0, policy_version 14010 (0.0008) -[2023-10-12 03:40:57,675][78123] Updated weights for policy 1, policy_version 13930 (0.0011) -[2023-10-12 03:40:58,048][78123] Updated weights for policy 1, policy_version 13940 (0.0011) -[2023-10-12 03:40:58,422][78123] Updated weights for policy 1, policy_version 13950 (0.0010) -[2023-10-12 03:40:59,818][78091] Updated weights for policy 0, policy_version 14020 (0.0008) -[2023-10-12 03:41:00,187][78091] Updated weights for policy 0, policy_version 14030 (0.0010) -[2023-10-12 03:41:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 28639232. Throughput: 0: 1597.4, 1: 1594.2. Samples: 7167090. Policy #0 lag: (min: 37.0, avg: 54.4, max: 56.0) -[2023-10-12 03:41:00,201][77203] Avg episode reward: [(0, '35.580'), (1, '35.270')] -[2023-10-12 03:41:00,554][78091] Updated weights for policy 0, policy_version 14040 (0.0011) -[2023-10-12 03:41:02,826][78123] Updated weights for policy 1, policy_version 13960 (0.0008) -[2023-10-12 03:41:03,185][78123] Updated weights for policy 1, policy_version 13970 (0.0011) -[2023-10-12 03:41:03,552][78123] Updated weights for policy 1, policy_version 13980 (0.0007) -[2023-10-12 03:41:04,903][78091] Updated weights for policy 0, policy_version 14050 (0.0010) -[2023-10-12 03:41:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 28704768. Throughput: 0: 1597.3, 1: 1577.3. Samples: 7185954. Policy #0 lag: (min: 37.0, avg: 54.4, max: 56.0) -[2023-10-12 03:41:05,201][77203] Avg episode reward: [(0, '35.070'), (1, '42.310')] -[2023-10-12 03:41:05,278][78091] Updated weights for policy 0, policy_version 14060 (0.0008) -[2023-10-12 03:41:05,643][78091] Updated weights for policy 0, policy_version 14070 (0.0010) -[2023-10-12 03:41:06,022][78091] Updated weights for policy 0, policy_version 14080 (0.0008) -[2023-10-12 03:41:07,941][78123] Updated weights for policy 1, policy_version 13990 (0.0009) -[2023-10-12 03:41:08,309][78123] Updated weights for policy 1, policy_version 14000 (0.0011) -[2023-10-12 03:41:08,678][78123] Updated weights for policy 1, policy_version 14010 (0.0010) -[2023-10-12 03:41:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 28770304. Throughput: 0: 1613.4, 1: 1580.0. Samples: 7205500. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-12 03:41:10,201][77203] Avg episode reward: [(0, '36.600'), (1, '32.400')] -[2023-10-12 03:41:10,209][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000014016_14352384.pth... -[2023-10-12 03:41:10,243][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000012544_12845056.pth -[2023-10-12 03:41:10,278][78091] Updated weights for policy 0, policy_version 14090 (0.0009) -[2023-10-12 03:41:10,647][78091] Updated weights for policy 0, policy_version 14100 (0.0007) -[2023-10-12 03:41:11,015][78091] Updated weights for policy 0, policy_version 14110 (0.0007) -[2023-10-12 03:41:11,087][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000014112_14450688.pth... -[2023-10-12 03:41:11,117][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000012608_12910592.pth -[2023-10-12 03:41:12,576][78123] Updated weights for policy 1, policy_version 14020 (0.0010) -[2023-10-12 03:41:12,952][78123] Updated weights for policy 1, policy_version 14030 (0.0008) -[2023-10-12 03:41:13,319][78123] Updated weights for policy 1, policy_version 14040 (0.0010) -[2023-10-12 03:41:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 28835840. Throughput: 0: 1593.5, 1: 1604.7. Samples: 7215086. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-12 03:41:15,201][77203] Avg episode reward: [(0, '34.460'), (1, '36.240')] -[2023-10-12 03:41:15,266][78091] Updated weights for policy 0, policy_version 14120 (0.0009) -[2023-10-12 03:41:15,633][78091] Updated weights for policy 0, policy_version 14130 (0.0007) -[2023-10-12 03:41:15,998][78091] Updated weights for policy 0, policy_version 14140 (0.0008) -[2023-10-12 03:41:17,697][78123] Updated weights for policy 1, policy_version 14050 (0.0009) -[2023-10-12 03:41:18,069][78123] Updated weights for policy 1, policy_version 14060 (0.0007) -[2023-10-12 03:41:18,436][78123] Updated weights for policy 1, policy_version 14070 (0.0007) -[2023-10-12 03:41:18,805][78123] Updated weights for policy 1, policy_version 14080 (0.0008) -[2023-10-12 03:41:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 28901376. Throughput: 0: 1593.2, 1: 1589.3. Samples: 7233928. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-12 03:41:20,201][77203] Avg episode reward: [(0, '34.880'), (1, '38.260')] -[2023-10-12 03:41:20,503][78091] Updated weights for policy 0, policy_version 14150 (0.0008) -[2023-10-12 03:41:20,873][78091] Updated weights for policy 0, policy_version 14160 (0.0008) -[2023-10-12 03:41:21,237][78091] Updated weights for policy 0, policy_version 14170 (0.0008) -[2023-10-12 03:41:23,079][78123] Updated weights for policy 1, policy_version 14090 (0.0009) -[2023-10-12 03:41:23,444][78123] Updated weights for policy 1, policy_version 14100 (0.0010) -[2023-10-12 03:41:23,800][78123] Updated weights for policy 1, policy_version 14110 (0.0010) -[2023-10-12 03:41:25,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 28966912. Throughput: 0: 1603.7, 1: 1588.0. Samples: 7253334. Policy #0 lag: (min: 30.0, avg: 37.0, max: 62.0) -[2023-10-12 03:41:25,202][77203] Avg episode reward: [(0, '37.410'), (1, '34.830')] -[2023-10-12 03:41:25,596][78091] Updated weights for policy 0, policy_version 14180 (0.0008) -[2023-10-12 03:41:25,966][78091] Updated weights for policy 0, policy_version 14190 (0.0008) -[2023-10-12 03:41:26,334][78091] Updated weights for policy 0, policy_version 14200 (0.0007) -[2023-10-12 03:41:28,360][78123] Updated weights for policy 1, policy_version 14120 (0.0008) -[2023-10-12 03:41:28,725][78123] Updated weights for policy 1, policy_version 14130 (0.0008) -[2023-10-12 03:41:29,086][78123] Updated weights for policy 1, policy_version 14140 (0.0007) -[2023-10-12 03:41:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 29032448. Throughput: 0: 1593.5, 1: 1612.8. Samples: 7263172. Policy #0 lag: (min: 30.0, avg: 37.0, max: 62.0) -[2023-10-12 03:41:30,202][77203] Avg episode reward: [(0, '36.030'), (1, '45.270')] -[2023-10-12 03:41:30,202][77950] Saving new best policy, reward=45.270! -[2023-10-12 03:41:30,626][78091] Updated weights for policy 0, policy_version 14210 (0.0008) -[2023-10-12 03:41:31,001][78091] Updated weights for policy 0, policy_version 14220 (0.0009) -[2023-10-12 03:41:31,368][78091] Updated weights for policy 0, policy_version 14230 (0.0007) -[2023-10-12 03:41:31,738][78091] Updated weights for policy 0, policy_version 14240 (0.0007) -[2023-10-12 03:41:33,287][78123] Updated weights for policy 1, policy_version 14150 (0.0008) -[2023-10-12 03:41:33,653][78123] Updated weights for policy 1, policy_version 14160 (0.0008) -[2023-10-12 03:41:34,027][78123] Updated weights for policy 1, policy_version 14170 (0.0009) -[2023-10-12 03:41:35,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 29097984. Throughput: 0: 1594.2, 1: 1605.7. Samples: 7282298. Policy #0 lag: (min: 30.0, avg: 37.0, max: 62.0) -[2023-10-12 03:41:35,201][77203] Avg episode reward: [(0, '35.850'), (1, '37.140')] -[2023-10-12 03:41:35,980][78091] Updated weights for policy 0, policy_version 14250 (0.0009) -[2023-10-12 03:41:36,349][78091] Updated weights for policy 0, policy_version 14260 (0.0009) -[2023-10-12 03:41:36,718][78091] Updated weights for policy 0, policy_version 14270 (0.0011) -[2023-10-12 03:41:38,257][78123] Updated weights for policy 1, policy_version 14180 (0.0008) -[2023-10-12 03:41:38,631][78123] Updated weights for policy 1, policy_version 14190 (0.0007) -[2023-10-12 03:41:38,994][78123] Updated weights for policy 1, policy_version 14200 (0.0010) -[2023-10-12 03:41:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 29163520. Throughput: 0: 1598.7, 1: 1597.0. Samples: 7301642. Policy #0 lag: (min: 31.0, avg: 42.9, max: 63.0) -[2023-10-12 03:41:40,201][77203] Avg episode reward: [(0, '37.690'), (1, '35.660')] -[2023-10-12 03:41:41,070][78091] Updated weights for policy 0, policy_version 14280 (0.0009) -[2023-10-12 03:41:41,451][78091] Updated weights for policy 0, policy_version 14290 (0.0007) -[2023-10-12 03:41:41,818][78091] Updated weights for policy 0, policy_version 14300 (0.0008) -[2023-10-12 03:41:43,324][78123] Updated weights for policy 1, policy_version 14210 (0.0009) -[2023-10-12 03:41:43,732][78123] Updated weights for policy 1, policy_version 14220 (0.0007) -[2023-10-12 03:41:44,097][78123] Updated weights for policy 1, policy_version 14230 (0.0009) -[2023-10-12 03:41:44,464][78123] Updated weights for policy 1, policy_version 14240 (0.0011) -[2023-10-12 03:41:45,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 29229056. Throughput: 0: 1595.1, 1: 1609.9. Samples: 7311314. Policy #0 lag: (min: 31.0, avg: 42.9, max: 63.0) -[2023-10-12 03:41:45,202][77203] Avg episode reward: [(0, '35.040'), (1, '41.720')] -[2023-10-12 03:41:46,085][78091] Updated weights for policy 0, policy_version 14310 (0.0008) -[2023-10-12 03:41:46,463][78091] Updated weights for policy 0, policy_version 14320 (0.0008) -[2023-10-12 03:41:46,838][78091] Updated weights for policy 0, policy_version 14330 (0.0008) -[2023-10-12 03:41:48,847][78123] Updated weights for policy 1, policy_version 14250 (0.0007) -[2023-10-12 03:41:49,210][78123] Updated weights for policy 1, policy_version 14260 (0.0008) -[2023-10-12 03:41:49,583][78123] Updated weights for policy 1, policy_version 14270 (0.0010) -[2023-10-12 03:41:50,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 29294592. Throughput: 0: 1593.1, 1: 1617.7. Samples: 7330440. Policy #0 lag: (min: 31.0, avg: 42.9, max: 63.0) -[2023-10-12 03:41:50,202][77203] Avg episode reward: [(0, '36.060'), (1, '38.340')] -[2023-10-12 03:41:51,088][78091] Updated weights for policy 0, policy_version 14340 (0.0007) -[2023-10-12 03:41:51,452][78091] Updated weights for policy 0, policy_version 14350 (0.0009) -[2023-10-12 03:41:51,836][78091] Updated weights for policy 0, policy_version 14360 (0.0008) -[2023-10-12 03:41:53,661][78123] Updated weights for policy 1, policy_version 14280 (0.0009) -[2023-10-12 03:41:54,033][78123] Updated weights for policy 1, policy_version 14290 (0.0008) -[2023-10-12 03:41:54,390][78123] Updated weights for policy 1, policy_version 14300 (0.0009) -[2023-10-12 03:41:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 29360128. Throughput: 0: 1598.2, 1: 1597.6. Samples: 7349312. Policy #0 lag: (min: 27.0, avg: 29.3, max: 59.0) -[2023-10-12 03:41:55,202][77203] Avg episode reward: [(0, '36.220'), (1, '39.540')] -[2023-10-12 03:41:56,010][78091] Updated weights for policy 0, policy_version 14370 (0.0009) -[2023-10-12 03:41:56,384][78091] Updated weights for policy 0, policy_version 14380 (0.0008) -[2023-10-12 03:41:56,762][78091] Updated weights for policy 0, policy_version 14390 (0.0008) -[2023-10-12 03:41:57,127][78091] Updated weights for policy 0, policy_version 14400 (0.0007) -[2023-10-12 03:41:58,657][78123] Updated weights for policy 1, policy_version 14310 (0.0010) -[2023-10-12 03:41:59,020][78123] Updated weights for policy 1, policy_version 14320 (0.0009) -[2023-10-12 03:41:59,387][78123] Updated weights for policy 1, policy_version 14330 (0.0008) -[2023-10-12 03:42:00,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 29425664. Throughput: 0: 1598.4, 1: 1598.6. Samples: 7358950. Policy #0 lag: (min: 27.0, avg: 29.3, max: 59.0) -[2023-10-12 03:42:00,201][77203] Avg episode reward: [(0, '36.580'), (1, '38.110')] -[2023-10-12 03:42:01,312][78091] Updated weights for policy 0, policy_version 14410 (0.0009) -[2023-10-12 03:42:01,683][78091] Updated weights for policy 0, policy_version 14420 (0.0010) -[2023-10-12 03:42:02,052][78091] Updated weights for policy 0, policy_version 14430 (0.0010) -[2023-10-12 03:42:03,925][78123] Updated weights for policy 1, policy_version 14340 (0.0008) -[2023-10-12 03:42:04,285][78123] Updated weights for policy 1, policy_version 14350 (0.0008) -[2023-10-12 03:42:04,656][78123] Updated weights for policy 1, policy_version 14360 (0.0007) -[2023-10-12 03:42:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 29491200. Throughput: 0: 1599.6, 1: 1610.9. Samples: 7378402. Policy #0 lag: (min: 27.0, avg: 29.3, max: 59.0) -[2023-10-12 03:42:05,202][77203] Avg episode reward: [(0, '32.870'), (1, '34.560')] -[2023-10-12 03:42:06,550][78091] Updated weights for policy 0, policy_version 14440 (0.0010) -[2023-10-12 03:42:06,923][78091] Updated weights for policy 0, policy_version 14450 (0.0010) -[2023-10-12 03:42:07,301][78091] Updated weights for policy 0, policy_version 14460 (0.0011) -[2023-10-12 03:42:09,040][78123] Updated weights for policy 1, policy_version 14370 (0.0010) -[2023-10-12 03:42:09,397][78123] Updated weights for policy 1, policy_version 14380 (0.0010) -[2023-10-12 03:42:09,778][78123] Updated weights for policy 1, policy_version 14390 (0.0010) -[2023-10-12 03:42:10,143][78123] Updated weights for policy 1, policy_version 14400 (0.0011) -[2023-10-12 03:42:10,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 29556736. Throughput: 0: 1602.9, 1: 1601.4. Samples: 7397530. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-10-12 03:42:10,202][77203] Avg episode reward: [(0, '36.900'), (1, '39.200')] -[2023-10-12 03:42:11,571][78091] Updated weights for policy 0, policy_version 14470 (0.0008) -[2023-10-12 03:42:11,949][78091] Updated weights for policy 0, policy_version 14480 (0.0009) -[2023-10-12 03:42:12,311][78091] Updated weights for policy 0, policy_version 14490 (0.0010) -[2023-10-12 03:42:14,479][78123] Updated weights for policy 1, policy_version 14410 (0.0007) -[2023-10-12 03:42:14,857][78123] Updated weights for policy 1, policy_version 14420 (0.0008) -[2023-10-12 03:42:15,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 29589504. Throughput: 0: 1599.6, 1: 1594.4. Samples: 7406904. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-10-12 03:42:15,201][77203] Avg episode reward: [(0, '35.790'), (1, '39.700')] -[2023-10-12 03:42:15,217][78123] Updated weights for policy 1, policy_version 14430 (0.0008) -[2023-10-12 03:42:16,706][78091] Updated weights for policy 0, policy_version 14500 (0.0008) -[2023-10-12 03:42:17,073][78091] Updated weights for policy 0, policy_version 14510 (0.0008) -[2023-10-12 03:42:17,446][78091] Updated weights for policy 0, policy_version 14520 (0.0008) -[2023-10-12 03:42:19,378][78123] Updated weights for policy 1, policy_version 14440 (0.0007) -[2023-10-12 03:42:19,751][78123] Updated weights for policy 1, policy_version 14450 (0.0008) -[2023-10-12 03:42:20,109][78123] Updated weights for policy 1, policy_version 14460 (0.0009) -[2023-10-12 03:42:20,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 29655040. Throughput: 0: 1597.5, 1: 1608.3. Samples: 7426562. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-10-12 03:42:20,202][77203] Avg episode reward: [(0, '36.800'), (1, '40.370')] -[2023-10-12 03:42:21,728][78091] Updated weights for policy 0, policy_version 14530 (0.0009) -[2023-10-12 03:42:22,093][78091] Updated weights for policy 0, policy_version 14540 (0.0007) -[2023-10-12 03:42:22,457][78091] Updated weights for policy 0, policy_version 14550 (0.0008) -[2023-10-12 03:42:22,834][78091] Updated weights for policy 0, policy_version 14560 (0.0008) -[2023-10-12 03:42:24,274][78123] Updated weights for policy 1, policy_version 14470 (0.0008) -[2023-10-12 03:42:24,642][78123] Updated weights for policy 1, policy_version 14480 (0.0007) -[2023-10-12 03:42:25,018][78123] Updated weights for policy 1, policy_version 14490 (0.0007) -[2023-10-12 03:42:25,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 29720576. Throughput: 0: 1597.4, 1: 1602.8. Samples: 7445652. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:42:25,202][77203] Avg episode reward: [(0, '35.320'), (1, '39.130')] -[2023-10-12 03:42:27,185][78091] Updated weights for policy 0, policy_version 14570 (0.0010) -[2023-10-12 03:42:27,563][78091] Updated weights for policy 0, policy_version 14580 (0.0009) -[2023-10-12 03:42:27,933][78091] Updated weights for policy 0, policy_version 14590 (0.0009) -[2023-10-12 03:42:29,396][78123] Updated weights for policy 1, policy_version 14500 (0.0009) -[2023-10-12 03:42:29,781][78123] Updated weights for policy 1, policy_version 14510 (0.0007) -[2023-10-12 03:42:30,154][78123] Updated weights for policy 1, policy_version 14520 (0.0007) -[2023-10-12 03:42:30,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 29786112. Throughput: 0: 1601.2, 1: 1590.6. Samples: 7454946. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:42:30,202][77203] Avg episode reward: [(0, '35.420'), (1, '36.940')] -[2023-10-12 03:42:32,150][78091] Updated weights for policy 0, policy_version 14600 (0.0008) -[2023-10-12 03:42:32,515][78091] Updated weights for policy 0, policy_version 14610 (0.0010) -[2023-10-12 03:42:32,890][78091] Updated weights for policy 0, policy_version 14620 (0.0011) -[2023-10-12 03:42:34,549][78123] Updated weights for policy 1, policy_version 14530 (0.0008) -[2023-10-12 03:42:34,921][78123] Updated weights for policy 1, policy_version 14540 (0.0009) -[2023-10-12 03:42:35,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 29851648. Throughput: 0: 1599.3, 1: 1598.5. Samples: 7474336. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:42:35,201][77203] Avg episode reward: [(0, '36.310'), (1, '34.730')] -[2023-10-12 03:42:35,290][78123] Updated weights for policy 1, policy_version 14550 (0.0007) -[2023-10-12 03:42:35,666][78123] Updated weights for policy 1, policy_version 14560 (0.0008) -[2023-10-12 03:42:37,068][78091] Updated weights for policy 0, policy_version 14630 (0.0008) -[2023-10-12 03:42:37,436][78091] Updated weights for policy 0, policy_version 14640 (0.0008) -[2023-10-12 03:42:37,806][78091] Updated weights for policy 0, policy_version 14650 (0.0007) -[2023-10-12 03:42:39,944][78123] Updated weights for policy 1, policy_version 14570 (0.0007) -[2023-10-12 03:42:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 29917184. Throughput: 0: 1595.1, 1: 1612.5. Samples: 7493654. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-12 03:42:40,201][77203] Avg episode reward: [(0, '36.290'), (1, '35.730')] -[2023-10-12 03:42:40,305][78123] Updated weights for policy 1, policy_version 14580 (0.0010) -[2023-10-12 03:42:40,675][78123] Updated weights for policy 1, policy_version 14590 (0.0007) -[2023-10-12 03:42:41,902][78091] Updated weights for policy 0, policy_version 14660 (0.0007) -[2023-10-12 03:42:42,264][78091] Updated weights for policy 0, policy_version 14670 (0.0008) -[2023-10-12 03:42:42,645][78091] Updated weights for policy 0, policy_version 14680 (0.0007) -[2023-10-12 03:42:45,062][78123] Updated weights for policy 1, policy_version 14600 (0.0007) -[2023-10-12 03:42:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 29982720. Throughput: 0: 1601.9, 1: 1591.9. Samples: 7502668. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-12 03:42:45,201][77203] Avg episode reward: [(0, '33.800'), (1, '37.360')] -[2023-10-12 03:42:45,449][78123] Updated weights for policy 1, policy_version 14610 (0.0008) -[2023-10-12 03:42:45,813][78123] Updated weights for policy 1, policy_version 14620 (0.0008) -[2023-10-12 03:42:47,215][78091] Updated weights for policy 0, policy_version 14690 (0.0009) -[2023-10-12 03:42:47,579][78091] Updated weights for policy 0, policy_version 14700 (0.0009) -[2023-10-12 03:42:47,965][78091] Updated weights for policy 0, policy_version 14710 (0.0009) -[2023-10-12 03:42:48,328][78091] Updated weights for policy 0, policy_version 14720 (0.0008) -[2023-10-12 03:42:50,192][78123] Updated weights for policy 1, policy_version 14630 (0.0008) -[2023-10-12 03:42:50,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 30048256. Throughput: 0: 1592.5, 1: 1592.8. Samples: 7521740. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-12 03:42:50,202][77203] Avg episode reward: [(0, '35.970'), (1, '37.710')] -[2023-10-12 03:42:50,552][78123] Updated weights for policy 1, policy_version 14640 (0.0009) -[2023-10-12 03:42:50,921][78123] Updated weights for policy 1, policy_version 14650 (0.0008) -[2023-10-12 03:42:52,548][78091] Updated weights for policy 0, policy_version 14730 (0.0009) -[2023-10-12 03:42:52,908][78091] Updated weights for policy 0, policy_version 14740 (0.0009) -[2023-10-12 03:42:53,280][78091] Updated weights for policy 0, policy_version 14750 (0.0009) -[2023-10-12 03:42:55,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 30113792. Throughput: 0: 1588.0, 1: 1605.5. Samples: 7541238. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-12 03:42:55,202][77203] Avg episode reward: [(0, '36.680'), (1, '38.060')] -[2023-10-12 03:42:55,222][78123] Updated weights for policy 1, policy_version 14660 (0.0009) -[2023-10-12 03:42:55,594][78123] Updated weights for policy 1, policy_version 14670 (0.0009) -[2023-10-12 03:42:55,963][78123] Updated weights for policy 1, policy_version 14680 (0.0010) -[2023-10-12 03:42:57,693][78091] Updated weights for policy 0, policy_version 14760 (0.0007) -[2023-10-12 03:42:58,057][78091] Updated weights for policy 0, policy_version 14770 (0.0007) -[2023-10-12 03:42:58,436][78091] Updated weights for policy 0, policy_version 14780 (0.0007) -[2023-10-12 03:43:00,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 30179328. Throughput: 0: 1611.2, 1: 1586.9. Samples: 7550820. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-12 03:43:00,201][77203] Avg episode reward: [(0, '35.580'), (1, '35.680')] -[2023-10-12 03:43:00,416][78123] Updated weights for policy 1, policy_version 14690 (0.0009) -[2023-10-12 03:43:00,782][78123] Updated weights for policy 1, policy_version 14700 (0.0007) -[2023-10-12 03:43:01,157][78123] Updated weights for policy 1, policy_version 14710 (0.0008) -[2023-10-12 03:43:01,513][78123] Updated weights for policy 1, policy_version 14720 (0.0008) -[2023-10-12 03:43:02,815][78091] Updated weights for policy 0, policy_version 14790 (0.0010) -[2023-10-12 03:43:03,178][78091] Updated weights for policy 0, policy_version 14800 (0.0008) -[2023-10-12 03:43:03,546][78091] Updated weights for policy 0, policy_version 14810 (0.0009) -[2023-10-12 03:43:05,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 30244864. Throughput: 0: 1595.1, 1: 1583.2. Samples: 7569584. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-12 03:43:05,201][77203] Avg episode reward: [(0, '33.530'), (1, '34.970')] -[2023-10-12 03:43:05,739][78123] Updated weights for policy 1, policy_version 14730 (0.0008) -[2023-10-12 03:43:06,110][78123] Updated weights for policy 1, policy_version 14740 (0.0008) -[2023-10-12 03:43:06,474][78123] Updated weights for policy 1, policy_version 14750 (0.0009) -[2023-10-12 03:43:07,937][78091] Updated weights for policy 0, policy_version 14820 (0.0009) -[2023-10-12 03:43:08,297][78091] Updated weights for policy 0, policy_version 14830 (0.0007) -[2023-10-12 03:43:08,666][78091] Updated weights for policy 0, policy_version 14840 (0.0008) -[2023-10-12 03:43:10,201][77203] Fps is (10 sec: 13106.8, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 30310400. Throughput: 0: 1590.2, 1: 1593.6. Samples: 7588922. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) -[2023-10-12 03:43:10,202][77203] Avg episode reward: [(0, '34.610'), (1, '40.240')] -[2023-10-12 03:43:10,214][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000014848_15204352.pth... -[2023-10-12 03:43:10,214][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000014752_15106048.pth... -[2023-10-12 03:43:10,252][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000013280_13598720.pth -[2023-10-12 03:43:10,255][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000013344_13664256.pth -[2023-10-12 03:43:10,256][77950] Saving a milestone ./train_atari/atari_hero_APPO/checkpoint_p1/milestones/checkpoint_000014752_15106048.pth -[2023-10-12 03:43:10,259][77792] Saving a milestone ./train_atari/atari_hero_APPO/checkpoint_p0/milestones/checkpoint_000014848_15204352.pth -[2023-10-12 03:43:10,786][78123] Updated weights for policy 1, policy_version 14760 (0.0011) -[2023-10-12 03:43:11,168][78123] Updated weights for policy 1, policy_version 14770 (0.0009) -[2023-10-12 03:43:11,542][78123] Updated weights for policy 1, policy_version 14780 (0.0008) -[2023-10-12 03:43:13,114][78091] Updated weights for policy 0, policy_version 14850 (0.0009) -[2023-10-12 03:43:13,514][78091] Updated weights for policy 0, policy_version 14860 (0.0008) -[2023-10-12 03:43:13,886][78091] Updated weights for policy 0, policy_version 14870 (0.0009) -[2023-10-12 03:43:14,254][78091] Updated weights for policy 0, policy_version 14880 (0.0010) -[2023-10-12 03:43:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 30375936. Throughput: 0: 1615.7, 1: 1579.6. Samples: 7598734. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) -[2023-10-12 03:43:15,202][77203] Avg episode reward: [(0, '35.770'), (1, '39.550')] -[2023-10-12 03:43:15,838][78123] Updated weights for policy 1, policy_version 14790 (0.0009) -[2023-10-12 03:43:16,199][78123] Updated weights for policy 1, policy_version 14800 (0.0007) -[2023-10-12 03:43:16,569][78123] Updated weights for policy 1, policy_version 14810 (0.0007) -[2023-10-12 03:43:18,396][78091] Updated weights for policy 0, policy_version 14890 (0.0009) -[2023-10-12 03:43:18,774][78091] Updated weights for policy 0, policy_version 14900 (0.0008) -[2023-10-12 03:43:19,148][78091] Updated weights for policy 0, policy_version 14910 (0.0008) -[2023-10-12 03:43:20,201][77203] Fps is (10 sec: 13107.7, 60 sec: 13107.3, 300 sec: 12774.0). Total num frames: 30441472. Throughput: 0: 1601.2, 1: 1583.3. Samples: 7617636. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) -[2023-10-12 03:43:20,201][77203] Avg episode reward: [(0, '34.280'), (1, '34.470')] -[2023-10-12 03:43:20,904][78123] Updated weights for policy 1, policy_version 14820 (0.0008) -[2023-10-12 03:43:21,269][78123] Updated weights for policy 1, policy_version 14830 (0.0008) -[2023-10-12 03:43:21,643][78123] Updated weights for policy 1, policy_version 14840 (0.0010) -[2023-10-12 03:43:23,446][78091] Updated weights for policy 0, policy_version 14920 (0.0008) -[2023-10-12 03:43:23,820][78091] Updated weights for policy 0, policy_version 14930 (0.0007) -[2023-10-12 03:43:24,189][78091] Updated weights for policy 0, policy_version 14940 (0.0009) -[2023-10-12 03:43:25,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 30507008. Throughput: 0: 1595.1, 1: 1587.9. Samples: 7636886. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-12 03:43:25,202][77203] Avg episode reward: [(0, '34.170'), (1, '40.840')] -[2023-10-12 03:43:26,114][78123] Updated weights for policy 1, policy_version 14850 (0.0009) -[2023-10-12 03:43:26,490][78123] Updated weights for policy 1, policy_version 14860 (0.0008) -[2023-10-12 03:43:26,863][78123] Updated weights for policy 1, policy_version 14870 (0.0009) -[2023-10-12 03:43:27,228][78123] Updated weights for policy 1, policy_version 14880 (0.0010) -[2023-10-12 03:43:28,436][78091] Updated weights for policy 0, policy_version 14950 (0.0009) -[2023-10-12 03:43:28,807][78091] Updated weights for policy 0, policy_version 14960 (0.0010) -[2023-10-12 03:43:29,183][78091] Updated weights for policy 0, policy_version 14970 (0.0009) -[2023-10-12 03:43:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 30572544. Throughput: 0: 1616.5, 1: 1582.4. Samples: 7646616. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-12 03:43:30,201][77203] Avg episode reward: [(0, '34.540'), (1, '32.690')] -[2023-10-12 03:43:31,535][78123] Updated weights for policy 1, policy_version 14890 (0.0008) -[2023-10-12 03:43:31,899][78123] Updated weights for policy 1, policy_version 14900 (0.0008) -[2023-10-12 03:43:32,278][78123] Updated weights for policy 1, policy_version 14910 (0.0009) -[2023-10-12 03:43:33,594][78091] Updated weights for policy 0, policy_version 14980 (0.0010) -[2023-10-12 03:43:33,966][78091] Updated weights for policy 0, policy_version 14990 (0.0008) -[2023-10-12 03:43:34,330][78091] Updated weights for policy 0, policy_version 15000 (0.0010) -[2023-10-12 03:43:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 30638080. Throughput: 0: 1616.1, 1: 1586.0. Samples: 7665838. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-12 03:43:35,202][77203] Avg episode reward: [(0, '37.400'), (1, '39.380')] -[2023-10-12 03:43:36,597][78123] Updated weights for policy 1, policy_version 14920 (0.0009) -[2023-10-12 03:43:36,965][78123] Updated weights for policy 1, policy_version 14930 (0.0010) -[2023-10-12 03:43:37,335][78123] Updated weights for policy 1, policy_version 14940 (0.0007) -[2023-10-12 03:43:38,528][78091] Updated weights for policy 0, policy_version 15010 (0.0010) -[2023-10-12 03:43:38,897][78091] Updated weights for policy 0, policy_version 15020 (0.0009) -[2023-10-12 03:43:39,272][78091] Updated weights for policy 0, policy_version 15030 (0.0009) -[2023-10-12 03:43:39,650][78091] Updated weights for policy 0, policy_version 15040 (0.0009) -[2023-10-12 03:43:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 30703616. Throughput: 0: 1595.8, 1: 1586.8. Samples: 7684454. Policy #0 lag: (min: 31.0, avg: 42.0, max: 63.0) -[2023-10-12 03:43:40,201][77203] Avg episode reward: [(0, '36.670'), (1, '37.890')] -[2023-10-12 03:43:41,682][78123] Updated weights for policy 1, policy_version 14950 (0.0010) -[2023-10-12 03:43:42,037][78123] Updated weights for policy 1, policy_version 14960 (0.0010) -[2023-10-12 03:43:42,406][78123] Updated weights for policy 1, policy_version 14970 (0.0010) -[2023-10-12 03:43:43,987][78091] Updated weights for policy 0, policy_version 15050 (0.0010) -[2023-10-12 03:43:44,359][78091] Updated weights for policy 0, policy_version 15060 (0.0007) -[2023-10-12 03:43:44,729][78091] Updated weights for policy 0, policy_version 15070 (0.0007) -[2023-10-12 03:43:45,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 30769152. Throughput: 0: 1597.1, 1: 1587.0. Samples: 7694104. Policy #0 lag: (min: 31.0, avg: 42.0, max: 63.0) -[2023-10-12 03:43:45,202][77203] Avg episode reward: [(0, '35.980'), (1, '33.520')] -[2023-10-12 03:43:46,840][78123] Updated weights for policy 1, policy_version 14980 (0.0007) -[2023-10-12 03:43:47,190][78123] Updated weights for policy 1, policy_version 14990 (0.0007) -[2023-10-12 03:43:47,554][78123] Updated weights for policy 1, policy_version 15000 (0.0008) -[2023-10-12 03:43:49,054][78091] Updated weights for policy 0, policy_version 15080 (0.0009) -[2023-10-12 03:43:49,427][78091] Updated weights for policy 0, policy_version 15090 (0.0008) -[2023-10-12 03:43:49,790][78091] Updated weights for policy 0, policy_version 15100 (0.0009) -[2023-10-12 03:43:50,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 30834688. Throughput: 0: 1613.4, 1: 1588.8. Samples: 7713682. Policy #0 lag: (min: 31.0, avg: 42.0, max: 63.0) -[2023-10-12 03:43:50,201][77203] Avg episode reward: [(0, '33.030'), (1, '41.090')] -[2023-10-12 03:43:51,888][78123] Updated weights for policy 1, policy_version 15010 (0.0008) -[2023-10-12 03:43:52,251][78123] Updated weights for policy 1, policy_version 15020 (0.0010) -[2023-10-12 03:43:52,615][78123] Updated weights for policy 1, policy_version 15030 (0.0010) -[2023-10-12 03:43:52,978][78123] Updated weights for policy 1, policy_version 15040 (0.0010) -[2023-10-12 03:43:54,090][78091] Updated weights for policy 0, policy_version 15110 (0.0010) -[2023-10-12 03:43:54,475][78091] Updated weights for policy 0, policy_version 15120 (0.0009) -[2023-10-12 03:43:54,854][78091] Updated weights for policy 0, policy_version 15130 (0.0009) -[2023-10-12 03:43:55,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 30900224. Throughput: 0: 1602.9, 1: 1591.3. Samples: 7732658. Policy #0 lag: (min: 24.0, avg: 50.0, max: 56.0) -[2023-10-12 03:43:55,201][77203] Avg episode reward: [(0, '33.030'), (1, '32.830')] -[2023-10-12 03:43:57,222][78123] Updated weights for policy 1, policy_version 15050 (0.0008) -[2023-10-12 03:43:57,584][78123] Updated weights for policy 1, policy_version 15060 (0.0009) -[2023-10-12 03:43:57,961][78123] Updated weights for policy 1, policy_version 15070 (0.0009) -[2023-10-12 03:43:59,033][78091] Updated weights for policy 0, policy_version 15140 (0.0008) -[2023-10-12 03:43:59,417][78091] Updated weights for policy 0, policy_version 15150 (0.0009) -[2023-10-12 03:43:59,787][78091] Updated weights for policy 0, policy_version 15160 (0.0008) -[2023-10-12 03:44:00,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 30965760. Throughput: 0: 1595.2, 1: 1602.3. Samples: 7742620. Policy #0 lag: (min: 24.0, avg: 50.0, max: 56.0) -[2023-10-12 03:44:00,202][77203] Avg episode reward: [(0, '34.150'), (1, '39.360')] -[2023-10-12 03:44:02,462][78123] Updated weights for policy 1, policy_version 15080 (0.0010) -[2023-10-12 03:44:02,829][78123] Updated weights for policy 1, policy_version 15090 (0.0010) -[2023-10-12 03:44:03,194][78123] Updated weights for policy 1, policy_version 15100 (0.0008) -[2023-10-12 03:44:04,119][78091] Updated weights for policy 0, policy_version 15170 (0.0007) -[2023-10-12 03:44:04,490][78091] Updated weights for policy 0, policy_version 15180 (0.0007) -[2023-10-12 03:44:04,855][78091] Updated weights for policy 0, policy_version 15190 (0.0007) -[2023-10-12 03:44:05,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 30998528. Throughput: 0: 1609.1, 1: 1588.8. Samples: 7761540. Policy #0 lag: (min: 24.0, avg: 50.0, max: 56.0) -[2023-10-12 03:44:05,202][77203] Avg episode reward: [(0, '32.430'), (1, '37.850')] -[2023-10-12 03:44:05,226][78091] Updated weights for policy 0, policy_version 15200 (0.0009) -[2023-10-12 03:44:07,450][78123] Updated weights for policy 1, policy_version 15110 (0.0009) -[2023-10-12 03:44:07,817][78123] Updated weights for policy 1, policy_version 15120 (0.0007) -[2023-10-12 03:44:08,186][78123] Updated weights for policy 1, policy_version 15130 (0.0009) -[2023-10-12 03:44:09,443][78091] Updated weights for policy 0, policy_version 15210 (0.0009) -[2023-10-12 03:44:09,816][78091] Updated weights for policy 0, policy_version 15220 (0.0009) -[2023-10-12 03:44:10,198][78091] Updated weights for policy 0, policy_version 15230 (0.0008) -[2023-10-12 03:44:10,201][77203] Fps is (10 sec: 9830.6, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 31064064. Throughput: 0: 1600.8, 1: 1589.1. Samples: 7780430. Policy #0 lag: (min: 24.0, avg: 50.0, max: 56.0) -[2023-10-12 03:44:10,201][77203] Avg episode reward: [(0, '34.640'), (1, '35.600')] -[2023-10-12 03:44:12,497][78123] Updated weights for policy 1, policy_version 15140 (0.0009) -[2023-10-12 03:44:12,862][78123] Updated weights for policy 1, policy_version 15150 (0.0007) -[2023-10-12 03:44:13,231][78123] Updated weights for policy 1, policy_version 15160 (0.0010) -[2023-10-12 03:44:14,422][78091] Updated weights for policy 0, policy_version 15240 (0.0007) -[2023-10-12 03:44:14,793][78091] Updated weights for policy 0, policy_version 15250 (0.0008) -[2023-10-12 03:44:15,164][78091] Updated weights for policy 0, policy_version 15260 (0.0008) -[2023-10-12 03:44:15,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 31129600. Throughput: 0: 1592.0, 1: 1606.9. Samples: 7790564. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-10-12 03:44:15,201][77203] Avg episode reward: [(0, '34.140'), (1, '41.620')] -[2023-10-12 03:44:17,430][78123] Updated weights for policy 1, policy_version 15170 (0.0008) -[2023-10-12 03:44:17,790][78123] Updated weights for policy 1, policy_version 15180 (0.0008) -[2023-10-12 03:44:18,169][78123] Updated weights for policy 1, policy_version 15190 (0.0007) -[2023-10-12 03:44:18,534][78123] Updated weights for policy 1, policy_version 15200 (0.0008) -[2023-10-12 03:44:19,451][78091] Updated weights for policy 0, policy_version 15270 (0.0008) -[2023-10-12 03:44:19,825][78091] Updated weights for policy 0, policy_version 15280 (0.0009) -[2023-10-12 03:44:20,190][78091] Updated weights for policy 0, policy_version 15290 (0.0008) -[2023-10-12 03:44:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 31195136. Throughput: 0: 1602.9, 1: 1587.7. Samples: 7809410. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-10-12 03:44:20,201][77203] Avg episode reward: [(0, '33.710'), (1, '35.030')] -[2023-10-12 03:44:22,806][78123] Updated weights for policy 1, policy_version 15210 (0.0007) -[2023-10-12 03:44:23,180][78123] Updated weights for policy 1, policy_version 15220 (0.0008) -[2023-10-12 03:44:23,544][78123] Updated weights for policy 1, policy_version 15230 (0.0009) -[2023-10-12 03:44:24,330][78091] Updated weights for policy 0, policy_version 15300 (0.0008) -[2023-10-12 03:44:24,701][78091] Updated weights for policy 0, policy_version 15310 (0.0007) -[2023-10-12 03:44:25,076][78091] Updated weights for policy 0, policy_version 15320 (0.0007) -[2023-10-12 03:44:25,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 31260672. Throughput: 0: 1615.5, 1: 1586.5. Samples: 7828546. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-10-12 03:44:25,202][77203] Avg episode reward: [(0, '33.320'), (1, '37.880')] -[2023-10-12 03:44:27,928][78123] Updated weights for policy 1, policy_version 15240 (0.0011) -[2023-10-12 03:44:28,302][78123] Updated weights for policy 1, policy_version 15250 (0.0010) -[2023-10-12 03:44:28,682][78123] Updated weights for policy 1, policy_version 15260 (0.0009) -[2023-10-12 03:44:29,410][78091] Updated weights for policy 0, policy_version 15330 (0.0008) -[2023-10-12 03:44:29,777][78091] Updated weights for policy 0, policy_version 15340 (0.0007) -[2023-10-12 03:44:30,139][78091] Updated weights for policy 0, policy_version 15350 (0.0007) -[2023-10-12 03:44:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 31326208. Throughput: 0: 1606.2, 1: 1606.8. Samples: 7838688. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-10-12 03:44:30,202][77203] Avg episode reward: [(0, '34.330'), (1, '35.310')] -[2023-10-12 03:44:30,505][78091] Updated weights for policy 0, policy_version 15360 (0.0009) -[2023-10-12 03:44:32,880][78123] Updated weights for policy 1, policy_version 15270 (0.0009) -[2023-10-12 03:44:33,244][78123] Updated weights for policy 1, policy_version 15280 (0.0008) -[2023-10-12 03:44:33,618][78123] Updated weights for policy 1, policy_version 15290 (0.0007) -[2023-10-12 03:44:34,676][78091] Updated weights for policy 0, policy_version 15370 (0.0007) -[2023-10-12 03:44:35,040][78091] Updated weights for policy 0, policy_version 15380 (0.0008) -[2023-10-12 03:44:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 31391744. Throughput: 0: 1611.5, 1: 1589.4. Samples: 7857722. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-10-12 03:44:35,202][77203] Avg episode reward: [(0, '32.420'), (1, '35.620')] -[2023-10-12 03:44:35,421][78091] Updated weights for policy 0, policy_version 15390 (0.0007) -[2023-10-12 03:44:37,987][78123] Updated weights for policy 1, policy_version 15300 (0.0008) -[2023-10-12 03:44:38,346][78123] Updated weights for policy 1, policy_version 15310 (0.0007) -[2023-10-12 03:44:38,718][78123] Updated weights for policy 1, policy_version 15320 (0.0007) -[2023-10-12 03:44:39,773][78091] Updated weights for policy 0, policy_version 15400 (0.0009) -[2023-10-12 03:44:40,155][78091] Updated weights for policy 0, policy_version 15410 (0.0011) -[2023-10-12 03:44:40,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 31457280. Throughput: 0: 1618.0, 1: 1583.3. Samples: 7876720. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-10-12 03:44:40,201][77203] Avg episode reward: [(0, '32.690'), (1, '40.560')] -[2023-10-12 03:44:40,518][78091] Updated weights for policy 0, policy_version 15420 (0.0011) -[2023-10-12 03:44:43,202][78123] Updated weights for policy 1, policy_version 15330 (0.0009) -[2023-10-12 03:44:43,567][78123] Updated weights for policy 1, policy_version 15340 (0.0007) -[2023-10-12 03:44:43,938][78123] Updated weights for policy 1, policy_version 15350 (0.0010) -[2023-10-12 03:44:44,309][78123] Updated weights for policy 1, policy_version 15360 (0.0010) -[2023-10-12 03:44:44,988][78091] Updated weights for policy 0, policy_version 15430 (0.0010) -[2023-10-12 03:44:45,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 31522816. Throughput: 0: 1602.5, 1: 1597.7. Samples: 7886628. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:44:45,201][77203] Avg episode reward: [(0, '30.920'), (1, '35.330')] -[2023-10-12 03:44:45,373][78091] Updated weights for policy 0, policy_version 15440 (0.0010) -[2023-10-12 03:44:45,748][78091] Updated weights for policy 0, policy_version 15450 (0.0010) -[2023-10-12 03:44:48,888][78123] Updated weights for policy 1, policy_version 15370 (0.0011) -[2023-10-12 03:44:49,265][78123] Updated weights for policy 1, policy_version 15380 (0.0009) -[2023-10-12 03:44:49,637][78123] Updated weights for policy 1, policy_version 15390 (0.0009) -[2023-10-12 03:44:50,037][78091] Updated weights for policy 0, policy_version 15460 (0.0008) -[2023-10-12 03:44:50,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 31588352. Throughput: 0: 1601.0, 1: 1602.4. Samples: 7905690. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:44:50,202][77203] Avg episode reward: [(0, '34.840'), (1, '36.750')] -[2023-10-12 03:44:50,395][78091] Updated weights for policy 0, policy_version 15470 (0.0010) -[2023-10-12 03:44:50,763][78091] Updated weights for policy 0, policy_version 15480 (0.0010) -[2023-10-12 03:44:53,729][78123] Updated weights for policy 1, policy_version 15400 (0.0008) -[2023-10-12 03:44:54,105][78123] Updated weights for policy 1, policy_version 15410 (0.0007) -[2023-10-12 03:44:54,471][78123] Updated weights for policy 1, policy_version 15420 (0.0011) -[2023-10-12 03:44:55,135][78091] Updated weights for policy 0, policy_version 15490 (0.0009) -[2023-10-12 03:44:55,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 31653888. Throughput: 0: 1612.3, 1: 1582.8. Samples: 7924210. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:44:55,201][77203] Avg episode reward: [(0, '33.160'), (1, '34.920')] -[2023-10-12 03:44:55,508][78091] Updated weights for policy 0, policy_version 15500 (0.0008) -[2023-10-12 03:44:55,878][78091] Updated weights for policy 0, policy_version 15510 (0.0007) -[2023-10-12 03:44:56,254][78091] Updated weights for policy 0, policy_version 15520 (0.0009) -[2023-10-12 03:44:58,875][78123] Updated weights for policy 1, policy_version 15430 (0.0010) -[2023-10-12 03:44:59,243][78123] Updated weights for policy 1, policy_version 15440 (0.0007) -[2023-10-12 03:44:59,608][78123] Updated weights for policy 1, policy_version 15450 (0.0007) -[2023-10-12 03:45:00,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 31719424. Throughput: 0: 1595.0, 1: 1592.8. Samples: 7934016. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:45:00,201][77203] Avg episode reward: [(0, '35.980'), (1, '35.320')] -[2023-10-12 03:45:00,516][78091] Updated weights for policy 0, policy_version 15530 (0.0008) -[2023-10-12 03:45:00,887][78091] Updated weights for policy 0, policy_version 15540 (0.0009) -[2023-10-12 03:45:01,249][78091] Updated weights for policy 0, policy_version 15550 (0.0009) -[2023-10-12 03:45:03,986][78123] Updated weights for policy 1, policy_version 15460 (0.0007) -[2023-10-12 03:45:04,350][78123] Updated weights for policy 1, policy_version 15470 (0.0009) -[2023-10-12 03:45:04,720][78123] Updated weights for policy 1, policy_version 15480 (0.0007) -[2023-10-12 03:45:05,201][77203] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 31784960. Throughput: 0: 1594.4, 1: 1607.3. Samples: 7953490. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:45:05,202][77203] Avg episode reward: [(0, '34.770'), (1, '38.850')] -[2023-10-12 03:45:05,434][78091] Updated weights for policy 0, policy_version 15560 (0.0007) -[2023-10-12 03:45:05,815][78091] Updated weights for policy 0, policy_version 15570 (0.0007) -[2023-10-12 03:45:06,194][78091] Updated weights for policy 0, policy_version 15580 (0.0008) -[2023-10-12 03:45:08,921][78123] Updated weights for policy 1, policy_version 15490 (0.0009) -[2023-10-12 03:45:09,286][78123] Updated weights for policy 1, policy_version 15500 (0.0011) -[2023-10-12 03:45:09,662][78123] Updated weights for policy 1, policy_version 15510 (0.0009) -[2023-10-12 03:45:10,024][78123] Updated weights for policy 1, policy_version 15520 (0.0008) -[2023-10-12 03:45:10,201][77203] Fps is (10 sec: 13106.7, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 31850496. Throughput: 0: 1605.4, 1: 1592.2. Samples: 7972438. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:45:10,202][77203] Avg episode reward: [(0, '34.910'), (1, '36.880')] -[2023-10-12 03:45:10,212][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000015520_15892480.pth... -[2023-10-12 03:45:10,251][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000014016_14352384.pth -[2023-10-12 03:45:10,390][78091] Updated weights for policy 0, policy_version 15590 (0.0009) -[2023-10-12 03:45:10,756][78091] Updated weights for policy 0, policy_version 15600 (0.0010) -[2023-10-12 03:45:11,134][78091] Updated weights for policy 0, policy_version 15610 (0.0007) -[2023-10-12 03:45:11,359][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000015616_15990784.pth... -[2023-10-12 03:45:11,399][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000014112_14450688.pth -[2023-10-12 03:45:14,352][78123] Updated weights for policy 1, policy_version 15530 (0.0008) -[2023-10-12 03:45:14,725][78123] Updated weights for policy 1, policy_version 15540 (0.0009) -[2023-10-12 03:45:15,099][78123] Updated weights for policy 1, policy_version 15550 (0.0007) -[2023-10-12 03:45:15,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 31916032. Throughput: 0: 1593.2, 1: 1591.8. Samples: 7982014. Policy #0 lag: (min: 21.0, avg: 29.0, max: 53.0) -[2023-10-12 03:45:15,202][77203] Avg episode reward: [(0, '32.620'), (1, '37.210')] -[2023-10-12 03:45:15,627][78091] Updated weights for policy 0, policy_version 15620 (0.0009) -[2023-10-12 03:45:15,997][78091] Updated weights for policy 0, policy_version 15630 (0.0009) -[2023-10-12 03:45:16,373][78091] Updated weights for policy 0, policy_version 15640 (0.0008) -[2023-10-12 03:45:19,315][78123] Updated weights for policy 1, policy_version 15560 (0.0009) -[2023-10-12 03:45:19,689][78123] Updated weights for policy 1, policy_version 15570 (0.0010) -[2023-10-12 03:45:20,066][78123] Updated weights for policy 1, policy_version 15580 (0.0009) -[2023-10-12 03:45:20,201][77203] Fps is (10 sec: 9830.8, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 31948800. Throughput: 0: 1586.6, 1: 1609.6. Samples: 8001550. Policy #0 lag: (min: 21.0, avg: 29.0, max: 53.0) -[2023-10-12 03:45:20,201][77203] Avg episode reward: [(0, '33.930'), (1, '35.400')] -[2023-10-12 03:45:20,688][78091] Updated weights for policy 0, policy_version 15650 (0.0009) -[2023-10-12 03:45:21,055][78091] Updated weights for policy 0, policy_version 15660 (0.0011) -[2023-10-12 03:45:21,427][78091] Updated weights for policy 0, policy_version 15670 (0.0009) -[2023-10-12 03:45:21,794][78091] Updated weights for policy 0, policy_version 15680 (0.0011) -[2023-10-12 03:45:24,578][78123] Updated weights for policy 1, policy_version 15590 (0.0009) -[2023-10-12 03:45:24,940][78123] Updated weights for policy 1, policy_version 15600 (0.0007) -[2023-10-12 03:45:25,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 32014336. Throughput: 0: 1593.2, 1: 1604.5. Samples: 8020616. Policy #0 lag: (min: 21.0, avg: 29.0, max: 53.0) -[2023-10-12 03:45:25,202][77203] Avg episode reward: [(0, '32.560'), (1, '38.820')] -[2023-10-12 03:45:25,297][78123] Updated weights for policy 1, policy_version 15610 (0.0009) -[2023-10-12 03:45:26,186][78091] Updated weights for policy 0, policy_version 15690 (0.0007) -[2023-10-12 03:45:26,551][78091] Updated weights for policy 0, policy_version 15700 (0.0009) -[2023-10-12 03:45:26,925][78091] Updated weights for policy 0, policy_version 15710 (0.0010) -[2023-10-12 03:45:29,671][78123] Updated weights for policy 1, policy_version 15620 (0.0010) -[2023-10-12 03:45:30,053][78123] Updated weights for policy 1, policy_version 15630 (0.0010) -[2023-10-12 03:45:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 32079872. Throughput: 0: 1586.8, 1: 1587.8. Samples: 8029486. Policy #0 lag: (min: 1.0, avg: 9.8, max: 33.0) -[2023-10-12 03:45:30,201][77203] Avg episode reward: [(0, '34.390'), (1, '37.410')] -[2023-10-12 03:45:30,421][78123] Updated weights for policy 1, policy_version 15640 (0.0008) -[2023-10-12 03:45:31,309][78091] Updated weights for policy 0, policy_version 15720 (0.0007) -[2023-10-12 03:45:31,679][78091] Updated weights for policy 0, policy_version 15730 (0.0009) -[2023-10-12 03:45:32,049][78091] Updated weights for policy 0, policy_version 15740 (0.0008) -[2023-10-12 03:45:34,794][78123] Updated weights for policy 1, policy_version 15650 (0.0007) -[2023-10-12 03:45:35,197][78123] Updated weights for policy 1, policy_version 15660 (0.0008) -[2023-10-12 03:45:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 32145408. Throughput: 0: 1587.5, 1: 1591.6. Samples: 8048748. Policy #0 lag: (min: 1.0, avg: 9.8, max: 33.0) -[2023-10-12 03:45:35,202][77203] Avg episode reward: [(0, '31.950'), (1, '36.380')] -[2023-10-12 03:45:35,569][78123] Updated weights for policy 1, policy_version 15670 (0.0008) -[2023-10-12 03:45:35,932][78123] Updated weights for policy 1, policy_version 15680 (0.0007) -[2023-10-12 03:45:36,485][78091] Updated weights for policy 0, policy_version 15750 (0.0007) -[2023-10-12 03:45:36,854][78091] Updated weights for policy 0, policy_version 15760 (0.0007) -[2023-10-12 03:45:37,221][78091] Updated weights for policy 0, policy_version 15770 (0.0008) -[2023-10-12 03:45:40,147][78123] Updated weights for policy 1, policy_version 15690 (0.0009) -[2023-10-12 03:45:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 32210944. Throughput: 0: 1590.7, 1: 1611.3. Samples: 8068302. Policy #0 lag: (min: 1.0, avg: 9.8, max: 33.0) -[2023-10-12 03:45:40,201][77203] Avg episode reward: [(0, '34.090'), (1, '39.810')] -[2023-10-12 03:45:40,517][78123] Updated weights for policy 1, policy_version 15700 (0.0008) -[2023-10-12 03:45:40,875][78123] Updated weights for policy 1, policy_version 15710 (0.0007) -[2023-10-12 03:45:41,489][78091] Updated weights for policy 0, policy_version 15780 (0.0009) -[2023-10-12 03:45:41,866][78091] Updated weights for policy 0, policy_version 15790 (0.0010) -[2023-10-12 03:45:42,236][78091] Updated weights for policy 0, policy_version 15800 (0.0011) -[2023-10-12 03:45:45,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 32276480. Throughput: 0: 1589.6, 1: 1587.0. Samples: 8076964. Policy #0 lag: (min: 2.0, avg: 6.6, max: 34.0) -[2023-10-12 03:45:45,201][77203] Avg episode reward: [(0, '30.570'), (1, '37.760')] -[2023-10-12 03:45:45,229][78123] Updated weights for policy 1, policy_version 15720 (0.0007) -[2023-10-12 03:45:45,598][78123] Updated weights for policy 1, policy_version 15730 (0.0008) -[2023-10-12 03:45:45,979][78123] Updated weights for policy 1, policy_version 15740 (0.0008) -[2023-10-12 03:45:46,629][78091] Updated weights for policy 0, policy_version 15810 (0.0009) -[2023-10-12 03:45:47,010][78091] Updated weights for policy 0, policy_version 15820 (0.0010) -[2023-10-12 03:45:47,376][78091] Updated weights for policy 0, policy_version 15830 (0.0012) -[2023-10-12 03:45:47,748][78091] Updated weights for policy 0, policy_version 15840 (0.0010) -[2023-10-12 03:45:50,201][77203] Fps is (10 sec: 13106.8, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 32342016. Throughput: 0: 1585.0, 1: 1586.8. Samples: 8096222. Policy #0 lag: (min: 2.0, avg: 6.6, max: 34.0) -[2023-10-12 03:45:50,202][77203] Avg episode reward: [(0, '36.000'), (1, '35.560')] -[2023-10-12 03:45:50,403][78123] Updated weights for policy 1, policy_version 15750 (0.0008) -[2023-10-12 03:45:50,763][78123] Updated weights for policy 1, policy_version 15760 (0.0009) -[2023-10-12 03:45:51,140][78123] Updated weights for policy 1, policy_version 15770 (0.0008) -[2023-10-12 03:45:52,065][78091] Updated weights for policy 0, policy_version 15850 (0.0007) -[2023-10-12 03:45:52,441][78091] Updated weights for policy 0, policy_version 15860 (0.0008) -[2023-10-12 03:45:52,819][78091] Updated weights for policy 0, policy_version 15870 (0.0008) -[2023-10-12 03:45:55,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 32407552. Throughput: 0: 1583.6, 1: 1604.7. Samples: 8115910. Policy #0 lag: (min: 2.0, avg: 6.6, max: 34.0) -[2023-10-12 03:45:55,202][77203] Avg episode reward: [(0, '33.940'), (1, '37.200')] -[2023-10-12 03:45:55,464][78123] Updated weights for policy 1, policy_version 15780 (0.0008) -[2023-10-12 03:45:55,837][78123] Updated weights for policy 1, policy_version 15790 (0.0008) -[2023-10-12 03:45:56,209][78123] Updated weights for policy 1, policy_version 15800 (0.0007) -[2023-10-12 03:45:57,123][78091] Updated weights for policy 0, policy_version 15880 (0.0011) -[2023-10-12 03:45:57,490][78091] Updated weights for policy 0, policy_version 15890 (0.0008) -[2023-10-12 03:45:57,861][78091] Updated weights for policy 0, policy_version 15900 (0.0007) -[2023-10-12 03:46:00,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 32473088. Throughput: 0: 1586.0, 1: 1581.7. Samples: 8124562. Policy #0 lag: (min: 0.0, avg: 22.4, max: 32.0) -[2023-10-12 03:46:00,202][77203] Avg episode reward: [(0, '32.130'), (1, '34.420')] -[2023-10-12 03:46:00,565][78123] Updated weights for policy 1, policy_version 15810 (0.0008) -[2023-10-12 03:46:00,939][78123] Updated weights for policy 1, policy_version 15820 (0.0010) -[2023-10-12 03:46:01,298][78123] Updated weights for policy 1, policy_version 15830 (0.0010) -[2023-10-12 03:46:01,672][78123] Updated weights for policy 1, policy_version 15840 (0.0008) -[2023-10-12 03:46:02,228][78091] Updated weights for policy 0, policy_version 15910 (0.0007) -[2023-10-12 03:46:02,593][78091] Updated weights for policy 0, policy_version 15920 (0.0010) -[2023-10-12 03:46:02,970][78091] Updated weights for policy 0, policy_version 15930 (0.0011) -[2023-10-12 03:46:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 32538624. Throughput: 0: 1581.4, 1: 1583.3. Samples: 8143962. Policy #0 lag: (min: 0.0, avg: 22.4, max: 32.0) -[2023-10-12 03:46:05,202][77203] Avg episode reward: [(0, '35.790'), (1, '44.820')] -[2023-10-12 03:46:05,936][78123] Updated weights for policy 1, policy_version 15850 (0.0009) -[2023-10-12 03:46:06,300][78123] Updated weights for policy 1, policy_version 15860 (0.0011) -[2023-10-12 03:46:06,665][78123] Updated weights for policy 1, policy_version 15870 (0.0010) -[2023-10-12 03:46:07,171][78091] Updated weights for policy 0, policy_version 15940 (0.0010) -[2023-10-12 03:46:07,542][78091] Updated weights for policy 0, policy_version 15950 (0.0009) -[2023-10-12 03:46:07,910][78091] Updated weights for policy 0, policy_version 15960 (0.0009) -[2023-10-12 03:46:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 32604160. Throughput: 0: 1582.9, 1: 1593.7. Samples: 8163564. Policy #0 lag: (min: 0.0, avg: 22.4, max: 32.0) -[2023-10-12 03:46:10,202][77203] Avg episode reward: [(0, '34.500'), (1, '35.670')] -[2023-10-12 03:46:11,068][78123] Updated weights for policy 1, policy_version 15880 (0.0008) -[2023-10-12 03:46:11,441][78123] Updated weights for policy 1, policy_version 15890 (0.0007) -[2023-10-12 03:46:11,811][78123] Updated weights for policy 1, policy_version 15900 (0.0007) -[2023-10-12 03:46:12,246][78091] Updated weights for policy 0, policy_version 15970 (0.0008) -[2023-10-12 03:46:12,609][78091] Updated weights for policy 0, policy_version 15980 (0.0009) -[2023-10-12 03:46:12,975][78091] Updated weights for policy 0, policy_version 15990 (0.0011) -[2023-10-12 03:46:13,354][78091] Updated weights for policy 0, policy_version 16000 (0.0010) -[2023-10-12 03:46:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 32669696. Throughput: 0: 1596.7, 1: 1584.3. Samples: 8172630. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:46:15,202][77203] Avg episode reward: [(0, '32.400'), (1, '35.310')] -[2023-10-12 03:46:16,133][78123] Updated weights for policy 1, policy_version 15910 (0.0009) -[2023-10-12 03:46:16,486][78123] Updated weights for policy 1, policy_version 15920 (0.0009) -[2023-10-12 03:46:16,849][78123] Updated weights for policy 1, policy_version 15930 (0.0008) -[2023-10-12 03:46:17,634][78091] Updated weights for policy 0, policy_version 16010 (0.0012) -[2023-10-12 03:46:18,008][78091] Updated weights for policy 0, policy_version 16020 (0.0009) -[2023-10-12 03:46:18,382][78091] Updated weights for policy 0, policy_version 16030 (0.0008) -[2023-10-12 03:46:20,201][77203] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 32735232. Throughput: 0: 1586.1, 1: 1589.8. Samples: 8191664. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:46:20,201][77203] Avg episode reward: [(0, '32.660'), (1, '37.790')] -[2023-10-12 03:46:21,250][78123] Updated weights for policy 1, policy_version 15940 (0.0007) -[2023-10-12 03:46:21,637][78123] Updated weights for policy 1, policy_version 15950 (0.0007) -[2023-10-12 03:46:22,011][78123] Updated weights for policy 1, policy_version 15960 (0.0008) -[2023-10-12 03:46:22,680][78091] Updated weights for policy 0, policy_version 16040 (0.0010) -[2023-10-12 03:46:23,061][78091] Updated weights for policy 0, policy_version 16050 (0.0010) -[2023-10-12 03:46:23,447][78091] Updated weights for policy 0, policy_version 16060 (0.0009) -[2023-10-12 03:46:25,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 32800768. Throughput: 0: 1584.4, 1: 1584.3. Samples: 8210894. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:46:25,202][77203] Avg episode reward: [(0, '33.360'), (1, '34.990')] -[2023-10-12 03:46:26,104][78123] Updated weights for policy 1, policy_version 15970 (0.0008) -[2023-10-12 03:46:26,473][78123] Updated weights for policy 1, policy_version 15980 (0.0008) -[2023-10-12 03:46:26,846][78123] Updated weights for policy 1, policy_version 15990 (0.0008) -[2023-10-12 03:46:27,209][78123] Updated weights for policy 1, policy_version 16000 (0.0007) -[2023-10-12 03:46:27,818][78091] Updated weights for policy 0, policy_version 16070 (0.0007) -[2023-10-12 03:46:28,196][78091] Updated weights for policy 0, policy_version 16080 (0.0009) -[2023-10-12 03:46:28,578][78091] Updated weights for policy 0, policy_version 16090 (0.0009) -[2023-10-12 03:46:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 32866304. Throughput: 0: 1603.7, 1: 1587.2. Samples: 8220556. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 03:46:30,201][77203] Avg episode reward: [(0, '32.690'), (1, '43.100')] -[2023-10-12 03:46:31,319][78123] Updated weights for policy 1, policy_version 16010 (0.0008) -[2023-10-12 03:46:31,696][78123] Updated weights for policy 1, policy_version 16020 (0.0010) -[2023-10-12 03:46:32,062][78123] Updated weights for policy 1, policy_version 16030 (0.0008) -[2023-10-12 03:46:32,737][78091] Updated weights for policy 0, policy_version 16100 (0.0007) -[2023-10-12 03:46:33,123][78091] Updated weights for policy 0, policy_version 16110 (0.0008) -[2023-10-12 03:46:33,485][78091] Updated weights for policy 0, policy_version 16120 (0.0008) -[2023-10-12 03:46:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 32931840. Throughput: 0: 1588.5, 1: 1593.9. Samples: 8239426. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 03:46:35,202][77203] Avg episode reward: [(0, '31.190'), (1, '33.450')] -[2023-10-12 03:46:36,472][78123] Updated weights for policy 1, policy_version 16040 (0.0009) -[2023-10-12 03:46:36,837][78123] Updated weights for policy 1, policy_version 16050 (0.0007) -[2023-10-12 03:46:37,210][78123] Updated weights for policy 1, policy_version 16060 (0.0007) -[2023-10-12 03:46:37,872][78091] Updated weights for policy 0, policy_version 16130 (0.0007) -[2023-10-12 03:46:38,242][78091] Updated weights for policy 0, policy_version 16140 (0.0007) -[2023-10-12 03:46:38,617][78091] Updated weights for policy 0, policy_version 16150 (0.0008) -[2023-10-12 03:46:38,992][78091] Updated weights for policy 0, policy_version 16160 (0.0008) -[2023-10-12 03:46:40,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 32997376. Throughput: 0: 1586.1, 1: 1592.8. Samples: 8258962. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 03:46:40,202][77203] Avg episode reward: [(0, '36.270'), (1, '36.120')] -[2023-10-12 03:46:41,425][78123] Updated weights for policy 1, policy_version 16070 (0.0009) -[2023-10-12 03:46:41,797][78123] Updated weights for policy 1, policy_version 16080 (0.0007) -[2023-10-12 03:46:42,158][78123] Updated weights for policy 1, policy_version 16090 (0.0008) -[2023-10-12 03:46:43,348][78091] Updated weights for policy 0, policy_version 16170 (0.0007) -[2023-10-12 03:46:43,719][78091] Updated weights for policy 0, policy_version 16180 (0.0009) -[2023-10-12 03:46:44,090][78091] Updated weights for policy 0, policy_version 16190 (0.0008) -[2023-10-12 03:46:45,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 33062912. Throughput: 0: 1606.8, 1: 1594.9. Samples: 8268640. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-12 03:46:45,202][77203] Avg episode reward: [(0, '39.000'), (1, '37.860')] -[2023-10-12 03:46:46,393][78123] Updated weights for policy 1, policy_version 16100 (0.0010) -[2023-10-12 03:46:46,754][78123] Updated weights for policy 1, policy_version 16110 (0.0009) -[2023-10-12 03:46:47,123][78123] Updated weights for policy 1, policy_version 16120 (0.0011) -[2023-10-12 03:46:48,440][78091] Updated weights for policy 0, policy_version 16200 (0.0007) -[2023-10-12 03:46:48,804][78091] Updated weights for policy 0, policy_version 16210 (0.0007) -[2023-10-12 03:46:49,174][78091] Updated weights for policy 0, policy_version 16220 (0.0009) -[2023-10-12 03:46:50,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.3, 300 sec: 12774.0). Total num frames: 33128448. Throughput: 0: 1598.1, 1: 1596.5. Samples: 8287718. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-12 03:46:50,201][77203] Avg episode reward: [(0, '37.950'), (1, '35.930')] -[2023-10-12 03:46:51,528][78123] Updated weights for policy 1, policy_version 16130 (0.0009) -[2023-10-12 03:46:51,898][78123] Updated weights for policy 1, policy_version 16140 (0.0011) -[2023-10-12 03:46:52,262][78123] Updated weights for policy 1, policy_version 16150 (0.0007) -[2023-10-12 03:46:52,633][78123] Updated weights for policy 1, policy_version 16160 (0.0010) -[2023-10-12 03:46:53,457][78091] Updated weights for policy 0, policy_version 16230 (0.0007) -[2023-10-12 03:46:53,832][78091] Updated weights for policy 0, policy_version 16240 (0.0009) -[2023-10-12 03:46:54,193][78091] Updated weights for policy 0, policy_version 16250 (0.0009) -[2023-10-12 03:46:55,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 33193984. Throughput: 0: 1587.7, 1: 1594.0. Samples: 8306742. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-12 03:46:55,201][77203] Avg episode reward: [(0, '36.290'), (1, '37.200')] -[2023-10-12 03:46:56,914][78123] Updated weights for policy 1, policy_version 16170 (0.0009) -[2023-10-12 03:46:57,277][78123] Updated weights for policy 1, policy_version 16180 (0.0009) -[2023-10-12 03:46:57,646][78123] Updated weights for policy 1, policy_version 16190 (0.0008) -[2023-10-12 03:46:58,514][78091] Updated weights for policy 0, policy_version 16260 (0.0009) -[2023-10-12 03:46:58,886][78091] Updated weights for policy 0, policy_version 16270 (0.0009) -[2023-10-12 03:46:59,263][78091] Updated weights for policy 0, policy_version 16280 (0.0010) -[2023-10-12 03:47:00,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 33259520. Throughput: 0: 1601.5, 1: 1595.1. Samples: 8316476. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-12 03:47:00,202][77203] Avg episode reward: [(0, '38.150'), (1, '34.610')] -[2023-10-12 03:47:01,940][78123] Updated weights for policy 1, policy_version 16200 (0.0009) -[2023-10-12 03:47:02,310][78123] Updated weights for policy 1, policy_version 16210 (0.0009) -[2023-10-12 03:47:02,662][78123] Updated weights for policy 1, policy_version 16220 (0.0008) -[2023-10-12 03:47:03,660][78091] Updated weights for policy 0, policy_version 16290 (0.0009) -[2023-10-12 03:47:04,027][78091] Updated weights for policy 0, policy_version 16300 (0.0010) -[2023-10-12 03:47:04,395][78091] Updated weights for policy 0, policy_version 16310 (0.0010) -[2023-10-12 03:47:04,768][78091] Updated weights for policy 0, policy_version 16320 (0.0008) -[2023-10-12 03:47:05,201][77203] Fps is (10 sec: 13106.7, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 33325056. Throughput: 0: 1609.2, 1: 1594.7. Samples: 8335840. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-12 03:47:05,202][77203] Avg episode reward: [(0, '34.650'), (1, '37.440')] -[2023-10-12 03:47:07,138][78123] Updated weights for policy 1, policy_version 16230 (0.0009) -[2023-10-12 03:47:07,519][78123] Updated weights for policy 1, policy_version 16240 (0.0009) -[2023-10-12 03:47:07,893][78123] Updated weights for policy 1, policy_version 16250 (0.0009) -[2023-10-12 03:47:09,106][78091] Updated weights for policy 0, policy_version 16330 (0.0010) -[2023-10-12 03:47:09,476][78091] Updated weights for policy 0, policy_version 16340 (0.0009) -[2023-10-12 03:47:09,844][78091] Updated weights for policy 0, policy_version 16350 (0.0010) -[2023-10-12 03:47:10,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.3, 300 sec: 12885.0). Total num frames: 33390592. Throughput: 0: 1588.8, 1: 1594.1. Samples: 8354124. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-12 03:47:10,201][77203] Avg episode reward: [(0, '35.260'), (1, '41.130')] -[2023-10-12 03:47:10,209][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000016352_16744448.pth... -[2023-10-12 03:47:10,209][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000016256_16646144.pth... -[2023-10-12 03:47:10,241][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000014752_15106048.pth -[2023-10-12 03:47:10,251][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000014848_15204352.pth -[2023-10-12 03:47:12,302][78123] Updated weights for policy 1, policy_version 16260 (0.0008) -[2023-10-12 03:47:12,682][78123] Updated weights for policy 1, policy_version 16270 (0.0009) -[2023-10-12 03:47:13,057][78123] Updated weights for policy 1, policy_version 16280 (0.0007) -[2023-10-12 03:47:14,115][78091] Updated weights for policy 0, policy_version 16360 (0.0010) -[2023-10-12 03:47:14,489][78091] Updated weights for policy 0, policy_version 16370 (0.0008) -[2023-10-12 03:47:14,859][78091] Updated weights for policy 0, policy_version 16380 (0.0009) -[2023-10-12 03:47:15,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 33456128. Throughput: 0: 1593.4, 1: 1600.9. Samples: 8364298. Policy #0 lag: (min: 8.0, avg: 31.2, max: 40.0) -[2023-10-12 03:47:15,202][77203] Avg episode reward: [(0, '36.260'), (1, '32.620')] -[2023-10-12 03:47:17,322][78123] Updated weights for policy 1, policy_version 16290 (0.0010) -[2023-10-12 03:47:17,699][78123] Updated weights for policy 1, policy_version 16300 (0.0009) -[2023-10-12 03:47:18,065][78123] Updated weights for policy 1, policy_version 16310 (0.0010) -[2023-10-12 03:47:18,429][78123] Updated weights for policy 1, policy_version 16320 (0.0007) -[2023-10-12 03:47:19,009][78091] Updated weights for policy 0, policy_version 16390 (0.0009) -[2023-10-12 03:47:19,381][78091] Updated weights for policy 0, policy_version 16400 (0.0009) -[2023-10-12 03:47:19,751][78091] Updated weights for policy 0, policy_version 16410 (0.0009) -[2023-10-12 03:47:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 33521664. Throughput: 0: 1617.2, 1: 1584.0. Samples: 8383482. Policy #0 lag: (min: 8.0, avg: 31.2, max: 40.0) -[2023-10-12 03:47:20,201][77203] Avg episode reward: [(0, '35.740'), (1, '39.870')] -[2023-10-12 03:47:22,944][78123] Updated weights for policy 1, policy_version 16330 (0.0008) -[2023-10-12 03:47:23,320][78123] Updated weights for policy 1, policy_version 16340 (0.0009) -[2023-10-12 03:47:23,684][78123] Updated weights for policy 1, policy_version 16350 (0.0007) -[2023-10-12 03:47:24,126][78091] Updated weights for policy 0, policy_version 16420 (0.0010) -[2023-10-12 03:47:24,491][78091] Updated weights for policy 0, policy_version 16430 (0.0007) -[2023-10-12 03:47:24,869][78091] Updated weights for policy 0, policy_version 16440 (0.0010) -[2023-10-12 03:47:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 33587200. Throughput: 0: 1605.2, 1: 1578.8. Samples: 8402242. Policy #0 lag: (min: 8.0, avg: 31.2, max: 40.0) -[2023-10-12 03:47:25,202][77203] Avg episode reward: [(0, '36.300'), (1, '38.690')] -[2023-10-12 03:47:28,142][78123] Updated weights for policy 1, policy_version 16360 (0.0007) -[2023-10-12 03:47:28,506][78123] Updated weights for policy 1, policy_version 16370 (0.0007) -[2023-10-12 03:47:28,877][78123] Updated weights for policy 1, policy_version 16380 (0.0009) -[2023-10-12 03:47:29,023][78091] Updated weights for policy 0, policy_version 16450 (0.0008) -[2023-10-12 03:47:29,393][78091] Updated weights for policy 0, policy_version 16460 (0.0010) -[2023-10-12 03:47:29,773][78091] Updated weights for policy 0, policy_version 16470 (0.0011) -[2023-10-12 03:47:30,143][78091] Updated weights for policy 0, policy_version 16480 (0.0009) -[2023-10-12 03:47:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 33652736. Throughput: 0: 1599.6, 1: 1605.1. Samples: 8412850. Policy #0 lag: (min: 6.0, avg: 8.4, max: 38.0) -[2023-10-12 03:47:30,201][77203] Avg episode reward: [(0, '36.670'), (1, '34.360')] -[2023-10-12 03:47:33,192][78123] Updated weights for policy 1, policy_version 16390 (0.0009) -[2023-10-12 03:47:33,556][78123] Updated weights for policy 1, policy_version 16400 (0.0009) -[2023-10-12 03:47:33,929][78123] Updated weights for policy 1, policy_version 16410 (0.0010) -[2023-10-12 03:47:34,458][78091] Updated weights for policy 0, policy_version 16490 (0.0009) -[2023-10-12 03:47:34,828][78091] Updated weights for policy 0, policy_version 16500 (0.0008) -[2023-10-12 03:47:35,195][78091] Updated weights for policy 0, policy_version 16510 (0.0007) -[2023-10-12 03:47:35,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 33685504. Throughput: 0: 1618.7, 1: 1586.7. Samples: 8431962. Policy #0 lag: (min: 6.0, avg: 8.4, max: 38.0) -[2023-10-12 03:47:35,201][77203] Avg episode reward: [(0, '35.830'), (1, '39.610')] -[2023-10-12 03:47:38,150][78123] Updated weights for policy 1, policy_version 16420 (0.0008) -[2023-10-12 03:47:38,518][78123] Updated weights for policy 1, policy_version 16430 (0.0010) -[2023-10-12 03:47:38,884][78123] Updated weights for policy 1, policy_version 16440 (0.0009) -[2023-10-12 03:47:39,310][78091] Updated weights for policy 0, policy_version 16520 (0.0009) -[2023-10-12 03:47:39,673][78091] Updated weights for policy 0, policy_version 16530 (0.0008) -[2023-10-12 03:47:40,045][78091] Updated weights for policy 0, policy_version 16540 (0.0007) -[2023-10-12 03:47:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 12885.0). Total num frames: 33783808. Throughput: 0: 1616.3, 1: 1584.7. Samples: 8450786. Policy #0 lag: (min: 6.0, avg: 8.4, max: 38.0) -[2023-10-12 03:47:40,201][77203] Avg episode reward: [(0, '37.070'), (1, '35.760')] -[2023-10-12 03:47:43,270][78123] Updated weights for policy 1, policy_version 16450 (0.0008) -[2023-10-12 03:47:43,638][78123] Updated weights for policy 1, policy_version 16460 (0.0010) -[2023-10-12 03:47:44,004][78123] Updated weights for policy 1, policy_version 16470 (0.0009) -[2023-10-12 03:47:44,327][78091] Updated weights for policy 0, policy_version 16550 (0.0009) -[2023-10-12 03:47:44,372][78123] Updated weights for policy 1, policy_version 16480 (0.0010) -[2023-10-12 03:47:44,702][78091] Updated weights for policy 0, policy_version 16560 (0.0010) -[2023-10-12 03:47:45,068][78091] Updated weights for policy 0, policy_version 16570 (0.0007) -[2023-10-12 03:47:45,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 33816576. Throughput: 0: 1610.5, 1: 1607.3. Samples: 8461278. Policy #0 lag: (min: 6.0, avg: 8.4, max: 38.0) -[2023-10-12 03:47:45,201][77203] Avg episode reward: [(0, '38.090'), (1, '40.320')] -[2023-10-12 03:47:48,542][78123] Updated weights for policy 1, policy_version 16490 (0.0008) -[2023-10-12 03:47:48,907][78123] Updated weights for policy 1, policy_version 16500 (0.0009) -[2023-10-12 03:47:49,268][78123] Updated weights for policy 1, policy_version 16510 (0.0009) -[2023-10-12 03:47:49,393][78091] Updated weights for policy 0, policy_version 16580 (0.0008) -[2023-10-12 03:47:49,758][78091] Updated weights for policy 0, policy_version 16590 (0.0010) -[2023-10-12 03:47:50,133][78091] Updated weights for policy 0, policy_version 16600 (0.0007) -[2023-10-12 03:47:50,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 33882112. Throughput: 0: 1614.3, 1: 1595.4. Samples: 8480276. Policy #0 lag: (min: 9.0, avg: 14.2, max: 41.0) -[2023-10-12 03:47:50,202][77203] Avg episode reward: [(0, '35.070'), (1, '36.110')] -[2023-10-12 03:47:53,474][78123] Updated weights for policy 1, policy_version 16520 (0.0007) -[2023-10-12 03:47:53,858][78123] Updated weights for policy 1, policy_version 16530 (0.0008) -[2023-10-12 03:47:54,217][78123] Updated weights for policy 1, policy_version 16540 (0.0009) -[2023-10-12 03:47:54,409][78091] Updated weights for policy 0, policy_version 16610 (0.0008) -[2023-10-12 03:47:54,794][78091] Updated weights for policy 0, policy_version 16620 (0.0007) -[2023-10-12 03:47:55,172][78091] Updated weights for policy 0, policy_version 16630 (0.0007) -[2023-10-12 03:47:55,201][77203] Fps is (10 sec: 13106.8, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 33947648. Throughput: 0: 1628.9, 1: 1592.3. Samples: 8499080. Policy #0 lag: (min: 9.0, avg: 14.2, max: 41.0) -[2023-10-12 03:47:55,202][77203] Avg episode reward: [(0, '34.540'), (1, '35.980')] -[2023-10-12 03:47:55,548][78091] Updated weights for policy 0, policy_version 16640 (0.0010) -[2023-10-12 03:47:58,716][78123] Updated weights for policy 1, policy_version 16550 (0.0009) -[2023-10-12 03:47:59,084][78123] Updated weights for policy 1, policy_version 16560 (0.0012) -[2023-10-12 03:47:59,449][78123] Updated weights for policy 1, policy_version 16570 (0.0009) -[2023-10-12 03:47:59,948][78091] Updated weights for policy 0, policy_version 16650 (0.0007) -[2023-10-12 03:48:00,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 34013184. Throughput: 0: 1612.5, 1: 1605.5. Samples: 8509110. Policy #0 lag: (min: 9.0, avg: 14.2, max: 41.0) -[2023-10-12 03:48:00,201][77203] Avg episode reward: [(0, '38.150'), (1, '39.420')] -[2023-10-12 03:48:00,313][78091] Updated weights for policy 0, policy_version 16660 (0.0008) -[2023-10-12 03:48:00,692][78091] Updated weights for policy 0, policy_version 16670 (0.0009) -[2023-10-12 03:48:03,813][78123] Updated weights for policy 1, policy_version 16580 (0.0009) -[2023-10-12 03:48:04,180][78123] Updated weights for policy 1, policy_version 16590 (0.0007) -[2023-10-12 03:48:04,545][78123] Updated weights for policy 1, policy_version 16600 (0.0008) -[2023-10-12 03:48:04,839][78091] Updated weights for policy 0, policy_version 16680 (0.0008) -[2023-10-12 03:48:05,201][77203] Fps is (10 sec: 13107.6, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 34078720. Throughput: 0: 1609.4, 1: 1617.2. Samples: 8528680. Policy #0 lag: (min: 23.0, avg: 23.2, max: 33.0) -[2023-10-12 03:48:05,201][77203] Avg episode reward: [(0, '36.290'), (1, '37.800')] -[2023-10-12 03:48:05,215][78091] Updated weights for policy 0, policy_version 16690 (0.0009) -[2023-10-12 03:48:05,582][78091] Updated weights for policy 0, policy_version 16700 (0.0007) -[2023-10-12 03:48:08,870][78123] Updated weights for policy 1, policy_version 16610 (0.0008) -[2023-10-12 03:48:09,239][78123] Updated weights for policy 1, policy_version 16620 (0.0009) -[2023-10-12 03:48:09,624][78123] Updated weights for policy 1, policy_version 16630 (0.0010) -[2023-10-12 03:48:09,982][78123] Updated weights for policy 1, policy_version 16640 (0.0010) -[2023-10-12 03:48:10,035][78091] Updated weights for policy 0, policy_version 16710 (0.0009) -[2023-10-12 03:48:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 34144256. Throughput: 0: 1619.7, 1: 1602.1. Samples: 8547224. Policy #0 lag: (min: 23.0, avg: 23.2, max: 33.0) -[2023-10-12 03:48:10,201][77203] Avg episode reward: [(0, '39.000'), (1, '35.950')] -[2023-10-12 03:48:10,400][78091] Updated weights for policy 0, policy_version 16720 (0.0007) -[2023-10-12 03:48:10,768][78091] Updated weights for policy 0, policy_version 16730 (0.0007) -[2023-10-12 03:48:14,257][78123] Updated weights for policy 1, policy_version 16650 (0.0009) -[2023-10-12 03:48:14,627][78123] Updated weights for policy 1, policy_version 16660 (0.0008) -[2023-10-12 03:48:14,997][78123] Updated weights for policy 1, policy_version 16670 (0.0008) -[2023-10-12 03:48:15,124][78091] Updated weights for policy 0, policy_version 16740 (0.0007) -[2023-10-12 03:48:15,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 34209792. Throughput: 0: 1599.9, 1: 1597.9. Samples: 8556748. Policy #0 lag: (min: 23.0, avg: 23.2, max: 33.0) -[2023-10-12 03:48:15,202][77203] Avg episode reward: [(0, '34.610'), (1, '40.510')] -[2023-10-12 03:48:15,499][78091] Updated weights for policy 0, policy_version 16750 (0.0010) -[2023-10-12 03:48:15,868][78091] Updated weights for policy 0, policy_version 16760 (0.0010) -[2023-10-12 03:48:19,274][78123] Updated weights for policy 1, policy_version 16680 (0.0009) -[2023-10-12 03:48:19,640][78123] Updated weights for policy 1, policy_version 16690 (0.0010) -[2023-10-12 03:48:19,998][78123] Updated weights for policy 1, policy_version 16700 (0.0009) -[2023-10-12 03:48:20,141][78091] Updated weights for policy 0, policy_version 16770 (0.0009) -[2023-10-12 03:48:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 34275328. Throughput: 0: 1596.7, 1: 1613.8. Samples: 8576432. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 03:48:20,201][77203] Avg episode reward: [(0, '39.570'), (1, '39.210')] -[2023-10-12 03:48:20,504][78091] Updated weights for policy 0, policy_version 16780 (0.0007) -[2023-10-12 03:48:20,868][78091] Updated weights for policy 0, policy_version 16790 (0.0011) -[2023-10-12 03:48:21,242][78091] Updated weights for policy 0, policy_version 16800 (0.0010) -[2023-10-12 03:48:24,469][78123] Updated weights for policy 1, policy_version 16710 (0.0008) -[2023-10-12 03:48:24,842][78123] Updated weights for policy 1, policy_version 16720 (0.0007) -[2023-10-12 03:48:25,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 34308096. Throughput: 0: 1607.2, 1: 1604.1. Samples: 8595294. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 03:48:25,201][77203] Avg episode reward: [(0, '35.680'), (1, '39.220')] -[2023-10-12 03:48:25,205][78123] Updated weights for policy 1, policy_version 16730 (0.0009) -[2023-10-12 03:48:25,519][78091] Updated weights for policy 0, policy_version 16810 (0.0008) -[2023-10-12 03:48:25,896][78091] Updated weights for policy 0, policy_version 16820 (0.0007) -[2023-10-12 03:48:26,268][78091] Updated weights for policy 0, policy_version 16830 (0.0009) -[2023-10-12 03:48:29,477][78123] Updated weights for policy 1, policy_version 16740 (0.0010) -[2023-10-12 03:48:29,842][78123] Updated weights for policy 1, policy_version 16750 (0.0008) -[2023-10-12 03:48:30,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 34373632. Throughput: 0: 1588.4, 1: 1590.8. Samples: 8604344. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 03:48:30,201][77203] Avg episode reward: [(0, '38.650'), (1, '38.860')] -[2023-10-12 03:48:30,224][78123] Updated weights for policy 1, policy_version 16760 (0.0009) -[2023-10-12 03:48:30,403][78091] Updated weights for policy 0, policy_version 16840 (0.0009) -[2023-10-12 03:48:30,767][78091] Updated weights for policy 0, policy_version 16850 (0.0009) -[2023-10-12 03:48:31,146][78091] Updated weights for policy 0, policy_version 16860 (0.0010) -[2023-10-12 03:48:34,524][78123] Updated weights for policy 1, policy_version 16770 (0.0008) -[2023-10-12 03:48:34,892][78123] Updated weights for policy 1, policy_version 16780 (0.0007) -[2023-10-12 03:48:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 34439168. Throughput: 0: 1589.7, 1: 1603.6. Samples: 8623974. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:48:35,201][77203] Avg episode reward: [(0, '37.860'), (1, '38.840')] -[2023-10-12 03:48:35,253][78123] Updated weights for policy 1, policy_version 16790 (0.0007) -[2023-10-12 03:48:35,491][78091] Updated weights for policy 0, policy_version 16870 (0.0007) -[2023-10-12 03:48:35,616][78123] Updated weights for policy 1, policy_version 16800 (0.0007) -[2023-10-12 03:48:35,871][78091] Updated weights for policy 0, policy_version 16880 (0.0009) -[2023-10-12 03:48:36,235][78091] Updated weights for policy 0, policy_version 16890 (0.0007) -[2023-10-12 03:48:40,035][78123] Updated weights for policy 1, policy_version 16810 (0.0009) -[2023-10-12 03:48:40,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 34504704. Throughput: 0: 1593.5, 1: 1608.2. Samples: 8643156. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:48:40,202][77203] Avg episode reward: [(0, '38.300'), (1, '40.730')] -[2023-10-12 03:48:40,404][78123] Updated weights for policy 1, policy_version 16820 (0.0007) -[2023-10-12 03:48:40,585][78091] Updated weights for policy 0, policy_version 16900 (0.0008) -[2023-10-12 03:48:40,770][78123] Updated weights for policy 1, policy_version 16830 (0.0009) -[2023-10-12 03:48:40,955][78091] Updated weights for policy 0, policy_version 16910 (0.0008) -[2023-10-12 03:48:41,328][78091] Updated weights for policy 0, policy_version 16920 (0.0007) -[2023-10-12 03:48:45,062][78123] Updated weights for policy 1, policy_version 16840 (0.0007) -[2023-10-12 03:48:45,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 34570240. Throughput: 0: 1586.3, 1: 1587.2. Samples: 8651914. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:48:45,201][77203] Avg episode reward: [(0, '32.970'), (1, '40.150')] -[2023-10-12 03:48:45,445][78123] Updated weights for policy 1, policy_version 16850 (0.0008) -[2023-10-12 03:48:45,790][78091] Updated weights for policy 0, policy_version 16930 (0.0009) -[2023-10-12 03:48:45,803][78123] Updated weights for policy 1, policy_version 16860 (0.0008) -[2023-10-12 03:48:46,170][78091] Updated weights for policy 0, policy_version 16940 (0.0007) -[2023-10-12 03:48:46,536][78091] Updated weights for policy 0, policy_version 16950 (0.0008) -[2023-10-12 03:48:46,908][78091] Updated weights for policy 0, policy_version 16960 (0.0007) -[2023-10-12 03:48:50,019][78123] Updated weights for policy 1, policy_version 16870 (0.0008) -[2023-10-12 03:48:50,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 34635776. Throughput: 0: 1578.9, 1: 1591.2. Samples: 8671334. Policy #0 lag: (min: 12.0, avg: 15.9, max: 44.0) -[2023-10-12 03:48:50,202][77203] Avg episode reward: [(0, '37.650'), (1, '38.830')] -[2023-10-12 03:48:50,386][78123] Updated weights for policy 1, policy_version 16880 (0.0009) -[2023-10-12 03:48:50,747][78123] Updated weights for policy 1, policy_version 16890 (0.0010) -[2023-10-12 03:48:51,337][78091] Updated weights for policy 0, policy_version 16970 (0.0008) -[2023-10-12 03:48:51,711][78091] Updated weights for policy 0, policy_version 16980 (0.0007) -[2023-10-12 03:48:52,082][78091] Updated weights for policy 0, policy_version 16990 (0.0008) -[2023-10-12 03:48:55,119][78123] Updated weights for policy 1, policy_version 16900 (0.0010) -[2023-10-12 03:48:55,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 34701312. Throughput: 0: 1583.3, 1: 1607.6. Samples: 8690816. Policy #0 lag: (min: 12.0, avg: 15.9, max: 44.0) -[2023-10-12 03:48:55,202][77203] Avg episode reward: [(0, '35.360'), (1, '41.620')] -[2023-10-12 03:48:55,474][78123] Updated weights for policy 1, policy_version 16910 (0.0010) -[2023-10-12 03:48:55,849][78123] Updated weights for policy 1, policy_version 16920 (0.0010) -[2023-10-12 03:48:56,498][78091] Updated weights for policy 0, policy_version 17000 (0.0009) -[2023-10-12 03:48:56,865][78091] Updated weights for policy 0, policy_version 17010 (0.0008) -[2023-10-12 03:48:57,240][78091] Updated weights for policy 0, policy_version 17020 (0.0008) -[2023-10-12 03:49:00,111][78123] Updated weights for policy 1, policy_version 16930 (0.0008) -[2023-10-12 03:49:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 34766848. Throughput: 0: 1582.9, 1: 1587.2. Samples: 8699402. Policy #0 lag: (min: 12.0, avg: 15.9, max: 44.0) -[2023-10-12 03:49:00,202][77203] Avg episode reward: [(0, '34.560'), (1, '37.830')] -[2023-10-12 03:49:00,473][78123] Updated weights for policy 1, policy_version 16940 (0.0007) -[2023-10-12 03:49:00,841][78123] Updated weights for policy 1, policy_version 16950 (0.0007) -[2023-10-12 03:49:01,208][78123] Updated weights for policy 1, policy_version 16960 (0.0008) -[2023-10-12 03:49:01,540][78091] Updated weights for policy 0, policy_version 17030 (0.0008) -[2023-10-12 03:49:01,917][78091] Updated weights for policy 0, policy_version 17040 (0.0007) -[2023-10-12 03:49:02,278][78091] Updated weights for policy 0, policy_version 17050 (0.0009) -[2023-10-12 03:49:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 34832384. Throughput: 0: 1584.9, 1: 1590.4. Samples: 8719320. Policy #0 lag: (min: 23.0, avg: 25.2, max: 55.0) -[2023-10-12 03:49:05,201][77203] Avg episode reward: [(0, '35.630'), (1, '37.020')] -[2023-10-12 03:49:05,385][78123] Updated weights for policy 1, policy_version 16970 (0.0009) -[2023-10-12 03:49:05,743][78123] Updated weights for policy 1, policy_version 16980 (0.0008) -[2023-10-12 03:49:06,117][78123] Updated weights for policy 1, policy_version 16990 (0.0010) -[2023-10-12 03:49:06,488][78091] Updated weights for policy 0, policy_version 17060 (0.0009) -[2023-10-12 03:49:06,872][78091] Updated weights for policy 0, policy_version 17070 (0.0009) -[2023-10-12 03:49:07,241][78091] Updated weights for policy 0, policy_version 17080 (0.0009) -[2023-10-12 03:49:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 34897920. Throughput: 0: 1592.4, 1: 1600.8. Samples: 8738984. Policy #0 lag: (min: 23.0, avg: 25.2, max: 55.0) -[2023-10-12 03:49:10,201][77203] Avg episode reward: [(0, '39.370'), (1, '43.030')] -[2023-10-12 03:49:10,209][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000017088_17498112.pth... -[2023-10-12 03:49:10,249][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000015616_15990784.pth -[2023-10-12 03:49:10,563][78123] Updated weights for policy 1, policy_version 17000 (0.0010) -[2023-10-12 03:49:10,932][78123] Updated weights for policy 1, policy_version 17010 (0.0007) -[2023-10-12 03:49:11,304][78123] Updated weights for policy 1, policy_version 17020 (0.0007) -[2023-10-12 03:49:11,443][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000017024_17432576.pth... -[2023-10-12 03:49:11,450][78091] Updated weights for policy 0, policy_version 17090 (0.0007) -[2023-10-12 03:49:11,472][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000015520_15892480.pth -[2023-10-12 03:49:11,828][78091] Updated weights for policy 0, policy_version 17100 (0.0007) -[2023-10-12 03:49:12,203][78091] Updated weights for policy 0, policy_version 17110 (0.0008) -[2023-10-12 03:49:12,573][78091] Updated weights for policy 0, policy_version 17120 (0.0008) -[2023-10-12 03:49:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 34963456. Throughput: 0: 1595.0, 1: 1593.2. Samples: 8747816. Policy #0 lag: (min: 23.0, avg: 25.2, max: 55.0) -[2023-10-12 03:49:15,201][77203] Avg episode reward: [(0, '34.840'), (1, '42.150')] -[2023-10-12 03:49:15,629][78123] Updated weights for policy 1, policy_version 17030 (0.0008) -[2023-10-12 03:49:15,993][78123] Updated weights for policy 1, policy_version 17040 (0.0007) -[2023-10-12 03:49:16,357][78123] Updated weights for policy 1, policy_version 17050 (0.0007) -[2023-10-12 03:49:16,785][78091] Updated weights for policy 0, policy_version 17130 (0.0009) -[2023-10-12 03:49:17,159][78091] Updated weights for policy 0, policy_version 17140 (0.0009) -[2023-10-12 03:49:17,536][78091] Updated weights for policy 0, policy_version 17150 (0.0008) -[2023-10-12 03:49:20,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 35028992. Throughput: 0: 1597.8, 1: 1593.8. Samples: 8767598. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-12 03:49:20,202][77203] Avg episode reward: [(0, '34.240'), (1, '41.970')] -[2023-10-12 03:49:20,610][78123] Updated weights for policy 1, policy_version 17060 (0.0009) -[2023-10-12 03:49:20,984][78123] Updated weights for policy 1, policy_version 17070 (0.0008) -[2023-10-12 03:49:21,347][78123] Updated weights for policy 1, policy_version 17080 (0.0008) -[2023-10-12 03:49:21,811][78091] Updated weights for policy 0, policy_version 17160 (0.0008) -[2023-10-12 03:49:22,187][78091] Updated weights for policy 0, policy_version 17170 (0.0007) -[2023-10-12 03:49:22,559][78091] Updated weights for policy 0, policy_version 17180 (0.0009) -[2023-10-12 03:49:25,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 35094528. Throughput: 0: 1598.9, 1: 1597.6. Samples: 8786998. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-12 03:49:25,202][77203] Avg episode reward: [(0, '36.820'), (1, '40.160')] -[2023-10-12 03:49:25,712][78123] Updated weights for policy 1, policy_version 17090 (0.0007) -[2023-10-12 03:49:26,114][78123] Updated weights for policy 1, policy_version 17100 (0.0010) -[2023-10-12 03:49:26,498][78123] Updated weights for policy 1, policy_version 17110 (0.0010) -[2023-10-12 03:49:26,862][78123] Updated weights for policy 1, policy_version 17120 (0.0008) -[2023-10-12 03:49:27,107][78091] Updated weights for policy 0, policy_version 17190 (0.0008) -[2023-10-12 03:49:27,491][78091] Updated weights for policy 0, policy_version 17200 (0.0007) -[2023-10-12 03:49:27,861][78091] Updated weights for policy 0, policy_version 17210 (0.0007) -[2023-10-12 03:49:30,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 35160064. Throughput: 0: 1604.4, 1: 1590.8. Samples: 8795700. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-12 03:49:30,202][77203] Avg episode reward: [(0, '34.910'), (1, '36.940')] -[2023-10-12 03:49:31,012][78123] Updated weights for policy 1, policy_version 17130 (0.0007) -[2023-10-12 03:49:31,372][78123] Updated weights for policy 1, policy_version 17140 (0.0007) -[2023-10-12 03:49:31,742][78123] Updated weights for policy 1, policy_version 17150 (0.0010) -[2023-10-12 03:49:32,040][78091] Updated weights for policy 0, policy_version 17220 (0.0007) -[2023-10-12 03:49:32,407][78091] Updated weights for policy 0, policy_version 17230 (0.0009) -[2023-10-12 03:49:32,784][78091] Updated weights for policy 0, policy_version 17240 (0.0009) -[2023-10-12 03:49:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 35225600. Throughput: 0: 1605.3, 1: 1591.6. Samples: 8815198. Policy #0 lag: (min: 26.0, avg: 36.6, max: 58.0) -[2023-10-12 03:49:35,202][77203] Avg episode reward: [(0, '36.240'), (1, '44.180')] -[2023-10-12 03:49:36,060][78123] Updated weights for policy 1, policy_version 17160 (0.0008) -[2023-10-12 03:49:36,430][78123] Updated weights for policy 1, policy_version 17170 (0.0011) -[2023-10-12 03:49:36,800][78123] Updated weights for policy 1, policy_version 17180 (0.0010) -[2023-10-12 03:49:37,149][78091] Updated weights for policy 0, policy_version 17250 (0.0009) -[2023-10-12 03:49:37,527][78091] Updated weights for policy 0, policy_version 17260 (0.0009) -[2023-10-12 03:49:37,894][78091] Updated weights for policy 0, policy_version 17270 (0.0007) -[2023-10-12 03:49:38,267][78091] Updated weights for policy 0, policy_version 17280 (0.0008) -[2023-10-12 03:49:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12773.9). Total num frames: 35291136. Throughput: 0: 1602.7, 1: 1593.9. Samples: 8834662. Policy #0 lag: (min: 26.0, avg: 36.6, max: 58.0) -[2023-10-12 03:49:40,202][77203] Avg episode reward: [(0, '37.980'), (1, '39.060')] -[2023-10-12 03:49:41,234][78123] Updated weights for policy 1, policy_version 17190 (0.0007) -[2023-10-12 03:49:41,605][78123] Updated weights for policy 1, policy_version 17200 (0.0007) -[2023-10-12 03:49:41,988][78123] Updated weights for policy 1, policy_version 17210 (0.0008) -[2023-10-12 03:49:42,611][78091] Updated weights for policy 0, policy_version 17290 (0.0011) -[2023-10-12 03:49:42,977][78091] Updated weights for policy 0, policy_version 17300 (0.0010) -[2023-10-12 03:49:43,351][78091] Updated weights for policy 0, policy_version 17310 (0.0010) -[2023-10-12 03:49:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 35356672. Throughput: 0: 1617.8, 1: 1591.5. Samples: 8843822. Policy #0 lag: (min: 26.0, avg: 36.6, max: 58.0) -[2023-10-12 03:49:45,202][77203] Avg episode reward: [(0, '37.730'), (1, '40.870')] -[2023-10-12 03:49:46,239][78123] Updated weights for policy 1, policy_version 17220 (0.0008) -[2023-10-12 03:49:46,604][78123] Updated weights for policy 1, policy_version 17230 (0.0010) -[2023-10-12 03:49:46,980][78123] Updated weights for policy 1, policy_version 17240 (0.0009) -[2023-10-12 03:49:47,528][78091] Updated weights for policy 0, policy_version 17320 (0.0010) -[2023-10-12 03:49:47,897][78091] Updated weights for policy 0, policy_version 17330 (0.0007) -[2023-10-12 03:49:48,269][78091] Updated weights for policy 0, policy_version 17340 (0.0010) -[2023-10-12 03:49:50,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 35422208. Throughput: 0: 1601.6, 1: 1588.7. Samples: 8862882. Policy #0 lag: (min: 15.0, avg: 22.9, max: 47.0) -[2023-10-12 03:49:50,202][77203] Avg episode reward: [(0, '37.510'), (1, '45.350')] -[2023-10-12 03:49:50,203][77950] Saving new best policy, reward=45.350! -[2023-10-12 03:49:51,314][78123] Updated weights for policy 1, policy_version 17250 (0.0010) -[2023-10-12 03:49:51,686][78123] Updated weights for policy 1, policy_version 17260 (0.0010) -[2023-10-12 03:49:52,063][78123] Updated weights for policy 1, policy_version 17270 (0.0010) -[2023-10-12 03:49:52,427][78123] Updated weights for policy 1, policy_version 17280 (0.0010) -[2023-10-12 03:49:52,748][78091] Updated weights for policy 0, policy_version 17350 (0.0009) -[2023-10-12 03:49:53,117][78091] Updated weights for policy 0, policy_version 17360 (0.0007) -[2023-10-12 03:49:53,489][78091] Updated weights for policy 0, policy_version 17370 (0.0009) -[2023-10-12 03:49:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 35487744. Throughput: 0: 1590.7, 1: 1594.3. Samples: 8882312. Policy #0 lag: (min: 15.0, avg: 22.9, max: 47.0) -[2023-10-12 03:49:55,202][77203] Avg episode reward: [(0, '40.140'), (1, '42.690')] -[2023-10-12 03:49:56,743][78123] Updated weights for policy 1, policy_version 17290 (0.0010) -[2023-10-12 03:49:57,113][78123] Updated weights for policy 1, policy_version 17300 (0.0010) -[2023-10-12 03:49:57,481][78123] Updated weights for policy 1, policy_version 17310 (0.0010) -[2023-10-12 03:49:57,789][78091] Updated weights for policy 0, policy_version 17380 (0.0009) -[2023-10-12 03:49:58,162][78091] Updated weights for policy 0, policy_version 17390 (0.0007) -[2023-10-12 03:49:58,534][78091] Updated weights for policy 0, policy_version 17400 (0.0008) -[2023-10-12 03:50:00,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 35553280. Throughput: 0: 1613.3, 1: 1593.2. Samples: 8892108. Policy #0 lag: (min: 15.0, avg: 22.9, max: 47.0) -[2023-10-12 03:50:00,201][77203] Avg episode reward: [(0, '38.280'), (1, '41.050')] -[2023-10-12 03:50:01,770][78123] Updated weights for policy 1, policy_version 17320 (0.0008) -[2023-10-12 03:50:02,137][78123] Updated weights for policy 1, policy_version 17330 (0.0007) -[2023-10-12 03:50:02,502][78123] Updated weights for policy 1, policy_version 17340 (0.0007) -[2023-10-12 03:50:02,725][78091] Updated weights for policy 0, policy_version 17410 (0.0009) -[2023-10-12 03:50:03,098][78091] Updated weights for policy 0, policy_version 17420 (0.0008) -[2023-10-12 03:50:03,479][78091] Updated weights for policy 0, policy_version 17430 (0.0009) -[2023-10-12 03:50:03,845][78091] Updated weights for policy 0, policy_version 17440 (0.0009) -[2023-10-12 03:50:05,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 35618816. Throughput: 0: 1591.8, 1: 1597.3. Samples: 8911108. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-12 03:50:05,201][77203] Avg episode reward: [(0, '36.500'), (1, '39.060')] -[2023-10-12 03:50:06,724][78123] Updated weights for policy 1, policy_version 17350 (0.0007) -[2023-10-12 03:50:07,087][78123] Updated weights for policy 1, policy_version 17360 (0.0008) -[2023-10-12 03:50:07,462][78123] Updated weights for policy 1, policy_version 17370 (0.0008) -[2023-10-12 03:50:08,139][78091] Updated weights for policy 0, policy_version 17450 (0.0009) -[2023-10-12 03:50:08,515][78091] Updated weights for policy 0, policy_version 17460 (0.0007) -[2023-10-12 03:50:08,880][78091] Updated weights for policy 0, policy_version 17470 (0.0010) -[2023-10-12 03:50:10,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 35684352. Throughput: 0: 1590.5, 1: 1604.6. Samples: 8930778. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-12 03:50:10,202][77203] Avg episode reward: [(0, '35.520'), (1, '45.080')] -[2023-10-12 03:50:11,686][78123] Updated weights for policy 1, policy_version 17380 (0.0010) -[2023-10-12 03:50:12,081][78123] Updated weights for policy 1, policy_version 17390 (0.0008) -[2023-10-12 03:50:12,448][78123] Updated weights for policy 1, policy_version 17400 (0.0010) -[2023-10-12 03:50:13,283][78091] Updated weights for policy 0, policy_version 17480 (0.0008) -[2023-10-12 03:50:13,654][78091] Updated weights for policy 0, policy_version 17490 (0.0007) -[2023-10-12 03:50:14,022][78091] Updated weights for policy 0, policy_version 17500 (0.0009) -[2023-10-12 03:50:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 35749888. Throughput: 0: 1611.6, 1: 1608.8. Samples: 8940616. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-12 03:50:15,202][77203] Avg episode reward: [(0, '38.390'), (1, '39.370')] -[2023-10-12 03:50:16,808][78123] Updated weights for policy 1, policy_version 17410 (0.0009) -[2023-10-12 03:50:17,171][78123] Updated weights for policy 1, policy_version 17420 (0.0007) -[2023-10-12 03:50:17,542][78123] Updated weights for policy 1, policy_version 17430 (0.0008) -[2023-10-12 03:50:17,905][78123] Updated weights for policy 1, policy_version 17440 (0.0007) -[2023-10-12 03:50:18,252][78091] Updated weights for policy 0, policy_version 17510 (0.0009) -[2023-10-12 03:50:18,614][78091] Updated weights for policy 0, policy_version 17520 (0.0008) -[2023-10-12 03:50:18,991][78091] Updated weights for policy 0, policy_version 17530 (0.0009) -[2023-10-12 03:50:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 35815424. Throughput: 0: 1597.6, 1: 1604.9. Samples: 8959308. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:50:20,201][77203] Avg episode reward: [(0, '33.950'), (1, '36.410')] -[2023-10-12 03:50:22,029][78123] Updated weights for policy 1, policy_version 17450 (0.0008) -[2023-10-12 03:50:22,401][78123] Updated weights for policy 1, policy_version 17460 (0.0008) -[2023-10-12 03:50:22,770][78123] Updated weights for policy 1, policy_version 17470 (0.0010) -[2023-10-12 03:50:23,328][78091] Updated weights for policy 0, policy_version 17540 (0.0008) -[2023-10-12 03:50:23,688][78091] Updated weights for policy 0, policy_version 17550 (0.0011) -[2023-10-12 03:50:24,063][78091] Updated weights for policy 0, policy_version 17560 (0.0010) -[2023-10-12 03:50:25,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 35880960. Throughput: 0: 1590.3, 1: 1608.7. Samples: 8978618. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:50:25,202][77203] Avg episode reward: [(0, '34.920'), (1, '41.140')] -[2023-10-12 03:50:27,224][78123] Updated weights for policy 1, policy_version 17480 (0.0007) -[2023-10-12 03:50:27,593][78123] Updated weights for policy 1, policy_version 17490 (0.0010) -[2023-10-12 03:50:27,973][78123] Updated weights for policy 1, policy_version 17500 (0.0011) -[2023-10-12 03:50:28,211][78091] Updated weights for policy 0, policy_version 17570 (0.0008) -[2023-10-12 03:50:28,585][78091] Updated weights for policy 0, policy_version 17580 (0.0009) -[2023-10-12 03:50:28,956][78091] Updated weights for policy 0, policy_version 17590 (0.0010) -[2023-10-12 03:50:29,327][78091] Updated weights for policy 0, policy_version 17600 (0.0008) -[2023-10-12 03:50:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 35946496. Throughput: 0: 1604.2, 1: 1620.1. Samples: 8988918. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:50:30,201][77203] Avg episode reward: [(0, '36.830'), (1, '38.440')] -[2023-10-12 03:50:32,210][78123] Updated weights for policy 1, policy_version 17510 (0.0008) -[2023-10-12 03:50:32,578][78123] Updated weights for policy 1, policy_version 17520 (0.0010) -[2023-10-12 03:50:32,934][78123] Updated weights for policy 1, policy_version 17530 (0.0011) -[2023-10-12 03:50:33,817][78091] Updated weights for policy 0, policy_version 17610 (0.0009) -[2023-10-12 03:50:34,175][78091] Updated weights for policy 0, policy_version 17620 (0.0009) -[2023-10-12 03:50:34,553][78091] Updated weights for policy 0, policy_version 17630 (0.0009) -[2023-10-12 03:50:35,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 36012032. Throughput: 0: 1607.7, 1: 1609.5. Samples: 9007658. Policy #0 lag: (min: 24.0, avg: 48.5, max: 56.0) -[2023-10-12 03:50:35,201][77203] Avg episode reward: [(0, '36.400'), (1, '40.650')] -[2023-10-12 03:50:37,213][78123] Updated weights for policy 1, policy_version 17540 (0.0009) -[2023-10-12 03:50:37,581][78123] Updated weights for policy 1, policy_version 17550 (0.0009) -[2023-10-12 03:50:37,944][78123] Updated weights for policy 1, policy_version 17560 (0.0007) -[2023-10-12 03:50:38,696][78091] Updated weights for policy 0, policy_version 17640 (0.0009) -[2023-10-12 03:50:39,062][78091] Updated weights for policy 0, policy_version 17650 (0.0011) -[2023-10-12 03:50:39,439][78091] Updated weights for policy 0, policy_version 17660 (0.0009) -[2023-10-12 03:50:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 12885.0). Total num frames: 36077568. Throughput: 0: 1596.5, 1: 1607.0. Samples: 9026470. Policy #0 lag: (min: 24.0, avg: 48.5, max: 56.0) -[2023-10-12 03:50:40,201][77203] Avg episode reward: [(0, '36.390'), (1, '37.740')] -[2023-10-12 03:50:42,392][78123] Updated weights for policy 1, policy_version 17570 (0.0008) -[2023-10-12 03:50:42,764][78123] Updated weights for policy 1, policy_version 17580 (0.0008) -[2023-10-12 03:50:43,122][78123] Updated weights for policy 1, policy_version 17590 (0.0009) -[2023-10-12 03:50:43,493][78123] Updated weights for policy 1, policy_version 17600 (0.0009) -[2023-10-12 03:50:43,802][78091] Updated weights for policy 0, policy_version 17670 (0.0008) -[2023-10-12 03:50:44,165][78091] Updated weights for policy 0, policy_version 17680 (0.0007) -[2023-10-12 03:50:44,544][78091] Updated weights for policy 0, policy_version 17690 (0.0009) -[2023-10-12 03:50:45,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 36143104. Throughput: 0: 1598.6, 1: 1620.6. Samples: 9036974. Policy #0 lag: (min: 24.0, avg: 48.5, max: 56.0) -[2023-10-12 03:50:45,202][77203] Avg episode reward: [(0, '37.070'), (1, '41.140')] -[2023-10-12 03:50:47,695][78123] Updated weights for policy 1, policy_version 17610 (0.0008) -[2023-10-12 03:50:48,060][78123] Updated weights for policy 1, policy_version 17620 (0.0007) -[2023-10-12 03:50:48,435][78123] Updated weights for policy 1, policy_version 17630 (0.0008) -[2023-10-12 03:50:48,841][78091] Updated weights for policy 0, policy_version 17700 (0.0008) -[2023-10-12 03:50:49,209][78091] Updated weights for policy 0, policy_version 17710 (0.0008) -[2023-10-12 03:50:49,594][78091] Updated weights for policy 0, policy_version 17720 (0.0009) -[2023-10-12 03:50:50,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 36208640. Throughput: 0: 1617.1, 1: 1598.9. Samples: 9055832. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:50:50,202][77203] Avg episode reward: [(0, '34.280'), (1, '38.570')] -[2023-10-12 03:50:52,663][78123] Updated weights for policy 1, policy_version 17640 (0.0008) -[2023-10-12 03:50:53,033][78123] Updated weights for policy 1, policy_version 17650 (0.0009) -[2023-10-12 03:50:53,401][78123] Updated weights for policy 1, policy_version 17660 (0.0007) -[2023-10-12 03:50:53,879][78091] Updated weights for policy 0, policy_version 17730 (0.0010) -[2023-10-12 03:50:54,249][78091] Updated weights for policy 0, policy_version 17740 (0.0007) -[2023-10-12 03:50:54,624][78091] Updated weights for policy 0, policy_version 17750 (0.0007) -[2023-10-12 03:50:54,990][78091] Updated weights for policy 0, policy_version 17760 (0.0009) -[2023-10-12 03:50:55,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.3, 300 sec: 12885.1). Total num frames: 36274176. Throughput: 0: 1603.8, 1: 1601.6. Samples: 9075022. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:50:55,201][77203] Avg episode reward: [(0, '34.600'), (1, '39.270')] -[2023-10-12 03:50:57,802][78123] Updated weights for policy 1, policy_version 17670 (0.0007) -[2023-10-12 03:50:58,182][78123] Updated weights for policy 1, policy_version 17680 (0.0009) -[2023-10-12 03:50:58,557][78123] Updated weights for policy 1, policy_version 17690 (0.0008) -[2023-10-12 03:50:59,182][78091] Updated weights for policy 0, policy_version 17770 (0.0010) -[2023-10-12 03:50:59,555][78091] Updated weights for policy 0, policy_version 17780 (0.0010) -[2023-10-12 03:50:59,934][78091] Updated weights for policy 0, policy_version 17790 (0.0010) -[2023-10-12 03:51:00,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 36339712. Throughput: 0: 1601.2, 1: 1620.6. Samples: 9085598. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:51:00,201][77203] Avg episode reward: [(0, '36.270'), (1, '39.270')] -[2023-10-12 03:51:02,891][78123] Updated weights for policy 1, policy_version 17700 (0.0009) -[2023-10-12 03:51:03,265][78123] Updated weights for policy 1, policy_version 17710 (0.0007) -[2023-10-12 03:51:03,627][78123] Updated weights for policy 1, policy_version 17720 (0.0007) -[2023-10-12 03:51:04,312][78091] Updated weights for policy 0, policy_version 17800 (0.0010) -[2023-10-12 03:51:04,693][78091] Updated weights for policy 0, policy_version 17810 (0.0009) -[2023-10-12 03:51:05,065][78091] Updated weights for policy 0, policy_version 17820 (0.0008) -[2023-10-12 03:51:05,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 36372480. Throughput: 0: 1615.3, 1: 1606.2. Samples: 9104274. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:51:05,201][77203] Avg episode reward: [(0, '34.220'), (1, '36.410')] -[2023-10-12 03:51:07,803][78123] Updated weights for policy 1, policy_version 17730 (0.0009) -[2023-10-12 03:51:08,171][78123] Updated weights for policy 1, policy_version 17740 (0.0008) -[2023-10-12 03:51:08,542][78123] Updated weights for policy 1, policy_version 17750 (0.0009) -[2023-10-12 03:51:08,914][78123] Updated weights for policy 1, policy_version 17760 (0.0009) -[2023-10-12 03:51:09,292][78091] Updated weights for policy 0, policy_version 17830 (0.0008) -[2023-10-12 03:51:09,663][78091] Updated weights for policy 0, policy_version 17840 (0.0009) -[2023-10-12 03:51:10,033][78091] Updated weights for policy 0, policy_version 17850 (0.0008) -[2023-10-12 03:51:10,201][77203] Fps is (10 sec: 9830.2, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 36438016. Throughput: 0: 1610.8, 1: 1599.0. Samples: 9123058. Policy #0 lag: (min: 18.0, avg: 26.4, max: 50.0) -[2023-10-12 03:51:10,202][77203] Avg episode reward: [(0, '37.990'), (1, '44.160')] -[2023-10-12 03:51:10,210][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000017760_18186240.pth... -[2023-10-12 03:51:10,246][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000016256_16646144.pth -[2023-10-12 03:51:10,256][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000017856_18284544.pth... -[2023-10-12 03:51:10,296][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000016352_16744448.pth -[2023-10-12 03:51:13,249][78123] Updated weights for policy 1, policy_version 17770 (0.0007) -[2023-10-12 03:51:13,635][78123] Updated weights for policy 1, policy_version 17780 (0.0009) -[2023-10-12 03:51:14,002][78123] Updated weights for policy 1, policy_version 17790 (0.0008) -[2023-10-12 03:51:14,412][78091] Updated weights for policy 0, policy_version 17860 (0.0009) -[2023-10-12 03:51:14,785][78091] Updated weights for policy 0, policy_version 17870 (0.0007) -[2023-10-12 03:51:15,156][78091] Updated weights for policy 0, policy_version 17880 (0.0007) -[2023-10-12 03:51:15,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 36503552. Throughput: 0: 1595.9, 1: 1615.2. Samples: 9133422. Policy #0 lag: (min: 18.0, avg: 26.4, max: 50.0) -[2023-10-12 03:51:15,202][77203] Avg episode reward: [(0, '34.950'), (1, '38.500')] -[2023-10-12 03:51:18,338][78123] Updated weights for policy 1, policy_version 17800 (0.0007) -[2023-10-12 03:51:18,703][78123] Updated weights for policy 1, policy_version 17810 (0.0009) -[2023-10-12 03:51:19,082][78123] Updated weights for policy 1, policy_version 17820 (0.0009) -[2023-10-12 03:51:19,601][78091] Updated weights for policy 0, policy_version 17890 (0.0007) -[2023-10-12 03:51:19,978][78091] Updated weights for policy 0, policy_version 17900 (0.0009) -[2023-10-12 03:51:20,201][77203] Fps is (10 sec: 13107.6, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 36569088. Throughput: 0: 1603.9, 1: 1605.4. Samples: 9152078. Policy #0 lag: (min: 18.0, avg: 26.4, max: 50.0) -[2023-10-12 03:51:20,201][77203] Avg episode reward: [(0, '39.600'), (1, '36.130')] -[2023-10-12 03:51:20,348][78091] Updated weights for policy 0, policy_version 17910 (0.0009) -[2023-10-12 03:51:20,711][78091] Updated weights for policy 0, policy_version 17920 (0.0011) -[2023-10-12 03:51:23,022][78123] Updated weights for policy 1, policy_version 17830 (0.0010) -[2023-10-12 03:51:23,395][78123] Updated weights for policy 1, policy_version 17840 (0.0010) -[2023-10-12 03:51:23,766][78123] Updated weights for policy 1, policy_version 17850 (0.0007) -[2023-10-12 03:51:25,070][78091] Updated weights for policy 0, policy_version 17930 (0.0009) -[2023-10-12 03:51:25,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12773.9). Total num frames: 36634624. Throughput: 0: 1613.8, 1: 1602.2. Samples: 9171192. Policy #0 lag: (min: 22.0, avg: 22.2, max: 31.0) -[2023-10-12 03:51:25,203][77203] Avg episode reward: [(0, '34.310'), (1, '40.370')] -[2023-10-12 03:51:25,440][78091] Updated weights for policy 0, policy_version 17940 (0.0010) -[2023-10-12 03:51:25,815][78091] Updated weights for policy 0, policy_version 17950 (0.0010) -[2023-10-12 03:51:28,053][78123] Updated weights for policy 1, policy_version 17860 (0.0008) -[2023-10-12 03:51:28,416][78123] Updated weights for policy 1, policy_version 17870 (0.0007) -[2023-10-12 03:51:28,789][78123] Updated weights for policy 1, policy_version 17880 (0.0008) -[2023-10-12 03:51:30,180][78091] Updated weights for policy 0, policy_version 17960 (0.0009) -[2023-10-12 03:51:30,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 36700160. Throughput: 0: 1587.5, 1: 1614.9. Samples: 9181082. Policy #0 lag: (min: 22.0, avg: 22.2, max: 31.0) -[2023-10-12 03:51:30,202][77203] Avg episode reward: [(0, '37.380'), (1, '35.190')] -[2023-10-12 03:51:30,540][78091] Updated weights for policy 0, policy_version 17970 (0.0010) -[2023-10-12 03:51:30,907][78091] Updated weights for policy 0, policy_version 17980 (0.0010) -[2023-10-12 03:51:33,131][78123] Updated weights for policy 1, policy_version 17890 (0.0010) -[2023-10-12 03:51:33,492][78123] Updated weights for policy 1, policy_version 17900 (0.0008) -[2023-10-12 03:51:33,866][78123] Updated weights for policy 1, policy_version 17910 (0.0007) -[2023-10-12 03:51:34,234][78123] Updated weights for policy 1, policy_version 17920 (0.0008) -[2023-10-12 03:51:35,194][78091] Updated weights for policy 0, policy_version 17990 (0.0010) -[2023-10-12 03:51:35,201][77203] Fps is (10 sec: 13107.7, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 36765696. Throughput: 0: 1587.7, 1: 1623.7. Samples: 9200348. Policy #0 lag: (min: 22.0, avg: 22.2, max: 31.0) -[2023-10-12 03:51:35,202][77203] Avg episode reward: [(0, '35.010'), (1, '37.190')] -[2023-10-12 03:51:35,567][78091] Updated weights for policy 0, policy_version 18000 (0.0009) -[2023-10-12 03:51:35,945][78091] Updated weights for policy 0, policy_version 18010 (0.0009) -[2023-10-12 03:51:38,438][78123] Updated weights for policy 1, policy_version 17930 (0.0007) -[2023-10-12 03:51:38,809][78123] Updated weights for policy 1, policy_version 17940 (0.0008) -[2023-10-12 03:51:39,180][78123] Updated weights for policy 1, policy_version 17950 (0.0008) -[2023-10-12 03:51:40,184][78091] Updated weights for policy 0, policy_version 18020 (0.0009) -[2023-10-12 03:51:40,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 36831232. Throughput: 0: 1606.3, 1: 1607.1. Samples: 9219626. Policy #0 lag: (min: 24.0, avg: 41.2, max: 56.0) -[2023-10-12 03:51:40,201][77203] Avg episode reward: [(0, '36.040'), (1, '41.730')] -[2023-10-12 03:51:40,546][78091] Updated weights for policy 0, policy_version 18030 (0.0009) -[2023-10-12 03:51:40,927][78091] Updated weights for policy 0, policy_version 18040 (0.0008) -[2023-10-12 03:51:43,657][78123] Updated weights for policy 1, policy_version 17960 (0.0007) -[2023-10-12 03:51:44,023][78123] Updated weights for policy 1, policy_version 17970 (0.0008) -[2023-10-12 03:51:44,405][78123] Updated weights for policy 1, policy_version 17980 (0.0010) -[2023-10-12 03:51:45,165][78091] Updated weights for policy 0, policy_version 18050 (0.0010) -[2023-10-12 03:51:45,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 36896768. Throughput: 0: 1584.9, 1: 1613.8. Samples: 9229540. Policy #0 lag: (min: 24.0, avg: 41.2, max: 56.0) -[2023-10-12 03:51:45,201][77203] Avg episode reward: [(0, '31.850'), (1, '39.470')] -[2023-10-12 03:51:45,550][78091] Updated weights for policy 0, policy_version 18060 (0.0009) -[2023-10-12 03:51:45,916][78091] Updated weights for policy 0, policy_version 18070 (0.0009) -[2023-10-12 03:51:46,298][78091] Updated weights for policy 0, policy_version 18080 (0.0008) -[2023-10-12 03:51:48,604][78123] Updated weights for policy 1, policy_version 17990 (0.0009) -[2023-10-12 03:51:48,968][78123] Updated weights for policy 1, policy_version 18000 (0.0007) -[2023-10-12 03:51:49,333][78123] Updated weights for policy 1, policy_version 18010 (0.0009) -[2023-10-12 03:51:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 36962304. Throughput: 0: 1591.2, 1: 1623.0. Samples: 9248914. Policy #0 lag: (min: 24.0, avg: 41.2, max: 56.0) -[2023-10-12 03:51:50,202][77203] Avg episode reward: [(0, '32.630'), (1, '41.690')] -[2023-10-12 03:51:50,475][78091] Updated weights for policy 0, policy_version 18090 (0.0010) -[2023-10-12 03:51:50,840][78091] Updated weights for policy 0, policy_version 18100 (0.0010) -[2023-10-12 03:51:51,217][78091] Updated weights for policy 0, policy_version 18110 (0.0008) -[2023-10-12 03:51:53,543][78123] Updated weights for policy 1, policy_version 18020 (0.0010) -[2023-10-12 03:51:53,907][78123] Updated weights for policy 1, policy_version 18030 (0.0010) -[2023-10-12 03:51:54,274][78123] Updated weights for policy 1, policy_version 18040 (0.0007) -[2023-10-12 03:51:55,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 37027840. Throughput: 0: 1602.5, 1: 1610.2. Samples: 9267630. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:51:55,202][77203] Avg episode reward: [(0, '33.340'), (1, '42.070')] -[2023-10-12 03:51:55,596][78091] Updated weights for policy 0, policy_version 18120 (0.0009) -[2023-10-12 03:51:55,967][78091] Updated weights for policy 0, policy_version 18130 (0.0007) -[2023-10-12 03:51:56,341][78091] Updated weights for policy 0, policy_version 18140 (0.0007) -[2023-10-12 03:51:58,428][78123] Updated weights for policy 1, policy_version 18050 (0.0007) -[2023-10-12 03:51:58,795][78123] Updated weights for policy 1, policy_version 18060 (0.0009) -[2023-10-12 03:51:59,159][78123] Updated weights for policy 1, policy_version 18070 (0.0010) -[2023-10-12 03:51:59,528][78123] Updated weights for policy 1, policy_version 18080 (0.0009) -[2023-10-12 03:52:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 37093376. Throughput: 0: 1588.0, 1: 1611.7. Samples: 9277412. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:52:00,202][77203] Avg episode reward: [(0, '32.550'), (1, '37.420')] -[2023-10-12 03:52:00,790][78091] Updated weights for policy 0, policy_version 18150 (0.0009) -[2023-10-12 03:52:01,162][78091] Updated weights for policy 0, policy_version 18160 (0.0011) -[2023-10-12 03:52:01,530][78091] Updated weights for policy 0, policy_version 18170 (0.0008) -[2023-10-12 03:52:03,916][78123] Updated weights for policy 1, policy_version 18090 (0.0009) -[2023-10-12 03:52:04,290][78123] Updated weights for policy 1, policy_version 18100 (0.0009) -[2023-10-12 03:52:04,662][78123] Updated weights for policy 1, policy_version 18110 (0.0008) -[2023-10-12 03:52:05,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 37158912. Throughput: 0: 1591.6, 1: 1624.8. Samples: 9296820. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:52:05,201][77203] Avg episode reward: [(0, '36.790'), (1, '39.230')] -[2023-10-12 03:52:05,830][78091] Updated weights for policy 0, policy_version 18180 (0.0007) -[2023-10-12 03:52:06,201][78091] Updated weights for policy 0, policy_version 18190 (0.0008) -[2023-10-12 03:52:06,575][78091] Updated weights for policy 0, policy_version 18200 (0.0008) -[2023-10-12 03:52:08,994][78123] Updated weights for policy 1, policy_version 18120 (0.0007) -[2023-10-12 03:52:09,359][78123] Updated weights for policy 1, policy_version 18130 (0.0007) -[2023-10-12 03:52:09,733][78123] Updated weights for policy 1, policy_version 18140 (0.0007) -[2023-10-12 03:52:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 37224448. Throughput: 0: 1599.9, 1: 1610.5. Samples: 9315660. Policy #0 lag: (min: 16.0, avg: 41.3, max: 48.0) -[2023-10-12 03:52:10,201][77203] Avg episode reward: [(0, '33.430'), (1, '40.880')] -[2023-10-12 03:52:10,746][78091] Updated weights for policy 0, policy_version 18210 (0.0010) -[2023-10-12 03:52:11,130][78091] Updated weights for policy 0, policy_version 18220 (0.0009) -[2023-10-12 03:52:11,501][78091] Updated weights for policy 0, policy_version 18230 (0.0009) -[2023-10-12 03:52:11,871][78091] Updated weights for policy 0, policy_version 18240 (0.0009) -[2023-10-12 03:52:13,944][78123] Updated weights for policy 1, policy_version 18150 (0.0010) -[2023-10-12 03:52:14,320][78123] Updated weights for policy 1, policy_version 18160 (0.0010) -[2023-10-12 03:52:14,698][78123] Updated weights for policy 1, policy_version 18170 (0.0009) -[2023-10-12 03:52:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 37289984. Throughput: 0: 1596.0, 1: 1607.9. Samples: 9325258. Policy #0 lag: (min: 16.0, avg: 41.3, max: 48.0) -[2023-10-12 03:52:15,201][77203] Avg episode reward: [(0, '34.030'), (1, '35.860')] -[2023-10-12 03:52:16,261][78091] Updated weights for policy 0, policy_version 18250 (0.0007) -[2023-10-12 03:52:16,637][78091] Updated weights for policy 0, policy_version 18260 (0.0009) -[2023-10-12 03:52:17,005][78091] Updated weights for policy 0, policy_version 18270 (0.0008) -[2023-10-12 03:52:18,934][78123] Updated weights for policy 1, policy_version 18180 (0.0008) -[2023-10-12 03:52:19,301][78123] Updated weights for policy 1, policy_version 18190 (0.0008) -[2023-10-12 03:52:19,672][78123] Updated weights for policy 1, policy_version 18200 (0.0008) -[2023-10-12 03:52:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 37355520. Throughput: 0: 1599.0, 1: 1619.0. Samples: 9345160. Policy #0 lag: (min: 16.0, avg: 41.3, max: 48.0) -[2023-10-12 03:52:20,201][77203] Avg episode reward: [(0, '35.740'), (1, '39.610')] -[2023-10-12 03:52:21,338][78091] Updated weights for policy 0, policy_version 18280 (0.0010) -[2023-10-12 03:52:21,718][78091] Updated weights for policy 0, policy_version 18290 (0.0009) -[2023-10-12 03:52:22,093][78091] Updated weights for policy 0, policy_version 18300 (0.0008) -[2023-10-12 03:52:23,924][78123] Updated weights for policy 1, policy_version 18210 (0.0007) -[2023-10-12 03:52:24,295][78123] Updated weights for policy 1, policy_version 18220 (0.0009) -[2023-10-12 03:52:24,667][78123] Updated weights for policy 1, policy_version 18230 (0.0010) -[2023-10-12 03:52:25,027][78123] Updated weights for policy 1, policy_version 18240 (0.0009) -[2023-10-12 03:52:25,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 37421056. Throughput: 0: 1600.7, 1: 1608.5. Samples: 9364038. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 03:52:25,202][77203] Avg episode reward: [(0, '33.890'), (1, '37.100')] -[2023-10-12 03:52:26,143][78091] Updated weights for policy 0, policy_version 18310 (0.0008) -[2023-10-12 03:52:26,506][78091] Updated weights for policy 0, policy_version 18320 (0.0007) -[2023-10-12 03:52:26,878][78091] Updated weights for policy 0, policy_version 18330 (0.0010) -[2023-10-12 03:52:29,550][78123] Updated weights for policy 1, policy_version 18250 (0.0010) -[2023-10-12 03:52:29,932][78123] Updated weights for policy 1, policy_version 18260 (0.0009) -[2023-10-12 03:52:30,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 37453824. Throughput: 0: 1599.3, 1: 1601.5. Samples: 9373576. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 03:52:30,201][77203] Avg episode reward: [(0, '35.160'), (1, '38.020')] -[2023-10-12 03:52:30,305][78123] Updated weights for policy 1, policy_version 18270 (0.0007) -[2023-10-12 03:52:31,128][78091] Updated weights for policy 0, policy_version 18340 (0.0007) -[2023-10-12 03:52:31,513][78091] Updated weights for policy 0, policy_version 18350 (0.0008) -[2023-10-12 03:52:31,883][78091] Updated weights for policy 0, policy_version 18360 (0.0010) -[2023-10-12 03:52:34,763][78123] Updated weights for policy 1, policy_version 18280 (0.0008) -[2023-10-12 03:52:35,135][78123] Updated weights for policy 1, policy_version 18290 (0.0009) -[2023-10-12 03:52:35,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 37519360. Throughput: 0: 1595.4, 1: 1605.2. Samples: 9392944. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 03:52:35,202][77203] Avg episode reward: [(0, '38.200'), (1, '39.630')] -[2023-10-12 03:52:35,495][78123] Updated weights for policy 1, policy_version 18300 (0.0009) -[2023-10-12 03:52:36,273][78091] Updated weights for policy 0, policy_version 18370 (0.0008) -[2023-10-12 03:52:36,635][78091] Updated weights for policy 0, policy_version 18380 (0.0007) -[2023-10-12 03:52:37,016][78091] Updated weights for policy 0, policy_version 18390 (0.0007) -[2023-10-12 03:52:37,389][78091] Updated weights for policy 0, policy_version 18400 (0.0007) -[2023-10-12 03:52:39,608][78123] Updated weights for policy 1, policy_version 18310 (0.0008) -[2023-10-12 03:52:39,974][78123] Updated weights for policy 1, policy_version 18320 (0.0007) -[2023-10-12 03:52:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 37584896. Throughput: 0: 1598.0, 1: 1615.9. Samples: 9412258. Policy #0 lag: (min: 31.0, avg: 31.7, max: 49.0) -[2023-10-12 03:52:40,201][77203] Avg episode reward: [(0, '32.120'), (1, '33.700')] -[2023-10-12 03:52:40,350][78123] Updated weights for policy 1, policy_version 18330 (0.0008) -[2023-10-12 03:52:41,829][78091] Updated weights for policy 0, policy_version 18410 (0.0008) -[2023-10-12 03:52:42,207][78091] Updated weights for policy 0, policy_version 18420 (0.0009) -[2023-10-12 03:52:42,584][78091] Updated weights for policy 0, policy_version 18430 (0.0011) -[2023-10-12 03:52:44,797][78123] Updated weights for policy 1, policy_version 18340 (0.0009) -[2023-10-12 03:52:45,173][78123] Updated weights for policy 1, policy_version 18350 (0.0010) -[2023-10-12 03:52:45,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 37650432. Throughput: 0: 1598.6, 1: 1594.1. Samples: 9421086. Policy #0 lag: (min: 31.0, avg: 31.7, max: 49.0) -[2023-10-12 03:52:45,202][77203] Avg episode reward: [(0, '37.240'), (1, '36.550')] -[2023-10-12 03:52:45,541][78123] Updated weights for policy 1, policy_version 18360 (0.0008) -[2023-10-12 03:52:46,792][78091] Updated weights for policy 0, policy_version 18440 (0.0008) -[2023-10-12 03:52:47,171][78091] Updated weights for policy 0, policy_version 18450 (0.0007) -[2023-10-12 03:52:47,538][78091] Updated weights for policy 0, policy_version 18460 (0.0008) -[2023-10-12 03:52:49,813][78123] Updated weights for policy 1, policy_version 18370 (0.0008) -[2023-10-12 03:52:50,182][78123] Updated weights for policy 1, policy_version 18380 (0.0008) -[2023-10-12 03:52:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 37715968. Throughput: 0: 1596.3, 1: 1597.3. Samples: 9440532. Policy #0 lag: (min: 31.0, avg: 31.7, max: 49.0) -[2023-10-12 03:52:50,201][77203] Avg episode reward: [(0, '37.650'), (1, '36.740')] -[2023-10-12 03:52:50,539][78123] Updated weights for policy 1, policy_version 18390 (0.0009) -[2023-10-12 03:52:50,906][78123] Updated weights for policy 1, policy_version 18400 (0.0008) -[2023-10-12 03:52:51,965][78091] Updated weights for policy 0, policy_version 18470 (0.0008) -[2023-10-12 03:52:52,328][78091] Updated weights for policy 0, policy_version 18480 (0.0010) -[2023-10-12 03:52:52,705][78091] Updated weights for policy 0, policy_version 18490 (0.0008) -[2023-10-12 03:52:55,130][78123] Updated weights for policy 1, policy_version 18410 (0.0008) -[2023-10-12 03:52:55,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 37781504. Throughput: 0: 1592.5, 1: 1623.8. Samples: 9460394. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:52:55,201][77203] Avg episode reward: [(0, '33.730'), (1, '36.620')] -[2023-10-12 03:52:55,499][78123] Updated weights for policy 1, policy_version 18420 (0.0008) -[2023-10-12 03:52:55,865][78123] Updated weights for policy 1, policy_version 18430 (0.0008) -[2023-10-12 03:52:57,023][78091] Updated weights for policy 0, policy_version 18500 (0.0009) -[2023-10-12 03:52:57,388][78091] Updated weights for policy 0, policy_version 18510 (0.0007) -[2023-10-12 03:52:57,761][78091] Updated weights for policy 0, policy_version 18520 (0.0008) -[2023-10-12 03:53:00,190][78123] Updated weights for policy 1, policy_version 18440 (0.0009) -[2023-10-12 03:53:00,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 37847040. Throughput: 0: 1603.0, 1: 1599.5. Samples: 9469368. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:53:00,201][77203] Avg episode reward: [(0, '37.780'), (1, '39.120')] -[2023-10-12 03:53:00,556][78123] Updated weights for policy 1, policy_version 18450 (0.0007) -[2023-10-12 03:53:00,925][78123] Updated weights for policy 1, policy_version 18460 (0.0007) -[2023-10-12 03:53:02,005][78091] Updated weights for policy 0, policy_version 18530 (0.0007) -[2023-10-12 03:53:02,375][78091] Updated weights for policy 0, policy_version 18540 (0.0010) -[2023-10-12 03:53:02,743][78091] Updated weights for policy 0, policy_version 18550 (0.0009) -[2023-10-12 03:53:03,119][78091] Updated weights for policy 0, policy_version 18560 (0.0008) -[2023-10-12 03:53:05,058][78123] Updated weights for policy 1, policy_version 18470 (0.0007) -[2023-10-12 03:53:05,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 37912576. Throughput: 0: 1593.8, 1: 1599.0. Samples: 9488836. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:53:05,202][77203] Avg episode reward: [(0, '36.080'), (1, '35.630')] -[2023-10-12 03:53:05,417][78123] Updated weights for policy 1, policy_version 18480 (0.0007) -[2023-10-12 03:53:05,794][78123] Updated weights for policy 1, policy_version 18490 (0.0007) -[2023-10-12 03:53:07,575][78091] Updated weights for policy 0, policy_version 18570 (0.0011) -[2023-10-12 03:53:07,950][78091] Updated weights for policy 0, policy_version 18580 (0.0010) -[2023-10-12 03:53:08,324][78091] Updated weights for policy 0, policy_version 18590 (0.0008) -[2023-10-12 03:53:10,072][78123] Updated weights for policy 1, policy_version 18500 (0.0008) -[2023-10-12 03:53:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 37978112. Throughput: 0: 1587.5, 1: 1618.7. Samples: 9508318. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-12 03:53:10,201][77203] Avg episode reward: [(0, '37.950'), (1, '40.000')] -[2023-10-12 03:53:10,209][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000018592_19038208.pth... -[2023-10-12 03:53:10,241][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000017088_17498112.pth -[2023-10-12 03:53:10,441][78123] Updated weights for policy 1, policy_version 18510 (0.0011) -[2023-10-12 03:53:10,816][78123] Updated weights for policy 1, policy_version 18520 (0.0007) -[2023-10-12 03:53:11,104][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000018528_18972672.pth... -[2023-10-12 03:53:11,142][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000017024_17432576.pth -[2023-10-12 03:53:12,527][78091] Updated weights for policy 0, policy_version 18600 (0.0010) -[2023-10-12 03:53:12,894][78091] Updated weights for policy 0, policy_version 18610 (0.0010) -[2023-10-12 03:53:13,259][78091] Updated weights for policy 0, policy_version 18620 (0.0010) -[2023-10-12 03:53:15,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 38043648. Throughput: 0: 1601.0, 1: 1598.8. Samples: 9517568. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-12 03:53:15,201][77203] Avg episode reward: [(0, '38.980'), (1, '37.060')] -[2023-10-12 03:53:15,214][78123] Updated weights for policy 1, policy_version 18530 (0.0008) -[2023-10-12 03:53:15,602][78123] Updated weights for policy 1, policy_version 18540 (0.0008) -[2023-10-12 03:53:15,966][78123] Updated weights for policy 1, policy_version 18550 (0.0009) -[2023-10-12 03:53:16,328][78123] Updated weights for policy 1, policy_version 18560 (0.0008) -[2023-10-12 03:53:17,698][78091] Updated weights for policy 0, policy_version 18630 (0.0008) -[2023-10-12 03:53:18,068][78091] Updated weights for policy 0, policy_version 18640 (0.0007) -[2023-10-12 03:53:18,441][78091] Updated weights for policy 0, policy_version 18650 (0.0008) -[2023-10-12 03:53:20,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12885.0). Total num frames: 38109184. Throughput: 0: 1586.5, 1: 1599.2. Samples: 9536302. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-12 03:53:20,202][77203] Avg episode reward: [(0, '35.010'), (1, '35.720')] -[2023-10-12 03:53:20,637][78123] Updated weights for policy 1, policy_version 18570 (0.0007) -[2023-10-12 03:53:20,996][78123] Updated weights for policy 1, policy_version 18580 (0.0008) -[2023-10-12 03:53:21,364][78123] Updated weights for policy 1, policy_version 18590 (0.0008) -[2023-10-12 03:53:22,846][78091] Updated weights for policy 0, policy_version 18660 (0.0008) -[2023-10-12 03:53:23,254][78091] Updated weights for policy 0, policy_version 18670 (0.0008) -[2023-10-12 03:53:23,620][78091] Updated weights for policy 0, policy_version 18680 (0.0009) -[2023-10-12 03:53:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12885.0). Total num frames: 38174720. Throughput: 0: 1584.0, 1: 1602.7. Samples: 9555660. Policy #0 lag: (min: 11.0, avg: 20.3, max: 43.0) -[2023-10-12 03:53:25,201][77203] Avg episode reward: [(0, '35.850'), (1, '36.520')] -[2023-10-12 03:53:25,724][78123] Updated weights for policy 1, policy_version 18600 (0.0007) -[2023-10-12 03:53:26,088][78123] Updated weights for policy 1, policy_version 18610 (0.0008) -[2023-10-12 03:53:26,463][78123] Updated weights for policy 1, policy_version 18620 (0.0009) -[2023-10-12 03:53:27,933][78091] Updated weights for policy 0, policy_version 18690 (0.0008) -[2023-10-12 03:53:28,303][78091] Updated weights for policy 0, policy_version 18700 (0.0009) -[2023-10-12 03:53:28,683][78091] Updated weights for policy 0, policy_version 18710 (0.0008) -[2023-10-12 03:53:29,051][78091] Updated weights for policy 0, policy_version 18720 (0.0009) -[2023-10-12 03:53:30,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 38240256. Throughput: 0: 1609.9, 1: 1600.1. Samples: 9565534. Policy #0 lag: (min: 11.0, avg: 20.3, max: 43.0) -[2023-10-12 03:53:30,201][77203] Avg episode reward: [(0, '37.510'), (1, '37.150')] -[2023-10-12 03:53:30,824][78123] Updated weights for policy 1, policy_version 18630 (0.0007) -[2023-10-12 03:53:31,189][78123] Updated weights for policy 1, policy_version 18640 (0.0008) -[2023-10-12 03:53:31,561][78123] Updated weights for policy 1, policy_version 18650 (0.0009) -[2023-10-12 03:53:33,385][78091] Updated weights for policy 0, policy_version 18730 (0.0008) -[2023-10-12 03:53:33,746][78091] Updated weights for policy 0, policy_version 18740 (0.0008) -[2023-10-12 03:53:34,128][78091] Updated weights for policy 0, policy_version 18750 (0.0008) -[2023-10-12 03:53:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 38305792. Throughput: 0: 1594.2, 1: 1602.0. Samples: 9584362. Policy #0 lag: (min: 11.0, avg: 20.3, max: 43.0) -[2023-10-12 03:53:35,201][77203] Avg episode reward: [(0, '36.300'), (1, '39.980')] -[2023-10-12 03:53:35,925][78123] Updated weights for policy 1, policy_version 18660 (0.0009) -[2023-10-12 03:53:36,289][78123] Updated weights for policy 1, policy_version 18670 (0.0008) -[2023-10-12 03:53:36,651][78123] Updated weights for policy 1, policy_version 18680 (0.0008) -[2023-10-12 03:53:38,440][78091] Updated weights for policy 0, policy_version 18760 (0.0009) -[2023-10-12 03:53:38,812][78091] Updated weights for policy 0, policy_version 18770 (0.0010) -[2023-10-12 03:53:39,189][78091] Updated weights for policy 0, policy_version 18780 (0.0010) -[2023-10-12 03:53:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 38371328. Throughput: 0: 1583.5, 1: 1596.7. Samples: 9603502. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:53:40,201][77203] Avg episode reward: [(0, '36.340'), (1, '37.390')] -[2023-10-12 03:53:40,712][78123] Updated weights for policy 1, policy_version 18690 (0.0007) -[2023-10-12 03:53:41,071][78123] Updated weights for policy 1, policy_version 18700 (0.0009) -[2023-10-12 03:53:41,443][78123] Updated weights for policy 1, policy_version 18710 (0.0007) -[2023-10-12 03:53:41,810][78123] Updated weights for policy 1, policy_version 18720 (0.0008) -[2023-10-12 03:53:43,442][78091] Updated weights for policy 0, policy_version 18790 (0.0009) -[2023-10-12 03:53:43,815][78091] Updated weights for policy 0, policy_version 18800 (0.0008) -[2023-10-12 03:53:44,178][78091] Updated weights for policy 0, policy_version 18810 (0.0010) -[2023-10-12 03:53:45,201][77203] Fps is (10 sec: 13106.7, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 38436864. Throughput: 0: 1601.9, 1: 1596.9. Samples: 9613314. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:53:45,202][77203] Avg episode reward: [(0, '38.560'), (1, '40.270')] -[2023-10-12 03:53:46,207][78123] Updated weights for policy 1, policy_version 18730 (0.0008) -[2023-10-12 03:53:46,571][78123] Updated weights for policy 1, policy_version 18740 (0.0007) -[2023-10-12 03:53:46,942][78123] Updated weights for policy 1, policy_version 18750 (0.0009) -[2023-10-12 03:53:48,414][78091] Updated weights for policy 0, policy_version 18820 (0.0007) -[2023-10-12 03:53:48,789][78091] Updated weights for policy 0, policy_version 18830 (0.0009) -[2023-10-12 03:53:49,170][78091] Updated weights for policy 0, policy_version 18840 (0.0008) -[2023-10-12 03:53:50,201][77203] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 12885.0). Total num frames: 38502400. Throughput: 0: 1598.5, 1: 1592.6. Samples: 9632438. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:53:50,202][77203] Avg episode reward: [(0, '36.760'), (1, '39.320')] -[2023-10-12 03:53:51,144][78123] Updated weights for policy 1, policy_version 18760 (0.0008) -[2023-10-12 03:53:51,521][78123] Updated weights for policy 1, policy_version 18770 (0.0010) -[2023-10-12 03:53:51,880][78123] Updated weights for policy 1, policy_version 18780 (0.0009) -[2023-10-12 03:53:53,380][78091] Updated weights for policy 0, policy_version 18850 (0.0009) -[2023-10-12 03:53:53,760][78091] Updated weights for policy 0, policy_version 18860 (0.0008) -[2023-10-12 03:53:54,130][78091] Updated weights for policy 0, policy_version 18870 (0.0010) -[2023-10-12 03:53:54,505][78091] Updated weights for policy 0, policy_version 18880 (0.0009) -[2023-10-12 03:53:55,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 38567936. Throughput: 0: 1588.5, 1: 1590.5. Samples: 9651376. Policy #0 lag: (min: 23.0, avg: 30.1, max: 55.0) -[2023-10-12 03:53:55,202][77203] Avg episode reward: [(0, '37.260'), (1, '37.960')] -[2023-10-12 03:53:56,258][78123] Updated weights for policy 1, policy_version 18790 (0.0009) -[2023-10-12 03:53:56,635][78123] Updated weights for policy 1, policy_version 18800 (0.0008) -[2023-10-12 03:53:57,011][78123] Updated weights for policy 1, policy_version 18810 (0.0009) -[2023-10-12 03:53:58,793][78091] Updated weights for policy 0, policy_version 18890 (0.0010) -[2023-10-12 03:53:59,163][78091] Updated weights for policy 0, policy_version 18900 (0.0010) -[2023-10-12 03:53:59,538][78091] Updated weights for policy 0, policy_version 18910 (0.0009) -[2023-10-12 03:54:00,201][77203] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 38633472. Throughput: 0: 1597.4, 1: 1587.5. Samples: 9660888. Policy #0 lag: (min: 23.0, avg: 30.1, max: 55.0) -[2023-10-12 03:54:00,201][77203] Avg episode reward: [(0, '37.540'), (1, '38.270')] -[2023-10-12 03:54:01,314][78123] Updated weights for policy 1, policy_version 18820 (0.0008) -[2023-10-12 03:54:01,696][78123] Updated weights for policy 1, policy_version 18830 (0.0007) -[2023-10-12 03:54:02,077][78123] Updated weights for policy 1, policy_version 18840 (0.0008) -[2023-10-12 03:54:03,943][78091] Updated weights for policy 0, policy_version 18920 (0.0007) -[2023-10-12 03:54:04,322][78091] Updated weights for policy 0, policy_version 18930 (0.0008) -[2023-10-12 03:54:04,688][78091] Updated weights for policy 0, policy_version 18940 (0.0007) -[2023-10-12 03:54:05,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.3, 300 sec: 12885.0). Total num frames: 38699008. Throughput: 0: 1612.7, 1: 1585.2. Samples: 9680206. Policy #0 lag: (min: 23.0, avg: 30.1, max: 55.0) -[2023-10-12 03:54:05,201][77203] Avg episode reward: [(0, '38.020'), (1, '42.590')] -[2023-10-12 03:54:06,603][78123] Updated weights for policy 1, policy_version 18850 (0.0008) -[2023-10-12 03:54:06,976][78123] Updated weights for policy 1, policy_version 18860 (0.0007) -[2023-10-12 03:54:07,342][78123] Updated weights for policy 1, policy_version 18870 (0.0007) -[2023-10-12 03:54:07,696][78123] Updated weights for policy 1, policy_version 18880 (0.0008) -[2023-10-12 03:54:08,951][78091] Updated weights for policy 0, policy_version 18950 (0.0009) -[2023-10-12 03:54:09,337][78091] Updated weights for policy 0, policy_version 18960 (0.0009) -[2023-10-12 03:54:09,709][78091] Updated weights for policy 0, policy_version 18970 (0.0009) -[2023-10-12 03:54:10,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 38764544. Throughput: 0: 1592.9, 1: 1587.7. Samples: 9698790. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) -[2023-10-12 03:54:10,202][77203] Avg episode reward: [(0, '34.320'), (1, '34.160')] -[2023-10-12 03:54:12,012][78123] Updated weights for policy 1, policy_version 18890 (0.0007) -[2023-10-12 03:54:12,385][78123] Updated weights for policy 1, policy_version 18900 (0.0008) -[2023-10-12 03:54:12,760][78123] Updated weights for policy 1, policy_version 18910 (0.0008) -[2023-10-12 03:54:13,957][78091] Updated weights for policy 0, policy_version 18980 (0.0008) -[2023-10-12 03:54:14,319][78091] Updated weights for policy 0, policy_version 18990 (0.0008) -[2023-10-12 03:54:14,694][78091] Updated weights for policy 0, policy_version 19000 (0.0008) -[2023-10-12 03:54:15,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 38830080. Throughput: 0: 1591.5, 1: 1587.4. Samples: 9708584. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) -[2023-10-12 03:54:15,202][77203] Avg episode reward: [(0, '37.990'), (1, '38.490')] -[2023-10-12 03:54:17,257][78123] Updated weights for policy 1, policy_version 18920 (0.0010) -[2023-10-12 03:54:17,619][78123] Updated weights for policy 1, policy_version 18930 (0.0009) -[2023-10-12 03:54:17,986][78123] Updated weights for policy 1, policy_version 18940 (0.0011) -[2023-10-12 03:54:18,983][78091] Updated weights for policy 0, policy_version 19010 (0.0009) -[2023-10-12 03:54:19,362][78091] Updated weights for policy 0, policy_version 19020 (0.0010) -[2023-10-12 03:54:19,731][78091] Updated weights for policy 0, policy_version 19030 (0.0008) -[2023-10-12 03:54:20,102][78091] Updated weights for policy 0, policy_version 19040 (0.0008) -[2023-10-12 03:54:20,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 38895616. Throughput: 0: 1609.9, 1: 1578.7. Samples: 9727850. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) -[2023-10-12 03:54:20,202][77203] Avg episode reward: [(0, '33.470'), (1, '41.360')] -[2023-10-12 03:54:22,135][78123] Updated weights for policy 1, policy_version 18950 (0.0009) -[2023-10-12 03:54:22,502][78123] Updated weights for policy 1, policy_version 18960 (0.0010) -[2023-10-12 03:54:22,867][78123] Updated weights for policy 1, policy_version 18970 (0.0008) -[2023-10-12 03:54:24,468][78091] Updated weights for policy 0, policy_version 19050 (0.0008) -[2023-10-12 03:54:24,839][78091] Updated weights for policy 0, policy_version 19060 (0.0008) -[2023-10-12 03:54:25,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 38928384. Throughput: 0: 1605.2, 1: 1578.0. Samples: 9746748. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) -[2023-10-12 03:54:25,201][77203] Avg episode reward: [(0, '37.530'), (1, '33.660')] -[2023-10-12 03:54:25,207][78091] Updated weights for policy 0, policy_version 19070 (0.0008) -[2023-10-12 03:54:27,174][78123] Updated weights for policy 1, policy_version 18980 (0.0010) -[2023-10-12 03:54:27,541][78123] Updated weights for policy 1, policy_version 18990 (0.0009) -[2023-10-12 03:54:27,908][78123] Updated weights for policy 1, policy_version 19000 (0.0007) -[2023-10-12 03:54:29,620][78091] Updated weights for policy 0, policy_version 19080 (0.0008) -[2023-10-12 03:54:29,990][78091] Updated weights for policy 0, policy_version 19090 (0.0007) -[2023-10-12 03:54:30,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 38993920. Throughput: 0: 1592.1, 1: 1593.4. Samples: 9756662. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-12 03:54:30,202][77203] Avg episode reward: [(0, '35.580'), (1, '38.380')] -[2023-10-12 03:54:30,369][78091] Updated weights for policy 0, policy_version 19100 (0.0008) -[2023-10-12 03:54:32,275][78123] Updated weights for policy 1, policy_version 19010 (0.0007) -[2023-10-12 03:54:32,637][78123] Updated weights for policy 1, policy_version 19020 (0.0008) -[2023-10-12 03:54:33,002][78123] Updated weights for policy 1, policy_version 19030 (0.0007) -[2023-10-12 03:54:33,371][78123] Updated weights for policy 1, policy_version 19040 (0.0008) -[2023-10-12 03:54:34,515][78091] Updated weights for policy 0, policy_version 19110 (0.0009) -[2023-10-12 03:54:34,889][78091] Updated weights for policy 0, policy_version 19120 (0.0007) -[2023-10-12 03:54:35,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 39059456. Throughput: 0: 1606.4, 1: 1582.7. Samples: 9775948. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-12 03:54:35,202][77203] Avg episode reward: [(0, '36.100'), (1, '39.550')] -[2023-10-12 03:54:35,265][78091] Updated weights for policy 0, policy_version 19130 (0.0007) -[2023-10-12 03:54:37,918][78123] Updated weights for policy 1, policy_version 19050 (0.0007) -[2023-10-12 03:54:38,291][78123] Updated weights for policy 1, policy_version 19060 (0.0007) -[2023-10-12 03:54:38,666][78123] Updated weights for policy 1, policy_version 19070 (0.0007) -[2023-10-12 03:54:39,498][78091] Updated weights for policy 0, policy_version 19140 (0.0008) -[2023-10-12 03:54:39,879][78091] Updated weights for policy 0, policy_version 19150 (0.0009) -[2023-10-12 03:54:40,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 39124992. Throughput: 0: 1615.1, 1: 1582.8. Samples: 9795280. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-12 03:54:40,201][77203] Avg episode reward: [(0, '35.990'), (1, '34.090')] -[2023-10-12 03:54:40,242][78091] Updated weights for policy 0, policy_version 19160 (0.0008) -[2023-10-12 03:54:42,779][78123] Updated weights for policy 1, policy_version 19080 (0.0009) -[2023-10-12 03:54:43,156][78123] Updated weights for policy 1, policy_version 19090 (0.0009) -[2023-10-12 03:54:43,521][78123] Updated weights for policy 1, policy_version 19100 (0.0008) -[2023-10-12 03:54:44,334][78091] Updated weights for policy 0, policy_version 19170 (0.0007) -[2023-10-12 03:54:44,702][78091] Updated weights for policy 0, policy_version 19180 (0.0007) -[2023-10-12 03:54:45,065][78091] Updated weights for policy 0, policy_version 19190 (0.0007) -[2023-10-12 03:54:45,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 39190528. Throughput: 0: 1603.2, 1: 1607.7. Samples: 9805380. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) -[2023-10-12 03:54:45,201][77203] Avg episode reward: [(0, '41.510'), (1, '38.030')] -[2023-10-12 03:54:45,432][77792] Saving new best policy, reward=41.510! -[2023-10-12 03:54:45,437][78091] Updated weights for policy 0, policy_version 19200 (0.0007) -[2023-10-12 03:54:47,844][78123] Updated weights for policy 1, policy_version 19110 (0.0008) -[2023-10-12 03:54:48,225][78123] Updated weights for policy 1, policy_version 19120 (0.0009) -[2023-10-12 03:54:48,600][78123] Updated weights for policy 1, policy_version 19130 (0.0009) -[2023-10-12 03:54:49,836][78091] Updated weights for policy 0, policy_version 19210 (0.0011) -[2023-10-12 03:54:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 39256064. Throughput: 0: 1605.6, 1: 1591.0. Samples: 9824054. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) -[2023-10-12 03:54:50,201][77203] Avg episode reward: [(0, '34.560'), (1, '39.240')] -[2023-10-12 03:54:50,208][78091] Updated weights for policy 0, policy_version 19220 (0.0009) -[2023-10-12 03:54:50,585][78091] Updated weights for policy 0, policy_version 19230 (0.0009) -[2023-10-12 03:54:53,023][78123] Updated weights for policy 1, policy_version 19140 (0.0010) -[2023-10-12 03:54:53,398][78123] Updated weights for policy 1, policy_version 19150 (0.0009) -[2023-10-12 03:54:53,755][78123] Updated weights for policy 1, policy_version 19160 (0.0009) -[2023-10-12 03:54:54,782][78091] Updated weights for policy 0, policy_version 19240 (0.0008) -[2023-10-12 03:54:55,160][78091] Updated weights for policy 0, policy_version 19250 (0.0008) -[2023-10-12 03:54:55,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 39321600. Throughput: 0: 1624.4, 1: 1582.0. Samples: 9843078. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) -[2023-10-12 03:54:55,202][77203] Avg episode reward: [(0, '35.980'), (1, '33.530')] -[2023-10-12 03:54:55,528][78091] Updated weights for policy 0, policy_version 19260 (0.0008) -[2023-10-12 03:54:58,108][78123] Updated weights for policy 1, policy_version 19170 (0.0009) -[2023-10-12 03:54:58,478][78123] Updated weights for policy 1, policy_version 19180 (0.0008) -[2023-10-12 03:54:58,852][78123] Updated weights for policy 1, policy_version 19190 (0.0008) -[2023-10-12 03:54:59,213][78123] Updated weights for policy 1, policy_version 19200 (0.0010) -[2023-10-12 03:54:59,763][78091] Updated weights for policy 0, policy_version 19270 (0.0008) -[2023-10-12 03:55:00,131][78091] Updated weights for policy 0, policy_version 19280 (0.0008) -[2023-10-12 03:55:00,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 39387136. Throughput: 0: 1606.7, 1: 1606.3. Samples: 9853170. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:55:00,202][77203] Avg episode reward: [(0, '36.300'), (1, '42.540')] -[2023-10-12 03:55:00,506][78091] Updated weights for policy 0, policy_version 19290 (0.0009) -[2023-10-12 03:55:03,695][78123] Updated weights for policy 1, policy_version 19210 (0.0007) -[2023-10-12 03:55:04,068][78123] Updated weights for policy 1, policy_version 19220 (0.0010) -[2023-10-12 03:55:04,444][78123] Updated weights for policy 1, policy_version 19230 (0.0009) -[2023-10-12 03:55:04,689][78091] Updated weights for policy 0, policy_version 19300 (0.0009) -[2023-10-12 03:55:05,061][78091] Updated weights for policy 0, policy_version 19310 (0.0007) -[2023-10-12 03:55:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 39452672. Throughput: 0: 1605.4, 1: 1604.4. Samples: 9872290. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:55:05,202][77203] Avg episode reward: [(0, '38.480'), (1, '40.050')] -[2023-10-12 03:55:05,442][78091] Updated weights for policy 0, policy_version 19320 (0.0007) -[2023-10-12 03:55:08,772][78123] Updated weights for policy 1, policy_version 19240 (0.0008) -[2023-10-12 03:55:09,144][78123] Updated weights for policy 1, policy_version 19250 (0.0010) -[2023-10-12 03:55:09,510][78123] Updated weights for policy 1, policy_version 19260 (0.0008) -[2023-10-12 03:55:09,721][78091] Updated weights for policy 0, policy_version 19330 (0.0009) -[2023-10-12 03:55:10,093][78091] Updated weights for policy 0, policy_version 19340 (0.0010) -[2023-10-12 03:55:10,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 39518208. Throughput: 0: 1618.3, 1: 1584.4. Samples: 9890868. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:55:10,201][77203] Avg episode reward: [(0, '34.690'), (1, '44.270')] -[2023-10-12 03:55:10,210][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000019264_19726336.pth... -[2023-10-12 03:55:10,249][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000017760_18186240.pth -[2023-10-12 03:55:10,472][78091] Updated weights for policy 0, policy_version 19350 (0.0009) -[2023-10-12 03:55:10,838][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000019360_19824640.pth... -[2023-10-12 03:55:10,839][78091] Updated weights for policy 0, policy_version 19360 (0.0009) -[2023-10-12 03:55:10,877][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000017856_18284544.pth -[2023-10-12 03:55:13,971][78123] Updated weights for policy 1, policy_version 19270 (0.0007) -[2023-10-12 03:55:14,343][78123] Updated weights for policy 1, policy_version 19280 (0.0009) -[2023-10-12 03:55:14,704][78123] Updated weights for policy 1, policy_version 19290 (0.0007) -[2023-10-12 03:55:15,201][78091] Updated weights for policy 0, policy_version 19370 (0.0010) -[2023-10-12 03:55:15,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 39583744. Throughput: 0: 1605.6, 1: 1594.0. Samples: 9900644. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-12 03:55:15,201][77203] Avg episode reward: [(0, '37.330'), (1, '37.700')] -[2023-10-12 03:55:15,587][78091] Updated weights for policy 0, policy_version 19380 (0.0010) -[2023-10-12 03:55:15,954][78091] Updated weights for policy 0, policy_version 19390 (0.0009) -[2023-10-12 03:55:18,929][78123] Updated weights for policy 1, policy_version 19300 (0.0008) -[2023-10-12 03:55:19,295][78123] Updated weights for policy 1, policy_version 19310 (0.0007) -[2023-10-12 03:55:19,659][78123] Updated weights for policy 1, policy_version 19320 (0.0007) -[2023-10-12 03:55:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 39649280. Throughput: 0: 1602.2, 1: 1603.9. Samples: 9920220. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-12 03:55:20,201][77203] Avg episode reward: [(0, '38.860'), (1, '34.780')] -[2023-10-12 03:55:20,252][78091] Updated weights for policy 0, policy_version 19400 (0.0009) -[2023-10-12 03:55:20,617][78091] Updated weights for policy 0, policy_version 19410 (0.0011) -[2023-10-12 03:55:20,993][78091] Updated weights for policy 0, policy_version 19420 (0.0011) -[2023-10-12 03:55:23,987][78123] Updated weights for policy 1, policy_version 19330 (0.0007) -[2023-10-12 03:55:24,347][78123] Updated weights for policy 1, policy_version 19340 (0.0009) -[2023-10-12 03:55:24,708][78123] Updated weights for policy 1, policy_version 19350 (0.0008) -[2023-10-12 03:55:25,076][78123] Updated weights for policy 1, policy_version 19360 (0.0008) -[2023-10-12 03:55:25,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 39714816. Throughput: 0: 1604.7, 1: 1586.0. Samples: 9938864. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-12 03:55:25,202][77203] Avg episode reward: [(0, '35.710'), (1, '45.680')] -[2023-10-12 03:55:25,212][77950] Saving new best policy, reward=45.680! -[2023-10-12 03:55:25,452][78091] Updated weights for policy 0, policy_version 19430 (0.0009) -[2023-10-12 03:55:25,829][78091] Updated weights for policy 0, policy_version 19440 (0.0008) -[2023-10-12 03:55:26,201][78091] Updated weights for policy 0, policy_version 19450 (0.0008) -[2023-10-12 03:55:29,515][78123] Updated weights for policy 1, policy_version 19370 (0.0010) -[2023-10-12 03:55:29,868][78123] Updated weights for policy 1, policy_version 19380 (0.0007) -[2023-10-12 03:55:30,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 39747584. Throughput: 0: 1591.1, 1: 1582.4. Samples: 9948190. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-10-12 03:55:30,201][77203] Avg episode reward: [(0, '35.830'), (1, '36.990')] -[2023-10-12 03:55:30,238][78123] Updated weights for policy 1, policy_version 19390 (0.0007) -[2023-10-12 03:55:30,447][78091] Updated weights for policy 0, policy_version 19460 (0.0008) -[2023-10-12 03:55:30,814][78091] Updated weights for policy 0, policy_version 19470 (0.0007) -[2023-10-12 03:55:31,184][78091] Updated weights for policy 0, policy_version 19480 (0.0007) -[2023-10-12 03:55:34,592][78123] Updated weights for policy 1, policy_version 19400 (0.0007) -[2023-10-12 03:55:34,966][78123] Updated weights for policy 1, policy_version 19410 (0.0007) -[2023-10-12 03:55:35,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 39813120. Throughput: 0: 1590.7, 1: 1604.0. Samples: 9967814. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-10-12 03:55:35,202][77203] Avg episode reward: [(0, '37.770'), (1, '38.980')] -[2023-10-12 03:55:35,334][78123] Updated weights for policy 1, policy_version 19420 (0.0008) -[2023-10-12 03:55:35,537][78091] Updated weights for policy 0, policy_version 19490 (0.0008) -[2023-10-12 03:55:35,909][78091] Updated weights for policy 0, policy_version 19500 (0.0008) -[2023-10-12 03:55:36,267][78091] Updated weights for policy 0, policy_version 19510 (0.0009) -[2023-10-12 03:55:36,642][78091] Updated weights for policy 0, policy_version 19520 (0.0008) -[2023-10-12 03:55:39,551][78123] Updated weights for policy 1, policy_version 19430 (0.0008) -[2023-10-12 03:55:39,917][78123] Updated weights for policy 1, policy_version 19440 (0.0007) -[2023-10-12 03:55:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 39878656. Throughput: 0: 1589.3, 1: 1602.7. Samples: 9986718. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-10-12 03:55:40,201][77203] Avg episode reward: [(0, '36.930'), (1, '46.850')] -[2023-10-12 03:55:40,289][78123] Updated weights for policy 1, policy_version 19450 (0.0009) -[2023-10-12 03:55:40,499][77950] Saving new best policy, reward=46.850! -[2023-10-12 03:55:41,189][78091] Updated weights for policy 0, policy_version 19530 (0.0008) -[2023-10-12 03:55:41,568][78091] Updated weights for policy 0, policy_version 19540 (0.0008) -[2023-10-12 03:55:41,934][78091] Updated weights for policy 0, policy_version 19550 (0.0008) -[2023-10-12 03:55:44,569][78123] Updated weights for policy 1, policy_version 19460 (0.0007) -[2023-10-12 03:55:44,934][78123] Updated weights for policy 1, policy_version 19470 (0.0009) -[2023-10-12 03:55:45,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 39944192. Throughput: 0: 1580.4, 1: 1584.8. Samples: 9995608. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:55:45,202][77203] Avg episode reward: [(0, '35.200'), (1, '33.560')] -[2023-10-12 03:55:45,302][78123] Updated weights for policy 1, policy_version 19480 (0.0008) -[2023-10-12 03:55:46,281][78091] Updated weights for policy 0, policy_version 19560 (0.0008) -[2023-10-12 03:55:46,653][78091] Updated weights for policy 0, policy_version 19570 (0.0009) -[2023-10-12 03:55:47,020][78091] Updated weights for policy 0, policy_version 19580 (0.0011) -[2023-10-12 03:55:49,583][78123] Updated weights for policy 1, policy_version 19490 (0.0007) -[2023-10-12 03:55:49,965][78123] Updated weights for policy 1, policy_version 19500 (0.0010) -[2023-10-12 03:55:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 40009728. Throughput: 0: 1575.8, 1: 1593.1. Samples: 10014890. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:55:50,201][77203] Avg episode reward: [(0, '39.770'), (1, '38.590')] -[2023-10-12 03:55:50,326][78123] Updated weights for policy 1, policy_version 19510 (0.0010) -[2023-10-12 03:55:50,706][78123] Updated weights for policy 1, policy_version 19520 (0.0007) -[2023-10-12 03:55:51,431][78091] Updated weights for policy 0, policy_version 19590 (0.0008) -[2023-10-12 03:55:51,811][78091] Updated weights for policy 0, policy_version 19600 (0.0007) -[2023-10-12 03:55:52,189][78091] Updated weights for policy 0, policy_version 19610 (0.0010) -[2023-10-12 03:55:55,073][78123] Updated weights for policy 1, policy_version 19530 (0.0010) -[2023-10-12 03:55:55,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 40075264. Throughput: 0: 1585.1, 1: 1609.7. Samples: 10034634. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:55:55,202][77203] Avg episode reward: [(0, '35.360'), (1, '37.560')] -[2023-10-12 03:55:55,449][78123] Updated weights for policy 1, policy_version 19540 (0.0010) -[2023-10-12 03:55:55,814][78123] Updated weights for policy 1, policy_version 19550 (0.0009) -[2023-10-12 03:55:56,431][78091] Updated weights for policy 0, policy_version 19620 (0.0007) -[2023-10-12 03:55:56,793][78091] Updated weights for policy 0, policy_version 19630 (0.0007) -[2023-10-12 03:55:57,166][78091] Updated weights for policy 0, policy_version 19640 (0.0007) -[2023-10-12 03:56:00,185][78123] Updated weights for policy 1, policy_version 19560 (0.0010) -[2023-10-12 03:56:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 40140800. Throughput: 0: 1582.6, 1: 1585.6. Samples: 10043212. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:56:00,201][77203] Avg episode reward: [(0, '38.600'), (1, '33.400')] -[2023-10-12 03:56:00,563][78123] Updated weights for policy 1, policy_version 19570 (0.0007) -[2023-10-12 03:56:00,935][78123] Updated weights for policy 1, policy_version 19580 (0.0009) -[2023-10-12 03:56:01,608][78091] Updated weights for policy 0, policy_version 19650 (0.0008) -[2023-10-12 03:56:01,982][78091] Updated weights for policy 0, policy_version 19660 (0.0010) -[2023-10-12 03:56:02,355][78091] Updated weights for policy 0, policy_version 19670 (0.0010) -[2023-10-12 03:56:02,718][78091] Updated weights for policy 0, policy_version 19680 (0.0008) -[2023-10-12 03:56:05,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 40206336. Throughput: 0: 1579.9, 1: 1584.3. Samples: 10062608. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:56:05,201][77203] Avg episode reward: [(0, '36.050'), (1, '42.190')] -[2023-10-12 03:56:05,339][78123] Updated weights for policy 1, policy_version 19590 (0.0008) -[2023-10-12 03:56:05,703][78123] Updated weights for policy 1, policy_version 19600 (0.0007) -[2023-10-12 03:56:06,074][78123] Updated weights for policy 1, policy_version 19610 (0.0009) -[2023-10-12 03:56:06,920][78091] Updated weights for policy 0, policy_version 19690 (0.0009) -[2023-10-12 03:56:07,292][78091] Updated weights for policy 0, policy_version 19700 (0.0008) -[2023-10-12 03:56:07,663][78091] Updated weights for policy 0, policy_version 19710 (0.0009) -[2023-10-12 03:56:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 40271872. Throughput: 0: 1583.1, 1: 1602.0. Samples: 10082192. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:56:10,201][77203] Avg episode reward: [(0, '39.370'), (1, '42.760')] -[2023-10-12 03:56:10,407][78123] Updated weights for policy 1, policy_version 19620 (0.0010) -[2023-10-12 03:56:10,772][78123] Updated weights for policy 1, policy_version 19630 (0.0008) -[2023-10-12 03:56:11,134][78123] Updated weights for policy 1, policy_version 19640 (0.0007) -[2023-10-12 03:56:11,788][78091] Updated weights for policy 0, policy_version 19720 (0.0009) -[2023-10-12 03:56:12,164][78091] Updated weights for policy 0, policy_version 19730 (0.0009) -[2023-10-12 03:56:12,520][78091] Updated weights for policy 0, policy_version 19740 (0.0008) -[2023-10-12 03:56:15,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 40337408. Throughput: 0: 1585.2, 1: 1585.7. Samples: 10090882. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-12 03:56:15,201][77203] Avg episode reward: [(0, '37.370'), (1, '36.400')] -[2023-10-12 03:56:15,289][78123] Updated weights for policy 1, policy_version 19650 (0.0008) -[2023-10-12 03:56:15,658][78123] Updated weights for policy 1, policy_version 19660 (0.0007) -[2023-10-12 03:56:16,024][78123] Updated weights for policy 1, policy_version 19670 (0.0009) -[2023-10-12 03:56:16,400][78123] Updated weights for policy 1, policy_version 19680 (0.0008) -[2023-10-12 03:56:16,998][78091] Updated weights for policy 0, policy_version 19750 (0.0009) -[2023-10-12 03:56:17,376][78091] Updated weights for policy 0, policy_version 19760 (0.0012) -[2023-10-12 03:56:17,753][78091] Updated weights for policy 0, policy_version 19770 (0.0010) -[2023-10-12 03:56:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 40402944. Throughput: 0: 1583.8, 1: 1586.2. Samples: 10110464. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-12 03:56:20,201][77203] Avg episode reward: [(0, '36.330'), (1, '40.780')] -[2023-10-12 03:56:20,806][78123] Updated weights for policy 1, policy_version 19690 (0.0010) -[2023-10-12 03:56:21,172][78123] Updated weights for policy 1, policy_version 19700 (0.0007) -[2023-10-12 03:56:21,541][78123] Updated weights for policy 1, policy_version 19710 (0.0008) -[2023-10-12 03:56:22,030][78091] Updated weights for policy 0, policy_version 19780 (0.0011) -[2023-10-12 03:56:22,415][78091] Updated weights for policy 0, policy_version 19790 (0.0010) -[2023-10-12 03:56:22,782][78091] Updated weights for policy 0, policy_version 19800 (0.0008) -[2023-10-12 03:56:25,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 40468480. Throughput: 0: 1591.0, 1: 1592.7. Samples: 10129982. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-12 03:56:25,201][77203] Avg episode reward: [(0, '36.800'), (1, '41.610')] -[2023-10-12 03:56:25,858][78123] Updated weights for policy 1, policy_version 19720 (0.0007) -[2023-10-12 03:56:26,220][78123] Updated weights for policy 1, policy_version 19730 (0.0008) -[2023-10-12 03:56:26,586][78123] Updated weights for policy 1, policy_version 19740 (0.0010) -[2023-10-12 03:56:27,174][78091] Updated weights for policy 0, policy_version 19810 (0.0008) -[2023-10-12 03:56:27,553][78091] Updated weights for policy 0, policy_version 19820 (0.0008) -[2023-10-12 03:56:27,918][78091] Updated weights for policy 0, policy_version 19830 (0.0008) -[2023-10-12 03:56:28,295][78091] Updated weights for policy 0, policy_version 19840 (0.0007) -[2023-10-12 03:56:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 40534016. Throughput: 0: 1605.0, 1: 1581.8. Samples: 10139012. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-12 03:56:30,202][77203] Avg episode reward: [(0, '38.740'), (1, '35.850')] -[2023-10-12 03:56:30,801][78123] Updated weights for policy 1, policy_version 19750 (0.0009) -[2023-10-12 03:56:31,165][78123] Updated weights for policy 1, policy_version 19760 (0.0009) -[2023-10-12 03:56:31,535][78123] Updated weights for policy 1, policy_version 19770 (0.0009) -[2023-10-12 03:56:32,574][78091] Updated weights for policy 0, policy_version 19850 (0.0007) -[2023-10-12 03:56:32,941][78091] Updated weights for policy 0, policy_version 19860 (0.0007) -[2023-10-12 03:56:33,326][78091] Updated weights for policy 0, policy_version 19870 (0.0009) -[2023-10-12 03:56:35,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 40599552. Throughput: 0: 1596.7, 1: 1588.3. Samples: 10158214. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-12 03:56:35,202][77203] Avg episode reward: [(0, '37.630'), (1, '42.930')] -[2023-10-12 03:56:35,756][78123] Updated weights for policy 1, policy_version 19780 (0.0009) -[2023-10-12 03:56:36,123][78123] Updated weights for policy 1, policy_version 19790 (0.0010) -[2023-10-12 03:56:36,486][78123] Updated weights for policy 1, policy_version 19800 (0.0008) -[2023-10-12 03:56:37,614][78091] Updated weights for policy 0, policy_version 19880 (0.0007) -[2023-10-12 03:56:37,986][78091] Updated weights for policy 0, policy_version 19890 (0.0007) -[2023-10-12 03:56:38,371][78091] Updated weights for policy 0, policy_version 19900 (0.0009) -[2023-10-12 03:56:40,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 40665088. Throughput: 0: 1594.2, 1: 1588.0. Samples: 10177832. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-12 03:56:40,202][77203] Avg episode reward: [(0, '38.850'), (1, '40.080')] -[2023-10-12 03:56:40,943][78123] Updated weights for policy 1, policy_version 19810 (0.0008) -[2023-10-12 03:56:41,317][78123] Updated weights for policy 1, policy_version 19820 (0.0009) -[2023-10-12 03:56:41,683][78123] Updated weights for policy 1, policy_version 19830 (0.0007) -[2023-10-12 03:56:42,049][78123] Updated weights for policy 1, policy_version 19840 (0.0010) -[2023-10-12 03:56:42,570][78091] Updated weights for policy 0, policy_version 19910 (0.0009) -[2023-10-12 03:56:42,942][78091] Updated weights for policy 0, policy_version 19920 (0.0010) -[2023-10-12 03:56:43,310][78091] Updated weights for policy 0, policy_version 19930 (0.0008) -[2023-10-12 03:56:45,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 40730624. Throughput: 0: 1613.2, 1: 1586.8. Samples: 10187214. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-12 03:56:45,202][77203] Avg episode reward: [(0, '38.560'), (1, '36.890')] -[2023-10-12 03:56:46,334][78123] Updated weights for policy 1, policy_version 19850 (0.0007) -[2023-10-12 03:56:46,706][78123] Updated weights for policy 1, policy_version 19860 (0.0011) -[2023-10-12 03:56:47,068][78123] Updated weights for policy 1, policy_version 19870 (0.0009) -[2023-10-12 03:56:47,587][78091] Updated weights for policy 0, policy_version 19940 (0.0008) -[2023-10-12 03:56:47,953][78091] Updated weights for policy 0, policy_version 19950 (0.0009) -[2023-10-12 03:56:48,328][78091] Updated weights for policy 0, policy_version 19960 (0.0007) -[2023-10-12 03:56:50,201][77203] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 40796160. Throughput: 0: 1598.1, 1: 1593.0. Samples: 10206208. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-12 03:56:50,201][77203] Avg episode reward: [(0, '39.760'), (1, '37.890')] -[2023-10-12 03:56:51,302][78123] Updated weights for policy 1, policy_version 19880 (0.0007) -[2023-10-12 03:56:51,675][78123] Updated weights for policy 1, policy_version 19890 (0.0010) -[2023-10-12 03:56:52,053][78123] Updated weights for policy 1, policy_version 19900 (0.0008) -[2023-10-12 03:56:52,616][78091] Updated weights for policy 0, policy_version 19970 (0.0010) -[2023-10-12 03:56:52,980][78091] Updated weights for policy 0, policy_version 19980 (0.0008) -[2023-10-12 03:56:53,365][78091] Updated weights for policy 0, policy_version 19990 (0.0009) -[2023-10-12 03:56:53,740][78091] Updated weights for policy 0, policy_version 20000 (0.0009) -[2023-10-12 03:56:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 40861696. Throughput: 0: 1595.2, 1: 1597.3. Samples: 10225856. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-12 03:56:55,202][77203] Avg episode reward: [(0, '39.110'), (1, '40.470')] -[2023-10-12 03:56:56,362][78123] Updated weights for policy 1, policy_version 19910 (0.0008) -[2023-10-12 03:56:56,732][78123] Updated weights for policy 1, policy_version 19920 (0.0010) -[2023-10-12 03:56:57,094][78123] Updated weights for policy 1, policy_version 19930 (0.0010) -[2023-10-12 03:56:57,970][78091] Updated weights for policy 0, policy_version 20010 (0.0007) -[2023-10-12 03:56:58,341][78091] Updated weights for policy 0, policy_version 20020 (0.0009) -[2023-10-12 03:56:58,717][78091] Updated weights for policy 0, policy_version 20030 (0.0009) -[2023-10-12 03:57:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 40927232. Throughput: 0: 1620.0, 1: 1592.9. Samples: 10235466. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) -[2023-10-12 03:57:00,201][77203] Avg episode reward: [(0, '38.620'), (1, '38.640')] -[2023-10-12 03:57:01,306][78123] Updated weights for policy 1, policy_version 19940 (0.0009) -[2023-10-12 03:57:01,676][78123] Updated weights for policy 1, policy_version 19950 (0.0010) -[2023-10-12 03:57:02,048][78123] Updated weights for policy 1, policy_version 19960 (0.0010) -[2023-10-12 03:57:02,915][78091] Updated weights for policy 0, policy_version 20040 (0.0009) -[2023-10-12 03:57:03,285][78091] Updated weights for policy 0, policy_version 20050 (0.0009) -[2023-10-12 03:57:03,661][78091] Updated weights for policy 0, policy_version 20060 (0.0008) -[2023-10-12 03:57:05,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 40992768. Throughput: 0: 1601.1, 1: 1599.7. Samples: 10254500. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) -[2023-10-12 03:57:05,202][77203] Avg episode reward: [(0, '40.190'), (1, '44.390')] -[2023-10-12 03:57:06,344][78123] Updated weights for policy 1, policy_version 19970 (0.0010) -[2023-10-12 03:57:06,741][78123] Updated weights for policy 1, policy_version 19980 (0.0007) -[2023-10-12 03:57:07,110][78123] Updated weights for policy 1, policy_version 19990 (0.0008) -[2023-10-12 03:57:07,474][78123] Updated weights for policy 1, policy_version 20000 (0.0009) -[2023-10-12 03:57:08,134][78091] Updated weights for policy 0, policy_version 20070 (0.0009) -[2023-10-12 03:57:08,508][78091] Updated weights for policy 0, policy_version 20080 (0.0008) -[2023-10-12 03:57:08,874][78091] Updated weights for policy 0, policy_version 20090 (0.0011) -[2023-10-12 03:57:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 41058304. Throughput: 0: 1597.4, 1: 1600.5. Samples: 10273888. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) -[2023-10-12 03:57:10,201][77203] Avg episode reward: [(0, '40.790'), (1, '43.890')] -[2023-10-12 03:57:10,208][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000020000_20480000.pth... -[2023-10-12 03:57:10,209][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000020096_20578304.pth... -[2023-10-12 03:57:10,238][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000018528_18972672.pth -[2023-10-12 03:57:10,250][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000018592_19038208.pth -[2023-10-12 03:57:11,907][78123] Updated weights for policy 1, policy_version 20010 (0.0009) -[2023-10-12 03:57:12,274][78123] Updated weights for policy 1, policy_version 20020 (0.0007) -[2023-10-12 03:57:12,646][78123] Updated weights for policy 1, policy_version 20030 (0.0008) -[2023-10-12 03:57:13,191][78091] Updated weights for policy 0, policy_version 20100 (0.0009) -[2023-10-12 03:57:13,578][78091] Updated weights for policy 0, policy_version 20110 (0.0009) -[2023-10-12 03:57:13,946][78091] Updated weights for policy 0, policy_version 20120 (0.0009) -[2023-10-12 03:57:15,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 41123840. Throughput: 0: 1611.9, 1: 1600.9. Samples: 10283590. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:57:15,202][77203] Avg episode reward: [(0, '38.980'), (1, '38.000')] -[2023-10-12 03:57:16,890][78123] Updated weights for policy 1, policy_version 20040 (0.0008) -[2023-10-12 03:57:17,259][78123] Updated weights for policy 1, policy_version 20050 (0.0009) -[2023-10-12 03:57:17,618][78123] Updated weights for policy 1, policy_version 20060 (0.0008) -[2023-10-12 03:57:18,242][78091] Updated weights for policy 0, policy_version 20130 (0.0009) -[2023-10-12 03:57:18,616][78091] Updated weights for policy 0, policy_version 20140 (0.0008) -[2023-10-12 03:57:18,986][78091] Updated weights for policy 0, policy_version 20150 (0.0007) -[2023-10-12 03:57:19,349][78091] Updated weights for policy 0, policy_version 20160 (0.0008) -[2023-10-12 03:57:20,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 41189376. Throughput: 0: 1610.8, 1: 1595.2. Samples: 10302484. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:57:20,201][77203] Avg episode reward: [(0, '41.560'), (1, '38.820')] -[2023-10-12 03:57:20,202][77792] Saving new best policy, reward=41.560! -[2023-10-12 03:57:22,040][78123] Updated weights for policy 1, policy_version 20070 (0.0010) -[2023-10-12 03:57:22,409][78123] Updated weights for policy 1, policy_version 20080 (0.0008) -[2023-10-12 03:57:22,773][78123] Updated weights for policy 1, policy_version 20090 (0.0009) -[2023-10-12 03:57:23,526][78091] Updated weights for policy 0, policy_version 20170 (0.0008) -[2023-10-12 03:57:23,898][78091] Updated weights for policy 0, policy_version 20180 (0.0010) -[2023-10-12 03:57:24,271][78091] Updated weights for policy 0, policy_version 20190 (0.0008) -[2023-10-12 03:57:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 41254912. Throughput: 0: 1593.1, 1: 1595.7. Samples: 10321330. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:57:25,202][77203] Avg episode reward: [(0, '43.560'), (1, '40.320')] -[2023-10-12 03:57:25,209][77792] Saving new best policy, reward=43.560! -[2023-10-12 03:57:27,249][78123] Updated weights for policy 1, policy_version 20100 (0.0010) -[2023-10-12 03:57:27,624][78123] Updated weights for policy 1, policy_version 20110 (0.0009) -[2023-10-12 03:57:27,996][78123] Updated weights for policy 1, policy_version 20120 (0.0008) -[2023-10-12 03:57:28,441][78091] Updated weights for policy 0, policy_version 20200 (0.0008) -[2023-10-12 03:57:28,822][78091] Updated weights for policy 0, policy_version 20210 (0.0009) -[2023-10-12 03:57:29,185][78091] Updated weights for policy 0, policy_version 20220 (0.0009) -[2023-10-12 03:57:30,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 41320448. Throughput: 0: 1608.1, 1: 1607.3. Samples: 10331908. Policy #0 lag: (min: 9.0, avg: 15.5, max: 41.0) -[2023-10-12 03:57:30,201][77203] Avg episode reward: [(0, '40.740'), (1, '38.880')] -[2023-10-12 03:57:32,422][78123] Updated weights for policy 1, policy_version 20130 (0.0008) -[2023-10-12 03:57:32,784][78123] Updated weights for policy 1, policy_version 20140 (0.0009) -[2023-10-12 03:57:33,162][78123] Updated weights for policy 1, policy_version 20150 (0.0007) -[2023-10-12 03:57:33,485][78091] Updated weights for policy 0, policy_version 20230 (0.0008) -[2023-10-12 03:57:33,521][78123] Updated weights for policy 1, policy_version 20160 (0.0009) -[2023-10-12 03:57:33,848][78091] Updated weights for policy 0, policy_version 20240 (0.0008) -[2023-10-12 03:57:34,223][78091] Updated weights for policy 0, policy_version 20250 (0.0008) -[2023-10-12 03:57:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 41385984. Throughput: 0: 1615.1, 1: 1588.0. Samples: 10350350. Policy #0 lag: (min: 9.0, avg: 15.5, max: 41.0) -[2023-10-12 03:57:35,201][77203] Avg episode reward: [(0, '39.670'), (1, '41.340')] -[2023-10-12 03:57:37,911][78123] Updated weights for policy 1, policy_version 20170 (0.0009) -[2023-10-12 03:57:38,281][78123] Updated weights for policy 1, policy_version 20180 (0.0009) -[2023-10-12 03:57:38,499][78091] Updated weights for policy 0, policy_version 20260 (0.0009) -[2023-10-12 03:57:38,643][78123] Updated weights for policy 1, policy_version 20190 (0.0009) -[2023-10-12 03:57:38,875][78091] Updated weights for policy 0, policy_version 20270 (0.0007) -[2023-10-12 03:57:39,251][78091] Updated weights for policy 0, policy_version 20280 (0.0009) -[2023-10-12 03:57:40,201][77203] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 41451520. Throughput: 0: 1603.9, 1: 1579.1. Samples: 10369090. Policy #0 lag: (min: 9.0, avg: 15.5, max: 41.0) -[2023-10-12 03:57:40,202][77203] Avg episode reward: [(0, '43.660'), (1, '42.460')] -[2023-10-12 03:57:40,213][77792] Saving new best policy, reward=43.660! -[2023-10-12 03:57:43,107][78123] Updated weights for policy 1, policy_version 20200 (0.0007) -[2023-10-12 03:57:43,438][78091] Updated weights for policy 0, policy_version 20290 (0.0009) -[2023-10-12 03:57:43,474][78123] Updated weights for policy 1, policy_version 20210 (0.0007) -[2023-10-12 03:57:43,810][78091] Updated weights for policy 0, policy_version 20300 (0.0007) -[2023-10-12 03:57:43,839][78123] Updated weights for policy 1, policy_version 20220 (0.0007) -[2023-10-12 03:57:44,170][78091] Updated weights for policy 0, policy_version 20310 (0.0009) -[2023-10-12 03:57:44,553][78091] Updated weights for policy 0, policy_version 20320 (0.0010) -[2023-10-12 03:57:45,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 12885.0). Total num frames: 41517056. Throughput: 0: 1610.5, 1: 1606.0. Samples: 10380208. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:57:45,201][77203] Avg episode reward: [(0, '36.610'), (1, '40.650')] -[2023-10-12 03:57:48,006][78123] Updated weights for policy 1, policy_version 20230 (0.0009) -[2023-10-12 03:57:48,387][78123] Updated weights for policy 1, policy_version 20240 (0.0010) -[2023-10-12 03:57:48,751][78123] Updated weights for policy 1, policy_version 20250 (0.0009) -[2023-10-12 03:57:48,999][78091] Updated weights for policy 0, policy_version 20330 (0.0008) -[2023-10-12 03:57:49,382][78091] Updated weights for policy 0, policy_version 20340 (0.0010) -[2023-10-12 03:57:49,744][78091] Updated weights for policy 0, policy_version 20350 (0.0009) -[2023-10-12 03:57:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.1, 300 sec: 12885.0). Total num frames: 41582592. Throughput: 0: 1624.2, 1: 1582.8. Samples: 10398816. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:57:50,202][77203] Avg episode reward: [(0, '41.760'), (1, '42.380')] -[2023-10-12 03:57:53,251][78123] Updated weights for policy 1, policy_version 20260 (0.0008) -[2023-10-12 03:57:53,641][78123] Updated weights for policy 1, policy_version 20270 (0.0009) -[2023-10-12 03:57:54,012][78123] Updated weights for policy 1, policy_version 20280 (0.0008) -[2023-10-12 03:57:54,067][78091] Updated weights for policy 0, policy_version 20360 (0.0009) -[2023-10-12 03:57:54,431][78091] Updated weights for policy 0, policy_version 20370 (0.0008) -[2023-10-12 03:57:54,804][78091] Updated weights for policy 0, policy_version 20380 (0.0008) -[2023-10-12 03:57:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 12885.0). Total num frames: 41648128. Throughput: 0: 1609.5, 1: 1574.9. Samples: 10417186. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:57:55,202][77203] Avg episode reward: [(0, '40.420'), (1, '42.990')] -[2023-10-12 03:57:58,378][78123] Updated weights for policy 1, policy_version 20290 (0.0008) -[2023-10-12 03:57:58,746][78123] Updated weights for policy 1, policy_version 20300 (0.0009) -[2023-10-12 03:57:59,108][78123] Updated weights for policy 1, policy_version 20310 (0.0010) -[2023-10-12 03:57:59,148][78091] Updated weights for policy 0, policy_version 20390 (0.0009) -[2023-10-12 03:57:59,475][78123] Updated weights for policy 1, policy_version 20320 (0.0009) -[2023-10-12 03:57:59,536][78091] Updated weights for policy 0, policy_version 20400 (0.0008) -[2023-10-12 03:57:59,903][78091] Updated weights for policy 0, policy_version 20410 (0.0010) -[2023-10-12 03:58:00,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 41713664. Throughput: 0: 1603.7, 1: 1598.3. Samples: 10427678. Policy #0 lag: (min: 1.0, avg: 11.1, max: 33.0) -[2023-10-12 03:58:00,201][77203] Avg episode reward: [(0, '39.600'), (1, '40.850')] -[2023-10-12 03:58:03,832][78123] Updated weights for policy 1, policy_version 20330 (0.0007) -[2023-10-12 03:58:04,013][78091] Updated weights for policy 0, policy_version 20420 (0.0009) -[2023-10-12 03:58:04,193][78123] Updated weights for policy 1, policy_version 20340 (0.0007) -[2023-10-12 03:58:04,386][78091] Updated weights for policy 0, policy_version 20430 (0.0007) -[2023-10-12 03:58:04,558][78123] Updated weights for policy 1, policy_version 20350 (0.0009) -[2023-10-12 03:58:04,757][78091] Updated weights for policy 0, policy_version 20440 (0.0007) -[2023-10-12 03:58:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 41779200. Throughput: 0: 1618.8, 1: 1591.8. Samples: 10446964. Policy #0 lag: (min: 1.0, avg: 11.1, max: 33.0) -[2023-10-12 03:58:05,201][77203] Avg episode reward: [(0, '44.450'), (1, '42.240')] -[2023-10-12 03:58:05,202][77792] Saving new best policy, reward=44.450! -[2023-10-12 03:58:08,799][78123] Updated weights for policy 1, policy_version 20360 (0.0008) -[2023-10-12 03:58:08,954][78091] Updated weights for policy 0, policy_version 20450 (0.0009) -[2023-10-12 03:58:09,168][78123] Updated weights for policy 1, policy_version 20370 (0.0008) -[2023-10-12 03:58:09,330][78091] Updated weights for policy 0, policy_version 20460 (0.0008) -[2023-10-12 03:58:09,524][78123] Updated weights for policy 1, policy_version 20380 (0.0010) -[2023-10-12 03:58:09,710][78091] Updated weights for policy 0, policy_version 20470 (0.0009) -[2023-10-12 03:58:10,082][78091] Updated weights for policy 0, policy_version 20480 (0.0008) -[2023-10-12 03:58:10,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 41844736. Throughput: 0: 1619.5, 1: 1571.1. Samples: 10464908. Policy #0 lag: (min: 1.0, avg: 11.1, max: 33.0) -[2023-10-12 03:58:10,202][77203] Avg episode reward: [(0, '38.400'), (1, '47.410')] -[2023-10-12 03:58:10,211][77950] Saving new best policy, reward=47.410! -[2023-10-12 03:58:13,720][78123] Updated weights for policy 1, policy_version 20390 (0.0010) -[2023-10-12 03:58:14,083][78123] Updated weights for policy 1, policy_version 20400 (0.0009) -[2023-10-12 03:58:14,246][78091] Updated weights for policy 0, policy_version 20490 (0.0009) -[2023-10-12 03:58:14,456][78123] Updated weights for policy 1, policy_version 20410 (0.0007) -[2023-10-12 03:58:14,607][78091] Updated weights for policy 0, policy_version 20500 (0.0008) -[2023-10-12 03:58:14,981][78091] Updated weights for policy 0, policy_version 20510 (0.0009) -[2023-10-12 03:58:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 41910272. Throughput: 0: 1605.2, 1: 1586.1. Samples: 10475518. Policy #0 lag: (min: 30.0, avg: 43.7, max: 62.0) -[2023-10-12 03:58:15,201][77203] Avg episode reward: [(0, '44.580'), (1, '42.350')] -[2023-10-12 03:58:15,202][77792] Saving new best policy, reward=44.580! -[2023-10-12 03:58:18,826][78123] Updated weights for policy 1, policy_version 20420 (0.0009) -[2023-10-12 03:58:19,188][78123] Updated weights for policy 1, policy_version 20430 (0.0009) -[2023-10-12 03:58:19,311][78091] Updated weights for policy 0, policy_version 20520 (0.0009) -[2023-10-12 03:58:19,556][78123] Updated weights for policy 1, policy_version 20440 (0.0009) -[2023-10-12 03:58:19,679][78091] Updated weights for policy 0, policy_version 20530 (0.0008) -[2023-10-12 03:58:20,043][78091] Updated weights for policy 0, policy_version 20540 (0.0009) -[2023-10-12 03:58:20,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 41975808. Throughput: 0: 1617.7, 1: 1600.0. Samples: 10495144. Policy #0 lag: (min: 30.0, avg: 43.7, max: 62.0) -[2023-10-12 03:58:20,201][77203] Avg episode reward: [(0, '39.140'), (1, '38.580')] -[2023-10-12 03:58:23,763][78123] Updated weights for policy 1, policy_version 20450 (0.0008) -[2023-10-12 03:58:24,134][78123] Updated weights for policy 1, policy_version 20460 (0.0010) -[2023-10-12 03:58:24,408][78091] Updated weights for policy 0, policy_version 20550 (0.0007) -[2023-10-12 03:58:24,494][78123] Updated weights for policy 1, policy_version 20470 (0.0008) -[2023-10-12 03:58:24,768][78091] Updated weights for policy 0, policy_version 20560 (0.0008) -[2023-10-12 03:58:24,863][78123] Updated weights for policy 1, policy_version 20480 (0.0008) -[2023-10-12 03:58:25,140][78091] Updated weights for policy 0, policy_version 20570 (0.0007) -[2023-10-12 03:58:25,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 42008576. Throughput: 0: 1617.3, 1: 1582.6. Samples: 10513082. Policy #0 lag: (min: 30.0, avg: 43.7, max: 62.0) -[2023-10-12 03:58:25,201][77203] Avg episode reward: [(0, '39.830'), (1, '43.760')] -[2023-10-12 03:58:29,198][78123] Updated weights for policy 1, policy_version 20490 (0.0007) -[2023-10-12 03:58:29,480][78091] Updated weights for policy 0, policy_version 20580 (0.0008) -[2023-10-12 03:58:29,569][78123] Updated weights for policy 1, policy_version 20500 (0.0008) -[2023-10-12 03:58:29,844][78091] Updated weights for policy 0, policy_version 20590 (0.0008) -[2023-10-12 03:58:29,938][78123] Updated weights for policy 1, policy_version 20510 (0.0008) -[2023-10-12 03:58:30,201][77203] Fps is (10 sec: 9830.2, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 42074112. Throughput: 0: 1598.8, 1: 1581.2. Samples: 10523308. Policy #0 lag: (min: 30.0, avg: 43.7, max: 62.0) -[2023-10-12 03:58:30,202][77203] Avg episode reward: [(0, '39.650'), (1, '41.920')] -[2023-10-12 03:58:30,211][78091] Updated weights for policy 0, policy_version 20600 (0.0009) -[2023-10-12 03:58:34,213][78123] Updated weights for policy 1, policy_version 20520 (0.0010) -[2023-10-12 03:58:34,565][78091] Updated weights for policy 0, policy_version 20610 (0.0009) -[2023-10-12 03:58:34,578][78123] Updated weights for policy 1, policy_version 20530 (0.0010) -[2023-10-12 03:58:34,931][78091] Updated weights for policy 0, policy_version 20620 (0.0008) -[2023-10-12 03:58:34,945][78123] Updated weights for policy 1, policy_version 20540 (0.0009) -[2023-10-12 03:58:35,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 42139648. Throughput: 0: 1600.7, 1: 1597.2. Samples: 10542720. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:58:35,202][77203] Avg episode reward: [(0, '36.540'), (1, '40.310')] -[2023-10-12 03:58:35,307][78091] Updated weights for policy 0, policy_version 20630 (0.0009) -[2023-10-12 03:58:35,674][78091] Updated weights for policy 0, policy_version 20640 (0.0008) -[2023-10-12 03:58:39,612][78123] Updated weights for policy 1, policy_version 20550 (0.0010) -[2023-10-12 03:58:39,978][78123] Updated weights for policy 1, policy_version 20560 (0.0008) -[2023-10-12 03:58:40,066][78091] Updated weights for policy 0, policy_version 20650 (0.0009) -[2023-10-12 03:58:40,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 42172416. Throughput: 0: 1615.7, 1: 1594.5. Samples: 10561644. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:58:40,201][77203] Avg episode reward: [(0, '42.420'), (1, '40.710')] -[2023-10-12 03:58:40,345][78123] Updated weights for policy 1, policy_version 20570 (0.0008) -[2023-10-12 03:58:40,443][78091] Updated weights for policy 0, policy_version 20660 (0.0009) -[2023-10-12 03:58:40,817][78091] Updated weights for policy 0, policy_version 20670 (0.0008) -[2023-10-12 03:58:44,810][78123] Updated weights for policy 1, policy_version 20580 (0.0010) -[2023-10-12 03:58:45,178][78123] Updated weights for policy 1, policy_version 20590 (0.0008) -[2023-10-12 03:58:45,201][77203] Fps is (10 sec: 9830.6, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 42237952. Throughput: 0: 1592.8, 1: 1580.3. Samples: 10570466. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:58:45,201][77203] Avg episode reward: [(0, '36.960'), (1, '43.640')] -[2023-10-12 03:58:45,374][78091] Updated weights for policy 0, policy_version 20680 (0.0007) -[2023-10-12 03:58:45,543][78123] Updated weights for policy 1, policy_version 20600 (0.0008) -[2023-10-12 03:58:45,740][78091] Updated weights for policy 0, policy_version 20690 (0.0008) -[2023-10-12 03:58:46,115][78091] Updated weights for policy 0, policy_version 20700 (0.0009) -[2023-10-12 03:58:49,958][78123] Updated weights for policy 1, policy_version 20610 (0.0008) -[2023-10-12 03:58:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 42303488. Throughput: 0: 1591.4, 1: 1585.4. Samples: 10589918. Policy #0 lag: (min: 19.0, avg: 19.0, max: 22.0) -[2023-10-12 03:58:50,201][77203] Avg episode reward: [(0, '42.590'), (1, '39.500')] -[2023-10-12 03:58:50,327][78123] Updated weights for policy 1, policy_version 20620 (0.0009) -[2023-10-12 03:58:50,332][78091] Updated weights for policy 0, policy_version 20710 (0.0008) -[2023-10-12 03:58:50,695][78123] Updated weights for policy 1, policy_version 20630 (0.0007) -[2023-10-12 03:58:50,705][78091] Updated weights for policy 0, policy_version 20720 (0.0010) -[2023-10-12 03:58:51,056][78123] Updated weights for policy 1, policy_version 20640 (0.0010) -[2023-10-12 03:58:51,080][78091] Updated weights for policy 0, policy_version 20730 (0.0009) -[2023-10-12 03:58:55,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 42369024. Throughput: 0: 1602.5, 1: 1606.4. Samples: 10609308. Policy #0 lag: (min: 19.0, avg: 19.0, max: 22.0) -[2023-10-12 03:58:55,201][77203] Avg episode reward: [(0, '37.250'), (1, '40.430')] -[2023-10-12 03:58:55,373][78091] Updated weights for policy 0, policy_version 20740 (0.0009) -[2023-10-12 03:58:55,447][78123] Updated weights for policy 1, policy_version 20650 (0.0007) -[2023-10-12 03:58:55,741][78091] Updated weights for policy 0, policy_version 20750 (0.0009) -[2023-10-12 03:58:55,815][78123] Updated weights for policy 1, policy_version 20660 (0.0009) -[2023-10-12 03:58:56,104][78091] Updated weights for policy 0, policy_version 20760 (0.0008) -[2023-10-12 03:58:56,187][78123] Updated weights for policy 1, policy_version 20670 (0.0009) -[2023-10-12 03:59:00,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 42434560. Throughput: 0: 1584.8, 1: 1578.5. Samples: 10617868. Policy #0 lag: (min: 19.0, avg: 19.0, max: 22.0) -[2023-10-12 03:59:00,201][77203] Avg episode reward: [(0, '39.200'), (1, '41.340')] -[2023-10-12 03:59:00,272][78123] Updated weights for policy 1, policy_version 20680 (0.0009) -[2023-10-12 03:59:00,473][78091] Updated weights for policy 0, policy_version 20770 (0.0007) -[2023-10-12 03:59:00,637][78123] Updated weights for policy 1, policy_version 20690 (0.0009) -[2023-10-12 03:59:00,846][78091] Updated weights for policy 0, policy_version 20780 (0.0007) -[2023-10-12 03:59:01,008][78123] Updated weights for policy 1, policy_version 20700 (0.0008) -[2023-10-12 03:59:01,215][78091] Updated weights for policy 0, policy_version 20790 (0.0007) -[2023-10-12 03:59:01,600][78091] Updated weights for policy 0, policy_version 20800 (0.0009) -[2023-10-12 03:59:05,201][77203] Fps is (10 sec: 13106.7, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 42500096. Throughput: 0: 1584.3, 1: 1580.6. Samples: 10637564. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:59:05,202][77203] Avg episode reward: [(0, '41.010'), (1, '39.710')] -[2023-10-12 03:59:05,379][78123] Updated weights for policy 1, policy_version 20710 (0.0009) -[2023-10-12 03:59:05,747][78123] Updated weights for policy 1, policy_version 20720 (0.0008) -[2023-10-12 03:59:05,870][78091] Updated weights for policy 0, policy_version 20810 (0.0008) -[2023-10-12 03:59:06,113][78123] Updated weights for policy 1, policy_version 20730 (0.0009) -[2023-10-12 03:59:06,240][78091] Updated weights for policy 0, policy_version 20820 (0.0007) -[2023-10-12 03:59:06,615][78091] Updated weights for policy 0, policy_version 20830 (0.0007) -[2023-10-12 03:59:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 42565632. Throughput: 0: 1592.2, 1: 1603.4. Samples: 10656882. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:59:10,201][77203] Avg episode reward: [(0, '35.950'), (1, '41.940')] -[2023-10-12 03:59:10,208][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000020832_21331968.pth... -[2023-10-12 03:59:10,209][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000020736_21233664.pth... -[2023-10-12 03:59:10,245][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000019264_19726336.pth -[2023-10-12 03:59:10,249][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000019360_19824640.pth -[2023-10-12 03:59:10,592][78123] Updated weights for policy 1, policy_version 20740 (0.0008) -[2023-10-12 03:59:10,947][78091] Updated weights for policy 0, policy_version 20840 (0.0008) -[2023-10-12 03:59:10,958][78123] Updated weights for policy 1, policy_version 20750 (0.0007) -[2023-10-12 03:59:11,315][78123] Updated weights for policy 1, policy_version 20760 (0.0009) -[2023-10-12 03:59:11,322][78091] Updated weights for policy 0, policy_version 20850 (0.0010) -[2023-10-12 03:59:11,687][78091] Updated weights for policy 0, policy_version 20860 (0.0008) -[2023-10-12 03:59:15,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 42631168. Throughput: 0: 1578.3, 1: 1580.2. Samples: 10665440. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:59:15,202][77203] Avg episode reward: [(0, '41.120'), (1, '44.800')] -[2023-10-12 03:59:15,587][78123] Updated weights for policy 1, policy_version 20770 (0.0009) -[2023-10-12 03:59:15,961][78123] Updated weights for policy 1, policy_version 20780 (0.0009) -[2023-10-12 03:59:16,017][78091] Updated weights for policy 0, policy_version 20870 (0.0008) -[2023-10-12 03:59:16,332][78123] Updated weights for policy 1, policy_version 20790 (0.0009) -[2023-10-12 03:59:16,388][78091] Updated weights for policy 0, policy_version 20880 (0.0007) -[2023-10-12 03:59:16,692][78123] Updated weights for policy 1, policy_version 20800 (0.0008) -[2023-10-12 03:59:16,761][78091] Updated weights for policy 0, policy_version 20890 (0.0009) -[2023-10-12 03:59:20,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12014.9, 300 sec: 12774.0). Total num frames: 42696704. Throughput: 0: 1583.0, 1: 1579.9. Samples: 10685048. Policy #0 lag: (min: 3.0, avg: 16.2, max: 35.0) -[2023-10-12 03:59:20,202][77203] Avg episode reward: [(0, '36.200'), (1, '39.170')] -[2023-10-12 03:59:21,036][78123] Updated weights for policy 1, policy_version 20810 (0.0011) -[2023-10-12 03:59:21,050][78091] Updated weights for policy 0, policy_version 20900 (0.0009) -[2023-10-12 03:59:21,414][78123] Updated weights for policy 1, policy_version 20820 (0.0008) -[2023-10-12 03:59:21,433][78091] Updated weights for policy 0, policy_version 20910 (0.0008) -[2023-10-12 03:59:21,776][78123] Updated weights for policy 1, policy_version 20830 (0.0008) -[2023-10-12 03:59:21,801][78091] Updated weights for policy 0, policy_version 20920 (0.0007) -[2023-10-12 03:59:25,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 42762240. Throughput: 0: 1580.8, 1: 1590.0. Samples: 10704330. Policy #0 lag: (min: 3.0, avg: 16.2, max: 35.0) -[2023-10-12 03:59:25,202][77203] Avg episode reward: [(0, '39.800'), (1, '42.160')] -[2023-10-12 03:59:26,116][78123] Updated weights for policy 1, policy_version 20840 (0.0010) -[2023-10-12 03:59:26,231][78091] Updated weights for policy 0, policy_version 20930 (0.0007) -[2023-10-12 03:59:26,494][78123] Updated weights for policy 1, policy_version 20850 (0.0008) -[2023-10-12 03:59:26,604][78091] Updated weights for policy 0, policy_version 20940 (0.0007) -[2023-10-12 03:59:26,859][78123] Updated weights for policy 1, policy_version 20860 (0.0009) -[2023-10-12 03:59:26,971][78091] Updated weights for policy 0, policy_version 20950 (0.0009) -[2023-10-12 03:59:27,344][78091] Updated weights for policy 0, policy_version 20960 (0.0009) -[2023-10-12 03:59:30,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 42827776. Throughput: 0: 1583.6, 1: 1580.4. Samples: 10712846. Policy #0 lag: (min: 3.0, avg: 16.2, max: 35.0) -[2023-10-12 03:59:30,202][77203] Avg episode reward: [(0, '40.380'), (1, '47.710')] -[2023-10-12 03:59:30,203][77950] Saving new best policy, reward=47.710! -[2023-10-12 03:59:31,206][78123] Updated weights for policy 1, policy_version 20870 (0.0009) -[2023-10-12 03:59:31,567][78123] Updated weights for policy 1, policy_version 20880 (0.0008) -[2023-10-12 03:59:31,650][78091] Updated weights for policy 0, policy_version 20970 (0.0009) -[2023-10-12 03:59:31,930][78123] Updated weights for policy 1, policy_version 20890 (0.0008) -[2023-10-12 03:59:32,022][78091] Updated weights for policy 0, policy_version 20980 (0.0009) -[2023-10-12 03:59:32,398][78091] Updated weights for policy 0, policy_version 20990 (0.0010) -[2023-10-12 03:59:35,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 42893312. Throughput: 0: 1582.4, 1: 1584.2. Samples: 10732414. Policy #0 lag: (min: 1.0, avg: 5.1, max: 33.0) -[2023-10-12 03:59:35,201][77203] Avg episode reward: [(0, '39.750'), (1, '36.980')] -[2023-10-12 03:59:36,342][78123] Updated weights for policy 1, policy_version 20900 (0.0008) -[2023-10-12 03:59:36,650][78091] Updated weights for policy 0, policy_version 21000 (0.0010) -[2023-10-12 03:59:36,719][78123] Updated weights for policy 1, policy_version 20910 (0.0009) -[2023-10-12 03:59:37,022][78091] Updated weights for policy 0, policy_version 21010 (0.0008) -[2023-10-12 03:59:37,086][78123] Updated weights for policy 1, policy_version 20920 (0.0009) -[2023-10-12 03:59:37,398][78091] Updated weights for policy 0, policy_version 21020 (0.0007) -[2023-10-12 03:59:40,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 42958848. Throughput: 0: 1589.2, 1: 1580.6. Samples: 10751952. Policy #0 lag: (min: 1.0, avg: 5.1, max: 33.0) -[2023-10-12 03:59:40,201][77203] Avg episode reward: [(0, '40.880'), (1, '43.420')] -[2023-10-12 03:59:41,513][78123] Updated weights for policy 1, policy_version 20930 (0.0009) -[2023-10-12 03:59:41,803][78091] Updated weights for policy 0, policy_version 21030 (0.0008) -[2023-10-12 03:59:41,879][78123] Updated weights for policy 1, policy_version 20940 (0.0009) -[2023-10-12 03:59:42,171][78091] Updated weights for policy 0, policy_version 21040 (0.0007) -[2023-10-12 03:59:42,253][78123] Updated weights for policy 1, policy_version 20950 (0.0008) -[2023-10-12 03:59:42,549][78091] Updated weights for policy 0, policy_version 21050 (0.0008) -[2023-10-12 03:59:42,620][78123] Updated weights for policy 1, policy_version 20960 (0.0009) -[2023-10-12 03:59:45,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 43024384. Throughput: 0: 1585.8, 1: 1581.1. Samples: 10760380. Policy #0 lag: (min: 1.0, avg: 5.1, max: 33.0) -[2023-10-12 03:59:45,202][77203] Avg episode reward: [(0, '37.190'), (1, '41.020')] -[2023-10-12 03:59:46,897][78091] Updated weights for policy 0, policy_version 21060 (0.0009) -[2023-10-12 03:59:47,055][78123] Updated weights for policy 1, policy_version 20970 (0.0008) -[2023-10-12 03:59:47,268][78091] Updated weights for policy 0, policy_version 21070 (0.0010) -[2023-10-12 03:59:47,429][78123] Updated weights for policy 1, policy_version 20980 (0.0009) -[2023-10-12 03:59:47,637][78091] Updated weights for policy 0, policy_version 21080 (0.0009) -[2023-10-12 03:59:47,795][78123] Updated weights for policy 1, policy_version 20990 (0.0009) -[2023-10-12 03:59:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 43089920. Throughput: 0: 1583.5, 1: 1582.1. Samples: 10780016. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:59:50,201][77203] Avg episode reward: [(0, '40.930'), (1, '39.330')] -[2023-10-12 03:59:51,987][78091] Updated weights for policy 0, policy_version 21090 (0.0008) -[2023-10-12 03:59:52,148][78123] Updated weights for policy 1, policy_version 21000 (0.0008) -[2023-10-12 03:59:52,360][78091] Updated weights for policy 0, policy_version 21100 (0.0009) -[2023-10-12 03:59:52,501][78123] Updated weights for policy 1, policy_version 21010 (0.0009) -[2023-10-12 03:59:52,732][78091] Updated weights for policy 0, policy_version 21110 (0.0009) -[2023-10-12 03:59:52,859][78123] Updated weights for policy 1, policy_version 21020 (0.0009) -[2023-10-12 03:59:53,108][78091] Updated weights for policy 0, policy_version 21120 (0.0009) -[2023-10-12 03:59:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 43155456. Throughput: 0: 1587.7, 1: 1577.6. Samples: 10799320. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 03:59:55,202][77203] Avg episode reward: [(0, '39.430'), (1, '36.640')] -[2023-10-12 03:59:57,110][78123] Updated weights for policy 1, policy_version 21030 (0.0009) -[2023-10-12 03:59:57,334][78091] Updated weights for policy 0, policy_version 21130 (0.0008) -[2023-10-12 03:59:57,466][78123] Updated weights for policy 1, policy_version 21040 (0.0009) -[2023-10-12 03:59:57,704][78091] Updated weights for policy 0, policy_version 21140 (0.0008) -[2023-10-12 03:59:57,832][78123] Updated weights for policy 1, policy_version 21050 (0.0008) -[2023-10-12 03:59:58,066][78091] Updated weights for policy 0, policy_version 21150 (0.0009) -[2023-10-12 04:00:00,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 43220992. Throughput: 0: 1599.0, 1: 1586.4. Samples: 10808780. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:00:00,202][77203] Avg episode reward: [(0, '37.710'), (1, '43.520')] -[2023-10-12 04:00:02,041][78123] Updated weights for policy 1, policy_version 21060 (0.0009) -[2023-10-12 04:00:02,334][78091] Updated weights for policy 0, policy_version 21160 (0.0009) -[2023-10-12 04:00:02,411][78123] Updated weights for policy 1, policy_version 21070 (0.0010) -[2023-10-12 04:00:02,711][78091] Updated weights for policy 0, policy_version 21170 (0.0008) -[2023-10-12 04:00:02,775][78123] Updated weights for policy 1, policy_version 21080 (0.0008) -[2023-10-12 04:00:03,074][78091] Updated weights for policy 0, policy_version 21180 (0.0010) -[2023-10-12 04:00:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 43286528. Throughput: 0: 1590.0, 1: 1579.6. Samples: 10827682. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:00:05,202][77203] Avg episode reward: [(0, '39.760'), (1, '41.340')] -[2023-10-12 04:00:07,232][78123] Updated weights for policy 1, policy_version 21090 (0.0008) -[2023-10-12 04:00:07,394][78091] Updated weights for policy 0, policy_version 21190 (0.0009) -[2023-10-12 04:00:07,603][78123] Updated weights for policy 1, policy_version 21100 (0.0007) -[2023-10-12 04:00:07,760][78091] Updated weights for policy 0, policy_version 21200 (0.0008) -[2023-10-12 04:00:07,957][78123] Updated weights for policy 1, policy_version 21110 (0.0007) -[2023-10-12 04:00:08,134][78091] Updated weights for policy 0, policy_version 21210 (0.0008) -[2023-10-12 04:00:08,320][78123] Updated weights for policy 1, policy_version 21120 (0.0007) -[2023-10-12 04:00:10,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 43352064. Throughput: 0: 1592.4, 1: 1581.5. Samples: 10847154. Policy #0 lag: (min: 11.0, avg: 20.6, max: 43.0) -[2023-10-12 04:00:10,202][77203] Avg episode reward: [(0, '39.520'), (1, '40.190')] -[2023-10-12 04:00:12,417][78091] Updated weights for policy 0, policy_version 21220 (0.0009) -[2023-10-12 04:00:12,632][78123] Updated weights for policy 1, policy_version 21130 (0.0007) -[2023-10-12 04:00:12,775][78091] Updated weights for policy 0, policy_version 21230 (0.0008) -[2023-10-12 04:00:13,005][78123] Updated weights for policy 1, policy_version 21140 (0.0007) -[2023-10-12 04:00:13,152][78091] Updated weights for policy 0, policy_version 21240 (0.0008) -[2023-10-12 04:00:13,366][78123] Updated weights for policy 1, policy_version 21150 (0.0007) -[2023-10-12 04:00:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 43417600. Throughput: 0: 1608.4, 1: 1596.3. Samples: 10857058. Policy #0 lag: (min: 11.0, avg: 20.6, max: 43.0) -[2023-10-12 04:00:15,202][77203] Avg episode reward: [(0, '40.730'), (1, '40.620')] -[2023-10-12 04:00:17,575][78091] Updated weights for policy 0, policy_version 21250 (0.0008) -[2023-10-12 04:00:17,788][78123] Updated weights for policy 1, policy_version 21160 (0.0009) -[2023-10-12 04:00:17,946][78091] Updated weights for policy 0, policy_version 21260 (0.0009) -[2023-10-12 04:00:18,155][78123] Updated weights for policy 1, policy_version 21170 (0.0009) -[2023-10-12 04:00:18,322][78091] Updated weights for policy 0, policy_version 21270 (0.0009) -[2023-10-12 04:00:18,525][78123] Updated weights for policy 1, policy_version 21180 (0.0008) -[2023-10-12 04:00:18,698][78091] Updated weights for policy 0, policy_version 21280 (0.0009) -[2023-10-12 04:00:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 43483136. Throughput: 0: 1594.3, 1: 1579.6. Samples: 10875242. Policy #0 lag: (min: 11.0, avg: 20.6, max: 43.0) -[2023-10-12 04:00:20,201][77203] Avg episode reward: [(0, '40.230'), (1, '41.430')] -[2023-10-12 04:00:22,967][78091] Updated weights for policy 0, policy_version 21290 (0.0009) -[2023-10-12 04:00:23,067][78123] Updated weights for policy 1, policy_version 21190 (0.0008) -[2023-10-12 04:00:23,348][78091] Updated weights for policy 0, policy_version 21300 (0.0008) -[2023-10-12 04:00:23,432][78123] Updated weights for policy 1, policy_version 21200 (0.0007) -[2023-10-12 04:00:23,715][78091] Updated weights for policy 0, policy_version 21310 (0.0008) -[2023-10-12 04:00:23,801][78123] Updated weights for policy 1, policy_version 21210 (0.0007) -[2023-10-12 04:00:25,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 43548672. Throughput: 0: 1587.2, 1: 1580.6. Samples: 10894504. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-12 04:00:25,201][77203] Avg episode reward: [(0, '41.310'), (1, '40.510')] -[2023-10-12 04:00:28,107][78091] Updated weights for policy 0, policy_version 21320 (0.0009) -[2023-10-12 04:00:28,170][78123] Updated weights for policy 1, policy_version 21220 (0.0008) -[2023-10-12 04:00:28,480][78091] Updated weights for policy 0, policy_version 21330 (0.0008) -[2023-10-12 04:00:28,533][78123] Updated weights for policy 1, policy_version 21230 (0.0007) -[2023-10-12 04:00:28,856][78091] Updated weights for policy 0, policy_version 21340 (0.0007) -[2023-10-12 04:00:28,892][78123] Updated weights for policy 1, policy_version 21240 (0.0009) -[2023-10-12 04:00:30,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 43614208. Throughput: 0: 1618.0, 1: 1605.5. Samples: 10905440. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-12 04:00:30,202][77203] Avg episode reward: [(0, '41.440'), (1, '44.300')] -[2023-10-12 04:00:33,105][78091] Updated weights for policy 0, policy_version 21350 (0.0010) -[2023-10-12 04:00:33,223][78123] Updated weights for policy 1, policy_version 21250 (0.0008) -[2023-10-12 04:00:33,472][78091] Updated weights for policy 0, policy_version 21360 (0.0007) -[2023-10-12 04:00:33,593][78123] Updated weights for policy 1, policy_version 21260 (0.0007) -[2023-10-12 04:00:33,843][78091] Updated weights for policy 0, policy_version 21370 (0.0007) -[2023-10-12 04:00:33,966][78123] Updated weights for policy 1, policy_version 21270 (0.0009) -[2023-10-12 04:00:34,330][78123] Updated weights for policy 1, policy_version 21280 (0.0007) -[2023-10-12 04:00:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 43679744. Throughput: 0: 1597.1, 1: 1593.9. Samples: 10923608. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-12 04:00:35,201][77203] Avg episode reward: [(0, '37.310'), (1, '41.550')] -[2023-10-12 04:00:38,451][78091] Updated weights for policy 0, policy_version 21380 (0.0010) -[2023-10-12 04:00:38,826][78091] Updated weights for policy 0, policy_version 21390 (0.0008) -[2023-10-12 04:00:38,847][78123] Updated weights for policy 1, policy_version 21290 (0.0009) -[2023-10-12 04:00:39,189][78091] Updated weights for policy 0, policy_version 21400 (0.0009) -[2023-10-12 04:00:39,211][78123] Updated weights for policy 1, policy_version 21300 (0.0008) -[2023-10-12 04:00:39,577][78123] Updated weights for policy 1, policy_version 21310 (0.0009) -[2023-10-12 04:00:40,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 43745280. Throughput: 0: 1582.5, 1: 1578.5. Samples: 10941564. Policy #0 lag: (min: 12.0, avg: 13.4, max: 38.0) -[2023-10-12 04:00:40,202][77203] Avg episode reward: [(0, '41.950'), (1, '39.060')] -[2023-10-12 04:00:43,639][78091] Updated weights for policy 0, policy_version 21410 (0.0007) -[2023-10-12 04:00:43,930][78123] Updated weights for policy 1, policy_version 21320 (0.0008) -[2023-10-12 04:00:44,020][78091] Updated weights for policy 0, policy_version 21420 (0.0008) -[2023-10-12 04:00:44,300][78123] Updated weights for policy 1, policy_version 21330 (0.0007) -[2023-10-12 04:00:44,387][78091] Updated weights for policy 0, policy_version 21430 (0.0009) -[2023-10-12 04:00:44,673][78123] Updated weights for policy 1, policy_version 21340 (0.0009) -[2023-10-12 04:00:44,762][78091] Updated weights for policy 0, policy_version 21440 (0.0009) -[2023-10-12 04:00:45,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 43810816. Throughput: 0: 1598.8, 1: 1592.4. Samples: 10952386. Policy #0 lag: (min: 12.0, avg: 13.4, max: 38.0) -[2023-10-12 04:00:45,202][77203] Avg episode reward: [(0, '37.110'), (1, '41.230')] -[2023-10-12 04:00:48,854][78123] Updated weights for policy 1, policy_version 21350 (0.0009) -[2023-10-12 04:00:48,954][78091] Updated weights for policy 0, policy_version 21450 (0.0010) -[2023-10-12 04:00:49,217][78123] Updated weights for policy 1, policy_version 21360 (0.0008) -[2023-10-12 04:00:49,329][78091] Updated weights for policy 0, policy_version 21460 (0.0008) -[2023-10-12 04:00:49,585][78123] Updated weights for policy 1, policy_version 21370 (0.0009) -[2023-10-12 04:00:49,703][78091] Updated weights for policy 0, policy_version 21470 (0.0010) -[2023-10-12 04:00:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 43876352. Throughput: 0: 1605.2, 1: 1595.5. Samples: 10971712. Policy #0 lag: (min: 12.0, avg: 13.4, max: 38.0) -[2023-10-12 04:00:50,201][77203] Avg episode reward: [(0, '40.510'), (1, '40.180')] -[2023-10-12 04:00:54,044][78091] Updated weights for policy 0, policy_version 21480 (0.0007) -[2023-10-12 04:00:54,133][78123] Updated weights for policy 1, policy_version 21380 (0.0008) -[2023-10-12 04:00:54,417][78091] Updated weights for policy 0, policy_version 21490 (0.0008) -[2023-10-12 04:00:54,501][78123] Updated weights for policy 1, policy_version 21390 (0.0008) -[2023-10-12 04:00:54,785][78091] Updated weights for policy 0, policy_version 21500 (0.0007) -[2023-10-12 04:00:54,865][78123] Updated weights for policy 1, policy_version 21400 (0.0008) -[2023-10-12 04:00:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 43941888. Throughput: 0: 1590.4, 1: 1577.0. Samples: 10989684. Policy #0 lag: (min: 15.0, avg: 22.9, max: 47.0) -[2023-10-12 04:00:55,202][77203] Avg episode reward: [(0, '39.640'), (1, '36.850')] -[2023-10-12 04:00:59,111][78091] Updated weights for policy 0, policy_version 21510 (0.0008) -[2023-10-12 04:00:59,379][78123] Updated weights for policy 1, policy_version 21410 (0.0008) -[2023-10-12 04:00:59,475][78091] Updated weights for policy 0, policy_version 21520 (0.0007) -[2023-10-12 04:00:59,745][78123] Updated weights for policy 1, policy_version 21420 (0.0008) -[2023-10-12 04:00:59,851][78091] Updated weights for policy 0, policy_version 21530 (0.0007) -[2023-10-12 04:01:00,112][78123] Updated weights for policy 1, policy_version 21430 (0.0010) -[2023-10-12 04:01:00,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 43974656. Throughput: 0: 1596.7, 1: 1577.2. Samples: 10999882. Policy #0 lag: (min: 15.0, avg: 22.9, max: 47.0) -[2023-10-12 04:01:00,201][77203] Avg episode reward: [(0, '39.340'), (1, '39.390')] -[2023-10-12 04:01:00,487][78123] Updated weights for policy 1, policy_version 21440 (0.0008) -[2023-10-12 04:01:04,100][78091] Updated weights for policy 0, policy_version 21540 (0.0009) -[2023-10-12 04:01:04,477][78091] Updated weights for policy 0, policy_version 21550 (0.0010) -[2023-10-12 04:01:04,774][78123] Updated weights for policy 1, policy_version 21450 (0.0009) -[2023-10-12 04:01:04,850][78091] Updated weights for policy 0, policy_version 21560 (0.0009) -[2023-10-12 04:01:05,146][78123] Updated weights for policy 1, policy_version 21460 (0.0009) -[2023-10-12 04:01:05,201][77203] Fps is (10 sec: 9830.7, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 44040192. Throughput: 0: 1610.6, 1: 1587.6. Samples: 11019164. Policy #0 lag: (min: 15.0, avg: 22.9, max: 47.0) -[2023-10-12 04:01:05,201][77203] Avg episode reward: [(0, '39.410'), (1, '34.910')] -[2023-10-12 04:01:05,512][78123] Updated weights for policy 1, policy_version 21470 (0.0008) -[2023-10-12 04:01:09,102][78091] Updated weights for policy 0, policy_version 21570 (0.0008) -[2023-10-12 04:01:09,504][78091] Updated weights for policy 0, policy_version 21580 (0.0008) -[2023-10-12 04:01:09,877][78091] Updated weights for policy 0, policy_version 21590 (0.0008) -[2023-10-12 04:01:09,990][78123] Updated weights for policy 1, policy_version 21480 (0.0008) -[2023-10-12 04:01:10,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 44072960. Throughput: 0: 1598.4, 1: 1585.1. Samples: 11037762. Policy #0 lag: (min: 15.0, avg: 22.9, max: 47.0) -[2023-10-12 04:01:10,202][77203] Avg episode reward: [(0, '38.360'), (1, '34.610')] -[2023-10-12 04:01:10,245][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000021600_22118400.pth... -[2023-10-12 04:01:10,247][78091] Updated weights for policy 0, policy_version 21600 (0.0009) -[2023-10-12 04:01:10,279][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000020096_20578304.pth -[2023-10-12 04:01:10,354][78123] Updated weights for policy 1, policy_version 21490 (0.0010) -[2023-10-12 04:01:10,730][78123] Updated weights for policy 1, policy_version 21500 (0.0007) -[2023-10-12 04:01:10,871][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000021504_22020096.pth... -[2023-10-12 04:01:10,900][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000020000_20480000.pth -[2023-10-12 04:01:14,567][78091] Updated weights for policy 0, policy_version 21610 (0.0008) -[2023-10-12 04:01:14,940][78091] Updated weights for policy 0, policy_version 21620 (0.0008) -[2023-10-12 04:01:15,114][78123] Updated weights for policy 1, policy_version 21510 (0.0007) -[2023-10-12 04:01:15,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 44138496. Throughput: 0: 1587.2, 1: 1560.8. Samples: 11047102. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-12 04:01:15,202][77203] Avg episode reward: [(0, '37.580'), (1, '40.130')] -[2023-10-12 04:01:15,300][78091] Updated weights for policy 0, policy_version 21630 (0.0009) -[2023-10-12 04:01:15,482][78123] Updated weights for policy 1, policy_version 21520 (0.0007) -[2023-10-12 04:01:15,846][78123] Updated weights for policy 1, policy_version 21530 (0.0008) -[2023-10-12 04:01:19,637][78091] Updated weights for policy 0, policy_version 21640 (0.0009) -[2023-10-12 04:01:20,012][78091] Updated weights for policy 0, policy_version 21650 (0.0009) -[2023-10-12 04:01:20,144][78123] Updated weights for policy 1, policy_version 21540 (0.0009) -[2023-10-12 04:01:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 44204032. Throughput: 0: 1607.3, 1: 1570.4. Samples: 11066604. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-12 04:01:20,202][77203] Avg episode reward: [(0, '36.250'), (1, '33.750')] -[2023-10-12 04:01:20,378][78091] Updated weights for policy 0, policy_version 21660 (0.0010) -[2023-10-12 04:01:20,504][78123] Updated weights for policy 1, policy_version 21550 (0.0009) -[2023-10-12 04:01:20,876][78123] Updated weights for policy 1, policy_version 21560 (0.0009) -[2023-10-12 04:01:24,784][78091] Updated weights for policy 0, policy_version 21670 (0.0007) -[2023-10-12 04:01:25,160][78091] Updated weights for policy 0, policy_version 21680 (0.0007) -[2023-10-12 04:01:25,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 44269568. Throughput: 0: 1615.0, 1: 1590.6. Samples: 11085816. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-12 04:01:25,202][77203] Avg episode reward: [(0, '39.360'), (1, '32.830')] -[2023-10-12 04:01:25,216][78123] Updated weights for policy 1, policy_version 21570 (0.0008) -[2023-10-12 04:01:25,526][78091] Updated weights for policy 0, policy_version 21690 (0.0007) -[2023-10-12 04:01:25,581][78123] Updated weights for policy 1, policy_version 21580 (0.0007) -[2023-10-12 04:01:25,951][78123] Updated weights for policy 1, policy_version 21590 (0.0007) -[2023-10-12 04:01:26,313][78123] Updated weights for policy 1, policy_version 21600 (0.0008) -[2023-10-12 04:01:29,669][78091] Updated weights for policy 0, policy_version 21700 (0.0009) -[2023-10-12 04:01:30,044][78091] Updated weights for policy 0, policy_version 21710 (0.0007) -[2023-10-12 04:01:30,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 44335104. Throughput: 0: 1593.2, 1: 1568.2. Samples: 11094648. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-12 04:01:30,201][77203] Avg episode reward: [(0, '38.620'), (1, '45.140')] -[2023-10-12 04:01:30,417][78091] Updated weights for policy 0, policy_version 21720 (0.0008) -[2023-10-12 04:01:30,638][78123] Updated weights for policy 1, policy_version 21610 (0.0007) -[2023-10-12 04:01:31,003][78123] Updated weights for policy 1, policy_version 21620 (0.0007) -[2023-10-12 04:01:31,369][78123] Updated weights for policy 1, policy_version 21630 (0.0009) -[2023-10-12 04:01:34,699][78091] Updated weights for policy 0, policy_version 21730 (0.0008) -[2023-10-12 04:01:35,064][78091] Updated weights for policy 0, policy_version 21740 (0.0008) -[2023-10-12 04:01:35,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 44400640. Throughput: 0: 1596.0, 1: 1570.1. Samples: 11114190. Policy #0 lag: (min: 31.0, avg: 32.5, max: 58.0) -[2023-10-12 04:01:35,201][77203] Avg episode reward: [(0, '39.700'), (1, '34.380')] -[2023-10-12 04:01:35,428][78123] Updated weights for policy 1, policy_version 21640 (0.0009) -[2023-10-12 04:01:35,429][78091] Updated weights for policy 0, policy_version 21750 (0.0008) -[2023-10-12 04:01:35,800][78123] Updated weights for policy 1, policy_version 21650 (0.0010) -[2023-10-12 04:01:35,811][78091] Updated weights for policy 0, policy_version 21760 (0.0008) -[2023-10-12 04:01:36,170][78123] Updated weights for policy 1, policy_version 21660 (0.0007) -[2023-10-12 04:01:40,074][78091] Updated weights for policy 0, policy_version 21770 (0.0010) -[2023-10-12 04:01:40,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 44466176. Throughput: 0: 1610.4, 1: 1587.4. Samples: 11133586. Policy #0 lag: (min: 31.0, avg: 32.5, max: 58.0) -[2023-10-12 04:01:40,202][77203] Avg episode reward: [(0, '40.100'), (1, '32.700')] -[2023-10-12 04:01:40,448][78091] Updated weights for policy 0, policy_version 21780 (0.0007) -[2023-10-12 04:01:40,581][78123] Updated weights for policy 1, policy_version 21670 (0.0008) -[2023-10-12 04:01:40,823][78091] Updated weights for policy 0, policy_version 21790 (0.0007) -[2023-10-12 04:01:40,939][78123] Updated weights for policy 1, policy_version 21680 (0.0007) -[2023-10-12 04:01:41,302][78123] Updated weights for policy 1, policy_version 21690 (0.0008) -[2023-10-12 04:01:45,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 44531712. Throughput: 0: 1586.8, 1: 1573.4. Samples: 11142092. Policy #0 lag: (min: 31.0, avg: 32.5, max: 58.0) -[2023-10-12 04:01:45,201][77203] Avg episode reward: [(0, '38.320'), (1, '40.540')] -[2023-10-12 04:01:45,209][78091] Updated weights for policy 0, policy_version 21800 (0.0009) -[2023-10-12 04:01:45,579][78091] Updated weights for policy 0, policy_version 21810 (0.0010) -[2023-10-12 04:01:45,882][78123] Updated weights for policy 1, policy_version 21700 (0.0007) -[2023-10-12 04:01:45,946][78091] Updated weights for policy 0, policy_version 21820 (0.0008) -[2023-10-12 04:01:46,257][78123] Updated weights for policy 1, policy_version 21710 (0.0009) -[2023-10-12 04:01:46,621][78123] Updated weights for policy 1, policy_version 21720 (0.0010) -[2023-10-12 04:01:50,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 44597248. Throughput: 0: 1582.5, 1: 1571.6. Samples: 11161100. Policy #0 lag: (min: 31.0, avg: 32.5, max: 58.0) -[2023-10-12 04:01:50,201][77203] Avg episode reward: [(0, '39.320'), (1, '35.730')] -[2023-10-12 04:01:50,367][78091] Updated weights for policy 0, policy_version 21830 (0.0008) -[2023-10-12 04:01:50,733][78091] Updated weights for policy 0, policy_version 21840 (0.0008) -[2023-10-12 04:01:50,997][78123] Updated weights for policy 1, policy_version 21730 (0.0009) -[2023-10-12 04:01:51,106][78091] Updated weights for policy 0, policy_version 21850 (0.0008) -[2023-10-12 04:01:51,360][78123] Updated weights for policy 1, policy_version 21740 (0.0007) -[2023-10-12 04:01:51,724][78123] Updated weights for policy 1, policy_version 21750 (0.0008) -[2023-10-12 04:01:52,098][78123] Updated weights for policy 1, policy_version 21760 (0.0009) -[2023-10-12 04:01:55,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 44662784. Throughput: 0: 1591.5, 1: 1568.2. Samples: 11179946. Policy #0 lag: (min: 13.0, avg: 19.9, max: 45.0) -[2023-10-12 04:01:55,202][77203] Avg episode reward: [(0, '42.360'), (1, '35.750')] -[2023-10-12 04:01:55,617][78091] Updated weights for policy 0, policy_version 21860 (0.0009) -[2023-10-12 04:01:56,000][78091] Updated weights for policy 0, policy_version 21870 (0.0009) -[2023-10-12 04:01:56,379][78091] Updated weights for policy 0, policy_version 21880 (0.0009) -[2023-10-12 04:01:56,663][78123] Updated weights for policy 1, policy_version 21770 (0.0009) -[2023-10-12 04:01:57,026][78123] Updated weights for policy 1, policy_version 21780 (0.0009) -[2023-10-12 04:01:57,398][78123] Updated weights for policy 1, policy_version 21790 (0.0008) -[2023-10-12 04:02:00,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 44728320. Throughput: 0: 1570.2, 1: 1568.3. Samples: 11188334. Policy #0 lag: (min: 13.0, avg: 19.9, max: 45.0) -[2023-10-12 04:02:00,201][77203] Avg episode reward: [(0, '38.500'), (1, '41.230')] -[2023-10-12 04:02:00,828][78091] Updated weights for policy 0, policy_version 21890 (0.0008) -[2023-10-12 04:02:01,193][78091] Updated weights for policy 0, policy_version 21900 (0.0010) -[2023-10-12 04:02:01,567][78091] Updated weights for policy 0, policy_version 21910 (0.0011) -[2023-10-12 04:02:01,794][78123] Updated weights for policy 1, policy_version 21800 (0.0009) -[2023-10-12 04:02:01,927][78091] Updated weights for policy 0, policy_version 21920 (0.0007) -[2023-10-12 04:02:02,163][78123] Updated weights for policy 1, policy_version 21810 (0.0009) -[2023-10-12 04:02:02,530][78123] Updated weights for policy 1, policy_version 21820 (0.0010) -[2023-10-12 04:02:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 44793856. Throughput: 0: 1569.5, 1: 1561.9. Samples: 11207516. Policy #0 lag: (min: 13.0, avg: 19.9, max: 45.0) -[2023-10-12 04:02:05,202][77203] Avg episode reward: [(0, '40.280'), (1, '35.300')] -[2023-10-12 04:02:06,347][78091] Updated weights for policy 0, policy_version 21930 (0.0009) -[2023-10-12 04:02:06,715][78091] Updated weights for policy 0, policy_version 21940 (0.0010) -[2023-10-12 04:02:07,071][78123] Updated weights for policy 1, policy_version 21830 (0.0009) -[2023-10-12 04:02:07,082][78091] Updated weights for policy 0, policy_version 21950 (0.0009) -[2023-10-12 04:02:07,439][78123] Updated weights for policy 1, policy_version 21840 (0.0008) -[2023-10-12 04:02:07,808][78123] Updated weights for policy 1, policy_version 21850 (0.0009) -[2023-10-12 04:02:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 44859392. Throughput: 0: 1571.4, 1: 1554.3. Samples: 11226470. Policy #0 lag: (min: 1.0, avg: 4.9, max: 33.0) -[2023-10-12 04:02:10,201][77203] Avg episode reward: [(0, '42.760'), (1, '38.050')] -[2023-10-12 04:02:11,517][78091] Updated weights for policy 0, policy_version 21960 (0.0010) -[2023-10-12 04:02:11,893][78091] Updated weights for policy 0, policy_version 21970 (0.0009) -[2023-10-12 04:02:12,262][78091] Updated weights for policy 0, policy_version 21980 (0.0009) -[2023-10-12 04:02:12,346][78123] Updated weights for policy 1, policy_version 21860 (0.0009) -[2023-10-12 04:02:12,705][78123] Updated weights for policy 1, policy_version 21870 (0.0010) -[2023-10-12 04:02:13,076][78123] Updated weights for policy 1, policy_version 21880 (0.0009) -[2023-10-12 04:02:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 44924928. Throughput: 0: 1563.9, 1: 1565.2. Samples: 11235460. Policy #0 lag: (min: 1.0, avg: 4.9, max: 33.0) -[2023-10-12 04:02:15,202][77203] Avg episode reward: [(0, '41.070'), (1, '43.020')] -[2023-10-12 04:02:16,683][78091] Updated weights for policy 0, policy_version 21990 (0.0009) -[2023-10-12 04:02:17,049][78091] Updated weights for policy 0, policy_version 22000 (0.0009) -[2023-10-12 04:02:17,423][78091] Updated weights for policy 0, policy_version 22010 (0.0008) -[2023-10-12 04:02:17,656][78123] Updated weights for policy 1, policy_version 21890 (0.0007) -[2023-10-12 04:02:18,020][78123] Updated weights for policy 1, policy_version 21900 (0.0008) -[2023-10-12 04:02:18,382][78123] Updated weights for policy 1, policy_version 21910 (0.0009) -[2023-10-12 04:02:18,749][78123] Updated weights for policy 1, policy_version 21920 (0.0008) -[2023-10-12 04:02:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 44990464. Throughput: 0: 1558.6, 1: 1547.2. Samples: 11253954. Policy #0 lag: (min: 1.0, avg: 4.9, max: 33.0) -[2023-10-12 04:02:20,202][77203] Avg episode reward: [(0, '39.940'), (1, '34.990')] -[2023-10-12 04:02:21,918][78091] Updated weights for policy 0, policy_version 22020 (0.0009) -[2023-10-12 04:02:22,289][78091] Updated weights for policy 0, policy_version 22030 (0.0010) -[2023-10-12 04:02:22,662][78091] Updated weights for policy 0, policy_version 22040 (0.0009) -[2023-10-12 04:02:23,331][78123] Updated weights for policy 1, policy_version 21930 (0.0009) -[2023-10-12 04:02:23,691][78123] Updated weights for policy 1, policy_version 21940 (0.0008) -[2023-10-12 04:02:24,056][78123] Updated weights for policy 1, policy_version 21950 (0.0009) -[2023-10-12 04:02:25,201][77203] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 45056000. Throughput: 0: 1548.2, 1: 1535.5. Samples: 11272352. Policy #0 lag: (min: 21.0, avg: 26.2, max: 53.0) -[2023-10-12 04:02:25,201][77203] Avg episode reward: [(0, '41.340'), (1, '41.020')] -[2023-10-12 04:02:27,255][78091] Updated weights for policy 0, policy_version 22050 (0.0011) -[2023-10-12 04:02:27,627][78091] Updated weights for policy 0, policy_version 22060 (0.0007) -[2023-10-12 04:02:27,998][78091] Updated weights for policy 0, policy_version 22070 (0.0008) -[2023-10-12 04:02:28,362][78091] Updated weights for policy 0, policy_version 22080 (0.0009) -[2023-10-12 04:02:28,487][78123] Updated weights for policy 1, policy_version 21960 (0.0009) -[2023-10-12 04:02:28,854][78123] Updated weights for policy 1, policy_version 21970 (0.0007) -[2023-10-12 04:02:29,224][78123] Updated weights for policy 1, policy_version 21980 (0.0008) -[2023-10-12 04:02:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 45121536. Throughput: 0: 1558.9, 1: 1555.9. Samples: 11282260. Policy #0 lag: (min: 21.0, avg: 26.2, max: 53.0) -[2023-10-12 04:02:30,201][77203] Avg episode reward: [(0, '40.500'), (1, '37.960')] -[2023-10-12 04:02:32,735][78091] Updated weights for policy 0, policy_version 22090 (0.0011) -[2023-10-12 04:02:33,111][78091] Updated weights for policy 0, policy_version 22100 (0.0009) -[2023-10-12 04:02:33,475][78091] Updated weights for policy 0, policy_version 22110 (0.0007) -[2023-10-12 04:02:33,635][78123] Updated weights for policy 1, policy_version 21990 (0.0010) -[2023-10-12 04:02:34,016][78123] Updated weights for policy 1, policy_version 22000 (0.0008) -[2023-10-12 04:02:34,385][78123] Updated weights for policy 1, policy_version 22010 (0.0009) -[2023-10-12 04:02:35,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 45187072. Throughput: 0: 1549.4, 1: 1555.0. Samples: 11300798. Policy #0 lag: (min: 21.0, avg: 26.2, max: 53.0) -[2023-10-12 04:02:35,202][77203] Avg episode reward: [(0, '39.220'), (1, '33.930')] -[2023-10-12 04:02:37,704][78091] Updated weights for policy 0, policy_version 22120 (0.0009) -[2023-10-12 04:02:38,076][78091] Updated weights for policy 0, policy_version 22130 (0.0007) -[2023-10-12 04:02:38,448][78091] Updated weights for policy 0, policy_version 22140 (0.0008) -[2023-10-12 04:02:38,511][78123] Updated weights for policy 1, policy_version 22020 (0.0009) -[2023-10-12 04:02:38,870][78123] Updated weights for policy 1, policy_version 22030 (0.0007) -[2023-10-12 04:02:39,233][78123] Updated weights for policy 1, policy_version 22040 (0.0008) -[2023-10-12 04:02:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 45252608. Throughput: 0: 1553.1, 1: 1548.1. Samples: 11319498. Policy #0 lag: (min: 2.0, avg: 2.5, max: 17.0) -[2023-10-12 04:02:40,201][77203] Avg episode reward: [(0, '40.010'), (1, '42.430')] -[2023-10-12 04:02:42,961][78091] Updated weights for policy 0, policy_version 22150 (0.0007) -[2023-10-12 04:02:43,338][78091] Updated weights for policy 0, policy_version 22160 (0.0009) -[2023-10-12 04:02:43,600][78123] Updated weights for policy 1, policy_version 22050 (0.0010) -[2023-10-12 04:02:43,711][78091] Updated weights for policy 0, policy_version 22170 (0.0007) -[2023-10-12 04:02:43,959][78123] Updated weights for policy 1, policy_version 22060 (0.0007) -[2023-10-12 04:02:44,329][78123] Updated weights for policy 1, policy_version 22070 (0.0009) -[2023-10-12 04:02:44,693][78123] Updated weights for policy 1, policy_version 22080 (0.0008) -[2023-10-12 04:02:45,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 45318144. Throughput: 0: 1577.3, 1: 1573.4. Samples: 11330116. Policy #0 lag: (min: 2.0, avg: 2.5, max: 17.0) -[2023-10-12 04:02:45,202][77203] Avg episode reward: [(0, '40.630'), (1, '37.110')] -[2023-10-12 04:02:48,120][78091] Updated weights for policy 0, policy_version 22180 (0.0009) -[2023-10-12 04:02:48,489][78091] Updated weights for policy 0, policy_version 22190 (0.0009) -[2023-10-12 04:02:48,855][78091] Updated weights for policy 0, policy_version 22200 (0.0009) -[2023-10-12 04:02:49,348][78123] Updated weights for policy 1, policy_version 22090 (0.0009) -[2023-10-12 04:02:49,720][78123] Updated weights for policy 1, policy_version 22100 (0.0008) -[2023-10-12 04:02:50,087][78123] Updated weights for policy 1, policy_version 22110 (0.0008) -[2023-10-12 04:02:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 45383680. Throughput: 0: 1559.7, 1: 1571.9. Samples: 11348438. Policy #0 lag: (min: 2.0, avg: 2.5, max: 17.0) -[2023-10-12 04:02:50,202][77203] Avg episode reward: [(0, '38.440'), (1, '35.280')] -[2023-10-12 04:02:53,235][78091] Updated weights for policy 0, policy_version 22210 (0.0009) -[2023-10-12 04:02:53,613][78091] Updated weights for policy 0, policy_version 22220 (0.0010) -[2023-10-12 04:02:53,987][78091] Updated weights for policy 0, policy_version 22230 (0.0010) -[2023-10-12 04:02:54,352][78091] Updated weights for policy 0, policy_version 22240 (0.0008) -[2023-10-12 04:02:54,649][78123] Updated weights for policy 1, policy_version 22120 (0.0009) -[2023-10-12 04:02:55,013][78123] Updated weights for policy 1, policy_version 22130 (0.0009) -[2023-10-12 04:02:55,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12551.8). Total num frames: 45416448. Throughput: 0: 1550.8, 1: 1563.0. Samples: 11366590. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:02:55,201][77203] Avg episode reward: [(0, '39.580'), (1, '39.510')] -[2023-10-12 04:02:55,384][78123] Updated weights for policy 1, policy_version 22140 (0.0010) -[2023-10-12 04:02:58,717][78091] Updated weights for policy 0, policy_version 22250 (0.0009) -[2023-10-12 04:02:59,087][78091] Updated weights for policy 0, policy_version 22260 (0.0007) -[2023-10-12 04:02:59,450][78091] Updated weights for policy 0, policy_version 22270 (0.0009) -[2023-10-12 04:02:59,740][78123] Updated weights for policy 1, policy_version 22150 (0.0009) -[2023-10-12 04:03:00,104][78123] Updated weights for policy 1, policy_version 22160 (0.0009) -[2023-10-12 04:03:00,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12551.8). Total num frames: 45481984. Throughput: 0: 1577.1, 1: 1555.8. Samples: 11376438. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:03:00,201][77203] Avg episode reward: [(0, '38.110'), (1, '36.610')] -[2023-10-12 04:03:00,469][78123] Updated weights for policy 1, policy_version 22170 (0.0008) -[2023-10-12 04:03:03,941][78091] Updated weights for policy 0, policy_version 22280 (0.0010) -[2023-10-12 04:03:04,307][78091] Updated weights for policy 0, policy_version 22290 (0.0009) -[2023-10-12 04:03:04,689][78091] Updated weights for policy 0, policy_version 22300 (0.0009) -[2023-10-12 04:03:04,894][78123] Updated weights for policy 1, policy_version 22180 (0.0007) -[2023-10-12 04:03:05,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12551.8). Total num frames: 45547520. Throughput: 0: 1573.0, 1: 1570.3. Samples: 11395402. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:03:05,201][77203] Avg episode reward: [(0, '39.530'), (1, '39.610')] -[2023-10-12 04:03:05,254][78123] Updated weights for policy 1, policy_version 22190 (0.0008) -[2023-10-12 04:03:05,628][78123] Updated weights for policy 1, policy_version 22200 (0.0010) -[2023-10-12 04:03:08,973][78091] Updated weights for policy 0, policy_version 22310 (0.0009) -[2023-10-12 04:03:09,333][78091] Updated weights for policy 0, policy_version 22320 (0.0009) -[2023-10-12 04:03:09,712][78091] Updated weights for policy 0, policy_version 22330 (0.0010) -[2023-10-12 04:03:10,054][78123] Updated weights for policy 1, policy_version 22210 (0.0011) -[2023-10-12 04:03:10,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12551.8). Total num frames: 45613056. Throughput: 0: 1561.4, 1: 1578.0. Samples: 11413626. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:03:10,202][77203] Avg episode reward: [(0, '38.510'), (1, '36.180')] -[2023-10-12 04:03:10,210][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000022336_22872064.pth... -[2023-10-12 04:03:10,240][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000020832_21331968.pth -[2023-10-12 04:03:10,245][77792] Saving a milestone ./train_atari/atari_hero_APPO/checkpoint_p0/milestones/checkpoint_000022336_22872064.pth -[2023-10-12 04:03:10,416][78123] Updated weights for policy 1, policy_version 22220 (0.0009) -[2023-10-12 04:03:10,778][78123] Updated weights for policy 1, policy_version 22230 (0.0010) -[2023-10-12 04:03:11,151][78123] Updated weights for policy 1, policy_version 22240 (0.0008) -[2023-10-12 04:03:11,151][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000022240_22773760.pth... -[2023-10-12 04:03:11,191][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000020736_21233664.pth -[2023-10-12 04:03:11,197][77950] Saving a milestone ./train_atari/atari_hero_APPO/checkpoint_p1/milestones/checkpoint_000022240_22773760.pth -[2023-10-12 04:03:14,200][78091] Updated weights for policy 0, policy_version 22340 (0.0009) -[2023-10-12 04:03:14,579][78091] Updated weights for policy 0, policy_version 22350 (0.0008) -[2023-10-12 04:03:14,948][78091] Updated weights for policy 0, policy_version 22360 (0.0009) -[2023-10-12 04:03:15,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12015.0, 300 sec: 12440.7). Total num frames: 45645824. Throughput: 0: 1574.7, 1: 1556.0. Samples: 11423142. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:03:15,201][77203] Avg episode reward: [(0, '41.420'), (1, '37.540')] -[2023-10-12 04:03:15,549][78123] Updated weights for policy 1, policy_version 22250 (0.0007) -[2023-10-12 04:03:15,930][78123] Updated weights for policy 1, policy_version 22260 (0.0009) -[2023-10-12 04:03:16,294][78123] Updated weights for policy 1, policy_version 22270 (0.0010) -[2023-10-12 04:03:19,323][78091] Updated weights for policy 0, policy_version 22370 (0.0008) -[2023-10-12 04:03:19,701][78091] Updated weights for policy 0, policy_version 22380 (0.0009) -[2023-10-12 04:03:20,074][78091] Updated weights for policy 0, policy_version 22390 (0.0007) -[2023-10-12 04:03:20,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12014.9, 300 sec: 12551.8). Total num frames: 45711360. Throughput: 0: 1591.7, 1: 1563.8. Samples: 11442796. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-12 04:03:20,201][77203] Avg episode reward: [(0, '40.050'), (1, '37.340')] -[2023-10-12 04:03:20,446][78091] Updated weights for policy 0, policy_version 22400 (0.0008) -[2023-10-12 04:03:20,703][78123] Updated weights for policy 1, policy_version 22280 (0.0009) -[2023-10-12 04:03:21,063][78123] Updated weights for policy 1, policy_version 22290 (0.0008) -[2023-10-12 04:03:21,432][78123] Updated weights for policy 1, policy_version 22300 (0.0008) -[2023-10-12 04:03:24,755][78091] Updated weights for policy 0, policy_version 22410 (0.0009) -[2023-10-12 04:03:25,121][78091] Updated weights for policy 0, policy_version 22420 (0.0009) -[2023-10-12 04:03:25,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12014.9, 300 sec: 12551.8). Total num frames: 45776896. Throughput: 0: 1584.0, 1: 1582.8. Samples: 11462006. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-12 04:03:25,201][77203] Avg episode reward: [(0, '36.390'), (1, '35.670')] -[2023-10-12 04:03:25,505][78091] Updated weights for policy 0, policy_version 22430 (0.0008) -[2023-10-12 04:03:25,702][78123] Updated weights for policy 1, policy_version 22310 (0.0009) -[2023-10-12 04:03:26,088][78123] Updated weights for policy 1, policy_version 22320 (0.0009) -[2023-10-12 04:03:26,453][78123] Updated weights for policy 1, policy_version 22330 (0.0008) -[2023-10-12 04:03:29,757][78091] Updated weights for policy 0, policy_version 22440 (0.0009) -[2023-10-12 04:03:30,124][78091] Updated weights for policy 0, policy_version 22450 (0.0008) -[2023-10-12 04:03:30,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12014.9, 300 sec: 12551.8). Total num frames: 45842432. Throughput: 0: 1577.1, 1: 1559.6. Samples: 11471266. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-12 04:03:30,201][77203] Avg episode reward: [(0, '42.480'), (1, '40.750')] -[2023-10-12 04:03:30,500][78091] Updated weights for policy 0, policy_version 22460 (0.0008) -[2023-10-12 04:03:30,916][78123] Updated weights for policy 1, policy_version 22340 (0.0008) -[2023-10-12 04:03:31,287][78123] Updated weights for policy 1, policy_version 22350 (0.0008) -[2023-10-12 04:03:31,661][78123] Updated weights for policy 1, policy_version 22360 (0.0007) -[2023-10-12 04:03:34,790][78091] Updated weights for policy 0, policy_version 22470 (0.0007) -[2023-10-12 04:03:35,159][78091] Updated weights for policy 0, policy_version 22480 (0.0007) -[2023-10-12 04:03:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 45907968. Throughput: 0: 1594.7, 1: 1568.1. Samples: 11490766. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-12 04:03:35,201][77203] Avg episode reward: [(0, '36.430'), (1, '39.070')] -[2023-10-12 04:03:35,527][78091] Updated weights for policy 0, policy_version 22490 (0.0008) -[2023-10-12 04:03:35,842][78123] Updated weights for policy 1, policy_version 22370 (0.0007) -[2023-10-12 04:03:36,202][78123] Updated weights for policy 1, policy_version 22380 (0.0009) -[2023-10-12 04:03:36,573][78123] Updated weights for policy 1, policy_version 22390 (0.0009) -[2023-10-12 04:03:36,932][78123] Updated weights for policy 1, policy_version 22400 (0.0009) -[2023-10-12 04:03:39,798][78091] Updated weights for policy 0, policy_version 22500 (0.0009) -[2023-10-12 04:03:40,167][78091] Updated weights for policy 0, policy_version 22510 (0.0011) -[2023-10-12 04:03:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 45973504. Throughput: 0: 1608.4, 1: 1585.3. Samples: 11510304. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 04:03:40,201][77203] Avg episode reward: [(0, '40.420'), (1, '38.840')] -[2023-10-12 04:03:40,535][78091] Updated weights for policy 0, policy_version 22520 (0.0008) -[2023-10-12 04:03:41,172][78123] Updated weights for policy 1, policy_version 22410 (0.0008) -[2023-10-12 04:03:41,538][78123] Updated weights for policy 1, policy_version 22420 (0.0008) -[2023-10-12 04:03:41,908][78123] Updated weights for policy 1, policy_version 22430 (0.0008) -[2023-10-12 04:03:44,787][78091] Updated weights for policy 0, policy_version 22530 (0.0008) -[2023-10-12 04:03:45,161][78091] Updated weights for policy 0, policy_version 22540 (0.0009) -[2023-10-12 04:03:45,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 46039040. Throughput: 0: 1587.5, 1: 1580.5. Samples: 11518996. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 04:03:45,202][77203] Avg episode reward: [(0, '39.860'), (1, '39.120')] -[2023-10-12 04:03:45,520][78091] Updated weights for policy 0, policy_version 22550 (0.0008) -[2023-10-12 04:03:45,897][78091] Updated weights for policy 0, policy_version 22560 (0.0009) -[2023-10-12 04:03:46,177][78123] Updated weights for policy 1, policy_version 22440 (0.0009) -[2023-10-12 04:03:46,552][78123] Updated weights for policy 1, policy_version 22450 (0.0010) -[2023-10-12 04:03:46,919][78123] Updated weights for policy 1, policy_version 22460 (0.0010) -[2023-10-12 04:03:50,187][78091] Updated weights for policy 0, policy_version 22570 (0.0009) -[2023-10-12 04:03:50,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 46104576. Throughput: 0: 1595.6, 1: 1585.6. Samples: 11538554. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 04:03:50,202][77203] Avg episode reward: [(0, '37.610'), (1, '36.470')] -[2023-10-12 04:03:50,555][78091] Updated weights for policy 0, policy_version 22580 (0.0009) -[2023-10-12 04:03:50,932][78091] Updated weights for policy 0, policy_version 22590 (0.0009) -[2023-10-12 04:03:51,428][78123] Updated weights for policy 1, policy_version 22470 (0.0009) -[2023-10-12 04:03:51,798][78123] Updated weights for policy 1, policy_version 22480 (0.0007) -[2023-10-12 04:03:52,170][78123] Updated weights for policy 1, policy_version 22490 (0.0007) -[2023-10-12 04:03:55,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 46170112. Throughput: 0: 1618.7, 1: 1591.6. Samples: 11558090. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 04:03:55,202][77203] Avg episode reward: [(0, '41.070'), (1, '42.750')] -[2023-10-12 04:03:55,248][78091] Updated weights for policy 0, policy_version 22600 (0.0008) -[2023-10-12 04:03:55,620][78091] Updated weights for policy 0, policy_version 22610 (0.0008) -[2023-10-12 04:03:55,983][78091] Updated weights for policy 0, policy_version 22620 (0.0007) -[2023-10-12 04:03:56,373][78123] Updated weights for policy 1, policy_version 22500 (0.0008) -[2023-10-12 04:03:56,743][78123] Updated weights for policy 1, policy_version 22510 (0.0009) -[2023-10-12 04:03:57,112][78123] Updated weights for policy 1, policy_version 22520 (0.0010) -[2023-10-12 04:04:00,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 46235648. Throughput: 0: 1598.4, 1: 1594.9. Samples: 11566844. Policy #0 lag: (min: 31.0, avg: 32.5, max: 59.0) -[2023-10-12 04:04:00,201][77203] Avg episode reward: [(0, '40.910'), (1, '37.610')] -[2023-10-12 04:04:00,414][78091] Updated weights for policy 0, policy_version 22630 (0.0009) -[2023-10-12 04:04:00,793][78091] Updated weights for policy 0, policy_version 22640 (0.0009) -[2023-10-12 04:04:01,157][78091] Updated weights for policy 0, policy_version 22650 (0.0007) -[2023-10-12 04:04:01,232][78123] Updated weights for policy 1, policy_version 22530 (0.0011) -[2023-10-12 04:04:01,607][78123] Updated weights for policy 1, policy_version 22540 (0.0009) -[2023-10-12 04:04:01,969][78123] Updated weights for policy 1, policy_version 22550 (0.0007) -[2023-10-12 04:04:02,341][78123] Updated weights for policy 1, policy_version 22560 (0.0008) -[2023-10-12 04:04:05,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 46301184. Throughput: 0: 1593.4, 1: 1598.4. Samples: 11586426. Policy #0 lag: (min: 31.0, avg: 32.5, max: 59.0) -[2023-10-12 04:04:05,201][77203] Avg episode reward: [(0, '39.470'), (1, '38.430')] -[2023-10-12 04:04:05,451][78091] Updated weights for policy 0, policy_version 22660 (0.0009) -[2023-10-12 04:04:05,825][78091] Updated weights for policy 0, policy_version 22670 (0.0010) -[2023-10-12 04:04:06,196][78091] Updated weights for policy 0, policy_version 22680 (0.0011) -[2023-10-12 04:04:06,768][78123] Updated weights for policy 1, policy_version 22570 (0.0007) -[2023-10-12 04:04:07,141][78123] Updated weights for policy 1, policy_version 22580 (0.0009) -[2023-10-12 04:04:07,503][78123] Updated weights for policy 1, policy_version 22590 (0.0009) -[2023-10-12 04:04:10,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 46366720. Throughput: 0: 1599.9, 1: 1591.5. Samples: 11605618. Policy #0 lag: (min: 31.0, avg: 32.5, max: 59.0) -[2023-10-12 04:04:10,201][77203] Avg episode reward: [(0, '40.990'), (1, '43.750')] -[2023-10-12 04:04:10,598][78091] Updated weights for policy 0, policy_version 22690 (0.0008) -[2023-10-12 04:04:10,966][78091] Updated weights for policy 0, policy_version 22700 (0.0009) -[2023-10-12 04:04:11,345][78091] Updated weights for policy 0, policy_version 22710 (0.0007) -[2023-10-12 04:04:11,704][78091] Updated weights for policy 0, policy_version 22720 (0.0009) -[2023-10-12 04:04:11,880][78123] Updated weights for policy 1, policy_version 22600 (0.0008) -[2023-10-12 04:04:12,252][78123] Updated weights for policy 1, policy_version 22610 (0.0008) -[2023-10-12 04:04:12,625][78123] Updated weights for policy 1, policy_version 22620 (0.0010) -[2023-10-12 04:04:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 46432256. Throughput: 0: 1585.2, 1: 1591.9. Samples: 11614234. Policy #0 lag: (min: 31.0, avg: 32.5, max: 59.0) -[2023-10-12 04:04:15,202][77203] Avg episode reward: [(0, '41.810'), (1, '37.690')] -[2023-10-12 04:04:15,987][78091] Updated weights for policy 0, policy_version 22730 (0.0009) -[2023-10-12 04:04:16,361][78091] Updated weights for policy 0, policy_version 22740 (0.0009) -[2023-10-12 04:04:16,729][78091] Updated weights for policy 0, policy_version 22750 (0.0009) -[2023-10-12 04:04:16,896][78123] Updated weights for policy 1, policy_version 22630 (0.0008) -[2023-10-12 04:04:17,263][78123] Updated weights for policy 1, policy_version 22640 (0.0007) -[2023-10-12 04:04:17,627][78123] Updated weights for policy 1, policy_version 22650 (0.0010) -[2023-10-12 04:04:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 46497792. Throughput: 0: 1587.1, 1: 1591.5. Samples: 11633800. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-10-12 04:04:20,201][77203] Avg episode reward: [(0, '39.400'), (1, '38.190')] -[2023-10-12 04:04:21,047][78091] Updated weights for policy 0, policy_version 22760 (0.0007) -[2023-10-12 04:04:21,424][78091] Updated weights for policy 0, policy_version 22770 (0.0009) -[2023-10-12 04:04:21,795][78091] Updated weights for policy 0, policy_version 22780 (0.0009) -[2023-10-12 04:04:21,854][78123] Updated weights for policy 1, policy_version 22660 (0.0008) -[2023-10-12 04:04:22,230][78123] Updated weights for policy 1, policy_version 22670 (0.0008) -[2023-10-12 04:04:22,594][78123] Updated weights for policy 1, policy_version 22680 (0.0011) -[2023-10-12 04:04:25,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 46563328. Throughput: 0: 1586.4, 1: 1595.0. Samples: 11653468. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-10-12 04:04:25,202][77203] Avg episode reward: [(0, '41.860'), (1, '40.360')] -[2023-10-12 04:04:26,011][78091] Updated weights for policy 0, policy_version 22790 (0.0008) -[2023-10-12 04:04:26,378][78091] Updated weights for policy 0, policy_version 22800 (0.0008) -[2023-10-12 04:04:26,752][78091] Updated weights for policy 0, policy_version 22810 (0.0007) -[2023-10-12 04:04:26,848][78123] Updated weights for policy 1, policy_version 22690 (0.0008) -[2023-10-12 04:04:27,204][78123] Updated weights for policy 1, policy_version 22700 (0.0007) -[2023-10-12 04:04:27,579][78123] Updated weights for policy 1, policy_version 22710 (0.0007) -[2023-10-12 04:04:27,942][78123] Updated weights for policy 1, policy_version 22720 (0.0007) -[2023-10-12 04:04:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 46628864. Throughput: 0: 1583.4, 1: 1602.5. Samples: 11662360. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-10-12 04:04:30,201][77203] Avg episode reward: [(0, '40.220'), (1, '35.200')] -[2023-10-12 04:04:31,145][78091] Updated weights for policy 0, policy_version 22820 (0.0008) -[2023-10-12 04:04:31,506][78091] Updated weights for policy 0, policy_version 22830 (0.0008) -[2023-10-12 04:04:31,878][78091] Updated weights for policy 0, policy_version 22840 (0.0009) -[2023-10-12 04:04:32,363][78123] Updated weights for policy 1, policy_version 22730 (0.0010) -[2023-10-12 04:04:32,740][78123] Updated weights for policy 1, policy_version 22740 (0.0009) -[2023-10-12 04:04:33,097][78123] Updated weights for policy 1, policy_version 22750 (0.0008) -[2023-10-12 04:04:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.1, 300 sec: 12662.9). Total num frames: 46694400. Throughput: 0: 1584.4, 1: 1595.4. Samples: 11681646. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-10-12 04:04:35,202][77203] Avg episode reward: [(0, '38.290'), (1, '38.300')] -[2023-10-12 04:04:36,052][78091] Updated weights for policy 0, policy_version 22850 (0.0009) -[2023-10-12 04:04:36,411][78091] Updated weights for policy 0, policy_version 22860 (0.0008) -[2023-10-12 04:04:36,786][78091] Updated weights for policy 0, policy_version 22870 (0.0009) -[2023-10-12 04:04:37,164][78091] Updated weights for policy 0, policy_version 22880 (0.0010) -[2023-10-12 04:04:37,499][78123] Updated weights for policy 1, policy_version 22760 (0.0008) -[2023-10-12 04:04:37,867][78123] Updated weights for policy 1, policy_version 22770 (0.0010) -[2023-10-12 04:04:38,230][78123] Updated weights for policy 1, policy_version 22780 (0.0010) -[2023-10-12 04:04:40,201][77203] Fps is (10 sec: 13106.7, 60 sec: 13107.1, 300 sec: 12662.9). Total num frames: 46759936. Throughput: 0: 1584.0, 1: 1593.6. Samples: 11701084. Policy #0 lag: (min: 28.0, avg: 46.3, max: 48.0) -[2023-10-12 04:04:40,203][77203] Avg episode reward: [(0, '41.250'), (1, '32.810')] -[2023-10-12 04:04:41,598][78091] Updated weights for policy 0, policy_version 22890 (0.0010) -[2023-10-12 04:04:41,985][78091] Updated weights for policy 0, policy_version 22900 (0.0010) -[2023-10-12 04:04:42,362][78091] Updated weights for policy 0, policy_version 22910 (0.0010) -[2023-10-12 04:04:42,535][78123] Updated weights for policy 1, policy_version 22790 (0.0009) -[2023-10-12 04:04:42,898][78123] Updated weights for policy 1, policy_version 22800 (0.0008) -[2023-10-12 04:04:43,271][78123] Updated weights for policy 1, policy_version 22810 (0.0007) -[2023-10-12 04:04:45,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 46825472. Throughput: 0: 1580.4, 1: 1612.7. Samples: 11710532. Policy #0 lag: (min: 28.0, avg: 46.3, max: 48.0) -[2023-10-12 04:04:45,201][77203] Avg episode reward: [(0, '38.260'), (1, '35.630')] -[2023-10-12 04:04:46,681][78091] Updated weights for policy 0, policy_version 22920 (0.0007) -[2023-10-12 04:04:47,047][78091] Updated weights for policy 0, policy_version 22930 (0.0008) -[2023-10-12 04:04:47,422][78091] Updated weights for policy 0, policy_version 22940 (0.0008) -[2023-10-12 04:04:47,626][78123] Updated weights for policy 1, policy_version 22820 (0.0009) -[2023-10-12 04:04:47,996][78123] Updated weights for policy 1, policy_version 22830 (0.0011) -[2023-10-12 04:04:48,366][78123] Updated weights for policy 1, policy_version 22840 (0.0009) -[2023-10-12 04:04:50,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 46891008. Throughput: 0: 1585.5, 1: 1590.9. Samples: 11729364. Policy #0 lag: (min: 28.0, avg: 46.3, max: 48.0) -[2023-10-12 04:04:50,202][77203] Avg episode reward: [(0, '39.930'), (1, '43.420')] -[2023-10-12 04:04:51,760][78091] Updated weights for policy 0, policy_version 22950 (0.0008) -[2023-10-12 04:04:52,137][78091] Updated weights for policy 0, policy_version 22960 (0.0008) -[2023-10-12 04:04:52,508][78091] Updated weights for policy 0, policy_version 22970 (0.0008) -[2023-10-12 04:04:52,685][78123] Updated weights for policy 1, policy_version 22850 (0.0008) -[2023-10-12 04:04:53,095][78123] Updated weights for policy 1, policy_version 22860 (0.0010) -[2023-10-12 04:04:53,465][78123] Updated weights for policy 1, policy_version 22870 (0.0008) -[2023-10-12 04:04:53,836][78123] Updated weights for policy 1, policy_version 22880 (0.0008) -[2023-10-12 04:04:55,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 46956544. Throughput: 0: 1588.7, 1: 1590.4. Samples: 11748680. Policy #0 lag: (min: 28.0, avg: 46.3, max: 48.0) -[2023-10-12 04:04:55,201][77203] Avg episode reward: [(0, '40.340'), (1, '38.550')] -[2023-10-12 04:04:56,776][78091] Updated weights for policy 0, policy_version 22980 (0.0009) -[2023-10-12 04:04:57,145][78091] Updated weights for policy 0, policy_version 22990 (0.0009) -[2023-10-12 04:04:57,511][78091] Updated weights for policy 0, policy_version 23000 (0.0007) -[2023-10-12 04:04:58,222][78123] Updated weights for policy 1, policy_version 22890 (0.0008) -[2023-10-12 04:04:58,587][78123] Updated weights for policy 1, policy_version 22900 (0.0009) -[2023-10-12 04:04:58,952][78123] Updated weights for policy 1, policy_version 22910 (0.0009) -[2023-10-12 04:05:00,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 47022080. Throughput: 0: 1592.5, 1: 1616.0. Samples: 11758618. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 04:05:00,201][77203] Avg episode reward: [(0, '37.240'), (1, '40.490')] -[2023-10-12 04:05:01,893][78091] Updated weights for policy 0, policy_version 23010 (0.0007) -[2023-10-12 04:05:02,289][78091] Updated weights for policy 0, policy_version 23020 (0.0009) -[2023-10-12 04:05:02,651][78091] Updated weights for policy 0, policy_version 23030 (0.0007) -[2023-10-12 04:05:03,028][78091] Updated weights for policy 0, policy_version 23040 (0.0008) -[2023-10-12 04:05:03,115][78123] Updated weights for policy 1, policy_version 22920 (0.0009) -[2023-10-12 04:05:03,491][78123] Updated weights for policy 1, policy_version 22930 (0.0010) -[2023-10-12 04:05:03,854][78123] Updated weights for policy 1, policy_version 22940 (0.0010) -[2023-10-12 04:05:05,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 47087616. Throughput: 0: 1587.4, 1: 1600.3. Samples: 11777246. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 04:05:05,202][77203] Avg episode reward: [(0, '40.480'), (1, '38.650')] -[2023-10-12 04:05:07,096][78091] Updated weights for policy 0, policy_version 23050 (0.0007) -[2023-10-12 04:05:07,474][78091] Updated weights for policy 0, policy_version 23060 (0.0007) -[2023-10-12 04:05:07,842][78091] Updated weights for policy 0, policy_version 23070 (0.0007) -[2023-10-12 04:05:08,157][78123] Updated weights for policy 1, policy_version 22950 (0.0010) -[2023-10-12 04:05:08,518][78123] Updated weights for policy 1, policy_version 22960 (0.0008) -[2023-10-12 04:05:08,885][78123] Updated weights for policy 1, policy_version 22970 (0.0009) -[2023-10-12 04:05:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 47153152. Throughput: 0: 1590.7, 1: 1585.7. Samples: 11796404. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 04:05:10,202][77203] Avg episode reward: [(0, '36.850'), (1, '36.720')] -[2023-10-12 04:05:10,212][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000022976_23527424.pth... -[2023-10-12 04:05:10,212][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000023072_23625728.pth... -[2023-10-12 04:05:10,251][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000021504_22020096.pth -[2023-10-12 04:05:10,253][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000021600_22118400.pth -[2023-10-12 04:05:12,157][78091] Updated weights for policy 0, policy_version 23080 (0.0007) -[2023-10-12 04:05:12,527][78091] Updated weights for policy 0, policy_version 23090 (0.0008) -[2023-10-12 04:05:12,894][78091] Updated weights for policy 0, policy_version 23100 (0.0009) -[2023-10-12 04:05:13,268][78123] Updated weights for policy 1, policy_version 22980 (0.0009) -[2023-10-12 04:05:13,645][78123] Updated weights for policy 1, policy_version 22990 (0.0008) -[2023-10-12 04:05:14,011][78123] Updated weights for policy 1, policy_version 23000 (0.0009) -[2023-10-12 04:05:15,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 47218688. Throughput: 0: 1597.5, 1: 1606.7. Samples: 11806550. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 04:05:15,202][77203] Avg episode reward: [(0, '37.860'), (1, '44.230')] -[2023-10-12 04:05:17,249][78091] Updated weights for policy 0, policy_version 23110 (0.0008) -[2023-10-12 04:05:17,629][78091] Updated weights for policy 0, policy_version 23120 (0.0011) -[2023-10-12 04:05:17,999][78091] Updated weights for policy 0, policy_version 23130 (0.0011) -[2023-10-12 04:05:18,387][78123] Updated weights for policy 1, policy_version 23010 (0.0011) -[2023-10-12 04:05:18,758][78123] Updated weights for policy 1, policy_version 23020 (0.0008) -[2023-10-12 04:05:19,132][78123] Updated weights for policy 1, policy_version 23030 (0.0009) -[2023-10-12 04:05:19,496][78123] Updated weights for policy 1, policy_version 23040 (0.0011) -[2023-10-12 04:05:20,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 47284224. Throughput: 0: 1591.3, 1: 1602.6. Samples: 11825370. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:05:20,202][77203] Avg episode reward: [(0, '38.270'), (1, '37.380')] -[2023-10-12 04:05:22,262][78091] Updated weights for policy 0, policy_version 23140 (0.0009) -[2023-10-12 04:05:22,618][78091] Updated weights for policy 0, policy_version 23150 (0.0008) -[2023-10-12 04:05:22,998][78091] Updated weights for policy 0, policy_version 23160 (0.0009) -[2023-10-12 04:05:23,760][78123] Updated weights for policy 1, policy_version 23050 (0.0007) -[2023-10-12 04:05:24,125][78123] Updated weights for policy 1, policy_version 23060 (0.0008) -[2023-10-12 04:05:24,495][78123] Updated weights for policy 1, policy_version 23070 (0.0008) -[2023-10-12 04:05:25,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 47349760. Throughput: 0: 1591.5, 1: 1589.9. Samples: 11844244. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:05:25,202][77203] Avg episode reward: [(0, '36.470'), (1, '38.890')] -[2023-10-12 04:05:27,310][78091] Updated weights for policy 0, policy_version 23170 (0.0008) -[2023-10-12 04:05:27,684][78091] Updated weights for policy 0, policy_version 23180 (0.0011) -[2023-10-12 04:05:28,051][78091] Updated weights for policy 0, policy_version 23190 (0.0011) -[2023-10-12 04:05:28,426][78091] Updated weights for policy 0, policy_version 23200 (0.0007) -[2023-10-12 04:05:28,828][78123] Updated weights for policy 1, policy_version 23080 (0.0008) -[2023-10-12 04:05:29,202][78123] Updated weights for policy 1, policy_version 23090 (0.0009) -[2023-10-12 04:05:29,575][78123] Updated weights for policy 1, policy_version 23100 (0.0010) -[2023-10-12 04:05:30,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 47415296. Throughput: 0: 1604.6, 1: 1594.0. Samples: 11854470. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:05:30,201][77203] Avg episode reward: [(0, '40.930'), (1, '47.250')] -[2023-10-12 04:05:32,887][78091] Updated weights for policy 0, policy_version 23210 (0.0007) -[2023-10-12 04:05:33,268][78091] Updated weights for policy 0, policy_version 23220 (0.0009) -[2023-10-12 04:05:33,640][78091] Updated weights for policy 0, policy_version 23230 (0.0009) -[2023-10-12 04:05:33,815][78123] Updated weights for policy 1, policy_version 23110 (0.0009) -[2023-10-12 04:05:34,184][78123] Updated weights for policy 1, policy_version 23120 (0.0007) -[2023-10-12 04:05:34,563][78123] Updated weights for policy 1, policy_version 23130 (0.0010) -[2023-10-12 04:05:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 47480832. Throughput: 0: 1584.3, 1: 1610.9. Samples: 11873150. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:05:35,202][77203] Avg episode reward: [(0, '35.400'), (1, '36.850')] -[2023-10-12 04:05:38,041][78091] Updated weights for policy 0, policy_version 23240 (0.0008) -[2023-10-12 04:05:38,411][78091] Updated weights for policy 0, policy_version 23250 (0.0010) -[2023-10-12 04:05:38,784][78091] Updated weights for policy 0, policy_version 23260 (0.0010) -[2023-10-12 04:05:39,020][78123] Updated weights for policy 1, policy_version 23140 (0.0009) -[2023-10-12 04:05:39,406][78123] Updated weights for policy 1, policy_version 23150 (0.0008) -[2023-10-12 04:05:39,765][78123] Updated weights for policy 1, policy_version 23160 (0.0008) -[2023-10-12 04:05:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 12662.9). Total num frames: 47546368. Throughput: 0: 1577.8, 1: 1597.2. Samples: 11891554. Policy #0 lag: (min: 0.0, avg: 24.6, max: 32.0) -[2023-10-12 04:05:40,201][77203] Avg episode reward: [(0, '37.550'), (1, '35.890')] -[2023-10-12 04:05:43,283][78091] Updated weights for policy 0, policy_version 23270 (0.0011) -[2023-10-12 04:05:43,647][78091] Updated weights for policy 0, policy_version 23280 (0.0011) -[2023-10-12 04:05:44,022][78091] Updated weights for policy 0, policy_version 23290 (0.0009) -[2023-10-12 04:05:44,197][78123] Updated weights for policy 1, policy_version 23170 (0.0009) -[2023-10-12 04:05:44,557][78123] Updated weights for policy 1, policy_version 23180 (0.0009) -[2023-10-12 04:05:44,930][78123] Updated weights for policy 1, policy_version 23190 (0.0008) -[2023-10-12 04:05:45,201][77203] Fps is (10 sec: 9830.6, 60 sec: 12561.1, 300 sec: 12551.8). Total num frames: 47579136. Throughput: 0: 1600.0, 1: 1586.2. Samples: 11901998. Policy #0 lag: (min: 0.0, avg: 24.6, max: 32.0) -[2023-10-12 04:05:45,201][77203] Avg episode reward: [(0, '39.600'), (1, '46.320')] -[2023-10-12 04:05:45,291][78123] Updated weights for policy 1, policy_version 23200 (0.0009) -[2023-10-12 04:05:48,516][78091] Updated weights for policy 0, policy_version 23300 (0.0009) -[2023-10-12 04:05:48,910][78091] Updated weights for policy 0, policy_version 23310 (0.0010) -[2023-10-12 04:05:49,287][78091] Updated weights for policy 0, policy_version 23320 (0.0009) -[2023-10-12 04:05:49,577][78123] Updated weights for policy 1, policy_version 23210 (0.0008) -[2023-10-12 04:05:49,937][78123] Updated weights for policy 1, policy_version 23220 (0.0010) -[2023-10-12 04:05:50,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.1, 300 sec: 12551.8). Total num frames: 47644672. Throughput: 0: 1593.2, 1: 1604.4. Samples: 11921142. Policy #0 lag: (min: 0.0, avg: 24.6, max: 32.0) -[2023-10-12 04:05:50,202][77203] Avg episode reward: [(0, '34.930'), (1, '34.050')] -[2023-10-12 04:05:50,300][78123] Updated weights for policy 1, policy_version 23230 (0.0010) -[2023-10-12 04:05:53,604][78091] Updated weights for policy 0, policy_version 23330 (0.0008) -[2023-10-12 04:05:53,983][78091] Updated weights for policy 0, policy_version 23340 (0.0009) -[2023-10-12 04:05:54,351][78091] Updated weights for policy 0, policy_version 23350 (0.0007) -[2023-10-12 04:05:54,594][78123] Updated weights for policy 1, policy_version 23240 (0.0008) -[2023-10-12 04:05:54,721][78091] Updated weights for policy 0, policy_version 23360 (0.0007) -[2023-10-12 04:05:54,962][78123] Updated weights for policy 1, policy_version 23250 (0.0010) -[2023-10-12 04:05:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 47710208. Throughput: 0: 1574.5, 1: 1604.4. Samples: 11939456. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:05:55,201][77203] Avg episode reward: [(0, '38.900'), (1, '40.650')] -[2023-10-12 04:05:55,326][78123] Updated weights for policy 1, policy_version 23260 (0.0007) -[2023-10-12 04:05:59,003][78091] Updated weights for policy 0, policy_version 23370 (0.0010) -[2023-10-12 04:05:59,367][78091] Updated weights for policy 0, policy_version 23380 (0.0011) -[2023-10-12 04:05:59,706][78123] Updated weights for policy 1, policy_version 23270 (0.0008) -[2023-10-12 04:05:59,744][78091] Updated weights for policy 0, policy_version 23390 (0.0007) -[2023-10-12 04:06:00,079][78123] Updated weights for policy 1, policy_version 23280 (0.0009) -[2023-10-12 04:06:00,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 47775744. Throughput: 0: 1594.0, 1: 1585.9. Samples: 11949642. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:06:00,201][77203] Avg episode reward: [(0, '41.430'), (1, '44.850')] -[2023-10-12 04:06:00,434][78123] Updated weights for policy 1, policy_version 23290 (0.0008) -[2023-10-12 04:06:04,036][78091] Updated weights for policy 0, policy_version 23400 (0.0008) -[2023-10-12 04:06:04,401][78091] Updated weights for policy 0, policy_version 23410 (0.0008) -[2023-10-12 04:06:04,604][78123] Updated weights for policy 1, policy_version 23300 (0.0010) -[2023-10-12 04:06:04,774][78091] Updated weights for policy 0, policy_version 23420 (0.0009) -[2023-10-12 04:06:04,981][78123] Updated weights for policy 1, policy_version 23310 (0.0009) -[2023-10-12 04:06:05,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 47841280. Throughput: 0: 1598.6, 1: 1598.0. Samples: 11969220. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:06:05,202][77203] Avg episode reward: [(0, '36.770'), (1, '39.390')] -[2023-10-12 04:06:05,350][78123] Updated weights for policy 1, policy_version 23320 (0.0009) -[2023-10-12 04:06:09,095][78091] Updated weights for policy 0, policy_version 23430 (0.0009) -[2023-10-12 04:06:09,460][78091] Updated weights for policy 0, policy_version 23440 (0.0009) -[2023-10-12 04:06:09,773][78123] Updated weights for policy 1, policy_version 23330 (0.0009) -[2023-10-12 04:06:09,826][78091] Updated weights for policy 0, policy_version 23450 (0.0009) -[2023-10-12 04:06:10,142][78123] Updated weights for policy 1, policy_version 23340 (0.0008) -[2023-10-12 04:06:10,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 47906816. Throughput: 0: 1578.8, 1: 1609.4. Samples: 11987710. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:06:10,202][77203] Avg episode reward: [(0, '42.740'), (1, '42.200')] -[2023-10-12 04:06:10,507][78123] Updated weights for policy 1, policy_version 23350 (0.0007) -[2023-10-12 04:06:10,877][78123] Updated weights for policy 1, policy_version 23360 (0.0007) -[2023-10-12 04:06:14,258][78091] Updated weights for policy 0, policy_version 23460 (0.0010) -[2023-10-12 04:06:14,640][78091] Updated weights for policy 0, policy_version 23470 (0.0008) -[2023-10-12 04:06:15,016][78091] Updated weights for policy 0, policy_version 23480 (0.0009) -[2023-10-12 04:06:15,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 47939584. Throughput: 0: 1584.7, 1: 1585.1. Samples: 11997110. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:06:15,202][77203] Avg episode reward: [(0, '38.180'), (1, '36.850')] -[2023-10-12 04:06:15,240][78123] Updated weights for policy 1, policy_version 23370 (0.0008) -[2023-10-12 04:06:15,610][78123] Updated weights for policy 1, policy_version 23380 (0.0007) -[2023-10-12 04:06:15,976][78123] Updated weights for policy 1, policy_version 23390 (0.0008) -[2023-10-12 04:06:19,090][78091] Updated weights for policy 0, policy_version 23490 (0.0007) -[2023-10-12 04:06:19,458][78091] Updated weights for policy 0, policy_version 23500 (0.0007) -[2023-10-12 04:06:19,832][78091] Updated weights for policy 0, policy_version 23510 (0.0008) -[2023-10-12 04:06:20,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 48005120. Throughput: 0: 1601.3, 1: 1584.5. Samples: 12016512. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:06:20,202][77203] Avg episode reward: [(0, '36.700'), (1, '36.320')] -[2023-10-12 04:06:20,207][78091] Updated weights for policy 0, policy_version 23520 (0.0009) -[2023-10-12 04:06:20,363][78123] Updated weights for policy 1, policy_version 23400 (0.0008) -[2023-10-12 04:06:20,733][78123] Updated weights for policy 1, policy_version 23410 (0.0007) -[2023-10-12 04:06:21,094][78123] Updated weights for policy 1, policy_version 23420 (0.0007) -[2023-10-12 04:06:24,606][78091] Updated weights for policy 0, policy_version 23530 (0.0011) -[2023-10-12 04:06:24,981][78091] Updated weights for policy 0, policy_version 23540 (0.0008) -[2023-10-12 04:06:25,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 48070656. Throughput: 0: 1593.8, 1: 1604.3. Samples: 12035468. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:06:25,202][77203] Avg episode reward: [(0, '43.020'), (1, '38.740')] -[2023-10-12 04:06:25,353][78091] Updated weights for policy 0, policy_version 23550 (0.0007) -[2023-10-12 04:06:25,530][78123] Updated weights for policy 1, policy_version 23430 (0.0008) -[2023-10-12 04:06:25,913][78123] Updated weights for policy 1, policy_version 23440 (0.0009) -[2023-10-12 04:06:26,279][78123] Updated weights for policy 1, policy_version 23450 (0.0008) -[2023-10-12 04:06:29,680][78091] Updated weights for policy 0, policy_version 23560 (0.0008) -[2023-10-12 04:06:30,050][78091] Updated weights for policy 0, policy_version 23570 (0.0008) -[2023-10-12 04:06:30,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 48136192. Throughput: 0: 1583.3, 1: 1584.2. Samples: 12044536. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:06:30,201][77203] Avg episode reward: [(0, '35.490'), (1, '45.870')] -[2023-10-12 04:06:30,421][78091] Updated weights for policy 0, policy_version 23580 (0.0008) -[2023-10-12 04:06:30,651][78123] Updated weights for policy 1, policy_version 23460 (0.0007) -[2023-10-12 04:06:31,020][78123] Updated weights for policy 1, policy_version 23470 (0.0009) -[2023-10-12 04:06:31,375][78123] Updated weights for policy 1, policy_version 23480 (0.0010) -[2023-10-12 04:06:34,762][78091] Updated weights for policy 0, policy_version 23590 (0.0009) -[2023-10-12 04:06:35,139][78091] Updated weights for policy 0, policy_version 23600 (0.0008) -[2023-10-12 04:06:35,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 48201728. Throughput: 0: 1595.2, 1: 1581.9. Samples: 12064110. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:06:35,201][77203] Avg episode reward: [(0, '38.210'), (1, '38.710')] -[2023-10-12 04:06:35,505][78091] Updated weights for policy 0, policy_version 23610 (0.0008) -[2023-10-12 04:06:35,625][78123] Updated weights for policy 1, policy_version 23490 (0.0009) -[2023-10-12 04:06:35,988][78123] Updated weights for policy 1, policy_version 23500 (0.0007) -[2023-10-12 04:06:36,354][78123] Updated weights for policy 1, policy_version 23510 (0.0007) -[2023-10-12 04:06:36,720][78123] Updated weights for policy 1, policy_version 23520 (0.0007) -[2023-10-12 04:06:39,876][78091] Updated weights for policy 0, policy_version 23620 (0.0009) -[2023-10-12 04:06:40,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 48267264. Throughput: 0: 1608.0, 1: 1591.7. Samples: 12083446. Policy #0 lag: (min: 2.0, avg: 26.5, max: 32.0) -[2023-10-12 04:06:40,202][77203] Avg episode reward: [(0, '40.050'), (1, '40.480')] -[2023-10-12 04:06:40,249][78091] Updated weights for policy 0, policy_version 23630 (0.0009) -[2023-10-12 04:06:40,623][78091] Updated weights for policy 0, policy_version 23640 (0.0009) -[2023-10-12 04:06:41,115][78123] Updated weights for policy 1, policy_version 23530 (0.0008) -[2023-10-12 04:06:41,480][78123] Updated weights for policy 1, policy_version 23540 (0.0010) -[2023-10-12 04:06:41,851][78123] Updated weights for policy 1, policy_version 23550 (0.0010) -[2023-10-12 04:06:44,774][78091] Updated weights for policy 0, policy_version 23650 (0.0009) -[2023-10-12 04:06:45,153][78091] Updated weights for policy 0, policy_version 23660 (0.0007) -[2023-10-12 04:06:45,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 48332800. Throughput: 0: 1586.0, 1: 1583.5. Samples: 12092266. Policy #0 lag: (min: 2.0, avg: 26.5, max: 32.0) -[2023-10-12 04:06:45,202][77203] Avg episode reward: [(0, '33.450'), (1, '43.000')] -[2023-10-12 04:06:45,522][78091] Updated weights for policy 0, policy_version 23670 (0.0008) -[2023-10-12 04:06:45,883][78091] Updated weights for policy 0, policy_version 23680 (0.0010) -[2023-10-12 04:06:46,162][78123] Updated weights for policy 1, policy_version 23560 (0.0008) -[2023-10-12 04:06:46,525][78123] Updated weights for policy 1, policy_version 23570 (0.0007) -[2023-10-12 04:06:46,897][78123] Updated weights for policy 1, policy_version 23580 (0.0009) -[2023-10-12 04:06:50,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 48398336. Throughput: 0: 1586.6, 1: 1579.5. Samples: 12111692. Policy #0 lag: (min: 2.0, avg: 26.5, max: 32.0) -[2023-10-12 04:06:50,201][77203] Avg episode reward: [(0, '41.540'), (1, '41.180')] -[2023-10-12 04:06:50,286][78091] Updated weights for policy 0, policy_version 23690 (0.0007) -[2023-10-12 04:06:50,650][78091] Updated weights for policy 0, policy_version 23700 (0.0007) -[2023-10-12 04:06:51,026][78091] Updated weights for policy 0, policy_version 23710 (0.0007) -[2023-10-12 04:06:51,155][78123] Updated weights for policy 1, policy_version 23590 (0.0010) -[2023-10-12 04:06:51,517][78123] Updated weights for policy 1, policy_version 23600 (0.0010) -[2023-10-12 04:06:51,888][78123] Updated weights for policy 1, policy_version 23610 (0.0009) -[2023-10-12 04:06:55,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 48463872. Throughput: 0: 1607.3, 1: 1580.2. Samples: 12131150. Policy #0 lag: (min: 2.0, avg: 26.5, max: 32.0) -[2023-10-12 04:06:55,202][77203] Avg episode reward: [(0, '37.660'), (1, '37.410')] -[2023-10-12 04:06:55,299][78091] Updated weights for policy 0, policy_version 23720 (0.0007) -[2023-10-12 04:06:55,674][78091] Updated weights for policy 0, policy_version 23730 (0.0008) -[2023-10-12 04:06:56,039][78091] Updated weights for policy 0, policy_version 23740 (0.0009) -[2023-10-12 04:06:56,269][78123] Updated weights for policy 1, policy_version 23620 (0.0007) -[2023-10-12 04:06:56,631][78123] Updated weights for policy 1, policy_version 23630 (0.0010) -[2023-10-12 04:06:57,011][78123] Updated weights for policy 1, policy_version 23640 (0.0008) -[2023-10-12 04:07:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 48529408. Throughput: 0: 1588.7, 1: 1578.8. Samples: 12139646. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-12 04:07:00,201][77203] Avg episode reward: [(0, '37.710'), (1, '36.550')] -[2023-10-12 04:07:00,376][78091] Updated weights for policy 0, policy_version 23750 (0.0007) -[2023-10-12 04:07:00,748][78091] Updated weights for policy 0, policy_version 23760 (0.0008) -[2023-10-12 04:07:01,120][78091] Updated weights for policy 0, policy_version 23770 (0.0007) -[2023-10-12 04:07:01,249][78123] Updated weights for policy 1, policy_version 23650 (0.0008) -[2023-10-12 04:07:01,615][78123] Updated weights for policy 1, policy_version 23660 (0.0008) -[2023-10-12 04:07:01,994][78123] Updated weights for policy 1, policy_version 23670 (0.0009) -[2023-10-12 04:07:02,364][78123] Updated weights for policy 1, policy_version 23680 (0.0009) -[2023-10-12 04:07:05,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 48594944. Throughput: 0: 1593.4, 1: 1579.8. Samples: 12159306. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-12 04:07:05,202][77203] Avg episode reward: [(0, '39.550'), (1, '39.490')] -[2023-10-12 04:07:05,449][78091] Updated weights for policy 0, policy_version 23780 (0.0008) -[2023-10-12 04:07:05,818][78091] Updated weights for policy 0, policy_version 23790 (0.0007) -[2023-10-12 04:07:06,194][78091] Updated weights for policy 0, policy_version 23800 (0.0007) -[2023-10-12 04:07:06,847][78123] Updated weights for policy 1, policy_version 23690 (0.0010) -[2023-10-12 04:07:07,213][78123] Updated weights for policy 1, policy_version 23700 (0.0011) -[2023-10-12 04:07:07,578][78123] Updated weights for policy 1, policy_version 23710 (0.0010) -[2023-10-12 04:07:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 48660480. Throughput: 0: 1601.8, 1: 1577.3. Samples: 12178526. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-12 04:07:10,201][77203] Avg episode reward: [(0, '40.120'), (1, '42.370')] -[2023-10-12 04:07:10,209][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000023808_24379392.pth... -[2023-10-12 04:07:10,209][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000023712_24281088.pth... -[2023-10-12 04:07:10,249][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000022240_22773760.pth -[2023-10-12 04:07:10,249][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000022336_22872064.pth -[2023-10-12 04:07:10,681][78091] Updated weights for policy 0, policy_version 23810 (0.0010) -[2023-10-12 04:07:11,056][78091] Updated weights for policy 0, policy_version 23820 (0.0007) -[2023-10-12 04:07:11,423][78091] Updated weights for policy 0, policy_version 23830 (0.0007) -[2023-10-12 04:07:11,792][78091] Updated weights for policy 0, policy_version 23840 (0.0008) -[2023-10-12 04:07:11,999][78123] Updated weights for policy 1, policy_version 23720 (0.0008) -[2023-10-12 04:07:12,379][78123] Updated weights for policy 1, policy_version 23730 (0.0010) -[2023-10-12 04:07:12,743][78123] Updated weights for policy 1, policy_version 23740 (0.0008) -[2023-10-12 04:07:15,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 48726016. Throughput: 0: 1587.0, 1: 1581.8. Samples: 12187132. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-12 04:07:15,202][77203] Avg episode reward: [(0, '37.320'), (1, '45.450')] -[2023-10-12 04:07:16,255][78091] Updated weights for policy 0, policy_version 23850 (0.0010) -[2023-10-12 04:07:16,630][78091] Updated weights for policy 0, policy_version 23860 (0.0009) -[2023-10-12 04:07:17,007][78091] Updated weights for policy 0, policy_version 23870 (0.0007) -[2023-10-12 04:07:17,033][78123] Updated weights for policy 1, policy_version 23750 (0.0009) -[2023-10-12 04:07:17,400][78123] Updated weights for policy 1, policy_version 23760 (0.0009) -[2023-10-12 04:07:17,766][78123] Updated weights for policy 1, policy_version 23770 (0.0007) -[2023-10-12 04:07:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 48791552. Throughput: 0: 1585.9, 1: 1578.7. Samples: 12206516. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:07:20,201][77203] Avg episode reward: [(0, '38.140'), (1, '44.230')] -[2023-10-12 04:07:21,328][78091] Updated weights for policy 0, policy_version 23880 (0.0008) -[2023-10-12 04:07:21,705][78091] Updated weights for policy 0, policy_version 23890 (0.0007) -[2023-10-12 04:07:22,077][78091] Updated weights for policy 0, policy_version 23900 (0.0007) -[2023-10-12 04:07:22,385][78123] Updated weights for policy 1, policy_version 23780 (0.0007) -[2023-10-12 04:07:22,753][78123] Updated weights for policy 1, policy_version 23790 (0.0007) -[2023-10-12 04:07:23,123][78123] Updated weights for policy 1, policy_version 23800 (0.0007) -[2023-10-12 04:07:25,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.3, 300 sec: 12662.9). Total num frames: 48857088. Throughput: 0: 1589.0, 1: 1577.0. Samples: 12225916. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:07:25,201][77203] Avg episode reward: [(0, '41.460'), (1, '41.070')] -[2023-10-12 04:07:26,239][78091] Updated weights for policy 0, policy_version 23910 (0.0008) -[2023-10-12 04:07:26,606][78091] Updated weights for policy 0, policy_version 23920 (0.0008) -[2023-10-12 04:07:26,982][78091] Updated weights for policy 0, policy_version 23930 (0.0009) -[2023-10-12 04:07:27,383][78123] Updated weights for policy 1, policy_version 23810 (0.0009) -[2023-10-12 04:07:27,738][78123] Updated weights for policy 1, policy_version 23820 (0.0009) -[2023-10-12 04:07:28,109][78123] Updated weights for policy 1, policy_version 23830 (0.0009) -[2023-10-12 04:07:28,472][78123] Updated weights for policy 1, policy_version 23840 (0.0007) -[2023-10-12 04:07:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 48922624. Throughput: 0: 1586.0, 1: 1595.0. Samples: 12235408. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:07:30,201][77203] Avg episode reward: [(0, '34.550'), (1, '35.770')] -[2023-10-12 04:07:31,417][78091] Updated weights for policy 0, policy_version 23940 (0.0009) -[2023-10-12 04:07:31,795][78091] Updated weights for policy 0, policy_version 23950 (0.0009) -[2023-10-12 04:07:32,168][78091] Updated weights for policy 0, policy_version 23960 (0.0011) -[2023-10-12 04:07:32,825][78123] Updated weights for policy 1, policy_version 23850 (0.0011) -[2023-10-12 04:07:33,202][78123] Updated weights for policy 1, policy_version 23860 (0.0008) -[2023-10-12 04:07:33,569][78123] Updated weights for policy 1, policy_version 23870 (0.0007) -[2023-10-12 04:07:35,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 48988160. Throughput: 0: 1582.9, 1: 1582.0. Samples: 12254114. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:07:35,201][77203] Avg episode reward: [(0, '40.480'), (1, '34.610')] -[2023-10-12 04:07:36,544][78091] Updated weights for policy 0, policy_version 23970 (0.0011) -[2023-10-12 04:07:36,919][78091] Updated weights for policy 0, policy_version 23980 (0.0009) -[2023-10-12 04:07:37,290][78091] Updated weights for policy 0, policy_version 23990 (0.0009) -[2023-10-12 04:07:37,659][78091] Updated weights for policy 0, policy_version 24000 (0.0010) -[2023-10-12 04:07:37,726][78123] Updated weights for policy 1, policy_version 23880 (0.0009) -[2023-10-12 04:07:38,085][78123] Updated weights for policy 1, policy_version 23890 (0.0009) -[2023-10-12 04:07:38,452][78123] Updated weights for policy 1, policy_version 23900 (0.0010) -[2023-10-12 04:07:40,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 49053696. Throughput: 0: 1578.9, 1: 1584.8. Samples: 12273518. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-12 04:07:40,202][77203] Avg episode reward: [(0, '37.970'), (1, '30.140')] -[2023-10-12 04:07:41,996][78091] Updated weights for policy 0, policy_version 24010 (0.0008) -[2023-10-12 04:07:42,367][78091] Updated weights for policy 0, policy_version 24020 (0.0007) -[2023-10-12 04:07:42,734][78123] Updated weights for policy 1, policy_version 23910 (0.0008) -[2023-10-12 04:07:42,743][78091] Updated weights for policy 0, policy_version 24030 (0.0009) -[2023-10-12 04:07:43,105][78123] Updated weights for policy 1, policy_version 23920 (0.0008) -[2023-10-12 04:07:43,475][78123] Updated weights for policy 1, policy_version 23930 (0.0009) -[2023-10-12 04:07:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 49119232. Throughput: 0: 1582.9, 1: 1607.0. Samples: 12283192. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-12 04:07:45,202][77203] Avg episode reward: [(0, '36.870'), (1, '36.750')] -[2023-10-12 04:07:47,016][78091] Updated weights for policy 0, policy_version 24040 (0.0008) -[2023-10-12 04:07:47,383][78091] Updated weights for policy 0, policy_version 24050 (0.0008) -[2023-10-12 04:07:47,730][78123] Updated weights for policy 1, policy_version 23940 (0.0009) -[2023-10-12 04:07:47,755][78091] Updated weights for policy 0, policy_version 24060 (0.0009) -[2023-10-12 04:07:48,103][78123] Updated weights for policy 1, policy_version 23950 (0.0008) -[2023-10-12 04:07:48,475][78123] Updated weights for policy 1, policy_version 23960 (0.0009) -[2023-10-12 04:07:50,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 49184768. Throughput: 0: 1579.3, 1: 1592.1. Samples: 12302020. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-12 04:07:50,202][77203] Avg episode reward: [(0, '40.690'), (1, '37.190')] -[2023-10-12 04:07:52,076][78091] Updated weights for policy 0, policy_version 24070 (0.0007) -[2023-10-12 04:07:52,452][78091] Updated weights for policy 0, policy_version 24080 (0.0009) -[2023-10-12 04:07:52,817][78123] Updated weights for policy 1, policy_version 23970 (0.0009) -[2023-10-12 04:07:52,827][78091] Updated weights for policy 0, policy_version 24090 (0.0008) -[2023-10-12 04:07:53,182][78123] Updated weights for policy 1, policy_version 23980 (0.0008) -[2023-10-12 04:07:53,553][78123] Updated weights for policy 1, policy_version 23990 (0.0007) -[2023-10-12 04:07:53,918][78123] Updated weights for policy 1, policy_version 24000 (0.0008) -[2023-10-12 04:07:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 49250304. Throughput: 0: 1586.1, 1: 1590.2. Samples: 12321458. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-12 04:07:55,201][77203] Avg episode reward: [(0, '39.940'), (1, '35.730')] -[2023-10-12 04:07:57,190][78091] Updated weights for policy 0, policy_version 24100 (0.0008) -[2023-10-12 04:07:57,562][78091] Updated weights for policy 0, policy_version 24110 (0.0008) -[2023-10-12 04:07:57,932][78091] Updated weights for policy 0, policy_version 24120 (0.0008) -[2023-10-12 04:07:58,419][78123] Updated weights for policy 1, policy_version 24010 (0.0008) -[2023-10-12 04:07:58,785][78123] Updated weights for policy 1, policy_version 24020 (0.0009) -[2023-10-12 04:07:59,156][78123] Updated weights for policy 1, policy_version 24030 (0.0008) -[2023-10-12 04:08:00,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 49315840. Throughput: 0: 1600.0, 1: 1614.8. Samples: 12331796. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-12 04:08:00,201][77203] Avg episode reward: [(0, '37.500'), (1, '43.490')] -[2023-10-12 04:08:02,050][78091] Updated weights for policy 0, policy_version 24130 (0.0008) -[2023-10-12 04:08:02,420][78091] Updated weights for policy 0, policy_version 24140 (0.0010) -[2023-10-12 04:08:02,795][78091] Updated weights for policy 0, policy_version 24150 (0.0010) -[2023-10-12 04:08:03,156][78091] Updated weights for policy 0, policy_version 24160 (0.0009) -[2023-10-12 04:08:03,428][78123] Updated weights for policy 1, policy_version 24040 (0.0008) -[2023-10-12 04:08:03,795][78123] Updated weights for policy 1, policy_version 24050 (0.0008) -[2023-10-12 04:08:04,162][78123] Updated weights for policy 1, policy_version 24060 (0.0009) -[2023-10-12 04:08:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 49381376. Throughput: 0: 1592.9, 1: 1605.9. Samples: 12350460. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-12 04:08:05,202][77203] Avg episode reward: [(0, '36.740'), (1, '39.870')] -[2023-10-12 04:08:07,485][78091] Updated weights for policy 0, policy_version 24170 (0.0008) -[2023-10-12 04:08:07,849][78091] Updated weights for policy 0, policy_version 24180 (0.0008) -[2023-10-12 04:08:08,225][78091] Updated weights for policy 0, policy_version 24190 (0.0008) -[2023-10-12 04:08:08,373][78123] Updated weights for policy 1, policy_version 24070 (0.0008) -[2023-10-12 04:08:08,735][78123] Updated weights for policy 1, policy_version 24080 (0.0008) -[2023-10-12 04:08:09,109][78123] Updated weights for policy 1, policy_version 24090 (0.0009) -[2023-10-12 04:08:10,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 49446912. Throughput: 0: 1592.1, 1: 1595.0. Samples: 12369336. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-12 04:08:10,202][77203] Avg episode reward: [(0, '35.420'), (1, '39.920')] -[2023-10-12 04:08:12,571][78091] Updated weights for policy 0, policy_version 24200 (0.0009) -[2023-10-12 04:08:12,943][78091] Updated weights for policy 0, policy_version 24210 (0.0007) -[2023-10-12 04:08:13,316][78091] Updated weights for policy 0, policy_version 24220 (0.0007) -[2023-10-12 04:08:13,427][78123] Updated weights for policy 1, policy_version 24100 (0.0008) -[2023-10-12 04:08:13,794][78123] Updated weights for policy 1, policy_version 24110 (0.0008) -[2023-10-12 04:08:14,155][78123] Updated weights for policy 1, policy_version 24120 (0.0008) -[2023-10-12 04:08:15,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 49512448. Throughput: 0: 1607.2, 1: 1600.6. Samples: 12379760. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-12 04:08:15,202][77203] Avg episode reward: [(0, '36.450'), (1, '42.030')] -[2023-10-12 04:08:17,711][78091] Updated weights for policy 0, policy_version 24230 (0.0009) -[2023-10-12 04:08:18,083][78091] Updated weights for policy 0, policy_version 24240 (0.0009) -[2023-10-12 04:08:18,454][78091] Updated weights for policy 0, policy_version 24250 (0.0010) -[2023-10-12 04:08:18,526][78123] Updated weights for policy 1, policy_version 24130 (0.0008) -[2023-10-12 04:08:18,894][78123] Updated weights for policy 1, policy_version 24140 (0.0009) -[2023-10-12 04:08:19,267][78123] Updated weights for policy 1, policy_version 24150 (0.0008) -[2023-10-12 04:08:19,633][78123] Updated weights for policy 1, policy_version 24160 (0.0007) -[2023-10-12 04:08:20,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 12885.0). Total num frames: 49577984. Throughput: 0: 1595.3, 1: 1609.4. Samples: 12398326. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:08:20,203][77203] Avg episode reward: [(0, '41.100'), (1, '38.960')] -[2023-10-12 04:08:22,715][78091] Updated weights for policy 0, policy_version 24260 (0.0008) -[2023-10-12 04:08:23,091][78091] Updated weights for policy 0, policy_version 24270 (0.0007) -[2023-10-12 04:08:23,459][78091] Updated weights for policy 0, policy_version 24280 (0.0007) -[2023-10-12 04:08:24,015][78123] Updated weights for policy 1, policy_version 24170 (0.0010) -[2023-10-12 04:08:24,394][78123] Updated weights for policy 1, policy_version 24180 (0.0010) -[2023-10-12 04:08:24,766][78123] Updated weights for policy 1, policy_version 24190 (0.0009) -[2023-10-12 04:08:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 49643520. Throughput: 0: 1598.1, 1: 1587.1. Samples: 12416852. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:08:25,202][77203] Avg episode reward: [(0, '37.910'), (1, '37.850')] -[2023-10-12 04:08:27,777][78091] Updated weights for policy 0, policy_version 24290 (0.0008) -[2023-10-12 04:08:28,150][78091] Updated weights for policy 0, policy_version 24300 (0.0008) -[2023-10-12 04:08:28,515][78091] Updated weights for policy 0, policy_version 24310 (0.0009) -[2023-10-12 04:08:28,877][78091] Updated weights for policy 0, policy_version 24320 (0.0008) -[2023-10-12 04:08:29,190][78123] Updated weights for policy 1, policy_version 24200 (0.0008) -[2023-10-12 04:08:29,549][78123] Updated weights for policy 1, policy_version 24210 (0.0009) -[2023-10-12 04:08:29,918][78123] Updated weights for policy 1, policy_version 24220 (0.0009) -[2023-10-12 04:08:30,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 49709056. Throughput: 0: 1619.6, 1: 1587.9. Samples: 12427532. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:08:30,202][77203] Avg episode reward: [(0, '35.840'), (1, '37.030')] -[2023-10-12 04:08:33,050][78091] Updated weights for policy 0, policy_version 24330 (0.0008) -[2023-10-12 04:08:33,430][78091] Updated weights for policy 0, policy_version 24340 (0.0009) -[2023-10-12 04:08:33,794][78091] Updated weights for policy 0, policy_version 24350 (0.0007) -[2023-10-12 04:08:34,318][78123] Updated weights for policy 1, policy_version 24230 (0.0008) -[2023-10-12 04:08:34,683][78123] Updated weights for policy 1, policy_version 24240 (0.0009) -[2023-10-12 04:08:35,049][78123] Updated weights for policy 1, policy_version 24250 (0.0009) -[2023-10-12 04:08:35,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 49741824. Throughput: 0: 1598.8, 1: 1606.4. Samples: 12446258. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:08:35,201][77203] Avg episode reward: [(0, '40.420'), (1, '44.760')] -[2023-10-12 04:08:38,230][78091] Updated weights for policy 0, policy_version 24360 (0.0008) -[2023-10-12 04:08:38,606][78091] Updated weights for policy 0, policy_version 24370 (0.0009) -[2023-10-12 04:08:38,971][78091] Updated weights for policy 0, policy_version 24380 (0.0007) -[2023-10-12 04:08:39,288][78123] Updated weights for policy 1, policy_version 24260 (0.0009) -[2023-10-12 04:08:39,662][78123] Updated weights for policy 1, policy_version 24270 (0.0010) -[2023-10-12 04:08:40,034][78123] Updated weights for policy 1, policy_version 24280 (0.0011) -[2023-10-12 04:08:40,201][77203] Fps is (10 sec: 9830.6, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 49807360. Throughput: 0: 1595.2, 1: 1599.3. Samples: 12465210. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-12 04:08:40,201][77203] Avg episode reward: [(0, '34.960'), (1, '37.170')] -[2023-10-12 04:08:43,313][78091] Updated weights for policy 0, policy_version 24390 (0.0008) -[2023-10-12 04:08:43,684][78091] Updated weights for policy 0, policy_version 24400 (0.0007) -[2023-10-12 04:08:44,058][78091] Updated weights for policy 0, policy_version 24410 (0.0009) -[2023-10-12 04:08:44,418][78123] Updated weights for policy 1, policy_version 24290 (0.0010) -[2023-10-12 04:08:44,802][78123] Updated weights for policy 1, policy_version 24300 (0.0010) -[2023-10-12 04:08:45,175][78123] Updated weights for policy 1, policy_version 24310 (0.0010) -[2023-10-12 04:08:45,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 49872896. Throughput: 0: 1611.5, 1: 1581.5. Samples: 12475478. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-12 04:08:45,202][77203] Avg episode reward: [(0, '39.530'), (1, '40.790')] -[2023-10-12 04:08:45,549][78123] Updated weights for policy 1, policy_version 24320 (0.0007) -[2023-10-12 04:08:48,208][78091] Updated weights for policy 0, policy_version 24420 (0.0008) -[2023-10-12 04:08:48,575][78091] Updated weights for policy 0, policy_version 24430 (0.0007) -[2023-10-12 04:08:48,954][78091] Updated weights for policy 0, policy_version 24440 (0.0007) -[2023-10-12 04:08:49,969][78123] Updated weights for policy 1, policy_version 24330 (0.0007) -[2023-10-12 04:08:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 49938432. Throughput: 0: 1606.7, 1: 1593.8. Samples: 12494480. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-12 04:08:50,201][77203] Avg episode reward: [(0, '40.290'), (1, '45.010')] -[2023-10-12 04:08:50,338][78123] Updated weights for policy 1, policy_version 24340 (0.0007) -[2023-10-12 04:08:50,716][78123] Updated weights for policy 1, policy_version 24350 (0.0008) -[2023-10-12 04:08:53,367][78091] Updated weights for policy 0, policy_version 24450 (0.0007) -[2023-10-12 04:08:53,773][78091] Updated weights for policy 0, policy_version 24460 (0.0007) -[2023-10-12 04:08:54,142][78091] Updated weights for policy 0, policy_version 24470 (0.0007) -[2023-10-12 04:08:54,516][78091] Updated weights for policy 0, policy_version 24480 (0.0007) -[2023-10-12 04:08:54,907][78123] Updated weights for policy 1, policy_version 24360 (0.0009) -[2023-10-12 04:08:55,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 50003968. Throughput: 0: 1592.9, 1: 1606.0. Samples: 12513290. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-12 04:08:55,201][77203] Avg episode reward: [(0, '34.150'), (1, '43.110')] -[2023-10-12 04:08:55,273][78123] Updated weights for policy 1, policy_version 24370 (0.0009) -[2023-10-12 04:08:55,650][78123] Updated weights for policy 1, policy_version 24380 (0.0009) -[2023-10-12 04:08:58,782][78091] Updated weights for policy 0, policy_version 24490 (0.0010) -[2023-10-12 04:08:59,160][78091] Updated weights for policy 0, policy_version 24500 (0.0010) -[2023-10-12 04:08:59,520][78091] Updated weights for policy 0, policy_version 24510 (0.0009) -[2023-10-12 04:08:59,823][78123] Updated weights for policy 1, policy_version 24390 (0.0008) -[2023-10-12 04:09:00,189][78123] Updated weights for policy 1, policy_version 24400 (0.0008) -[2023-10-12 04:09:00,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 50069504. Throughput: 0: 1601.9, 1: 1585.9. Samples: 12523210. Policy #0 lag: (min: 20.0, avg: 31.2, max: 52.0) -[2023-10-12 04:09:00,201][77203] Avg episode reward: [(0, '42.550'), (1, '37.120')] -[2023-10-12 04:09:00,556][78123] Updated weights for policy 1, policy_version 24410 (0.0009) -[2023-10-12 04:09:03,685][78091] Updated weights for policy 0, policy_version 24520 (0.0007) -[2023-10-12 04:09:04,054][78091] Updated weights for policy 0, policy_version 24530 (0.0008) -[2023-10-12 04:09:04,419][78091] Updated weights for policy 0, policy_version 24540 (0.0009) -[2023-10-12 04:09:04,962][78123] Updated weights for policy 1, policy_version 24420 (0.0008) -[2023-10-12 04:09:05,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 50135040. Throughput: 0: 1610.1, 1: 1594.8. Samples: 12542546. Policy #0 lag: (min: 20.0, avg: 31.2, max: 52.0) -[2023-10-12 04:09:05,202][77203] Avg episode reward: [(0, '35.880'), (1, '40.310')] -[2023-10-12 04:09:05,336][78123] Updated weights for policy 1, policy_version 24430 (0.0008) -[2023-10-12 04:09:05,701][78123] Updated weights for policy 1, policy_version 24440 (0.0007) -[2023-10-12 04:09:08,661][78091] Updated weights for policy 0, policy_version 24550 (0.0010) -[2023-10-12 04:09:09,032][78091] Updated weights for policy 0, policy_version 24560 (0.0007) -[2023-10-12 04:09:09,394][78091] Updated weights for policy 0, policy_version 24570 (0.0009) -[2023-10-12 04:09:09,939][78123] Updated weights for policy 1, policy_version 24450 (0.0009) -[2023-10-12 04:09:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 50200576. Throughput: 0: 1592.7, 1: 1616.6. Samples: 12561268. Policy #0 lag: (min: 20.0, avg: 31.2, max: 52.0) -[2023-10-12 04:09:10,201][77203] Avg episode reward: [(0, '35.190'), (1, '42.760')] -[2023-10-12 04:09:10,210][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000024576_25165824.pth... -[2023-10-12 04:09:10,245][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000023072_23625728.pth -[2023-10-12 04:09:10,308][78123] Updated weights for policy 1, policy_version 24460 (0.0010) -[2023-10-12 04:09:10,675][78123] Updated weights for policy 1, policy_version 24470 (0.0008) -[2023-10-12 04:09:11,040][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000024480_25067520.pth... -[2023-10-12 04:09:11,041][78123] Updated weights for policy 1, policy_version 24480 (0.0009) -[2023-10-12 04:09:11,069][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000022976_23527424.pth -[2023-10-12 04:09:13,698][78091] Updated weights for policy 0, policy_version 24580 (0.0010) -[2023-10-12 04:09:14,074][78091] Updated weights for policy 0, policy_version 24590 (0.0010) -[2023-10-12 04:09:14,444][78091] Updated weights for policy 0, policy_version 24600 (0.0009) -[2023-10-12 04:09:15,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 50266112. Throughput: 0: 1595.6, 1: 1597.6. Samples: 12571222. Policy #0 lag: (min: 20.0, avg: 31.2, max: 52.0) -[2023-10-12 04:09:15,201][77203] Avg episode reward: [(0, '41.120'), (1, '41.420')] -[2023-10-12 04:09:15,259][78123] Updated weights for policy 1, policy_version 24490 (0.0010) -[2023-10-12 04:09:15,628][78123] Updated weights for policy 1, policy_version 24500 (0.0010) -[2023-10-12 04:09:15,995][78123] Updated weights for policy 1, policy_version 24510 (0.0007) -[2023-10-12 04:09:18,703][78091] Updated weights for policy 0, policy_version 24610 (0.0008) -[2023-10-12 04:09:19,071][78091] Updated weights for policy 0, policy_version 24620 (0.0008) -[2023-10-12 04:09:19,439][78091] Updated weights for policy 0, policy_version 24630 (0.0010) -[2023-10-12 04:09:19,825][78091] Updated weights for policy 0, policy_version 24640 (0.0011) -[2023-10-12 04:09:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 50331648. Throughput: 0: 1611.6, 1: 1596.3. Samples: 12590612. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:09:20,201][77203] Avg episode reward: [(0, '34.060'), (1, '38.990')] -[2023-10-12 04:09:20,309][78123] Updated weights for policy 1, policy_version 24520 (0.0007) -[2023-10-12 04:09:20,674][78123] Updated weights for policy 1, policy_version 24530 (0.0010) -[2023-10-12 04:09:21,044][78123] Updated weights for policy 1, policy_version 24540 (0.0009) -[2023-10-12 04:09:24,180][78091] Updated weights for policy 0, policy_version 24650 (0.0007) -[2023-10-12 04:09:24,557][78091] Updated weights for policy 0, policy_version 24660 (0.0007) -[2023-10-12 04:09:24,937][78091] Updated weights for policy 0, policy_version 24670 (0.0007) -[2023-10-12 04:09:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 50397184. Throughput: 0: 1601.7, 1: 1603.3. Samples: 12609436. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:09:25,202][77203] Avg episode reward: [(0, '40.230'), (1, '37.720')] -[2023-10-12 04:09:25,525][78123] Updated weights for policy 1, policy_version 24550 (0.0008) -[2023-10-12 04:09:25,888][78123] Updated weights for policy 1, policy_version 24560 (0.0010) -[2023-10-12 04:09:26,262][78123] Updated weights for policy 1, policy_version 24570 (0.0008) -[2023-10-12 04:09:29,285][78091] Updated weights for policy 0, policy_version 24680 (0.0007) -[2023-10-12 04:09:29,652][78091] Updated weights for policy 0, policy_version 24690 (0.0007) -[2023-10-12 04:09:30,031][78091] Updated weights for policy 0, policy_version 24700 (0.0007) -[2023-10-12 04:09:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 50462720. Throughput: 0: 1591.2, 1: 1596.4. Samples: 12618920. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:09:30,201][77203] Avg episode reward: [(0, '36.750'), (1, '44.870')] -[2023-10-12 04:09:30,477][78123] Updated weights for policy 1, policy_version 24580 (0.0007) -[2023-10-12 04:09:30,868][78123] Updated weights for policy 1, policy_version 24590 (0.0008) -[2023-10-12 04:09:31,238][78123] Updated weights for policy 1, policy_version 24600 (0.0007) -[2023-10-12 04:09:34,352][78091] Updated weights for policy 0, policy_version 24710 (0.0010) -[2023-10-12 04:09:34,728][78091] Updated weights for policy 0, policy_version 24720 (0.0011) -[2023-10-12 04:09:35,099][78091] Updated weights for policy 0, policy_version 24730 (0.0011) -[2023-10-12 04:09:35,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 50495488. Throughput: 0: 1607.7, 1: 1594.9. Samples: 12638600. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:09:35,201][77203] Avg episode reward: [(0, '37.480'), (1, '44.040')] -[2023-10-12 04:09:35,612][78123] Updated weights for policy 1, policy_version 24610 (0.0010) -[2023-10-12 04:09:35,978][78123] Updated weights for policy 1, policy_version 24620 (0.0011) -[2023-10-12 04:09:36,343][78123] Updated weights for policy 1, policy_version 24630 (0.0008) -[2023-10-12 04:09:36,708][78123] Updated weights for policy 1, policy_version 24640 (0.0008) -[2023-10-12 04:09:39,582][78091] Updated weights for policy 0, policy_version 24740 (0.0010) -[2023-10-12 04:09:39,960][78091] Updated weights for policy 0, policy_version 24750 (0.0009) -[2023-10-12 04:09:40,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 50561024. Throughput: 0: 1610.5, 1: 1593.8. Samples: 12657484. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:09:40,201][77203] Avg episode reward: [(0, '40.230'), (1, '38.700')] -[2023-10-12 04:09:40,322][78091] Updated weights for policy 0, policy_version 24760 (0.0008) -[2023-10-12 04:09:41,059][78123] Updated weights for policy 1, policy_version 24650 (0.0009) -[2023-10-12 04:09:41,420][78123] Updated weights for policy 1, policy_version 24660 (0.0009) -[2023-10-12 04:09:41,786][78123] Updated weights for policy 1, policy_version 24670 (0.0007) -[2023-10-12 04:09:44,663][78091] Updated weights for policy 0, policy_version 24770 (0.0011) -[2023-10-12 04:09:45,033][78091] Updated weights for policy 0, policy_version 24780 (0.0009) -[2023-10-12 04:09:45,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 50626560. Throughput: 0: 1593.3, 1: 1589.3. Samples: 12666428. Policy #0 lag: (min: 2.0, avg: 2.0, max: 4.0) -[2023-10-12 04:09:45,202][77203] Avg episode reward: [(0, '36.600'), (1, '38.390')] -[2023-10-12 04:09:45,409][78091] Updated weights for policy 0, policy_version 24790 (0.0007) -[2023-10-12 04:09:45,776][78091] Updated weights for policy 0, policy_version 24800 (0.0008) -[2023-10-12 04:09:46,015][78123] Updated weights for policy 1, policy_version 24680 (0.0009) -[2023-10-12 04:09:46,384][78123] Updated weights for policy 1, policy_version 24690 (0.0010) -[2023-10-12 04:09:46,744][78123] Updated weights for policy 1, policy_version 24700 (0.0009) -[2023-10-12 04:09:50,198][78091] Updated weights for policy 0, policy_version 24810 (0.0008) -[2023-10-12 04:09:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 50692096. Throughput: 0: 1595.1, 1: 1588.2. Samples: 12685794. Policy #0 lag: (min: 2.0, avg: 2.0, max: 4.0) -[2023-10-12 04:09:50,201][77203] Avg episode reward: [(0, '38.750'), (1, '40.500')] -[2023-10-12 04:09:50,570][78091] Updated weights for policy 0, policy_version 24820 (0.0007) -[2023-10-12 04:09:50,945][78091] Updated weights for policy 0, policy_version 24830 (0.0008) -[2023-10-12 04:09:51,206][78123] Updated weights for policy 1, policy_version 24710 (0.0008) -[2023-10-12 04:09:51,577][78123] Updated weights for policy 1, policy_version 24720 (0.0008) -[2023-10-12 04:09:51,943][78123] Updated weights for policy 1, policy_version 24730 (0.0007) -[2023-10-12 04:09:55,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 50757632. Throughput: 0: 1616.0, 1: 1588.8. Samples: 12705486. Policy #0 lag: (min: 2.0, avg: 2.0, max: 4.0) -[2023-10-12 04:09:55,202][77203] Avg episode reward: [(0, '37.810'), (1, '42.410')] -[2023-10-12 04:09:55,242][78091] Updated weights for policy 0, policy_version 24840 (0.0008) -[2023-10-12 04:09:55,616][78091] Updated weights for policy 0, policy_version 24850 (0.0007) -[2023-10-12 04:09:55,980][78091] Updated weights for policy 0, policy_version 24860 (0.0008) -[2023-10-12 04:09:56,207][78123] Updated weights for policy 1, policy_version 24740 (0.0008) -[2023-10-12 04:09:56,583][78123] Updated weights for policy 1, policy_version 24750 (0.0008) -[2023-10-12 04:09:56,951][78123] Updated weights for policy 1, policy_version 24760 (0.0009) -[2023-10-12 04:10:00,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 50823168. Throughput: 0: 1587.2, 1: 1586.6. Samples: 12714046. Policy #0 lag: (min: 2.0, avg: 2.0, max: 4.0) -[2023-10-12 04:10:00,201][77203] Avg episode reward: [(0, '36.200'), (1, '37.070')] -[2023-10-12 04:10:00,324][78091] Updated weights for policy 0, policy_version 24870 (0.0009) -[2023-10-12 04:10:00,693][78091] Updated weights for policy 0, policy_version 24880 (0.0008) -[2023-10-12 04:10:01,058][78091] Updated weights for policy 0, policy_version 24890 (0.0010) -[2023-10-12 04:10:01,129][78123] Updated weights for policy 1, policy_version 24770 (0.0008) -[2023-10-12 04:10:01,489][78123] Updated weights for policy 1, policy_version 24780 (0.0007) -[2023-10-12 04:10:01,856][78123] Updated weights for policy 1, policy_version 24790 (0.0007) -[2023-10-12 04:10:02,233][78123] Updated weights for policy 1, policy_version 24800 (0.0007) -[2023-10-12 04:10:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 50888704. Throughput: 0: 1595.9, 1: 1587.4. Samples: 12733860. Policy #0 lag: (min: 28.0, avg: 30.3, max: 60.0) -[2023-10-12 04:10:05,202][77203] Avg episode reward: [(0, '38.710'), (1, '37.850')] -[2023-10-12 04:10:05,286][78091] Updated weights for policy 0, policy_version 24900 (0.0008) -[2023-10-12 04:10:05,648][78091] Updated weights for policy 0, policy_version 24910 (0.0007) -[2023-10-12 04:10:06,024][78091] Updated weights for policy 0, policy_version 24920 (0.0008) -[2023-10-12 04:10:06,307][78123] Updated weights for policy 1, policy_version 24810 (0.0009) -[2023-10-12 04:10:06,678][78123] Updated weights for policy 1, policy_version 24820 (0.0009) -[2023-10-12 04:10:07,041][78123] Updated weights for policy 1, policy_version 24830 (0.0008) -[2023-10-12 04:10:10,160][78091] Updated weights for policy 0, policy_version 24930 (0.0007) -[2023-10-12 04:10:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 50954240. Throughput: 0: 1610.9, 1: 1589.0. Samples: 12753432. Policy #0 lag: (min: 28.0, avg: 30.3, max: 60.0) -[2023-10-12 04:10:10,202][77203] Avg episode reward: [(0, '37.480'), (1, '37.920')] -[2023-10-12 04:10:10,521][78091] Updated weights for policy 0, policy_version 24940 (0.0009) -[2023-10-12 04:10:10,889][78091] Updated weights for policy 0, policy_version 24950 (0.0008) -[2023-10-12 04:10:11,273][78091] Updated weights for policy 0, policy_version 24960 (0.0007) -[2023-10-12 04:10:11,594][78123] Updated weights for policy 1, policy_version 24840 (0.0009) -[2023-10-12 04:10:11,969][78123] Updated weights for policy 1, policy_version 24850 (0.0007) -[2023-10-12 04:10:12,337][78123] Updated weights for policy 1, policy_version 24860 (0.0007) -[2023-10-12 04:10:15,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 51019776. Throughput: 0: 1593.2, 1: 1586.2. Samples: 12761992. Policy #0 lag: (min: 28.0, avg: 30.3, max: 60.0) -[2023-10-12 04:10:15,201][77203] Avg episode reward: [(0, '36.930'), (1, '41.280')] -[2023-10-12 04:10:15,731][78091] Updated weights for policy 0, policy_version 24970 (0.0008) -[2023-10-12 04:10:16,107][78091] Updated weights for policy 0, policy_version 24980 (0.0007) -[2023-10-12 04:10:16,482][78091] Updated weights for policy 0, policy_version 24990 (0.0007) -[2023-10-12 04:10:16,595][78123] Updated weights for policy 1, policy_version 24870 (0.0007) -[2023-10-12 04:10:16,955][78123] Updated weights for policy 1, policy_version 24880 (0.0010) -[2023-10-12 04:10:17,324][78123] Updated weights for policy 1, policy_version 24890 (0.0009) -[2023-10-12 04:10:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 51085312. Throughput: 0: 1591.0, 1: 1586.5. Samples: 12781590. Policy #0 lag: (min: 28.0, avg: 30.3, max: 60.0) -[2023-10-12 04:10:20,202][77203] Avg episode reward: [(0, '37.750'), (1, '40.230')] -[2023-10-12 04:10:20,609][78091] Updated weights for policy 0, policy_version 25000 (0.0008) -[2023-10-12 04:10:20,990][78091] Updated weights for policy 0, policy_version 25010 (0.0007) -[2023-10-12 04:10:21,358][78091] Updated weights for policy 0, policy_version 25020 (0.0007) -[2023-10-12 04:10:22,002][78123] Updated weights for policy 1, policy_version 24900 (0.0009) -[2023-10-12 04:10:22,389][78123] Updated weights for policy 1, policy_version 24910 (0.0010) -[2023-10-12 04:10:22,759][78123] Updated weights for policy 1, policy_version 24920 (0.0010) -[2023-10-12 04:10:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 51150848. Throughput: 0: 1606.6, 1: 1585.4. Samples: 12801124. Policy #0 lag: (min: 13.0, avg: 16.0, max: 45.0) -[2023-10-12 04:10:25,201][77203] Avg episode reward: [(0, '36.130'), (1, '40.960')] -[2023-10-12 04:10:25,616][78091] Updated weights for policy 0, policy_version 25030 (0.0008) -[2023-10-12 04:10:26,004][78091] Updated weights for policy 0, policy_version 25040 (0.0009) -[2023-10-12 04:10:26,378][78091] Updated weights for policy 0, policy_version 25050 (0.0008) -[2023-10-12 04:10:26,920][78123] Updated weights for policy 1, policy_version 24930 (0.0008) -[2023-10-12 04:10:27,283][78123] Updated weights for policy 1, policy_version 24940 (0.0008) -[2023-10-12 04:10:27,650][78123] Updated weights for policy 1, policy_version 24950 (0.0009) -[2023-10-12 04:10:28,010][78123] Updated weights for policy 1, policy_version 24960 (0.0010) -[2023-10-12 04:10:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 51216384. Throughput: 0: 1594.8, 1: 1596.2. Samples: 12810022. Policy #0 lag: (min: 13.0, avg: 16.0, max: 45.0) -[2023-10-12 04:10:30,202][77203] Avg episode reward: [(0, '36.740'), (1, '42.630')] -[2023-10-12 04:10:30,525][78091] Updated weights for policy 0, policy_version 25060 (0.0009) -[2023-10-12 04:10:30,904][78091] Updated weights for policy 0, policy_version 25070 (0.0010) -[2023-10-12 04:10:31,263][78091] Updated weights for policy 0, policy_version 25080 (0.0011) -[2023-10-12 04:10:32,269][78123] Updated weights for policy 1, policy_version 24970 (0.0009) -[2023-10-12 04:10:32,641][78123] Updated weights for policy 1, policy_version 24980 (0.0008) -[2023-10-12 04:10:33,005][78123] Updated weights for policy 1, policy_version 24990 (0.0009) -[2023-10-12 04:10:35,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 51281920. Throughput: 0: 1602.5, 1: 1587.9. Samples: 12829364. Policy #0 lag: (min: 13.0, avg: 16.0, max: 45.0) -[2023-10-12 04:10:35,202][77203] Avg episode reward: [(0, '35.720'), (1, '43.120')] -[2023-10-12 04:10:35,556][78091] Updated weights for policy 0, policy_version 25090 (0.0010) -[2023-10-12 04:10:35,938][78091] Updated weights for policy 0, policy_version 25100 (0.0007) -[2023-10-12 04:10:36,309][78091] Updated weights for policy 0, policy_version 25110 (0.0009) -[2023-10-12 04:10:36,674][78091] Updated weights for policy 0, policy_version 25120 (0.0009) -[2023-10-12 04:10:37,377][78123] Updated weights for policy 1, policy_version 25000 (0.0007) -[2023-10-12 04:10:37,744][78123] Updated weights for policy 1, policy_version 25010 (0.0009) -[2023-10-12 04:10:38,116][78123] Updated weights for policy 1, policy_version 25020 (0.0008) -[2023-10-12 04:10:40,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 51347456. Throughput: 0: 1597.6, 1: 1587.2. Samples: 12848802. Policy #0 lag: (min: 13.0, avg: 16.0, max: 45.0) -[2023-10-12 04:10:40,202][77203] Avg episode reward: [(0, '36.080'), (1, '40.950')] -[2023-10-12 04:10:41,124][78091] Updated weights for policy 0, policy_version 25130 (0.0008) -[2023-10-12 04:10:41,502][78091] Updated weights for policy 0, policy_version 25140 (0.0009) -[2023-10-12 04:10:41,877][78091] Updated weights for policy 0, policy_version 25150 (0.0009) -[2023-10-12 04:10:42,597][78123] Updated weights for policy 1, policy_version 25030 (0.0008) -[2023-10-12 04:10:42,974][78123] Updated weights for policy 1, policy_version 25040 (0.0010) -[2023-10-12 04:10:43,341][78123] Updated weights for policy 1, policy_version 25050 (0.0009) -[2023-10-12 04:10:45,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 51412992. Throughput: 0: 1594.9, 1: 1606.8. Samples: 12858124. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-12 04:10:45,201][77203] Avg episode reward: [(0, '38.950'), (1, '36.490')] -[2023-10-12 04:10:46,168][78091] Updated weights for policy 0, policy_version 25160 (0.0009) -[2023-10-12 04:10:46,539][78091] Updated weights for policy 0, policy_version 25170 (0.0009) -[2023-10-12 04:10:46,910][78091] Updated weights for policy 0, policy_version 25180 (0.0010) -[2023-10-12 04:10:47,779][78123] Updated weights for policy 1, policy_version 25060 (0.0008) -[2023-10-12 04:10:48,146][78123] Updated weights for policy 1, policy_version 25070 (0.0008) -[2023-10-12 04:10:48,515][78123] Updated weights for policy 1, policy_version 25080 (0.0011) -[2023-10-12 04:10:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 51478528. Throughput: 0: 1592.1, 1: 1588.2. Samples: 12876974. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-12 04:10:50,202][77203] Avg episode reward: [(0, '35.760'), (1, '37.130')] -[2023-10-12 04:10:51,326][78091] Updated weights for policy 0, policy_version 25190 (0.0009) -[2023-10-12 04:10:51,703][78091] Updated weights for policy 0, policy_version 25200 (0.0007) -[2023-10-12 04:10:52,062][78091] Updated weights for policy 0, policy_version 25210 (0.0010) -[2023-10-12 04:10:52,694][78123] Updated weights for policy 1, policy_version 25090 (0.0010) -[2023-10-12 04:10:53,063][78123] Updated weights for policy 1, policy_version 25100 (0.0008) -[2023-10-12 04:10:53,429][78123] Updated weights for policy 1, policy_version 25110 (0.0009) -[2023-10-12 04:10:53,795][78123] Updated weights for policy 1, policy_version 25120 (0.0008) -[2023-10-12 04:10:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 51544064. Throughput: 0: 1588.5, 1: 1586.4. Samples: 12896306. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-12 04:10:55,201][77203] Avg episode reward: [(0, '40.680'), (1, '40.690')] -[2023-10-12 04:10:56,426][78091] Updated weights for policy 0, policy_version 25220 (0.0008) -[2023-10-12 04:10:56,791][78091] Updated weights for policy 0, policy_version 25230 (0.0008) -[2023-10-12 04:10:57,168][78091] Updated weights for policy 0, policy_version 25240 (0.0007) -[2023-10-12 04:10:58,046][78123] Updated weights for policy 1, policy_version 25130 (0.0010) -[2023-10-12 04:10:58,414][78123] Updated weights for policy 1, policy_version 25140 (0.0010) -[2023-10-12 04:10:58,781][78123] Updated weights for policy 1, policy_version 25150 (0.0010) -[2023-10-12 04:11:00,201][77203] Fps is (10 sec: 13106.6, 60 sec: 13107.1, 300 sec: 12773.9). Total num frames: 51609600. Throughput: 0: 1588.0, 1: 1615.2. Samples: 12906136. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-12 04:11:00,203][77203] Avg episode reward: [(0, '37.800'), (1, '42.810')] -[2023-10-12 04:11:01,373][78091] Updated weights for policy 0, policy_version 25250 (0.0008) -[2023-10-12 04:11:01,746][78091] Updated weights for policy 0, policy_version 25260 (0.0010) -[2023-10-12 04:11:02,111][78091] Updated weights for policy 0, policy_version 25270 (0.0009) -[2023-10-12 04:11:02,488][78091] Updated weights for policy 0, policy_version 25280 (0.0009) -[2023-10-12 04:11:03,099][78123] Updated weights for policy 1, policy_version 25160 (0.0008) -[2023-10-12 04:11:03,474][78123] Updated weights for policy 1, policy_version 25170 (0.0009) -[2023-10-12 04:11:03,843][78123] Updated weights for policy 1, policy_version 25180 (0.0008) -[2023-10-12 04:11:05,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 51675136. Throughput: 0: 1590.8, 1: 1594.7. Samples: 12924940. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 04:11:05,202][77203] Avg episode reward: [(0, '36.940'), (1, '41.020')] -[2023-10-12 04:11:06,744][78091] Updated weights for policy 0, policy_version 25290 (0.0010) -[2023-10-12 04:11:07,115][78091] Updated weights for policy 0, policy_version 25300 (0.0009) -[2023-10-12 04:11:07,485][78091] Updated weights for policy 0, policy_version 25310 (0.0009) -[2023-10-12 04:11:08,027][78123] Updated weights for policy 1, policy_version 25190 (0.0007) -[2023-10-12 04:11:08,397][78123] Updated weights for policy 1, policy_version 25200 (0.0008) -[2023-10-12 04:11:08,761][78123] Updated weights for policy 1, policy_version 25210 (0.0007) -[2023-10-12 04:11:10,201][77203] Fps is (10 sec: 13107.9, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 51740672. Throughput: 0: 1588.7, 1: 1594.3. Samples: 12944358. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 04:11:10,202][77203] Avg episode reward: [(0, '38.000'), (1, '39.950')] -[2023-10-12 04:11:10,210][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000025216_25821184.pth... -[2023-10-12 04:11:10,211][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000025312_25919488.pth... -[2023-10-12 04:11:10,240][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000023712_24281088.pth -[2023-10-12 04:11:10,248][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000023808_24379392.pth -[2023-10-12 04:11:11,847][78091] Updated weights for policy 0, policy_version 25320 (0.0007) -[2023-10-12 04:11:12,221][78091] Updated weights for policy 0, policy_version 25330 (0.0007) -[2023-10-12 04:11:12,590][78091] Updated weights for policy 0, policy_version 25340 (0.0009) -[2023-10-12 04:11:13,223][78123] Updated weights for policy 1, policy_version 25220 (0.0008) -[2023-10-12 04:11:13,590][78123] Updated weights for policy 1, policy_version 25230 (0.0007) -[2023-10-12 04:11:13,958][78123] Updated weights for policy 1, policy_version 25240 (0.0009) -[2023-10-12 04:11:15,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 51806208. Throughput: 0: 1588.4, 1: 1608.5. Samples: 12953882. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 04:11:15,201][77203] Avg episode reward: [(0, '34.070'), (1, '41.010')] -[2023-10-12 04:11:16,911][78091] Updated weights for policy 0, policy_version 25350 (0.0009) -[2023-10-12 04:11:17,274][78091] Updated weights for policy 0, policy_version 25360 (0.0009) -[2023-10-12 04:11:17,642][78091] Updated weights for policy 0, policy_version 25370 (0.0010) -[2023-10-12 04:11:18,091][78123] Updated weights for policy 1, policy_version 25250 (0.0010) -[2023-10-12 04:11:18,458][78123] Updated weights for policy 1, policy_version 25260 (0.0011) -[2023-10-12 04:11:18,829][78123] Updated weights for policy 1, policy_version 25270 (0.0009) -[2023-10-12 04:11:19,188][78123] Updated weights for policy 1, policy_version 25280 (0.0009) -[2023-10-12 04:11:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 51871744. Throughput: 0: 1587.6, 1: 1600.8. Samples: 12972842. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 04:11:20,201][77203] Avg episode reward: [(0, '39.640'), (1, '38.910')] -[2023-10-12 04:11:21,986][78091] Updated weights for policy 0, policy_version 25380 (0.0008) -[2023-10-12 04:11:22,370][78091] Updated weights for policy 0, policy_version 25390 (0.0008) -[2023-10-12 04:11:22,736][78091] Updated weights for policy 0, policy_version 25400 (0.0009) -[2023-10-12 04:11:23,678][78123] Updated weights for policy 1, policy_version 25290 (0.0010) -[2023-10-12 04:11:24,049][78123] Updated weights for policy 1, policy_version 25300 (0.0010) -[2023-10-12 04:11:24,416][78123] Updated weights for policy 1, policy_version 25310 (0.0008) -[2023-10-12 04:11:25,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 51937280. Throughput: 0: 1589.7, 1: 1590.1. Samples: 12991894. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-12 04:11:25,202][77203] Avg episode reward: [(0, '39.320'), (1, '43.040')] -[2023-10-12 04:11:27,069][78091] Updated weights for policy 0, policy_version 25410 (0.0009) -[2023-10-12 04:11:27,441][78091] Updated weights for policy 0, policy_version 25420 (0.0008) -[2023-10-12 04:11:27,815][78091] Updated weights for policy 0, policy_version 25430 (0.0007) -[2023-10-12 04:11:28,188][78091] Updated weights for policy 0, policy_version 25440 (0.0008) -[2023-10-12 04:11:28,850][78123] Updated weights for policy 1, policy_version 25320 (0.0010) -[2023-10-12 04:11:29,216][78123] Updated weights for policy 1, policy_version 25330 (0.0008) -[2023-10-12 04:11:29,586][78123] Updated weights for policy 1, policy_version 25340 (0.0009) -[2023-10-12 04:11:30,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 52002816. Throughput: 0: 1604.4, 1: 1595.5. Samples: 13002118. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-12 04:11:30,202][77203] Avg episode reward: [(0, '35.130'), (1, '39.060')] -[2023-10-12 04:11:32,320][78091] Updated weights for policy 0, policy_version 25450 (0.0007) -[2023-10-12 04:11:32,687][78091] Updated weights for policy 0, policy_version 25460 (0.0007) -[2023-10-12 04:11:33,060][78091] Updated weights for policy 0, policy_version 25470 (0.0007) -[2023-10-12 04:11:34,058][78123] Updated weights for policy 1, policy_version 25350 (0.0010) -[2023-10-12 04:11:34,426][78123] Updated weights for policy 1, policy_version 25360 (0.0009) -[2023-10-12 04:11:34,787][78123] Updated weights for policy 1, policy_version 25370 (0.0007) -[2023-10-12 04:11:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 52068352. Throughput: 0: 1598.9, 1: 1612.2. Samples: 13021472. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-12 04:11:35,202][77203] Avg episode reward: [(0, '38.720'), (1, '41.230')] -[2023-10-12 04:11:37,445][78091] Updated weights for policy 0, policy_version 25480 (0.0008) -[2023-10-12 04:11:37,820][78091] Updated weights for policy 0, policy_version 25490 (0.0008) -[2023-10-12 04:11:38,196][78091] Updated weights for policy 0, policy_version 25500 (0.0008) -[2023-10-12 04:11:39,009][78123] Updated weights for policy 1, policy_version 25380 (0.0010) -[2023-10-12 04:11:39,368][78123] Updated weights for policy 1, policy_version 25390 (0.0008) -[2023-10-12 04:11:39,741][78123] Updated weights for policy 1, policy_version 25400 (0.0008) -[2023-10-12 04:11:40,201][77203] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 52133888. Throughput: 0: 1599.7, 1: 1595.3. Samples: 13040084. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-12 04:11:40,201][77203] Avg episode reward: [(0, '37.300'), (1, '37.850')] -[2023-10-12 04:11:42,424][78091] Updated weights for policy 0, policy_version 25510 (0.0009) -[2023-10-12 04:11:42,786][78091] Updated weights for policy 0, policy_version 25520 (0.0008) -[2023-10-12 04:11:43,155][78091] Updated weights for policy 0, policy_version 25530 (0.0008) -[2023-10-12 04:11:43,973][78123] Updated weights for policy 1, policy_version 25410 (0.0009) -[2023-10-12 04:11:44,341][78123] Updated weights for policy 1, policy_version 25420 (0.0007) -[2023-10-12 04:11:44,709][78123] Updated weights for policy 1, policy_version 25430 (0.0007) -[2023-10-12 04:11:45,077][78123] Updated weights for policy 1, policy_version 25440 (0.0010) -[2023-10-12 04:11:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 52199424. Throughput: 0: 1611.9, 1: 1587.1. Samples: 13050090. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-12 04:11:45,202][77203] Avg episode reward: [(0, '36.890'), (1, '40.510')] -[2023-10-12 04:11:47,416][78091] Updated weights for policy 0, policy_version 25540 (0.0010) -[2023-10-12 04:11:47,789][78091] Updated weights for policy 0, policy_version 25550 (0.0008) -[2023-10-12 04:11:48,149][78091] Updated weights for policy 0, policy_version 25560 (0.0009) -[2023-10-12 04:11:49,305][78123] Updated weights for policy 1, policy_version 25450 (0.0007) -[2023-10-12 04:11:49,670][78123] Updated weights for policy 1, policy_version 25460 (0.0008) -[2023-10-12 04:11:50,038][78123] Updated weights for policy 1, policy_version 25470 (0.0009) -[2023-10-12 04:11:50,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 52264960. Throughput: 0: 1594.8, 1: 1614.1. Samples: 13069342. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-12 04:11:50,202][77203] Avg episode reward: [(0, '45.000'), (1, '47.140')] -[2023-10-12 04:11:50,202][77792] Saving new best policy, reward=45.000! -[2023-10-12 04:11:52,495][78091] Updated weights for policy 0, policy_version 25570 (0.0009) -[2023-10-12 04:11:52,860][78091] Updated weights for policy 0, policy_version 25580 (0.0009) -[2023-10-12 04:11:53,224][78091] Updated weights for policy 0, policy_version 25590 (0.0007) -[2023-10-12 04:11:53,601][78091] Updated weights for policy 0, policy_version 25600 (0.0007) -[2023-10-12 04:11:54,576][78123] Updated weights for policy 1, policy_version 25480 (0.0008) -[2023-10-12 04:11:54,960][78123] Updated weights for policy 1, policy_version 25490 (0.0007) -[2023-10-12 04:11:55,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 52297728. Throughput: 0: 1591.5, 1: 1603.8. Samples: 13088146. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-12 04:11:55,202][77203] Avg episode reward: [(0, '36.120'), (1, '36.720')] -[2023-10-12 04:11:55,331][78123] Updated weights for policy 1, policy_version 25500 (0.0007) -[2023-10-12 04:11:57,932][78091] Updated weights for policy 0, policy_version 25610 (0.0008) -[2023-10-12 04:11:58,316][78091] Updated weights for policy 0, policy_version 25620 (0.0009) -[2023-10-12 04:11:58,692][78091] Updated weights for policy 0, policy_version 25630 (0.0007) -[2023-10-12 04:11:59,400][78123] Updated weights for policy 1, policy_version 25510 (0.0010) -[2023-10-12 04:11:59,768][78123] Updated weights for policy 1, policy_version 25520 (0.0008) -[2023-10-12 04:12:00,133][78123] Updated weights for policy 1, policy_version 25530 (0.0008) -[2023-10-12 04:12:00,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.2, 300 sec: 12774.0). Total num frames: 52363264. Throughput: 0: 1616.8, 1: 1586.0. Samples: 13098012. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-12 04:12:00,201][77203] Avg episode reward: [(0, '38.510'), (1, '36.610')] -[2023-10-12 04:12:03,053][78091] Updated weights for policy 0, policy_version 25640 (0.0008) -[2023-10-12 04:12:03,429][78091] Updated weights for policy 0, policy_version 25650 (0.0008) -[2023-10-12 04:12:03,797][78091] Updated weights for policy 0, policy_version 25660 (0.0008) -[2023-10-12 04:12:04,593][78123] Updated weights for policy 1, policy_version 25540 (0.0009) -[2023-10-12 04:12:04,956][78123] Updated weights for policy 1, policy_version 25550 (0.0009) -[2023-10-12 04:12:05,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 52428800. Throughput: 0: 1599.3, 1: 1602.4. Samples: 13116920. Policy #0 lag: (min: 9.0, avg: 14.9, max: 41.0) -[2023-10-12 04:12:05,201][77203] Avg episode reward: [(0, '38.300'), (1, '37.960')] -[2023-10-12 04:12:05,328][78123] Updated weights for policy 1, policy_version 25560 (0.0009) -[2023-10-12 04:12:07,981][78091] Updated weights for policy 0, policy_version 25670 (0.0008) -[2023-10-12 04:12:08,345][78091] Updated weights for policy 0, policy_version 25680 (0.0007) -[2023-10-12 04:12:08,725][78091] Updated weights for policy 0, policy_version 25690 (0.0008) -[2023-10-12 04:12:09,891][78123] Updated weights for policy 1, policy_version 25570 (0.0009) -[2023-10-12 04:12:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 52494336. Throughput: 0: 1596.1, 1: 1609.9. Samples: 13136164. Policy #0 lag: (min: 9.0, avg: 14.9, max: 41.0) -[2023-10-12 04:12:10,201][77203] Avg episode reward: [(0, '35.030'), (1, '40.110')] -[2023-10-12 04:12:10,246][78123] Updated weights for policy 1, policy_version 25580 (0.0011) -[2023-10-12 04:12:10,615][78123] Updated weights for policy 1, policy_version 25590 (0.0011) -[2023-10-12 04:12:10,985][78123] Updated weights for policy 1, policy_version 25600 (0.0010) -[2023-10-12 04:12:13,158][78091] Updated weights for policy 0, policy_version 25700 (0.0008) -[2023-10-12 04:12:13,529][78091] Updated weights for policy 0, policy_version 25710 (0.0010) -[2023-10-12 04:12:13,902][78091] Updated weights for policy 0, policy_version 25720 (0.0010) -[2023-10-12 04:12:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 52559872. Throughput: 0: 1610.6, 1: 1584.0. Samples: 13145874. Policy #0 lag: (min: 9.0, avg: 14.9, max: 41.0) -[2023-10-12 04:12:15,201][77203] Avg episode reward: [(0, '40.410'), (1, '41.630')] -[2023-10-12 04:12:15,395][78123] Updated weights for policy 1, policy_version 25610 (0.0010) -[2023-10-12 04:12:15,767][78123] Updated weights for policy 1, policy_version 25620 (0.0008) -[2023-10-12 04:12:16,133][78123] Updated weights for policy 1, policy_version 25630 (0.0009) -[2023-10-12 04:12:18,242][78091] Updated weights for policy 0, policy_version 25730 (0.0009) -[2023-10-12 04:12:18,613][78091] Updated weights for policy 0, policy_version 25740 (0.0008) -[2023-10-12 04:12:18,987][78091] Updated weights for policy 0, policy_version 25750 (0.0009) -[2023-10-12 04:12:19,358][78091] Updated weights for policy 0, policy_version 25760 (0.0010) -[2023-10-12 04:12:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 52625408. Throughput: 0: 1597.0, 1: 1586.2. Samples: 13164716. Policy #0 lag: (min: 9.0, avg: 14.9, max: 41.0) -[2023-10-12 04:12:20,201][77203] Avg episode reward: [(0, '37.460'), (1, '39.390')] -[2023-10-12 04:12:20,325][78123] Updated weights for policy 1, policy_version 25640 (0.0009) -[2023-10-12 04:12:20,693][78123] Updated weights for policy 1, policy_version 25650 (0.0009) -[2023-10-12 04:12:21,052][78123] Updated weights for policy 1, policy_version 25660 (0.0009) -[2023-10-12 04:12:23,660][78091] Updated weights for policy 0, policy_version 25770 (0.0009) -[2023-10-12 04:12:24,022][78091] Updated weights for policy 0, policy_version 25780 (0.0007) -[2023-10-12 04:12:24,399][78091] Updated weights for policy 0, policy_version 25790 (0.0008) -[2023-10-12 04:12:25,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 52690944. Throughput: 0: 1584.8, 1: 1602.7. Samples: 13183522. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-10-12 04:12:25,202][77203] Avg episode reward: [(0, '37.330'), (1, '38.110')] -[2023-10-12 04:12:25,499][78123] Updated weights for policy 1, policy_version 25670 (0.0011) -[2023-10-12 04:12:25,873][78123] Updated weights for policy 1, policy_version 25680 (0.0008) -[2023-10-12 04:12:26,234][78123] Updated weights for policy 1, policy_version 25690 (0.0007) -[2023-10-12 04:12:28,661][78091] Updated weights for policy 0, policy_version 25800 (0.0007) -[2023-10-12 04:12:29,030][78091] Updated weights for policy 0, policy_version 25810 (0.0007) -[2023-10-12 04:12:29,387][78091] Updated weights for policy 0, policy_version 25820 (0.0011) -[2023-10-12 04:12:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 52756480. Throughput: 0: 1597.5, 1: 1581.7. Samples: 13193150. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-10-12 04:12:30,201][77203] Avg episode reward: [(0, '37.610'), (1, '41.850')] -[2023-10-12 04:12:30,574][78123] Updated weights for policy 1, policy_version 25700 (0.0008) -[2023-10-12 04:12:30,949][78123] Updated weights for policy 1, policy_version 25710 (0.0009) -[2023-10-12 04:12:31,311][78123] Updated weights for policy 1, policy_version 25720 (0.0009) -[2023-10-12 04:12:33,836][78091] Updated weights for policy 0, policy_version 25830 (0.0009) -[2023-10-12 04:12:34,210][78091] Updated weights for policy 0, policy_version 25840 (0.0010) -[2023-10-12 04:12:34,575][78091] Updated weights for policy 0, policy_version 25850 (0.0010) -[2023-10-12 04:12:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 52822016. Throughput: 0: 1607.8, 1: 1576.0. Samples: 13212612. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-10-12 04:12:35,202][77203] Avg episode reward: [(0, '37.530'), (1, '43.360')] -[2023-10-12 04:12:35,595][78123] Updated weights for policy 1, policy_version 25730 (0.0008) -[2023-10-12 04:12:35,967][78123] Updated weights for policy 1, policy_version 25740 (0.0007) -[2023-10-12 04:12:36,336][78123] Updated weights for policy 1, policy_version 25750 (0.0008) -[2023-10-12 04:12:36,705][78123] Updated weights for policy 1, policy_version 25760 (0.0008) -[2023-10-12 04:12:38,944][78091] Updated weights for policy 0, policy_version 25860 (0.0008) -[2023-10-12 04:12:39,311][78091] Updated weights for policy 0, policy_version 25870 (0.0009) -[2023-10-12 04:12:39,687][78091] Updated weights for policy 0, policy_version 25880 (0.0007) -[2023-10-12 04:12:40,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 52887552. Throughput: 0: 1589.7, 1: 1588.0. Samples: 13231146. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-10-12 04:12:40,202][77203] Avg episode reward: [(0, '36.800'), (1, '41.320')] -[2023-10-12 04:12:41,227][78123] Updated weights for policy 1, policy_version 25770 (0.0010) -[2023-10-12 04:12:41,601][78123] Updated weights for policy 1, policy_version 25780 (0.0007) -[2023-10-12 04:12:41,971][78123] Updated weights for policy 1, policy_version 25790 (0.0009) -[2023-10-12 04:12:44,055][78091] Updated weights for policy 0, policy_version 25890 (0.0011) -[2023-10-12 04:12:44,457][78091] Updated weights for policy 0, policy_version 25900 (0.0009) -[2023-10-12 04:12:44,835][78091] Updated weights for policy 0, policy_version 25910 (0.0009) -[2023-10-12 04:12:45,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 52920320. Throughput: 0: 1589.1, 1: 1576.6. Samples: 13240470. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-10-12 04:12:45,201][77203] Avg episode reward: [(0, '38.000'), (1, '41.680')] -[2023-10-12 04:12:45,209][78091] Updated weights for policy 0, policy_version 25920 (0.0008) -[2023-10-12 04:12:46,364][78123] Updated weights for policy 1, policy_version 25800 (0.0009) -[2023-10-12 04:12:46,732][78123] Updated weights for policy 1, policy_version 25810 (0.0008) -[2023-10-12 04:12:47,106][78123] Updated weights for policy 1, policy_version 25820 (0.0008) -[2023-10-12 04:12:49,471][78091] Updated weights for policy 0, policy_version 25930 (0.0008) -[2023-10-12 04:12:49,850][78091] Updated weights for policy 0, policy_version 25940 (0.0008) -[2023-10-12 04:12:50,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 52985856. Throughput: 0: 1601.8, 1: 1573.9. Samples: 13259826. Policy #0 lag: (min: 9.0, avg: 17.0, max: 41.0) -[2023-10-12 04:12:50,201][77203] Avg episode reward: [(0, '34.360'), (1, '42.830')] -[2023-10-12 04:12:50,216][78091] Updated weights for policy 0, policy_version 25950 (0.0009) -[2023-10-12 04:12:51,481][78123] Updated weights for policy 1, policy_version 25830 (0.0008) -[2023-10-12 04:12:51,840][78123] Updated weights for policy 1, policy_version 25840 (0.0010) -[2023-10-12 04:12:52,206][78123] Updated weights for policy 1, policy_version 25850 (0.0010) -[2023-10-12 04:12:54,438][78091] Updated weights for policy 0, policy_version 25960 (0.0007) -[2023-10-12 04:12:54,822][78091] Updated weights for policy 0, policy_version 25970 (0.0010) -[2023-10-12 04:12:55,193][78091] Updated weights for policy 0, policy_version 25980 (0.0012) -[2023-10-12 04:12:55,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 53051392. Throughput: 0: 1596.8, 1: 1576.7. Samples: 13278968. Policy #0 lag: (min: 9.0, avg: 17.0, max: 41.0) -[2023-10-12 04:12:55,202][77203] Avg episode reward: [(0, '36.450'), (1, '46.410')] -[2023-10-12 04:12:56,382][78123] Updated weights for policy 1, policy_version 25860 (0.0009) -[2023-10-12 04:12:56,747][78123] Updated weights for policy 1, policy_version 25870 (0.0009) -[2023-10-12 04:12:57,114][78123] Updated weights for policy 1, policy_version 25880 (0.0007) -[2023-10-12 04:12:59,488][78091] Updated weights for policy 0, policy_version 25990 (0.0009) -[2023-10-12 04:12:59,855][78091] Updated weights for policy 0, policy_version 26000 (0.0010) -[2023-10-12 04:13:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 53116928. Throughput: 0: 1589.9, 1: 1575.2. Samples: 13288302. Policy #0 lag: (min: 9.0, avg: 17.0, max: 41.0) -[2023-10-12 04:13:00,201][77203] Avg episode reward: [(0, '35.870'), (1, '37.000')] -[2023-10-12 04:13:00,232][78091] Updated weights for policy 0, policy_version 26010 (0.0009) -[2023-10-12 04:13:01,531][78123] Updated weights for policy 1, policy_version 25890 (0.0008) -[2023-10-12 04:13:01,897][78123] Updated weights for policy 1, policy_version 25900 (0.0007) -[2023-10-12 04:13:02,258][78123] Updated weights for policy 1, policy_version 25910 (0.0007) -[2023-10-12 04:13:02,624][78123] Updated weights for policy 1, policy_version 25920 (0.0011) -[2023-10-12 04:13:04,684][78091] Updated weights for policy 0, policy_version 26020 (0.0008) -[2023-10-12 04:13:05,051][78091] Updated weights for policy 0, policy_version 26030 (0.0011) -[2023-10-12 04:13:05,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 53182464. Throughput: 0: 1605.8, 1: 1572.6. Samples: 13307744. Policy #0 lag: (min: 9.0, avg: 17.0, max: 41.0) -[2023-10-12 04:13:05,201][77203] Avg episode reward: [(0, '39.940'), (1, '39.090')] -[2023-10-12 04:13:05,430][78091] Updated weights for policy 0, policy_version 26040 (0.0010) -[2023-10-12 04:13:06,925][78123] Updated weights for policy 1, policy_version 25930 (0.0008) -[2023-10-12 04:13:07,295][78123] Updated weights for policy 1, policy_version 25940 (0.0007) -[2023-10-12 04:13:07,661][78123] Updated weights for policy 1, policy_version 25950 (0.0007) -[2023-10-12 04:13:09,578][78091] Updated weights for policy 0, policy_version 26050 (0.0008) -[2023-10-12 04:13:09,950][78091] Updated weights for policy 0, policy_version 26060 (0.0007) -[2023-10-12 04:13:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 53248000. Throughput: 0: 1617.9, 1: 1577.3. Samples: 13327306. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:13:10,201][77203] Avg episode reward: [(0, '36.750'), (1, '42.890')] -[2023-10-12 04:13:10,208][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000025952_26574848.pth... -[2023-10-12 04:13:10,241][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000024480_25067520.pth -[2023-10-12 04:13:10,328][78091] Updated weights for policy 0, policy_version 26070 (0.0011) -[2023-10-12 04:13:10,695][78091] Updated weights for policy 0, policy_version 26080 (0.0009) -[2023-10-12 04:13:10,695][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000026080_26705920.pth... -[2023-10-12 04:13:10,737][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000024576_25165824.pth -[2023-10-12 04:13:11,963][78123] Updated weights for policy 1, policy_version 25960 (0.0009) -[2023-10-12 04:13:12,333][78123] Updated weights for policy 1, policy_version 25970 (0.0008) -[2023-10-12 04:13:12,699][78123] Updated weights for policy 1, policy_version 25980 (0.0009) -[2023-10-12 04:13:15,167][78091] Updated weights for policy 0, policy_version 26090 (0.0008) -[2023-10-12 04:13:15,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 53313536. Throughput: 0: 1598.1, 1: 1584.4. Samples: 13336366. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:13:15,201][77203] Avg episode reward: [(0, '38.870'), (1, '41.980')] -[2023-10-12 04:13:15,536][78091] Updated weights for policy 0, policy_version 26100 (0.0010) -[2023-10-12 04:13:15,917][78091] Updated weights for policy 0, policy_version 26110 (0.0008) -[2023-10-12 04:13:17,050][78123] Updated weights for policy 1, policy_version 25990 (0.0009) -[2023-10-12 04:13:17,426][78123] Updated weights for policy 1, policy_version 26000 (0.0007) -[2023-10-12 04:13:17,794][78123] Updated weights for policy 1, policy_version 26010 (0.0008) -[2023-10-12 04:13:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 53379072. Throughput: 0: 1597.7, 1: 1576.5. Samples: 13355452. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:13:20,206][77203] Avg episode reward: [(0, '41.780'), (1, '39.920')] -[2023-10-12 04:13:20,237][78091] Updated weights for policy 0, policy_version 26120 (0.0007) -[2023-10-12 04:13:20,598][78091] Updated weights for policy 0, policy_version 26130 (0.0007) -[2023-10-12 04:13:20,974][78091] Updated weights for policy 0, policy_version 26140 (0.0007) -[2023-10-12 04:13:22,005][78123] Updated weights for policy 1, policy_version 26020 (0.0007) -[2023-10-12 04:13:22,377][78123] Updated weights for policy 1, policy_version 26030 (0.0007) -[2023-10-12 04:13:22,747][78123] Updated weights for policy 1, policy_version 26040 (0.0008) -[2023-10-12 04:13:25,197][78091] Updated weights for policy 0, policy_version 26150 (0.0008) -[2023-10-12 04:13:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 53444608. Throughput: 0: 1617.4, 1: 1579.1. Samples: 13374988. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:13:25,201][77203] Avg episode reward: [(0, '39.590'), (1, '43.420')] -[2023-10-12 04:13:25,561][78091] Updated weights for policy 0, policy_version 26160 (0.0007) -[2023-10-12 04:13:25,926][78091] Updated weights for policy 0, policy_version 26170 (0.0008) -[2023-10-12 04:13:27,182][78123] Updated weights for policy 1, policy_version 26050 (0.0008) -[2023-10-12 04:13:27,577][78123] Updated weights for policy 1, policy_version 26060 (0.0008) -[2023-10-12 04:13:27,936][78123] Updated weights for policy 1, policy_version 26070 (0.0007) -[2023-10-12 04:13:28,316][78123] Updated weights for policy 1, policy_version 26080 (0.0010) -[2023-10-12 04:13:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 53510144. Throughput: 0: 1597.2, 1: 1594.4. Samples: 13384092. Policy #0 lag: (min: 31.0, avg: 33.0, max: 61.0) -[2023-10-12 04:13:30,201][77203] Avg episode reward: [(0, '39.250'), (1, '44.160')] -[2023-10-12 04:13:30,339][78091] Updated weights for policy 0, policy_version 26180 (0.0009) -[2023-10-12 04:13:30,733][78091] Updated weights for policy 0, policy_version 26190 (0.0009) -[2023-10-12 04:13:31,100][78091] Updated weights for policy 0, policy_version 26200 (0.0008) -[2023-10-12 04:13:32,571][78123] Updated weights for policy 1, policy_version 26090 (0.0008) -[2023-10-12 04:13:32,940][78123] Updated weights for policy 1, policy_version 26100 (0.0010) -[2023-10-12 04:13:33,303][78123] Updated weights for policy 1, policy_version 26110 (0.0008) -[2023-10-12 04:13:35,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 53575680. Throughput: 0: 1600.7, 1: 1582.7. Samples: 13403082. Policy #0 lag: (min: 31.0, avg: 33.0, max: 61.0) -[2023-10-12 04:13:35,202][77203] Avg episode reward: [(0, '39.550'), (1, '43.890')] -[2023-10-12 04:13:35,423][78091] Updated weights for policy 0, policy_version 26210 (0.0007) -[2023-10-12 04:13:35,794][78091] Updated weights for policy 0, policy_version 26220 (0.0007) -[2023-10-12 04:13:36,158][78091] Updated weights for policy 0, policy_version 26230 (0.0007) -[2023-10-12 04:13:36,534][78091] Updated weights for policy 0, policy_version 26240 (0.0009) -[2023-10-12 04:13:37,617][78123] Updated weights for policy 1, policy_version 26120 (0.0008) -[2023-10-12 04:13:37,990][78123] Updated weights for policy 1, policy_version 26130 (0.0008) -[2023-10-12 04:13:38,364][78123] Updated weights for policy 1, policy_version 26140 (0.0008) -[2023-10-12 04:13:40,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 53641216. Throughput: 0: 1607.1, 1: 1581.6. Samples: 13422460. Policy #0 lag: (min: 31.0, avg: 33.0, max: 61.0) -[2023-10-12 04:13:40,202][77203] Avg episode reward: [(0, '37.100'), (1, '40.730')] -[2023-10-12 04:13:40,712][78091] Updated weights for policy 0, policy_version 26250 (0.0007) -[2023-10-12 04:13:41,089][78091] Updated weights for policy 0, policy_version 26260 (0.0007) -[2023-10-12 04:13:41,466][78091] Updated weights for policy 0, policy_version 26270 (0.0008) -[2023-10-12 04:13:42,744][78123] Updated weights for policy 1, policy_version 26150 (0.0010) -[2023-10-12 04:13:43,110][78123] Updated weights for policy 1, policy_version 26160 (0.0008) -[2023-10-12 04:13:43,477][78123] Updated weights for policy 1, policy_version 26170 (0.0007) -[2023-10-12 04:13:45,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 53706752. Throughput: 0: 1587.5, 1: 1608.4. Samples: 13432118. Policy #0 lag: (min: 31.0, avg: 33.0, max: 61.0) -[2023-10-12 04:13:45,201][77203] Avg episode reward: [(0, '40.630'), (1, '41.730')] -[2023-10-12 04:13:45,587][78091] Updated weights for policy 0, policy_version 26280 (0.0007) -[2023-10-12 04:13:45,950][78091] Updated weights for policy 0, policy_version 26290 (0.0009) -[2023-10-12 04:13:46,331][78091] Updated weights for policy 0, policy_version 26300 (0.0007) -[2023-10-12 04:13:47,871][78123] Updated weights for policy 1, policy_version 26180 (0.0007) -[2023-10-12 04:13:48,229][78123] Updated weights for policy 1, policy_version 26190 (0.0007) -[2023-10-12 04:13:48,601][78123] Updated weights for policy 1, policy_version 26200 (0.0008) -[2023-10-12 04:13:50,201][77203] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 53772288. Throughput: 0: 1587.8, 1: 1593.5. Samples: 13450904. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:13:50,201][77203] Avg episode reward: [(0, '40.800'), (1, '40.380')] -[2023-10-12 04:13:50,642][78091] Updated weights for policy 0, policy_version 26310 (0.0007) -[2023-10-12 04:13:51,004][78091] Updated weights for policy 0, policy_version 26320 (0.0008) -[2023-10-12 04:13:51,377][78091] Updated weights for policy 0, policy_version 26330 (0.0009) -[2023-10-12 04:13:53,042][78123] Updated weights for policy 1, policy_version 26210 (0.0009) -[2023-10-12 04:13:53,406][78123] Updated weights for policy 1, policy_version 26220 (0.0008) -[2023-10-12 04:13:53,779][78123] Updated weights for policy 1, policy_version 26230 (0.0008) -[2023-10-12 04:13:54,143][78123] Updated weights for policy 1, policy_version 26240 (0.0009) -[2023-10-12 04:13:55,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 53837824. Throughput: 0: 1588.3, 1: 1587.6. Samples: 13470224. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:13:55,202][77203] Avg episode reward: [(0, '37.200'), (1, '43.500')] -[2023-10-12 04:13:55,799][78091] Updated weights for policy 0, policy_version 26340 (0.0007) -[2023-10-12 04:13:56,179][78091] Updated weights for policy 0, policy_version 26350 (0.0007) -[2023-10-12 04:13:56,547][78091] Updated weights for policy 0, policy_version 26360 (0.0008) -[2023-10-12 04:13:58,521][78123] Updated weights for policy 1, policy_version 26250 (0.0007) -[2023-10-12 04:13:58,889][78123] Updated weights for policy 1, policy_version 26260 (0.0010) -[2023-10-12 04:13:59,256][78123] Updated weights for policy 1, policy_version 26270 (0.0008) -[2023-10-12 04:14:00,201][77203] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 53903360. Throughput: 0: 1582.2, 1: 1606.8. Samples: 13479872. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:14:00,202][77203] Avg episode reward: [(0, '40.250'), (1, '43.500')] -[2023-10-12 04:14:00,914][78091] Updated weights for policy 0, policy_version 26370 (0.0009) -[2023-10-12 04:14:01,281][78091] Updated weights for policy 0, policy_version 26380 (0.0007) -[2023-10-12 04:14:01,658][78091] Updated weights for policy 0, policy_version 26390 (0.0007) -[2023-10-12 04:14:02,026][78091] Updated weights for policy 0, policy_version 26400 (0.0007) -[2023-10-12 04:14:03,569][78123] Updated weights for policy 1, policy_version 26280 (0.0008) -[2023-10-12 04:14:03,927][78123] Updated weights for policy 1, policy_version 26290 (0.0009) -[2023-10-12 04:14:04,292][78123] Updated weights for policy 1, policy_version 26300 (0.0009) -[2023-10-12 04:14:05,201][77203] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 53968896. Throughput: 0: 1587.6, 1: 1605.5. Samples: 13499142. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:14:05,201][77203] Avg episode reward: [(0, '37.830'), (1, '39.870')] -[2023-10-12 04:14:06,052][78091] Updated weights for policy 0, policy_version 26410 (0.0010) -[2023-10-12 04:14:06,416][78091] Updated weights for policy 0, policy_version 26420 (0.0010) -[2023-10-12 04:14:06,788][78091] Updated weights for policy 0, policy_version 26430 (0.0008) -[2023-10-12 04:14:08,630][78123] Updated weights for policy 1, policy_version 26310 (0.0009) -[2023-10-12 04:14:08,998][78123] Updated weights for policy 1, policy_version 26320 (0.0008) -[2023-10-12 04:14:09,370][78123] Updated weights for policy 1, policy_version 26330 (0.0009) -[2023-10-12 04:14:10,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 54034432. Throughput: 0: 1591.9, 1: 1586.6. Samples: 13518022. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-12 04:14:10,202][77203] Avg episode reward: [(0, '35.580'), (1, '39.680')] -[2023-10-12 04:14:11,358][78091] Updated weights for policy 0, policy_version 26440 (0.0010) -[2023-10-12 04:14:11,736][78091] Updated weights for policy 0, policy_version 26450 (0.0008) -[2023-10-12 04:14:12,114][78091] Updated weights for policy 0, policy_version 26460 (0.0007) -[2023-10-12 04:14:13,905][78123] Updated weights for policy 1, policy_version 26340 (0.0009) -[2023-10-12 04:14:14,285][78123] Updated weights for policy 1, policy_version 26350 (0.0009) -[2023-10-12 04:14:14,647][78123] Updated weights for policy 1, policy_version 26360 (0.0008) -[2023-10-12 04:14:15,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 54099968. Throughput: 0: 1589.7, 1: 1599.5. Samples: 13527606. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-12 04:14:15,202][77203] Avg episode reward: [(0, '38.360'), (1, '42.420')] -[2023-10-12 04:14:16,303][78091] Updated weights for policy 0, policy_version 26470 (0.0009) -[2023-10-12 04:14:16,672][78091] Updated weights for policy 0, policy_version 26480 (0.0007) -[2023-10-12 04:14:17,039][78091] Updated weights for policy 0, policy_version 26490 (0.0009) -[2023-10-12 04:14:19,035][78123] Updated weights for policy 1, policy_version 26370 (0.0008) -[2023-10-12 04:14:19,401][78123] Updated weights for policy 1, policy_version 26380 (0.0008) -[2023-10-12 04:14:19,775][78123] Updated weights for policy 1, policy_version 26390 (0.0008) -[2023-10-12 04:14:20,142][78123] Updated weights for policy 1, policy_version 26400 (0.0009) -[2023-10-12 04:14:20,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 54165504. Throughput: 0: 1595.3, 1: 1605.3. Samples: 13547108. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-12 04:14:20,202][77203] Avg episode reward: [(0, '36.760'), (1, '40.840')] -[2023-10-12 04:14:21,384][78091] Updated weights for policy 0, policy_version 26500 (0.0008) -[2023-10-12 04:14:21,779][78091] Updated weights for policy 0, policy_version 26510 (0.0007) -[2023-10-12 04:14:22,151][78091] Updated weights for policy 0, policy_version 26520 (0.0007) -[2023-10-12 04:14:24,366][78123] Updated weights for policy 1, policy_version 26410 (0.0009) -[2023-10-12 04:14:24,733][78123] Updated weights for policy 1, policy_version 26420 (0.0009) -[2023-10-12 04:14:25,101][78123] Updated weights for policy 1, policy_version 26430 (0.0007) -[2023-10-12 04:14:25,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 54231040. Throughput: 0: 1596.5, 1: 1595.5. Samples: 13566098. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-12 04:14:25,201][77203] Avg episode reward: [(0, '38.190'), (1, '38.140')] -[2023-10-12 04:14:26,232][78091] Updated weights for policy 0, policy_version 26530 (0.0009) -[2023-10-12 04:14:26,600][78091] Updated weights for policy 0, policy_version 26540 (0.0009) -[2023-10-12 04:14:26,961][78091] Updated weights for policy 0, policy_version 26550 (0.0010) -[2023-10-12 04:14:27,335][78091] Updated weights for policy 0, policy_version 26560 (0.0008) -[2023-10-12 04:14:29,427][78123] Updated weights for policy 1, policy_version 26440 (0.0009) -[2023-10-12 04:14:29,800][78123] Updated weights for policy 1, policy_version 26450 (0.0010) -[2023-10-12 04:14:30,168][78123] Updated weights for policy 1, policy_version 26460 (0.0010) -[2023-10-12 04:14:30,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 54263808. Throughput: 0: 1598.4, 1: 1585.4. Samples: 13575388. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:14:30,201][77203] Avg episode reward: [(0, '38.310'), (1, '41.890')] -[2023-10-12 04:14:31,730][78091] Updated weights for policy 0, policy_version 26570 (0.0008) -[2023-10-12 04:14:32,111][78091] Updated weights for policy 0, policy_version 26580 (0.0008) -[2023-10-12 04:14:32,487][78091] Updated weights for policy 0, policy_version 26590 (0.0009) -[2023-10-12 04:14:34,533][78123] Updated weights for policy 1, policy_version 26470 (0.0008) -[2023-10-12 04:14:34,894][78123] Updated weights for policy 1, policy_version 26480 (0.0008) -[2023-10-12 04:14:35,201][77203] Fps is (10 sec: 9830.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 54329344. Throughput: 0: 1604.2, 1: 1601.1. Samples: 13595144. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:14:35,202][77203] Avg episode reward: [(0, '36.790'), (1, '39.320')] -[2023-10-12 04:14:35,267][78123] Updated weights for policy 1, policy_version 26490 (0.0008) -[2023-10-12 04:14:36,753][78091] Updated weights for policy 0, policy_version 26600 (0.0009) -[2023-10-12 04:14:37,121][78091] Updated weights for policy 0, policy_version 26610 (0.0009) -[2023-10-12 04:14:37,484][78091] Updated weights for policy 0, policy_version 26620 (0.0009) -[2023-10-12 04:14:39,482][78123] Updated weights for policy 1, policy_version 26500 (0.0007) -[2023-10-12 04:14:39,846][78123] Updated weights for policy 1, policy_version 26510 (0.0008) -[2023-10-12 04:14:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 54394880. Throughput: 0: 1610.9, 1: 1598.8. Samples: 13614662. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:14:40,201][77203] Avg episode reward: [(0, '37.820'), (1, '38.950')] -[2023-10-12 04:14:40,206][78123] Updated weights for policy 1, policy_version 26520 (0.0008) -[2023-10-12 04:14:41,559][78091] Updated weights for policy 0, policy_version 26630 (0.0008) -[2023-10-12 04:14:41,932][78091] Updated weights for policy 0, policy_version 26640 (0.0007) -[2023-10-12 04:14:42,300][78091] Updated weights for policy 0, policy_version 26650 (0.0010) -[2023-10-12 04:14:44,585][78123] Updated weights for policy 1, policy_version 26530 (0.0008) -[2023-10-12 04:14:44,954][78123] Updated weights for policy 1, policy_version 26540 (0.0007) -[2023-10-12 04:14:45,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 54460416. Throughput: 0: 1611.1, 1: 1587.2. Samples: 13623792. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:14:45,201][77203] Avg episode reward: [(0, '37.930'), (1, '39.490')] -[2023-10-12 04:14:45,318][78123] Updated weights for policy 1, policy_version 26550 (0.0008) -[2023-10-12 04:14:45,689][78123] Updated weights for policy 1, policy_version 26560 (0.0009) -[2023-10-12 04:14:46,729][78091] Updated weights for policy 0, policy_version 26660 (0.0009) -[2023-10-12 04:14:47,104][78091] Updated weights for policy 0, policy_version 26670 (0.0010) -[2023-10-12 04:14:47,470][78091] Updated weights for policy 0, policy_version 26680 (0.0008) -[2023-10-12 04:14:50,058][78123] Updated weights for policy 1, policy_version 26570 (0.0009) -[2023-10-12 04:14:50,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 54525952. Throughput: 0: 1610.3, 1: 1594.1. Samples: 13643340. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-12 04:14:50,202][77203] Avg episode reward: [(0, '38.890'), (1, '38.480')] -[2023-10-12 04:14:50,423][78123] Updated weights for policy 1, policy_version 26580 (0.0008) -[2023-10-12 04:14:50,783][78123] Updated weights for policy 1, policy_version 26590 (0.0008) -[2023-10-12 04:14:51,774][78091] Updated weights for policy 0, policy_version 26690 (0.0010) -[2023-10-12 04:14:52,143][78091] Updated weights for policy 0, policy_version 26700 (0.0007) -[2023-10-12 04:14:52,523][78091] Updated weights for policy 0, policy_version 26710 (0.0008) -[2023-10-12 04:14:52,881][78091] Updated weights for policy 0, policy_version 26720 (0.0007) -[2023-10-12 04:14:54,998][78123] Updated weights for policy 1, policy_version 26600 (0.0008) -[2023-10-12 04:14:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 54591488. Throughput: 0: 1605.7, 1: 1609.7. Samples: 13662714. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-12 04:14:55,201][77203] Avg episode reward: [(0, '34.770'), (1, '43.560')] -[2023-10-12 04:14:55,369][78123] Updated weights for policy 1, policy_version 26610 (0.0007) -[2023-10-12 04:14:55,746][78123] Updated weights for policy 1, policy_version 26620 (0.0008) -[2023-10-12 04:14:57,265][78091] Updated weights for policy 0, policy_version 26730 (0.0007) -[2023-10-12 04:14:57,641][78091] Updated weights for policy 0, policy_version 26740 (0.0009) -[2023-10-12 04:14:58,023][78091] Updated weights for policy 0, policy_version 26750 (0.0007) -[2023-10-12 04:15:00,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 54657024. Throughput: 0: 1617.1, 1: 1586.6. Samples: 13671772. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-12 04:15:00,201][77203] Avg episode reward: [(0, '36.940'), (1, '43.870')] -[2023-10-12 04:15:00,213][78123] Updated weights for policy 1, policy_version 26630 (0.0009) -[2023-10-12 04:15:00,586][78123] Updated weights for policy 1, policy_version 26640 (0.0010) -[2023-10-12 04:15:00,962][78123] Updated weights for policy 1, policy_version 26650 (0.0008) -[2023-10-12 04:15:02,416][78091] Updated weights for policy 0, policy_version 26760 (0.0010) -[2023-10-12 04:15:02,789][78091] Updated weights for policy 0, policy_version 26770 (0.0009) -[2023-10-12 04:15:03,168][78091] Updated weights for policy 0, policy_version 26780 (0.0008) -[2023-10-12 04:15:05,057][78123] Updated weights for policy 1, policy_version 26660 (0.0008) -[2023-10-12 04:15:05,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 54722560. Throughput: 0: 1600.5, 1: 1590.8. Samples: 13690718. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-12 04:15:05,202][77203] Avg episode reward: [(0, '40.110'), (1, '42.330')] -[2023-10-12 04:15:05,418][78123] Updated weights for policy 1, policy_version 26670 (0.0009) -[2023-10-12 04:15:05,787][78123] Updated weights for policy 1, policy_version 26680 (0.0009) -[2023-10-12 04:15:07,548][78091] Updated weights for policy 0, policy_version 26790 (0.0007) -[2023-10-12 04:15:07,922][78091] Updated weights for policy 0, policy_version 26800 (0.0007) -[2023-10-12 04:15:08,301][78091] Updated weights for policy 0, policy_version 26810 (0.0008) -[2023-10-12 04:15:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 54788096. Throughput: 0: 1600.5, 1: 1602.8. Samples: 13710246. Policy #0 lag: (min: 23.0, avg: 25.4, max: 55.0) -[2023-10-12 04:15:10,201][77203] Avg episode reward: [(0, '34.750'), (1, '42.200')] -[2023-10-12 04:15:10,208][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000026816_27459584.pth... -[2023-10-12 04:15:10,241][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000025312_25919488.pth -[2023-10-12 04:15:10,253][78123] Updated weights for policy 1, policy_version 26690 (0.0009) -[2023-10-12 04:15:10,629][78123] Updated weights for policy 1, policy_version 26700 (0.0008) -[2023-10-12 04:15:10,993][78123] Updated weights for policy 1, policy_version 26710 (0.0008) -[2023-10-12 04:15:11,367][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000026720_27361280.pth... -[2023-10-12 04:15:11,370][78123] Updated weights for policy 1, policy_version 26720 (0.0009) -[2023-10-12 04:15:11,407][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000025216_25821184.pth -[2023-10-12 04:15:12,302][78091] Updated weights for policy 0, policy_version 26820 (0.0007) -[2023-10-12 04:15:12,664][78091] Updated weights for policy 0, policy_version 26830 (0.0010) -[2023-10-12 04:15:13,046][78091] Updated weights for policy 0, policy_version 26840 (0.0008) -[2023-10-12 04:15:15,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 54853632. Throughput: 0: 1615.1, 1: 1589.2. Samples: 13719578. Policy #0 lag: (min: 23.0, avg: 25.4, max: 55.0) -[2023-10-12 04:15:15,202][77203] Avg episode reward: [(0, '41.920'), (1, '43.300')] -[2023-10-12 04:15:15,624][78123] Updated weights for policy 1, policy_version 26730 (0.0007) -[2023-10-12 04:15:15,992][78123] Updated weights for policy 1, policy_version 26740 (0.0007) -[2023-10-12 04:15:16,355][78123] Updated weights for policy 1, policy_version 26750 (0.0007) -[2023-10-12 04:15:17,502][78091] Updated weights for policy 0, policy_version 26850 (0.0009) -[2023-10-12 04:15:17,876][78091] Updated weights for policy 0, policy_version 26860 (0.0008) -[2023-10-12 04:15:18,249][78091] Updated weights for policy 0, policy_version 26870 (0.0009) -[2023-10-12 04:15:18,627][78091] Updated weights for policy 0, policy_version 26880 (0.0009) -[2023-10-12 04:15:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 54919168. Throughput: 0: 1594.1, 1: 1591.6. Samples: 13738502. Policy #0 lag: (min: 23.0, avg: 25.4, max: 55.0) -[2023-10-12 04:15:20,201][77203] Avg episode reward: [(0, '33.510'), (1, '41.350')] -[2023-10-12 04:15:20,511][78123] Updated weights for policy 1, policy_version 26760 (0.0008) -[2023-10-12 04:15:20,884][78123] Updated weights for policy 1, policy_version 26770 (0.0010) -[2023-10-12 04:15:21,250][78123] Updated weights for policy 1, policy_version 26780 (0.0009) -[2023-10-12 04:15:23,020][78091] Updated weights for policy 0, policy_version 26890 (0.0011) -[2023-10-12 04:15:23,399][78091] Updated weights for policy 0, policy_version 26900 (0.0009) -[2023-10-12 04:15:23,777][78091] Updated weights for policy 0, policy_version 26910 (0.0009) -[2023-10-12 04:15:25,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 54984704. Throughput: 0: 1588.2, 1: 1598.9. Samples: 13758082. Policy #0 lag: (min: 23.0, avg: 25.4, max: 55.0) -[2023-10-12 04:15:25,202][77203] Avg episode reward: [(0, '34.580'), (1, '34.270')] -[2023-10-12 04:15:25,554][78123] Updated weights for policy 1, policy_version 26790 (0.0009) -[2023-10-12 04:15:25,916][78123] Updated weights for policy 1, policy_version 26800 (0.0009) -[2023-10-12 04:15:26,281][78123] Updated weights for policy 1, policy_version 26810 (0.0007) -[2023-10-12 04:15:28,115][78091] Updated weights for policy 0, policy_version 26920 (0.0008) -[2023-10-12 04:15:28,485][78091] Updated weights for policy 0, policy_version 26930 (0.0008) -[2023-10-12 04:15:28,867][78091] Updated weights for policy 0, policy_version 26940 (0.0008) -[2023-10-12 04:15:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 55050240. Throughput: 0: 1613.0, 1: 1584.3. Samples: 13767670. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-12 04:15:30,201][77203] Avg episode reward: [(0, '39.560'), (1, '40.310')] -[2023-10-12 04:15:30,845][78123] Updated weights for policy 1, policy_version 26820 (0.0007) -[2023-10-12 04:15:31,213][78123] Updated weights for policy 1, policy_version 26830 (0.0008) -[2023-10-12 04:15:31,573][78123] Updated weights for policy 1, policy_version 26840 (0.0008) -[2023-10-12 04:15:33,264][78091] Updated weights for policy 0, policy_version 26950 (0.0009) -[2023-10-12 04:15:33,649][78091] Updated weights for policy 0, policy_version 26960 (0.0009) -[2023-10-12 04:15:34,021][78091] Updated weights for policy 0, policy_version 26970 (0.0009) -[2023-10-12 04:15:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 55115776. Throughput: 0: 1594.4, 1: 1583.7. Samples: 13786352. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-12 04:15:35,202][77203] Avg episode reward: [(0, '33.950'), (1, '40.520')] -[2023-10-12 04:15:35,770][78123] Updated weights for policy 1, policy_version 26850 (0.0007) -[2023-10-12 04:15:36,142][78123] Updated weights for policy 1, policy_version 26860 (0.0009) -[2023-10-12 04:15:36,510][78123] Updated weights for policy 1, policy_version 26870 (0.0009) -[2023-10-12 04:15:36,876][78123] Updated weights for policy 1, policy_version 26880 (0.0009) -[2023-10-12 04:15:38,184][78091] Updated weights for policy 0, policy_version 26980 (0.0009) -[2023-10-12 04:15:38,551][78091] Updated weights for policy 0, policy_version 26990 (0.0008) -[2023-10-12 04:15:38,921][78091] Updated weights for policy 0, policy_version 27000 (0.0008) -[2023-10-12 04:15:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 55181312. Throughput: 0: 1583.5, 1: 1587.8. Samples: 13805422. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-12 04:15:40,202][77203] Avg episode reward: [(0, '36.520'), (1, '37.890')] -[2023-10-12 04:15:41,181][78123] Updated weights for policy 1, policy_version 26890 (0.0007) -[2023-10-12 04:15:41,545][78123] Updated weights for policy 1, policy_version 26900 (0.0009) -[2023-10-12 04:15:41,913][78123] Updated weights for policy 1, policy_version 26910 (0.0009) -[2023-10-12 04:15:43,045][78091] Updated weights for policy 0, policy_version 27010 (0.0010) -[2023-10-12 04:15:43,421][78091] Updated weights for policy 0, policy_version 27020 (0.0010) -[2023-10-12 04:15:43,789][78091] Updated weights for policy 0, policy_version 27030 (0.0008) -[2023-10-12 04:15:44,164][78091] Updated weights for policy 0, policy_version 27040 (0.0007) -[2023-10-12 04:15:45,201][77203] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 55246848. Throughput: 0: 1604.8, 1: 1584.7. Samples: 13815300. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-12 04:15:45,201][77203] Avg episode reward: [(0, '36.190'), (1, '38.420')] -[2023-10-12 04:15:46,223][78123] Updated weights for policy 1, policy_version 26920 (0.0009) -[2023-10-12 04:15:46,589][78123] Updated weights for policy 1, policy_version 26930 (0.0009) -[2023-10-12 04:15:46,961][78123] Updated weights for policy 1, policy_version 26940 (0.0010) -[2023-10-12 04:15:48,542][78091] Updated weights for policy 0, policy_version 27050 (0.0007) -[2023-10-12 04:15:48,918][78091] Updated weights for policy 0, policy_version 27060 (0.0009) -[2023-10-12 04:15:49,280][78091] Updated weights for policy 0, policy_version 27070 (0.0009) -[2023-10-12 04:15:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 55312384. Throughput: 0: 1601.9, 1: 1589.1. Samples: 13834314. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-12 04:15:50,202][77203] Avg episode reward: [(0, '35.780'), (1, '42.590')] -[2023-10-12 04:15:51,459][78123] Updated weights for policy 1, policy_version 26950 (0.0009) -[2023-10-12 04:15:51,834][78123] Updated weights for policy 1, policy_version 26960 (0.0009) -[2023-10-12 04:15:52,208][78123] Updated weights for policy 1, policy_version 26970 (0.0007) -[2023-10-12 04:15:53,762][78091] Updated weights for policy 0, policy_version 27080 (0.0008) -[2023-10-12 04:15:54,143][78091] Updated weights for policy 0, policy_version 27090 (0.0010) -[2023-10-12 04:15:54,522][78091] Updated weights for policy 0, policy_version 27100 (0.0007) -[2023-10-12 04:15:55,201][77203] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 55377920. Throughput: 0: 1583.0, 1: 1587.1. Samples: 13852902. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-12 04:15:55,202][77203] Avg episode reward: [(0, '36.750'), (1, '45.170')] -[2023-10-12 04:15:56,407][78123] Updated weights for policy 1, policy_version 26980 (0.0008) -[2023-10-12 04:15:56,763][78123] Updated weights for policy 1, policy_version 26990 (0.0010) -[2023-10-12 04:15:57,131][78123] Updated weights for policy 1, policy_version 27000 (0.0009) -[2023-10-12 04:15:58,701][78091] Updated weights for policy 0, policy_version 27110 (0.0008) -[2023-10-12 04:15:59,068][78091] Updated weights for policy 0, policy_version 27120 (0.0008) -[2023-10-12 04:15:59,450][78091] Updated weights for policy 0, policy_version 27130 (0.0008) -[2023-10-12 04:16:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 55443456. Throughput: 0: 1599.9, 1: 1585.3. Samples: 13862912. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-12 04:16:00,202][77203] Avg episode reward: [(0, '35.760'), (1, '34.410')] -[2023-10-12 04:16:01,566][78123] Updated weights for policy 1, policy_version 27010 (0.0008) -[2023-10-12 04:16:01,936][78123] Updated weights for policy 1, policy_version 27020 (0.0007) -[2023-10-12 04:16:02,305][78123] Updated weights for policy 1, policy_version 27030 (0.0009) -[2023-10-12 04:16:02,685][78123] Updated weights for policy 1, policy_version 27040 (0.0009) -[2023-10-12 04:16:03,687][78091] Updated weights for policy 0, policy_version 27140 (0.0010) -[2023-10-12 04:16:04,054][78091] Updated weights for policy 0, policy_version 27150 (0.0010) -[2023-10-12 04:16:04,423][78091] Updated weights for policy 0, policy_version 27160 (0.0010) -[2023-10-12 04:16:05,201][77203] Fps is (10 sec: 13107.6, 60 sec: 13107.3, 300 sec: 12774.0). Total num frames: 55508992. Throughput: 0: 1610.5, 1: 1584.0. Samples: 13882258. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-12 04:16:05,201][77203] Avg episode reward: [(0, '41.360'), (1, '34.840')] -[2023-10-12 04:16:06,859][78123] Updated weights for policy 1, policy_version 27050 (0.0007) -[2023-10-12 04:16:07,227][78123] Updated weights for policy 1, policy_version 27060 (0.0009) -[2023-10-12 04:16:07,588][78123] Updated weights for policy 1, policy_version 27070 (0.0008) -[2023-10-12 04:16:08,829][78091] Updated weights for policy 0, policy_version 27170 (0.0011) -[2023-10-12 04:16:09,203][78091] Updated weights for policy 0, policy_version 27180 (0.0010) -[2023-10-12 04:16:09,572][78091] Updated weights for policy 0, policy_version 27190 (0.0009) -[2023-10-12 04:16:09,938][78091] Updated weights for policy 0, policy_version 27200 (0.0008) -[2023-10-12 04:16:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 55574528. Throughput: 0: 1594.3, 1: 1588.4. Samples: 13901300. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) -[2023-10-12 04:16:10,202][77203] Avg episode reward: [(0, '34.480'), (1, '41.190')] -[2023-10-12 04:16:11,810][78123] Updated weights for policy 1, policy_version 27080 (0.0010) -[2023-10-12 04:16:12,182][78123] Updated weights for policy 1, policy_version 27090 (0.0008) -[2023-10-12 04:16:12,552][78123] Updated weights for policy 1, policy_version 27100 (0.0007) -[2023-10-12 04:16:14,249][78091] Updated weights for policy 0, policy_version 27210 (0.0008) -[2023-10-12 04:16:14,612][78091] Updated weights for policy 0, policy_version 27220 (0.0007) -[2023-10-12 04:16:14,987][78091] Updated weights for policy 0, policy_version 27230 (0.0007) -[2023-10-12 04:16:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 55640064. Throughput: 0: 1592.0, 1: 1591.8. Samples: 13910940. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) -[2023-10-12 04:16:15,201][77203] Avg episode reward: [(0, '39.990'), (1, '41.140')] -[2023-10-12 04:16:16,995][78123] Updated weights for policy 1, policy_version 27110 (0.0010) -[2023-10-12 04:16:17,353][78123] Updated weights for policy 1, policy_version 27120 (0.0011) -[2023-10-12 04:16:17,717][78123] Updated weights for policy 1, policy_version 27130 (0.0007) -[2023-10-12 04:16:19,318][78091] Updated weights for policy 0, policy_version 27240 (0.0008) -[2023-10-12 04:16:19,695][78091] Updated weights for policy 0, policy_version 27250 (0.0009) -[2023-10-12 04:16:20,062][78091] Updated weights for policy 0, policy_version 27260 (0.0008) -[2023-10-12 04:16:20,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 55672832. Throughput: 0: 1611.5, 1: 1589.4. Samples: 13930390. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) -[2023-10-12 04:16:20,201][77203] Avg episode reward: [(0, '31.920'), (1, '38.830')] -[2023-10-12 04:16:22,054][78123] Updated weights for policy 1, policy_version 27140 (0.0007) -[2023-10-12 04:16:22,427][78123] Updated weights for policy 1, policy_version 27150 (0.0007) -[2023-10-12 04:16:22,804][78123] Updated weights for policy 1, policy_version 27160 (0.0008) -[2023-10-12 04:16:24,419][78091] Updated weights for policy 0, policy_version 27270 (0.0010) -[2023-10-12 04:16:24,795][78091] Updated weights for policy 0, policy_version 27280 (0.0010) -[2023-10-12 04:16:25,162][78091] Updated weights for policy 0, policy_version 27290 (0.0008) -[2023-10-12 04:16:25,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 55738368. Throughput: 0: 1611.4, 1: 1592.2. Samples: 13949584. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) -[2023-10-12 04:16:25,202][77203] Avg episode reward: [(0, '35.790'), (1, '38.870')] -[2023-10-12 04:16:27,054][78123] Updated weights for policy 1, policy_version 27170 (0.0008) -[2023-10-12 04:16:27,417][78123] Updated weights for policy 1, policy_version 27180 (0.0007) -[2023-10-12 04:16:27,779][78123] Updated weights for policy 1, policy_version 27190 (0.0010) -[2023-10-12 04:16:28,151][78123] Updated weights for policy 1, policy_version 27200 (0.0010) -[2023-10-12 04:16:29,493][78091] Updated weights for policy 0, policy_version 27300 (0.0009) -[2023-10-12 04:16:29,855][78091] Updated weights for policy 0, policy_version 27310 (0.0008) -[2023-10-12 04:16:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 55803904. Throughput: 0: 1596.6, 1: 1605.6. Samples: 13959402. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) -[2023-10-12 04:16:30,201][77203] Avg episode reward: [(0, '38.660'), (1, '36.500')] -[2023-10-12 04:16:30,232][78091] Updated weights for policy 0, policy_version 27320 (0.0010) -[2023-10-12 04:16:32,407][78123] Updated weights for policy 1, policy_version 27210 (0.0009) -[2023-10-12 04:16:32,771][78123] Updated weights for policy 1, policy_version 27220 (0.0009) -[2023-10-12 04:16:33,147][78123] Updated weights for policy 1, policy_version 27230 (0.0010) -[2023-10-12 04:16:34,422][78091] Updated weights for policy 0, policy_version 27330 (0.0009) -[2023-10-12 04:16:34,796][78091] Updated weights for policy 0, policy_version 27340 (0.0007) -[2023-10-12 04:16:35,168][78091] Updated weights for policy 0, policy_version 27350 (0.0007) -[2023-10-12 04:16:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 55869440. Throughput: 0: 1608.4, 1: 1596.4. Samples: 13978532. Policy #0 lag: (min: 31.0, avg: 33.1, max: 60.0) -[2023-10-12 04:16:35,202][77203] Avg episode reward: [(0, '33.480'), (1, '41.660')] -[2023-10-12 04:16:35,546][78091] Updated weights for policy 0, policy_version 27360 (0.0008) -[2023-10-12 04:16:37,713][78123] Updated weights for policy 1, policy_version 27240 (0.0009) -[2023-10-12 04:16:38,095][78123] Updated weights for policy 1, policy_version 27250 (0.0008) -[2023-10-12 04:16:38,468][78123] Updated weights for policy 1, policy_version 27260 (0.0009) -[2023-10-12 04:16:40,007][78091] Updated weights for policy 0, policy_version 27370 (0.0010) -[2023-10-12 04:16:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 55934976. Throughput: 0: 1621.3, 1: 1592.5. Samples: 13997522. Policy #0 lag: (min: 31.0, avg: 33.1, max: 60.0) -[2023-10-12 04:16:40,202][77203] Avg episode reward: [(0, '37.620'), (1, '43.180')] -[2023-10-12 04:16:40,383][78091] Updated weights for policy 0, policy_version 27380 (0.0010) -[2023-10-12 04:16:40,753][78091] Updated weights for policy 0, policy_version 27390 (0.0008) -[2023-10-12 04:16:42,850][78123] Updated weights for policy 1, policy_version 27270 (0.0009) -[2023-10-12 04:16:43,221][78123] Updated weights for policy 1, policy_version 27280 (0.0007) -[2023-10-12 04:16:43,581][78123] Updated weights for policy 1, policy_version 27290 (0.0007) -[2023-10-12 04:16:44,942][78091] Updated weights for policy 0, policy_version 27400 (0.0009) -[2023-10-12 04:16:45,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 56000512. Throughput: 0: 1594.9, 1: 1616.3. Samples: 14007414. Policy #0 lag: (min: 31.0, avg: 33.1, max: 60.0) -[2023-10-12 04:16:45,201][77203] Avg episode reward: [(0, '36.450'), (1, '39.890')] -[2023-10-12 04:16:45,318][78091] Updated weights for policy 0, policy_version 27410 (0.0008) -[2023-10-12 04:16:45,693][78091] Updated weights for policy 0, policy_version 27420 (0.0008) -[2023-10-12 04:16:47,846][78123] Updated weights for policy 1, policy_version 27300 (0.0008) -[2023-10-12 04:16:48,225][78123] Updated weights for policy 1, policy_version 27310 (0.0010) -[2023-10-12 04:16:48,597][78123] Updated weights for policy 1, policy_version 27320 (0.0007) -[2023-10-12 04:16:50,043][78091] Updated weights for policy 0, policy_version 27430 (0.0008) -[2023-10-12 04:16:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 56066048. Throughput: 0: 1599.6, 1: 1597.7. Samples: 14026138. Policy #0 lag: (min: 31.0, avg: 33.1, max: 60.0) -[2023-10-12 04:16:50,201][77203] Avg episode reward: [(0, '34.180'), (1, '41.760')] -[2023-10-12 04:16:50,413][78091] Updated weights for policy 0, policy_version 27440 (0.0011) -[2023-10-12 04:16:50,795][78091] Updated weights for policy 0, policy_version 27450 (0.0007) -[2023-10-12 04:16:53,003][78123] Updated weights for policy 1, policy_version 27330 (0.0008) -[2023-10-12 04:16:53,364][78123] Updated weights for policy 1, policy_version 27340 (0.0008) -[2023-10-12 04:16:53,732][78123] Updated weights for policy 1, policy_version 27350 (0.0009) -[2023-10-12 04:16:54,099][78123] Updated weights for policy 1, policy_version 27360 (0.0008) -[2023-10-12 04:16:55,174][78091] Updated weights for policy 0, policy_version 27460 (0.0010) -[2023-10-12 04:16:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 56131584. Throughput: 0: 1613.2, 1: 1584.8. Samples: 14045210. Policy #0 lag: (min: 17.0, avg: 32.9, max: 49.0) -[2023-10-12 04:16:55,201][77203] Avg episode reward: [(0, '41.050'), (1, '41.450')] -[2023-10-12 04:16:55,545][78091] Updated weights for policy 0, policy_version 27470 (0.0009) -[2023-10-12 04:16:55,915][78091] Updated weights for policy 0, policy_version 27480 (0.0007) -[2023-10-12 04:16:58,439][78123] Updated weights for policy 1, policy_version 27370 (0.0010) -[2023-10-12 04:16:58,810][78123] Updated weights for policy 1, policy_version 27380 (0.0009) -[2023-10-12 04:16:59,168][78123] Updated weights for policy 1, policy_version 27390 (0.0008) -[2023-10-12 04:16:59,972][78091] Updated weights for policy 0, policy_version 27490 (0.0009) -[2023-10-12 04:17:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 56197120. Throughput: 0: 1593.7, 1: 1611.4. Samples: 14055168. Policy #0 lag: (min: 17.0, avg: 32.9, max: 49.0) -[2023-10-12 04:17:00,201][77203] Avg episode reward: [(0, '36.530'), (1, '44.940')] -[2023-10-12 04:17:00,348][78091] Updated weights for policy 0, policy_version 27500 (0.0007) -[2023-10-12 04:17:00,719][78091] Updated weights for policy 0, policy_version 27510 (0.0008) -[2023-10-12 04:17:01,088][78091] Updated weights for policy 0, policy_version 27520 (0.0009) -[2023-10-12 04:17:03,500][78123] Updated weights for policy 1, policy_version 27400 (0.0008) -[2023-10-12 04:17:03,868][78123] Updated weights for policy 1, policy_version 27410 (0.0007) -[2023-10-12 04:17:04,235][78123] Updated weights for policy 1, policy_version 27420 (0.0008) -[2023-10-12 04:17:05,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 56262656. Throughput: 0: 1592.9, 1: 1604.5. Samples: 14074276. Policy #0 lag: (min: 17.0, avg: 32.9, max: 49.0) -[2023-10-12 04:17:05,202][77203] Avg episode reward: [(0, '36.800'), (1, '41.960')] -[2023-10-12 04:17:05,330][78091] Updated weights for policy 0, policy_version 27530 (0.0007) -[2023-10-12 04:17:05,694][78091] Updated weights for policy 0, policy_version 27540 (0.0009) -[2023-10-12 04:17:06,070][78091] Updated weights for policy 0, policy_version 27550 (0.0009) -[2023-10-12 04:17:08,603][78123] Updated weights for policy 1, policy_version 27430 (0.0008) -[2023-10-12 04:17:08,977][78123] Updated weights for policy 1, policy_version 27440 (0.0007) -[2023-10-12 04:17:09,336][78123] Updated weights for policy 1, policy_version 27450 (0.0009) -[2023-10-12 04:17:10,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 56328192. Throughput: 0: 1607.0, 1: 1585.9. Samples: 14093264. Policy #0 lag: (min: 17.0, avg: 32.9, max: 49.0) -[2023-10-12 04:17:10,202][77203] Avg episode reward: [(0, '38.930'), (1, '37.320')] -[2023-10-12 04:17:10,210][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000027456_28114944.pth... -[2023-10-12 04:17:10,239][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000025952_26574848.pth -[2023-10-12 04:17:10,451][78091] Updated weights for policy 0, policy_version 27560 (0.0010) -[2023-10-12 04:17:10,822][78091] Updated weights for policy 0, policy_version 27570 (0.0010) -[2023-10-12 04:17:11,189][78091] Updated weights for policy 0, policy_version 27580 (0.0010) -[2023-10-12 04:17:11,337][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000027584_28246016.pth... -[2023-10-12 04:17:11,376][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000026080_26705920.pth -[2023-10-12 04:17:13,367][78123] Updated weights for policy 1, policy_version 27460 (0.0007) -[2023-10-12 04:17:13,739][78123] Updated weights for policy 1, policy_version 27470 (0.0007) -[2023-10-12 04:17:14,094][78123] Updated weights for policy 1, policy_version 27480 (0.0009) -[2023-10-12 04:17:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 56393728. Throughput: 0: 1588.9, 1: 1602.7. Samples: 14103022. Policy #0 lag: (min: 9.0, avg: 12.1, max: 41.0) -[2023-10-12 04:17:15,201][77203] Avg episode reward: [(0, '35.850'), (1, '43.630')] -[2023-10-12 04:17:15,649][78091] Updated weights for policy 0, policy_version 27590 (0.0008) -[2023-10-12 04:17:16,015][78091] Updated weights for policy 0, policy_version 27600 (0.0007) -[2023-10-12 04:17:16,388][78091] Updated weights for policy 0, policy_version 27610 (0.0009) -[2023-10-12 04:17:18,460][78123] Updated weights for policy 1, policy_version 27490 (0.0009) -[2023-10-12 04:17:18,825][78123] Updated weights for policy 1, policy_version 27500 (0.0010) -[2023-10-12 04:17:19,193][78123] Updated weights for policy 1, policy_version 27510 (0.0009) -[2023-10-12 04:17:19,557][78123] Updated weights for policy 1, policy_version 27520 (0.0009) -[2023-10-12 04:17:20,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 56459264. Throughput: 0: 1588.1, 1: 1605.8. Samples: 14122256. Policy #0 lag: (min: 9.0, avg: 12.1, max: 41.0) -[2023-10-12 04:17:20,201][77203] Avg episode reward: [(0, '35.760'), (1, '42.390')] -[2023-10-12 04:17:20,795][78091] Updated weights for policy 0, policy_version 27620 (0.0008) -[2023-10-12 04:17:21,164][78091] Updated weights for policy 0, policy_version 27630 (0.0008) -[2023-10-12 04:17:21,530][78091] Updated weights for policy 0, policy_version 27640 (0.0008) -[2023-10-12 04:17:23,870][78123] Updated weights for policy 1, policy_version 27530 (0.0008) -[2023-10-12 04:17:24,239][78123] Updated weights for policy 1, policy_version 27540 (0.0010) -[2023-10-12 04:17:24,604][78123] Updated weights for policy 1, policy_version 27550 (0.0008) -[2023-10-12 04:17:25,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 56524800. Throughput: 0: 1591.1, 1: 1590.2. Samples: 14140682. Policy #0 lag: (min: 9.0, avg: 12.1, max: 41.0) -[2023-10-12 04:17:25,202][77203] Avg episode reward: [(0, '39.110'), (1, '37.360')] -[2023-10-12 04:17:25,783][78091] Updated weights for policy 0, policy_version 27650 (0.0010) -[2023-10-12 04:17:26,180][78091] Updated weights for policy 0, policy_version 27660 (0.0007) -[2023-10-12 04:17:26,559][78091] Updated weights for policy 0, policy_version 27670 (0.0008) -[2023-10-12 04:17:26,927][78091] Updated weights for policy 0, policy_version 27680 (0.0007) -[2023-10-12 04:17:28,911][78123] Updated weights for policy 1, policy_version 27560 (0.0008) -[2023-10-12 04:17:29,280][78123] Updated weights for policy 1, policy_version 27570 (0.0009) -[2023-10-12 04:17:29,650][78123] Updated weights for policy 1, policy_version 27580 (0.0011) -[2023-10-12 04:17:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 56590336. Throughput: 0: 1583.2, 1: 1591.2. Samples: 14150266. Policy #0 lag: (min: 9.0, avg: 12.1, max: 41.0) -[2023-10-12 04:17:30,202][77203] Avg episode reward: [(0, '37.340'), (1, '41.290')] -[2023-10-12 04:17:31,235][78091] Updated weights for policy 0, policy_version 27690 (0.0007) -[2023-10-12 04:17:31,614][78091] Updated weights for policy 0, policy_version 27700 (0.0007) -[2023-10-12 04:17:31,981][78091] Updated weights for policy 0, policy_version 27710 (0.0007) -[2023-10-12 04:17:34,023][78123] Updated weights for policy 1, policy_version 27590 (0.0009) -[2023-10-12 04:17:34,386][78123] Updated weights for policy 1, policy_version 27600 (0.0008) -[2023-10-12 04:17:34,761][78123] Updated weights for policy 1, policy_version 27610 (0.0009) -[2023-10-12 04:17:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 56655872. Throughput: 0: 1586.3, 1: 1606.5. Samples: 14169814. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 04:17:35,202][77203] Avg episode reward: [(0, '35.880'), (1, '41.450')] -[2023-10-12 04:17:36,238][78091] Updated weights for policy 0, policy_version 27720 (0.0008) -[2023-10-12 04:17:36,615][78091] Updated weights for policy 0, policy_version 27730 (0.0008) -[2023-10-12 04:17:36,984][78091] Updated weights for policy 0, policy_version 27740 (0.0007) -[2023-10-12 04:17:39,201][78123] Updated weights for policy 1, policy_version 27620 (0.0009) -[2023-10-12 04:17:39,571][78123] Updated weights for policy 1, policy_version 27630 (0.0008) -[2023-10-12 04:17:39,945][78123] Updated weights for policy 1, policy_version 27640 (0.0008) -[2023-10-12 04:17:40,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 56688640. Throughput: 0: 1589.8, 1: 1599.6. Samples: 14188732. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 04:17:40,202][77203] Avg episode reward: [(0, '39.650'), (1, '41.150')] -[2023-10-12 04:17:41,398][78091] Updated weights for policy 0, policy_version 27750 (0.0009) -[2023-10-12 04:17:41,763][78091] Updated weights for policy 0, policy_version 27760 (0.0009) -[2023-10-12 04:17:42,132][78091] Updated weights for policy 0, policy_version 27770 (0.0007) -[2023-10-12 04:17:44,334][78123] Updated weights for policy 1, policy_version 27650 (0.0008) -[2023-10-12 04:17:44,702][78123] Updated weights for policy 1, policy_version 27660 (0.0008) -[2023-10-12 04:17:45,068][78123] Updated weights for policy 1, policy_version 27670 (0.0008) -[2023-10-12 04:17:45,201][77203] Fps is (10 sec: 9830.7, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 56754176. Throughput: 0: 1586.2, 1: 1584.4. Samples: 14197844. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 04:17:45,201][77203] Avg episode reward: [(0, '37.010'), (1, '39.480')] -[2023-10-12 04:17:45,443][78123] Updated weights for policy 1, policy_version 27680 (0.0008) -[2023-10-12 04:17:46,398][78091] Updated weights for policy 0, policy_version 27780 (0.0010) -[2023-10-12 04:17:46,766][78091] Updated weights for policy 0, policy_version 27790 (0.0010) -[2023-10-12 04:17:47,149][78091] Updated weights for policy 0, policy_version 27800 (0.0008) -[2023-10-12 04:17:49,858][78123] Updated weights for policy 1, policy_version 27690 (0.0007) -[2023-10-12 04:17:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 56819712. Throughput: 0: 1585.0, 1: 1590.3. Samples: 14217164. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 04:17:50,201][77203] Avg episode reward: [(0, '36.700'), (1, '42.220')] -[2023-10-12 04:17:50,220][78123] Updated weights for policy 1, policy_version 27700 (0.0010) -[2023-10-12 04:17:50,585][78123] Updated weights for policy 1, policy_version 27710 (0.0008) -[2023-10-12 04:17:51,501][78091] Updated weights for policy 0, policy_version 27810 (0.0008) -[2023-10-12 04:17:51,871][78091] Updated weights for policy 0, policy_version 27820 (0.0009) -[2023-10-12 04:17:52,242][78091] Updated weights for policy 0, policy_version 27830 (0.0008) -[2023-10-12 04:17:52,605][78091] Updated weights for policy 0, policy_version 27840 (0.0007) -[2023-10-12 04:17:54,977][78123] Updated weights for policy 1, policy_version 27720 (0.0007) -[2023-10-12 04:17:55,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 56885248. Throughput: 0: 1581.4, 1: 1599.6. Samples: 14236406. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-12 04:17:55,202][77203] Avg episode reward: [(0, '37.770'), (1, '47.770')] -[2023-10-12 04:17:55,356][78123] Updated weights for policy 1, policy_version 27730 (0.0008) -[2023-10-12 04:17:55,727][78123] Updated weights for policy 1, policy_version 27740 (0.0010) -[2023-10-12 04:17:55,876][77950] Saving new best policy, reward=47.770! -[2023-10-12 04:17:56,883][78091] Updated weights for policy 0, policy_version 27850 (0.0007) -[2023-10-12 04:17:57,263][78091] Updated weights for policy 0, policy_version 27860 (0.0007) -[2023-10-12 04:17:57,634][78091] Updated weights for policy 0, policy_version 27870 (0.0007) -[2023-10-12 04:18:00,094][78123] Updated weights for policy 1, policy_version 27750 (0.0009) -[2023-10-12 04:18:00,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 56950784. Throughput: 0: 1584.7, 1: 1574.3. Samples: 14245176. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-12 04:18:00,201][77203] Avg episode reward: [(0, '37.910'), (1, '44.240')] -[2023-10-12 04:18:00,464][78123] Updated weights for policy 1, policy_version 27760 (0.0011) -[2023-10-12 04:18:00,831][78123] Updated weights for policy 1, policy_version 27770 (0.0010) -[2023-10-12 04:18:01,872][78091] Updated weights for policy 0, policy_version 27880 (0.0008) -[2023-10-12 04:18:02,240][78091] Updated weights for policy 0, policy_version 27890 (0.0007) -[2023-10-12 04:18:02,611][78091] Updated weights for policy 0, policy_version 27900 (0.0007) -[2023-10-12 04:18:05,131][78123] Updated weights for policy 1, policy_version 27780 (0.0010) -[2023-10-12 04:18:05,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 57016320. Throughput: 0: 1590.4, 1: 1580.2. Samples: 14264936. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-12 04:18:05,202][77203] Avg episode reward: [(0, '37.880'), (1, '37.990')] -[2023-10-12 04:18:05,499][78123] Updated weights for policy 1, policy_version 27790 (0.0007) -[2023-10-12 04:18:05,872][78123] Updated weights for policy 1, policy_version 27800 (0.0011) -[2023-10-12 04:18:06,836][78091] Updated weights for policy 0, policy_version 27910 (0.0007) -[2023-10-12 04:18:07,210][78091] Updated weights for policy 0, policy_version 27920 (0.0008) -[2023-10-12 04:18:07,589][78091] Updated weights for policy 0, policy_version 27930 (0.0009) -[2023-10-12 04:18:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 57081856. Throughput: 0: 1595.0, 1: 1603.5. Samples: 14284616. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-12 04:18:10,201][77203] Avg episode reward: [(0, '35.000'), (1, '40.190')] -[2023-10-12 04:18:10,233][78123] Updated weights for policy 1, policy_version 27810 (0.0009) -[2023-10-12 04:18:10,612][78123] Updated weights for policy 1, policy_version 27820 (0.0007) -[2023-10-12 04:18:10,986][78123] Updated weights for policy 1, policy_version 27830 (0.0008) -[2023-10-12 04:18:11,349][78123] Updated weights for policy 1, policy_version 27840 (0.0009) -[2023-10-12 04:18:12,041][78091] Updated weights for policy 0, policy_version 27940 (0.0008) -[2023-10-12 04:18:12,422][78091] Updated weights for policy 0, policy_version 27950 (0.0007) -[2023-10-12 04:18:12,794][78091] Updated weights for policy 0, policy_version 27960 (0.0009) -[2023-10-12 04:18:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 57147392. Throughput: 0: 1605.1, 1: 1580.0. Samples: 14293596. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:18:15,201][77203] Avg episode reward: [(0, '39.010'), (1, '42.070')] -[2023-10-12 04:18:15,522][78123] Updated weights for policy 1, policy_version 27850 (0.0008) -[2023-10-12 04:18:15,894][78123] Updated weights for policy 1, policy_version 27860 (0.0007) -[2023-10-12 04:18:16,259][78123] Updated weights for policy 1, policy_version 27870 (0.0007) -[2023-10-12 04:18:17,039][78091] Updated weights for policy 0, policy_version 27970 (0.0008) -[2023-10-12 04:18:17,416][78091] Updated weights for policy 0, policy_version 27980 (0.0008) -[2023-10-12 04:18:17,783][78091] Updated weights for policy 0, policy_version 27990 (0.0009) -[2023-10-12 04:18:18,160][78091] Updated weights for policy 0, policy_version 28000 (0.0009) -[2023-10-12 04:18:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 57212928. Throughput: 0: 1594.4, 1: 1583.0. Samples: 14312798. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:18:20,202][77203] Avg episode reward: [(0, '38.710'), (1, '43.050')] -[2023-10-12 04:18:20,622][78123] Updated weights for policy 1, policy_version 27880 (0.0008) -[2023-10-12 04:18:20,987][78123] Updated weights for policy 1, policy_version 27890 (0.0008) -[2023-10-12 04:18:21,348][78123] Updated weights for policy 1, policy_version 27900 (0.0009) -[2023-10-12 04:18:22,463][78091] Updated weights for policy 0, policy_version 28010 (0.0010) -[2023-10-12 04:18:22,848][78091] Updated weights for policy 0, policy_version 28020 (0.0009) -[2023-10-12 04:18:23,208][78091] Updated weights for policy 0, policy_version 28030 (0.0009) -[2023-10-12 04:18:25,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 57278464. Throughput: 0: 1591.4, 1: 1598.3. Samples: 14332270. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:18:25,202][77203] Avg episode reward: [(0, '36.450'), (1, '40.970')] -[2023-10-12 04:18:25,669][78123] Updated weights for policy 1, policy_version 27910 (0.0010) -[2023-10-12 04:18:26,045][78123] Updated weights for policy 1, policy_version 27920 (0.0011) -[2023-10-12 04:18:26,417][78123] Updated weights for policy 1, policy_version 27930 (0.0008) -[2023-10-12 04:18:27,510][78091] Updated weights for policy 0, policy_version 28040 (0.0009) -[2023-10-12 04:18:27,888][78091] Updated weights for policy 0, policy_version 28050 (0.0010) -[2023-10-12 04:18:28,260][78091] Updated weights for policy 0, policy_version 28060 (0.0009) -[2023-10-12 04:18:30,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 57344000. Throughput: 0: 1608.6, 1: 1585.6. Samples: 14341582. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:18:30,201][77203] Avg episode reward: [(0, '35.080'), (1, '34.020')] -[2023-10-12 04:18:30,757][78123] Updated weights for policy 1, policy_version 27940 (0.0009) -[2023-10-12 04:18:31,130][78123] Updated weights for policy 1, policy_version 27950 (0.0008) -[2023-10-12 04:18:31,505][78123] Updated weights for policy 1, policy_version 27960 (0.0008) -[2023-10-12 04:18:32,491][78091] Updated weights for policy 0, policy_version 28070 (0.0007) -[2023-10-12 04:18:32,865][78091] Updated weights for policy 0, policy_version 28080 (0.0010) -[2023-10-12 04:18:33,246][78091] Updated weights for policy 0, policy_version 28090 (0.0007) -[2023-10-12 04:18:35,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 57409536. Throughput: 0: 1594.0, 1: 1585.7. Samples: 14360252. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-12 04:18:35,202][77203] Avg episode reward: [(0, '38.190'), (1, '36.990')] -[2023-10-12 04:18:35,869][78123] Updated weights for policy 1, policy_version 27970 (0.0009) -[2023-10-12 04:18:36,237][78123] Updated weights for policy 1, policy_version 27980 (0.0007) -[2023-10-12 04:18:36,603][78123] Updated weights for policy 1, policy_version 27990 (0.0007) -[2023-10-12 04:18:36,959][78123] Updated weights for policy 1, policy_version 28000 (0.0007) -[2023-10-12 04:18:37,417][78091] Updated weights for policy 0, policy_version 28100 (0.0008) -[2023-10-12 04:18:37,796][78091] Updated weights for policy 0, policy_version 28110 (0.0011) -[2023-10-12 04:18:38,171][78091] Updated weights for policy 0, policy_version 28120 (0.0008) -[2023-10-12 04:18:40,201][77203] Fps is (10 sec: 13106.6, 60 sec: 13107.1, 300 sec: 12773.9). Total num frames: 57475072. Throughput: 0: 1595.4, 1: 1590.7. Samples: 14379784. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-12 04:18:40,203][77203] Avg episode reward: [(0, '37.360'), (1, '37.770')] -[2023-10-12 04:18:41,217][78123] Updated weights for policy 1, policy_version 28010 (0.0010) -[2023-10-12 04:18:41,588][78123] Updated weights for policy 1, policy_version 28020 (0.0010) -[2023-10-12 04:18:41,962][78123] Updated weights for policy 1, policy_version 28030 (0.0009) -[2023-10-12 04:18:42,601][78091] Updated weights for policy 0, policy_version 28130 (0.0009) -[2023-10-12 04:18:42,962][78091] Updated weights for policy 0, policy_version 28140 (0.0008) -[2023-10-12 04:18:43,340][78091] Updated weights for policy 0, policy_version 28150 (0.0009) -[2023-10-12 04:18:43,699][78091] Updated weights for policy 0, policy_version 28160 (0.0008) -[2023-10-12 04:18:45,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 57540608. Throughput: 0: 1615.8, 1: 1589.1. Samples: 14389394. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-12 04:18:45,201][77203] Avg episode reward: [(0, '39.270'), (1, '39.560')] -[2023-10-12 04:18:46,360][78123] Updated weights for policy 1, policy_version 28040 (0.0011) -[2023-10-12 04:18:46,729][78123] Updated weights for policy 1, policy_version 28050 (0.0010) -[2023-10-12 04:18:47,096][78123] Updated weights for policy 1, policy_version 28060 (0.0008) -[2023-10-12 04:18:48,092][78091] Updated weights for policy 0, policy_version 28170 (0.0009) -[2023-10-12 04:18:48,459][78091] Updated weights for policy 0, policy_version 28180 (0.0007) -[2023-10-12 04:18:48,822][78091] Updated weights for policy 0, policy_version 28190 (0.0007) -[2023-10-12 04:18:50,201][77203] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 57606144. Throughput: 0: 1595.0, 1: 1586.3. Samples: 14408094. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-12 04:18:50,202][77203] Avg episode reward: [(0, '39.590'), (1, '43.410')] -[2023-10-12 04:18:51,494][78123] Updated weights for policy 1, policy_version 28070 (0.0011) -[2023-10-12 04:18:51,870][78123] Updated weights for policy 1, policy_version 28080 (0.0011) -[2023-10-12 04:18:52,236][78123] Updated weights for policy 1, policy_version 28090 (0.0007) -[2023-10-12 04:18:53,179][78091] Updated weights for policy 0, policy_version 28200 (0.0009) -[2023-10-12 04:18:53,561][78091] Updated weights for policy 0, policy_version 28210 (0.0008) -[2023-10-12 04:18:53,929][78091] Updated weights for policy 0, policy_version 28220 (0.0011) -[2023-10-12 04:18:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 57671680. Throughput: 0: 1586.1, 1: 1580.7. Samples: 14427120. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 04:18:55,202][77203] Avg episode reward: [(0, '39.540'), (1, '38.190')] -[2023-10-12 04:18:56,691][78123] Updated weights for policy 1, policy_version 28100 (0.0010) -[2023-10-12 04:18:57,068][78123] Updated weights for policy 1, policy_version 28110 (0.0010) -[2023-10-12 04:18:57,430][78123] Updated weights for policy 1, policy_version 28120 (0.0009) -[2023-10-12 04:18:58,242][78091] Updated weights for policy 0, policy_version 28230 (0.0008) -[2023-10-12 04:18:58,616][78091] Updated weights for policy 0, policy_version 28240 (0.0011) -[2023-10-12 04:18:58,995][78091] Updated weights for policy 0, policy_version 28250 (0.0010) -[2023-10-12 04:19:00,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 57737216. Throughput: 0: 1608.8, 1: 1578.0. Samples: 14437002. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 04:19:00,201][77203] Avg episode reward: [(0, '36.610'), (1, '39.180')] -[2023-10-12 04:19:01,671][78123] Updated weights for policy 1, policy_version 28130 (0.0009) -[2023-10-12 04:19:02,030][78123] Updated weights for policy 1, policy_version 28140 (0.0010) -[2023-10-12 04:19:02,394][78123] Updated weights for policy 1, policy_version 28150 (0.0009) -[2023-10-12 04:19:02,766][78123] Updated weights for policy 1, policy_version 28160 (0.0011) -[2023-10-12 04:19:03,257][78091] Updated weights for policy 0, policy_version 28260 (0.0008) -[2023-10-12 04:19:03,625][78091] Updated weights for policy 0, policy_version 28270 (0.0007) -[2023-10-12 04:19:04,000][78091] Updated weights for policy 0, policy_version 28280 (0.0007) -[2023-10-12 04:19:05,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 57802752. Throughput: 0: 1602.7, 1: 1577.0. Samples: 14455886. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 04:19:05,201][77203] Avg episode reward: [(0, '35.080'), (1, '44.530')] -[2023-10-12 04:19:07,181][78123] Updated weights for policy 1, policy_version 28170 (0.0008) -[2023-10-12 04:19:07,553][78123] Updated weights for policy 1, policy_version 28180 (0.0009) -[2023-10-12 04:19:07,920][78123] Updated weights for policy 1, policy_version 28190 (0.0007) -[2023-10-12 04:19:08,247][78091] Updated weights for policy 0, policy_version 28290 (0.0007) -[2023-10-12 04:19:08,610][78091] Updated weights for policy 0, policy_version 28300 (0.0007) -[2023-10-12 04:19:08,981][78091] Updated weights for policy 0, policy_version 28310 (0.0008) -[2023-10-12 04:19:09,348][78091] Updated weights for policy 0, policy_version 28320 (0.0008) -[2023-10-12 04:19:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 57868288. Throughput: 0: 1595.6, 1: 1573.6. Samples: 14474888. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 04:19:10,201][77203] Avg episode reward: [(0, '36.650'), (1, '41.890')] -[2023-10-12 04:19:10,210][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000028192_28868608.pth... -[2023-10-12 04:19:10,210][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000028320_28999680.pth... -[2023-10-12 04:19:10,243][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000026720_27361280.pth -[2023-10-12 04:19:10,247][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000026816_27459584.pth -[2023-10-12 04:19:12,421][78123] Updated weights for policy 1, policy_version 28200 (0.0010) -[2023-10-12 04:19:12,788][78123] Updated weights for policy 1, policy_version 28210 (0.0008) -[2023-10-12 04:19:13,153][78123] Updated weights for policy 1, policy_version 28220 (0.0010) -[2023-10-12 04:19:13,675][78091] Updated weights for policy 0, policy_version 28330 (0.0008) -[2023-10-12 04:19:14,055][78091] Updated weights for policy 0, policy_version 28340 (0.0011) -[2023-10-12 04:19:14,422][78091] Updated weights for policy 0, policy_version 28350 (0.0007) -[2023-10-12 04:19:15,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 57933824. Throughput: 0: 1607.3, 1: 1585.9. Samples: 14485274. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-12 04:19:15,202][77203] Avg episode reward: [(0, '37.280'), (1, '39.230')] -[2023-10-12 04:19:17,388][78123] Updated weights for policy 1, policy_version 28230 (0.0010) -[2023-10-12 04:19:17,765][78123] Updated weights for policy 1, policy_version 28240 (0.0011) -[2023-10-12 04:19:18,130][78123] Updated weights for policy 1, policy_version 28250 (0.0007) -[2023-10-12 04:19:18,680][78091] Updated weights for policy 0, policy_version 28360 (0.0009) -[2023-10-12 04:19:19,048][78091] Updated weights for policy 0, policy_version 28370 (0.0012) -[2023-10-12 04:19:19,417][78091] Updated weights for policy 0, policy_version 28380 (0.0009) -[2023-10-12 04:19:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 57999360. Throughput: 0: 1614.5, 1: 1577.0. Samples: 14503868. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-12 04:19:20,201][77203] Avg episode reward: [(0, '38.110'), (1, '42.430')] -[2023-10-12 04:19:22,446][78123] Updated weights for policy 1, policy_version 28260 (0.0009) -[2023-10-12 04:19:22,803][78123] Updated weights for policy 1, policy_version 28270 (0.0010) -[2023-10-12 04:19:23,177][78123] Updated weights for policy 1, policy_version 28280 (0.0007) -[2023-10-12 04:19:23,590][78091] Updated weights for policy 0, policy_version 28390 (0.0010) -[2023-10-12 04:19:23,956][78091] Updated weights for policy 0, policy_version 28400 (0.0008) -[2023-10-12 04:19:24,320][78091] Updated weights for policy 0, policy_version 28410 (0.0010) -[2023-10-12 04:19:25,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 58064896. Throughput: 0: 1598.4, 1: 1577.3. Samples: 14522686. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-12 04:19:25,201][77203] Avg episode reward: [(0, '35.350'), (1, '43.700')] -[2023-10-12 04:19:27,808][78123] Updated weights for policy 1, policy_version 28290 (0.0008) -[2023-10-12 04:19:28,176][78123] Updated weights for policy 1, policy_version 28300 (0.0009) -[2023-10-12 04:19:28,551][78123] Updated weights for policy 1, policy_version 28310 (0.0009) -[2023-10-12 04:19:28,663][78091] Updated weights for policy 0, policy_version 28420 (0.0009) -[2023-10-12 04:19:28,917][78123] Updated weights for policy 1, policy_version 28320 (0.0008) -[2023-10-12 04:19:29,032][78091] Updated weights for policy 0, policy_version 28430 (0.0010) -[2023-10-12 04:19:29,403][78091] Updated weights for policy 0, policy_version 28440 (0.0009) -[2023-10-12 04:19:30,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.1, 300 sec: 12885.0). Total num frames: 58130432. Throughput: 0: 1603.0, 1: 1603.6. Samples: 14533692. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-12 04:19:30,202][77203] Avg episode reward: [(0, '41.860'), (1, '41.360')] -[2023-10-12 04:19:33,262][78123] Updated weights for policy 1, policy_version 28330 (0.0007) -[2023-10-12 04:19:33,577][78091] Updated weights for policy 0, policy_version 28450 (0.0009) -[2023-10-12 04:19:33,640][78123] Updated weights for policy 1, policy_version 28340 (0.0007) -[2023-10-12 04:19:33,949][78091] Updated weights for policy 0, policy_version 28460 (0.0010) -[2023-10-12 04:19:34,015][78123] Updated weights for policy 1, policy_version 28350 (0.0008) -[2023-10-12 04:19:34,320][78091] Updated weights for policy 0, policy_version 28470 (0.0009) -[2023-10-12 04:19:34,690][78091] Updated weights for policy 0, policy_version 28480 (0.0008) -[2023-10-12 04:19:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 58195968. Throughput: 0: 1619.9, 1: 1587.2. Samples: 14552416. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:19:35,201][77203] Avg episode reward: [(0, '38.760'), (1, '37.070')] -[2023-10-12 04:19:38,119][78123] Updated weights for policy 1, policy_version 28360 (0.0008) -[2023-10-12 04:19:38,491][78123] Updated weights for policy 1, policy_version 28370 (0.0009) -[2023-10-12 04:19:38,848][78123] Updated weights for policy 1, policy_version 28380 (0.0008) -[2023-10-12 04:19:38,915][78091] Updated weights for policy 0, policy_version 28490 (0.0010) -[2023-10-12 04:19:39,286][78091] Updated weights for policy 0, policy_version 28500 (0.0009) -[2023-10-12 04:19:39,645][78091] Updated weights for policy 0, policy_version 28510 (0.0007) -[2023-10-12 04:19:40,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.3, 300 sec: 12885.0). Total num frames: 58261504. Throughput: 0: 1610.7, 1: 1583.9. Samples: 14570876. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:19:40,201][77203] Avg episode reward: [(0, '35.660'), (1, '41.960')] -[2023-10-12 04:19:43,417][78123] Updated weights for policy 1, policy_version 28390 (0.0009) -[2023-10-12 04:19:43,798][78123] Updated weights for policy 1, policy_version 28400 (0.0010) -[2023-10-12 04:19:43,998][78091] Updated weights for policy 0, policy_version 28520 (0.0007) -[2023-10-12 04:19:44,160][78123] Updated weights for policy 1, policy_version 28410 (0.0009) -[2023-10-12 04:19:44,369][78091] Updated weights for policy 0, policy_version 28530 (0.0007) -[2023-10-12 04:19:44,752][78091] Updated weights for policy 0, policy_version 28540 (0.0009) -[2023-10-12 04:19:45,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 58327040. Throughput: 0: 1611.0, 1: 1610.3. Samples: 14581958. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:19:45,202][77203] Avg episode reward: [(0, '39.260'), (1, '43.050')] -[2023-10-12 04:19:48,484][78123] Updated weights for policy 1, policy_version 28420 (0.0007) -[2023-10-12 04:19:48,838][78123] Updated weights for policy 1, policy_version 28430 (0.0008) -[2023-10-12 04:19:49,035][78091] Updated weights for policy 0, policy_version 28550 (0.0009) -[2023-10-12 04:19:49,198][78123] Updated weights for policy 1, policy_version 28440 (0.0009) -[2023-10-12 04:19:49,409][78091] Updated weights for policy 0, policy_version 28560 (0.0010) -[2023-10-12 04:19:49,772][78091] Updated weights for policy 0, policy_version 28570 (0.0009) -[2023-10-12 04:19:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 58392576. Throughput: 0: 1624.0, 1: 1593.7. Samples: 14600680. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:19:50,201][77203] Avg episode reward: [(0, '34.360'), (1, '41.500')] -[2023-10-12 04:19:53,611][78123] Updated weights for policy 1, policy_version 28450 (0.0009) -[2023-10-12 04:19:53,986][78123] Updated weights for policy 1, policy_version 28460 (0.0009) -[2023-10-12 04:19:54,154][78091] Updated weights for policy 0, policy_version 28580 (0.0009) -[2023-10-12 04:19:54,351][78123] Updated weights for policy 1, policy_version 28470 (0.0007) -[2023-10-12 04:19:54,527][78091] Updated weights for policy 0, policy_version 28590 (0.0007) -[2023-10-12 04:19:54,712][78123] Updated weights for policy 1, policy_version 28480 (0.0007) -[2023-10-12 04:19:54,896][78091] Updated weights for policy 0, policy_version 28600 (0.0008) -[2023-10-12 04:19:55,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 58458112. Throughput: 0: 1619.6, 1: 1577.2. Samples: 14618740. Policy #0 lag: (min: 17.0, avg: 26.0, max: 49.0) -[2023-10-12 04:19:55,202][77203] Avg episode reward: [(0, '37.240'), (1, '40.040')] -[2023-10-12 04:19:59,018][78123] Updated weights for policy 1, policy_version 28490 (0.0009) -[2023-10-12 04:19:59,050][78091] Updated weights for policy 0, policy_version 28610 (0.0009) -[2023-10-12 04:19:59,378][78123] Updated weights for policy 1, policy_version 28500 (0.0009) -[2023-10-12 04:19:59,410][78091] Updated weights for policy 0, policy_version 28620 (0.0009) -[2023-10-12 04:19:59,751][78123] Updated weights for policy 1, policy_version 28510 (0.0009) -[2023-10-12 04:19:59,779][78091] Updated weights for policy 0, policy_version 28630 (0.0008) -[2023-10-12 04:20:00,149][78091] Updated weights for policy 0, policy_version 28640 (0.0008) -[2023-10-12 04:20:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 58523648. Throughput: 0: 1608.5, 1: 1589.7. Samples: 14629190. Policy #0 lag: (min: 17.0, avg: 26.0, max: 49.0) -[2023-10-12 04:20:00,201][77203] Avg episode reward: [(0, '39.970'), (1, '38.300')] -[2023-10-12 04:20:04,025][78123] Updated weights for policy 1, policy_version 28520 (0.0009) -[2023-10-12 04:20:04,396][78123] Updated weights for policy 1, policy_version 28530 (0.0009) -[2023-10-12 04:20:04,563][78091] Updated weights for policy 0, policy_version 28650 (0.0007) -[2023-10-12 04:20:04,760][78123] Updated weights for policy 1, policy_version 28540 (0.0007) -[2023-10-12 04:20:04,936][78091] Updated weights for policy 0, policy_version 28660 (0.0007) -[2023-10-12 04:20:05,201][77203] Fps is (10 sec: 9830.6, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 58556416. Throughput: 0: 1615.1, 1: 1606.2. Samples: 14648826. Policy #0 lag: (min: 17.0, avg: 26.0, max: 49.0) -[2023-10-12 04:20:05,201][77203] Avg episode reward: [(0, '33.520'), (1, '39.700')] -[2023-10-12 04:20:05,306][78091] Updated weights for policy 0, policy_version 28670 (0.0007) -[2023-10-12 04:20:09,115][78123] Updated weights for policy 1, policy_version 28550 (0.0008) -[2023-10-12 04:20:09,483][78123] Updated weights for policy 1, policy_version 28560 (0.0008) -[2023-10-12 04:20:09,644][78091] Updated weights for policy 0, policy_version 28680 (0.0007) -[2023-10-12 04:20:09,850][78123] Updated weights for policy 1, policy_version 28570 (0.0008) -[2023-10-12 04:20:10,019][78091] Updated weights for policy 0, policy_version 28690 (0.0009) -[2023-10-12 04:20:10,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 58621952. Throughput: 0: 1622.6, 1: 1587.0. Samples: 14667120. Policy #0 lag: (min: 17.0, avg: 26.0, max: 49.0) -[2023-10-12 04:20:10,201][77203] Avg episode reward: [(0, '39.680'), (1, '44.090')] -[2023-10-12 04:20:10,389][78091] Updated weights for policy 0, policy_version 28700 (0.0007) -[2023-10-12 04:20:13,829][78123] Updated weights for policy 1, policy_version 28580 (0.0007) -[2023-10-12 04:20:14,191][78123] Updated weights for policy 1, policy_version 28590 (0.0009) -[2023-10-12 04:20:14,572][78123] Updated weights for policy 1, policy_version 28600 (0.0007) -[2023-10-12 04:20:14,752][78091] Updated weights for policy 0, policy_version 28710 (0.0007) -[2023-10-12 04:20:15,118][78091] Updated weights for policy 0, policy_version 28720 (0.0007) -[2023-10-12 04:20:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 58687488. Throughput: 0: 1606.8, 1: 1580.0. Samples: 14677096. Policy #0 lag: (min: 17.0, avg: 26.0, max: 49.0) -[2023-10-12 04:20:15,201][77203] Avg episode reward: [(0, '40.790'), (1, '44.460')] -[2023-10-12 04:20:15,499][78091] Updated weights for policy 0, policy_version 28730 (0.0010) -[2023-10-12 04:20:18,954][78123] Updated weights for policy 1, policy_version 28610 (0.0008) -[2023-10-12 04:20:19,328][78123] Updated weights for policy 1, policy_version 28620 (0.0008) -[2023-10-12 04:20:19,690][78123] Updated weights for policy 1, policy_version 28630 (0.0009) -[2023-10-12 04:20:19,962][78091] Updated weights for policy 0, policy_version 28740 (0.0009) -[2023-10-12 04:20:20,062][78123] Updated weights for policy 1, policy_version 28640 (0.0007) -[2023-10-12 04:20:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 58753024. Throughput: 0: 1604.0, 1: 1598.4. Samples: 14696526. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-12 04:20:20,202][77203] Avg episode reward: [(0, '33.060'), (1, '37.220')] -[2023-10-12 04:20:20,330][78091] Updated weights for policy 0, policy_version 28750 (0.0009) -[2023-10-12 04:20:20,714][78091] Updated weights for policy 0, policy_version 28760 (0.0010) -[2023-10-12 04:20:24,528][78123] Updated weights for policy 1, policy_version 28650 (0.0007) -[2023-10-12 04:20:24,827][78091] Updated weights for policy 0, policy_version 28770 (0.0009) -[2023-10-12 04:20:24,894][78123] Updated weights for policy 1, policy_version 28660 (0.0007) -[2023-10-12 04:20:25,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 58785792. Throughput: 0: 1620.8, 1: 1590.0. Samples: 14715360. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-12 04:20:25,201][78091] Updated weights for policy 0, policy_version 28780 (0.0007) -[2023-10-12 04:20:25,201][77203] Avg episode reward: [(0, '40.690'), (1, '36.190')] -[2023-10-12 04:20:25,256][78123] Updated weights for policy 1, policy_version 28670 (0.0008) -[2023-10-12 04:20:25,574][78091] Updated weights for policy 0, policy_version 28790 (0.0007) -[2023-10-12 04:20:25,940][78091] Updated weights for policy 0, policy_version 28800 (0.0007) -[2023-10-12 04:20:29,616][78123] Updated weights for policy 1, policy_version 28680 (0.0007) -[2023-10-12 04:20:29,994][78123] Updated weights for policy 1, policy_version 28690 (0.0008) -[2023-10-12 04:20:30,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 58851328. Throughput: 0: 1589.3, 1: 1577.7. Samples: 14724468. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-12 04:20:30,201][77203] Avg episode reward: [(0, '34.150'), (1, '39.180')] -[2023-10-12 04:20:30,366][78123] Updated weights for policy 1, policy_version 28700 (0.0010) -[2023-10-12 04:20:30,424][78091] Updated weights for policy 0, policy_version 28810 (0.0009) -[2023-10-12 04:20:30,791][78091] Updated weights for policy 0, policy_version 28820 (0.0007) -[2023-10-12 04:20:31,166][78091] Updated weights for policy 0, policy_version 28830 (0.0009) -[2023-10-12 04:20:34,770][78123] Updated weights for policy 1, policy_version 28710 (0.0007) -[2023-10-12 04:20:35,150][78123] Updated weights for policy 1, policy_version 28720 (0.0009) -[2023-10-12 04:20:35,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 58916864. Throughput: 0: 1583.9, 1: 1589.9. Samples: 14743500. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-12 04:20:35,202][77203] Avg episode reward: [(0, '37.330'), (1, '41.520')] -[2023-10-12 04:20:35,505][78123] Updated weights for policy 1, policy_version 28730 (0.0009) -[2023-10-12 04:20:35,506][78091] Updated weights for policy 0, policy_version 28840 (0.0007) -[2023-10-12 04:20:35,896][78091] Updated weights for policy 0, policy_version 28850 (0.0007) -[2023-10-12 04:20:36,259][78091] Updated weights for policy 0, policy_version 28860 (0.0008) -[2023-10-12 04:20:39,849][78123] Updated weights for policy 1, policy_version 28740 (0.0008) -[2023-10-12 04:20:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 58982400. Throughput: 0: 1600.2, 1: 1606.9. Samples: 14763060. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-12 04:20:40,201][77203] Avg episode reward: [(0, '39.760'), (1, '41.160')] -[2023-10-12 04:20:40,214][78123] Updated weights for policy 1, policy_version 28750 (0.0009) -[2023-10-12 04:20:40,419][78091] Updated weights for policy 0, policy_version 28870 (0.0011) -[2023-10-12 04:20:40,590][78123] Updated weights for policy 1, policy_version 28760 (0.0009) -[2023-10-12 04:20:40,789][78091] Updated weights for policy 0, policy_version 28880 (0.0010) -[2023-10-12 04:20:41,154][78091] Updated weights for policy 0, policy_version 28890 (0.0009) -[2023-10-12 04:20:45,158][78123] Updated weights for policy 1, policy_version 28770 (0.0007) -[2023-10-12 04:20:45,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 59047936. Throughput: 0: 1582.4, 1: 1583.8. Samples: 14771668. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-12 04:20:45,201][77203] Avg episode reward: [(0, '38.240'), (1, '41.470')] -[2023-10-12 04:20:45,523][78123] Updated weights for policy 1, policy_version 28780 (0.0010) -[2023-10-12 04:20:45,581][78091] Updated weights for policy 0, policy_version 28900 (0.0008) -[2023-10-12 04:20:45,887][78123] Updated weights for policy 1, policy_version 28790 (0.0007) -[2023-10-12 04:20:45,955][78091] Updated weights for policy 0, policy_version 28910 (0.0008) -[2023-10-12 04:20:46,248][78123] Updated weights for policy 1, policy_version 28800 (0.0007) -[2023-10-12 04:20:46,325][78091] Updated weights for policy 0, policy_version 28920 (0.0008) -[2023-10-12 04:20:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 59113472. Throughput: 0: 1582.0, 1: 1576.4. Samples: 14790956. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-12 04:20:50,201][77203] Avg episode reward: [(0, '35.530'), (1, '40.200')] -[2023-10-12 04:20:50,469][78091] Updated weights for policy 0, policy_version 28930 (0.0008) -[2023-10-12 04:20:50,488][78123] Updated weights for policy 1, policy_version 28810 (0.0007) -[2023-10-12 04:20:50,844][78091] Updated weights for policy 0, policy_version 28940 (0.0008) -[2023-10-12 04:20:50,862][78123] Updated weights for policy 1, policy_version 28820 (0.0009) -[2023-10-12 04:20:51,214][78091] Updated weights for policy 0, policy_version 28950 (0.0007) -[2023-10-12 04:20:51,225][78123] Updated weights for policy 1, policy_version 28830 (0.0010) -[2023-10-12 04:20:51,574][78091] Updated weights for policy 0, policy_version 28960 (0.0010) -[2023-10-12 04:20:55,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 59179008. Throughput: 0: 1590.0, 1: 1591.6. Samples: 14810290. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-12 04:20:55,202][77203] Avg episode reward: [(0, '41.070'), (1, '41.980')] -[2023-10-12 04:20:55,828][78123] Updated weights for policy 1, policy_version 28840 (0.0010) -[2023-10-12 04:20:55,981][78091] Updated weights for policy 0, policy_version 28970 (0.0009) -[2023-10-12 04:20:56,193][78123] Updated weights for policy 1, policy_version 28850 (0.0007) -[2023-10-12 04:20:56,346][78091] Updated weights for policy 0, policy_version 28980 (0.0008) -[2023-10-12 04:20:56,555][78123] Updated weights for policy 1, policy_version 28860 (0.0009) -[2023-10-12 04:20:56,715][78091] Updated weights for policy 0, policy_version 28990 (0.0007) -[2023-10-12 04:21:00,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 59244544. Throughput: 0: 1578.3, 1: 1569.9. Samples: 14818762. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-12 04:21:00,201][77203] Avg episode reward: [(0, '37.620'), (1, '40.180')] -[2023-10-12 04:21:00,919][78123] Updated weights for policy 1, policy_version 28870 (0.0007) -[2023-10-12 04:21:01,269][78091] Updated weights for policy 0, policy_version 29000 (0.0007) -[2023-10-12 04:21:01,285][78123] Updated weights for policy 1, policy_version 28880 (0.0008) -[2023-10-12 04:21:01,646][78091] Updated weights for policy 0, policy_version 29010 (0.0008) -[2023-10-12 04:21:01,647][78123] Updated weights for policy 1, policy_version 28890 (0.0008) -[2023-10-12 04:21:02,011][78091] Updated weights for policy 0, policy_version 29020 (0.0008) -[2023-10-12 04:21:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 59310080. Throughput: 0: 1579.9, 1: 1568.8. Samples: 14838220. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-12 04:21:05,202][77203] Avg episode reward: [(0, '35.720'), (1, '38.470')] -[2023-10-12 04:21:05,783][78123] Updated weights for policy 1, policy_version 28900 (0.0008) -[2023-10-12 04:21:06,153][78123] Updated weights for policy 1, policy_version 28910 (0.0007) -[2023-10-12 04:21:06,296][78091] Updated weights for policy 0, policy_version 29030 (0.0009) -[2023-10-12 04:21:06,512][78123] Updated weights for policy 1, policy_version 28920 (0.0007) -[2023-10-12 04:21:06,673][78091] Updated weights for policy 0, policy_version 29040 (0.0007) -[2023-10-12 04:21:07,040][78091] Updated weights for policy 0, policy_version 29050 (0.0007) -[2023-10-12 04:21:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 59375616. Throughput: 0: 1578.0, 1: 1585.1. Samples: 14857698. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-12 04:21:10,201][77203] Avg episode reward: [(0, '38.180'), (1, '44.140')] -[2023-10-12 04:21:10,209][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000029056_29753344.pth... -[2023-10-12 04:21:10,209][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000028928_29622272.pth... -[2023-10-12 04:21:10,240][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000027456_28114944.pth -[2023-10-12 04:21:10,248][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000027584_28246016.pth -[2023-10-12 04:21:10,993][78123] Updated weights for policy 1, policy_version 28930 (0.0007) -[2023-10-12 04:21:11,351][78123] Updated weights for policy 1, policy_version 28940 (0.0007) -[2023-10-12 04:21:11,422][78091] Updated weights for policy 0, policy_version 29060 (0.0008) -[2023-10-12 04:21:11,720][78123] Updated weights for policy 1, policy_version 28950 (0.0007) -[2023-10-12 04:21:11,790][78091] Updated weights for policy 0, policy_version 29070 (0.0008) -[2023-10-12 04:21:12,087][78123] Updated weights for policy 1, policy_version 28960 (0.0009) -[2023-10-12 04:21:12,161][78091] Updated weights for policy 0, policy_version 29080 (0.0009) -[2023-10-12 04:21:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 59441152. Throughput: 0: 1577.6, 1: 1571.1. Samples: 14866162. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-12 04:21:15,202][77203] Avg episode reward: [(0, '41.370'), (1, '40.150')] -[2023-10-12 04:21:16,380][78123] Updated weights for policy 1, policy_version 28970 (0.0008) -[2023-10-12 04:21:16,720][78091] Updated weights for policy 0, policy_version 29090 (0.0007) -[2023-10-12 04:21:16,748][78123] Updated weights for policy 1, policy_version 28980 (0.0009) -[2023-10-12 04:21:17,094][78091] Updated weights for policy 0, policy_version 29100 (0.0010) -[2023-10-12 04:21:17,113][78123] Updated weights for policy 1, policy_version 28990 (0.0007) -[2023-10-12 04:21:17,462][78091] Updated weights for policy 0, policy_version 29110 (0.0010) -[2023-10-12 04:21:17,829][78091] Updated weights for policy 0, policy_version 29120 (0.0011) -[2023-10-12 04:21:20,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 59506688. Throughput: 0: 1578.4, 1: 1578.1. Samples: 14885542. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-10-12 04:21:20,202][77203] Avg episode reward: [(0, '41.590'), (1, '39.980')] -[2023-10-12 04:21:21,401][78123] Updated weights for policy 1, policy_version 29000 (0.0007) -[2023-10-12 04:21:21,762][78123] Updated weights for policy 1, policy_version 29010 (0.0010) -[2023-10-12 04:21:22,127][78123] Updated weights for policy 1, policy_version 29020 (0.0007) -[2023-10-12 04:21:22,293][78091] Updated weights for policy 0, policy_version 29130 (0.0010) -[2023-10-12 04:21:22,656][78091] Updated weights for policy 0, policy_version 29140 (0.0009) -[2023-10-12 04:21:23,026][78091] Updated weights for policy 0, policy_version 29150 (0.0010) -[2023-10-12 04:21:25,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 59572224. Throughput: 0: 1568.7, 1: 1580.5. Samples: 14904772. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-10-12 04:21:25,202][77203] Avg episode reward: [(0, '41.690'), (1, '37.110')] -[2023-10-12 04:21:26,425][78123] Updated weights for policy 1, policy_version 29030 (0.0009) -[2023-10-12 04:21:26,790][78123] Updated weights for policy 1, policy_version 29040 (0.0009) -[2023-10-12 04:21:27,158][78123] Updated weights for policy 1, policy_version 29050 (0.0007) -[2023-10-12 04:21:27,507][78091] Updated weights for policy 0, policy_version 29160 (0.0009) -[2023-10-12 04:21:27,881][78091] Updated weights for policy 0, policy_version 29170 (0.0008) -[2023-10-12 04:21:28,254][78091] Updated weights for policy 0, policy_version 29180 (0.0010) -[2023-10-12 04:21:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 59637760. Throughput: 0: 1580.8, 1: 1580.2. Samples: 14913912. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-10-12 04:21:30,201][77203] Avg episode reward: [(0, '38.650'), (1, '35.340')] -[2023-10-12 04:21:31,462][78123] Updated weights for policy 1, policy_version 29060 (0.0009) -[2023-10-12 04:21:31,839][78123] Updated weights for policy 1, policy_version 29070 (0.0009) -[2023-10-12 04:21:32,202][78123] Updated weights for policy 1, policy_version 29080 (0.0009) -[2023-10-12 04:21:32,560][78091] Updated weights for policy 0, policy_version 29190 (0.0007) -[2023-10-12 04:21:32,931][78091] Updated weights for policy 0, policy_version 29200 (0.0009) -[2023-10-12 04:21:33,307][78091] Updated weights for policy 0, policy_version 29210 (0.0008) -[2023-10-12 04:21:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 59703296. Throughput: 0: 1565.4, 1: 1590.3. Samples: 14932962. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-10-12 04:21:35,202][77203] Avg episode reward: [(0, '40.720'), (1, '41.240')] -[2023-10-12 04:21:36,450][78123] Updated weights for policy 1, policy_version 29090 (0.0009) -[2023-10-12 04:21:36,815][78123] Updated weights for policy 1, policy_version 29100 (0.0010) -[2023-10-12 04:21:37,184][78123] Updated weights for policy 1, policy_version 29110 (0.0009) -[2023-10-12 04:21:37,553][78123] Updated weights for policy 1, policy_version 29120 (0.0009) -[2023-10-12 04:21:37,729][78091] Updated weights for policy 0, policy_version 29220 (0.0008) -[2023-10-12 04:21:38,103][78091] Updated weights for policy 0, policy_version 29230 (0.0010) -[2023-10-12 04:21:38,470][78091] Updated weights for policy 0, policy_version 29240 (0.0009) -[2023-10-12 04:21:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 59768832. Throughput: 0: 1566.9, 1: 1597.1. Samples: 14952672. Policy #0 lag: (min: 31.0, avg: 42.6, max: 63.0) -[2023-10-12 04:21:40,202][77203] Avg episode reward: [(0, '36.560'), (1, '40.520')] -[2023-10-12 04:21:41,831][78123] Updated weights for policy 1, policy_version 29130 (0.0008) -[2023-10-12 04:21:42,195][78123] Updated weights for policy 1, policy_version 29140 (0.0009) -[2023-10-12 04:21:42,561][78123] Updated weights for policy 1, policy_version 29150 (0.0010) -[2023-10-12 04:21:42,622][78091] Updated weights for policy 0, policy_version 29250 (0.0008) -[2023-10-12 04:21:42,991][78091] Updated weights for policy 0, policy_version 29260 (0.0009) -[2023-10-12 04:21:43,362][78091] Updated weights for policy 0, policy_version 29270 (0.0009) -[2023-10-12 04:21:43,736][78091] Updated weights for policy 0, policy_version 29280 (0.0009) -[2023-10-12 04:21:45,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 59834368. Throughput: 0: 1589.5, 1: 1599.1. Samples: 14962250. Policy #0 lag: (min: 31.0, avg: 42.6, max: 63.0) -[2023-10-12 04:21:45,201][77203] Avg episode reward: [(0, '36.140'), (1, '37.340')] -[2023-10-12 04:21:46,885][78123] Updated weights for policy 1, policy_version 29160 (0.0009) -[2023-10-12 04:21:47,253][78123] Updated weights for policy 1, policy_version 29170 (0.0009) -[2023-10-12 04:21:47,614][78123] Updated weights for policy 1, policy_version 29180 (0.0009) -[2023-10-12 04:21:48,121][78091] Updated weights for policy 0, policy_version 29290 (0.0009) -[2023-10-12 04:21:48,502][78091] Updated weights for policy 0, policy_version 29300 (0.0010) -[2023-10-12 04:21:48,871][78091] Updated weights for policy 0, policy_version 29310 (0.0010) -[2023-10-12 04:21:50,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 59899904. Throughput: 0: 1574.3, 1: 1602.0. Samples: 14981154. Policy #0 lag: (min: 31.0, avg: 42.6, max: 63.0) -[2023-10-12 04:21:50,202][77203] Avg episode reward: [(0, '33.210'), (1, '39.980')] -[2023-10-12 04:21:52,041][78123] Updated weights for policy 1, policy_version 29190 (0.0008) -[2023-10-12 04:21:52,413][78123] Updated weights for policy 1, policy_version 29200 (0.0010) -[2023-10-12 04:21:52,784][78123] Updated weights for policy 1, policy_version 29210 (0.0008) -[2023-10-12 04:21:53,085][78091] Updated weights for policy 0, policy_version 29320 (0.0007) -[2023-10-12 04:21:53,454][78091] Updated weights for policy 0, policy_version 29330 (0.0007) -[2023-10-12 04:21:53,831][78091] Updated weights for policy 0, policy_version 29340 (0.0009) -[2023-10-12 04:21:55,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 59965440. Throughput: 0: 1576.1, 1: 1599.1. Samples: 15000584. Policy #0 lag: (min: 31.0, avg: 42.6, max: 63.0) -[2023-10-12 04:21:55,202][77203] Avg episode reward: [(0, '38.970'), (1, '39.960')] -[2023-10-12 04:21:56,979][78123] Updated weights for policy 1, policy_version 29220 (0.0010) -[2023-10-12 04:21:57,354][78123] Updated weights for policy 1, policy_version 29230 (0.0008) -[2023-10-12 04:21:57,720][78123] Updated weights for policy 1, policy_version 29240 (0.0007) -[2023-10-12 04:21:57,926][78091] Updated weights for policy 0, policy_version 29350 (0.0009) -[2023-10-12 04:21:58,291][78091] Updated weights for policy 0, policy_version 29360 (0.0008) -[2023-10-12 04:21:58,672][78091] Updated weights for policy 0, policy_version 29370 (0.0010) -[2023-10-12 04:22:00,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 60030976. Throughput: 0: 1604.4, 1: 1608.0. Samples: 15010720. Policy #0 lag: (min: 31.0, avg: 42.6, max: 63.0) -[2023-10-12 04:22:00,202][77203] Avg episode reward: [(0, '40.310'), (1, '36.460')] -[2023-10-12 04:22:02,024][78123] Updated weights for policy 1, policy_version 29250 (0.0008) -[2023-10-12 04:22:02,427][78123] Updated weights for policy 1, policy_version 29260 (0.0010) -[2023-10-12 04:22:02,791][78123] Updated weights for policy 1, policy_version 29270 (0.0008) -[2023-10-12 04:22:03,067][78091] Updated weights for policy 0, policy_version 29380 (0.0009) -[2023-10-12 04:22:03,159][78123] Updated weights for policy 1, policy_version 29280 (0.0008) -[2023-10-12 04:22:03,438][78091] Updated weights for policy 0, policy_version 29390 (0.0008) -[2023-10-12 04:22:03,812][78091] Updated weights for policy 0, policy_version 29400 (0.0009) -[2023-10-12 04:22:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 60096512. Throughput: 0: 1596.2, 1: 1595.5. Samples: 15029166. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:22:05,202][77203] Avg episode reward: [(0, '40.080'), (1, '37.240')] -[2023-10-12 04:22:07,483][78123] Updated weights for policy 1, policy_version 29290 (0.0009) -[2023-10-12 04:22:07,858][78123] Updated weights for policy 1, policy_version 29300 (0.0007) -[2023-10-12 04:22:08,194][78091] Updated weights for policy 0, policy_version 29410 (0.0010) -[2023-10-12 04:22:08,225][78123] Updated weights for policy 1, policy_version 29310 (0.0007) -[2023-10-12 04:22:08,607][78091] Updated weights for policy 0, policy_version 29420 (0.0007) -[2023-10-12 04:22:08,975][78091] Updated weights for policy 0, policy_version 29430 (0.0007) -[2023-10-12 04:22:09,341][78091] Updated weights for policy 0, policy_version 29440 (0.0007) -[2023-10-12 04:22:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 60162048. Throughput: 0: 1591.5, 1: 1596.4. Samples: 15048228. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:22:10,202][77203] Avg episode reward: [(0, '37.140'), (1, '40.110')] -[2023-10-12 04:22:12,608][78123] Updated weights for policy 1, policy_version 29320 (0.0008) -[2023-10-12 04:22:12,981][78123] Updated weights for policy 1, policy_version 29330 (0.0007) -[2023-10-12 04:22:13,361][78123] Updated weights for policy 1, policy_version 29340 (0.0009) -[2023-10-12 04:22:13,671][78091] Updated weights for policy 0, policy_version 29450 (0.0011) -[2023-10-12 04:22:14,054][78091] Updated weights for policy 0, policy_version 29460 (0.0011) -[2023-10-12 04:22:14,425][78091] Updated weights for policy 0, policy_version 29470 (0.0008) -[2023-10-12 04:22:15,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 60227584. Throughput: 0: 1604.3, 1: 1611.9. Samples: 15058642. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:22:15,202][77203] Avg episode reward: [(0, '40.660'), (1, '39.170')] -[2023-10-12 04:22:17,775][78123] Updated weights for policy 1, policy_version 29350 (0.0009) -[2023-10-12 04:22:18,141][78123] Updated weights for policy 1, policy_version 29360 (0.0007) -[2023-10-12 04:22:18,504][78123] Updated weights for policy 1, policy_version 29370 (0.0007) -[2023-10-12 04:22:18,670][78091] Updated weights for policy 0, policy_version 29480 (0.0007) -[2023-10-12 04:22:19,046][78091] Updated weights for policy 0, policy_version 29490 (0.0010) -[2023-10-12 04:22:19,417][78091] Updated weights for policy 0, policy_version 29500 (0.0010) -[2023-10-12 04:22:20,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 60293120. Throughput: 0: 1613.9, 1: 1591.2. Samples: 15077190. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:22:20,202][77203] Avg episode reward: [(0, '35.890'), (1, '37.800')] -[2023-10-12 04:22:22,760][78123] Updated weights for policy 1, policy_version 29380 (0.0008) -[2023-10-12 04:22:23,120][78123] Updated weights for policy 1, policy_version 29390 (0.0008) -[2023-10-12 04:22:23,482][78123] Updated weights for policy 1, policy_version 29400 (0.0007) -[2023-10-12 04:22:23,707][78091] Updated weights for policy 0, policy_version 29510 (0.0008) -[2023-10-12 04:22:24,067][78091] Updated weights for policy 0, policy_version 29520 (0.0010) -[2023-10-12 04:22:24,436][78091] Updated weights for policy 0, policy_version 29530 (0.0007) -[2023-10-12 04:22:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 60358656. Throughput: 0: 1597.8, 1: 1587.0. Samples: 15095988. Policy #0 lag: (min: 13.0, avg: 15.8, max: 45.0) -[2023-10-12 04:22:25,202][77203] Avg episode reward: [(0, '36.620'), (1, '36.700')] -[2023-10-12 04:22:27,832][78123] Updated weights for policy 1, policy_version 29410 (0.0009) -[2023-10-12 04:22:28,207][78123] Updated weights for policy 1, policy_version 29420 (0.0008) -[2023-10-12 04:22:28,571][78123] Updated weights for policy 1, policy_version 29430 (0.0007) -[2023-10-12 04:22:28,669][78091] Updated weights for policy 0, policy_version 29540 (0.0008) -[2023-10-12 04:22:28,929][78123] Updated weights for policy 1, policy_version 29440 (0.0010) -[2023-10-12 04:22:29,045][78091] Updated weights for policy 0, policy_version 29550 (0.0009) -[2023-10-12 04:22:29,415][78091] Updated weights for policy 0, policy_version 29560 (0.0008) -[2023-10-12 04:22:30,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 60424192. Throughput: 0: 1605.8, 1: 1615.1. Samples: 15107190. Policy #0 lag: (min: 13.0, avg: 15.8, max: 45.0) -[2023-10-12 04:22:30,201][77203] Avg episode reward: [(0, '39.310'), (1, '36.800')] -[2023-10-12 04:22:33,320][78123] Updated weights for policy 1, policy_version 29450 (0.0007) -[2023-10-12 04:22:33,678][78123] Updated weights for policy 1, policy_version 29460 (0.0008) -[2023-10-12 04:22:33,803][78091] Updated weights for policy 0, policy_version 29570 (0.0010) -[2023-10-12 04:22:34,043][78123] Updated weights for policy 1, policy_version 29470 (0.0008) -[2023-10-12 04:22:34,162][78091] Updated weights for policy 0, policy_version 29580 (0.0007) -[2023-10-12 04:22:34,541][78091] Updated weights for policy 0, policy_version 29590 (0.0007) -[2023-10-12 04:22:34,908][78091] Updated weights for policy 0, policy_version 29600 (0.0008) -[2023-10-12 04:22:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 60489728. Throughput: 0: 1618.9, 1: 1598.1. Samples: 15125920. Policy #0 lag: (min: 13.0, avg: 15.8, max: 45.0) -[2023-10-12 04:22:35,202][77203] Avg episode reward: [(0, '36.250'), (1, '40.100')] -[2023-10-12 04:22:38,326][78123] Updated weights for policy 1, policy_version 29480 (0.0010) -[2023-10-12 04:22:38,701][78123] Updated weights for policy 1, policy_version 29490 (0.0010) -[2023-10-12 04:22:39,068][78123] Updated weights for policy 1, policy_version 29500 (0.0007) -[2023-10-12 04:22:39,175][78091] Updated weights for policy 0, policy_version 29610 (0.0008) -[2023-10-12 04:22:39,547][78091] Updated weights for policy 0, policy_version 29620 (0.0010) -[2023-10-12 04:22:39,914][78091] Updated weights for policy 0, policy_version 29630 (0.0010) -[2023-10-12 04:22:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 60555264. Throughput: 0: 1600.3, 1: 1589.2. Samples: 15144110. Policy #0 lag: (min: 13.0, avg: 15.8, max: 45.0) -[2023-10-12 04:22:40,201][77203] Avg episode reward: [(0, '42.310'), (1, '41.330')] -[2023-10-12 04:22:43,394][78123] Updated weights for policy 1, policy_version 29510 (0.0007) -[2023-10-12 04:22:43,763][78123] Updated weights for policy 1, policy_version 29520 (0.0008) -[2023-10-12 04:22:44,138][78123] Updated weights for policy 1, policy_version 29530 (0.0009) -[2023-10-12 04:22:44,223][78091] Updated weights for policy 0, policy_version 29640 (0.0009) -[2023-10-12 04:22:44,586][78091] Updated weights for policy 0, policy_version 29650 (0.0010) -[2023-10-12 04:22:44,956][78091] Updated weights for policy 0, policy_version 29660 (0.0010) -[2023-10-12 04:22:45,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 60620800. Throughput: 0: 1595.1, 1: 1608.3. Samples: 15154872. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 04:22:45,201][77203] Avg episode reward: [(0, '43.040'), (1, '42.530')] -[2023-10-12 04:22:48,774][78123] Updated weights for policy 1, policy_version 29540 (0.0008) -[2023-10-12 04:22:49,160][78123] Updated weights for policy 1, policy_version 29550 (0.0010) -[2023-10-12 04:22:49,419][78091] Updated weights for policy 0, policy_version 29670 (0.0009) -[2023-10-12 04:22:49,524][78123] Updated weights for policy 1, policy_version 29560 (0.0009) -[2023-10-12 04:22:49,797][78091] Updated weights for policy 0, policy_version 29680 (0.0007) -[2023-10-12 04:22:50,170][78091] Updated weights for policy 0, policy_version 29690 (0.0008) -[2023-10-12 04:22:50,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 60653568. Throughput: 0: 1609.2, 1: 1605.5. Samples: 15173828. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 04:22:50,201][77203] Avg episode reward: [(0, '35.810'), (1, '38.500')] -[2023-10-12 04:22:53,798][78123] Updated weights for policy 1, policy_version 29570 (0.0008) -[2023-10-12 04:22:54,164][78123] Updated weights for policy 1, policy_version 29580 (0.0010) -[2023-10-12 04:22:54,362][78091] Updated weights for policy 0, policy_version 29700 (0.0008) -[2023-10-12 04:22:54,521][78123] Updated weights for policy 1, policy_version 29590 (0.0007) -[2023-10-12 04:22:54,747][78091] Updated weights for policy 0, policy_version 29710 (0.0007) -[2023-10-12 04:22:54,881][78123] Updated weights for policy 1, policy_version 29600 (0.0007) -[2023-10-12 04:22:55,135][78091] Updated weights for policy 0, policy_version 29720 (0.0008) -[2023-10-12 04:22:55,201][77203] Fps is (10 sec: 9830.2, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 60719104. Throughput: 0: 1611.7, 1: 1580.4. Samples: 15191872. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 04:22:55,202][77203] Avg episode reward: [(0, '38.470'), (1, '40.460')] -[2023-10-12 04:22:59,223][78123] Updated weights for policy 1, policy_version 29610 (0.0009) -[2023-10-12 04:22:59,491][78091] Updated weights for policy 0, policy_version 29730 (0.0009) -[2023-10-12 04:22:59,580][78123] Updated weights for policy 1, policy_version 29620 (0.0009) -[2023-10-12 04:22:59,871][78091] Updated weights for policy 0, policy_version 29740 (0.0008) -[2023-10-12 04:22:59,946][78123] Updated weights for policy 1, policy_version 29630 (0.0009) -[2023-10-12 04:23:00,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 60784640. Throughput: 0: 1595.0, 1: 1584.8. Samples: 15201734. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 04:23:00,202][77203] Avg episode reward: [(0, '38.110'), (1, '45.940')] -[2023-10-12 04:23:00,246][78091] Updated weights for policy 0, policy_version 29750 (0.0009) -[2023-10-12 04:23:00,611][78091] Updated weights for policy 0, policy_version 29760 (0.0010) -[2023-10-12 04:23:04,374][78123] Updated weights for policy 1, policy_version 29640 (0.0008) -[2023-10-12 04:23:04,739][78123] Updated weights for policy 1, policy_version 29650 (0.0007) -[2023-10-12 04:23:04,951][78091] Updated weights for policy 0, policy_version 29770 (0.0008) -[2023-10-12 04:23:05,106][78123] Updated weights for policy 1, policy_version 29660 (0.0007) -[2023-10-12 04:23:05,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 60817408. Throughput: 0: 1597.7, 1: 1597.9. Samples: 15220994. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 04:23:05,202][77203] Avg episode reward: [(0, '39.150'), (1, '44.960')] -[2023-10-12 04:23:05,311][78091] Updated weights for policy 0, policy_version 29780 (0.0009) -[2023-10-12 04:23:05,686][78091] Updated weights for policy 0, policy_version 29790 (0.0011) -[2023-10-12 04:23:09,616][78123] Updated weights for policy 1, policy_version 29670 (0.0008) -[2023-10-12 04:23:09,831][78091] Updated weights for policy 0, policy_version 29800 (0.0008) -[2023-10-12 04:23:09,978][78123] Updated weights for policy 1, policy_version 29680 (0.0007) -[2023-10-12 04:23:10,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 60882944. Throughput: 0: 1610.6, 1: 1587.7. Samples: 15239910. Policy #0 lag: (min: 3.0, avg: 8.0, max: 35.0) -[2023-10-12 04:23:10,201][77203] Avg episode reward: [(0, '41.510'), (1, '44.150')] -[2023-10-12 04:23:10,202][78091] Updated weights for policy 0, policy_version 29810 (0.0009) -[2023-10-12 04:23:10,350][78123] Updated weights for policy 1, policy_version 29690 (0.0008) -[2023-10-12 04:23:10,565][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000029696_30408704.pth... -[2023-10-12 04:23:10,575][78091] Updated weights for policy 0, policy_version 29820 (0.0009) -[2023-10-12 04:23:10,594][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000028192_28868608.pth -[2023-10-12 04:23:10,598][77950] Saving a milestone ./train_atari/atari_hero_APPO/checkpoint_p1/milestones/checkpoint_000029696_30408704.pth -[2023-10-12 04:23:10,725][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000029824_30539776.pth... -[2023-10-12 04:23:10,765][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000028320_28999680.pth -[2023-10-12 04:23:10,770][77792] Saving a milestone ./train_atari/atari_hero_APPO/checkpoint_p0/milestones/checkpoint_000029824_30539776.pth -[2023-10-12 04:23:14,632][78123] Updated weights for policy 1, policy_version 29700 (0.0008) -[2023-10-12 04:23:14,945][78091] Updated weights for policy 0, policy_version 29830 (0.0007) -[2023-10-12 04:23:14,991][78123] Updated weights for policy 1, policy_version 29710 (0.0009) -[2023-10-12 04:23:15,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 60948480. Throughput: 0: 1586.6, 1: 1565.8. Samples: 15249050. Policy #0 lag: (min: 3.0, avg: 8.0, max: 35.0) -[2023-10-12 04:23:15,202][77203] Avg episode reward: [(0, '40.400'), (1, '40.260')] -[2023-10-12 04:23:15,323][78091] Updated weights for policy 0, policy_version 29840 (0.0008) -[2023-10-12 04:23:15,352][78123] Updated weights for policy 1, policy_version 29720 (0.0009) -[2023-10-12 04:23:15,695][78091] Updated weights for policy 0, policy_version 29850 (0.0008) -[2023-10-12 04:23:19,678][78123] Updated weights for policy 1, policy_version 29730 (0.0009) -[2023-10-12 04:23:19,970][78091] Updated weights for policy 0, policy_version 29860 (0.0008) -[2023-10-12 04:23:20,041][78123] Updated weights for policy 1, policy_version 29740 (0.0009) -[2023-10-12 04:23:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 61014016. Throughput: 0: 1591.1, 1: 1578.8. Samples: 15268564. Policy #0 lag: (min: 3.0, avg: 8.0, max: 35.0) -[2023-10-12 04:23:20,201][77203] Avg episode reward: [(0, '38.310'), (1, '40.430')] -[2023-10-12 04:23:20,344][78091] Updated weights for policy 0, policy_version 29870 (0.0007) -[2023-10-12 04:23:20,401][78123] Updated weights for policy 1, policy_version 29750 (0.0007) -[2023-10-12 04:23:20,713][78091] Updated weights for policy 0, policy_version 29880 (0.0008) -[2023-10-12 04:23:20,765][78123] Updated weights for policy 1, policy_version 29760 (0.0007) -[2023-10-12 04:23:25,032][78123] Updated weights for policy 1, policy_version 29770 (0.0007) -[2023-10-12 04:23:25,131][78091] Updated weights for policy 0, policy_version 29890 (0.0010) -[2023-10-12 04:23:25,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 61079552. Throughput: 0: 1605.3, 1: 1593.4. Samples: 15288050. Policy #0 lag: (min: 3.0, avg: 8.0, max: 35.0) -[2023-10-12 04:23:25,202][77203] Avg episode reward: [(0, '38.700'), (1, '44.130')] -[2023-10-12 04:23:25,392][78123] Updated weights for policy 1, policy_version 29780 (0.0008) -[2023-10-12 04:23:25,504][78091] Updated weights for policy 0, policy_version 29900 (0.0009) -[2023-10-12 04:23:25,768][78123] Updated weights for policy 1, policy_version 29790 (0.0009) -[2023-10-12 04:23:25,877][78091] Updated weights for policy 0, policy_version 29910 (0.0008) -[2023-10-12 04:23:26,252][78091] Updated weights for policy 0, policy_version 29920 (0.0009) -[2023-10-12 04:23:29,976][78123] Updated weights for policy 1, policy_version 29800 (0.0008) -[2023-10-12 04:23:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 61145088. Throughput: 0: 1581.3, 1: 1570.0. Samples: 15296680. Policy #0 lag: (min: 12.0, avg: 14.5, max: 43.0) -[2023-10-12 04:23:30,201][77203] Avg episode reward: [(0, '31.470'), (1, '40.390')] -[2023-10-12 04:23:30,350][78123] Updated weights for policy 1, policy_version 29810 (0.0007) -[2023-10-12 04:23:30,597][78091] Updated weights for policy 0, policy_version 29930 (0.0007) -[2023-10-12 04:23:30,725][78123] Updated weights for policy 1, policy_version 29820 (0.0007) -[2023-10-12 04:23:30,959][78091] Updated weights for policy 0, policy_version 29940 (0.0008) -[2023-10-12 04:23:31,335][78091] Updated weights for policy 0, policy_version 29950 (0.0009) -[2023-10-12 04:23:35,142][78123] Updated weights for policy 1, policy_version 29830 (0.0008) -[2023-10-12 04:23:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 61210624. Throughput: 0: 1579.2, 1: 1579.7. Samples: 15315978. Policy #0 lag: (min: 12.0, avg: 14.5, max: 43.0) -[2023-10-12 04:23:35,202][77203] Avg episode reward: [(0, '37.870'), (1, '35.860')] -[2023-10-12 04:23:35,518][78123] Updated weights for policy 1, policy_version 29840 (0.0008) -[2023-10-12 04:23:35,590][78091] Updated weights for policy 0, policy_version 29960 (0.0008) -[2023-10-12 04:23:35,892][78123] Updated weights for policy 1, policy_version 29850 (0.0008) -[2023-10-12 04:23:35,956][78091] Updated weights for policy 0, policy_version 29970 (0.0009) -[2023-10-12 04:23:36,335][78091] Updated weights for policy 0, policy_version 29980 (0.0008) -[2023-10-12 04:23:40,201][77203] Fps is (10 sec: 13106.8, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 61276160. Throughput: 0: 1591.9, 1: 1599.7. Samples: 15335494. Policy #0 lag: (min: 12.0, avg: 14.5, max: 43.0) -[2023-10-12 04:23:40,202][77203] Avg episode reward: [(0, '38.490'), (1, '39.000')] -[2023-10-12 04:23:40,326][78123] Updated weights for policy 1, policy_version 29860 (0.0008) -[2023-10-12 04:23:40,676][78123] Updated weights for policy 1, policy_version 29870 (0.0007) -[2023-10-12 04:23:40,772][78091] Updated weights for policy 0, policy_version 29990 (0.0007) -[2023-10-12 04:23:41,040][78123] Updated weights for policy 1, policy_version 29880 (0.0009) -[2023-10-12 04:23:41,150][78091] Updated weights for policy 0, policy_version 30000 (0.0007) -[2023-10-12 04:23:41,523][78091] Updated weights for policy 0, policy_version 30010 (0.0009) -[2023-10-12 04:23:45,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 61341696. Throughput: 0: 1585.9, 1: 1582.4. Samples: 15344308. Policy #0 lag: (min: 12.0, avg: 14.5, max: 43.0) -[2023-10-12 04:23:45,202][77203] Avg episode reward: [(0, '36.250'), (1, '40.820')] -[2023-10-12 04:23:45,268][78123] Updated weights for policy 1, policy_version 29890 (0.0007) -[2023-10-12 04:23:45,642][78123] Updated weights for policy 1, policy_version 29900 (0.0010) -[2023-10-12 04:23:45,747][78091] Updated weights for policy 0, policy_version 30020 (0.0007) -[2023-10-12 04:23:46,018][78123] Updated weights for policy 1, policy_version 29910 (0.0009) -[2023-10-12 04:23:46,116][78091] Updated weights for policy 0, policy_version 30030 (0.0007) -[2023-10-12 04:23:46,383][78123] Updated weights for policy 1, policy_version 29920 (0.0008) -[2023-10-12 04:23:46,488][78091] Updated weights for policy 0, policy_version 30040 (0.0008) -[2023-10-12 04:23:50,201][77203] Fps is (10 sec: 13107.6, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 61407232. Throughput: 0: 1587.6, 1: 1581.1. Samples: 15363586. Policy #0 lag: (min: 14.0, avg: 16.6, max: 46.0) -[2023-10-12 04:23:50,202][77203] Avg episode reward: [(0, '39.690'), (1, '40.240')] -[2023-10-12 04:23:50,771][78091] Updated weights for policy 0, policy_version 30050 (0.0010) -[2023-10-12 04:23:51,004][78123] Updated weights for policy 1, policy_version 29930 (0.0008) -[2023-10-12 04:23:51,140][78091] Updated weights for policy 0, policy_version 30060 (0.0009) -[2023-10-12 04:23:51,370][78123] Updated weights for policy 1, policy_version 29940 (0.0010) -[2023-10-12 04:23:51,510][78091] Updated weights for policy 0, policy_version 30070 (0.0009) -[2023-10-12 04:23:51,737][78123] Updated weights for policy 1, policy_version 29950 (0.0008) -[2023-10-12 04:23:51,872][78091] Updated weights for policy 0, policy_version 30080 (0.0007) -[2023-10-12 04:23:55,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 61472768. Throughput: 0: 1590.9, 1: 1592.4. Samples: 15383156. Policy #0 lag: (min: 14.0, avg: 16.6, max: 46.0) -[2023-10-12 04:23:55,202][77203] Avg episode reward: [(0, '35.780'), (1, '42.560')] -[2023-10-12 04:23:55,985][78123] Updated weights for policy 1, policy_version 29960 (0.0009) -[2023-10-12 04:23:56,186][78091] Updated weights for policy 0, policy_version 30090 (0.0007) -[2023-10-12 04:23:56,354][78123] Updated weights for policy 1, policy_version 29970 (0.0008) -[2023-10-12 04:23:56,564][78091] Updated weights for policy 0, policy_version 30100 (0.0009) -[2023-10-12 04:23:56,706][78123] Updated weights for policy 1, policy_version 29980 (0.0009) -[2023-10-12 04:23:56,928][78091] Updated weights for policy 0, policy_version 30110 (0.0009) -[2023-10-12 04:24:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 61538304. Throughput: 0: 1584.8, 1: 1584.5. Samples: 15391666. Policy #0 lag: (min: 14.0, avg: 16.6, max: 46.0) -[2023-10-12 04:24:00,201][77203] Avg episode reward: [(0, '32.640'), (1, '41.890')] -[2023-10-12 04:24:01,068][78123] Updated weights for policy 1, policy_version 29990 (0.0008) -[2023-10-12 04:24:01,416][78091] Updated weights for policy 0, policy_version 30120 (0.0007) -[2023-10-12 04:24:01,442][78123] Updated weights for policy 1, policy_version 30000 (0.0007) -[2023-10-12 04:24:01,788][78091] Updated weights for policy 0, policy_version 30130 (0.0007) -[2023-10-12 04:24:01,812][78123] Updated weights for policy 1, policy_version 30010 (0.0007) -[2023-10-12 04:24:02,152][78091] Updated weights for policy 0, policy_version 30140 (0.0009) -[2023-10-12 04:24:05,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 61603840. Throughput: 0: 1577.7, 1: 1586.2. Samples: 15410942. Policy #0 lag: (min: 14.0, avg: 16.6, max: 46.0) -[2023-10-12 04:24:05,201][77203] Avg episode reward: [(0, '35.560'), (1, '45.820')] -[2023-10-12 04:24:06,074][78123] Updated weights for policy 1, policy_version 30020 (0.0008) -[2023-10-12 04:24:06,441][78123] Updated weights for policy 1, policy_version 30030 (0.0008) -[2023-10-12 04:24:06,611][78091] Updated weights for policy 0, policy_version 30150 (0.0009) -[2023-10-12 04:24:06,812][78123] Updated weights for policy 1, policy_version 30040 (0.0007) -[2023-10-12 04:24:06,982][78091] Updated weights for policy 0, policy_version 30160 (0.0009) -[2023-10-12 04:24:07,349][78091] Updated weights for policy 0, policy_version 30170 (0.0007) -[2023-10-12 04:24:10,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 61669376. Throughput: 0: 1582.5, 1: 1584.3. Samples: 15430556. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-12 04:24:10,202][77203] Avg episode reward: [(0, '36.120'), (1, '40.270')] -[2023-10-12 04:24:10,993][78123] Updated weights for policy 1, policy_version 30050 (0.0008) -[2023-10-12 04:24:11,363][78123] Updated weights for policy 1, policy_version 30060 (0.0009) -[2023-10-12 04:24:11,686][78091] Updated weights for policy 0, policy_version 30180 (0.0008) -[2023-10-12 04:24:11,727][78123] Updated weights for policy 1, policy_version 30070 (0.0008) -[2023-10-12 04:24:12,066][78091] Updated weights for policy 0, policy_version 30190 (0.0007) -[2023-10-12 04:24:12,097][78123] Updated weights for policy 1, policy_version 30080 (0.0011) -[2023-10-12 04:24:12,430][78091] Updated weights for policy 0, policy_version 30200 (0.0010) -[2023-10-12 04:24:15,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 61734912. Throughput: 0: 1583.7, 1: 1580.5. Samples: 15439072. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-12 04:24:15,202][77203] Avg episode reward: [(0, '37.680'), (1, '40.020')] -[2023-10-12 04:24:16,455][78123] Updated weights for policy 1, policy_version 30090 (0.0008) -[2023-10-12 04:24:16,584][78091] Updated weights for policy 0, policy_version 30210 (0.0007) -[2023-10-12 04:24:16,817][78123] Updated weights for policy 1, policy_version 30100 (0.0009) -[2023-10-12 04:24:16,959][78091] Updated weights for policy 0, policy_version 30220 (0.0008) -[2023-10-12 04:24:17,187][78123] Updated weights for policy 1, policy_version 30110 (0.0008) -[2023-10-12 04:24:17,327][78091] Updated weights for policy 0, policy_version 30230 (0.0008) -[2023-10-12 04:24:17,702][78091] Updated weights for policy 0, policy_version 30240 (0.0009) -[2023-10-12 04:24:20,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 12662.9). Total num frames: 61800448. Throughput: 0: 1586.7, 1: 1579.3. Samples: 15458448. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-12 04:24:20,203][77203] Avg episode reward: [(0, '38.000'), (1, '40.280')] -[2023-10-12 04:24:21,697][78123] Updated weights for policy 1, policy_version 30120 (0.0007) -[2023-10-12 04:24:22,039][78091] Updated weights for policy 0, policy_version 30250 (0.0008) -[2023-10-12 04:24:22,067][78123] Updated weights for policy 1, policy_version 30130 (0.0007) -[2023-10-12 04:24:22,401][78091] Updated weights for policy 0, policy_version 30260 (0.0009) -[2023-10-12 04:24:22,426][78123] Updated weights for policy 1, policy_version 30140 (0.0008) -[2023-10-12 04:24:22,774][78091] Updated weights for policy 0, policy_version 30270 (0.0009) -[2023-10-12 04:24:25,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 61865984. Throughput: 0: 1588.3, 1: 1581.8. Samples: 15478148. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-12 04:24:25,201][77203] Avg episode reward: [(0, '40.840'), (1, '40.990')] -[2023-10-12 04:24:26,772][78123] Updated weights for policy 1, policy_version 30150 (0.0008) -[2023-10-12 04:24:27,059][78091] Updated weights for policy 0, policy_version 30280 (0.0007) -[2023-10-12 04:24:27,136][78123] Updated weights for policy 1, policy_version 30160 (0.0008) -[2023-10-12 04:24:27,425][78091] Updated weights for policy 0, policy_version 30290 (0.0008) -[2023-10-12 04:24:27,494][78123] Updated weights for policy 1, policy_version 30170 (0.0009) -[2023-10-12 04:24:27,795][78091] Updated weights for policy 0, policy_version 30300 (0.0008) -[2023-10-12 04:24:30,201][77203] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 61931520. Throughput: 0: 1592.9, 1: 1580.5. Samples: 15487112. Policy #0 lag: (min: 28.0, avg: 36.0, max: 60.0) -[2023-10-12 04:24:30,201][77203] Avg episode reward: [(0, '38.930'), (1, '37.970')] -[2023-10-12 04:24:31,804][78123] Updated weights for policy 1, policy_version 30180 (0.0007) -[2023-10-12 04:24:32,028][78091] Updated weights for policy 0, policy_version 30310 (0.0008) -[2023-10-12 04:24:32,168][78123] Updated weights for policy 1, policy_version 30190 (0.0009) -[2023-10-12 04:24:32,390][78091] Updated weights for policy 0, policy_version 30320 (0.0008) -[2023-10-12 04:24:32,532][78123] Updated weights for policy 1, policy_version 30200 (0.0009) -[2023-10-12 04:24:32,761][78091] Updated weights for policy 0, policy_version 30330 (0.0010) -[2023-10-12 04:24:35,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 61997056. Throughput: 0: 1589.0, 1: 1580.6. Samples: 15506218. Policy #0 lag: (min: 28.0, avg: 36.0, max: 60.0) -[2023-10-12 04:24:35,202][77203] Avg episode reward: [(0, '41.700'), (1, '41.100')] -[2023-10-12 04:24:36,976][78123] Updated weights for policy 1, policy_version 30210 (0.0007) -[2023-10-12 04:24:37,151][78091] Updated weights for policy 0, policy_version 30340 (0.0008) -[2023-10-12 04:24:37,340][78123] Updated weights for policy 1, policy_version 30220 (0.0010) -[2023-10-12 04:24:37,512][78091] Updated weights for policy 0, policy_version 30350 (0.0007) -[2023-10-12 04:24:37,709][78123] Updated weights for policy 1, policy_version 30230 (0.0007) -[2023-10-12 04:24:37,879][78091] Updated weights for policy 0, policy_version 30360 (0.0009) -[2023-10-12 04:24:38,071][78123] Updated weights for policy 1, policy_version 30240 (0.0008) -[2023-10-12 04:24:40,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 12662.9). Total num frames: 62062592. Throughput: 0: 1588.9, 1: 1579.0. Samples: 15525712. Policy #0 lag: (min: 28.0, avg: 36.0, max: 60.0) -[2023-10-12 04:24:40,201][77203] Avg episode reward: [(0, '35.300'), (1, '44.270')] -[2023-10-12 04:24:42,018][78091] Updated weights for policy 0, policy_version 30370 (0.0009) -[2023-10-12 04:24:42,382][78091] Updated weights for policy 0, policy_version 30380 (0.0008) -[2023-10-12 04:24:42,496][78123] Updated weights for policy 1, policy_version 30250 (0.0009) -[2023-10-12 04:24:42,750][78091] Updated weights for policy 0, policy_version 30390 (0.0009) -[2023-10-12 04:24:42,859][78123] Updated weights for policy 1, policy_version 30260 (0.0008) -[2023-10-12 04:24:43,122][78091] Updated weights for policy 0, policy_version 30400 (0.0010) -[2023-10-12 04:24:43,237][78123] Updated weights for policy 1, policy_version 30270 (0.0007) -[2023-10-12 04:24:45,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 62128128. Throughput: 0: 1602.4, 1: 1592.5. Samples: 15535434. Policy #0 lag: (min: 28.0, avg: 36.0, max: 60.0) -[2023-10-12 04:24:45,201][77203] Avg episode reward: [(0, '32.660'), (1, '41.620')] -[2023-10-12 04:24:47,455][78091] Updated weights for policy 0, policy_version 30410 (0.0009) -[2023-10-12 04:24:47,563][78123] Updated weights for policy 1, policy_version 30280 (0.0009) -[2023-10-12 04:24:47,836][78091] Updated weights for policy 0, policy_version 30420 (0.0008) -[2023-10-12 04:24:47,923][78123] Updated weights for policy 1, policy_version 30290 (0.0007) -[2023-10-12 04:24:48,200][78091] Updated weights for policy 0, policy_version 30430 (0.0007) -[2023-10-12 04:24:48,292][78123] Updated weights for policy 1, policy_version 30300 (0.0008) -[2023-10-12 04:24:50,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 62193664. Throughput: 0: 1599.0, 1: 1577.8. Samples: 15553900. Policy #0 lag: (min: 28.0, avg: 36.0, max: 60.0) -[2023-10-12 04:24:50,201][77203] Avg episode reward: [(0, '35.730'), (1, '36.860')] -[2023-10-12 04:24:52,374][78091] Updated weights for policy 0, policy_version 30440 (0.0009) -[2023-10-12 04:24:52,552][78123] Updated weights for policy 1, policy_version 30310 (0.0008) -[2023-10-12 04:24:52,743][78091] Updated weights for policy 0, policy_version 30450 (0.0009) -[2023-10-12 04:24:52,919][78123] Updated weights for policy 1, policy_version 30320 (0.0008) -[2023-10-12 04:24:53,123][78091] Updated weights for policy 0, policy_version 30460 (0.0008) -[2023-10-12 04:24:53,282][78123] Updated weights for policy 1, policy_version 30330 (0.0009) -[2023-10-12 04:24:55,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 62259200. Throughput: 0: 1600.9, 1: 1576.4. Samples: 15573536. Policy #0 lag: (min: 12.0, avg: 25.3, max: 44.0) -[2023-10-12 04:24:55,202][77203] Avg episode reward: [(0, '36.070'), (1, '44.540')] -[2023-10-12 04:24:57,463][78123] Updated weights for policy 1, policy_version 30340 (0.0009) -[2023-10-12 04:24:57,575][78091] Updated weights for policy 0, policy_version 30470 (0.0009) -[2023-10-12 04:24:57,826][78123] Updated weights for policy 1, policy_version 30350 (0.0007) -[2023-10-12 04:24:57,937][78091] Updated weights for policy 0, policy_version 30480 (0.0007) -[2023-10-12 04:24:58,185][78123] Updated weights for policy 1, policy_version 30360 (0.0010) -[2023-10-12 04:24:58,305][78091] Updated weights for policy 0, policy_version 30490 (0.0007) -[2023-10-12 04:25:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 62324736. Throughput: 0: 1619.3, 1: 1593.8. Samples: 15583662. Policy #0 lag: (min: 12.0, avg: 25.3, max: 44.0) -[2023-10-12 04:25:00,201][77203] Avg episode reward: [(0, '42.990'), (1, '41.500')] -[2023-10-12 04:25:02,537][78123] Updated weights for policy 1, policy_version 30370 (0.0008) -[2023-10-12 04:25:02,599][78091] Updated weights for policy 0, policy_version 30500 (0.0007) -[2023-10-12 04:25:02,915][78123] Updated weights for policy 1, policy_version 30380 (0.0007) -[2023-10-12 04:25:02,978][78091] Updated weights for policy 0, policy_version 30510 (0.0009) -[2023-10-12 04:25:03,276][78123] Updated weights for policy 1, policy_version 30390 (0.0008) -[2023-10-12 04:25:03,343][78091] Updated weights for policy 0, policy_version 30520 (0.0008) -[2023-10-12 04:25:03,644][78123] Updated weights for policy 1, policy_version 30400 (0.0008) -[2023-10-12 04:25:05,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 62390272. Throughput: 0: 1608.0, 1: 1578.0. Samples: 15601816. Policy #0 lag: (min: 12.0, avg: 25.3, max: 44.0) -[2023-10-12 04:25:05,201][77203] Avg episode reward: [(0, '39.900'), (1, '39.910')] -[2023-10-12 04:25:07,654][78091] Updated weights for policy 0, policy_version 30530 (0.0008) -[2023-10-12 04:25:08,020][78091] Updated weights for policy 0, policy_version 30540 (0.0007) -[2023-10-12 04:25:08,173][78123] Updated weights for policy 1, policy_version 30410 (0.0008) -[2023-10-12 04:25:08,400][78091] Updated weights for policy 0, policy_version 30550 (0.0008) -[2023-10-12 04:25:08,542][78123] Updated weights for policy 1, policy_version 30420 (0.0008) -[2023-10-12 04:25:08,763][78091] Updated weights for policy 0, policy_version 30560 (0.0008) -[2023-10-12 04:25:08,910][78123] Updated weights for policy 1, policy_version 30430 (0.0008) -[2023-10-12 04:25:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 62455808. Throughput: 0: 1600.9, 1: 1577.4. Samples: 15621172. Policy #0 lag: (min: 12.0, avg: 25.3, max: 44.0) -[2023-10-12 04:25:10,201][77203] Avg episode reward: [(0, '42.840'), (1, '43.610')] -[2023-10-12 04:25:10,209][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000030560_31293440.pth... -[2023-10-12 04:25:10,210][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000030432_31162368.pth... -[2023-10-12 04:25:10,242][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000028928_29622272.pth -[2023-10-12 04:25:10,249][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000029056_29753344.pth -[2023-10-12 04:25:13,101][78091] Updated weights for policy 0, policy_version 30570 (0.0007) -[2023-10-12 04:25:13,244][78123] Updated weights for policy 1, policy_version 30440 (0.0008) -[2023-10-12 04:25:13,471][78091] Updated weights for policy 0, policy_version 30580 (0.0008) -[2023-10-12 04:25:13,611][78123] Updated weights for policy 1, policy_version 30450 (0.0007) -[2023-10-12 04:25:13,847][78091] Updated weights for policy 0, policy_version 30590 (0.0010) -[2023-10-12 04:25:13,967][78123] Updated weights for policy 1, policy_version 30460 (0.0008) -[2023-10-12 04:25:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 62521344. Throughput: 0: 1619.2, 1: 1600.0. Samples: 15631972. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-10-12 04:25:15,201][77203] Avg episode reward: [(0, '41.320'), (1, '44.680')] -[2023-10-12 04:25:18,069][78091] Updated weights for policy 0, policy_version 30600 (0.0009) -[2023-10-12 04:25:18,449][78091] Updated weights for policy 0, policy_version 30610 (0.0009) -[2023-10-12 04:25:18,592][78123] Updated weights for policy 1, policy_version 30470 (0.0008) -[2023-10-12 04:25:18,811][78091] Updated weights for policy 0, policy_version 30620 (0.0009) -[2023-10-12 04:25:18,952][78123] Updated weights for policy 1, policy_version 30480 (0.0010) -[2023-10-12 04:25:19,317][78123] Updated weights for policy 1, policy_version 30490 (0.0009) -[2023-10-12 04:25:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 12885.0). Total num frames: 62586880. Throughput: 0: 1606.7, 1: 1593.9. Samples: 15650244. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-10-12 04:25:20,201][77203] Avg episode reward: [(0, '45.520'), (1, '42.650')] -[2023-10-12 04:25:20,202][77792] Saving new best policy, reward=45.520! -[2023-10-12 04:25:23,183][78091] Updated weights for policy 0, policy_version 30630 (0.0007) -[2023-10-12 04:25:23,549][78091] Updated weights for policy 0, policy_version 30640 (0.0007) -[2023-10-12 04:25:23,619][78123] Updated weights for policy 1, policy_version 30500 (0.0009) -[2023-10-12 04:25:23,918][78091] Updated weights for policy 0, policy_version 30650 (0.0009) -[2023-10-12 04:25:23,979][78123] Updated weights for policy 1, policy_version 30510 (0.0009) -[2023-10-12 04:25:24,342][78123] Updated weights for policy 1, policy_version 30520 (0.0009) -[2023-10-12 04:25:25,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 62652416. Throughput: 0: 1601.8, 1: 1577.3. Samples: 15668772. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-10-12 04:25:25,202][77203] Avg episode reward: [(0, '45.480'), (1, '38.830')] -[2023-10-12 04:25:28,111][78091] Updated weights for policy 0, policy_version 30660 (0.0008) -[2023-10-12 04:25:28,484][78091] Updated weights for policy 0, policy_version 30670 (0.0009) -[2023-10-12 04:25:28,652][78123] Updated weights for policy 1, policy_version 30530 (0.0010) -[2023-10-12 04:25:28,858][78091] Updated weights for policy 0, policy_version 30680 (0.0009) -[2023-10-12 04:25:29,025][78123] Updated weights for policy 1, policy_version 30540 (0.0010) -[2023-10-12 04:25:29,390][78123] Updated weights for policy 1, policy_version 30550 (0.0010) -[2023-10-12 04:25:29,766][78123] Updated weights for policy 1, policy_version 30560 (0.0010) -[2023-10-12 04:25:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 62717952. Throughput: 0: 1620.3, 1: 1593.6. Samples: 15680058. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-10-12 04:25:30,201][77203] Avg episode reward: [(0, '32.060'), (1, '42.050')] -[2023-10-12 04:25:33,059][78091] Updated weights for policy 0, policy_version 30690 (0.0010) -[2023-10-12 04:25:33,433][78091] Updated weights for policy 0, policy_version 30700 (0.0008) -[2023-10-12 04:25:33,803][78091] Updated weights for policy 0, policy_version 30710 (0.0009) -[2023-10-12 04:25:33,888][78123] Updated weights for policy 1, policy_version 30570 (0.0009) -[2023-10-12 04:25:34,169][78091] Updated weights for policy 0, policy_version 30720 (0.0009) -[2023-10-12 04:25:34,244][78123] Updated weights for policy 1, policy_version 30580 (0.0009) -[2023-10-12 04:25:34,614][78123] Updated weights for policy 1, policy_version 30590 (0.0009) -[2023-10-12 04:25:35,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 62783488. Throughput: 0: 1613.1, 1: 1607.0. Samples: 15698804. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-10-12 04:25:35,201][77203] Avg episode reward: [(0, '31.920'), (1, '39.550')] -[2023-10-12 04:25:38,379][78091] Updated weights for policy 0, policy_version 30730 (0.0007) -[2023-10-12 04:25:38,752][78091] Updated weights for policy 0, policy_version 30740 (0.0008) -[2023-10-12 04:25:38,980][78123] Updated weights for policy 1, policy_version 30600 (0.0010) -[2023-10-12 04:25:39,123][78091] Updated weights for policy 0, policy_version 30750 (0.0008) -[2023-10-12 04:25:39,342][78123] Updated weights for policy 1, policy_version 30610 (0.0008) -[2023-10-12 04:25:39,707][78123] Updated weights for policy 1, policy_version 30620 (0.0010) -[2023-10-12 04:25:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 62849024. Throughput: 0: 1607.2, 1: 1589.9. Samples: 15717404. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:25:40,201][77203] Avg episode reward: [(0, '35.590'), (1, '40.590')] -[2023-10-12 04:25:43,444][78091] Updated weights for policy 0, policy_version 30760 (0.0010) -[2023-10-12 04:25:43,816][78091] Updated weights for policy 0, policy_version 30770 (0.0009) -[2023-10-12 04:25:43,993][78123] Updated weights for policy 1, policy_version 30630 (0.0008) -[2023-10-12 04:25:44,183][78091] Updated weights for policy 0, policy_version 30780 (0.0009) -[2023-10-12 04:25:44,362][78123] Updated weights for policy 1, policy_version 30640 (0.0008) -[2023-10-12 04:25:44,728][78123] Updated weights for policy 1, policy_version 30650 (0.0009) -[2023-10-12 04:25:45,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 62914560. Throughput: 0: 1615.3, 1: 1596.4. Samples: 15728190. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:25:45,202][77203] Avg episode reward: [(0, '40.430'), (1, '38.810')] -[2023-10-12 04:25:48,534][78091] Updated weights for policy 0, policy_version 30790 (0.0009) -[2023-10-12 04:25:48,900][78091] Updated weights for policy 0, policy_version 30800 (0.0007) -[2023-10-12 04:25:49,211][78123] Updated weights for policy 1, policy_version 30660 (0.0007) -[2023-10-12 04:25:49,272][78091] Updated weights for policy 0, policy_version 30810 (0.0007) -[2023-10-12 04:25:49,577][78123] Updated weights for policy 1, policy_version 30670 (0.0009) -[2023-10-12 04:25:49,943][78123] Updated weights for policy 1, policy_version 30680 (0.0007) -[2023-10-12 04:25:50,201][77203] Fps is (10 sec: 9830.2, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 62947328. Throughput: 0: 1613.5, 1: 1617.9. Samples: 15747230. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:25:50,202][77203] Avg episode reward: [(0, '37.630'), (1, '37.460')] -[2023-10-12 04:25:53,571][78091] Updated weights for policy 0, policy_version 30820 (0.0008) -[2023-10-12 04:25:53,945][78091] Updated weights for policy 0, policy_version 30830 (0.0009) -[2023-10-12 04:25:54,204][78123] Updated weights for policy 1, policy_version 30690 (0.0009) -[2023-10-12 04:25:54,312][78091] Updated weights for policy 0, policy_version 30840 (0.0008) -[2023-10-12 04:25:54,604][78123] Updated weights for policy 1, policy_version 30700 (0.0008) -[2023-10-12 04:25:54,972][78123] Updated weights for policy 1, policy_version 30710 (0.0009) -[2023-10-12 04:25:55,201][77203] Fps is (10 sec: 9830.6, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 63012864. Throughput: 0: 1601.6, 1: 1606.5. Samples: 15765536. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:25:55,201][77203] Avg episode reward: [(0, '40.330'), (1, '40.310')] -[2023-10-12 04:25:55,339][78123] Updated weights for policy 1, policy_version 30720 (0.0007) -[2023-10-12 04:25:58,780][78091] Updated weights for policy 0, policy_version 30850 (0.0007) -[2023-10-12 04:25:59,170][78091] Updated weights for policy 0, policy_version 30860 (0.0010) -[2023-10-12 04:25:59,534][78091] Updated weights for policy 0, policy_version 30870 (0.0008) -[2023-10-12 04:25:59,575][78123] Updated weights for policy 1, policy_version 30730 (0.0009) -[2023-10-12 04:25:59,903][78091] Updated weights for policy 0, policy_version 30880 (0.0008) -[2023-10-12 04:25:59,945][78123] Updated weights for policy 1, policy_version 30740 (0.0007) -[2023-10-12 04:26:00,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 63078400. Throughput: 0: 1604.8, 1: 1591.7. Samples: 15775814. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:26:00,201][77203] Avg episode reward: [(0, '40.370'), (1, '39.400')] -[2023-10-12 04:26:00,316][78123] Updated weights for policy 1, policy_version 30750 (0.0009) -[2023-10-12 04:26:04,103][78091] Updated weights for policy 0, policy_version 30890 (0.0011) -[2023-10-12 04:26:04,467][78091] Updated weights for policy 0, policy_version 30900 (0.0009) -[2023-10-12 04:26:04,756][78123] Updated weights for policy 1, policy_version 30760 (0.0008) -[2023-10-12 04:26:04,838][78091] Updated weights for policy 0, policy_version 30910 (0.0008) -[2023-10-12 04:26:05,115][78123] Updated weights for policy 1, policy_version 30770 (0.0008) -[2023-10-12 04:26:05,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 63143936. Throughput: 0: 1620.5, 1: 1598.3. Samples: 15795090. Policy #0 lag: (min: 26.0, avg: 27.1, max: 46.0) -[2023-10-12 04:26:05,202][77203] Avg episode reward: [(0, '38.060'), (1, '39.210')] -[2023-10-12 04:26:05,479][78123] Updated weights for policy 1, policy_version 30780 (0.0009) -[2023-10-12 04:26:09,132][78091] Updated weights for policy 0, policy_version 30920 (0.0008) -[2023-10-12 04:26:09,512][78091] Updated weights for policy 0, policy_version 30930 (0.0008) -[2023-10-12 04:26:09,668][78123] Updated weights for policy 1, policy_version 30790 (0.0009) -[2023-10-12 04:26:09,879][78091] Updated weights for policy 0, policy_version 30940 (0.0008) -[2023-10-12 04:26:10,039][78123] Updated weights for policy 1, policy_version 30800 (0.0008) -[2023-10-12 04:26:10,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 63209472. Throughput: 0: 1606.6, 1: 1608.7. Samples: 15813458. Policy #0 lag: (min: 26.0, avg: 27.1, max: 46.0) -[2023-10-12 04:26:10,202][77203] Avg episode reward: [(0, '43.480'), (1, '42.930')] -[2023-10-12 04:26:10,405][78123] Updated weights for policy 1, policy_version 30810 (0.0010) -[2023-10-12 04:26:14,273][78091] Updated weights for policy 0, policy_version 30950 (0.0009) -[2023-10-12 04:26:14,640][78091] Updated weights for policy 0, policy_version 30960 (0.0009) -[2023-10-12 04:26:14,845][78123] Updated weights for policy 1, policy_version 30820 (0.0008) -[2023-10-12 04:26:15,009][78091] Updated weights for policy 0, policy_version 30970 (0.0008) -[2023-10-12 04:26:15,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 63242240. Throughput: 0: 1595.7, 1: 1583.1. Samples: 15823102. Policy #0 lag: (min: 26.0, avg: 27.1, max: 46.0) -[2023-10-12 04:26:15,201][77203] Avg episode reward: [(0, '42.180'), (1, '45.840')] -[2023-10-12 04:26:15,217][78123] Updated weights for policy 1, policy_version 30830 (0.0008) -[2023-10-12 04:26:15,592][78123] Updated weights for policy 1, policy_version 30840 (0.0007) -[2023-10-12 04:26:19,193][78091] Updated weights for policy 0, policy_version 30980 (0.0009) -[2023-10-12 04:26:19,567][78091] Updated weights for policy 0, policy_version 30990 (0.0010) -[2023-10-12 04:26:19,941][78091] Updated weights for policy 0, policy_version 31000 (0.0009) -[2023-10-12 04:26:19,984][78123] Updated weights for policy 1, policy_version 30850 (0.0008) -[2023-10-12 04:26:20,201][77203] Fps is (10 sec: 9830.2, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 63307776. Throughput: 0: 1610.3, 1: 1582.0. Samples: 15842456. Policy #0 lag: (min: 26.0, avg: 27.1, max: 46.0) -[2023-10-12 04:26:20,202][77203] Avg episode reward: [(0, '41.130'), (1, '40.590')] -[2023-10-12 04:26:20,351][78123] Updated weights for policy 1, policy_version 30860 (0.0008) -[2023-10-12 04:26:20,717][78123] Updated weights for policy 1, policy_version 30870 (0.0007) -[2023-10-12 04:26:21,076][78123] Updated weights for policy 1, policy_version 30880 (0.0007) -[2023-10-12 04:26:24,199][78091] Updated weights for policy 0, policy_version 31010 (0.0008) -[2023-10-12 04:26:24,568][78091] Updated weights for policy 0, policy_version 31020 (0.0008) -[2023-10-12 04:26:24,937][78091] Updated weights for policy 0, policy_version 31030 (0.0007) -[2023-10-12 04:26:25,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 63373312. Throughput: 0: 1600.5, 1: 1598.4. Samples: 15861358. Policy #0 lag: (min: 26.0, avg: 27.1, max: 46.0) -[2023-10-12 04:26:25,202][77203] Avg episode reward: [(0, '38.260'), (1, '42.320')] -[2023-10-12 04:26:25,308][78091] Updated weights for policy 0, policy_version 31040 (0.0008) -[2023-10-12 04:26:25,415][78123] Updated weights for policy 1, policy_version 30890 (0.0010) -[2023-10-12 04:26:25,782][78123] Updated weights for policy 1, policy_version 30900 (0.0008) -[2023-10-12 04:26:26,150][78123] Updated weights for policy 1, policy_version 30910 (0.0010) -[2023-10-12 04:26:29,577][78091] Updated weights for policy 0, policy_version 31050 (0.0008) -[2023-10-12 04:26:29,948][78091] Updated weights for policy 0, policy_version 31060 (0.0008) -[2023-10-12 04:26:30,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 63438848. Throughput: 0: 1592.1, 1: 1575.1. Samples: 15870716. Policy #0 lag: (min: 26.0, avg: 27.1, max: 46.0) -[2023-10-12 04:26:30,202][77203] Avg episode reward: [(0, '41.660'), (1, '42.190')] -[2023-10-12 04:26:30,313][78091] Updated weights for policy 0, policy_version 31070 (0.0008) -[2023-10-12 04:26:30,580][78123] Updated weights for policy 1, policy_version 30920 (0.0009) -[2023-10-12 04:26:30,953][78123] Updated weights for policy 1, policy_version 30930 (0.0008) -[2023-10-12 04:26:31,312][78123] Updated weights for policy 1, policy_version 30940 (0.0008) -[2023-10-12 04:26:34,677][78091] Updated weights for policy 0, policy_version 31080 (0.0007) -[2023-10-12 04:26:35,046][78091] Updated weights for policy 0, policy_version 31090 (0.0007) -[2023-10-12 04:26:35,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 63504384. Throughput: 0: 1599.3, 1: 1574.4. Samples: 15890042. Policy #0 lag: (min: 0.0, avg: 26.9, max: 32.0) -[2023-10-12 04:26:35,201][77203] Avg episode reward: [(0, '34.190'), (1, '41.960')] -[2023-10-12 04:26:35,416][78091] Updated weights for policy 0, policy_version 31100 (0.0009) -[2023-10-12 04:26:35,608][78123] Updated weights for policy 1, policy_version 30950 (0.0007) -[2023-10-12 04:26:35,983][78123] Updated weights for policy 1, policy_version 30960 (0.0007) -[2023-10-12 04:26:36,343][78123] Updated weights for policy 1, policy_version 30970 (0.0009) -[2023-10-12 04:26:39,755][78091] Updated weights for policy 0, policy_version 31110 (0.0007) -[2023-10-12 04:26:40,120][78091] Updated weights for policy 0, policy_version 31120 (0.0007) -[2023-10-12 04:26:40,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 63569920. Throughput: 0: 1606.6, 1: 1587.6. Samples: 15909276. Policy #0 lag: (min: 0.0, avg: 26.9, max: 32.0) -[2023-10-12 04:26:40,202][77203] Avg episode reward: [(0, '35.630'), (1, '44.270')] -[2023-10-12 04:26:40,499][78091] Updated weights for policy 0, policy_version 31130 (0.0009) -[2023-10-12 04:26:40,811][78123] Updated weights for policy 1, policy_version 30980 (0.0008) -[2023-10-12 04:26:41,198][78123] Updated weights for policy 1, policy_version 30990 (0.0008) -[2023-10-12 04:26:41,563][78123] Updated weights for policy 1, policy_version 31000 (0.0007) -[2023-10-12 04:26:44,875][78091] Updated weights for policy 0, policy_version 31140 (0.0009) -[2023-10-12 04:26:45,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 63635456. Throughput: 0: 1583.3, 1: 1575.0. Samples: 15917936. Policy #0 lag: (min: 0.0, avg: 26.9, max: 32.0) -[2023-10-12 04:26:45,201][77203] Avg episode reward: [(0, '32.940'), (1, '41.830')] -[2023-10-12 04:26:45,269][78091] Updated weights for policy 0, policy_version 31150 (0.0007) -[2023-10-12 04:26:45,646][78091] Updated weights for policy 0, policy_version 31160 (0.0008) -[2023-10-12 04:26:45,871][78123] Updated weights for policy 1, policy_version 31010 (0.0009) -[2023-10-12 04:26:46,236][78123] Updated weights for policy 1, policy_version 31020 (0.0007) -[2023-10-12 04:26:46,601][78123] Updated weights for policy 1, policy_version 31030 (0.0011) -[2023-10-12 04:26:46,979][78123] Updated weights for policy 1, policy_version 31040 (0.0010) -[2023-10-12 04:26:49,989][78091] Updated weights for policy 0, policy_version 31170 (0.0009) -[2023-10-12 04:26:50,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 63700992. Throughput: 0: 1583.7, 1: 1576.3. Samples: 15937288. Policy #0 lag: (min: 0.0, avg: 26.9, max: 32.0) -[2023-10-12 04:26:50,201][77203] Avg episode reward: [(0, '37.840'), (1, '43.260')] -[2023-10-12 04:26:50,359][78091] Updated weights for policy 0, policy_version 31180 (0.0007) -[2023-10-12 04:26:50,741][78091] Updated weights for policy 0, policy_version 31190 (0.0007) -[2023-10-12 04:26:51,110][78091] Updated weights for policy 0, policy_version 31200 (0.0009) -[2023-10-12 04:26:51,346][78123] Updated weights for policy 1, policy_version 31050 (0.0010) -[2023-10-12 04:26:51,718][78123] Updated weights for policy 1, policy_version 31060 (0.0009) -[2023-10-12 04:26:52,084][78123] Updated weights for policy 1, policy_version 31070 (0.0008) -[2023-10-12 04:26:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 63766528. Throughput: 0: 1607.1, 1: 1584.4. Samples: 15957074. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:26:55,202][77203] Avg episode reward: [(0, '37.950'), (1, '43.530')] -[2023-10-12 04:26:55,238][78091] Updated weights for policy 0, policy_version 31210 (0.0009) -[2023-10-12 04:26:55,615][78091] Updated weights for policy 0, policy_version 31220 (0.0009) -[2023-10-12 04:26:55,992][78091] Updated weights for policy 0, policy_version 31230 (0.0008) -[2023-10-12 04:26:56,399][78123] Updated weights for policy 1, policy_version 31080 (0.0008) -[2023-10-12 04:26:56,770][78123] Updated weights for policy 1, policy_version 31090 (0.0011) -[2023-10-12 04:26:57,134][78123] Updated weights for policy 1, policy_version 31100 (0.0008) -[2023-10-12 04:27:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 63832064. Throughput: 0: 1587.1, 1: 1578.0. Samples: 15965534. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:27:00,201][77203] Avg episode reward: [(0, '41.440'), (1, '41.500')] -[2023-10-12 04:27:00,455][78091] Updated weights for policy 0, policy_version 31240 (0.0009) -[2023-10-12 04:27:00,832][78091] Updated weights for policy 0, policy_version 31250 (0.0008) -[2023-10-12 04:27:01,204][78091] Updated weights for policy 0, policy_version 31260 (0.0009) -[2023-10-12 04:27:01,562][78123] Updated weights for policy 1, policy_version 31110 (0.0008) -[2023-10-12 04:27:01,926][78123] Updated weights for policy 1, policy_version 31120 (0.0010) -[2023-10-12 04:27:02,287][78123] Updated weights for policy 1, policy_version 31130 (0.0010) -[2023-10-12 04:27:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 63897600. Throughput: 0: 1582.1, 1: 1575.6. Samples: 15984552. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:27:05,201][77203] Avg episode reward: [(0, '39.490'), (1, '42.390')] -[2023-10-12 04:27:05,606][78091] Updated weights for policy 0, policy_version 31270 (0.0008) -[2023-10-12 04:27:05,970][78091] Updated weights for policy 0, policy_version 31280 (0.0010) -[2023-10-12 04:27:06,341][78091] Updated weights for policy 0, policy_version 31290 (0.0011) -[2023-10-12 04:27:06,668][78123] Updated weights for policy 1, policy_version 31140 (0.0008) -[2023-10-12 04:27:07,031][78123] Updated weights for policy 1, policy_version 31150 (0.0010) -[2023-10-12 04:27:07,408][78123] Updated weights for policy 1, policy_version 31160 (0.0010) -[2023-10-12 04:27:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 63963136. Throughput: 0: 1599.7, 1: 1567.5. Samples: 16003882. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:27:10,201][77203] Avg episode reward: [(0, '43.760'), (1, '44.820')] -[2023-10-12 04:27:10,209][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000031296_32047104.pth... -[2023-10-12 04:27:10,209][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000031168_31916032.pth... -[2023-10-12 04:27:10,247][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000029824_30539776.pth -[2023-10-12 04:27:10,247][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000029696_30408704.pth -[2023-10-12 04:27:10,574][78091] Updated weights for policy 0, policy_version 31300 (0.0009) -[2023-10-12 04:27:10,942][78091] Updated weights for policy 0, policy_version 31310 (0.0007) -[2023-10-12 04:27:11,314][78091] Updated weights for policy 0, policy_version 31320 (0.0007) -[2023-10-12 04:27:11,872][78123] Updated weights for policy 1, policy_version 31170 (0.0009) -[2023-10-12 04:27:12,233][78123] Updated weights for policy 1, policy_version 31180 (0.0009) -[2023-10-12 04:27:12,602][78123] Updated weights for policy 1, policy_version 31190 (0.0008) -[2023-10-12 04:27:12,959][78123] Updated weights for policy 1, policy_version 31200 (0.0009) -[2023-10-12 04:27:15,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 64028672. Throughput: 0: 1584.7, 1: 1574.9. Samples: 16012900. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:27:15,202][77203] Avg episode reward: [(0, '36.750'), (1, '48.980')] -[2023-10-12 04:27:15,203][77950] Saving new best policy, reward=48.980! -[2023-10-12 04:27:15,542][78091] Updated weights for policy 0, policy_version 31330 (0.0009) -[2023-10-12 04:27:15,916][78091] Updated weights for policy 0, policy_version 31340 (0.0008) -[2023-10-12 04:27:16,291][78091] Updated weights for policy 0, policy_version 31350 (0.0007) -[2023-10-12 04:27:16,661][78091] Updated weights for policy 0, policy_version 31360 (0.0009) -[2023-10-12 04:27:17,499][78123] Updated weights for policy 1, policy_version 31210 (0.0011) -[2023-10-12 04:27:17,856][78123] Updated weights for policy 1, policy_version 31220 (0.0011) -[2023-10-12 04:27:18,228][78123] Updated weights for policy 1, policy_version 31230 (0.0010) -[2023-10-12 04:27:20,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 64094208. Throughput: 0: 1597.1, 1: 1561.3. Samples: 16032170. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-12 04:27:20,202][77203] Avg episode reward: [(0, '37.750'), (1, '41.590')] -[2023-10-12 04:27:20,839][78091] Updated weights for policy 0, policy_version 31370 (0.0008) -[2023-10-12 04:27:21,206][78091] Updated weights for policy 0, policy_version 31380 (0.0007) -[2023-10-12 04:27:21,576][78091] Updated weights for policy 0, policy_version 31390 (0.0007) -[2023-10-12 04:27:22,523][78123] Updated weights for policy 1, policy_version 31240 (0.0010) -[2023-10-12 04:27:22,891][78123] Updated weights for policy 1, policy_version 31250 (0.0008) -[2023-10-12 04:27:23,272][78123] Updated weights for policy 1, policy_version 31260 (0.0007) -[2023-10-12 04:27:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 64159744. Throughput: 0: 1599.7, 1: 1561.3. Samples: 16051522. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-12 04:27:25,202][77203] Avg episode reward: [(0, '33.560'), (1, '42.910')] -[2023-10-12 04:27:26,105][78091] Updated weights for policy 0, policy_version 31400 (0.0007) -[2023-10-12 04:27:26,469][78091] Updated weights for policy 0, policy_version 31410 (0.0008) -[2023-10-12 04:27:26,840][78091] Updated weights for policy 0, policy_version 31420 (0.0011) -[2023-10-12 04:27:27,728][78123] Updated weights for policy 1, policy_version 31270 (0.0009) -[2023-10-12 04:27:28,114][78123] Updated weights for policy 1, policy_version 31280 (0.0007) -[2023-10-12 04:27:28,487][78123] Updated weights for policy 1, policy_version 31290 (0.0007) -[2023-10-12 04:27:30,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 64225280. Throughput: 0: 1595.8, 1: 1583.4. Samples: 16061000. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-12 04:27:30,201][77203] Avg episode reward: [(0, '33.190'), (1, '42.180')] -[2023-10-12 04:27:31,170][78091] Updated weights for policy 0, policy_version 31430 (0.0010) -[2023-10-12 04:27:31,545][78091] Updated weights for policy 0, policy_version 31440 (0.0007) -[2023-10-12 04:27:31,917][78091] Updated weights for policy 0, policy_version 31450 (0.0009) -[2023-10-12 04:27:32,718][78123] Updated weights for policy 1, policy_version 31300 (0.0008) -[2023-10-12 04:27:33,077][78123] Updated weights for policy 1, policy_version 31310 (0.0008) -[2023-10-12 04:27:33,442][78123] Updated weights for policy 1, policy_version 31320 (0.0008) -[2023-10-12 04:27:35,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 64290816. Throughput: 0: 1597.9, 1: 1565.5. Samples: 16079640. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-12 04:27:35,202][77203] Avg episode reward: [(0, '33.090'), (1, '40.720')] -[2023-10-12 04:27:36,200][78091] Updated weights for policy 0, policy_version 31460 (0.0009) -[2023-10-12 04:27:36,572][78091] Updated weights for policy 0, policy_version 31470 (0.0010) -[2023-10-12 04:27:36,945][78091] Updated weights for policy 0, policy_version 31480 (0.0011) -[2023-10-12 04:27:37,810][78123] Updated weights for policy 1, policy_version 31330 (0.0009) -[2023-10-12 04:27:38,169][78123] Updated weights for policy 1, policy_version 31340 (0.0008) -[2023-10-12 04:27:38,542][78123] Updated weights for policy 1, policy_version 31350 (0.0008) -[2023-10-12 04:27:38,910][78123] Updated weights for policy 1, policy_version 31360 (0.0009) -[2023-10-12 04:27:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 64356352. Throughput: 0: 1593.5, 1: 1563.4. Samples: 16099134. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) -[2023-10-12 04:27:40,202][77203] Avg episode reward: [(0, '34.820'), (1, '40.090')] -[2023-10-12 04:27:41,185][78091] Updated weights for policy 0, policy_version 31490 (0.0009) -[2023-10-12 04:27:41,550][78091] Updated weights for policy 0, policy_version 31500 (0.0007) -[2023-10-12 04:27:41,923][78091] Updated weights for policy 0, policy_version 31510 (0.0010) -[2023-10-12 04:27:42,296][78091] Updated weights for policy 0, policy_version 31520 (0.0008) -[2023-10-12 04:27:43,366][78123] Updated weights for policy 1, policy_version 31370 (0.0008) -[2023-10-12 04:27:43,730][78123] Updated weights for policy 1, policy_version 31380 (0.0008) -[2023-10-12 04:27:44,086][78123] Updated weights for policy 1, policy_version 31390 (0.0009) -[2023-10-12 04:27:45,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 64421888. Throughput: 0: 1594.0, 1: 1593.1. Samples: 16108956. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) -[2023-10-12 04:27:45,202][77203] Avg episode reward: [(0, '36.930'), (1, '40.600')] -[2023-10-12 04:27:46,545][78091] Updated weights for policy 0, policy_version 31530 (0.0010) -[2023-10-12 04:27:46,918][78091] Updated weights for policy 0, policy_version 31540 (0.0007) -[2023-10-12 04:27:47,280][78091] Updated weights for policy 0, policy_version 31550 (0.0009) -[2023-10-12 04:27:48,398][78123] Updated weights for policy 1, policy_version 31400 (0.0008) -[2023-10-12 04:27:48,759][78123] Updated weights for policy 1, policy_version 31410 (0.0009) -[2023-10-12 04:27:49,128][78123] Updated weights for policy 1, policy_version 31420 (0.0009) -[2023-10-12 04:27:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 64487424. Throughput: 0: 1601.6, 1: 1583.4. Samples: 16127876. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) -[2023-10-12 04:27:50,201][77203] Avg episode reward: [(0, '38.640'), (1, '42.960')] -[2023-10-12 04:27:51,729][78091] Updated weights for policy 0, policy_version 31560 (0.0007) -[2023-10-12 04:27:52,094][78091] Updated weights for policy 0, policy_version 31570 (0.0007) -[2023-10-12 04:27:52,453][78091] Updated weights for policy 0, policy_version 31580 (0.0009) -[2023-10-12 04:27:53,530][78123] Updated weights for policy 1, policy_version 31430 (0.0010) -[2023-10-12 04:27:53,892][78123] Updated weights for policy 1, policy_version 31440 (0.0009) -[2023-10-12 04:27:54,255][78123] Updated weights for policy 1, policy_version 31450 (0.0010) -[2023-10-12 04:27:55,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 64552960. Throughput: 0: 1597.2, 1: 1576.7. Samples: 16146710. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) -[2023-10-12 04:27:55,202][77203] Avg episode reward: [(0, '38.780'), (1, '40.120')] -[2023-10-12 04:27:56,927][78091] Updated weights for policy 0, policy_version 31590 (0.0011) -[2023-10-12 04:27:57,294][78091] Updated weights for policy 0, policy_version 31600 (0.0011) -[2023-10-12 04:27:57,669][78091] Updated weights for policy 0, policy_version 31610 (0.0008) -[2023-10-12 04:27:58,550][78123] Updated weights for policy 1, policy_version 31460 (0.0009) -[2023-10-12 04:27:58,923][78123] Updated weights for policy 1, policy_version 31470 (0.0010) -[2023-10-12 04:27:59,282][78123] Updated weights for policy 1, policy_version 31480 (0.0009) -[2023-10-12 04:28:00,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 12885.0). Total num frames: 64618496. Throughput: 0: 1597.4, 1: 1599.3. Samples: 16156750. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) -[2023-10-12 04:28:00,202][77203] Avg episode reward: [(0, '36.680'), (1, '41.280')] -[2023-10-12 04:28:01,890][78091] Updated weights for policy 0, policy_version 31620 (0.0009) -[2023-10-12 04:28:02,261][78091] Updated weights for policy 0, policy_version 31630 (0.0008) -[2023-10-12 04:28:02,644][78091] Updated weights for policy 0, policy_version 31640 (0.0010) -[2023-10-12 04:28:03,492][78123] Updated weights for policy 1, policy_version 31490 (0.0008) -[2023-10-12 04:28:03,860][78123] Updated weights for policy 1, policy_version 31500 (0.0008) -[2023-10-12 04:28:04,228][78123] Updated weights for policy 1, policy_version 31510 (0.0009) -[2023-10-12 04:28:04,597][78123] Updated weights for policy 1, policy_version 31520 (0.0009) -[2023-10-12 04:28:05,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.1, 300 sec: 12885.0). Total num frames: 64684032. Throughput: 0: 1589.0, 1: 1606.5. Samples: 16175968. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 04:28:05,202][77203] Avg episode reward: [(0, '45.500'), (1, '42.820')] -[2023-10-12 04:28:06,923][78091] Updated weights for policy 0, policy_version 31650 (0.0007) -[2023-10-12 04:28:07,297][78091] Updated weights for policy 0, policy_version 31660 (0.0009) -[2023-10-12 04:28:07,667][78091] Updated weights for policy 0, policy_version 31670 (0.0008) -[2023-10-12 04:28:08,037][78091] Updated weights for policy 0, policy_version 31680 (0.0008) -[2023-10-12 04:28:08,867][78123] Updated weights for policy 1, policy_version 31530 (0.0009) -[2023-10-12 04:28:09,239][78123] Updated weights for policy 1, policy_version 31540 (0.0009) -[2023-10-12 04:28:09,610][78123] Updated weights for policy 1, policy_version 31550 (0.0008) -[2023-10-12 04:28:10,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 64749568. Throughput: 0: 1594.8, 1: 1590.6. Samples: 16194866. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 04:28:10,202][77203] Avg episode reward: [(0, '38.460'), (1, '42.900')] -[2023-10-12 04:28:12,259][78091] Updated weights for policy 0, policy_version 31690 (0.0009) -[2023-10-12 04:28:12,629][78091] Updated weights for policy 0, policy_version 31700 (0.0010) -[2023-10-12 04:28:12,999][78091] Updated weights for policy 0, policy_version 31710 (0.0008) -[2023-10-12 04:28:14,032][78123] Updated weights for policy 1, policy_version 31560 (0.0009) -[2023-10-12 04:28:14,404][78123] Updated weights for policy 1, policy_version 31570 (0.0010) -[2023-10-12 04:28:14,772][78123] Updated weights for policy 1, policy_version 31580 (0.0010) -[2023-10-12 04:28:15,201][77203] Fps is (10 sec: 13107.7, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 64815104. Throughput: 0: 1603.4, 1: 1595.8. Samples: 16204962. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 04:28:15,201][77203] Avg episode reward: [(0, '37.670'), (1, '41.620')] -[2023-10-12 04:28:17,425][78091] Updated weights for policy 0, policy_version 31720 (0.0008) -[2023-10-12 04:28:17,795][78091] Updated weights for policy 0, policy_version 31730 (0.0008) -[2023-10-12 04:28:18,158][78091] Updated weights for policy 0, policy_version 31740 (0.0008) -[2023-10-12 04:28:19,221][78123] Updated weights for policy 1, policy_version 31590 (0.0009) -[2023-10-12 04:28:19,591][78123] Updated weights for policy 1, policy_version 31600 (0.0009) -[2023-10-12 04:28:19,959][78123] Updated weights for policy 1, policy_version 31610 (0.0007) -[2023-10-12 04:28:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 64880640. Throughput: 0: 1593.7, 1: 1609.3. Samples: 16223776. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 04:28:20,201][77203] Avg episode reward: [(0, '40.610'), (1, '38.240')] -[2023-10-12 04:28:22,306][78091] Updated weights for policy 0, policy_version 31750 (0.0009) -[2023-10-12 04:28:22,678][78091] Updated weights for policy 0, policy_version 31760 (0.0009) -[2023-10-12 04:28:23,056][78091] Updated weights for policy 0, policy_version 31770 (0.0007) -[2023-10-12 04:28:24,306][78123] Updated weights for policy 1, policy_version 31620 (0.0008) -[2023-10-12 04:28:24,678][78123] Updated weights for policy 1, policy_version 31630 (0.0009) -[2023-10-12 04:28:25,049][78123] Updated weights for policy 1, policy_version 31640 (0.0008) -[2023-10-12 04:28:25,201][77203] Fps is (10 sec: 9830.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 64913408. Throughput: 0: 1595.8, 1: 1600.1. Samples: 16242948. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 04:28:25,202][77203] Avg episode reward: [(0, '40.100'), (1, '41.560')] -[2023-10-12 04:28:27,219][78091] Updated weights for policy 0, policy_version 31780 (0.0008) -[2023-10-12 04:28:27,587][78091] Updated weights for policy 0, policy_version 31790 (0.0008) -[2023-10-12 04:28:27,946][78091] Updated weights for policy 0, policy_version 31800 (0.0009) -[2023-10-12 04:28:29,409][78123] Updated weights for policy 1, policy_version 31650 (0.0007) -[2023-10-12 04:28:29,777][78123] Updated weights for policy 1, policy_version 31660 (0.0007) -[2023-10-12 04:28:30,148][78123] Updated weights for policy 1, policy_version 31670 (0.0008) -[2023-10-12 04:28:30,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 64978944. Throughput: 0: 1607.9, 1: 1584.6. Samples: 16252620. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:28:30,201][77203] Avg episode reward: [(0, '36.560'), (1, '44.680')] -[2023-10-12 04:28:30,520][78123] Updated weights for policy 1, policy_version 31680 (0.0010) -[2023-10-12 04:28:32,221][78091] Updated weights for policy 0, policy_version 31810 (0.0008) -[2023-10-12 04:28:32,596][78091] Updated weights for policy 0, policy_version 31820 (0.0008) -[2023-10-12 04:28:32,964][78091] Updated weights for policy 0, policy_version 31830 (0.0010) -[2023-10-12 04:28:33,334][78091] Updated weights for policy 0, policy_version 31840 (0.0008) -[2023-10-12 04:28:35,012][78123] Updated weights for policy 1, policy_version 31690 (0.0008) -[2023-10-12 04:28:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 65044480. Throughput: 0: 1599.2, 1: 1598.1. Samples: 16271756. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:28:35,202][77203] Avg episode reward: [(0, '40.780'), (1, '39.390')] -[2023-10-12 04:28:35,382][78123] Updated weights for policy 1, policy_version 31700 (0.0008) -[2023-10-12 04:28:35,748][78123] Updated weights for policy 1, policy_version 31710 (0.0008) -[2023-10-12 04:28:37,679][78091] Updated weights for policy 0, policy_version 31850 (0.0010) -[2023-10-12 04:28:38,049][78091] Updated weights for policy 0, policy_version 31860 (0.0010) -[2023-10-12 04:28:38,421][78091] Updated weights for policy 0, policy_version 31870 (0.0007) -[2023-10-12 04:28:39,942][78123] Updated weights for policy 1, policy_version 31720 (0.0009) -[2023-10-12 04:28:40,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 65110016. Throughput: 0: 1602.3, 1: 1610.9. Samples: 16291302. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:28:40,201][77203] Avg episode reward: [(0, '42.220'), (1, '39.770')] -[2023-10-12 04:28:40,321][78123] Updated weights for policy 1, policy_version 31730 (0.0010) -[2023-10-12 04:28:40,690][78123] Updated weights for policy 1, policy_version 31740 (0.0008) -[2023-10-12 04:28:42,721][78091] Updated weights for policy 0, policy_version 31880 (0.0007) -[2023-10-12 04:28:43,086][78091] Updated weights for policy 0, policy_version 31890 (0.0007) -[2023-10-12 04:28:43,461][78091] Updated weights for policy 0, policy_version 31900 (0.0008) -[2023-10-12 04:28:45,157][78123] Updated weights for policy 1, policy_version 31750 (0.0009) -[2023-10-12 04:28:45,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 65175552. Throughput: 0: 1623.1, 1: 1580.2. Samples: 16300896. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:28:45,201][77203] Avg episode reward: [(0, '40.320'), (1, '44.310')] -[2023-10-12 04:28:45,528][78123] Updated weights for policy 1, policy_version 31760 (0.0008) -[2023-10-12 04:28:45,893][78123] Updated weights for policy 1, policy_version 31770 (0.0007) -[2023-10-12 04:28:47,498][78091] Updated weights for policy 0, policy_version 31910 (0.0009) -[2023-10-12 04:28:47,870][78091] Updated weights for policy 0, policy_version 31920 (0.0007) -[2023-10-12 04:28:48,241][78091] Updated weights for policy 0, policy_version 31930 (0.0008) -[2023-10-12 04:28:50,157][78123] Updated weights for policy 1, policy_version 31780 (0.0010) -[2023-10-12 04:28:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 65241088. Throughput: 0: 1612.1, 1: 1585.7. Samples: 16319868. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:28:50,201][77203] Avg episode reward: [(0, '38.620'), (1, '37.710')] -[2023-10-12 04:28:50,527][78123] Updated weights for policy 1, policy_version 31790 (0.0008) -[2023-10-12 04:28:50,896][78123] Updated weights for policy 1, policy_version 31800 (0.0007) -[2023-10-12 04:28:52,435][78091] Updated weights for policy 0, policy_version 31940 (0.0008) -[2023-10-12 04:28:52,804][78091] Updated weights for policy 0, policy_version 31950 (0.0009) -[2023-10-12 04:28:53,173][78091] Updated weights for policy 0, policy_version 31960 (0.0008) -[2023-10-12 04:28:55,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 65306624. Throughput: 0: 1612.9, 1: 1603.4. Samples: 16339598. Policy #0 lag: (min: 6.0, avg: 16.0, max: 38.0) -[2023-10-12 04:28:55,201][77203] Avg episode reward: [(0, '38.500'), (1, '37.360')] -[2023-10-12 04:28:55,249][78123] Updated weights for policy 1, policy_version 31810 (0.0009) -[2023-10-12 04:28:55,618][78123] Updated weights for policy 1, policy_version 31820 (0.0007) -[2023-10-12 04:28:55,984][78123] Updated weights for policy 1, policy_version 31830 (0.0009) -[2023-10-12 04:28:56,351][78123] Updated weights for policy 1, policy_version 31840 (0.0010) -[2023-10-12 04:28:57,389][78091] Updated weights for policy 0, policy_version 31970 (0.0008) -[2023-10-12 04:28:57,761][78091] Updated weights for policy 0, policy_version 31980 (0.0007) -[2023-10-12 04:28:58,123][78091] Updated weights for policy 0, policy_version 31990 (0.0007) -[2023-10-12 04:28:58,485][78091] Updated weights for policy 0, policy_version 32000 (0.0007) -[2023-10-12 04:29:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 65372160. Throughput: 0: 1621.2, 1: 1577.8. Samples: 16348918. Policy #0 lag: (min: 6.0, avg: 16.0, max: 38.0) -[2023-10-12 04:29:00,201][77203] Avg episode reward: [(0, '32.780'), (1, '45.130')] -[2023-10-12 04:29:00,672][78123] Updated weights for policy 1, policy_version 31850 (0.0010) -[2023-10-12 04:29:01,042][78123] Updated weights for policy 1, policy_version 31860 (0.0007) -[2023-10-12 04:29:01,411][78123] Updated weights for policy 1, policy_version 31870 (0.0007) -[2023-10-12 04:29:02,876][78091] Updated weights for policy 0, policy_version 32010 (0.0010) -[2023-10-12 04:29:03,248][78091] Updated weights for policy 0, policy_version 32020 (0.0009) -[2023-10-12 04:29:03,614][78091] Updated weights for policy 0, policy_version 32030 (0.0010) -[2023-10-12 04:29:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.2, 300 sec: 12774.0). Total num frames: 65437696. Throughput: 0: 1613.1, 1: 1582.1. Samples: 16367560. Policy #0 lag: (min: 6.0, avg: 16.0, max: 38.0) -[2023-10-12 04:29:05,201][77203] Avg episode reward: [(0, '30.830'), (1, '35.020')] -[2023-10-12 04:29:05,703][78123] Updated weights for policy 1, policy_version 31880 (0.0008) -[2023-10-12 04:29:06,066][78123] Updated weights for policy 1, policy_version 31890 (0.0010) -[2023-10-12 04:29:06,441][78123] Updated weights for policy 1, policy_version 31900 (0.0009) -[2023-10-12 04:29:08,020][78091] Updated weights for policy 0, policy_version 32040 (0.0007) -[2023-10-12 04:29:08,398][78091] Updated weights for policy 0, policy_version 32050 (0.0007) -[2023-10-12 04:29:08,778][78091] Updated weights for policy 0, policy_version 32060 (0.0009) -[2023-10-12 04:29:10,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 65503232. Throughput: 0: 1607.4, 1: 1591.0. Samples: 16386874. Policy #0 lag: (min: 6.0, avg: 16.0, max: 38.0) -[2023-10-12 04:29:10,202][77203] Avg episode reward: [(0, '32.610'), (1, '37.680')] -[2023-10-12 04:29:10,209][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000031904_32669696.pth... -[2023-10-12 04:29:10,209][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000032064_32833536.pth... -[2023-10-12 04:29:10,258][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000030560_31293440.pth -[2023-10-12 04:29:10,259][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000030432_31162368.pth -[2023-10-12 04:29:11,005][78123] Updated weights for policy 1, policy_version 31910 (0.0007) -[2023-10-12 04:29:11,378][78123] Updated weights for policy 1, policy_version 31920 (0.0008) -[2023-10-12 04:29:11,740][78123] Updated weights for policy 1, policy_version 31930 (0.0007) -[2023-10-12 04:29:13,109][78091] Updated weights for policy 0, policy_version 32070 (0.0008) -[2023-10-12 04:29:13,490][78091] Updated weights for policy 0, policy_version 32080 (0.0009) -[2023-10-12 04:29:13,864][78091] Updated weights for policy 0, policy_version 32090 (0.0009) -[2023-10-12 04:29:15,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 65568768. Throughput: 0: 1621.2, 1: 1579.4. Samples: 16396646. Policy #0 lag: (min: 6.0, avg: 16.0, max: 38.0) -[2023-10-12 04:29:15,202][77203] Avg episode reward: [(0, '33.180'), (1, '41.730')] -[2023-10-12 04:29:15,936][78123] Updated weights for policy 1, policy_version 31940 (0.0009) -[2023-10-12 04:29:16,292][78123] Updated weights for policy 1, policy_version 31950 (0.0009) -[2023-10-12 04:29:16,663][78123] Updated weights for policy 1, policy_version 31960 (0.0009) -[2023-10-12 04:29:18,133][78091] Updated weights for policy 0, policy_version 32100 (0.0008) -[2023-10-12 04:29:18,498][78091] Updated weights for policy 0, policy_version 32110 (0.0008) -[2023-10-12 04:29:18,868][78091] Updated weights for policy 0, policy_version 32120 (0.0009) -[2023-10-12 04:29:20,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 65634304. Throughput: 0: 1614.0, 1: 1581.6. Samples: 16415554. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-12 04:29:20,201][77203] Avg episode reward: [(0, '35.570'), (1, '37.460')] -[2023-10-12 04:29:21,012][78123] Updated weights for policy 1, policy_version 31970 (0.0009) -[2023-10-12 04:29:21,385][78123] Updated weights for policy 1, policy_version 31980 (0.0011) -[2023-10-12 04:29:21,748][78123] Updated weights for policy 1, policy_version 31990 (0.0007) -[2023-10-12 04:29:22,124][78123] Updated weights for policy 1, policy_version 32000 (0.0010) -[2023-10-12 04:29:23,256][78091] Updated weights for policy 0, policy_version 32130 (0.0009) -[2023-10-12 04:29:23,628][78091] Updated weights for policy 0, policy_version 32140 (0.0008) -[2023-10-12 04:29:23,996][78091] Updated weights for policy 0, policy_version 32150 (0.0010) -[2023-10-12 04:29:24,369][78091] Updated weights for policy 0, policy_version 32160 (0.0008) -[2023-10-12 04:29:25,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 65699840. Throughput: 0: 1602.0, 1: 1584.8. Samples: 16434710. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-12 04:29:25,202][77203] Avg episode reward: [(0, '33.640'), (1, '39.670')] -[2023-10-12 04:29:26,376][78123] Updated weights for policy 1, policy_version 32010 (0.0009) -[2023-10-12 04:29:26,744][78123] Updated weights for policy 1, policy_version 32020 (0.0009) -[2023-10-12 04:29:27,110][78123] Updated weights for policy 1, policy_version 32030 (0.0011) -[2023-10-12 04:29:28,659][78091] Updated weights for policy 0, policy_version 32170 (0.0008) -[2023-10-12 04:29:29,036][78091] Updated weights for policy 0, policy_version 32180 (0.0008) -[2023-10-12 04:29:29,403][78091] Updated weights for policy 0, policy_version 32190 (0.0007) -[2023-10-12 04:29:30,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 65765376. Throughput: 0: 1607.2, 1: 1584.9. Samples: 16444540. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-12 04:29:30,202][77203] Avg episode reward: [(0, '37.890'), (1, '39.310')] -[2023-10-12 04:29:31,551][78123] Updated weights for policy 1, policy_version 32040 (0.0007) -[2023-10-12 04:29:31,910][78123] Updated weights for policy 1, policy_version 32050 (0.0008) -[2023-10-12 04:29:32,276][78123] Updated weights for policy 1, policy_version 32060 (0.0008) -[2023-10-12 04:29:33,570][78091] Updated weights for policy 0, policy_version 32200 (0.0007) -[2023-10-12 04:29:33,932][78091] Updated weights for policy 0, policy_version 32210 (0.0008) -[2023-10-12 04:29:34,302][78091] Updated weights for policy 0, policy_version 32220 (0.0009) -[2023-10-12 04:29:35,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 65830912. Throughput: 0: 1607.7, 1: 1580.6. Samples: 16463340. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-12 04:29:35,202][77203] Avg episode reward: [(0, '38.200'), (1, '37.010')] -[2023-10-12 04:29:36,607][78123] Updated weights for policy 1, policy_version 32070 (0.0009) -[2023-10-12 04:29:36,983][78123] Updated weights for policy 1, policy_version 32080 (0.0009) -[2023-10-12 04:29:37,355][78123] Updated weights for policy 1, policy_version 32090 (0.0009) -[2023-10-12 04:29:38,822][78091] Updated weights for policy 0, policy_version 32230 (0.0011) -[2023-10-12 04:29:39,189][78091] Updated weights for policy 0, policy_version 32240 (0.0010) -[2023-10-12 04:29:39,570][78091] Updated weights for policy 0, policy_version 32250 (0.0010) -[2023-10-12 04:29:40,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 65896448. Throughput: 0: 1585.7, 1: 1577.3. Samples: 16481934. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-12 04:29:40,202][77203] Avg episode reward: [(0, '37.700'), (1, '38.540')] -[2023-10-12 04:29:41,793][78123] Updated weights for policy 1, policy_version 32100 (0.0009) -[2023-10-12 04:29:42,158][78123] Updated weights for policy 1, policy_version 32110 (0.0008) -[2023-10-12 04:29:42,521][78123] Updated weights for policy 1, policy_version 32120 (0.0007) -[2023-10-12 04:29:43,835][78091] Updated weights for policy 0, policy_version 32260 (0.0009) -[2023-10-12 04:29:44,205][78091] Updated weights for policy 0, policy_version 32270 (0.0008) -[2023-10-12 04:29:44,588][78091] Updated weights for policy 0, policy_version 32280 (0.0007) -[2023-10-12 04:29:45,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 65961984. Throughput: 0: 1595.5, 1: 1581.7. Samples: 16491892. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 04:29:45,201][77203] Avg episode reward: [(0, '39.740'), (1, '32.490')] -[2023-10-12 04:29:46,867][78123] Updated weights for policy 1, policy_version 32130 (0.0009) -[2023-10-12 04:29:47,235][78123] Updated weights for policy 1, policy_version 32140 (0.0007) -[2023-10-12 04:29:47,603][78123] Updated weights for policy 1, policy_version 32150 (0.0009) -[2023-10-12 04:29:47,979][78123] Updated weights for policy 1, policy_version 32160 (0.0009) -[2023-10-12 04:29:48,927][78091] Updated weights for policy 0, policy_version 32290 (0.0007) -[2023-10-12 04:29:49,319][78091] Updated weights for policy 0, policy_version 32300 (0.0008) -[2023-10-12 04:29:49,686][78091] Updated weights for policy 0, policy_version 32310 (0.0009) -[2023-10-12 04:29:50,059][78091] Updated weights for policy 0, policy_version 32320 (0.0009) -[2023-10-12 04:29:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 66027520. Throughput: 0: 1613.9, 1: 1583.4. Samples: 16511438. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 04:29:50,202][77203] Avg episode reward: [(0, '41.540'), (1, '36.730')] -[2023-10-12 04:29:52,320][78123] Updated weights for policy 1, policy_version 32170 (0.0009) -[2023-10-12 04:29:52,683][78123] Updated weights for policy 1, policy_version 32180 (0.0010) -[2023-10-12 04:29:53,056][78123] Updated weights for policy 1, policy_version 32190 (0.0008) -[2023-10-12 04:29:54,310][78091] Updated weights for policy 0, policy_version 32330 (0.0009) -[2023-10-12 04:29:54,677][78091] Updated weights for policy 0, policy_version 32340 (0.0010) -[2023-10-12 04:29:55,048][78091] Updated weights for policy 0, policy_version 32350 (0.0007) -[2023-10-12 04:29:55,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 66093056. Throughput: 0: 1598.9, 1: 1581.1. Samples: 16529972. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 04:29:55,202][77203] Avg episode reward: [(0, '45.480'), (1, '37.360')] -[2023-10-12 04:29:57,441][78123] Updated weights for policy 1, policy_version 32200 (0.0008) -[2023-10-12 04:29:57,806][78123] Updated weights for policy 1, policy_version 32210 (0.0008) -[2023-10-12 04:29:58,177][78123] Updated weights for policy 1, policy_version 32220 (0.0009) -[2023-10-12 04:29:59,227][78091] Updated weights for policy 0, policy_version 32360 (0.0009) -[2023-10-12 04:29:59,596][78091] Updated weights for policy 0, policy_version 32370 (0.0007) -[2023-10-12 04:29:59,977][78091] Updated weights for policy 0, policy_version 32380 (0.0008) -[2023-10-12 04:30:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 66158592. Throughput: 0: 1591.1, 1: 1593.6. Samples: 16539958. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 04:30:00,202][77203] Avg episode reward: [(0, '43.250'), (1, '36.640')] -[2023-10-12 04:30:02,404][78123] Updated weights for policy 1, policy_version 32230 (0.0009) -[2023-10-12 04:30:02,781][78123] Updated weights for policy 1, policy_version 32240 (0.0010) -[2023-10-12 04:30:03,139][78123] Updated weights for policy 1, policy_version 32250 (0.0008) -[2023-10-12 04:30:04,347][78091] Updated weights for policy 0, policy_version 32390 (0.0008) -[2023-10-12 04:30:04,717][78091] Updated weights for policy 0, policy_version 32400 (0.0009) -[2023-10-12 04:30:05,084][78091] Updated weights for policy 0, policy_version 32410 (0.0009) -[2023-10-12 04:30:05,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 66191360. Throughput: 0: 1610.0, 1: 1580.3. Samples: 16559116. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 04:30:05,201][77203] Avg episode reward: [(0, '40.190'), (1, '37.410')] -[2023-10-12 04:30:07,443][78123] Updated weights for policy 1, policy_version 32260 (0.0010) -[2023-10-12 04:30:07,810][78123] Updated weights for policy 1, policy_version 32270 (0.0007) -[2023-10-12 04:30:08,164][78123] Updated weights for policy 1, policy_version 32280 (0.0007) -[2023-10-12 04:30:09,312][78091] Updated weights for policy 0, policy_version 32420 (0.0008) -[2023-10-12 04:30:09,680][78091] Updated weights for policy 0, policy_version 32430 (0.0008) -[2023-10-12 04:30:10,054][78091] Updated weights for policy 0, policy_version 32440 (0.0010) -[2023-10-12 04:30:10,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 66256896. Throughput: 0: 1605.8, 1: 1578.8. Samples: 16578016. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 04:30:10,201][77203] Avg episode reward: [(0, '38.280'), (1, '37.840')] -[2023-10-12 04:30:12,580][78123] Updated weights for policy 1, policy_version 32290 (0.0009) -[2023-10-12 04:30:12,939][78123] Updated weights for policy 1, policy_version 32300 (0.0009) -[2023-10-12 04:30:13,306][78123] Updated weights for policy 1, policy_version 32310 (0.0011) -[2023-10-12 04:30:13,678][78123] Updated weights for policy 1, policy_version 32320 (0.0009) -[2023-10-12 04:30:14,201][78091] Updated weights for policy 0, policy_version 32450 (0.0008) -[2023-10-12 04:30:14,576][78091] Updated weights for policy 0, policy_version 32460 (0.0009) -[2023-10-12 04:30:14,943][78091] Updated weights for policy 0, policy_version 32470 (0.0007) -[2023-10-12 04:30:15,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 66322432. Throughput: 0: 1595.0, 1: 1595.4. Samples: 16588108. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:30:15,202][77203] Avg episode reward: [(0, '39.250'), (1, '39.410')] -[2023-10-12 04:30:15,308][78091] Updated weights for policy 0, policy_version 32480 (0.0007) -[2023-10-12 04:30:18,131][78123] Updated weights for policy 1, policy_version 32330 (0.0009) -[2023-10-12 04:30:18,499][78123] Updated weights for policy 1, policy_version 32340 (0.0009) -[2023-10-12 04:30:18,865][78123] Updated weights for policy 1, policy_version 32350 (0.0009) -[2023-10-12 04:30:19,594][78091] Updated weights for policy 0, policy_version 32490 (0.0008) -[2023-10-12 04:30:19,965][78091] Updated weights for policy 0, policy_version 32500 (0.0011) -[2023-10-12 04:30:20,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 66387968. Throughput: 0: 1612.5, 1: 1583.6. Samples: 16607168. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:30:20,202][77203] Avg episode reward: [(0, '35.920'), (1, '37.070')] -[2023-10-12 04:30:20,343][78091] Updated weights for policy 0, policy_version 32510 (0.0009) -[2023-10-12 04:30:23,255][78123] Updated weights for policy 1, policy_version 32360 (0.0008) -[2023-10-12 04:30:23,621][78123] Updated weights for policy 1, policy_version 32370 (0.0007) -[2023-10-12 04:30:23,989][78123] Updated weights for policy 1, policy_version 32380 (0.0010) -[2023-10-12 04:30:24,811][78091] Updated weights for policy 0, policy_version 32520 (0.0008) -[2023-10-12 04:30:25,182][78091] Updated weights for policy 0, policy_version 32530 (0.0008) -[2023-10-12 04:30:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 66453504. Throughput: 0: 1624.2, 1: 1579.5. Samples: 16626100. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:30:25,202][77203] Avg episode reward: [(0, '35.040'), (1, '36.470')] -[2023-10-12 04:30:25,562][78091] Updated weights for policy 0, policy_version 32540 (0.0007) -[2023-10-12 04:30:28,085][78123] Updated weights for policy 1, policy_version 32390 (0.0008) -[2023-10-12 04:30:28,459][78123] Updated weights for policy 1, policy_version 32400 (0.0010) -[2023-10-12 04:30:28,819][78123] Updated weights for policy 1, policy_version 32410 (0.0010) -[2023-10-12 04:30:29,694][78091] Updated weights for policy 0, policy_version 32550 (0.0010) -[2023-10-12 04:30:30,069][78091] Updated weights for policy 0, policy_version 32560 (0.0011) -[2023-10-12 04:30:30,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 66519040. Throughput: 0: 1603.0, 1: 1606.7. Samples: 16636330. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:30:30,201][77203] Avg episode reward: [(0, '37.050'), (1, '40.530')] -[2023-10-12 04:30:30,437][78091] Updated weights for policy 0, policy_version 32570 (0.0008) -[2023-10-12 04:30:33,266][78123] Updated weights for policy 1, policy_version 32420 (0.0009) -[2023-10-12 04:30:33,637][78123] Updated weights for policy 1, policy_version 32430 (0.0008) -[2023-10-12 04:30:33,998][78123] Updated weights for policy 1, policy_version 32440 (0.0008) -[2023-10-12 04:30:34,964][78091] Updated weights for policy 0, policy_version 32580 (0.0008) -[2023-10-12 04:30:35,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 66584576. Throughput: 0: 1601.9, 1: 1589.6. Samples: 16655056. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:30:35,201][77203] Avg episode reward: [(0, '32.540'), (1, '36.830')] -[2023-10-12 04:30:35,368][78091] Updated weights for policy 0, policy_version 32590 (0.0008) -[2023-10-12 04:30:35,744][78091] Updated weights for policy 0, policy_version 32600 (0.0010) -[2023-10-12 04:30:38,246][78123] Updated weights for policy 1, policy_version 32450 (0.0008) -[2023-10-12 04:30:38,659][78123] Updated weights for policy 1, policy_version 32460 (0.0009) -[2023-10-12 04:30:39,026][78123] Updated weights for policy 1, policy_version 32470 (0.0007) -[2023-10-12 04:30:39,388][78123] Updated weights for policy 1, policy_version 32480 (0.0007) -[2023-10-12 04:30:39,972][78091] Updated weights for policy 0, policy_version 32610 (0.0009) -[2023-10-12 04:30:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 66650112. Throughput: 0: 1616.8, 1: 1584.4. Samples: 16674028. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:30:40,201][77203] Avg episode reward: [(0, '36.870'), (1, '39.880')] -[2023-10-12 04:30:40,345][78091] Updated weights for policy 0, policy_version 32620 (0.0007) -[2023-10-12 04:30:40,717][78091] Updated weights for policy 0, policy_version 32630 (0.0008) -[2023-10-12 04:30:41,079][78091] Updated weights for policy 0, policy_version 32640 (0.0007) -[2023-10-12 04:30:43,752][78123] Updated weights for policy 1, policy_version 32490 (0.0009) -[2023-10-12 04:30:44,122][78123] Updated weights for policy 1, policy_version 32500 (0.0007) -[2023-10-12 04:30:44,498][78123] Updated weights for policy 1, policy_version 32510 (0.0008) -[2023-10-12 04:30:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 66715648. Throughput: 0: 1599.5, 1: 1598.2. Samples: 16683854. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:30:45,201][77203] Avg episode reward: [(0, '38.170'), (1, '39.050')] -[2023-10-12 04:30:45,356][78091] Updated weights for policy 0, policy_version 32650 (0.0007) -[2023-10-12 04:30:45,720][78091] Updated weights for policy 0, policy_version 32660 (0.0007) -[2023-10-12 04:30:46,083][78091] Updated weights for policy 0, policy_version 32670 (0.0008) -[2023-10-12 04:30:48,813][78123] Updated weights for policy 1, policy_version 32520 (0.0009) -[2023-10-12 04:30:49,183][78123] Updated weights for policy 1, policy_version 32530 (0.0010) -[2023-10-12 04:30:49,544][78123] Updated weights for policy 1, policy_version 32540 (0.0008) -[2023-10-12 04:30:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 66781184. Throughput: 0: 1596.2, 1: 1601.9. Samples: 16703030. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:30:50,202][77203] Avg episode reward: [(0, '43.490'), (1, '33.170')] -[2023-10-12 04:30:50,337][78091] Updated weights for policy 0, policy_version 32680 (0.0008) -[2023-10-12 04:30:50,713][78091] Updated weights for policy 0, policy_version 32690 (0.0009) -[2023-10-12 04:30:51,084][78091] Updated weights for policy 0, policy_version 32700 (0.0009) -[2023-10-12 04:30:53,984][78123] Updated weights for policy 1, policy_version 32550 (0.0009) -[2023-10-12 04:30:54,359][78123] Updated weights for policy 1, policy_version 32560 (0.0008) -[2023-10-12 04:30:54,727][78123] Updated weights for policy 1, policy_version 32570 (0.0007) -[2023-10-12 04:30:55,201][77203] Fps is (10 sec: 13106.7, 60 sec: 12561.0, 300 sec: 12773.9). Total num frames: 66846720. Throughput: 0: 1609.6, 1: 1585.6. Samples: 16721802. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:30:55,203][77203] Avg episode reward: [(0, '37.650'), (1, '38.680')] -[2023-10-12 04:30:55,425][78091] Updated weights for policy 0, policy_version 32710 (0.0008) -[2023-10-12 04:30:55,800][78091] Updated weights for policy 0, policy_version 32720 (0.0008) -[2023-10-12 04:30:56,184][78091] Updated weights for policy 0, policy_version 32730 (0.0010) -[2023-10-12 04:30:59,176][78123] Updated weights for policy 1, policy_version 32580 (0.0007) -[2023-10-12 04:30:59,533][78123] Updated weights for policy 1, policy_version 32590 (0.0009) -[2023-10-12 04:30:59,901][78123] Updated weights for policy 1, policy_version 32600 (0.0008) -[2023-10-12 04:31:00,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 66879488. Throughput: 0: 1593.4, 1: 1591.2. Samples: 16731412. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:31:00,202][77203] Avg episode reward: [(0, '45.240'), (1, '36.030')] -[2023-10-12 04:31:00,484][78091] Updated weights for policy 0, policy_version 32740 (0.0008) -[2023-10-12 04:31:00,845][78091] Updated weights for policy 0, policy_version 32750 (0.0007) -[2023-10-12 04:31:01,213][78091] Updated weights for policy 0, policy_version 32760 (0.0008) -[2023-10-12 04:31:04,411][78123] Updated weights for policy 1, policy_version 32610 (0.0009) -[2023-10-12 04:31:04,781][78123] Updated weights for policy 1, policy_version 32620 (0.0009) -[2023-10-12 04:31:05,154][78123] Updated weights for policy 1, policy_version 32630 (0.0008) -[2023-10-12 04:31:05,201][77203] Fps is (10 sec: 9830.7, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 66945024. Throughput: 0: 1586.0, 1: 1604.6. Samples: 16750746. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-12 04:31:05,202][77203] Avg episode reward: [(0, '38.150'), (1, '35.250')] -[2023-10-12 04:31:05,517][78123] Updated weights for policy 1, policy_version 32640 (0.0008) -[2023-10-12 04:31:05,663][78091] Updated weights for policy 0, policy_version 32770 (0.0008) -[2023-10-12 04:31:06,029][78091] Updated weights for policy 0, policy_version 32780 (0.0009) -[2023-10-12 04:31:06,403][78091] Updated weights for policy 0, policy_version 32790 (0.0008) -[2023-10-12 04:31:06,770][78091] Updated weights for policy 0, policy_version 32800 (0.0008) -[2023-10-12 04:31:09,902][78123] Updated weights for policy 1, policy_version 32650 (0.0008) -[2023-10-12 04:31:10,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 67010560. Throughput: 0: 1598.6, 1: 1602.8. Samples: 16770160. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-12 04:31:10,202][77203] Avg episode reward: [(0, '39.880'), (1, '41.080')] -[2023-10-12 04:31:10,213][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000032800_33587200.pth... -[2023-10-12 04:31:10,251][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000031296_32047104.pth -[2023-10-12 04:31:10,260][78123] Updated weights for policy 1, policy_version 32660 (0.0009) -[2023-10-12 04:31:10,627][78123] Updated weights for policy 1, policy_version 32670 (0.0008) -[2023-10-12 04:31:10,696][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000032672_33456128.pth... -[2023-10-12 04:31:10,725][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000031168_31916032.pth -[2023-10-12 04:31:11,032][78091] Updated weights for policy 0, policy_version 32810 (0.0010) -[2023-10-12 04:31:11,409][78091] Updated weights for policy 0, policy_version 32820 (0.0010) -[2023-10-12 04:31:11,786][78091] Updated weights for policy 0, policy_version 32830 (0.0010) -[2023-10-12 04:31:14,798][78123] Updated weights for policy 1, policy_version 32680 (0.0009) -[2023-10-12 04:31:15,170][78123] Updated weights for policy 1, policy_version 32690 (0.0009) -[2023-10-12 04:31:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 67076096. Throughput: 0: 1595.9, 1: 1575.8. Samples: 16779056. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-12 04:31:15,201][77203] Avg episode reward: [(0, '37.750'), (1, '38.010')] -[2023-10-12 04:31:15,534][78123] Updated weights for policy 1, policy_version 32700 (0.0008) -[2023-10-12 04:31:15,971][78091] Updated weights for policy 0, policy_version 32840 (0.0009) -[2023-10-12 04:31:16,337][78091] Updated weights for policy 0, policy_version 32850 (0.0007) -[2023-10-12 04:31:16,703][78091] Updated weights for policy 0, policy_version 32860 (0.0008) -[2023-10-12 04:31:20,097][78123] Updated weights for policy 1, policy_version 32710 (0.0010) -[2023-10-12 04:31:20,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 67141632. Throughput: 0: 1591.6, 1: 1590.2. Samples: 16798238. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-12 04:31:20,202][77203] Avg episode reward: [(0, '34.090'), (1, '37.140')] -[2023-10-12 04:31:20,457][78123] Updated weights for policy 1, policy_version 32720 (0.0010) -[2023-10-12 04:31:20,829][78123] Updated weights for policy 1, policy_version 32730 (0.0007) -[2023-10-12 04:31:21,247][78091] Updated weights for policy 0, policy_version 32870 (0.0009) -[2023-10-12 04:31:21,631][78091] Updated weights for policy 0, policy_version 32880 (0.0008) -[2023-10-12 04:31:22,006][78091] Updated weights for policy 0, policy_version 32890 (0.0007) -[2023-10-12 04:31:25,151][78123] Updated weights for policy 1, policy_version 32740 (0.0009) -[2023-10-12 04:31:25,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 67207168. Throughput: 0: 1588.4, 1: 1596.2. Samples: 16817334. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-12 04:31:25,201][77203] Avg episode reward: [(0, '34.480'), (1, '41.150')] -[2023-10-12 04:31:25,515][78123] Updated weights for policy 1, policy_version 32750 (0.0008) -[2023-10-12 04:31:25,889][78123] Updated weights for policy 1, policy_version 32760 (0.0007) -[2023-10-12 04:31:26,297][78091] Updated weights for policy 0, policy_version 32900 (0.0008) -[2023-10-12 04:31:26,674][78091] Updated weights for policy 0, policy_version 32910 (0.0009) -[2023-10-12 04:31:27,040][78091] Updated weights for policy 0, policy_version 32920 (0.0008) -[2023-10-12 04:31:30,097][78123] Updated weights for policy 1, policy_version 32770 (0.0007) -[2023-10-12 04:31:30,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 67272704. Throughput: 0: 1587.6, 1: 1570.5. Samples: 16825966. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-12 04:31:30,201][77203] Avg episode reward: [(0, '41.900'), (1, '39.970')] -[2023-10-12 04:31:30,467][78123] Updated weights for policy 1, policy_version 32780 (0.0009) -[2023-10-12 04:31:30,843][78123] Updated weights for policy 1, policy_version 32790 (0.0008) -[2023-10-12 04:31:31,209][78123] Updated weights for policy 1, policy_version 32800 (0.0010) -[2023-10-12 04:31:31,533][78091] Updated weights for policy 0, policy_version 32930 (0.0008) -[2023-10-12 04:31:31,911][78091] Updated weights for policy 0, policy_version 32940 (0.0007) -[2023-10-12 04:31:32,279][78091] Updated weights for policy 0, policy_version 32950 (0.0009) -[2023-10-12 04:31:32,655][78091] Updated weights for policy 0, policy_version 32960 (0.0007) -[2023-10-12 04:31:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 67338240. Throughput: 0: 1586.0, 1: 1580.7. Samples: 16845530. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-12 04:31:35,201][77203] Avg episode reward: [(0, '38.130'), (1, '37.260')] -[2023-10-12 04:31:35,582][78123] Updated weights for policy 1, policy_version 32810 (0.0007) -[2023-10-12 04:31:35,955][78123] Updated weights for policy 1, policy_version 32820 (0.0011) -[2023-10-12 04:31:36,319][78123] Updated weights for policy 1, policy_version 32830 (0.0010) -[2023-10-12 04:31:36,886][78091] Updated weights for policy 0, policy_version 32970 (0.0008) -[2023-10-12 04:31:37,265][78091] Updated weights for policy 0, policy_version 32980 (0.0009) -[2023-10-12 04:31:37,632][78091] Updated weights for policy 0, policy_version 32990 (0.0008) -[2023-10-12 04:31:40,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 67403776. Throughput: 0: 1590.3, 1: 1594.6. Samples: 16865120. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-12 04:31:40,202][77203] Avg episode reward: [(0, '39.450'), (1, '38.800')] -[2023-10-12 04:31:40,620][78123] Updated weights for policy 1, policy_version 32840 (0.0007) -[2023-10-12 04:31:40,999][78123] Updated weights for policy 1, policy_version 32850 (0.0007) -[2023-10-12 04:31:41,369][78123] Updated weights for policy 1, policy_version 32860 (0.0009) -[2023-10-12 04:31:41,684][78091] Updated weights for policy 0, policy_version 33000 (0.0007) -[2023-10-12 04:31:42,053][78091] Updated weights for policy 0, policy_version 33010 (0.0008) -[2023-10-12 04:31:42,421][78091] Updated weights for policy 0, policy_version 33020 (0.0011) -[2023-10-12 04:31:45,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 67469312. Throughput: 0: 1588.4, 1: 1573.7. Samples: 16873710. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-12 04:31:45,202][77203] Avg episode reward: [(0, '44.300'), (1, '43.060')] -[2023-10-12 04:31:45,671][78123] Updated weights for policy 1, policy_version 32870 (0.0007) -[2023-10-12 04:31:46,050][78123] Updated weights for policy 1, policy_version 32880 (0.0011) -[2023-10-12 04:31:46,420][78123] Updated weights for policy 1, policy_version 32890 (0.0010) -[2023-10-12 04:31:46,955][78091] Updated weights for policy 0, policy_version 33030 (0.0008) -[2023-10-12 04:31:47,328][78091] Updated weights for policy 0, policy_version 33040 (0.0009) -[2023-10-12 04:31:47,692][78091] Updated weights for policy 0, policy_version 33050 (0.0008) -[2023-10-12 04:31:50,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 67534848. Throughput: 0: 1586.6, 1: 1575.4. Samples: 16893038. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-12 04:31:50,202][77203] Avg episode reward: [(0, '36.530'), (1, '41.430')] -[2023-10-12 04:31:50,875][78123] Updated weights for policy 1, policy_version 32900 (0.0008) -[2023-10-12 04:31:51,232][78123] Updated weights for policy 1, policy_version 32910 (0.0009) -[2023-10-12 04:31:51,595][78123] Updated weights for policy 1, policy_version 32920 (0.0009) -[2023-10-12 04:31:52,098][78091] Updated weights for policy 0, policy_version 33060 (0.0009) -[2023-10-12 04:31:52,473][78091] Updated weights for policy 0, policy_version 33070 (0.0009) -[2023-10-12 04:31:52,839][78091] Updated weights for policy 0, policy_version 33080 (0.0010) -[2023-10-12 04:31:55,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 67600384. Throughput: 0: 1578.3, 1: 1580.4. Samples: 16912298. Policy #0 lag: (min: 17.0, avg: 45.8, max: 48.0) -[2023-10-12 04:31:55,202][77203] Avg episode reward: [(0, '33.920'), (1, '36.800')] -[2023-10-12 04:31:55,966][78123] Updated weights for policy 1, policy_version 32930 (0.0010) -[2023-10-12 04:31:56,343][78123] Updated weights for policy 1, policy_version 32940 (0.0008) -[2023-10-12 04:31:56,702][78123] Updated weights for policy 1, policy_version 32950 (0.0008) -[2023-10-12 04:31:57,067][78123] Updated weights for policy 1, policy_version 32960 (0.0009) -[2023-10-12 04:31:57,079][78091] Updated weights for policy 0, policy_version 33090 (0.0010) -[2023-10-12 04:31:57,448][78091] Updated weights for policy 0, policy_version 33100 (0.0008) -[2023-10-12 04:31:57,813][78091] Updated weights for policy 0, policy_version 33110 (0.0007) -[2023-10-12 04:31:58,192][78091] Updated weights for policy 0, policy_version 33120 (0.0007) -[2023-10-12 04:32:00,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 67665920. Throughput: 0: 1587.0, 1: 1576.4. Samples: 16921412. Policy #0 lag: (min: 17.0, avg: 45.8, max: 48.0) -[2023-10-12 04:32:00,201][77203] Avg episode reward: [(0, '39.000'), (1, '42.090')] -[2023-10-12 04:32:01,475][78123] Updated weights for policy 1, policy_version 32970 (0.0008) -[2023-10-12 04:32:01,839][78123] Updated weights for policy 1, policy_version 32980 (0.0009) -[2023-10-12 04:32:02,218][78123] Updated weights for policy 1, policy_version 32990 (0.0010) -[2023-10-12 04:32:02,440][78091] Updated weights for policy 0, policy_version 33130 (0.0009) -[2023-10-12 04:32:02,820][78091] Updated weights for policy 0, policy_version 33140 (0.0008) -[2023-10-12 04:32:03,190][78091] Updated weights for policy 0, policy_version 33150 (0.0008) -[2023-10-12 04:32:05,201][77203] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 67731456. Throughput: 0: 1584.5, 1: 1581.6. Samples: 16940710. Policy #0 lag: (min: 17.0, avg: 45.8, max: 48.0) -[2023-10-12 04:32:05,201][77203] Avg episode reward: [(0, '37.950'), (1, '37.450')] -[2023-10-12 04:32:06,434][78123] Updated weights for policy 1, policy_version 33000 (0.0008) -[2023-10-12 04:32:06,804][78123] Updated weights for policy 1, policy_version 33010 (0.0009) -[2023-10-12 04:32:07,171][78123] Updated weights for policy 1, policy_version 33020 (0.0009) -[2023-10-12 04:32:07,537][78091] Updated weights for policy 0, policy_version 33160 (0.0009) -[2023-10-12 04:32:07,919][78091] Updated weights for policy 0, policy_version 33170 (0.0010) -[2023-10-12 04:32:08,292][78091] Updated weights for policy 0, policy_version 33180 (0.0010) -[2023-10-12 04:32:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.3, 300 sec: 12774.0). Total num frames: 67796992. Throughput: 0: 1588.0, 1: 1588.4. Samples: 16960274. Policy #0 lag: (min: 17.0, avg: 45.8, max: 48.0) -[2023-10-12 04:32:10,202][77203] Avg episode reward: [(0, '37.170'), (1, '34.530')] -[2023-10-12 04:32:11,557][78123] Updated weights for policy 1, policy_version 33030 (0.0009) -[2023-10-12 04:32:11,938][78123] Updated weights for policy 1, policy_version 33040 (0.0009) -[2023-10-12 04:32:12,300][78123] Updated weights for policy 1, policy_version 33050 (0.0010) -[2023-10-12 04:32:12,695][78091] Updated weights for policy 0, policy_version 33190 (0.0009) -[2023-10-12 04:32:13,062][78091] Updated weights for policy 0, policy_version 33200 (0.0010) -[2023-10-12 04:32:13,437][78091] Updated weights for policy 0, policy_version 33210 (0.0009) -[2023-10-12 04:32:15,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 67862528. Throughput: 0: 1608.9, 1: 1585.7. Samples: 16969726. Policy #0 lag: (min: 17.0, avg: 45.8, max: 48.0) -[2023-10-12 04:32:15,202][77203] Avg episode reward: [(0, '42.140'), (1, '38.210')] -[2023-10-12 04:32:16,571][78123] Updated weights for policy 1, policy_version 33060 (0.0009) -[2023-10-12 04:32:16,938][78123] Updated weights for policy 1, policy_version 33070 (0.0010) -[2023-10-12 04:32:17,306][78123] Updated weights for policy 1, policy_version 33080 (0.0008) -[2023-10-12 04:32:17,701][78091] Updated weights for policy 0, policy_version 33220 (0.0007) -[2023-10-12 04:32:18,073][78091] Updated weights for policy 0, policy_version 33230 (0.0008) -[2023-10-12 04:32:18,451][78091] Updated weights for policy 0, policy_version 33240 (0.0008) -[2023-10-12 04:32:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 67928064. Throughput: 0: 1593.8, 1: 1585.6. Samples: 16988604. Policy #0 lag: (min: 20.0, avg: 25.7, max: 52.0) -[2023-10-12 04:32:20,201][77203] Avg episode reward: [(0, '39.130'), (1, '35.770')] -[2023-10-12 04:32:21,534][78123] Updated weights for policy 1, policy_version 33090 (0.0008) -[2023-10-12 04:32:21,899][78123] Updated weights for policy 1, policy_version 33100 (0.0009) -[2023-10-12 04:32:22,263][78123] Updated weights for policy 1, policy_version 33110 (0.0009) -[2023-10-12 04:32:22,637][78123] Updated weights for policy 1, policy_version 33120 (0.0010) -[2023-10-12 04:32:22,909][78091] Updated weights for policy 0, policy_version 33250 (0.0009) -[2023-10-12 04:32:23,273][78091] Updated weights for policy 0, policy_version 33260 (0.0010) -[2023-10-12 04:32:23,647][78091] Updated weights for policy 0, policy_version 33270 (0.0009) -[2023-10-12 04:32:24,018][78091] Updated weights for policy 0, policy_version 33280 (0.0009) -[2023-10-12 04:32:25,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 67993600. Throughput: 0: 1587.1, 1: 1590.6. Samples: 17008116. Policy #0 lag: (min: 20.0, avg: 25.7, max: 52.0) -[2023-10-12 04:32:25,201][77203] Avg episode reward: [(0, '36.820'), (1, '37.960')] -[2023-10-12 04:32:26,715][78123] Updated weights for policy 1, policy_version 33130 (0.0007) -[2023-10-12 04:32:27,083][78123] Updated weights for policy 1, policy_version 33140 (0.0007) -[2023-10-12 04:32:27,446][78123] Updated weights for policy 1, policy_version 33150 (0.0007) -[2023-10-12 04:32:28,125][78091] Updated weights for policy 0, policy_version 33290 (0.0010) -[2023-10-12 04:32:28,501][78091] Updated weights for policy 0, policy_version 33300 (0.0008) -[2023-10-12 04:32:28,877][78091] Updated weights for policy 0, policy_version 33310 (0.0008) -[2023-10-12 04:32:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 68059136. Throughput: 0: 1615.5, 1: 1594.2. Samples: 17018148. Policy #0 lag: (min: 20.0, avg: 25.7, max: 52.0) -[2023-10-12 04:32:30,201][77203] Avg episode reward: [(0, '38.040'), (1, '38.010')] -[2023-10-12 04:32:31,877][78123] Updated weights for policy 1, policy_version 33160 (0.0008) -[2023-10-12 04:32:32,243][78123] Updated weights for policy 1, policy_version 33170 (0.0009) -[2023-10-12 04:32:32,620][78123] Updated weights for policy 1, policy_version 33180 (0.0009) -[2023-10-12 04:32:33,209][78091] Updated weights for policy 0, policy_version 33320 (0.0009) -[2023-10-12 04:32:33,571][78091] Updated weights for policy 0, policy_version 33330 (0.0009) -[2023-10-12 04:32:33,943][78091] Updated weights for policy 0, policy_version 33340 (0.0010) -[2023-10-12 04:32:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 68124672. Throughput: 0: 1598.8, 1: 1593.1. Samples: 17036674. Policy #0 lag: (min: 20.0, avg: 25.7, max: 52.0) -[2023-10-12 04:32:35,202][77203] Avg episode reward: [(0, '42.940'), (1, '38.130')] -[2023-10-12 04:32:36,867][78123] Updated weights for policy 1, policy_version 33190 (0.0010) -[2023-10-12 04:32:37,239][78123] Updated weights for policy 1, policy_version 33200 (0.0008) -[2023-10-12 04:32:37,597][78123] Updated weights for policy 1, policy_version 33210 (0.0008) -[2023-10-12 04:32:38,492][78091] Updated weights for policy 0, policy_version 33350 (0.0009) -[2023-10-12 04:32:38,867][78091] Updated weights for policy 0, policy_version 33360 (0.0009) -[2023-10-12 04:32:39,236][78091] Updated weights for policy 0, policy_version 33370 (0.0009) -[2023-10-12 04:32:40,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 68190208. Throughput: 0: 1593.1, 1: 1600.7. Samples: 17056018. Policy #0 lag: (min: 20.0, avg: 25.7, max: 52.0) -[2023-10-12 04:32:40,202][77203] Avg episode reward: [(0, '39.140'), (1, '42.350')] -[2023-10-12 04:32:42,004][78123] Updated weights for policy 1, policy_version 33220 (0.0008) -[2023-10-12 04:32:42,378][78123] Updated weights for policy 1, policy_version 33230 (0.0009) -[2023-10-12 04:32:42,752][78123] Updated weights for policy 1, policy_version 33240 (0.0007) -[2023-10-12 04:32:43,257][78091] Updated weights for policy 0, policy_version 33380 (0.0009) -[2023-10-12 04:32:43,629][78091] Updated weights for policy 0, policy_version 33390 (0.0008) -[2023-10-12 04:32:44,003][78091] Updated weights for policy 0, policy_version 33400 (0.0009) -[2023-10-12 04:32:45,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 68255744. Throughput: 0: 1614.7, 1: 1607.9. Samples: 17066428. Policy #0 lag: (min: 31.0, avg: 41.3, max: 63.0) -[2023-10-12 04:32:45,202][77203] Avg episode reward: [(0, '40.780'), (1, '40.550')] -[2023-10-12 04:32:46,998][78123] Updated weights for policy 1, policy_version 33250 (0.0007) -[2023-10-12 04:32:47,358][78123] Updated weights for policy 1, policy_version 33260 (0.0007) -[2023-10-12 04:32:47,722][78123] Updated weights for policy 1, policy_version 33270 (0.0009) -[2023-10-12 04:32:48,084][78123] Updated weights for policy 1, policy_version 33280 (0.0010) -[2023-10-12 04:32:48,185][78091] Updated weights for policy 0, policy_version 33410 (0.0008) -[2023-10-12 04:32:48,565][78091] Updated weights for policy 0, policy_version 33420 (0.0010) -[2023-10-12 04:32:48,929][78091] Updated weights for policy 0, policy_version 33430 (0.0007) -[2023-10-12 04:32:49,304][78091] Updated weights for policy 0, policy_version 33440 (0.0010) -[2023-10-12 04:32:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 68321280. Throughput: 0: 1607.7, 1: 1600.1. Samples: 17085062. Policy #0 lag: (min: 31.0, avg: 41.3, max: 63.0) -[2023-10-12 04:32:50,201][77203] Avg episode reward: [(0, '44.410'), (1, '38.690')] -[2023-10-12 04:32:52,290][78123] Updated weights for policy 1, policy_version 33290 (0.0008) -[2023-10-12 04:32:52,659][78123] Updated weights for policy 1, policy_version 33300 (0.0008) -[2023-10-12 04:32:53,021][78123] Updated weights for policy 1, policy_version 33310 (0.0008) -[2023-10-12 04:32:53,826][78091] Updated weights for policy 0, policy_version 33450 (0.0008) -[2023-10-12 04:32:54,198][78091] Updated weights for policy 0, policy_version 33460 (0.0008) -[2023-10-12 04:32:54,580][78091] Updated weights for policy 0, policy_version 33470 (0.0007) -[2023-10-12 04:32:55,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 68386816. Throughput: 0: 1594.8, 1: 1597.3. Samples: 17103920. Policy #0 lag: (min: 31.0, avg: 41.3, max: 63.0) -[2023-10-12 04:32:55,202][77203] Avg episode reward: [(0, '36.550'), (1, '39.130')] -[2023-10-12 04:32:57,583][78123] Updated weights for policy 1, policy_version 33320 (0.0010) -[2023-10-12 04:32:57,955][78123] Updated weights for policy 1, policy_version 33330 (0.0008) -[2023-10-12 04:32:58,314][78123] Updated weights for policy 1, policy_version 33340 (0.0007) -[2023-10-12 04:32:58,640][78091] Updated weights for policy 0, policy_version 33480 (0.0008) -[2023-10-12 04:32:59,009][78091] Updated weights for policy 0, policy_version 33490 (0.0009) -[2023-10-12 04:32:59,380][78091] Updated weights for policy 0, policy_version 33500 (0.0008) -[2023-10-12 04:33:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 68452352. Throughput: 0: 1600.7, 1: 1612.1. Samples: 17114298. Policy #0 lag: (min: 31.0, avg: 41.3, max: 63.0) -[2023-10-12 04:33:00,201][77203] Avg episode reward: [(0, '36.010'), (1, '34.410')] -[2023-10-12 04:33:02,642][78123] Updated weights for policy 1, policy_version 33350 (0.0009) -[2023-10-12 04:33:03,009][78123] Updated weights for policy 1, policy_version 33360 (0.0009) -[2023-10-12 04:33:03,386][78123] Updated weights for policy 1, policy_version 33370 (0.0007) -[2023-10-12 04:33:03,665][78091] Updated weights for policy 0, policy_version 33510 (0.0008) -[2023-10-12 04:33:04,036][78091] Updated weights for policy 0, policy_version 33520 (0.0008) -[2023-10-12 04:33:04,405][78091] Updated weights for policy 0, policy_version 33530 (0.0009) -[2023-10-12 04:33:05,201][77203] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 68517888. Throughput: 0: 1613.5, 1: 1594.6. Samples: 17132966. Policy #0 lag: (min: 31.0, avg: 41.3, max: 63.0) -[2023-10-12 04:33:05,201][77203] Avg episode reward: [(0, '41.360'), (1, '39.290')] -[2023-10-12 04:33:07,661][78123] Updated weights for policy 1, policy_version 33380 (0.0010) -[2023-10-12 04:33:08,033][78123] Updated weights for policy 1, policy_version 33390 (0.0007) -[2023-10-12 04:33:08,409][78123] Updated weights for policy 1, policy_version 33400 (0.0007) -[2023-10-12 04:33:08,660][78091] Updated weights for policy 0, policy_version 33540 (0.0010) -[2023-10-12 04:33:09,017][78091] Updated weights for policy 0, policy_version 33550 (0.0010) -[2023-10-12 04:33:09,384][78091] Updated weights for policy 0, policy_version 33560 (0.0009) -[2023-10-12 04:33:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 68583424. Throughput: 0: 1596.6, 1: 1593.5. Samples: 17151668. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:33:10,202][77203] Avg episode reward: [(0, '42.180'), (1, '36.620')] -[2023-10-12 04:33:10,210][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000033568_34373632.pth... -[2023-10-12 04:33:10,210][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000033408_34209792.pth... -[2023-10-12 04:33:10,242][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000032064_32833536.pth -[2023-10-12 04:33:10,248][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000031904_32669696.pth -[2023-10-12 04:33:12,624][78123] Updated weights for policy 1, policy_version 33410 (0.0009) -[2023-10-12 04:33:12,988][78123] Updated weights for policy 1, policy_version 33420 (0.0007) -[2023-10-12 04:33:13,351][78123] Updated weights for policy 1, policy_version 33430 (0.0007) -[2023-10-12 04:33:13,704][78091] Updated weights for policy 0, policy_version 33570 (0.0010) -[2023-10-12 04:33:13,721][78123] Updated weights for policy 1, policy_version 33440 (0.0007) -[2023-10-12 04:33:14,083][78091] Updated weights for policy 0, policy_version 33580 (0.0009) -[2023-10-12 04:33:14,454][78091] Updated weights for policy 0, policy_version 33590 (0.0007) -[2023-10-12 04:33:14,830][78091] Updated weights for policy 0, policy_version 33600 (0.0007) -[2023-10-12 04:33:15,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 68648960. Throughput: 0: 1595.3, 1: 1611.8. Samples: 17162466. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:33:15,202][77203] Avg episode reward: [(0, '36.790'), (1, '34.340')] -[2023-10-12 04:33:18,047][78123] Updated weights for policy 1, policy_version 33450 (0.0009) -[2023-10-12 04:33:18,404][78123] Updated weights for policy 1, policy_version 33460 (0.0009) -[2023-10-12 04:33:18,770][78123] Updated weights for policy 1, policy_version 33470 (0.0007) -[2023-10-12 04:33:19,202][78091] Updated weights for policy 0, policy_version 33610 (0.0008) -[2023-10-12 04:33:19,565][78091] Updated weights for policy 0, policy_version 33620 (0.0009) -[2023-10-12 04:33:19,937][78091] Updated weights for policy 0, policy_version 33630 (0.0007) -[2023-10-12 04:33:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 68714496. Throughput: 0: 1620.0, 1: 1597.9. Samples: 17181476. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:33:20,202][77203] Avg episode reward: [(0, '44.620'), (1, '38.190')] -[2023-10-12 04:33:23,124][78123] Updated weights for policy 1, policy_version 33480 (0.0008) -[2023-10-12 04:33:23,493][78123] Updated weights for policy 1, policy_version 33490 (0.0008) -[2023-10-12 04:33:23,860][78123] Updated weights for policy 1, policy_version 33500 (0.0008) -[2023-10-12 04:33:24,256][78091] Updated weights for policy 0, policy_version 33640 (0.0010) -[2023-10-12 04:33:24,629][78091] Updated weights for policy 0, policy_version 33650 (0.0007) -[2023-10-12 04:33:25,000][78091] Updated weights for policy 0, policy_version 33660 (0.0007) -[2023-10-12 04:33:25,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 68780032. Throughput: 0: 1612.8, 1: 1589.9. Samples: 17200142. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:33:25,202][77203] Avg episode reward: [(0, '38.180'), (1, '37.080')] -[2023-10-12 04:33:28,463][78123] Updated weights for policy 1, policy_version 33510 (0.0009) -[2023-10-12 04:33:28,827][78123] Updated weights for policy 1, policy_version 33520 (0.0007) -[2023-10-12 04:33:29,183][78091] Updated weights for policy 0, policy_version 33670 (0.0007) -[2023-10-12 04:33:29,190][78123] Updated weights for policy 1, policy_version 33530 (0.0009) -[2023-10-12 04:33:29,554][78091] Updated weights for policy 0, policy_version 33680 (0.0009) -[2023-10-12 04:33:29,922][78091] Updated weights for policy 0, policy_version 33690 (0.0010) -[2023-10-12 04:33:30,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 68845568. Throughput: 0: 1598.1, 1: 1605.5. Samples: 17210588. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:33:30,201][77203] Avg episode reward: [(0, '42.580'), (1, '35.590')] -[2023-10-12 04:33:33,591][78123] Updated weights for policy 1, policy_version 33540 (0.0009) -[2023-10-12 04:33:33,959][78123] Updated weights for policy 1, policy_version 33550 (0.0008) -[2023-10-12 04:33:34,274][78091] Updated weights for policy 0, policy_version 33700 (0.0009) -[2023-10-12 04:33:34,318][78123] Updated weights for policy 1, policy_version 33560 (0.0008) -[2023-10-12 04:33:34,641][78091] Updated weights for policy 0, policy_version 33710 (0.0009) -[2023-10-12 04:33:35,014][78091] Updated weights for policy 0, policy_version 33720 (0.0008) -[2023-10-12 04:33:35,201][77203] Fps is (10 sec: 9830.2, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 68878336. Throughput: 0: 1613.3, 1: 1600.7. Samples: 17229692. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:33:35,202][77203] Avg episode reward: [(0, '45.250'), (1, '38.220')] -[2023-10-12 04:33:38,598][78123] Updated weights for policy 1, policy_version 33570 (0.0008) -[2023-10-12 04:33:38,967][78123] Updated weights for policy 1, policy_version 33580 (0.0008) -[2023-10-12 04:33:39,328][78123] Updated weights for policy 1, policy_version 33590 (0.0007) -[2023-10-12 04:33:39,347][78091] Updated weights for policy 0, policy_version 33730 (0.0010) -[2023-10-12 04:33:39,692][78123] Updated weights for policy 1, policy_version 33600 (0.0010) -[2023-10-12 04:33:39,717][78091] Updated weights for policy 0, policy_version 33740 (0.0007) -[2023-10-12 04:33:40,087][78091] Updated weights for policy 0, policy_version 33750 (0.0010) -[2023-10-12 04:33:40,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 68943872. Throughput: 0: 1618.3, 1: 1582.4. Samples: 17247950. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-12 04:33:40,201][77203] Avg episode reward: [(0, '42.940'), (1, '38.090')] -[2023-10-12 04:33:40,454][78091] Updated weights for policy 0, policy_version 33760 (0.0008) -[2023-10-12 04:33:44,066][78123] Updated weights for policy 1, policy_version 33610 (0.0009) -[2023-10-12 04:33:44,439][78123] Updated weights for policy 1, policy_version 33620 (0.0010) -[2023-10-12 04:33:44,749][78091] Updated weights for policy 0, policy_version 33770 (0.0008) -[2023-10-12 04:33:44,804][78123] Updated weights for policy 1, policy_version 33630 (0.0008) -[2023-10-12 04:33:45,112][78091] Updated weights for policy 0, policy_version 33780 (0.0009) -[2023-10-12 04:33:45,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 69009408. Throughput: 0: 1602.6, 1: 1596.3. Samples: 17258248. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-12 04:33:45,201][77203] Avg episode reward: [(0, '43.530'), (1, '36.130')] -[2023-10-12 04:33:45,483][78091] Updated weights for policy 0, policy_version 33790 (0.0007) -[2023-10-12 04:33:49,023][78123] Updated weights for policy 1, policy_version 33640 (0.0009) -[2023-10-12 04:33:49,389][78123] Updated weights for policy 1, policy_version 33650 (0.0008) -[2023-10-12 04:33:49,764][78123] Updated weights for policy 1, policy_version 33660 (0.0008) -[2023-10-12 04:33:49,836][78091] Updated weights for policy 0, policy_version 33800 (0.0008) -[2023-10-12 04:33:50,199][78091] Updated weights for policy 0, policy_version 33810 (0.0007) -[2023-10-12 04:33:50,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 69074944. Throughput: 0: 1602.9, 1: 1607.8. Samples: 17277446. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-12 04:33:50,203][77203] Avg episode reward: [(0, '49.530'), (1, '37.560')] -[2023-10-12 04:33:50,567][78091] Updated weights for policy 0, policy_version 33820 (0.0009) -[2023-10-12 04:33:50,714][77792] Saving new best policy, reward=49.530! -[2023-10-12 04:33:54,213][78123] Updated weights for policy 1, policy_version 33670 (0.0010) -[2023-10-12 04:33:54,575][78123] Updated weights for policy 1, policy_version 33680 (0.0008) -[2023-10-12 04:33:54,779][78091] Updated weights for policy 0, policy_version 33830 (0.0009) -[2023-10-12 04:33:54,942][78123] Updated weights for policy 1, policy_version 33690 (0.0008) -[2023-10-12 04:33:55,147][78091] Updated weights for policy 0, policy_version 33840 (0.0007) -[2023-10-12 04:33:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 69140480. Throughput: 0: 1617.1, 1: 1588.4. Samples: 17295912. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-12 04:33:55,201][77203] Avg episode reward: [(0, '44.470'), (1, '41.430')] -[2023-10-12 04:33:55,521][78091] Updated weights for policy 0, policy_version 33850 (0.0008) -[2023-10-12 04:33:59,236][78123] Updated weights for policy 1, policy_version 33700 (0.0009) -[2023-10-12 04:33:59,608][78123] Updated weights for policy 1, policy_version 33710 (0.0010) -[2023-10-12 04:33:59,976][78123] Updated weights for policy 1, policy_version 33720 (0.0007) -[2023-10-12 04:33:59,980][78091] Updated weights for policy 0, policy_version 33860 (0.0007) -[2023-10-12 04:34:00,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 69173248. Throughput: 0: 1596.4, 1: 1581.5. Samples: 17305472. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-12 04:34:00,201][77203] Avg episode reward: [(0, '43.030'), (1, '36.540')] -[2023-10-12 04:34:00,364][78091] Updated weights for policy 0, policy_version 33870 (0.0008) -[2023-10-12 04:34:00,727][78091] Updated weights for policy 0, policy_version 33880 (0.0007) -[2023-10-12 04:34:04,194][78123] Updated weights for policy 1, policy_version 33730 (0.0007) -[2023-10-12 04:34:04,558][78123] Updated weights for policy 1, policy_version 33740 (0.0010) -[2023-10-12 04:34:04,913][78123] Updated weights for policy 1, policy_version 33750 (0.0010) -[2023-10-12 04:34:05,066][78091] Updated weights for policy 0, policy_version 33890 (0.0009) -[2023-10-12 04:34:05,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 69238784. Throughput: 0: 1589.7, 1: 1600.3. Samples: 17325028. Policy #0 lag: (min: 4.0, avg: 11.8, max: 36.0) -[2023-10-12 04:34:05,201][77203] Avg episode reward: [(0, '47.610'), (1, '36.180')] -[2023-10-12 04:34:05,287][78123] Updated weights for policy 1, policy_version 33760 (0.0008) -[2023-10-12 04:34:05,442][78091] Updated weights for policy 0, policy_version 33900 (0.0009) -[2023-10-12 04:34:05,817][78091] Updated weights for policy 0, policy_version 33910 (0.0009) -[2023-10-12 04:34:06,175][78091] Updated weights for policy 0, policy_version 33920 (0.0008) -[2023-10-12 04:34:09,667][78123] Updated weights for policy 1, policy_version 33770 (0.0008) -[2023-10-12 04:34:10,025][78123] Updated weights for policy 1, policy_version 33780 (0.0009) -[2023-10-12 04:34:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 69304320. Throughput: 0: 1603.6, 1: 1593.9. Samples: 17344026. Policy #0 lag: (min: 4.0, avg: 11.8, max: 36.0) -[2023-10-12 04:34:10,201][77203] Avg episode reward: [(0, '40.450'), (1, '40.580')] -[2023-10-12 04:34:10,383][78091] Updated weights for policy 0, policy_version 33930 (0.0008) -[2023-10-12 04:34:10,399][78123] Updated weights for policy 1, policy_version 33790 (0.0009) -[2023-10-12 04:34:10,758][78091] Updated weights for policy 0, policy_version 33940 (0.0007) -[2023-10-12 04:34:11,130][78091] Updated weights for policy 0, policy_version 33950 (0.0007) -[2023-10-12 04:34:14,826][78123] Updated weights for policy 1, policy_version 33800 (0.0008) -[2023-10-12 04:34:15,185][78123] Updated weights for policy 1, policy_version 33810 (0.0007) -[2023-10-12 04:34:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 69369856. Throughput: 0: 1587.0, 1: 1578.4. Samples: 17353032. Policy #0 lag: (min: 4.0, avg: 11.8, max: 36.0) -[2023-10-12 04:34:15,202][77203] Avg episode reward: [(0, '43.270'), (1, '31.650')] -[2023-10-12 04:34:15,506][78091] Updated weights for policy 0, policy_version 33960 (0.0009) -[2023-10-12 04:34:15,559][78123] Updated weights for policy 1, policy_version 33820 (0.0010) -[2023-10-12 04:34:15,873][78091] Updated weights for policy 0, policy_version 33970 (0.0010) -[2023-10-12 04:34:16,247][78091] Updated weights for policy 0, policy_version 33980 (0.0010) -[2023-10-12 04:34:19,950][78123] Updated weights for policy 1, policy_version 33830 (0.0009) -[2023-10-12 04:34:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 69435392. Throughput: 0: 1587.5, 1: 1590.4. Samples: 17372698. Policy #0 lag: (min: 4.0, avg: 11.8, max: 36.0) -[2023-10-12 04:34:20,201][77203] Avg episode reward: [(0, '45.020'), (1, '35.360')] -[2023-10-12 04:34:20,314][78123] Updated weights for policy 1, policy_version 33840 (0.0009) -[2023-10-12 04:34:20,595][78091] Updated weights for policy 0, policy_version 33990 (0.0007) -[2023-10-12 04:34:20,681][78123] Updated weights for policy 1, policy_version 33850 (0.0007) -[2023-10-12 04:34:20,975][78091] Updated weights for policy 0, policy_version 34000 (0.0010) -[2023-10-12 04:34:21,338][78091] Updated weights for policy 0, policy_version 34010 (0.0008) -[2023-10-12 04:34:25,042][78123] Updated weights for policy 1, policy_version 33860 (0.0007) -[2023-10-12 04:34:25,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 69500928. Throughput: 0: 1599.0, 1: 1602.0. Samples: 17391996. Policy #0 lag: (min: 4.0, avg: 11.8, max: 36.0) -[2023-10-12 04:34:25,201][77203] Avg episode reward: [(0, '36.330'), (1, '42.490')] -[2023-10-12 04:34:25,417][78123] Updated weights for policy 1, policy_version 33870 (0.0008) -[2023-10-12 04:34:25,731][78091] Updated weights for policy 0, policy_version 34020 (0.0008) -[2023-10-12 04:34:25,782][78123] Updated weights for policy 1, policy_version 33880 (0.0010) -[2023-10-12 04:34:26,125][78091] Updated weights for policy 0, policy_version 34030 (0.0008) -[2023-10-12 04:34:26,491][78091] Updated weights for policy 0, policy_version 34040 (0.0010) -[2023-10-12 04:34:30,192][78123] Updated weights for policy 1, policy_version 33890 (0.0008) -[2023-10-12 04:34:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 69566464. Throughput: 0: 1586.0, 1: 1574.4. Samples: 17400464. Policy #0 lag: (min: 31.0, avg: 32.7, max: 59.0) -[2023-10-12 04:34:30,201][77203] Avg episode reward: [(0, '43.470'), (1, '36.310')] -[2023-10-12 04:34:30,610][78123] Updated weights for policy 1, policy_version 33900 (0.0008) -[2023-10-12 04:34:30,746][78091] Updated weights for policy 0, policy_version 34050 (0.0008) -[2023-10-12 04:34:30,982][78123] Updated weights for policy 1, policy_version 33910 (0.0010) -[2023-10-12 04:34:31,120][78091] Updated weights for policy 0, policy_version 34060 (0.0007) -[2023-10-12 04:34:31,341][78123] Updated weights for policy 1, policy_version 33920 (0.0008) -[2023-10-12 04:34:31,486][78091] Updated weights for policy 0, policy_version 34070 (0.0008) -[2023-10-12 04:34:31,858][78091] Updated weights for policy 0, policy_version 34080 (0.0009) -[2023-10-12 04:34:35,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 69632000. Throughput: 0: 1588.5, 1: 1573.8. Samples: 17419750. Policy #0 lag: (min: 31.0, avg: 32.7, max: 59.0) -[2023-10-12 04:34:35,202][77203] Avg episode reward: [(0, '42.790'), (1, '34.370')] -[2023-10-12 04:34:35,790][78123] Updated weights for policy 1, policy_version 33930 (0.0008) -[2023-10-12 04:34:36,151][78091] Updated weights for policy 0, policy_version 34090 (0.0007) -[2023-10-12 04:34:36,157][78123] Updated weights for policy 1, policy_version 33940 (0.0007) -[2023-10-12 04:34:36,523][78091] Updated weights for policy 0, policy_version 34100 (0.0008) -[2023-10-12 04:34:36,530][78123] Updated weights for policy 1, policy_version 33950 (0.0008) -[2023-10-12 04:34:36,898][78091] Updated weights for policy 0, policy_version 34110 (0.0008) -[2023-10-12 04:34:40,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 69697536. Throughput: 0: 1593.6, 1: 1588.0. Samples: 17439086. Policy #0 lag: (min: 31.0, avg: 32.7, max: 59.0) -[2023-10-12 04:34:40,202][77203] Avg episode reward: [(0, '41.050'), (1, '41.870')] -[2023-10-12 04:34:40,856][78123] Updated weights for policy 1, policy_version 33960 (0.0009) -[2023-10-12 04:34:41,212][78123] Updated weights for policy 1, policy_version 33970 (0.0008) -[2023-10-12 04:34:41,212][78091] Updated weights for policy 0, policy_version 34120 (0.0007) -[2023-10-12 04:34:41,582][78091] Updated weights for policy 0, policy_version 34130 (0.0007) -[2023-10-12 04:34:41,583][78123] Updated weights for policy 1, policy_version 33980 (0.0007) -[2023-10-12 04:34:41,951][78091] Updated weights for policy 0, policy_version 34140 (0.0007) -[2023-10-12 04:34:45,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 69763072. Throughput: 0: 1586.8, 1: 1571.8. Samples: 17447610. Policy #0 lag: (min: 31.0, avg: 32.7, max: 59.0) -[2023-10-12 04:34:45,202][77203] Avg episode reward: [(0, '42.570'), (1, '43.390')] -[2023-10-12 04:34:45,972][78123] Updated weights for policy 1, policy_version 33990 (0.0010) -[2023-10-12 04:34:46,337][78123] Updated weights for policy 1, policy_version 34000 (0.0009) -[2023-10-12 04:34:46,399][78091] Updated weights for policy 0, policy_version 34150 (0.0009) -[2023-10-12 04:34:46,707][78123] Updated weights for policy 1, policy_version 34010 (0.0009) -[2023-10-12 04:34:46,762][78091] Updated weights for policy 0, policy_version 34160 (0.0010) -[2023-10-12 04:34:47,127][78091] Updated weights for policy 0, policy_version 34170 (0.0008) -[2023-10-12 04:34:50,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 69828608. Throughput: 0: 1589.1, 1: 1567.6. Samples: 17467080. Policy #0 lag: (min: 31.0, avg: 32.7, max: 59.0) -[2023-10-12 04:34:50,201][77203] Avg episode reward: [(0, '46.260'), (1, '34.830')] -[2023-10-12 04:34:51,136][78123] Updated weights for policy 1, policy_version 34020 (0.0010) -[2023-10-12 04:34:51,220][78091] Updated weights for policy 0, policy_version 34180 (0.0007) -[2023-10-12 04:34:51,492][78123] Updated weights for policy 1, policy_version 34030 (0.0007) -[2023-10-12 04:34:51,584][78091] Updated weights for policy 0, policy_version 34190 (0.0007) -[2023-10-12 04:34:51,858][78123] Updated weights for policy 1, policy_version 34040 (0.0007) -[2023-10-12 04:34:51,966][78091] Updated weights for policy 0, policy_version 34200 (0.0009) -[2023-10-12 04:34:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 69894144. Throughput: 0: 1594.1, 1: 1576.1. Samples: 17486684. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-12 04:34:55,202][77203] Avg episode reward: [(0, '43.370'), (1, '37.710')] -[2023-10-12 04:34:56,246][78091] Updated weights for policy 0, policy_version 34210 (0.0008) -[2023-10-12 04:34:56,299][78123] Updated weights for policy 1, policy_version 34050 (0.0008) -[2023-10-12 04:34:56,626][78091] Updated weights for policy 0, policy_version 34220 (0.0007) -[2023-10-12 04:34:56,666][78123] Updated weights for policy 1, policy_version 34060 (0.0008) -[2023-10-12 04:34:56,985][78091] Updated weights for policy 0, policy_version 34230 (0.0009) -[2023-10-12 04:34:57,027][78123] Updated weights for policy 1, policy_version 34070 (0.0008) -[2023-10-12 04:34:57,354][78091] Updated weights for policy 0, policy_version 34240 (0.0008) -[2023-10-12 04:34:57,394][78123] Updated weights for policy 1, policy_version 34080 (0.0008) -[2023-10-12 04:35:00,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 69959680. Throughput: 0: 1590.8, 1: 1567.8. Samples: 17495166. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-12 04:35:00,202][77203] Avg episode reward: [(0, '37.650'), (1, '40.430')] -[2023-10-12 04:35:01,755][78091] Updated weights for policy 0, policy_version 34250 (0.0008) -[2023-10-12 04:35:01,843][78123] Updated weights for policy 1, policy_version 34090 (0.0008) -[2023-10-12 04:35:02,131][78091] Updated weights for policy 0, policy_version 34260 (0.0008) -[2023-10-12 04:35:02,207][78123] Updated weights for policy 1, policy_version 34100 (0.0009) -[2023-10-12 04:35:02,499][78091] Updated weights for policy 0, policy_version 34270 (0.0007) -[2023-10-12 04:35:02,582][78123] Updated weights for policy 1, policy_version 34110 (0.0008) -[2023-10-12 04:35:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 70025216. Throughput: 0: 1589.1, 1: 1566.5. Samples: 17514702. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-12 04:35:05,202][77203] Avg episode reward: [(0, '45.210'), (1, '36.190')] -[2023-10-12 04:35:06,763][78123] Updated weights for policy 1, policy_version 34120 (0.0009) -[2023-10-12 04:35:06,897][78091] Updated weights for policy 0, policy_version 34280 (0.0008) -[2023-10-12 04:35:07,133][78123] Updated weights for policy 1, policy_version 34130 (0.0008) -[2023-10-12 04:35:07,274][78091] Updated weights for policy 0, policy_version 34290 (0.0009) -[2023-10-12 04:35:07,488][78123] Updated weights for policy 1, policy_version 34140 (0.0007) -[2023-10-12 04:35:07,635][78091] Updated weights for policy 0, policy_version 34300 (0.0009) -[2023-10-12 04:35:10,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 70090752. Throughput: 0: 1584.7, 1: 1574.2. Samples: 17534148. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-12 04:35:10,201][77203] Avg episode reward: [(0, '42.470'), (1, '34.840')] -[2023-10-12 04:35:10,213][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000034144_34963456.pth... -[2023-10-12 04:35:10,213][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000034304_35127296.pth... -[2023-10-12 04:35:10,251][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000032800_33587200.pth -[2023-10-12 04:35:10,252][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000032672_33456128.pth -[2023-10-12 04:35:11,933][78123] Updated weights for policy 1, policy_version 34150 (0.0008) -[2023-10-12 04:35:12,024][78091] Updated weights for policy 0, policy_version 34310 (0.0009) -[2023-10-12 04:35:12,299][78123] Updated weights for policy 1, policy_version 34160 (0.0009) -[2023-10-12 04:35:12,388][78091] Updated weights for policy 0, policy_version 34320 (0.0008) -[2023-10-12 04:35:12,657][78123] Updated weights for policy 1, policy_version 34170 (0.0010) -[2023-10-12 04:35:12,759][78091] Updated weights for policy 0, policy_version 34330 (0.0008) -[2023-10-12 04:35:15,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.3, 300 sec: 12774.0). Total num frames: 70156288. Throughput: 0: 1589.8, 1: 1580.3. Samples: 17543120. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-12 04:35:15,201][77203] Avg episode reward: [(0, '43.150'), (1, '35.220')] -[2023-10-12 04:35:16,868][78123] Updated weights for policy 1, policy_version 34180 (0.0007) -[2023-10-12 04:35:17,237][78123] Updated weights for policy 1, policy_version 34190 (0.0007) -[2023-10-12 04:35:17,249][78091] Updated weights for policy 0, policy_version 34340 (0.0009) -[2023-10-12 04:35:17,608][78123] Updated weights for policy 1, policy_version 34200 (0.0008) -[2023-10-12 04:35:17,613][78091] Updated weights for policy 0, policy_version 34350 (0.0008) -[2023-10-12 04:35:17,971][78091] Updated weights for policy 0, policy_version 34360 (0.0007) -[2023-10-12 04:35:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 70221824. Throughput: 0: 1578.3, 1: 1583.7. Samples: 17562038. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:35:20,201][77203] Avg episode reward: [(0, '44.700'), (1, '40.460')] -[2023-10-12 04:35:21,864][78123] Updated weights for policy 1, policy_version 34210 (0.0008) -[2023-10-12 04:35:22,267][78123] Updated weights for policy 1, policy_version 34220 (0.0010) -[2023-10-12 04:35:22,354][78091] Updated weights for policy 0, policy_version 34370 (0.0007) -[2023-10-12 04:35:22,632][78123] Updated weights for policy 1, policy_version 34230 (0.0007) -[2023-10-12 04:35:22,717][78091] Updated weights for policy 0, policy_version 34380 (0.0007) -[2023-10-12 04:35:22,989][78123] Updated weights for policy 1, policy_version 34240 (0.0009) -[2023-10-12 04:35:23,093][78091] Updated weights for policy 0, policy_version 34390 (0.0008) -[2023-10-12 04:35:23,451][78091] Updated weights for policy 0, policy_version 34400 (0.0008) -[2023-10-12 04:35:25,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 70287360. Throughput: 0: 1581.6, 1: 1582.0. Samples: 17581448. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:35:25,202][77203] Avg episode reward: [(0, '42.740'), (1, '40.370')] -[2023-10-12 04:35:27,334][78123] Updated weights for policy 1, policy_version 34250 (0.0008) -[2023-10-12 04:35:27,645][78091] Updated weights for policy 0, policy_version 34410 (0.0009) -[2023-10-12 04:35:27,704][78123] Updated weights for policy 1, policy_version 34260 (0.0007) -[2023-10-12 04:35:28,014][78091] Updated weights for policy 0, policy_version 34420 (0.0008) -[2023-10-12 04:35:28,070][78123] Updated weights for policy 1, policy_version 34270 (0.0007) -[2023-10-12 04:35:28,385][78091] Updated weights for policy 0, policy_version 34430 (0.0009) -[2023-10-12 04:35:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 70352896. Throughput: 0: 1598.5, 1: 1595.3. Samples: 17591332. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:35:30,201][77203] Avg episode reward: [(0, '39.840'), (1, '35.200')] -[2023-10-12 04:35:32,376][78123] Updated weights for policy 1, policy_version 34280 (0.0008) -[2023-10-12 04:35:32,618][78091] Updated weights for policy 0, policy_version 34440 (0.0009) -[2023-10-12 04:35:32,746][78123] Updated weights for policy 1, policy_version 34290 (0.0009) -[2023-10-12 04:35:32,991][78091] Updated weights for policy 0, policy_version 34450 (0.0007) -[2023-10-12 04:35:33,110][78123] Updated weights for policy 1, policy_version 34300 (0.0008) -[2023-10-12 04:35:33,360][78091] Updated weights for policy 0, policy_version 34460 (0.0008) -[2023-10-12 04:35:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 70418432. Throughput: 0: 1588.4, 1: 1589.5. Samples: 17610088. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:35:35,202][77203] Avg episode reward: [(0, '41.000'), (1, '33.360')] -[2023-10-12 04:35:37,355][78123] Updated weights for policy 1, policy_version 34310 (0.0010) -[2023-10-12 04:35:37,690][78091] Updated weights for policy 0, policy_version 34470 (0.0007) -[2023-10-12 04:35:37,725][78123] Updated weights for policy 1, policy_version 34320 (0.0010) -[2023-10-12 04:35:38,067][78091] Updated weights for policy 0, policy_version 34480 (0.0008) -[2023-10-12 04:35:38,087][78123] Updated weights for policy 1, policy_version 34330 (0.0008) -[2023-10-12 04:35:38,440][78091] Updated weights for policy 0, policy_version 34490 (0.0007) -[2023-10-12 04:35:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 70483968. Throughput: 0: 1580.5, 1: 1592.5. Samples: 17629466. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:35:40,201][77203] Avg episode reward: [(0, '40.530'), (1, '39.230')] -[2023-10-12 04:35:42,348][78123] Updated weights for policy 1, policy_version 34340 (0.0007) -[2023-10-12 04:35:42,724][78123] Updated weights for policy 1, policy_version 34350 (0.0010) -[2023-10-12 04:35:42,800][78091] Updated weights for policy 0, policy_version 34500 (0.0007) -[2023-10-12 04:35:43,088][78123] Updated weights for policy 1, policy_version 34360 (0.0008) -[2023-10-12 04:35:43,172][78091] Updated weights for policy 0, policy_version 34510 (0.0009) -[2023-10-12 04:35:43,545][78091] Updated weights for policy 0, policy_version 34520 (0.0009) -[2023-10-12 04:35:45,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 70549504. Throughput: 0: 1602.4, 1: 1611.4. Samples: 17639790. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-12 04:35:45,202][77203] Avg episode reward: [(0, '37.340'), (1, '39.560')] -[2023-10-12 04:35:47,302][78123] Updated weights for policy 1, policy_version 34370 (0.0009) -[2023-10-12 04:35:47,662][78123] Updated weights for policy 1, policy_version 34380 (0.0008) -[2023-10-12 04:35:47,873][78091] Updated weights for policy 0, policy_version 34530 (0.0009) -[2023-10-12 04:35:48,030][78123] Updated weights for policy 1, policy_version 34390 (0.0010) -[2023-10-12 04:35:48,249][78091] Updated weights for policy 0, policy_version 34540 (0.0008) -[2023-10-12 04:35:48,399][78123] Updated weights for policy 1, policy_version 34400 (0.0009) -[2023-10-12 04:35:48,620][78091] Updated weights for policy 0, policy_version 34550 (0.0008) -[2023-10-12 04:35:48,992][78091] Updated weights for policy 0, policy_version 34560 (0.0009) -[2023-10-12 04:35:50,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 70615040. Throughput: 0: 1583.5, 1: 1595.4. Samples: 17657752. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-12 04:35:50,202][77203] Avg episode reward: [(0, '44.590'), (1, '36.630')] -[2023-10-12 04:35:52,721][78123] Updated weights for policy 1, policy_version 34410 (0.0009) -[2023-10-12 04:35:53,096][78123] Updated weights for policy 1, policy_version 34420 (0.0009) -[2023-10-12 04:35:53,384][78091] Updated weights for policy 0, policy_version 34570 (0.0007) -[2023-10-12 04:35:53,468][78123] Updated weights for policy 1, policy_version 34430 (0.0009) -[2023-10-12 04:35:53,757][78091] Updated weights for policy 0, policy_version 34580 (0.0009) -[2023-10-12 04:35:54,116][78091] Updated weights for policy 0, policy_version 34590 (0.0009) -[2023-10-12 04:35:55,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 70680576. Throughput: 0: 1580.9, 1: 1594.7. Samples: 17677048. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-12 04:35:55,202][77203] Avg episode reward: [(0, '37.680'), (1, '34.150')] -[2023-10-12 04:35:57,775][78123] Updated weights for policy 1, policy_version 34440 (0.0010) -[2023-10-12 04:35:58,142][78123] Updated weights for policy 1, policy_version 34450 (0.0010) -[2023-10-12 04:35:58,458][78091] Updated weights for policy 0, policy_version 34600 (0.0008) -[2023-10-12 04:35:58,509][78123] Updated weights for policy 1, policy_version 34460 (0.0009) -[2023-10-12 04:35:58,834][78091] Updated weights for policy 0, policy_version 34610 (0.0007) -[2023-10-12 04:35:59,202][78091] Updated weights for policy 0, policy_version 34620 (0.0008) -[2023-10-12 04:36:00,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 70746112. Throughput: 0: 1603.4, 1: 1609.9. Samples: 17687720. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-12 04:36:00,202][77203] Avg episode reward: [(0, '40.810'), (1, '39.970')] -[2023-10-12 04:36:02,930][78123] Updated weights for policy 1, policy_version 34470 (0.0008) -[2023-10-12 04:36:03,299][78123] Updated weights for policy 1, policy_version 34480 (0.0007) -[2023-10-12 04:36:03,485][78091] Updated weights for policy 0, policy_version 34630 (0.0010) -[2023-10-12 04:36:03,665][78123] Updated weights for policy 1, policy_version 34490 (0.0008) -[2023-10-12 04:36:03,849][78091] Updated weights for policy 0, policy_version 34640 (0.0008) -[2023-10-12 04:36:04,216][78091] Updated weights for policy 0, policy_version 34650 (0.0009) -[2023-10-12 04:36:05,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 70811648. Throughput: 0: 1605.6, 1: 1592.6. Samples: 17705960. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-12 04:36:05,201][77203] Avg episode reward: [(0, '43.240'), (1, '43.270')] -[2023-10-12 04:36:08,236][78123] Updated weights for policy 1, policy_version 34500 (0.0007) -[2023-10-12 04:36:08,509][78091] Updated weights for policy 0, policy_version 34660 (0.0008) -[2023-10-12 04:36:08,639][78123] Updated weights for policy 1, policy_version 34510 (0.0008) -[2023-10-12 04:36:08,869][78091] Updated weights for policy 0, policy_version 34670 (0.0007) -[2023-10-12 04:36:08,992][78123] Updated weights for policy 1, policy_version 34520 (0.0009) -[2023-10-12 04:36:09,241][78091] Updated weights for policy 0, policy_version 34680 (0.0007) -[2023-10-12 04:36:10,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 70877184. Throughput: 0: 1591.6, 1: 1588.8. Samples: 17724566. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) -[2023-10-12 04:36:10,202][77203] Avg episode reward: [(0, '40.110'), (1, '35.980')] -[2023-10-12 04:36:13,344][78123] Updated weights for policy 1, policy_version 34530 (0.0009) -[2023-10-12 04:36:13,576][78091] Updated weights for policy 0, policy_version 34690 (0.0009) -[2023-10-12 04:36:13,720][78123] Updated weights for policy 1, policy_version 34540 (0.0007) -[2023-10-12 04:36:13,941][78091] Updated weights for policy 0, policy_version 34700 (0.0009) -[2023-10-12 04:36:14,087][78123] Updated weights for policy 1, policy_version 34550 (0.0008) -[2023-10-12 04:36:14,296][78091] Updated weights for policy 0, policy_version 34710 (0.0008) -[2023-10-12 04:36:14,447][78123] Updated weights for policy 1, policy_version 34560 (0.0007) -[2023-10-12 04:36:14,675][78091] Updated weights for policy 0, policy_version 34720 (0.0009) -[2023-10-12 04:36:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 70942720. Throughput: 0: 1601.8, 1: 1602.7. Samples: 17735534. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) -[2023-10-12 04:36:15,202][77203] Avg episode reward: [(0, '46.500'), (1, '36.710')] -[2023-10-12 04:36:18,676][78123] Updated weights for policy 1, policy_version 34570 (0.0008) -[2023-10-12 04:36:18,982][78091] Updated weights for policy 0, policy_version 34730 (0.0009) -[2023-10-12 04:36:19,054][78123] Updated weights for policy 1, policy_version 34580 (0.0007) -[2023-10-12 04:36:19,351][78091] Updated weights for policy 0, policy_version 34740 (0.0008) -[2023-10-12 04:36:19,426][78123] Updated weights for policy 1, policy_version 34590 (0.0008) -[2023-10-12 04:36:19,713][78091] Updated weights for policy 0, policy_version 34750 (0.0009) -[2023-10-12 04:36:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 71008256. Throughput: 0: 1611.6, 1: 1600.6. Samples: 17754638. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) -[2023-10-12 04:36:20,202][77203] Avg episode reward: [(0, '40.020'), (1, '38.560')] -[2023-10-12 04:36:23,681][78123] Updated weights for policy 1, policy_version 34600 (0.0008) -[2023-10-12 04:36:23,860][78091] Updated weights for policy 0, policy_version 34760 (0.0009) -[2023-10-12 04:36:24,054][78123] Updated weights for policy 1, policy_version 34610 (0.0010) -[2023-10-12 04:36:24,236][78091] Updated weights for policy 0, policy_version 34770 (0.0009) -[2023-10-12 04:36:24,417][78123] Updated weights for policy 1, policy_version 34620 (0.0008) -[2023-10-12 04:36:24,600][78091] Updated weights for policy 0, policy_version 34780 (0.0007) -[2023-10-12 04:36:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 71073792. Throughput: 0: 1599.2, 1: 1583.1. Samples: 17772670. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) -[2023-10-12 04:36:25,202][77203] Avg episode reward: [(0, '45.650'), (1, '39.300')] -[2023-10-12 04:36:28,639][78123] Updated weights for policy 1, policy_version 34630 (0.0008) -[2023-10-12 04:36:28,930][78091] Updated weights for policy 0, policy_version 34790 (0.0009) -[2023-10-12 04:36:29,008][78123] Updated weights for policy 1, policy_version 34640 (0.0009) -[2023-10-12 04:36:29,306][78091] Updated weights for policy 0, policy_version 34800 (0.0007) -[2023-10-12 04:36:29,370][78123] Updated weights for policy 1, policy_version 34650 (0.0009) -[2023-10-12 04:36:29,680][78091] Updated weights for policy 0, policy_version 34810 (0.0009) -[2023-10-12 04:36:30,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.1, 300 sec: 12885.0). Total num frames: 71139328. Throughput: 0: 1603.1, 1: 1596.8. Samples: 17783782. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) -[2023-10-12 04:36:30,202][77203] Avg episode reward: [(0, '38.710'), (1, '36.500')] -[2023-10-12 04:36:33,829][78123] Updated weights for policy 1, policy_version 34660 (0.0007) -[2023-10-12 04:36:33,944][78091] Updated weights for policy 0, policy_version 34820 (0.0008) -[2023-10-12 04:36:34,190][78123] Updated weights for policy 1, policy_version 34670 (0.0008) -[2023-10-12 04:36:34,310][78091] Updated weights for policy 0, policy_version 34830 (0.0008) -[2023-10-12 04:36:34,565][78123] Updated weights for policy 1, policy_version 34680 (0.0007) -[2023-10-12 04:36:34,679][78091] Updated weights for policy 0, policy_version 34840 (0.0007) -[2023-10-12 04:36:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 71204864. Throughput: 0: 1619.5, 1: 1612.8. Samples: 17803206. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-12 04:36:35,201][77203] Avg episode reward: [(0, '40.800'), (1, '35.760')] -[2023-10-12 04:36:38,900][78123] Updated weights for policy 1, policy_version 34690 (0.0008) -[2023-10-12 04:36:39,006][78091] Updated weights for policy 0, policy_version 34850 (0.0008) -[2023-10-12 04:36:39,260][78123] Updated weights for policy 1, policy_version 34700 (0.0009) -[2023-10-12 04:36:39,365][78091] Updated weights for policy 0, policy_version 34860 (0.0007) -[2023-10-12 04:36:39,637][78123] Updated weights for policy 1, policy_version 34710 (0.0010) -[2023-10-12 04:36:39,737][78091] Updated weights for policy 0, policy_version 34870 (0.0007) -[2023-10-12 04:36:39,998][78123] Updated weights for policy 1, policy_version 34720 (0.0009) -[2023-10-12 04:36:40,103][78091] Updated weights for policy 0, policy_version 34880 (0.0007) -[2023-10-12 04:36:40,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.1, 300 sec: 12885.0). Total num frames: 71270400. Throughput: 0: 1607.6, 1: 1595.1. Samples: 17821166. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-12 04:36:40,202][77203] Avg episode reward: [(0, '42.390'), (1, '37.550')] -[2023-10-12 04:36:43,997][78123] Updated weights for policy 1, policy_version 34730 (0.0010) -[2023-10-12 04:36:44,370][78123] Updated weights for policy 1, policy_version 34740 (0.0007) -[2023-10-12 04:36:44,740][78123] Updated weights for policy 1, policy_version 34750 (0.0007) -[2023-10-12 04:36:44,747][78091] Updated weights for policy 0, policy_version 34890 (0.0007) -[2023-10-12 04:36:45,115][78091] Updated weights for policy 0, policy_version 34900 (0.0007) -[2023-10-12 04:36:45,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 71303168. Throughput: 0: 1594.5, 1: 1594.5. Samples: 17831224. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-12 04:36:45,202][77203] Avg episode reward: [(0, '46.840'), (1, '43.450')] -[2023-10-12 04:36:45,485][78091] Updated weights for policy 0, policy_version 34910 (0.0009) -[2023-10-12 04:36:49,095][78123] Updated weights for policy 1, policy_version 34760 (0.0008) -[2023-10-12 04:36:49,454][78123] Updated weights for policy 1, policy_version 34770 (0.0009) -[2023-10-12 04:36:49,715][78091] Updated weights for policy 0, policy_version 34920 (0.0008) -[2023-10-12 04:36:49,823][78123] Updated weights for policy 1, policy_version 34780 (0.0008) -[2023-10-12 04:36:50,084][78091] Updated weights for policy 0, policy_version 34930 (0.0008) -[2023-10-12 04:36:50,201][77203] Fps is (10 sec: 9830.7, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 71368704. Throughput: 0: 1606.7, 1: 1613.9. Samples: 17850886. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-12 04:36:50,201][77203] Avg episode reward: [(0, '38.440'), (1, '40.150')] -[2023-10-12 04:36:50,466][78091] Updated weights for policy 0, policy_version 34940 (0.0008) -[2023-10-12 04:36:54,274][78123] Updated weights for policy 1, policy_version 34790 (0.0010) -[2023-10-12 04:36:54,654][78123] Updated weights for policy 1, policy_version 34800 (0.0007) -[2023-10-12 04:36:54,860][78091] Updated weights for policy 0, policy_version 34950 (0.0008) -[2023-10-12 04:36:55,017][78123] Updated weights for policy 1, policy_version 34810 (0.0007) -[2023-10-12 04:36:55,201][77203] Fps is (10 sec: 9830.2, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 71401472. Throughput: 0: 1613.8, 1: 1608.4. Samples: 17869566. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-12 04:36:55,202][77203] Avg episode reward: [(0, '43.470'), (1, '32.260')] -[2023-10-12 04:36:55,239][78091] Updated weights for policy 0, policy_version 34960 (0.0008) -[2023-10-12 04:36:55,606][78091] Updated weights for policy 0, policy_version 34970 (0.0007) -[2023-10-12 04:36:59,209][78123] Updated weights for policy 1, policy_version 34820 (0.0008) -[2023-10-12 04:36:59,574][78123] Updated weights for policy 1, policy_version 34830 (0.0009) -[2023-10-12 04:36:59,828][78091] Updated weights for policy 0, policy_version 34980 (0.0007) -[2023-10-12 04:36:59,943][78123] Updated weights for policy 1, policy_version 34840 (0.0009) -[2023-10-12 04:37:00,196][78091] Updated weights for policy 0, policy_version 34990 (0.0007) -[2023-10-12 04:37:00,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 71467008. Throughput: 0: 1588.3, 1: 1597.3. Samples: 17878886. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-12 04:37:00,201][77203] Avg episode reward: [(0, '41.270'), (1, '35.760')] -[2023-10-12 04:37:00,574][78091] Updated weights for policy 0, policy_version 35000 (0.0008) -[2023-10-12 04:37:04,273][78123] Updated weights for policy 1, policy_version 34850 (0.0010) -[2023-10-12 04:37:04,636][78123] Updated weights for policy 1, policy_version 34860 (0.0008) -[2023-10-12 04:37:04,858][78091] Updated weights for policy 0, policy_version 35010 (0.0007) -[2023-10-12 04:37:05,002][78123] Updated weights for policy 1, policy_version 34870 (0.0009) -[2023-10-12 04:37:05,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 71532544. Throughput: 0: 1590.4, 1: 1607.8. Samples: 17898558. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:37:05,201][77203] Avg episode reward: [(0, '40.750'), (1, '39.400')] -[2023-10-12 04:37:05,240][78091] Updated weights for policy 0, policy_version 35020 (0.0008) -[2023-10-12 04:37:05,371][78123] Updated weights for policy 1, policy_version 34880 (0.0008) -[2023-10-12 04:37:05,612][78091] Updated weights for policy 0, policy_version 35030 (0.0007) -[2023-10-12 04:37:05,983][78091] Updated weights for policy 0, policy_version 35040 (0.0008) -[2023-10-12 04:37:09,906][78123] Updated weights for policy 1, policy_version 34890 (0.0010) -[2023-10-12 04:37:10,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 71598080. Throughput: 0: 1607.3, 1: 1611.6. Samples: 17917518. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:37:10,201][77203] Avg episode reward: [(0, '43.870'), (1, '34.110')] -[2023-10-12 04:37:10,258][78091] Updated weights for policy 0, policy_version 35050 (0.0008) -[2023-10-12 04:37:10,266][78123] Updated weights for policy 1, policy_version 34900 (0.0008) -[2023-10-12 04:37:10,632][78091] Updated weights for policy 0, policy_version 35060 (0.0007) -[2023-10-12 04:37:10,637][78123] Updated weights for policy 1, policy_version 34910 (0.0008) -[2023-10-12 04:37:10,704][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000034912_35749888.pth... -[2023-10-12 04:37:10,738][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000033408_34209792.pth -[2023-10-12 04:37:11,012][78091] Updated weights for policy 0, policy_version 35070 (0.0007) -[2023-10-12 04:37:11,077][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000035072_35913728.pth... -[2023-10-12 04:37:11,106][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000033568_34373632.pth -[2023-10-12 04:37:15,171][78123] Updated weights for policy 1, policy_version 34920 (0.0008) -[2023-10-12 04:37:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 71663616. Throughput: 0: 1584.6, 1: 1582.7. Samples: 17926312. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:37:15,201][77203] Avg episode reward: [(0, '45.850'), (1, '36.000')] -[2023-10-12 04:37:15,262][78091] Updated weights for policy 0, policy_version 35080 (0.0007) -[2023-10-12 04:37:15,544][78123] Updated weights for policy 1, policy_version 34930 (0.0008) -[2023-10-12 04:37:15,627][78091] Updated weights for policy 0, policy_version 35090 (0.0007) -[2023-10-12 04:37:15,899][78123] Updated weights for policy 1, policy_version 34940 (0.0010) -[2023-10-12 04:37:16,002][78091] Updated weights for policy 0, policy_version 35100 (0.0009) -[2023-10-12 04:37:20,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 71729152. Throughput: 0: 1585.0, 1: 1579.5. Samples: 17945612. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:37:20,202][77203] Avg episode reward: [(0, '45.750'), (1, '45.010')] -[2023-10-12 04:37:20,396][78091] Updated weights for policy 0, policy_version 35110 (0.0008) -[2023-10-12 04:37:20,408][78123] Updated weights for policy 1, policy_version 34950 (0.0009) -[2023-10-12 04:37:20,767][78123] Updated weights for policy 1, policy_version 34960 (0.0008) -[2023-10-12 04:37:20,768][78091] Updated weights for policy 0, policy_version 35120 (0.0009) -[2023-10-12 04:37:21,137][78123] Updated weights for policy 1, policy_version 34970 (0.0007) -[2023-10-12 04:37:21,146][78091] Updated weights for policy 0, policy_version 35130 (0.0007) -[2023-10-12 04:37:25,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 71794688. Throughput: 0: 1608.5, 1: 1589.9. Samples: 17965094. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:37:25,201][77203] Avg episode reward: [(0, '41.160'), (1, '42.340')] -[2023-10-12 04:37:25,345][78091] Updated weights for policy 0, policy_version 35140 (0.0008) -[2023-10-12 04:37:25,523][78123] Updated weights for policy 1, policy_version 34980 (0.0008) -[2023-10-12 04:37:25,711][78091] Updated weights for policy 0, policy_version 35150 (0.0008) -[2023-10-12 04:37:25,894][78123] Updated weights for policy 1, policy_version 34990 (0.0009) -[2023-10-12 04:37:26,074][78091] Updated weights for policy 0, policy_version 35160 (0.0009) -[2023-10-12 04:37:26,252][78123] Updated weights for policy 1, policy_version 35000 (0.0008) -[2023-10-12 04:37:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 71860224. Throughput: 0: 1593.7, 1: 1573.4. Samples: 17973746. Policy #0 lag: (min: 16.0, avg: 31.5, max: 48.0) -[2023-10-12 04:37:30,202][77203] Avg episode reward: [(0, '43.050'), (1, '32.350')] -[2023-10-12 04:37:30,490][78091] Updated weights for policy 0, policy_version 35170 (0.0009) -[2023-10-12 04:37:30,697][78123] Updated weights for policy 1, policy_version 35010 (0.0007) -[2023-10-12 04:37:30,879][78091] Updated weights for policy 0, policy_version 35180 (0.0008) -[2023-10-12 04:37:31,061][78123] Updated weights for policy 1, policy_version 35020 (0.0007) -[2023-10-12 04:37:31,242][78091] Updated weights for policy 0, policy_version 35190 (0.0008) -[2023-10-12 04:37:31,431][78123] Updated weights for policy 1, policy_version 35030 (0.0007) -[2023-10-12 04:37:31,614][78091] Updated weights for policy 0, policy_version 35200 (0.0008) -[2023-10-12 04:37:31,809][78123] Updated weights for policy 1, policy_version 35040 (0.0008) -[2023-10-12 04:37:35,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 71925760. Throughput: 0: 1594.6, 1: 1569.9. Samples: 17993290. Policy #0 lag: (min: 16.0, avg: 31.5, max: 48.0) -[2023-10-12 04:37:35,201][77203] Avg episode reward: [(0, '45.340'), (1, '34.670')] -[2023-10-12 04:37:35,943][78091] Updated weights for policy 0, policy_version 35210 (0.0007) -[2023-10-12 04:37:36,022][78123] Updated weights for policy 1, policy_version 35050 (0.0008) -[2023-10-12 04:37:36,314][78091] Updated weights for policy 0, policy_version 35220 (0.0009) -[2023-10-12 04:37:36,389][78123] Updated weights for policy 1, policy_version 35060 (0.0007) -[2023-10-12 04:37:36,681][78091] Updated weights for policy 0, policy_version 35230 (0.0007) -[2023-10-12 04:37:36,758][78123] Updated weights for policy 1, policy_version 35070 (0.0008) -[2023-10-12 04:37:40,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 71991296. Throughput: 0: 1605.8, 1: 1582.9. Samples: 18013058. Policy #0 lag: (min: 16.0, avg: 31.5, max: 48.0) -[2023-10-12 04:37:40,202][77203] Avg episode reward: [(0, '42.670'), (1, '36.400')] -[2023-10-12 04:37:40,867][78091] Updated weights for policy 0, policy_version 35240 (0.0008) -[2023-10-12 04:37:41,203][78123] Updated weights for policy 1, policy_version 35080 (0.0007) -[2023-10-12 04:37:41,232][78091] Updated weights for policy 0, policy_version 35250 (0.0008) -[2023-10-12 04:37:41,572][78123] Updated weights for policy 1, policy_version 35090 (0.0007) -[2023-10-12 04:37:41,603][78091] Updated weights for policy 0, policy_version 35260 (0.0007) -[2023-10-12 04:37:41,933][78123] Updated weights for policy 1, policy_version 35100 (0.0008) -[2023-10-12 04:37:45,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 72056832. Throughput: 0: 1602.2, 1: 1567.5. Samples: 18021522. Policy #0 lag: (min: 16.0, avg: 31.5, max: 48.0) -[2023-10-12 04:37:45,202][77203] Avg episode reward: [(0, '45.370'), (1, '35.020')] -[2023-10-12 04:37:45,934][78091] Updated weights for policy 0, policy_version 35270 (0.0008) -[2023-10-12 04:37:46,177][78123] Updated weights for policy 1, policy_version 35110 (0.0008) -[2023-10-12 04:37:46,299][78091] Updated weights for policy 0, policy_version 35280 (0.0007) -[2023-10-12 04:37:46,541][78123] Updated weights for policy 1, policy_version 35120 (0.0008) -[2023-10-12 04:37:46,675][78091] Updated weights for policy 0, policy_version 35290 (0.0008) -[2023-10-12 04:37:46,909][78123] Updated weights for policy 1, policy_version 35130 (0.0009) -[2023-10-12 04:37:50,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 72122368. Throughput: 0: 1598.4, 1: 1563.3. Samples: 18040838. Policy #0 lag: (min: 16.0, avg: 31.5, max: 48.0) -[2023-10-12 04:37:50,202][77203] Avg episode reward: [(0, '50.060'), (1, '36.180')] -[2023-10-12 04:37:50,205][77792] Saving new best policy, reward=50.060! -[2023-10-12 04:37:51,093][78091] Updated weights for policy 0, policy_version 35300 (0.0008) -[2023-10-12 04:37:51,433][78123] Updated weights for policy 1, policy_version 35140 (0.0009) -[2023-10-12 04:37:51,469][78091] Updated weights for policy 0, policy_version 35310 (0.0007) -[2023-10-12 04:37:51,806][78123] Updated weights for policy 1, policy_version 35150 (0.0008) -[2023-10-12 04:37:51,846][78091] Updated weights for policy 0, policy_version 35320 (0.0009) -[2023-10-12 04:37:52,179][78123] Updated weights for policy 1, policy_version 35160 (0.0008) -[2023-10-12 04:37:55,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 72187904. Throughput: 0: 1596.4, 1: 1575.9. Samples: 18060270. Policy #0 lag: (min: 6.0, avg: 12.5, max: 38.0) -[2023-10-12 04:37:55,202][77203] Avg episode reward: [(0, '42.130'), (1, '43.290')] -[2023-10-12 04:37:56,160][78091] Updated weights for policy 0, policy_version 35330 (0.0010) -[2023-10-12 04:37:56,356][78123] Updated weights for policy 1, policy_version 35170 (0.0009) -[2023-10-12 04:37:56,525][78091] Updated weights for policy 0, policy_version 35340 (0.0008) -[2023-10-12 04:37:56,722][78123] Updated weights for policy 1, policy_version 35180 (0.0008) -[2023-10-12 04:37:56,902][78091] Updated weights for policy 0, policy_version 35350 (0.0009) -[2023-10-12 04:37:57,091][78123] Updated weights for policy 1, policy_version 35190 (0.0008) -[2023-10-12 04:37:57,268][78091] Updated weights for policy 0, policy_version 35360 (0.0007) -[2023-10-12 04:37:57,456][78123] Updated weights for policy 1, policy_version 35200 (0.0009) -[2023-10-12 04:38:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.1, 300 sec: 12662.9). Total num frames: 72253440. Throughput: 0: 1595.7, 1: 1574.3. Samples: 18068962. Policy #0 lag: (min: 6.0, avg: 12.5, max: 38.0) -[2023-10-12 04:38:00,202][77203] Avg episode reward: [(0, '45.740'), (1, '33.980')] -[2023-10-12 04:38:01,491][78091] Updated weights for policy 0, policy_version 35370 (0.0010) -[2023-10-12 04:38:01,865][78091] Updated weights for policy 0, policy_version 35380 (0.0008) -[2023-10-12 04:38:01,901][78123] Updated weights for policy 1, policy_version 35210 (0.0008) -[2023-10-12 04:38:02,238][78091] Updated weights for policy 0, policy_version 35390 (0.0008) -[2023-10-12 04:38:02,260][78123] Updated weights for policy 1, policy_version 35220 (0.0008) -[2023-10-12 04:38:02,628][78123] Updated weights for policy 1, policy_version 35230 (0.0007) -[2023-10-12 04:38:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 72318976. Throughput: 0: 1598.2, 1: 1581.9. Samples: 18088716. Policy #0 lag: (min: 6.0, avg: 12.5, max: 38.0) -[2023-10-12 04:38:05,202][77203] Avg episode reward: [(0, '43.390'), (1, '38.290')] -[2023-10-12 04:38:06,537][78091] Updated weights for policy 0, policy_version 35400 (0.0009) -[2023-10-12 04:38:06,571][78123] Updated weights for policy 1, policy_version 35240 (0.0008) -[2023-10-12 04:38:06,900][78091] Updated weights for policy 0, policy_version 35410 (0.0009) -[2023-10-12 04:38:06,937][78123] Updated weights for policy 1, policy_version 35250 (0.0009) -[2023-10-12 04:38:07,272][78091] Updated weights for policy 0, policy_version 35420 (0.0010) -[2023-10-12 04:38:07,305][78123] Updated weights for policy 1, policy_version 35260 (0.0009) -[2023-10-12 04:38:10,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 72384512. Throughput: 0: 1588.0, 1: 1594.1. Samples: 18108290. Policy #0 lag: (min: 6.0, avg: 12.5, max: 38.0) -[2023-10-12 04:38:10,202][77203] Avg episode reward: [(0, '38.200'), (1, '36.850')] -[2023-10-12 04:38:11,629][78123] Updated weights for policy 1, policy_version 35270 (0.0008) -[2023-10-12 04:38:11,659][78091] Updated weights for policy 0, policy_version 35430 (0.0009) -[2023-10-12 04:38:12,004][78123] Updated weights for policy 1, policy_version 35280 (0.0008) -[2023-10-12 04:38:12,019][78091] Updated weights for policy 0, policy_version 35440 (0.0007) -[2023-10-12 04:38:12,358][78123] Updated weights for policy 1, policy_version 35290 (0.0008) -[2023-10-12 04:38:12,388][78091] Updated weights for policy 0, policy_version 35450 (0.0008) -[2023-10-12 04:38:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 72450048. Throughput: 0: 1588.8, 1: 1591.8. Samples: 18116874. Policy #0 lag: (min: 6.0, avg: 12.5, max: 38.0) -[2023-10-12 04:38:15,201][77203] Avg episode reward: [(0, '42.450'), (1, '35.790')] -[2023-10-12 04:38:16,622][78123] Updated weights for policy 1, policy_version 35300 (0.0009) -[2023-10-12 04:38:16,810][78091] Updated weights for policy 0, policy_version 35460 (0.0008) -[2023-10-12 04:38:16,994][78123] Updated weights for policy 1, policy_version 35310 (0.0007) -[2023-10-12 04:38:17,179][78091] Updated weights for policy 0, policy_version 35470 (0.0009) -[2023-10-12 04:38:17,354][78123] Updated weights for policy 1, policy_version 35320 (0.0009) -[2023-10-12 04:38:17,561][78091] Updated weights for policy 0, policy_version 35480 (0.0011) -[2023-10-12 04:38:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 72515584. Throughput: 0: 1583.5, 1: 1596.0. Samples: 18136368. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-12 04:38:20,202][77203] Avg episode reward: [(0, '46.380'), (1, '41.720')] -[2023-10-12 04:38:21,789][78123] Updated weights for policy 1, policy_version 35330 (0.0009) -[2023-10-12 04:38:22,159][78123] Updated weights for policy 1, policy_version 35340 (0.0009) -[2023-10-12 04:38:22,211][78091] Updated weights for policy 0, policy_version 35490 (0.0009) -[2023-10-12 04:38:22,525][78123] Updated weights for policy 1, policy_version 35350 (0.0008) -[2023-10-12 04:38:22,601][78091] Updated weights for policy 0, policy_version 35500 (0.0007) -[2023-10-12 04:38:22,884][78123] Updated weights for policy 1, policy_version 35360 (0.0008) -[2023-10-12 04:38:22,980][78091] Updated weights for policy 0, policy_version 35510 (0.0008) -[2023-10-12 04:38:23,343][78091] Updated weights for policy 0, policy_version 35520 (0.0009) -[2023-10-12 04:38:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 72581120. Throughput: 0: 1571.6, 1: 1600.4. Samples: 18155796. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-12 04:38:25,202][77203] Avg episode reward: [(0, '38.030'), (1, '36.410')] -[2023-10-12 04:38:27,163][78123] Updated weights for policy 1, policy_version 35370 (0.0009) -[2023-10-12 04:38:27,448][78091] Updated weights for policy 0, policy_version 35530 (0.0008) -[2023-10-12 04:38:27,524][78123] Updated weights for policy 1, policy_version 35380 (0.0008) -[2023-10-12 04:38:27,809][78091] Updated weights for policy 0, policy_version 35540 (0.0009) -[2023-10-12 04:38:27,890][78123] Updated weights for policy 1, policy_version 35390 (0.0009) -[2023-10-12 04:38:28,180][78091] Updated weights for policy 0, policy_version 35550 (0.0010) -[2023-10-12 04:38:30,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 72646656. Throughput: 0: 1585.9, 1: 1606.5. Samples: 18165180. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-12 04:38:30,201][77203] Avg episode reward: [(0, '45.900'), (1, '35.420')] -[2023-10-12 04:38:32,186][78123] Updated weights for policy 1, policy_version 35400 (0.0009) -[2023-10-12 04:38:32,546][78091] Updated weights for policy 0, policy_version 35560 (0.0009) -[2023-10-12 04:38:32,552][78123] Updated weights for policy 1, policy_version 35410 (0.0009) -[2023-10-12 04:38:32,909][78123] Updated weights for policy 1, policy_version 35420 (0.0009) -[2023-10-12 04:38:32,930][78091] Updated weights for policy 0, policy_version 35570 (0.0008) -[2023-10-12 04:38:33,295][78091] Updated weights for policy 0, policy_version 35580 (0.0010) -[2023-10-12 04:38:35,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 72712192. Throughput: 0: 1576.4, 1: 1602.9. Samples: 18183908. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-12 04:38:35,202][77203] Avg episode reward: [(0, '44.650'), (1, '42.860')] -[2023-10-12 04:38:37,407][78123] Updated weights for policy 1, policy_version 35430 (0.0009) -[2023-10-12 04:38:37,474][78091] Updated weights for policy 0, policy_version 35590 (0.0010) -[2023-10-12 04:38:37,774][78123] Updated weights for policy 1, policy_version 35440 (0.0009) -[2023-10-12 04:38:37,844][78091] Updated weights for policy 0, policy_version 35600 (0.0009) -[2023-10-12 04:38:38,132][78123] Updated weights for policy 1, policy_version 35450 (0.0008) -[2023-10-12 04:38:38,221][78091] Updated weights for policy 0, policy_version 35610 (0.0009) -[2023-10-12 04:38:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 72777728. Throughput: 0: 1580.2, 1: 1598.9. Samples: 18203328. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-12 04:38:40,202][77203] Avg episode reward: [(0, '38.930'), (1, '39.170')] -[2023-10-12 04:38:42,463][78091] Updated weights for policy 0, policy_version 35620 (0.0008) -[2023-10-12 04:38:42,510][78123] Updated weights for policy 1, policy_version 35460 (0.0008) -[2023-10-12 04:38:42,845][78091] Updated weights for policy 0, policy_version 35630 (0.0009) -[2023-10-12 04:38:42,875][78123] Updated weights for policy 1, policy_version 35470 (0.0008) -[2023-10-12 04:38:43,216][78091] Updated weights for policy 0, policy_version 35640 (0.0009) -[2023-10-12 04:38:43,236][78123] Updated weights for policy 1, policy_version 35480 (0.0008) -[2023-10-12 04:38:45,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 72843264. Throughput: 0: 1595.6, 1: 1615.2. Samples: 18213446. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:38:45,202][77203] Avg episode reward: [(0, '44.380'), (1, '36.650')] -[2023-10-12 04:38:47,490][78091] Updated weights for policy 0, policy_version 35650 (0.0007) -[2023-10-12 04:38:47,598][78123] Updated weights for policy 1, policy_version 35490 (0.0008) -[2023-10-12 04:38:47,845][78091] Updated weights for policy 0, policy_version 35660 (0.0008) -[2023-10-12 04:38:47,965][78123] Updated weights for policy 1, policy_version 35500 (0.0007) -[2023-10-12 04:38:48,218][78091] Updated weights for policy 0, policy_version 35670 (0.0010) -[2023-10-12 04:38:48,334][78123] Updated weights for policy 1, policy_version 35510 (0.0008) -[2023-10-12 04:38:48,588][78091] Updated weights for policy 0, policy_version 35680 (0.0009) -[2023-10-12 04:38:48,714][78123] Updated weights for policy 1, policy_version 35520 (0.0008) -[2023-10-12 04:38:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 72908800. Throughput: 0: 1579.6, 1: 1591.8. Samples: 18231428. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:38:50,202][77203] Avg episode reward: [(0, '45.740'), (1, '36.660')] -[2023-10-12 04:38:53,059][78091] Updated weights for policy 0, policy_version 35690 (0.0008) -[2023-10-12 04:38:53,265][78123] Updated weights for policy 1, policy_version 35530 (0.0007) -[2023-10-12 04:38:53,425][78091] Updated weights for policy 0, policy_version 35700 (0.0009) -[2023-10-12 04:38:53,629][78123] Updated weights for policy 1, policy_version 35540 (0.0008) -[2023-10-12 04:38:53,797][78091] Updated weights for policy 0, policy_version 35710 (0.0008) -[2023-10-12 04:38:54,003][78123] Updated weights for policy 1, policy_version 35550 (0.0009) -[2023-10-12 04:38:55,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 72974336. Throughput: 0: 1585.6, 1: 1583.5. Samples: 18250900. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:38:55,201][77203] Avg episode reward: [(0, '42.300'), (1, '38.750')] -[2023-10-12 04:38:58,146][78091] Updated weights for policy 0, policy_version 35720 (0.0007) -[2023-10-12 04:38:58,245][78123] Updated weights for policy 1, policy_version 35560 (0.0010) -[2023-10-12 04:38:58,522][78091] Updated weights for policy 0, policy_version 35730 (0.0007) -[2023-10-12 04:38:58,605][78123] Updated weights for policy 1, policy_version 35570 (0.0007) -[2023-10-12 04:38:58,902][78091] Updated weights for policy 0, policy_version 35740 (0.0009) -[2023-10-12 04:38:58,973][78123] Updated weights for policy 1, policy_version 35580 (0.0009) -[2023-10-12 04:39:00,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 73039872. Throughput: 0: 1614.0, 1: 1606.5. Samples: 18261798. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:39:00,202][77203] Avg episode reward: [(0, '42.910'), (1, '34.980')] -[2023-10-12 04:39:03,084][78091] Updated weights for policy 0, policy_version 35750 (0.0009) -[2023-10-12 04:39:03,265][78123] Updated weights for policy 1, policy_version 35590 (0.0008) -[2023-10-12 04:39:03,461][78091] Updated weights for policy 0, policy_version 35760 (0.0010) -[2023-10-12 04:39:03,634][78123] Updated weights for policy 1, policy_version 35600 (0.0009) -[2023-10-12 04:39:03,836][78091] Updated weights for policy 0, policy_version 35770 (0.0008) -[2023-10-12 04:39:04,002][78123] Updated weights for policy 1, policy_version 35610 (0.0009) -[2023-10-12 04:39:05,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 73105408. Throughput: 0: 1597.2, 1: 1590.3. Samples: 18279802. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:39:05,202][77203] Avg episode reward: [(0, '45.370'), (1, '39.250')] -[2023-10-12 04:39:08,275][78091] Updated weights for policy 0, policy_version 35780 (0.0008) -[2023-10-12 04:39:08,518][78123] Updated weights for policy 1, policy_version 35620 (0.0009) -[2023-10-12 04:39:08,657][78091] Updated weights for policy 0, policy_version 35790 (0.0009) -[2023-10-12 04:39:08,876][78123] Updated weights for policy 1, policy_version 35630 (0.0008) -[2023-10-12 04:39:09,021][78091] Updated weights for policy 0, policy_version 35800 (0.0008) -[2023-10-12 04:39:09,236][78123] Updated weights for policy 1, policy_version 35640 (0.0010) -[2023-10-12 04:39:10,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 73170944. Throughput: 0: 1596.1, 1: 1571.0. Samples: 18298316. Policy #0 lag: (min: 31.0, avg: 31.2, max: 40.0) -[2023-10-12 04:39:10,201][77203] Avg episode reward: [(0, '46.470'), (1, '43.130')] -[2023-10-12 04:39:10,208][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000035648_36503552.pth... -[2023-10-12 04:39:10,208][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000035808_36667392.pth... -[2023-10-12 04:39:10,246][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000034144_34963456.pth -[2023-10-12 04:39:10,250][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000034304_35127296.pth -[2023-10-12 04:39:13,501][78091] Updated weights for policy 0, policy_version 35810 (0.0009) -[2023-10-12 04:39:13,729][78123] Updated weights for policy 1, policy_version 35650 (0.0010) -[2023-10-12 04:39:13,871][78091] Updated weights for policy 0, policy_version 35820 (0.0009) -[2023-10-12 04:39:14,115][78123] Updated weights for policy 1, policy_version 35660 (0.0008) -[2023-10-12 04:39:14,234][78091] Updated weights for policy 0, policy_version 35830 (0.0009) -[2023-10-12 04:39:14,487][78123] Updated weights for policy 1, policy_version 35670 (0.0009) -[2023-10-12 04:39:14,615][78091] Updated weights for policy 0, policy_version 35840 (0.0007) -[2023-10-12 04:39:14,852][78123] Updated weights for policy 1, policy_version 35680 (0.0008) -[2023-10-12 04:39:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 73236480. Throughput: 0: 1607.7, 1: 1588.1. Samples: 18308994. Policy #0 lag: (min: 31.0, avg: 31.2, max: 40.0) -[2023-10-12 04:39:15,202][77203] Avg episode reward: [(0, '38.290'), (1, '32.610')] -[2023-10-12 04:39:18,903][78091] Updated weights for policy 0, policy_version 35850 (0.0008) -[2023-10-12 04:39:18,984][78123] Updated weights for policy 1, policy_version 35690 (0.0008) -[2023-10-12 04:39:19,293][78091] Updated weights for policy 0, policy_version 35860 (0.0008) -[2023-10-12 04:39:19,358][78123] Updated weights for policy 1, policy_version 35700 (0.0009) -[2023-10-12 04:39:19,667][78091] Updated weights for policy 0, policy_version 35870 (0.0009) -[2023-10-12 04:39:19,725][78123] Updated weights for policy 1, policy_version 35710 (0.0009) -[2023-10-12 04:39:20,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 73302016. Throughput: 0: 1612.4, 1: 1594.0. Samples: 18328196. Policy #0 lag: (min: 31.0, avg: 31.2, max: 40.0) -[2023-10-12 04:39:20,202][77203] Avg episode reward: [(0, '44.600'), (1, '37.810')] -[2023-10-12 04:39:23,923][78123] Updated weights for policy 1, policy_version 35720 (0.0009) -[2023-10-12 04:39:23,937][78091] Updated weights for policy 0, policy_version 35880 (0.0009) -[2023-10-12 04:39:24,289][78123] Updated weights for policy 1, policy_version 35730 (0.0008) -[2023-10-12 04:39:24,306][78091] Updated weights for policy 0, policy_version 35890 (0.0010) -[2023-10-12 04:39:24,666][78123] Updated weights for policy 1, policy_version 35740 (0.0007) -[2023-10-12 04:39:24,677][78091] Updated weights for policy 0, policy_version 35900 (0.0008) -[2023-10-12 04:39:25,201][77203] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 12885.0). Total num frames: 73367552. Throughput: 0: 1593.3, 1: 1577.7. Samples: 18346024. Policy #0 lag: (min: 31.0, avg: 31.2, max: 40.0) -[2023-10-12 04:39:25,203][77203] Avg episode reward: [(0, '46.010'), (1, '40.400')] -[2023-10-12 04:39:28,934][78091] Updated weights for policy 0, policy_version 35910 (0.0007) -[2023-10-12 04:39:28,985][78123] Updated weights for policy 1, policy_version 35750 (0.0008) -[2023-10-12 04:39:29,301][78091] Updated weights for policy 0, policy_version 35920 (0.0009) -[2023-10-12 04:39:29,352][78123] Updated weights for policy 1, policy_version 35760 (0.0009) -[2023-10-12 04:39:29,681][78091] Updated weights for policy 0, policy_version 35930 (0.0008) -[2023-10-12 04:39:29,714][78123] Updated weights for policy 1, policy_version 35770 (0.0009) -[2023-10-12 04:39:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 73433088. Throughput: 0: 1599.7, 1: 1584.1. Samples: 18356718. Policy #0 lag: (min: 31.0, avg: 31.2, max: 40.0) -[2023-10-12 04:39:30,202][77203] Avg episode reward: [(0, '43.040'), (1, '34.240')] -[2023-10-12 04:39:34,029][78123] Updated weights for policy 1, policy_version 35780 (0.0007) -[2023-10-12 04:39:34,132][78091] Updated weights for policy 0, policy_version 35940 (0.0007) -[2023-10-12 04:39:34,397][78123] Updated weights for policy 1, policy_version 35790 (0.0007) -[2023-10-12 04:39:34,502][78091] Updated weights for policy 0, policy_version 35950 (0.0009) -[2023-10-12 04:39:34,760][78123] Updated weights for policy 1, policy_version 35800 (0.0007) -[2023-10-12 04:39:34,862][78091] Updated weights for policy 0, policy_version 35960 (0.0008) -[2023-10-12 04:39:35,201][77203] Fps is (10 sec: 13107.7, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 73498624. Throughput: 0: 1615.0, 1: 1607.5. Samples: 18376442. Policy #0 lag: (min: 31.0, avg: 31.7, max: 48.0) -[2023-10-12 04:39:35,201][77203] Avg episode reward: [(0, '45.220'), (1, '40.450')] -[2023-10-12 04:39:39,131][78091] Updated weights for policy 0, policy_version 35970 (0.0007) -[2023-10-12 04:39:39,142][78123] Updated weights for policy 1, policy_version 35810 (0.0009) -[2023-10-12 04:39:39,505][78091] Updated weights for policy 0, policy_version 35980 (0.0009) -[2023-10-12 04:39:39,511][78123] Updated weights for policy 1, policy_version 35820 (0.0008) -[2023-10-12 04:39:39,868][78123] Updated weights for policy 1, policy_version 35830 (0.0008) -[2023-10-12 04:39:39,890][78091] Updated weights for policy 0, policy_version 35990 (0.0007) -[2023-10-12 04:39:40,201][77203] Fps is (10 sec: 6553.6, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 73498624. Throughput: 0: 1596.8, 1: 1593.5. Samples: 18394468. Policy #0 lag: (min: 31.0, avg: 31.7, max: 48.0) -[2023-10-12 04:39:40,202][77203] Avg episode reward: [(0, '49.440'), (1, '34.280')] -[2023-10-12 04:39:40,235][78123] Updated weights for policy 1, policy_version 35840 (0.0008) -[2023-10-12 04:39:40,250][78091] Updated weights for policy 0, policy_version 36000 (0.0009) -[2023-10-12 04:39:44,424][78091] Updated weights for policy 0, policy_version 36010 (0.0008) -[2023-10-12 04:39:44,722][78123] Updated weights for policy 1, policy_version 35850 (0.0008) -[2023-10-12 04:39:44,786][78091] Updated weights for policy 0, policy_version 36020 (0.0008) -[2023-10-12 04:39:45,085][78123] Updated weights for policy 1, policy_version 35860 (0.0008) -[2023-10-12 04:39:45,155][78091] Updated weights for policy 0, policy_version 36030 (0.0008) -[2023-10-12 04:39:45,201][77203] Fps is (10 sec: 6553.6, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 73564160. Throughput: 0: 1583.4, 1: 1583.0. Samples: 18404288. Policy #0 lag: (min: 31.0, avg: 31.7, max: 48.0) -[2023-10-12 04:39:45,201][77203] Avg episode reward: [(0, '40.040'), (1, '37.920')] -[2023-10-12 04:39:45,455][78123] Updated weights for policy 1, policy_version 35870 (0.0007) -[2023-10-12 04:39:49,550][78091] Updated weights for policy 0, policy_version 36040 (0.0008) -[2023-10-12 04:39:49,855][78123] Updated weights for policy 1, policy_version 35880 (0.0009) -[2023-10-12 04:39:49,917][78091] Updated weights for policy 0, policy_version 36050 (0.0010) -[2023-10-12 04:39:50,201][77203] Fps is (10 sec: 13107.6, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 73629696. Throughput: 0: 1603.6, 1: 1590.4. Samples: 18423528. Policy #0 lag: (min: 31.0, avg: 31.7, max: 48.0) -[2023-10-12 04:39:50,201][77203] Avg episode reward: [(0, '41.870'), (1, '42.400')] -[2023-10-12 04:39:50,216][78123] Updated weights for policy 1, policy_version 35890 (0.0009) -[2023-10-12 04:39:50,287][78091] Updated weights for policy 0, policy_version 36060 (0.0009) -[2023-10-12 04:39:50,589][78123] Updated weights for policy 1, policy_version 35900 (0.0009) -[2023-10-12 04:39:54,741][78091] Updated weights for policy 0, policy_version 36070 (0.0009) -[2023-10-12 04:39:54,926][78123] Updated weights for policy 1, policy_version 35910 (0.0008) -[2023-10-12 04:39:55,121][78091] Updated weights for policy 0, policy_version 36080 (0.0008) -[2023-10-12 04:39:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 73695232. Throughput: 0: 1599.8, 1: 1605.6. Samples: 18442556. Policy #0 lag: (min: 31.0, avg: 31.7, max: 48.0) -[2023-10-12 04:39:55,201][77203] Avg episode reward: [(0, '45.920'), (1, '34.200')] -[2023-10-12 04:39:55,282][78123] Updated weights for policy 1, policy_version 35920 (0.0007) -[2023-10-12 04:39:55,484][78091] Updated weights for policy 0, policy_version 36090 (0.0009) -[2023-10-12 04:39:55,651][78123] Updated weights for policy 1, policy_version 35930 (0.0009) -[2023-10-12 04:39:59,767][78091] Updated weights for policy 0, policy_version 36100 (0.0008) -[2023-10-12 04:40:00,084][78123] Updated weights for policy 1, policy_version 35940 (0.0008) -[2023-10-12 04:40:00,130][78091] Updated weights for policy 0, policy_version 36110 (0.0008) -[2023-10-12 04:40:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 73760768. Throughput: 0: 1582.3, 1: 1585.5. Samples: 18451542. Policy #0 lag: (min: 31.0, avg: 31.7, max: 48.0) -[2023-10-12 04:40:00,201][77203] Avg episode reward: [(0, '41.490'), (1, '40.270')] -[2023-10-12 04:40:00,486][78123] Updated weights for policy 1, policy_version 35950 (0.0008) -[2023-10-12 04:40:00,504][78091] Updated weights for policy 0, policy_version 36120 (0.0009) -[2023-10-12 04:40:00,850][78123] Updated weights for policy 1, policy_version 35960 (0.0009) -[2023-10-12 04:40:04,940][78091] Updated weights for policy 0, policy_version 36130 (0.0008) -[2023-10-12 04:40:05,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 73826304. Throughput: 0: 1588.0, 1: 1579.6. Samples: 18470740. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:40:05,202][77203] Avg episode reward: [(0, '43.460'), (1, '42.200')] -[2023-10-12 04:40:05,277][78123] Updated weights for policy 1, policy_version 35970 (0.0008) -[2023-10-12 04:40:05,324][78091] Updated weights for policy 0, policy_version 36140 (0.0007) -[2023-10-12 04:40:05,637][78123] Updated weights for policy 1, policy_version 35980 (0.0008) -[2023-10-12 04:40:05,687][78091] Updated weights for policy 0, policy_version 36150 (0.0009) -[2023-10-12 04:40:05,991][78123] Updated weights for policy 1, policy_version 35990 (0.0009) -[2023-10-12 04:40:06,044][78091] Updated weights for policy 0, policy_version 36160 (0.0009) -[2023-10-12 04:40:06,353][78123] Updated weights for policy 1, policy_version 36000 (0.0007) -[2023-10-12 04:40:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 73891840. Throughput: 0: 1609.0, 1: 1599.1. Samples: 18490388. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:40:10,201][77203] Avg episode reward: [(0, '47.630'), (1, '32.260')] -[2023-10-12 04:40:10,268][78091] Updated weights for policy 0, policy_version 36170 (0.0008) -[2023-10-12 04:40:10,641][78091] Updated weights for policy 0, policy_version 36180 (0.0007) -[2023-10-12 04:40:10,773][78123] Updated weights for policy 1, policy_version 36010 (0.0007) -[2023-10-12 04:40:11,015][78091] Updated weights for policy 0, policy_version 36190 (0.0008) -[2023-10-12 04:40:11,139][78123] Updated weights for policy 1, policy_version 36020 (0.0008) -[2023-10-12 04:40:11,495][78123] Updated weights for policy 1, policy_version 36030 (0.0008) -[2023-10-12 04:40:15,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 73957376. Throughput: 0: 1585.3, 1: 1575.3. Samples: 18498946. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:40:15,201][77203] Avg episode reward: [(0, '49.630'), (1, '38.880')] -[2023-10-12 04:40:15,475][78091] Updated weights for policy 0, policy_version 36200 (0.0007) -[2023-10-12 04:40:15,754][78123] Updated weights for policy 1, policy_version 36040 (0.0009) -[2023-10-12 04:40:15,860][78091] Updated weights for policy 0, policy_version 36210 (0.0008) -[2023-10-12 04:40:16,114][78123] Updated weights for policy 1, policy_version 36050 (0.0008) -[2023-10-12 04:40:16,219][78091] Updated weights for policy 0, policy_version 36220 (0.0009) -[2023-10-12 04:40:16,487][78123] Updated weights for policy 1, policy_version 36060 (0.0008) -[2023-10-12 04:40:20,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 74022912. Throughput: 0: 1583.1, 1: 1568.8. Samples: 18518276. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:40:20,202][77203] Avg episode reward: [(0, '40.620'), (1, '37.380')] -[2023-10-12 04:40:20,445][78091] Updated weights for policy 0, policy_version 36230 (0.0009) -[2023-10-12 04:40:20,809][78091] Updated weights for policy 0, policy_version 36240 (0.0009) -[2023-10-12 04:40:20,889][78123] Updated weights for policy 1, policy_version 36070 (0.0008) -[2023-10-12 04:40:21,179][78091] Updated weights for policy 0, policy_version 36250 (0.0009) -[2023-10-12 04:40:21,250][78123] Updated weights for policy 1, policy_version 36080 (0.0008) -[2023-10-12 04:40:21,612][78123] Updated weights for policy 1, policy_version 36090 (0.0008) -[2023-10-12 04:40:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 74088448. Throughput: 0: 1600.5, 1: 1582.9. Samples: 18537720. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:40:25,201][77203] Avg episode reward: [(0, '46.020'), (1, '37.640')] -[2023-10-12 04:40:25,539][78091] Updated weights for policy 0, policy_version 36260 (0.0010) -[2023-10-12 04:40:25,908][78091] Updated weights for policy 0, policy_version 36270 (0.0010) -[2023-10-12 04:40:26,011][78123] Updated weights for policy 1, policy_version 36100 (0.0009) -[2023-10-12 04:40:26,275][78091] Updated weights for policy 0, policy_version 36280 (0.0009) -[2023-10-12 04:40:26,381][78123] Updated weights for policy 1, policy_version 36110 (0.0008) -[2023-10-12 04:40:26,753][78123] Updated weights for policy 1, policy_version 36120 (0.0009) -[2023-10-12 04:40:30,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 74153984. Throughput: 0: 1586.9, 1: 1567.6. Samples: 18546242. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-12 04:40:30,202][77203] Avg episode reward: [(0, '47.910'), (1, '39.910')] -[2023-10-12 04:40:30,582][78091] Updated weights for policy 0, policy_version 36290 (0.0009) -[2023-10-12 04:40:30,959][78091] Updated weights for policy 0, policy_version 36300 (0.0009) -[2023-10-12 04:40:31,181][78123] Updated weights for policy 1, policy_version 36130 (0.0008) -[2023-10-12 04:40:31,327][78091] Updated weights for policy 0, policy_version 36310 (0.0009) -[2023-10-12 04:40:31,550][78123] Updated weights for policy 1, policy_version 36140 (0.0008) -[2023-10-12 04:40:31,691][78091] Updated weights for policy 0, policy_version 36320 (0.0008) -[2023-10-12 04:40:31,906][78123] Updated weights for policy 1, policy_version 36150 (0.0008) -[2023-10-12 04:40:32,277][78123] Updated weights for policy 1, policy_version 36160 (0.0008) -[2023-10-12 04:40:35,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 74219520. Throughput: 0: 1583.6, 1: 1574.7. Samples: 18565656. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-12 04:40:35,202][77203] Avg episode reward: [(0, '41.610'), (1, '39.470')] -[2023-10-12 04:40:35,937][78091] Updated weights for policy 0, policy_version 36330 (0.0007) -[2023-10-12 04:40:36,302][78091] Updated weights for policy 0, policy_version 36340 (0.0009) -[2023-10-12 04:40:36,602][78123] Updated weights for policy 1, policy_version 36170 (0.0007) -[2023-10-12 04:40:36,672][78091] Updated weights for policy 0, policy_version 36350 (0.0008) -[2023-10-12 04:40:36,976][78123] Updated weights for policy 1, policy_version 36180 (0.0008) -[2023-10-12 04:40:37,339][78123] Updated weights for policy 1, policy_version 36190 (0.0009) -[2023-10-12 04:40:40,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 74285056. Throughput: 0: 1596.0, 1: 1572.0. Samples: 18585116. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-12 04:40:40,201][77203] Avg episode reward: [(0, '43.150'), (1, '37.670')] -[2023-10-12 04:40:41,155][78091] Updated weights for policy 0, policy_version 36360 (0.0007) -[2023-10-12 04:40:41,527][78091] Updated weights for policy 0, policy_version 36370 (0.0007) -[2023-10-12 04:40:41,793][78123] Updated weights for policy 1, policy_version 36200 (0.0009) -[2023-10-12 04:40:41,895][78091] Updated weights for policy 0, policy_version 36380 (0.0008) -[2023-10-12 04:40:42,164][78123] Updated weights for policy 1, policy_version 36210 (0.0009) -[2023-10-12 04:40:42,534][78123] Updated weights for policy 1, policy_version 36220 (0.0009) -[2023-10-12 04:40:45,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 74350592. Throughput: 0: 1589.3, 1: 1566.7. Samples: 18593562. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-12 04:40:45,201][77203] Avg episode reward: [(0, '45.370'), (1, '37.350')] -[2023-10-12 04:40:45,994][78091] Updated weights for policy 0, policy_version 36390 (0.0007) -[2023-10-12 04:40:46,361][78091] Updated weights for policy 0, policy_version 36400 (0.0007) -[2023-10-12 04:40:46,720][78091] Updated weights for policy 0, policy_version 36410 (0.0008) -[2023-10-12 04:40:46,944][78123] Updated weights for policy 1, policy_version 36230 (0.0008) -[2023-10-12 04:40:47,315][78123] Updated weights for policy 1, policy_version 36240 (0.0008) -[2023-10-12 04:40:47,682][78123] Updated weights for policy 1, policy_version 36250 (0.0009) -[2023-10-12 04:40:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 74416128. Throughput: 0: 1594.5, 1: 1568.8. Samples: 18613090. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-12 04:40:50,202][77203] Avg episode reward: [(0, '47.680'), (1, '39.650')] -[2023-10-12 04:40:50,991][78091] Updated weights for policy 0, policy_version 36420 (0.0008) -[2023-10-12 04:40:51,358][78091] Updated weights for policy 0, policy_version 36430 (0.0008) -[2023-10-12 04:40:51,736][78091] Updated weights for policy 0, policy_version 36440 (0.0008) -[2023-10-12 04:40:52,061][78123] Updated weights for policy 1, policy_version 36260 (0.0007) -[2023-10-12 04:40:52,449][78123] Updated weights for policy 1, policy_version 36270 (0.0007) -[2023-10-12 04:40:52,819][78123] Updated weights for policy 1, policy_version 36280 (0.0009) -[2023-10-12 04:40:55,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 74481664. Throughput: 0: 1591.9, 1: 1564.7. Samples: 18632436. Policy #0 lag: (min: 11.0, avg: 12.5, max: 38.0) -[2023-10-12 04:40:55,202][77203] Avg episode reward: [(0, '44.610'), (1, '39.460')] -[2023-10-12 04:40:56,120][78091] Updated weights for policy 0, policy_version 36450 (0.0008) -[2023-10-12 04:40:56,500][78091] Updated weights for policy 0, policy_version 36460 (0.0008) -[2023-10-12 04:40:56,874][78091] Updated weights for policy 0, policy_version 36470 (0.0011) -[2023-10-12 04:40:57,213][78123] Updated weights for policy 1, policy_version 36290 (0.0010) -[2023-10-12 04:40:57,252][78091] Updated weights for policy 0, policy_version 36480 (0.0008) -[2023-10-12 04:40:57,582][78123] Updated weights for policy 1, policy_version 36300 (0.0010) -[2023-10-12 04:40:57,957][78123] Updated weights for policy 1, policy_version 36310 (0.0010) -[2023-10-12 04:40:58,321][78123] Updated weights for policy 1, policy_version 36320 (0.0009) -[2023-10-12 04:41:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 74547200. Throughput: 0: 1591.7, 1: 1579.8. Samples: 18641664. Policy #0 lag: (min: 11.0, avg: 12.5, max: 38.0) -[2023-10-12 04:41:00,201][77203] Avg episode reward: [(0, '43.070'), (1, '36.400')] -[2023-10-12 04:41:01,388][78091] Updated weights for policy 0, policy_version 36490 (0.0008) -[2023-10-12 04:41:01,765][78091] Updated weights for policy 0, policy_version 36500 (0.0008) -[2023-10-12 04:41:02,143][78091] Updated weights for policy 0, policy_version 36510 (0.0009) -[2023-10-12 04:41:02,508][78123] Updated weights for policy 1, policy_version 36330 (0.0009) -[2023-10-12 04:41:02,873][78123] Updated weights for policy 1, policy_version 36340 (0.0008) -[2023-10-12 04:41:03,250][78123] Updated weights for policy 1, policy_version 36350 (0.0008) -[2023-10-12 04:41:05,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 74612736. Throughput: 0: 1596.4, 1: 1570.4. Samples: 18660782. Policy #0 lag: (min: 11.0, avg: 12.5, max: 38.0) -[2023-10-12 04:41:05,202][77203] Avg episode reward: [(0, '44.980'), (1, '42.960')] -[2023-10-12 04:41:06,465][78091] Updated weights for policy 0, policy_version 36520 (0.0009) -[2023-10-12 04:41:06,834][78091] Updated weights for policy 0, policy_version 36530 (0.0007) -[2023-10-12 04:41:07,208][78091] Updated weights for policy 0, policy_version 36540 (0.0009) -[2023-10-12 04:41:07,466][78123] Updated weights for policy 1, policy_version 36360 (0.0009) -[2023-10-12 04:41:07,830][78123] Updated weights for policy 1, policy_version 36370 (0.0007) -[2023-10-12 04:41:08,199][78123] Updated weights for policy 1, policy_version 36380 (0.0009) -[2023-10-12 04:41:10,201][77203] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 12662.9). Total num frames: 74678272. Throughput: 0: 1594.3, 1: 1574.8. Samples: 18680334. Policy #0 lag: (min: 11.0, avg: 12.5, max: 38.0) -[2023-10-12 04:41:10,202][77203] Avg episode reward: [(0, '42.680'), (1, '36.670')] -[2023-10-12 04:41:10,213][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000036384_37257216.pth... -[2023-10-12 04:41:10,214][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000036544_37421056.pth... -[2023-10-12 04:41:10,253][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000035072_35913728.pth -[2023-10-12 04:41:10,254][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000034912_35749888.pth -[2023-10-12 04:41:11,586][78091] Updated weights for policy 0, policy_version 36550 (0.0008) -[2023-10-12 04:41:11,960][78091] Updated weights for policy 0, policy_version 36560 (0.0008) -[2023-10-12 04:41:12,335][78091] Updated weights for policy 0, policy_version 36570 (0.0009) -[2023-10-12 04:41:12,621][78123] Updated weights for policy 1, policy_version 36390 (0.0008) -[2023-10-12 04:41:12,979][78123] Updated weights for policy 1, policy_version 36400 (0.0007) -[2023-10-12 04:41:13,355][78123] Updated weights for policy 1, policy_version 36410 (0.0009) -[2023-10-12 04:41:15,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 74743808. Throughput: 0: 1592.3, 1: 1594.4. Samples: 18689644. Policy #0 lag: (min: 11.0, avg: 12.5, max: 38.0) -[2023-10-12 04:41:15,201][77203] Avg episode reward: [(0, '46.210'), (1, '37.830')] -[2023-10-12 04:41:16,635][78091] Updated weights for policy 0, policy_version 36580 (0.0008) -[2023-10-12 04:41:17,001][78091] Updated weights for policy 0, policy_version 36590 (0.0009) -[2023-10-12 04:41:17,378][78091] Updated weights for policy 0, policy_version 36600 (0.0008) -[2023-10-12 04:41:17,716][78123] Updated weights for policy 1, policy_version 36420 (0.0009) -[2023-10-12 04:41:18,087][78123] Updated weights for policy 1, policy_version 36430 (0.0007) -[2023-10-12 04:41:18,456][78123] Updated weights for policy 1, policy_version 36440 (0.0007) -[2023-10-12 04:41:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 74809344. Throughput: 0: 1599.0, 1: 1577.0. Samples: 18708576. Policy #0 lag: (min: 1.0, avg: 15.8, max: 33.0) -[2023-10-12 04:41:20,202][77203] Avg episode reward: [(0, '46.880'), (1, '41.290')] -[2023-10-12 04:41:21,710][78091] Updated weights for policy 0, policy_version 36610 (0.0008) -[2023-10-12 04:41:22,089][78091] Updated weights for policy 0, policy_version 36620 (0.0010) -[2023-10-12 04:41:22,453][78091] Updated weights for policy 0, policy_version 36630 (0.0010) -[2023-10-12 04:41:22,823][78091] Updated weights for policy 0, policy_version 36640 (0.0010) -[2023-10-12 04:41:22,854][78123] Updated weights for policy 1, policy_version 36450 (0.0009) -[2023-10-12 04:41:23,226][78123] Updated weights for policy 1, policy_version 36460 (0.0008) -[2023-10-12 04:41:23,596][78123] Updated weights for policy 1, policy_version 36470 (0.0008) -[2023-10-12 04:41:23,958][78123] Updated weights for policy 1, policy_version 36480 (0.0010) -[2023-10-12 04:41:25,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 74874880. Throughput: 0: 1593.4, 1: 1579.6. Samples: 18727900. Policy #0 lag: (min: 1.0, avg: 15.8, max: 33.0) -[2023-10-12 04:41:25,202][77203] Avg episode reward: [(0, '41.240'), (1, '37.420')] -[2023-10-12 04:41:27,286][78091] Updated weights for policy 0, policy_version 36650 (0.0008) -[2023-10-12 04:41:27,654][78091] Updated weights for policy 0, policy_version 36660 (0.0010) -[2023-10-12 04:41:28,034][78091] Updated weights for policy 0, policy_version 36670 (0.0008) -[2023-10-12 04:41:28,329][78123] Updated weights for policy 1, policy_version 36490 (0.0008) -[2023-10-12 04:41:28,701][78123] Updated weights for policy 1, policy_version 36500 (0.0009) -[2023-10-12 04:41:29,075][78123] Updated weights for policy 1, policy_version 36510 (0.0007) -[2023-10-12 04:41:30,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 74940416. Throughput: 0: 1599.1, 1: 1604.4. Samples: 18737720. Policy #0 lag: (min: 1.0, avg: 15.8, max: 33.0) -[2023-10-12 04:41:30,201][77203] Avg episode reward: [(0, '44.740'), (1, '36.900')] -[2023-10-12 04:41:32,185][78091] Updated weights for policy 0, policy_version 36680 (0.0007) -[2023-10-12 04:41:32,554][78091] Updated weights for policy 0, policy_version 36690 (0.0009) -[2023-10-12 04:41:32,928][78091] Updated weights for policy 0, policy_version 36700 (0.0008) -[2023-10-12 04:41:33,484][78123] Updated weights for policy 1, policy_version 36520 (0.0007) -[2023-10-12 04:41:33,857][78123] Updated weights for policy 1, policy_version 36530 (0.0008) -[2023-10-12 04:41:34,230][78123] Updated weights for policy 1, policy_version 36540 (0.0008) -[2023-10-12 04:41:35,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 75005952. Throughput: 0: 1586.8, 1: 1600.0. Samples: 18756492. Policy #0 lag: (min: 1.0, avg: 15.8, max: 33.0) -[2023-10-12 04:41:35,202][77203] Avg episode reward: [(0, '51.590'), (1, '41.270')] -[2023-10-12 04:41:35,202][77792] Saving new best policy, reward=51.590! -[2023-10-12 04:41:37,149][78091] Updated weights for policy 0, policy_version 36710 (0.0010) -[2023-10-12 04:41:37,520][78091] Updated weights for policy 0, policy_version 36720 (0.0010) -[2023-10-12 04:41:37,877][78091] Updated weights for policy 0, policy_version 36730 (0.0010) -[2023-10-12 04:41:38,725][78123] Updated weights for policy 1, policy_version 36550 (0.0008) -[2023-10-12 04:41:39,104][78123] Updated weights for policy 1, policy_version 36560 (0.0011) -[2023-10-12 04:41:39,482][78123] Updated weights for policy 1, policy_version 36570 (0.0011) -[2023-10-12 04:41:40,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 75071488. Throughput: 0: 1586.7, 1: 1588.4. Samples: 18775314. Policy #0 lag: (min: 1.0, avg: 15.8, max: 33.0) -[2023-10-12 04:41:40,202][77203] Avg episode reward: [(0, '44.740'), (1, '34.730')] -[2023-10-12 04:41:42,348][78091] Updated weights for policy 0, policy_version 36740 (0.0009) -[2023-10-12 04:41:42,716][78091] Updated weights for policy 0, policy_version 36750 (0.0011) -[2023-10-12 04:41:43,094][78091] Updated weights for policy 0, policy_version 36760 (0.0007) -[2023-10-12 04:41:43,660][78123] Updated weights for policy 1, policy_version 36580 (0.0008) -[2023-10-12 04:41:44,024][78123] Updated weights for policy 1, policy_version 36590 (0.0009) -[2023-10-12 04:41:44,381][78123] Updated weights for policy 1, policy_version 36600 (0.0009) -[2023-10-12 04:41:45,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 75137024. Throughput: 0: 1598.3, 1: 1594.9. Samples: 18785362. Policy #0 lag: (min: 6.0, avg: 10.6, max: 38.0) -[2023-10-12 04:41:45,202][77203] Avg episode reward: [(0, '43.860'), (1, '40.650')] -[2023-10-12 04:41:47,507][78091] Updated weights for policy 0, policy_version 36770 (0.0008) -[2023-10-12 04:41:47,872][78091] Updated weights for policy 0, policy_version 36780 (0.0008) -[2023-10-12 04:41:48,247][78091] Updated weights for policy 0, policy_version 36790 (0.0008) -[2023-10-12 04:41:48,492][78123] Updated weights for policy 1, policy_version 36610 (0.0010) -[2023-10-12 04:41:48,614][78091] Updated weights for policy 0, policy_version 36800 (0.0008) -[2023-10-12 04:41:48,868][78123] Updated weights for policy 1, policy_version 36620 (0.0007) -[2023-10-12 04:41:49,236][78123] Updated weights for policy 1, policy_version 36630 (0.0009) -[2023-10-12 04:41:49,605][78123] Updated weights for policy 1, policy_version 36640 (0.0007) -[2023-10-12 04:41:50,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 75202560. Throughput: 0: 1579.6, 1: 1597.4. Samples: 18803744. Policy #0 lag: (min: 6.0, avg: 10.6, max: 38.0) -[2023-10-12 04:41:50,201][77203] Avg episode reward: [(0, '42.750'), (1, '39.970')] -[2023-10-12 04:41:52,904][78091] Updated weights for policy 0, policy_version 36810 (0.0010) -[2023-10-12 04:41:53,263][78091] Updated weights for policy 0, policy_version 36820 (0.0011) -[2023-10-12 04:41:53,643][78091] Updated weights for policy 0, policy_version 36830 (0.0009) -[2023-10-12 04:41:53,851][78123] Updated weights for policy 1, policy_version 36650 (0.0008) -[2023-10-12 04:41:54,216][78123] Updated weights for policy 1, policy_version 36660 (0.0010) -[2023-10-12 04:41:54,587][78123] Updated weights for policy 1, policy_version 36670 (0.0010) -[2023-10-12 04:41:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 75268096. Throughput: 0: 1584.6, 1: 1580.4. Samples: 18822758. Policy #0 lag: (min: 6.0, avg: 10.6, max: 38.0) -[2023-10-12 04:41:55,202][77203] Avg episode reward: [(0, '47.020'), (1, '36.550')] -[2023-10-12 04:41:57,984][78091] Updated weights for policy 0, policy_version 36840 (0.0008) -[2023-10-12 04:41:58,359][78091] Updated weights for policy 0, policy_version 36850 (0.0008) -[2023-10-12 04:41:58,724][78091] Updated weights for policy 0, policy_version 36860 (0.0007) -[2023-10-12 04:41:59,080][78123] Updated weights for policy 1, policy_version 36680 (0.0008) -[2023-10-12 04:41:59,446][78123] Updated weights for policy 1, policy_version 36690 (0.0007) -[2023-10-12 04:41:59,813][78123] Updated weights for policy 1, policy_version 36700 (0.0007) -[2023-10-12 04:42:00,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 75333632. Throughput: 0: 1609.6, 1: 1586.3. Samples: 18833462. Policy #0 lag: (min: 6.0, avg: 10.6, max: 38.0) -[2023-10-12 04:42:00,202][77203] Avg episode reward: [(0, '43.700'), (1, '39.280')] -[2023-10-12 04:42:03,145][78091] Updated weights for policy 0, policy_version 36870 (0.0008) -[2023-10-12 04:42:03,505][78091] Updated weights for policy 0, policy_version 36880 (0.0010) -[2023-10-12 04:42:03,871][78091] Updated weights for policy 0, policy_version 36890 (0.0008) -[2023-10-12 04:42:04,381][78123] Updated weights for policy 1, policy_version 36710 (0.0008) -[2023-10-12 04:42:04,746][78123] Updated weights for policy 1, policy_version 36720 (0.0007) -[2023-10-12 04:42:05,111][78123] Updated weights for policy 1, policy_version 36730 (0.0008) -[2023-10-12 04:42:05,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 75366400. Throughput: 0: 1587.4, 1: 1600.7. Samples: 18852038. Policy #0 lag: (min: 6.0, avg: 10.6, max: 38.0) -[2023-10-12 04:42:05,202][77203] Avg episode reward: [(0, '43.920'), (1, '39.270')] -[2023-10-12 04:42:08,083][78091] Updated weights for policy 0, policy_version 36900 (0.0008) -[2023-10-12 04:42:08,449][78091] Updated weights for policy 0, policy_version 36910 (0.0008) -[2023-10-12 04:42:08,815][78091] Updated weights for policy 0, policy_version 36920 (0.0008) -[2023-10-12 04:42:09,618][78123] Updated weights for policy 1, policy_version 36740 (0.0007) -[2023-10-12 04:42:09,991][78123] Updated weights for policy 1, policy_version 36750 (0.0007) -[2023-10-12 04:42:10,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 75431936. Throughput: 0: 1585.2, 1: 1595.8. Samples: 18871048. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 04:42:10,202][77203] Avg episode reward: [(0, '51.530'), (1, '33.500')] -[2023-10-12 04:42:10,350][78123] Updated weights for policy 1, policy_version 36760 (0.0009) -[2023-10-12 04:42:13,039][78091] Updated weights for policy 0, policy_version 36930 (0.0009) -[2023-10-12 04:42:13,432][78091] Updated weights for policy 0, policy_version 36940 (0.0010) -[2023-10-12 04:42:13,809][78091] Updated weights for policy 0, policy_version 36950 (0.0010) -[2023-10-12 04:42:14,192][78091] Updated weights for policy 0, policy_version 36960 (0.0010) -[2023-10-12 04:42:14,516][78123] Updated weights for policy 1, policy_version 36770 (0.0008) -[2023-10-12 04:42:14,877][78123] Updated weights for policy 1, policy_version 36780 (0.0009) -[2023-10-12 04:42:15,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 75497472. Throughput: 0: 1609.0, 1: 1581.1. Samples: 18881274. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 04:42:15,201][77203] Avg episode reward: [(0, '46.360'), (1, '34.500')] -[2023-10-12 04:42:15,245][78123] Updated weights for policy 1, policy_version 36790 (0.0009) -[2023-10-12 04:42:15,613][78123] Updated weights for policy 1, policy_version 36800 (0.0009) -[2023-10-12 04:42:18,541][78091] Updated weights for policy 0, policy_version 36970 (0.0007) -[2023-10-12 04:42:18,912][78091] Updated weights for policy 0, policy_version 36980 (0.0007) -[2023-10-12 04:42:19,286][78091] Updated weights for policy 0, policy_version 36990 (0.0007) -[2023-10-12 04:42:19,996][78123] Updated weights for policy 1, policy_version 36810 (0.0007) -[2023-10-12 04:42:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 75563008. Throughput: 0: 1603.6, 1: 1586.4. Samples: 18900040. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 04:42:20,202][77203] Avg episode reward: [(0, '43.100'), (1, '38.870')] -[2023-10-12 04:42:20,359][78123] Updated weights for policy 1, policy_version 36820 (0.0011) -[2023-10-12 04:42:20,723][78123] Updated weights for policy 1, policy_version 36830 (0.0010) -[2023-10-12 04:42:23,211][78091] Updated weights for policy 0, policy_version 37000 (0.0008) -[2023-10-12 04:42:23,577][78091] Updated weights for policy 0, policy_version 37010 (0.0009) -[2023-10-12 04:42:23,951][78091] Updated weights for policy 0, policy_version 37020 (0.0008) -[2023-10-12 04:42:25,133][78123] Updated weights for policy 1, policy_version 36840 (0.0009) -[2023-10-12 04:42:25,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 75628544. Throughput: 0: 1600.2, 1: 1598.5. Samples: 18919252. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 04:42:25,201][77203] Avg episode reward: [(0, '55.840'), (1, '38.680')] -[2023-10-12 04:42:25,211][77792] Saving new best policy, reward=55.840! -[2023-10-12 04:42:25,502][78123] Updated weights for policy 1, policy_version 36850 (0.0008) -[2023-10-12 04:42:25,873][78123] Updated weights for policy 1, policy_version 36860 (0.0009) -[2023-10-12 04:42:28,243][78091] Updated weights for policy 0, policy_version 37030 (0.0009) -[2023-10-12 04:42:28,620][78091] Updated weights for policy 0, policy_version 37040 (0.0009) -[2023-10-12 04:42:28,981][78091] Updated weights for policy 0, policy_version 37050 (0.0009) -[2023-10-12 04:42:30,049][78123] Updated weights for policy 1, policy_version 36870 (0.0009) -[2023-10-12 04:42:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 75694080. Throughput: 0: 1614.4, 1: 1576.4. Samples: 18928944. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 04:42:30,202][77203] Avg episode reward: [(0, '42.530'), (1, '32.220')] -[2023-10-12 04:42:30,409][78123] Updated weights for policy 1, policy_version 36880 (0.0009) -[2023-10-12 04:42:30,785][78123] Updated weights for policy 1, policy_version 36890 (0.0010) -[2023-10-12 04:42:33,309][78091] Updated weights for policy 0, policy_version 37060 (0.0008) -[2023-10-12 04:42:33,678][78091] Updated weights for policy 0, policy_version 37070 (0.0010) -[2023-10-12 04:42:34,045][78091] Updated weights for policy 0, policy_version 37080 (0.0010) -[2023-10-12 04:42:35,177][78123] Updated weights for policy 1, policy_version 36900 (0.0008) -[2023-10-12 04:42:35,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 75759616. Throughput: 0: 1621.6, 1: 1582.3. Samples: 18947918. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:42:35,202][77203] Avg episode reward: [(0, '38.480'), (1, '39.310')] -[2023-10-12 04:42:35,543][78123] Updated weights for policy 1, policy_version 36910 (0.0008) -[2023-10-12 04:42:35,914][78123] Updated weights for policy 1, policy_version 36920 (0.0009) -[2023-10-12 04:42:38,301][78091] Updated weights for policy 0, policy_version 37090 (0.0008) -[2023-10-12 04:42:38,663][78091] Updated weights for policy 0, policy_version 37100 (0.0007) -[2023-10-12 04:42:39,041][78091] Updated weights for policy 0, policy_version 37110 (0.0010) -[2023-10-12 04:42:39,406][78091] Updated weights for policy 0, policy_version 37120 (0.0010) -[2023-10-12 04:42:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 75825152. Throughput: 0: 1605.4, 1: 1597.2. Samples: 18966874. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:42:40,202][77203] Avg episode reward: [(0, '49.360'), (1, '42.050')] -[2023-10-12 04:42:40,221][78123] Updated weights for policy 1, policy_version 36930 (0.0008) -[2023-10-12 04:42:40,596][78123] Updated weights for policy 1, policy_version 36940 (0.0008) -[2023-10-12 04:42:40,957][78123] Updated weights for policy 1, policy_version 36950 (0.0007) -[2023-10-12 04:42:41,321][78123] Updated weights for policy 1, policy_version 36960 (0.0009) -[2023-10-12 04:42:43,834][78091] Updated weights for policy 0, policy_version 37130 (0.0007) -[2023-10-12 04:42:44,204][78091] Updated weights for policy 0, policy_version 37140 (0.0008) -[2023-10-12 04:42:44,571][78091] Updated weights for policy 0, policy_version 37150 (0.0009) -[2023-10-12 04:42:45,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 75890688. Throughput: 0: 1607.6, 1: 1575.9. Samples: 18976720. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:42:45,202][77203] Avg episode reward: [(0, '36.980'), (1, '41.590')] -[2023-10-12 04:42:45,704][78123] Updated weights for policy 1, policy_version 36970 (0.0007) -[2023-10-12 04:42:46,072][78123] Updated weights for policy 1, policy_version 36980 (0.0008) -[2023-10-12 04:42:46,437][78123] Updated weights for policy 1, policy_version 36990 (0.0008) -[2023-10-12 04:42:48,742][78091] Updated weights for policy 0, policy_version 37160 (0.0007) -[2023-10-12 04:42:49,118][78091] Updated weights for policy 0, policy_version 37170 (0.0007) -[2023-10-12 04:42:49,495][78091] Updated weights for policy 0, policy_version 37180 (0.0007) -[2023-10-12 04:42:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 75956224. Throughput: 0: 1618.2, 1: 1572.0. Samples: 18995600. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:42:50,202][77203] Avg episode reward: [(0, '40.080'), (1, '40.970')] -[2023-10-12 04:42:50,932][78123] Updated weights for policy 1, policy_version 37000 (0.0008) -[2023-10-12 04:42:51,294][78123] Updated weights for policy 1, policy_version 37010 (0.0007) -[2023-10-12 04:42:51,659][78123] Updated weights for policy 1, policy_version 37020 (0.0009) -[2023-10-12 04:42:53,761][78091] Updated weights for policy 0, policy_version 37190 (0.0008) -[2023-10-12 04:42:54,139][78091] Updated weights for policy 0, policy_version 37200 (0.0008) -[2023-10-12 04:42:54,503][78091] Updated weights for policy 0, policy_version 37210 (0.0009) -[2023-10-12 04:42:55,201][77203] Fps is (10 sec: 13107.6, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 76021760. Throughput: 0: 1604.9, 1: 1574.9. Samples: 19014142. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:42:55,201][77203] Avg episode reward: [(0, '47.190'), (1, '35.750')] -[2023-10-12 04:42:56,224][78123] Updated weights for policy 1, policy_version 37030 (0.0009) -[2023-10-12 04:42:56,590][78123] Updated weights for policy 1, policy_version 37040 (0.0007) -[2023-10-12 04:42:56,958][78123] Updated weights for policy 1, policy_version 37050 (0.0007) -[2023-10-12 04:42:58,965][78091] Updated weights for policy 0, policy_version 37220 (0.0010) -[2023-10-12 04:42:59,348][78091] Updated weights for policy 0, policy_version 37230 (0.0010) -[2023-10-12 04:42:59,720][78091] Updated weights for policy 0, policy_version 37240 (0.0008) -[2023-10-12 04:43:00,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 76087296. Throughput: 0: 1605.2, 1: 1564.0. Samples: 19023886. Policy #0 lag: (min: 1.0, avg: 7.7, max: 33.0) -[2023-10-12 04:43:00,201][77203] Avg episode reward: [(0, '41.540'), (1, '43.270')] -[2023-10-12 04:43:01,300][78123] Updated weights for policy 1, policy_version 37060 (0.0009) -[2023-10-12 04:43:01,670][78123] Updated weights for policy 1, policy_version 37070 (0.0010) -[2023-10-12 04:43:02,043][78123] Updated weights for policy 1, policy_version 37080 (0.0007) -[2023-10-12 04:43:03,972][78091] Updated weights for policy 0, policy_version 37250 (0.0009) -[2023-10-12 04:43:04,354][78091] Updated weights for policy 0, policy_version 37260 (0.0008) -[2023-10-12 04:43:04,725][78091] Updated weights for policy 0, policy_version 37270 (0.0007) -[2023-10-12 04:43:05,100][78091] Updated weights for policy 0, policy_version 37280 (0.0008) -[2023-10-12 04:43:05,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 76152832. Throughput: 0: 1615.3, 1: 1566.1. Samples: 19043206. Policy #0 lag: (min: 1.0, avg: 7.7, max: 33.0) -[2023-10-12 04:43:05,202][77203] Avg episode reward: [(0, '40.400'), (1, '43.180')] -[2023-10-12 04:43:06,433][78123] Updated weights for policy 1, policy_version 37090 (0.0008) -[2023-10-12 04:43:06,805][78123] Updated weights for policy 1, policy_version 37100 (0.0009) -[2023-10-12 04:43:07,168][78123] Updated weights for policy 1, policy_version 37110 (0.0009) -[2023-10-12 04:43:07,530][78123] Updated weights for policy 1, policy_version 37120 (0.0009) -[2023-10-12 04:43:09,325][78091] Updated weights for policy 0, policy_version 37290 (0.0008) -[2023-10-12 04:43:09,701][78091] Updated weights for policy 0, policy_version 37300 (0.0008) -[2023-10-12 04:43:10,062][78091] Updated weights for policy 0, policy_version 37310 (0.0008) -[2023-10-12 04:43:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 76218368. Throughput: 0: 1606.3, 1: 1568.4. Samples: 19062114. Policy #0 lag: (min: 1.0, avg: 7.7, max: 33.0) -[2023-10-12 04:43:10,201][77203] Avg episode reward: [(0, '41.850'), (1, '33.520')] -[2023-10-12 04:43:10,210][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000037120_38010880.pth... -[2023-10-12 04:43:10,211][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000037312_38207488.pth... -[2023-10-12 04:43:10,240][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000035648_36503552.pth -[2023-10-12 04:43:10,244][77950] Saving a milestone ./train_atari/atari_hero_APPO/checkpoint_p1/milestones/checkpoint_000037120_38010880.pth -[2023-10-12 04:43:10,247][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000035808_36667392.pth -[2023-10-12 04:43:10,251][77792] Saving a milestone ./train_atari/atari_hero_APPO/checkpoint_p0/milestones/checkpoint_000037312_38207488.pth -[2023-10-12 04:43:11,855][78123] Updated weights for policy 1, policy_version 37130 (0.0009) -[2023-10-12 04:43:12,226][78123] Updated weights for policy 1, policy_version 37140 (0.0007) -[2023-10-12 04:43:12,598][78123] Updated weights for policy 1, policy_version 37150 (0.0008) -[2023-10-12 04:43:14,469][78091] Updated weights for policy 0, policy_version 37320 (0.0007) -[2023-10-12 04:43:14,832][78091] Updated weights for policy 0, policy_version 37330 (0.0008) -[2023-10-12 04:43:15,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 76251136. Throughput: 0: 1599.4, 1: 1566.9. Samples: 19071428. Policy #0 lag: (min: 1.0, avg: 7.7, max: 33.0) -[2023-10-12 04:43:15,201][77203] Avg episode reward: [(0, '54.180'), (1, '42.240')] -[2023-10-12 04:43:15,210][78091] Updated weights for policy 0, policy_version 37340 (0.0007) -[2023-10-12 04:43:16,862][78123] Updated weights for policy 1, policy_version 37160 (0.0008) -[2023-10-12 04:43:17,231][78123] Updated weights for policy 1, policy_version 37170 (0.0009) -[2023-10-12 04:43:17,601][78123] Updated weights for policy 1, policy_version 37180 (0.0009) -[2023-10-12 04:43:19,716][78091] Updated weights for policy 0, policy_version 37350 (0.0008) -[2023-10-12 04:43:20,084][78091] Updated weights for policy 0, policy_version 37360 (0.0007) -[2023-10-12 04:43:20,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 76316672. Throughput: 0: 1606.2, 1: 1572.3. Samples: 19090952. Policy #0 lag: (min: 1.0, avg: 7.7, max: 33.0) -[2023-10-12 04:43:20,202][77203] Avg episode reward: [(0, '39.040'), (1, '40.620')] -[2023-10-12 04:43:20,454][78091] Updated weights for policy 0, policy_version 37370 (0.0010) -[2023-10-12 04:43:22,114][78123] Updated weights for policy 1, policy_version 37190 (0.0007) -[2023-10-12 04:43:22,475][78123] Updated weights for policy 1, policy_version 37200 (0.0009) -[2023-10-12 04:43:22,838][78123] Updated weights for policy 1, policy_version 37210 (0.0008) -[2023-10-12 04:43:24,811][78091] Updated weights for policy 0, policy_version 37380 (0.0008) -[2023-10-12 04:43:25,189][78091] Updated weights for policy 0, policy_version 37390 (0.0009) -[2023-10-12 04:43:25,201][77203] Fps is (10 sec: 13106.8, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 76382208. Throughput: 0: 1614.2, 1: 1569.1. Samples: 19110122. Policy #0 lag: (min: 1.0, avg: 7.7, max: 33.0) -[2023-10-12 04:43:25,202][77203] Avg episode reward: [(0, '44.720'), (1, '34.640')] -[2023-10-12 04:43:25,551][78091] Updated weights for policy 0, policy_version 37400 (0.0008) -[2023-10-12 04:43:27,065][78123] Updated weights for policy 1, policy_version 37220 (0.0007) -[2023-10-12 04:43:27,429][78123] Updated weights for policy 1, policy_version 37230 (0.0008) -[2023-10-12 04:43:27,798][78123] Updated weights for policy 1, policy_version 37240 (0.0009) -[2023-10-12 04:43:29,993][78091] Updated weights for policy 0, policy_version 37410 (0.0008) -[2023-10-12 04:43:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 76447744. Throughput: 0: 1592.4, 1: 1576.8. Samples: 19119334. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-12 04:43:30,202][77203] Avg episode reward: [(0, '46.390'), (1, '44.980')] -[2023-10-12 04:43:30,368][78091] Updated weights for policy 0, policy_version 37420 (0.0008) -[2023-10-12 04:43:30,740][78091] Updated weights for policy 0, policy_version 37430 (0.0007) -[2023-10-12 04:43:31,107][78091] Updated weights for policy 0, policy_version 37440 (0.0008) -[2023-10-12 04:43:32,142][78123] Updated weights for policy 1, policy_version 37250 (0.0008) -[2023-10-12 04:43:32,509][78123] Updated weights for policy 1, policy_version 37260 (0.0011) -[2023-10-12 04:43:32,872][78123] Updated weights for policy 1, policy_version 37270 (0.0011) -[2023-10-12 04:43:33,244][78123] Updated weights for policy 1, policy_version 37280 (0.0011) -[2023-10-12 04:43:35,077][78091] Updated weights for policy 0, policy_version 37450 (0.0007) -[2023-10-12 04:43:35,201][77203] Fps is (10 sec: 13107.7, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 76513280. Throughput: 0: 1599.6, 1: 1571.3. Samples: 19138292. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-12 04:43:35,201][77203] Avg episode reward: [(0, '38.620'), (1, '31.530')] -[2023-10-12 04:43:35,453][78091] Updated weights for policy 0, policy_version 37460 (0.0008) -[2023-10-12 04:43:35,821][78091] Updated weights for policy 0, policy_version 37470 (0.0007) -[2023-10-12 04:43:37,626][78123] Updated weights for policy 1, policy_version 37290 (0.0008) -[2023-10-12 04:43:37,997][78123] Updated weights for policy 1, policy_version 37300 (0.0007) -[2023-10-12 04:43:38,362][78123] Updated weights for policy 1, policy_version 37310 (0.0009) -[2023-10-12 04:43:40,141][78091] Updated weights for policy 0, policy_version 37480 (0.0008) -[2023-10-12 04:43:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 76578816. Throughput: 0: 1622.4, 1: 1577.0. Samples: 19158116. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-12 04:43:40,202][77203] Avg episode reward: [(0, '40.230'), (1, '35.040')] -[2023-10-12 04:43:40,511][78091] Updated weights for policy 0, policy_version 37490 (0.0007) -[2023-10-12 04:43:40,882][78091] Updated weights for policy 0, policy_version 37500 (0.0007) -[2023-10-12 04:43:42,563][78123] Updated weights for policy 1, policy_version 37320 (0.0009) -[2023-10-12 04:43:42,936][78123] Updated weights for policy 1, policy_version 37330 (0.0007) -[2023-10-12 04:43:43,297][78123] Updated weights for policy 1, policy_version 37340 (0.0008) -[2023-10-12 04:43:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 76644352. Throughput: 0: 1595.4, 1: 1597.6. Samples: 19167572. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-12 04:43:45,201][77203] Avg episode reward: [(0, '46.280'), (1, '47.070')] -[2023-10-12 04:43:45,291][78091] Updated weights for policy 0, policy_version 37510 (0.0009) -[2023-10-12 04:43:45,659][78091] Updated weights for policy 0, policy_version 37520 (0.0009) -[2023-10-12 04:43:46,031][78091] Updated weights for policy 0, policy_version 37530 (0.0008) -[2023-10-12 04:43:47,925][78123] Updated weights for policy 1, policy_version 37350 (0.0010) -[2023-10-12 04:43:48,298][78123] Updated weights for policy 1, policy_version 37360 (0.0009) -[2023-10-12 04:43:48,658][78123] Updated weights for policy 1, policy_version 37370 (0.0008) -[2023-10-12 04:43:50,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 76709888. Throughput: 0: 1592.4, 1: 1580.2. Samples: 19185976. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-12 04:43:50,202][77203] Avg episode reward: [(0, '46.320'), (1, '33.170')] -[2023-10-12 04:43:50,292][78091] Updated weights for policy 0, policy_version 37540 (0.0008) -[2023-10-12 04:43:50,664][78091] Updated weights for policy 0, policy_version 37550 (0.0009) -[2023-10-12 04:43:51,043][78091] Updated weights for policy 0, policy_version 37560 (0.0007) -[2023-10-12 04:43:53,016][78123] Updated weights for policy 1, policy_version 37380 (0.0008) -[2023-10-12 04:43:53,380][78123] Updated weights for policy 1, policy_version 37390 (0.0007) -[2023-10-12 04:43:53,749][78123] Updated weights for policy 1, policy_version 37400 (0.0009) -[2023-10-12 04:43:55,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 76775424. Throughput: 0: 1605.4, 1: 1574.9. Samples: 19205228. Policy #0 lag: (min: 35.0, avg: 54.3, max: 56.0) -[2023-10-12 04:43:55,202][77203] Avg episode reward: [(0, '45.930'), (1, '35.530')] -[2023-10-12 04:43:55,253][78091] Updated weights for policy 0, policy_version 37570 (0.0007) -[2023-10-12 04:43:55,623][78091] Updated weights for policy 0, policy_version 37580 (0.0007) -[2023-10-12 04:43:55,983][78091] Updated weights for policy 0, policy_version 37590 (0.0009) -[2023-10-12 04:43:56,355][78091] Updated weights for policy 0, policy_version 37600 (0.0009) -[2023-10-12 04:43:58,151][78123] Updated weights for policy 1, policy_version 37410 (0.0008) -[2023-10-12 04:43:58,553][78123] Updated weights for policy 1, policy_version 37420 (0.0010) -[2023-10-12 04:43:58,917][78123] Updated weights for policy 1, policy_version 37430 (0.0010) -[2023-10-12 04:43:59,276][78123] Updated weights for policy 1, policy_version 37440 (0.0010) -[2023-10-12 04:44:00,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 76840960. Throughput: 0: 1588.3, 1: 1607.0. Samples: 19215216. Policy #0 lag: (min: 35.0, avg: 54.3, max: 56.0) -[2023-10-12 04:44:00,201][77203] Avg episode reward: [(0, '52.790'), (1, '41.560')] -[2023-10-12 04:44:00,614][78091] Updated weights for policy 0, policy_version 37610 (0.0010) -[2023-10-12 04:44:00,982][78091] Updated weights for policy 0, policy_version 37620 (0.0008) -[2023-10-12 04:44:01,350][78091] Updated weights for policy 0, policy_version 37630 (0.0009) -[2023-10-12 04:44:03,718][78123] Updated weights for policy 1, policy_version 37450 (0.0010) -[2023-10-12 04:44:04,074][78123] Updated weights for policy 1, policy_version 37460 (0.0009) -[2023-10-12 04:44:04,453][78123] Updated weights for policy 1, policy_version 37470 (0.0010) -[2023-10-12 04:44:05,201][77203] Fps is (10 sec: 13106.8, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 76906496. Throughput: 0: 1590.6, 1: 1594.7. Samples: 19234292. Policy #0 lag: (min: 35.0, avg: 54.3, max: 56.0) -[2023-10-12 04:44:05,203][77203] Avg episode reward: [(0, '39.320'), (1, '33.790')] -[2023-10-12 04:44:05,658][78091] Updated weights for policy 0, policy_version 37640 (0.0009) -[2023-10-12 04:44:06,037][78091] Updated weights for policy 0, policy_version 37650 (0.0008) -[2023-10-12 04:44:06,394][78091] Updated weights for policy 0, policy_version 37660 (0.0009) -[2023-10-12 04:44:08,619][78123] Updated weights for policy 1, policy_version 37480 (0.0008) -[2023-10-12 04:44:08,985][78123] Updated weights for policy 1, policy_version 37490 (0.0009) -[2023-10-12 04:44:09,351][78123] Updated weights for policy 1, policy_version 37500 (0.0007) -[2023-10-12 04:44:10,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 76972032. Throughput: 0: 1595.7, 1: 1586.2. Samples: 19253308. Policy #0 lag: (min: 35.0, avg: 54.3, max: 56.0) -[2023-10-12 04:44:10,202][77203] Avg episode reward: [(0, '43.790'), (1, '38.640')] -[2023-10-12 04:44:10,757][78091] Updated weights for policy 0, policy_version 37670 (0.0008) -[2023-10-12 04:44:11,129][78091] Updated weights for policy 0, policy_version 37680 (0.0009) -[2023-10-12 04:44:11,502][78091] Updated weights for policy 0, policy_version 37690 (0.0008) -[2023-10-12 04:44:13,502][78123] Updated weights for policy 1, policy_version 37510 (0.0010) -[2023-10-12 04:44:13,873][78123] Updated weights for policy 1, policy_version 37520 (0.0009) -[2023-10-12 04:44:14,230][78123] Updated weights for policy 1, policy_version 37530 (0.0009) -[2023-10-12 04:44:15,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 77037568. Throughput: 0: 1590.8, 1: 1606.2. Samples: 19263198. Policy #0 lag: (min: 35.0, avg: 54.3, max: 56.0) -[2023-10-12 04:44:15,202][77203] Avg episode reward: [(0, '44.620'), (1, '42.580')] -[2023-10-12 04:44:15,898][78091] Updated weights for policy 0, policy_version 37700 (0.0008) -[2023-10-12 04:44:16,274][78091] Updated weights for policy 0, policy_version 37710 (0.0007) -[2023-10-12 04:44:16,638][78091] Updated weights for policy 0, policy_version 37720 (0.0008) -[2023-10-12 04:44:18,774][78123] Updated weights for policy 1, policy_version 37540 (0.0009) -[2023-10-12 04:44:19,144][78123] Updated weights for policy 1, policy_version 37550 (0.0007) -[2023-10-12 04:44:19,508][78123] Updated weights for policy 1, policy_version 37560 (0.0008) -[2023-10-12 04:44:20,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 77103104. Throughput: 0: 1591.6, 1: 1608.9. Samples: 19282314. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-12 04:44:20,201][77203] Avg episode reward: [(0, '35.200'), (1, '34.950')] -[2023-10-12 04:44:20,793][78091] Updated weights for policy 0, policy_version 37730 (0.0008) -[2023-10-12 04:44:21,166][78091] Updated weights for policy 0, policy_version 37740 (0.0009) -[2023-10-12 04:44:21,549][78091] Updated weights for policy 0, policy_version 37750 (0.0008) -[2023-10-12 04:44:21,925][78091] Updated weights for policy 0, policy_version 37760 (0.0007) -[2023-10-12 04:44:23,850][78123] Updated weights for policy 1, policy_version 37570 (0.0008) -[2023-10-12 04:44:24,211][78123] Updated weights for policy 1, policy_version 37580 (0.0009) -[2023-10-12 04:44:24,585][78123] Updated weights for policy 1, policy_version 37590 (0.0009) -[2023-10-12 04:44:24,949][78123] Updated weights for policy 1, policy_version 37600 (0.0007) -[2023-10-12 04:44:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 77168640. Throughput: 0: 1587.1, 1: 1590.8. Samples: 19301124. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-12 04:44:25,202][77203] Avg episode reward: [(0, '35.120'), (1, '36.280')] -[2023-10-12 04:44:26,459][78091] Updated weights for policy 0, policy_version 37770 (0.0007) -[2023-10-12 04:44:26,829][78091] Updated weights for policy 0, policy_version 37780 (0.0008) -[2023-10-12 04:44:27,205][78091] Updated weights for policy 0, policy_version 37790 (0.0009) -[2023-10-12 04:44:29,311][78123] Updated weights for policy 1, policy_version 37610 (0.0007) -[2023-10-12 04:44:29,676][78123] Updated weights for policy 1, policy_version 37620 (0.0007) -[2023-10-12 04:44:30,037][78123] Updated weights for policy 1, policy_version 37630 (0.0009) -[2023-10-12 04:44:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 77234176. Throughput: 0: 1583.5, 1: 1594.8. Samples: 19310598. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-12 04:44:30,201][77203] Avg episode reward: [(0, '39.010'), (1, '48.330')] -[2023-10-12 04:44:31,387][78091] Updated weights for policy 0, policy_version 37800 (0.0009) -[2023-10-12 04:44:31,759][78091] Updated weights for policy 0, policy_version 37810 (0.0007) -[2023-10-12 04:44:32,131][78091] Updated weights for policy 0, policy_version 37820 (0.0007) -[2023-10-12 04:44:34,182][78123] Updated weights for policy 1, policy_version 37640 (0.0008) -[2023-10-12 04:44:34,547][78123] Updated weights for policy 1, policy_version 37650 (0.0007) -[2023-10-12 04:44:34,911][78123] Updated weights for policy 1, policy_version 37660 (0.0009) -[2023-10-12 04:44:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.1, 300 sec: 12885.0). Total num frames: 77299712. Throughput: 0: 1589.1, 1: 1613.2. Samples: 19330076. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-12 04:44:35,202][77203] Avg episode reward: [(0, '39.410'), (1, '33.190')] -[2023-10-12 04:44:36,418][78091] Updated weights for policy 0, policy_version 37830 (0.0008) -[2023-10-12 04:44:36,783][78091] Updated weights for policy 0, policy_version 37840 (0.0010) -[2023-10-12 04:44:37,152][78091] Updated weights for policy 0, policy_version 37850 (0.0011) -[2023-10-12 04:44:39,203][78123] Updated weights for policy 1, policy_version 37670 (0.0008) -[2023-10-12 04:44:39,575][78123] Updated weights for policy 1, policy_version 37680 (0.0010) -[2023-10-12 04:44:39,938][78123] Updated weights for policy 1, policy_version 37690 (0.0007) -[2023-10-12 04:44:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 12885.0). Total num frames: 77365248. Throughput: 0: 1585.5, 1: 1606.0. Samples: 19348844. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-12 04:44:40,201][77203] Avg episode reward: [(0, '44.900'), (1, '39.620')] -[2023-10-12 04:44:41,596][78091] Updated weights for policy 0, policy_version 37860 (0.0008) -[2023-10-12 04:44:41,964][78091] Updated weights for policy 0, policy_version 37870 (0.0007) -[2023-10-12 04:44:42,329][78091] Updated weights for policy 0, policy_version 37880 (0.0007) -[2023-10-12 04:44:44,251][78123] Updated weights for policy 1, policy_version 37700 (0.0008) -[2023-10-12 04:44:44,634][78123] Updated weights for policy 1, policy_version 37710 (0.0007) -[2023-10-12 04:44:45,002][78123] Updated weights for policy 1, policy_version 37720 (0.0007) -[2023-10-12 04:44:45,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 77398016. Throughput: 0: 1584.7, 1: 1592.4. Samples: 19358190. Policy #0 lag: (min: 25.0, avg: 30.2, max: 57.0) -[2023-10-12 04:44:45,202][77203] Avg episode reward: [(0, '46.190'), (1, '41.230')] -[2023-10-12 04:44:46,867][78091] Updated weights for policy 0, policy_version 37890 (0.0007) -[2023-10-12 04:44:47,241][78091] Updated weights for policy 0, policy_version 37900 (0.0007) -[2023-10-12 04:44:47,604][78091] Updated weights for policy 0, policy_version 37910 (0.0010) -[2023-10-12 04:44:47,971][78091] Updated weights for policy 0, policy_version 37920 (0.0008) -[2023-10-12 04:44:49,393][78123] Updated weights for policy 1, policy_version 37730 (0.0008) -[2023-10-12 04:44:49,761][78123] Updated weights for policy 1, policy_version 37740 (0.0007) -[2023-10-12 04:44:50,125][78123] Updated weights for policy 1, policy_version 37750 (0.0009) -[2023-10-12 04:44:50,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 77463552. Throughput: 0: 1581.8, 1: 1599.7. Samples: 19377460. Policy #0 lag: (min: 25.0, avg: 30.2, max: 57.0) -[2023-10-12 04:44:50,201][77203] Avg episode reward: [(0, '40.910'), (1, '31.640')] -[2023-10-12 04:44:50,493][78123] Updated weights for policy 1, policy_version 37760 (0.0011) -[2023-10-12 04:44:52,182][78091] Updated weights for policy 0, policy_version 37930 (0.0009) -[2023-10-12 04:44:52,549][78091] Updated weights for policy 0, policy_version 37940 (0.0011) -[2023-10-12 04:44:52,924][78091] Updated weights for policy 0, policy_version 37950 (0.0008) -[2023-10-12 04:44:54,827][78123] Updated weights for policy 1, policy_version 37770 (0.0010) -[2023-10-12 04:44:55,196][78123] Updated weights for policy 1, policy_version 37780 (0.0010) -[2023-10-12 04:44:55,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 77529088. Throughput: 0: 1586.3, 1: 1605.6. Samples: 19396944. Policy #0 lag: (min: 25.0, avg: 30.2, max: 57.0) -[2023-10-12 04:44:55,202][77203] Avg episode reward: [(0, '42.070'), (1, '39.640')] -[2023-10-12 04:44:55,576][78123] Updated weights for policy 1, policy_version 37790 (0.0009) -[2023-10-12 04:44:57,423][78091] Updated weights for policy 0, policy_version 37960 (0.0007) -[2023-10-12 04:44:57,791][78091] Updated weights for policy 0, policy_version 37970 (0.0007) -[2023-10-12 04:44:58,168][78091] Updated weights for policy 0, policy_version 37980 (0.0007) -[2023-10-12 04:44:59,977][78123] Updated weights for policy 1, policy_version 37800 (0.0010) -[2023-10-12 04:45:00,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 77594624. Throughput: 0: 1597.4, 1: 1579.2. Samples: 19406146. Policy #0 lag: (min: 25.0, avg: 30.2, max: 57.0) -[2023-10-12 04:45:00,202][77203] Avg episode reward: [(0, '49.840'), (1, '42.960')] -[2023-10-12 04:45:00,351][78123] Updated weights for policy 1, policy_version 37810 (0.0010) -[2023-10-12 04:45:00,724][78123] Updated weights for policy 1, policy_version 37820 (0.0008) -[2023-10-12 04:45:02,512][78091] Updated weights for policy 0, policy_version 37990 (0.0010) -[2023-10-12 04:45:02,891][78091] Updated weights for policy 0, policy_version 38000 (0.0010) -[2023-10-12 04:45:03,269][78091] Updated weights for policy 0, policy_version 38010 (0.0010) -[2023-10-12 04:45:05,180][78123] Updated weights for policy 1, policy_version 37830 (0.0009) -[2023-10-12 04:45:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 77660160. Throughput: 0: 1579.1, 1: 1586.2. Samples: 19424752. Policy #0 lag: (min: 25.0, avg: 30.2, max: 57.0) -[2023-10-12 04:45:05,202][77203] Avg episode reward: [(0, '37.230'), (1, '34.530')] -[2023-10-12 04:45:05,550][78123] Updated weights for policy 1, policy_version 37840 (0.0008) -[2023-10-12 04:45:05,921][78123] Updated weights for policy 1, policy_version 37850 (0.0009) -[2023-10-12 04:45:07,466][78091] Updated weights for policy 0, policy_version 38020 (0.0009) -[2023-10-12 04:45:07,841][78091] Updated weights for policy 0, policy_version 38030 (0.0008) -[2023-10-12 04:45:08,203][78091] Updated weights for policy 0, policy_version 38040 (0.0009) -[2023-10-12 04:45:10,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 77725696. Throughput: 0: 1580.1, 1: 1599.5. Samples: 19444206. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-10-12 04:45:10,202][77203] Avg episode reward: [(0, '37.820'), (1, '39.530')] -[2023-10-12 04:45:10,210][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000038048_38961152.pth... -[2023-10-12 04:45:10,242][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000036544_37421056.pth -[2023-10-12 04:45:10,357][78123] Updated weights for policy 1, policy_version 37860 (0.0008) -[2023-10-12 04:45:10,720][78123] Updated weights for policy 1, policy_version 37870 (0.0009) -[2023-10-12 04:45:11,086][78123] Updated weights for policy 1, policy_version 37880 (0.0007) -[2023-10-12 04:45:11,372][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000037888_38797312.pth... -[2023-10-12 04:45:11,410][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000036384_37257216.pth -[2023-10-12 04:45:12,596][78091] Updated weights for policy 0, policy_version 38050 (0.0010) -[2023-10-12 04:45:12,973][78091] Updated weights for policy 0, policy_version 38060 (0.0009) -[2023-10-12 04:45:13,347][78091] Updated weights for policy 0, policy_version 38070 (0.0008) -[2023-10-12 04:45:13,713][78091] Updated weights for policy 0, policy_version 38080 (0.0009) -[2023-10-12 04:45:15,201][77203] Fps is (10 sec: 13107.6, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 77791232. Throughput: 0: 1602.4, 1: 1579.4. Samples: 19453780. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-10-12 04:45:15,201][77203] Avg episode reward: [(0, '44.190'), (1, '41.710')] -[2023-10-12 04:45:15,498][78123] Updated weights for policy 1, policy_version 37890 (0.0008) -[2023-10-12 04:45:15,863][78123] Updated weights for policy 1, policy_version 37900 (0.0007) -[2023-10-12 04:45:16,226][78123] Updated weights for policy 1, policy_version 37910 (0.0007) -[2023-10-12 04:45:16,592][78123] Updated weights for policy 1, policy_version 37920 (0.0008) -[2023-10-12 04:45:17,949][78091] Updated weights for policy 0, policy_version 38090 (0.0007) -[2023-10-12 04:45:18,310][78091] Updated weights for policy 0, policy_version 38100 (0.0007) -[2023-10-12 04:45:18,693][78091] Updated weights for policy 0, policy_version 38110 (0.0008) -[2023-10-12 04:45:20,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 77856768. Throughput: 0: 1583.0, 1: 1582.0. Samples: 19472500. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-10-12 04:45:20,201][77203] Avg episode reward: [(0, '33.620'), (1, '37.330')] -[2023-10-12 04:45:20,933][78123] Updated weights for policy 1, policy_version 37930 (0.0007) -[2023-10-12 04:45:21,316][78123] Updated weights for policy 1, policy_version 37940 (0.0009) -[2023-10-12 04:45:21,687][78123] Updated weights for policy 1, policy_version 37950 (0.0011) -[2023-10-12 04:45:22,935][78091] Updated weights for policy 0, policy_version 38120 (0.0009) -[2023-10-12 04:45:23,310][78091] Updated weights for policy 0, policy_version 38130 (0.0008) -[2023-10-12 04:45:23,678][78091] Updated weights for policy 0, policy_version 38140 (0.0009) -[2023-10-12 04:45:25,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 77922304. Throughput: 0: 1585.1, 1: 1596.9. Samples: 19492036. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-10-12 04:45:25,202][77203] Avg episode reward: [(0, '33.850'), (1, '36.640')] -[2023-10-12 04:45:25,730][78123] Updated weights for policy 1, policy_version 37960 (0.0011) -[2023-10-12 04:45:26,101][78123] Updated weights for policy 1, policy_version 37970 (0.0007) -[2023-10-12 04:45:26,470][78123] Updated weights for policy 1, policy_version 37980 (0.0008) -[2023-10-12 04:45:28,059][78091] Updated weights for policy 0, policy_version 38150 (0.0008) -[2023-10-12 04:45:28,433][78091] Updated weights for policy 0, policy_version 38160 (0.0007) -[2023-10-12 04:45:28,797][78091] Updated weights for policy 0, policy_version 38170 (0.0009) -[2023-10-12 04:45:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 77987840. Throughput: 0: 1612.0, 1: 1579.7. Samples: 19501818. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-10-12 04:45:30,201][77203] Avg episode reward: [(0, '40.810'), (1, '41.580')] -[2023-10-12 04:45:30,878][78123] Updated weights for policy 1, policy_version 37990 (0.0010) -[2023-10-12 04:45:31,252][78123] Updated weights for policy 1, policy_version 38000 (0.0007) -[2023-10-12 04:45:31,614][78123] Updated weights for policy 1, policy_version 38010 (0.0009) -[2023-10-12 04:45:32,905][78091] Updated weights for policy 0, policy_version 38180 (0.0009) -[2023-10-12 04:45:33,287][78091] Updated weights for policy 0, policy_version 38190 (0.0007) -[2023-10-12 04:45:33,650][78091] Updated weights for policy 0, policy_version 38200 (0.0007) -[2023-10-12 04:45:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 78053376. Throughput: 0: 1601.4, 1: 1582.5. Samples: 19520736. Policy #0 lag: (min: 30.0, avg: 37.1, max: 62.0) -[2023-10-12 04:45:35,202][77203] Avg episode reward: [(0, '41.090'), (1, '42.970')] -[2023-10-12 04:45:35,941][78123] Updated weights for policy 1, policy_version 38020 (0.0008) -[2023-10-12 04:45:36,310][78123] Updated weights for policy 1, policy_version 38030 (0.0010) -[2023-10-12 04:45:36,677][78123] Updated weights for policy 1, policy_version 38040 (0.0007) -[2023-10-12 04:45:38,110][78091] Updated weights for policy 0, policy_version 38210 (0.0008) -[2023-10-12 04:45:38,474][78091] Updated weights for policy 0, policy_version 38220 (0.0008) -[2023-10-12 04:45:38,846][78091] Updated weights for policy 0, policy_version 38230 (0.0008) -[2023-10-12 04:45:39,208][78091] Updated weights for policy 0, policy_version 38240 (0.0008) -[2023-10-12 04:45:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 78118912. Throughput: 0: 1591.9, 1: 1582.9. Samples: 19539810. Policy #0 lag: (min: 30.0, avg: 37.1, max: 62.0) -[2023-10-12 04:45:40,201][77203] Avg episode reward: [(0, '45.350'), (1, '36.490')] -[2023-10-12 04:45:41,063][78123] Updated weights for policy 1, policy_version 38050 (0.0010) -[2023-10-12 04:45:41,433][78123] Updated weights for policy 1, policy_version 38060 (0.0009) -[2023-10-12 04:45:41,793][78123] Updated weights for policy 1, policy_version 38070 (0.0010) -[2023-10-12 04:45:42,160][78123] Updated weights for policy 1, policy_version 38080 (0.0010) -[2023-10-12 04:45:43,323][78091] Updated weights for policy 0, policy_version 38250 (0.0008) -[2023-10-12 04:45:43,695][78091] Updated weights for policy 0, policy_version 38260 (0.0008) -[2023-10-12 04:45:44,063][78091] Updated weights for policy 0, policy_version 38270 (0.0008) -[2023-10-12 04:45:45,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 78184448. Throughput: 0: 1608.8, 1: 1578.1. Samples: 19549556. Policy #0 lag: (min: 30.0, avg: 37.1, max: 62.0) -[2023-10-12 04:45:45,202][77203] Avg episode reward: [(0, '40.630'), (1, '42.380')] -[2023-10-12 04:45:46,601][78123] Updated weights for policy 1, policy_version 38090 (0.0007) -[2023-10-12 04:45:46,963][78123] Updated weights for policy 1, policy_version 38100 (0.0008) -[2023-10-12 04:45:47,333][78123] Updated weights for policy 1, policy_version 38110 (0.0008) -[2023-10-12 04:45:48,445][78091] Updated weights for policy 0, policy_version 38280 (0.0009) -[2023-10-12 04:45:48,819][78091] Updated weights for policy 0, policy_version 38290 (0.0008) -[2023-10-12 04:45:49,184][78091] Updated weights for policy 0, policy_version 38300 (0.0010) -[2023-10-12 04:45:50,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 78249984. Throughput: 0: 1611.8, 1: 1581.6. Samples: 19568456. Policy #0 lag: (min: 30.0, avg: 37.1, max: 62.0) -[2023-10-12 04:45:50,201][77203] Avg episode reward: [(0, '37.440'), (1, '42.620')] -[2023-10-12 04:45:51,576][78123] Updated weights for policy 1, policy_version 38120 (0.0010) -[2023-10-12 04:45:51,954][78123] Updated weights for policy 1, policy_version 38130 (0.0008) -[2023-10-12 04:45:52,319][78123] Updated weights for policy 1, policy_version 38140 (0.0008) -[2023-10-12 04:45:53,509][78091] Updated weights for policy 0, policy_version 38310 (0.0008) -[2023-10-12 04:45:53,881][78091] Updated weights for policy 0, policy_version 38320 (0.0007) -[2023-10-12 04:45:54,255][78091] Updated weights for policy 0, policy_version 38330 (0.0010) -[2023-10-12 04:45:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 12774.0). Total num frames: 78315520. Throughput: 0: 1600.5, 1: 1584.2. Samples: 19587518. Policy #0 lag: (min: 30.0, avg: 37.1, max: 62.0) -[2023-10-12 04:45:55,202][77203] Avg episode reward: [(0, '36.540'), (1, '36.810')] -[2023-10-12 04:45:56,558][78123] Updated weights for policy 1, policy_version 38150 (0.0009) -[2023-10-12 04:45:56,921][78123] Updated weights for policy 1, policy_version 38160 (0.0010) -[2023-10-12 04:45:57,283][78123] Updated weights for policy 1, policy_version 38170 (0.0010) -[2023-10-12 04:45:58,589][78091] Updated weights for policy 0, policy_version 38340 (0.0009) -[2023-10-12 04:45:58,958][78091] Updated weights for policy 0, policy_version 38350 (0.0007) -[2023-10-12 04:45:59,328][78091] Updated weights for policy 0, policy_version 38360 (0.0007) -[2023-10-12 04:46:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 78381056. Throughput: 0: 1610.8, 1: 1582.4. Samples: 19597474. Policy #0 lag: (min: 20.0, avg: 45.4, max: 48.0) -[2023-10-12 04:46:00,201][77203] Avg episode reward: [(0, '38.490'), (1, '41.910')] -[2023-10-12 04:46:01,761][78123] Updated weights for policy 1, policy_version 38180 (0.0009) -[2023-10-12 04:46:02,125][78123] Updated weights for policy 1, policy_version 38190 (0.0010) -[2023-10-12 04:46:02,498][78123] Updated weights for policy 1, policy_version 38200 (0.0008) -[2023-10-12 04:46:03,615][78091] Updated weights for policy 0, policy_version 38370 (0.0007) -[2023-10-12 04:46:04,006][78091] Updated weights for policy 0, policy_version 38380 (0.0008) -[2023-10-12 04:46:04,367][78091] Updated weights for policy 0, policy_version 38390 (0.0007) -[2023-10-12 04:46:04,733][78091] Updated weights for policy 0, policy_version 38400 (0.0007) -[2023-10-12 04:46:05,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 78446592. Throughput: 0: 1627.7, 1: 1578.7. Samples: 19616790. Policy #0 lag: (min: 20.0, avg: 45.4, max: 48.0) -[2023-10-12 04:46:05,202][77203] Avg episode reward: [(0, '37.050'), (1, '43.130')] -[2023-10-12 04:46:06,826][78123] Updated weights for policy 1, policy_version 38210 (0.0008) -[2023-10-12 04:46:07,194][78123] Updated weights for policy 1, policy_version 38220 (0.0009) -[2023-10-12 04:46:07,558][78123] Updated weights for policy 1, policy_version 38230 (0.0010) -[2023-10-12 04:46:07,928][78123] Updated weights for policy 1, policy_version 38240 (0.0009) -[2023-10-12 04:46:08,959][78091] Updated weights for policy 0, policy_version 38410 (0.0010) -[2023-10-12 04:46:09,325][78091] Updated weights for policy 0, policy_version 38420 (0.0009) -[2023-10-12 04:46:09,696][78091] Updated weights for policy 0, policy_version 38430 (0.0010) -[2023-10-12 04:46:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 78512128. Throughput: 0: 1608.6, 1: 1578.7. Samples: 19635462. Policy #0 lag: (min: 20.0, avg: 45.4, max: 48.0) -[2023-10-12 04:46:10,202][77203] Avg episode reward: [(0, '39.670'), (1, '41.220')] -[2023-10-12 04:46:12,308][78123] Updated weights for policy 1, policy_version 38250 (0.0008) -[2023-10-12 04:46:12,674][78123] Updated weights for policy 1, policy_version 38260 (0.0007) -[2023-10-12 04:46:13,045][78123] Updated weights for policy 1, policy_version 38270 (0.0007) -[2023-10-12 04:46:14,081][78091] Updated weights for policy 0, policy_version 38440 (0.0010) -[2023-10-12 04:46:14,448][78091] Updated weights for policy 0, policy_version 38450 (0.0009) -[2023-10-12 04:46:14,821][78091] Updated weights for policy 0, policy_version 38460 (0.0008) -[2023-10-12 04:46:15,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 78577664. Throughput: 0: 1604.2, 1: 1590.2. Samples: 19645568. Policy #0 lag: (min: 20.0, avg: 45.4, max: 48.0) -[2023-10-12 04:46:15,201][77203] Avg episode reward: [(0, '45.280'), (1, '38.040')] -[2023-10-12 04:46:17,380][78123] Updated weights for policy 1, policy_version 38280 (0.0008) -[2023-10-12 04:46:17,754][78123] Updated weights for policy 1, policy_version 38290 (0.0010) -[2023-10-12 04:46:18,122][78123] Updated weights for policy 1, policy_version 38300 (0.0007) -[2023-10-12 04:46:18,972][78091] Updated weights for policy 0, policy_version 38470 (0.0007) -[2023-10-12 04:46:19,349][78091] Updated weights for policy 0, policy_version 38480 (0.0008) -[2023-10-12 04:46:19,714][78091] Updated weights for policy 0, policy_version 38490 (0.0008) -[2023-10-12 04:46:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 78643200. Throughput: 0: 1616.6, 1: 1583.5. Samples: 19664740. Policy #0 lag: (min: 20.0, avg: 45.4, max: 48.0) -[2023-10-12 04:46:20,201][77203] Avg episode reward: [(0, '35.820'), (1, '39.560')] -[2023-10-12 04:46:22,348][78123] Updated weights for policy 1, policy_version 38310 (0.0009) -[2023-10-12 04:46:22,715][78123] Updated weights for policy 1, policy_version 38320 (0.0008) -[2023-10-12 04:46:23,079][78123] Updated weights for policy 1, policy_version 38330 (0.0007) -[2023-10-12 04:46:23,959][78091] Updated weights for policy 0, policy_version 38500 (0.0009) -[2023-10-12 04:46:24,330][78091] Updated weights for policy 0, policy_version 38510 (0.0008) -[2023-10-12 04:46:24,695][78091] Updated weights for policy 0, policy_version 38520 (0.0007) -[2023-10-12 04:46:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 78708736. Throughput: 0: 1607.5, 1: 1589.9. Samples: 19683692. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-12 04:46:25,201][77203] Avg episode reward: [(0, '36.230'), (1, '45.570')] -[2023-10-12 04:46:27,414][78123] Updated weights for policy 1, policy_version 38340 (0.0008) -[2023-10-12 04:46:27,792][78123] Updated weights for policy 1, policy_version 38350 (0.0009) -[2023-10-12 04:46:28,158][78123] Updated weights for policy 1, policy_version 38360 (0.0009) -[2023-10-12 04:46:28,890][78091] Updated weights for policy 0, policy_version 38530 (0.0009) -[2023-10-12 04:46:29,247][78091] Updated weights for policy 0, policy_version 38540 (0.0008) -[2023-10-12 04:46:29,616][78091] Updated weights for policy 0, policy_version 38550 (0.0009) -[2023-10-12 04:46:29,989][78091] Updated weights for policy 0, policy_version 38560 (0.0011) -[2023-10-12 04:46:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 78774272. Throughput: 0: 1599.2, 1: 1606.8. Samples: 19693824. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-12 04:46:30,202][77203] Avg episode reward: [(0, '45.840'), (1, '38.620')] -[2023-10-12 04:46:32,261][78123] Updated weights for policy 1, policy_version 38370 (0.0008) -[2023-10-12 04:46:32,637][78123] Updated weights for policy 1, policy_version 38380 (0.0010) -[2023-10-12 04:46:32,993][78123] Updated weights for policy 1, policy_version 38390 (0.0010) -[2023-10-12 04:46:33,356][78123] Updated weights for policy 1, policy_version 38400 (0.0010) -[2023-10-12 04:46:34,320][78091] Updated weights for policy 0, policy_version 38570 (0.0007) -[2023-10-12 04:46:34,696][78091] Updated weights for policy 0, policy_version 38580 (0.0008) -[2023-10-12 04:46:35,058][78091] Updated weights for policy 0, policy_version 38590 (0.0007) -[2023-10-12 04:46:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 12774.0). Total num frames: 78839808. Throughput: 0: 1615.2, 1: 1590.4. Samples: 19712706. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-12 04:46:35,201][77203] Avg episode reward: [(0, '43.970'), (1, '41.340')] -[2023-10-12 04:46:37,791][78123] Updated weights for policy 1, policy_version 38410 (0.0009) -[2023-10-12 04:46:38,151][78123] Updated weights for policy 1, policy_version 38420 (0.0010) -[2023-10-12 04:46:38,525][78123] Updated weights for policy 1, policy_version 38430 (0.0009) -[2023-10-12 04:46:39,480][78091] Updated weights for policy 0, policy_version 38600 (0.0008) -[2023-10-12 04:46:39,849][78091] Updated weights for policy 0, policy_version 38610 (0.0008) -[2023-10-12 04:46:40,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 78872576. Throughput: 0: 1612.4, 1: 1589.7. Samples: 19731612. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-12 04:46:40,202][77203] Avg episode reward: [(0, '43.480'), (1, '44.930')] -[2023-10-12 04:46:40,225][78091] Updated weights for policy 0, policy_version 38620 (0.0009) -[2023-10-12 04:46:42,825][78123] Updated weights for policy 1, policy_version 38440 (0.0008) -[2023-10-12 04:46:43,201][78123] Updated weights for policy 1, policy_version 38450 (0.0007) -[2023-10-12 04:46:43,571][78123] Updated weights for policy 1, policy_version 38460 (0.0007) -[2023-10-12 04:46:44,552][78091] Updated weights for policy 0, policy_version 38630 (0.0007) -[2023-10-12 04:46:44,912][78091] Updated weights for policy 0, policy_version 38640 (0.0008) -[2023-10-12 04:46:45,201][77203] Fps is (10 sec: 9830.2, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 78938112. Throughput: 0: 1594.1, 1: 1611.4. Samples: 19741724. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-12 04:46:45,202][77203] Avg episode reward: [(0, '46.890'), (1, '40.030')] -[2023-10-12 04:46:45,276][78091] Updated weights for policy 0, policy_version 38650 (0.0009) -[2023-10-12 04:46:47,864][78123] Updated weights for policy 1, policy_version 38470 (0.0010) -[2023-10-12 04:46:48,229][78123] Updated weights for policy 1, policy_version 38480 (0.0007) -[2023-10-12 04:46:48,600][78123] Updated weights for policy 1, policy_version 38490 (0.0007) -[2023-10-12 04:46:49,843][78091] Updated weights for policy 0, policy_version 38660 (0.0008) -[2023-10-12 04:46:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 79003648. Throughput: 0: 1594.8, 1: 1594.3. Samples: 19760298. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-12 04:46:50,201][77203] Avg episode reward: [(0, '48.710'), (1, '44.620')] -[2023-10-12 04:46:50,226][78091] Updated weights for policy 0, policy_version 38670 (0.0011) -[2023-10-12 04:46:50,598][78091] Updated weights for policy 0, policy_version 38680 (0.0010) -[2023-10-12 04:46:53,034][78123] Updated weights for policy 1, policy_version 38500 (0.0008) -[2023-10-12 04:46:53,401][78123] Updated weights for policy 1, policy_version 38510 (0.0008) -[2023-10-12 04:46:53,768][78123] Updated weights for policy 1, policy_version 38520 (0.0009) -[2023-10-12 04:46:55,055][78091] Updated weights for policy 0, policy_version 38690 (0.0010) -[2023-10-12 04:46:55,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 79069184. Throughput: 0: 1607.9, 1: 1589.7. Samples: 19779352. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:46:55,201][77203] Avg episode reward: [(0, '43.610'), (1, '45.400')] -[2023-10-12 04:46:55,423][78091] Updated weights for policy 0, policy_version 38700 (0.0007) -[2023-10-12 04:46:55,780][78091] Updated weights for policy 0, policy_version 38710 (0.0007) -[2023-10-12 04:46:56,151][78091] Updated weights for policy 0, policy_version 38720 (0.0007) -[2023-10-12 04:46:58,189][78123] Updated weights for policy 1, policy_version 38530 (0.0008) -[2023-10-12 04:46:58,555][78123] Updated weights for policy 1, policy_version 38540 (0.0008) -[2023-10-12 04:46:58,931][78123] Updated weights for policy 1, policy_version 38550 (0.0009) -[2023-10-12 04:46:59,295][78123] Updated weights for policy 1, policy_version 38560 (0.0008) -[2023-10-12 04:47:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 79134720. Throughput: 0: 1585.0, 1: 1606.6. Samples: 19789188. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:47:00,201][77203] Avg episode reward: [(0, '41.410'), (1, '38.180')] -[2023-10-12 04:47:00,357][78091] Updated weights for policy 0, policy_version 38730 (0.0007) -[2023-10-12 04:47:00,737][78091] Updated weights for policy 0, policy_version 38740 (0.0007) -[2023-10-12 04:47:01,115][78091] Updated weights for policy 0, policy_version 38750 (0.0007) -[2023-10-12 04:47:03,655][78123] Updated weights for policy 1, policy_version 38570 (0.0008) -[2023-10-12 04:47:04,021][78123] Updated weights for policy 1, policy_version 38580 (0.0008) -[2023-10-12 04:47:04,384][78123] Updated weights for policy 1, policy_version 38590 (0.0009) -[2023-10-12 04:47:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 79200256. Throughput: 0: 1585.5, 1: 1604.1. Samples: 19808270. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:47:05,201][77203] Avg episode reward: [(0, '43.390'), (1, '41.090')] -[2023-10-12 04:47:05,566][78091] Updated weights for policy 0, policy_version 38760 (0.0010) -[2023-10-12 04:47:05,945][78091] Updated weights for policy 0, policy_version 38770 (0.0009) -[2023-10-12 04:47:06,317][78091] Updated weights for policy 0, policy_version 38780 (0.0008) -[2023-10-12 04:47:08,705][78123] Updated weights for policy 1, policy_version 38600 (0.0007) -[2023-10-12 04:47:09,085][78123] Updated weights for policy 1, policy_version 38610 (0.0007) -[2023-10-12 04:47:09,452][78123] Updated weights for policy 1, policy_version 38620 (0.0008) -[2023-10-12 04:47:10,201][77203] Fps is (10 sec: 13106.8, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 79265792. Throughput: 0: 1596.2, 1: 1587.4. Samples: 19826954. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:47:10,202][77203] Avg episode reward: [(0, '44.290'), (1, '40.590')] -[2023-10-12 04:47:10,212][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000038624_39550976.pth... -[2023-10-12 04:47:10,213][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000038784_39714816.pth... -[2023-10-12 04:47:10,243][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000037120_38010880.pth -[2023-10-12 04:47:10,253][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000037312_38207488.pth -[2023-10-12 04:47:10,619][78091] Updated weights for policy 0, policy_version 38790 (0.0009) -[2023-10-12 04:47:10,998][78091] Updated weights for policy 0, policy_version 38800 (0.0011) -[2023-10-12 04:47:11,364][78091] Updated weights for policy 0, policy_version 38810 (0.0011) -[2023-10-12 04:47:13,738][78123] Updated weights for policy 1, policy_version 38630 (0.0008) -[2023-10-12 04:47:14,097][78123] Updated weights for policy 1, policy_version 38640 (0.0008) -[2023-10-12 04:47:14,474][78123] Updated weights for policy 1, policy_version 38650 (0.0008) -[2023-10-12 04:47:15,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 79331328. Throughput: 0: 1576.0, 1: 1600.8. Samples: 19836782. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:47:15,202][77203] Avg episode reward: [(0, '45.260'), (1, '38.120')] -[2023-10-12 04:47:15,849][78091] Updated weights for policy 0, policy_version 38820 (0.0009) -[2023-10-12 04:47:16,217][78091] Updated weights for policy 0, policy_version 38830 (0.0008) -[2023-10-12 04:47:16,576][78091] Updated weights for policy 0, policy_version 38840 (0.0010) -[2023-10-12 04:47:18,808][78123] Updated weights for policy 1, policy_version 38660 (0.0010) -[2023-10-12 04:47:19,182][78123] Updated weights for policy 1, policy_version 38670 (0.0009) -[2023-10-12 04:47:19,540][78123] Updated weights for policy 1, policy_version 38680 (0.0008) -[2023-10-12 04:47:20,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 79396864. Throughput: 0: 1574.5, 1: 1614.4. Samples: 19856204. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-12 04:47:20,202][77203] Avg episode reward: [(0, '44.510'), (1, '38.800')] -[2023-10-12 04:47:20,894][78091] Updated weights for policy 0, policy_version 38850 (0.0010) -[2023-10-12 04:47:21,266][78091] Updated weights for policy 0, policy_version 38860 (0.0009) -[2023-10-12 04:47:21,639][78091] Updated weights for policy 0, policy_version 38870 (0.0008) -[2023-10-12 04:47:22,003][78091] Updated weights for policy 0, policy_version 38880 (0.0007) -[2023-10-12 04:47:23,795][78123] Updated weights for policy 1, policy_version 38690 (0.0009) -[2023-10-12 04:47:24,159][78123] Updated weights for policy 1, policy_version 38700 (0.0009) -[2023-10-12 04:47:24,521][78123] Updated weights for policy 1, policy_version 38710 (0.0009) -[2023-10-12 04:47:24,892][78123] Updated weights for policy 1, policy_version 38720 (0.0007) -[2023-10-12 04:47:25,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 79462400. Throughput: 0: 1591.6, 1: 1594.7. Samples: 19874996. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-12 04:47:25,202][77203] Avg episode reward: [(0, '44.620'), (1, '43.330')] -[2023-10-12 04:47:26,177][78091] Updated weights for policy 0, policy_version 38890 (0.0008) -[2023-10-12 04:47:26,545][78091] Updated weights for policy 0, policy_version 38900 (0.0009) -[2023-10-12 04:47:26,921][78091] Updated weights for policy 0, policy_version 38910 (0.0009) -[2023-10-12 04:47:29,201][78123] Updated weights for policy 1, policy_version 38730 (0.0008) -[2023-10-12 04:47:29,560][78123] Updated weights for policy 1, policy_version 38740 (0.0007) -[2023-10-12 04:47:29,928][78123] Updated weights for policy 1, policy_version 38750 (0.0009) -[2023-10-12 04:47:30,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 79527936. Throughput: 0: 1581.4, 1: 1596.2. Samples: 19884716. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-12 04:47:30,201][77203] Avg episode reward: [(0, '48.540'), (1, '37.540')] -[2023-10-12 04:47:30,973][78091] Updated weights for policy 0, policy_version 38920 (0.0009) -[2023-10-12 04:47:31,349][78091] Updated weights for policy 0, policy_version 38930 (0.0010) -[2023-10-12 04:47:31,720][78091] Updated weights for policy 0, policy_version 38940 (0.0007) -[2023-10-12 04:47:34,245][78123] Updated weights for policy 1, policy_version 38760 (0.0008) -[2023-10-12 04:47:34,618][78123] Updated weights for policy 1, policy_version 38770 (0.0009) -[2023-10-12 04:47:34,985][78123] Updated weights for policy 1, policy_version 38780 (0.0008) -[2023-10-12 04:47:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 79593472. Throughput: 0: 1584.0, 1: 1615.1. Samples: 19904260. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-12 04:47:35,202][77203] Avg episode reward: [(0, '47.160'), (1, '39.970')] -[2023-10-12 04:47:36,096][78091] Updated weights for policy 0, policy_version 38950 (0.0008) -[2023-10-12 04:47:36,477][78091] Updated weights for policy 0, policy_version 38960 (0.0007) -[2023-10-12 04:47:36,849][78091] Updated weights for policy 0, policy_version 38970 (0.0008) -[2023-10-12 04:47:39,126][78123] Updated weights for policy 1, policy_version 38790 (0.0009) -[2023-10-12 04:47:39,490][78123] Updated weights for policy 1, policy_version 38800 (0.0007) -[2023-10-12 04:47:39,859][78123] Updated weights for policy 1, policy_version 38810 (0.0011) -[2023-10-12 04:47:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 79659008. Throughput: 0: 1589.9, 1: 1603.4. Samples: 19923048. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-12 04:47:40,201][77203] Avg episode reward: [(0, '46.700'), (1, '44.550')] -[2023-10-12 04:47:41,123][78091] Updated weights for policy 0, policy_version 38980 (0.0009) -[2023-10-12 04:47:41,485][78091] Updated weights for policy 0, policy_version 38990 (0.0009) -[2023-10-12 04:47:41,859][78091] Updated weights for policy 0, policy_version 39000 (0.0009) -[2023-10-12 04:47:44,384][78123] Updated weights for policy 1, policy_version 38820 (0.0010) -[2023-10-12 04:47:44,764][78123] Updated weights for policy 1, policy_version 38830 (0.0008) -[2023-10-12 04:47:45,121][78123] Updated weights for policy 1, policy_version 38840 (0.0009) -[2023-10-12 04:47:45,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 79691776. Throughput: 0: 1590.4, 1: 1594.3. Samples: 19932502. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-12 04:47:45,201][77203] Avg episode reward: [(0, '46.410'), (1, '36.070')] -[2023-10-12 04:47:46,317][78091] Updated weights for policy 0, policy_version 39010 (0.0008) -[2023-10-12 04:47:46,683][78091] Updated weights for policy 0, policy_version 39020 (0.0009) -[2023-10-12 04:47:47,064][78091] Updated weights for policy 0, policy_version 39030 (0.0008) -[2023-10-12 04:47:47,440][78091] Updated weights for policy 0, policy_version 39040 (0.0009) -[2023-10-12 04:47:49,613][78123] Updated weights for policy 1, policy_version 38850 (0.0008) -[2023-10-12 04:47:50,007][78123] Updated weights for policy 1, policy_version 38860 (0.0009) -[2023-10-12 04:47:50,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 79757312. Throughput: 0: 1593.4, 1: 1598.1. Samples: 19951888. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-12 04:47:50,202][77203] Avg episode reward: [(0, '46.230'), (1, '40.710')] -[2023-10-12 04:47:50,373][78123] Updated weights for policy 1, policy_version 38870 (0.0008) -[2023-10-12 04:47:50,740][78123] Updated weights for policy 1, policy_version 38880 (0.0007) -[2023-10-12 04:47:51,655][78091] Updated weights for policy 0, policy_version 39050 (0.0010) -[2023-10-12 04:47:52,038][78091] Updated weights for policy 0, policy_version 39060 (0.0009) -[2023-10-12 04:47:52,415][78091] Updated weights for policy 0, policy_version 39070 (0.0008) -[2023-10-12 04:47:55,044][78123] Updated weights for policy 1, policy_version 38890 (0.0008) -[2023-10-12 04:47:55,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 79822848. Throughput: 0: 1595.5, 1: 1612.0. Samples: 19971292. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-12 04:47:55,202][77203] Avg episode reward: [(0, '46.010'), (1, '41.820')] -[2023-10-12 04:47:55,408][78123] Updated weights for policy 1, policy_version 38900 (0.0011) -[2023-10-12 04:47:55,790][78123] Updated weights for policy 1, policy_version 38910 (0.0010) -[2023-10-12 04:47:56,565][78091] Updated weights for policy 0, policy_version 39080 (0.0009) -[2023-10-12 04:47:56,941][78091] Updated weights for policy 0, policy_version 39090 (0.0009) -[2023-10-12 04:47:57,318][78091] Updated weights for policy 0, policy_version 39100 (0.0010) -[2023-10-12 04:47:59,820][78123] Updated weights for policy 1, policy_version 38920 (0.0008) -[2023-10-12 04:48:00,187][78123] Updated weights for policy 1, policy_version 38930 (0.0009) -[2023-10-12 04:48:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 79888384. Throughput: 0: 1599.6, 1: 1587.6. Samples: 19980206. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-12 04:48:00,201][77203] Avg episode reward: [(0, '45.320'), (1, '37.400')] -[2023-10-12 04:48:00,560][78123] Updated weights for policy 1, policy_version 38940 (0.0010) -[2023-10-12 04:48:01,560][78091] Updated weights for policy 0, policy_version 39110 (0.0010) -[2023-10-12 04:48:01,921][78091] Updated weights for policy 0, policy_version 39120 (0.0009) -[2023-10-12 04:48:02,293][78091] Updated weights for policy 0, policy_version 39130 (0.0009) -[2023-10-12 04:48:04,901][78123] Updated weights for policy 1, policy_version 38950 (0.0009) -[2023-10-12 04:48:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 79953920. Throughput: 0: 1601.7, 1: 1587.9. Samples: 19999736. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-12 04:48:05,202][77203] Avg episode reward: [(0, '43.540'), (1, '42.390')] -[2023-10-12 04:48:05,266][78123] Updated weights for policy 1, policy_version 38960 (0.0008) -[2023-10-12 04:48:05,627][78123] Updated weights for policy 1, policy_version 38970 (0.0010) -[2023-10-12 04:48:06,484][78091] Updated weights for policy 0, policy_version 39140 (0.0009) -[2023-10-12 04:48:06,856][78091] Updated weights for policy 0, policy_version 39150 (0.0009) -[2023-10-12 04:48:07,237][78091] Updated weights for policy 0, policy_version 39160 (0.0009) -[2023-10-12 04:48:10,071][78123] Updated weights for policy 1, policy_version 38980 (0.0008) -[2023-10-12 04:48:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 80019456. Throughput: 0: 1598.0, 1: 1609.7. Samples: 20019344. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-12 04:48:10,201][77203] Avg episode reward: [(0, '47.270'), (1, '41.620')] -[2023-10-12 04:48:10,442][78123] Updated weights for policy 1, policy_version 38990 (0.0010) -[2023-10-12 04:48:10,808][78123] Updated weights for policy 1, policy_version 39000 (0.0008) -[2023-10-12 04:48:11,682][78091] Updated weights for policy 0, policy_version 39170 (0.0009) -[2023-10-12 04:48:12,047][78091] Updated weights for policy 0, policy_version 39180 (0.0008) -[2023-10-12 04:48:12,418][78091] Updated weights for policy 0, policy_version 39190 (0.0009) -[2023-10-12 04:48:12,789][78091] Updated weights for policy 0, policy_version 39200 (0.0008) -[2023-10-12 04:48:14,988][78123] Updated weights for policy 1, policy_version 39010 (0.0007) -[2023-10-12 04:48:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 80084992. Throughput: 0: 1595.1, 1: 1587.7. Samples: 20027940. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-12 04:48:15,201][77203] Avg episode reward: [(0, '42.800'), (1, '41.720')] -[2023-10-12 04:48:15,352][78123] Updated weights for policy 1, policy_version 39020 (0.0008) -[2023-10-12 04:48:15,721][78123] Updated weights for policy 1, policy_version 39030 (0.0009) -[2023-10-12 04:48:16,087][78123] Updated weights for policy 1, policy_version 39040 (0.0008) -[2023-10-12 04:48:17,006][78091] Updated weights for policy 0, policy_version 39210 (0.0008) -[2023-10-12 04:48:17,378][78091] Updated weights for policy 0, policy_version 39220 (0.0008) -[2023-10-12 04:48:17,747][78091] Updated weights for policy 0, policy_version 39230 (0.0008) -[2023-10-12 04:48:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 80150528. Throughput: 0: 1598.7, 1: 1595.9. Samples: 20048014. Policy #0 lag: (min: 23.0, avg: 26.6, max: 55.0) -[2023-10-12 04:48:20,202][77203] Avg episode reward: [(0, '42.210'), (1, '37.520')] -[2023-10-12 04:48:20,359][78123] Updated weights for policy 1, policy_version 39050 (0.0010) -[2023-10-12 04:48:20,721][78123] Updated weights for policy 1, policy_version 39060 (0.0010) -[2023-10-12 04:48:21,091][78123] Updated weights for policy 1, policy_version 39070 (0.0010) -[2023-10-12 04:48:22,106][78091] Updated weights for policy 0, policy_version 39240 (0.0008) -[2023-10-12 04:48:22,485][78091] Updated weights for policy 0, policy_version 39250 (0.0007) -[2023-10-12 04:48:22,854][78091] Updated weights for policy 0, policy_version 39260 (0.0010) -[2023-10-12 04:48:25,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 80216064. Throughput: 0: 1600.2, 1: 1609.3. Samples: 20067474. Policy #0 lag: (min: 23.0, avg: 26.6, max: 55.0) -[2023-10-12 04:48:25,201][77203] Avg episode reward: [(0, '39.020'), (1, '43.170')] -[2023-10-12 04:48:25,582][78123] Updated weights for policy 1, policy_version 39080 (0.0009) -[2023-10-12 04:48:25,956][78123] Updated weights for policy 1, policy_version 39090 (0.0010) -[2023-10-12 04:48:26,329][78123] Updated weights for policy 1, policy_version 39100 (0.0010) -[2023-10-12 04:48:27,059][78091] Updated weights for policy 0, policy_version 39270 (0.0008) -[2023-10-12 04:48:27,436][78091] Updated weights for policy 0, policy_version 39280 (0.0008) -[2023-10-12 04:48:27,798][78091] Updated weights for policy 0, policy_version 39290 (0.0008) -[2023-10-12 04:48:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 80281600. Throughput: 0: 1608.8, 1: 1591.0. Samples: 20076496. Policy #0 lag: (min: 23.0, avg: 26.6, max: 55.0) -[2023-10-12 04:48:30,202][77203] Avg episode reward: [(0, '46.090'), (1, '45.200')] -[2023-10-12 04:48:30,767][78123] Updated weights for policy 1, policy_version 39110 (0.0010) -[2023-10-12 04:48:31,128][78123] Updated weights for policy 1, policy_version 39120 (0.0007) -[2023-10-12 04:48:31,508][78123] Updated weights for policy 1, policy_version 39130 (0.0010) -[2023-10-12 04:48:32,219][78091] Updated weights for policy 0, policy_version 39300 (0.0008) -[2023-10-12 04:48:32,592][78091] Updated weights for policy 0, policy_version 39310 (0.0008) -[2023-10-12 04:48:32,959][78091] Updated weights for policy 0, policy_version 39320 (0.0010) -[2023-10-12 04:48:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 80347136. Throughput: 0: 1599.9, 1: 1594.9. Samples: 20095654. Policy #0 lag: (min: 23.0, avg: 26.6, max: 55.0) -[2023-10-12 04:48:35,201][77203] Avg episode reward: [(0, '44.420'), (1, '39.630')] -[2023-10-12 04:48:35,810][78123] Updated weights for policy 1, policy_version 39140 (0.0010) -[2023-10-12 04:48:36,208][78123] Updated weights for policy 1, policy_version 39150 (0.0008) -[2023-10-12 04:48:36,565][78123] Updated weights for policy 1, policy_version 39160 (0.0009) -[2023-10-12 04:48:37,259][78091] Updated weights for policy 0, policy_version 39330 (0.0008) -[2023-10-12 04:48:37,621][78091] Updated weights for policy 0, policy_version 39340 (0.0008) -[2023-10-12 04:48:37,999][78091] Updated weights for policy 0, policy_version 39350 (0.0007) -[2023-10-12 04:48:38,370][78091] Updated weights for policy 0, policy_version 39360 (0.0008) -[2023-10-12 04:48:40,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 80412672. Throughput: 0: 1600.5, 1: 1595.3. Samples: 20115106. Policy #0 lag: (min: 23.0, avg: 26.6, max: 55.0) -[2023-10-12 04:48:40,201][77203] Avg episode reward: [(0, '43.750'), (1, '44.880')] -[2023-10-12 04:48:41,010][78123] Updated weights for policy 1, policy_version 39170 (0.0010) -[2023-10-12 04:48:41,366][78123] Updated weights for policy 1, policy_version 39180 (0.0007) -[2023-10-12 04:48:41,732][78123] Updated weights for policy 1, policy_version 39190 (0.0007) -[2023-10-12 04:48:42,100][78123] Updated weights for policy 1, policy_version 39200 (0.0008) -[2023-10-12 04:48:42,689][78091] Updated weights for policy 0, policy_version 39370 (0.0008) -[2023-10-12 04:48:43,062][78091] Updated weights for policy 0, policy_version 39380 (0.0007) -[2023-10-12 04:48:43,433][78091] Updated weights for policy 0, policy_version 39390 (0.0008) -[2023-10-12 04:48:45,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 80478208. Throughput: 0: 1614.4, 1: 1591.2. Samples: 20124458. Policy #0 lag: (min: 23.0, avg: 26.6, max: 55.0) -[2023-10-12 04:48:45,202][77203] Avg episode reward: [(0, '41.490'), (1, '44.090')] -[2023-10-12 04:48:46,347][78123] Updated weights for policy 1, policy_version 39210 (0.0007) -[2023-10-12 04:48:46,710][78123] Updated weights for policy 1, policy_version 39220 (0.0009) -[2023-10-12 04:48:47,087][78123] Updated weights for policy 1, policy_version 39230 (0.0010) -[2023-10-12 04:48:47,771][78091] Updated weights for policy 0, policy_version 39400 (0.0010) -[2023-10-12 04:48:48,135][78091] Updated weights for policy 0, policy_version 39410 (0.0007) -[2023-10-12 04:48:48,514][78091] Updated weights for policy 0, policy_version 39420 (0.0007) -[2023-10-12 04:48:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 80543744. Throughput: 0: 1592.2, 1: 1593.7. Samples: 20143104. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:48:50,201][77203] Avg episode reward: [(0, '47.600'), (1, '39.650')] -[2023-10-12 04:48:51,395][78123] Updated weights for policy 1, policy_version 39240 (0.0007) -[2023-10-12 04:48:51,760][78123] Updated weights for policy 1, policy_version 39250 (0.0007) -[2023-10-12 04:48:52,131][78123] Updated weights for policy 1, policy_version 39260 (0.0008) -[2023-10-12 04:48:52,900][78091] Updated weights for policy 0, policy_version 39430 (0.0007) -[2023-10-12 04:48:53,281][78091] Updated weights for policy 0, policy_version 39440 (0.0007) -[2023-10-12 04:48:53,641][78091] Updated weights for policy 0, policy_version 39450 (0.0007) -[2023-10-12 04:48:55,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 80609280. Throughput: 0: 1589.5, 1: 1592.8. Samples: 20162546. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:48:55,201][77203] Avg episode reward: [(0, '49.410'), (1, '44.790')] -[2023-10-12 04:48:56,524][78123] Updated weights for policy 1, policy_version 39270 (0.0009) -[2023-10-12 04:48:56,891][78123] Updated weights for policy 1, policy_version 39280 (0.0010) -[2023-10-12 04:48:57,252][78123] Updated weights for policy 1, policy_version 39290 (0.0011) -[2023-10-12 04:48:58,033][78091] Updated weights for policy 0, policy_version 39460 (0.0008) -[2023-10-12 04:48:58,410][78091] Updated weights for policy 0, policy_version 39470 (0.0010) -[2023-10-12 04:48:58,769][78091] Updated weights for policy 0, policy_version 39480 (0.0011) -[2023-10-12 04:49:00,201][77203] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 80674816. Throughput: 0: 1617.1, 1: 1591.5. Samples: 20172328. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:49:00,202][77203] Avg episode reward: [(0, '55.010'), (1, '40.800')] -[2023-10-12 04:49:01,410][78123] Updated weights for policy 1, policy_version 39300 (0.0009) -[2023-10-12 04:49:01,777][78123] Updated weights for policy 1, policy_version 39310 (0.0010) -[2023-10-12 04:49:02,151][78123] Updated weights for policy 1, policy_version 39320 (0.0009) -[2023-10-12 04:49:03,086][78091] Updated weights for policy 0, policy_version 39490 (0.0009) -[2023-10-12 04:49:03,471][78091] Updated weights for policy 0, policy_version 39500 (0.0009) -[2023-10-12 04:49:03,843][78091] Updated weights for policy 0, policy_version 39510 (0.0008) -[2023-10-12 04:49:04,207][78091] Updated weights for policy 0, policy_version 39520 (0.0007) -[2023-10-12 04:49:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 80740352. Throughput: 0: 1597.2, 1: 1584.9. Samples: 20191208. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:49:05,201][77203] Avg episode reward: [(0, '47.520'), (1, '37.080')] -[2023-10-12 04:49:06,179][78123] Updated weights for policy 1, policy_version 39330 (0.0010) -[2023-10-12 04:49:06,545][78123] Updated weights for policy 1, policy_version 39340 (0.0008) -[2023-10-12 04:49:06,929][78123] Updated weights for policy 1, policy_version 39350 (0.0009) -[2023-10-12 04:49:07,285][78123] Updated weights for policy 1, policy_version 39360 (0.0008) -[2023-10-12 04:49:08,693][78091] Updated weights for policy 0, policy_version 39530 (0.0007) -[2023-10-12 04:49:09,071][78091] Updated weights for policy 0, policy_version 39540 (0.0008) -[2023-10-12 04:49:09,437][78091] Updated weights for policy 0, policy_version 39550 (0.0008) -[2023-10-12 04:49:10,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 80805888. Throughput: 0: 1580.1, 1: 1592.2. Samples: 20210226. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:49:10,201][77203] Avg episode reward: [(0, '47.660'), (1, '43.500')] -[2023-10-12 04:49:10,210][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000039360_40304640.pth... -[2023-10-12 04:49:10,210][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000039552_40501248.pth... -[2023-10-12 04:49:10,240][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000038048_38961152.pth -[2023-10-12 04:49:10,245][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000037888_38797312.pth -[2023-10-12 04:49:11,676][78123] Updated weights for policy 1, policy_version 39370 (0.0009) -[2023-10-12 04:49:12,039][78123] Updated weights for policy 1, policy_version 39380 (0.0010) -[2023-10-12 04:49:12,420][78123] Updated weights for policy 1, policy_version 39390 (0.0008) -[2023-10-12 04:49:13,801][78091] Updated weights for policy 0, policy_version 39560 (0.0008) -[2023-10-12 04:49:14,177][78091] Updated weights for policy 0, policy_version 39570 (0.0009) -[2023-10-12 04:49:14,557][78091] Updated weights for policy 0, policy_version 39580 (0.0009) -[2023-10-12 04:49:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 80871424. Throughput: 0: 1598.0, 1: 1593.3. Samples: 20220102. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:49:15,202][77203] Avg episode reward: [(0, '44.680'), (1, '36.610')] -[2023-10-12 04:49:16,648][78123] Updated weights for policy 1, policy_version 39400 (0.0007) -[2023-10-12 04:49:17,027][78123] Updated weights for policy 1, policy_version 39410 (0.0010) -[2023-10-12 04:49:17,390][78123] Updated weights for policy 1, policy_version 39420 (0.0007) -[2023-10-12 04:49:18,712][78091] Updated weights for policy 0, policy_version 39590 (0.0008) -[2023-10-12 04:49:19,097][78091] Updated weights for policy 0, policy_version 39600 (0.0009) -[2023-10-12 04:49:19,468][78091] Updated weights for policy 0, policy_version 39610 (0.0008) -[2023-10-12 04:49:20,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 80936960. Throughput: 0: 1599.4, 1: 1597.1. Samples: 20239496. Policy #0 lag: (min: 31.0, avg: 31.2, max: 39.0) -[2023-10-12 04:49:20,201][77203] Avg episode reward: [(0, '44.870'), (1, '34.700')] -[2023-10-12 04:49:21,785][78123] Updated weights for policy 1, policy_version 39430 (0.0010) -[2023-10-12 04:49:22,172][78123] Updated weights for policy 1, policy_version 39440 (0.0010) -[2023-10-12 04:49:22,540][78123] Updated weights for policy 1, policy_version 39450 (0.0011) -[2023-10-12 04:49:23,721][78091] Updated weights for policy 0, policy_version 39620 (0.0008) -[2023-10-12 04:49:24,096][78091] Updated weights for policy 0, policy_version 39630 (0.0008) -[2023-10-12 04:49:24,465][78091] Updated weights for policy 0, policy_version 39640 (0.0009) -[2023-10-12 04:49:25,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 81002496. Throughput: 0: 1576.8, 1: 1598.6. Samples: 20257998. Policy #0 lag: (min: 31.0, avg: 31.2, max: 39.0) -[2023-10-12 04:49:25,202][77203] Avg episode reward: [(0, '47.130'), (1, '42.550')] -[2023-10-12 04:49:26,912][78123] Updated weights for policy 1, policy_version 39460 (0.0008) -[2023-10-12 04:49:27,269][78123] Updated weights for policy 1, policy_version 39470 (0.0008) -[2023-10-12 04:49:27,646][78123] Updated weights for policy 1, policy_version 39480 (0.0010) -[2023-10-12 04:49:28,784][78091] Updated weights for policy 0, policy_version 39650 (0.0010) -[2023-10-12 04:49:29,154][78091] Updated weights for policy 0, policy_version 39660 (0.0008) -[2023-10-12 04:49:29,518][78091] Updated weights for policy 0, policy_version 39670 (0.0010) -[2023-10-12 04:49:29,887][78091] Updated weights for policy 0, policy_version 39680 (0.0008) -[2023-10-12 04:49:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 81068032. Throughput: 0: 1588.6, 1: 1601.5. Samples: 20268012. Policy #0 lag: (min: 31.0, avg: 31.2, max: 39.0) -[2023-10-12 04:49:30,201][77203] Avg episode reward: [(0, '48.700'), (1, '39.440')] -[2023-10-12 04:49:32,035][78123] Updated weights for policy 1, policy_version 39490 (0.0009) -[2023-10-12 04:49:32,410][78123] Updated weights for policy 1, policy_version 39500 (0.0010) -[2023-10-12 04:49:32,778][78123] Updated weights for policy 1, policy_version 39510 (0.0009) -[2023-10-12 04:49:33,143][78123] Updated weights for policy 1, policy_version 39520 (0.0007) -[2023-10-12 04:49:34,335][78091] Updated weights for policy 0, policy_version 39690 (0.0010) -[2023-10-12 04:49:34,705][78091] Updated weights for policy 0, policy_version 39700 (0.0009) -[2023-10-12 04:49:35,069][78091] Updated weights for policy 0, policy_version 39710 (0.0009) -[2023-10-12 04:49:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 81133568. Throughput: 0: 1607.3, 1: 1594.0. Samples: 20287164. Policy #0 lag: (min: 31.0, avg: 31.2, max: 39.0) -[2023-10-12 04:49:35,202][77203] Avg episode reward: [(0, '48.720'), (1, '37.720')] -[2023-10-12 04:49:37,402][78123] Updated weights for policy 1, policy_version 39530 (0.0009) -[2023-10-12 04:49:37,765][78123] Updated weights for policy 1, policy_version 39540 (0.0009) -[2023-10-12 04:49:38,131][78123] Updated weights for policy 1, policy_version 39550 (0.0008) -[2023-10-12 04:49:39,299][78091] Updated weights for policy 0, policy_version 39720 (0.0009) -[2023-10-12 04:49:39,671][78091] Updated weights for policy 0, policy_version 39730 (0.0007) -[2023-10-12 04:49:40,051][78091] Updated weights for policy 0, policy_version 39740 (0.0008) -[2023-10-12 04:49:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 81199104. Throughput: 0: 1594.5, 1: 1594.8. Samples: 20306066. Policy #0 lag: (min: 31.0, avg: 31.2, max: 39.0) -[2023-10-12 04:49:40,202][77203] Avg episode reward: [(0, '45.080'), (1, '46.600')] -[2023-10-12 04:49:42,345][78123] Updated weights for policy 1, policy_version 39560 (0.0009) -[2023-10-12 04:49:42,717][78123] Updated weights for policy 1, policy_version 39570 (0.0009) -[2023-10-12 04:49:43,090][78123] Updated weights for policy 1, policy_version 39580 (0.0009) -[2023-10-12 04:49:44,354][78091] Updated weights for policy 0, policy_version 39750 (0.0008) -[2023-10-12 04:49:44,728][78091] Updated weights for policy 0, policy_version 39760 (0.0008) -[2023-10-12 04:49:45,097][78091] Updated weights for policy 0, policy_version 39770 (0.0008) -[2023-10-12 04:49:45,201][77203] Fps is (10 sec: 9830.6, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 81231872. Throughput: 0: 1584.1, 1: 1609.3. Samples: 20316030. Policy #0 lag: (min: 31.0, avg: 31.2, max: 39.0) -[2023-10-12 04:49:45,202][77203] Avg episode reward: [(0, '47.000'), (1, '37.430')] -[2023-10-12 04:49:47,412][78123] Updated weights for policy 1, policy_version 39590 (0.0007) -[2023-10-12 04:49:47,769][78123] Updated weights for policy 1, policy_version 39600 (0.0010) -[2023-10-12 04:49:48,146][78123] Updated weights for policy 1, policy_version 39610 (0.0008) -[2023-10-12 04:49:49,399][78091] Updated weights for policy 0, policy_version 39780 (0.0011) -[2023-10-12 04:49:49,776][78091] Updated weights for policy 0, policy_version 39790 (0.0007) -[2023-10-12 04:49:50,151][78091] Updated weights for policy 0, policy_version 39800 (0.0008) -[2023-10-12 04:49:50,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 81297408. Throughput: 0: 1598.5, 1: 1599.9. Samples: 20335134. Policy #0 lag: (min: 31.0, avg: 31.2, max: 39.0) -[2023-10-12 04:49:50,202][77203] Avg episode reward: [(0, '47.410'), (1, '36.900')] -[2023-10-12 04:49:52,210][78123] Updated weights for policy 1, policy_version 39620 (0.0008) -[2023-10-12 04:49:52,575][78123] Updated weights for policy 1, policy_version 39630 (0.0008) -[2023-10-12 04:49:52,945][78123] Updated weights for policy 1, policy_version 39640 (0.0007) -[2023-10-12 04:49:54,537][78091] Updated weights for policy 0, policy_version 39810 (0.0007) -[2023-10-12 04:49:54,939][78091] Updated weights for policy 0, policy_version 39820 (0.0008) -[2023-10-12 04:49:55,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 81362944. Throughput: 0: 1607.1, 1: 1597.2. Samples: 20354420. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-12 04:49:55,201][77203] Avg episode reward: [(0, '45.130'), (1, '45.800')] -[2023-10-12 04:49:55,310][78091] Updated weights for policy 0, policy_version 39830 (0.0009) -[2023-10-12 04:49:55,689][78091] Updated weights for policy 0, policy_version 39840 (0.0009) -[2023-10-12 04:49:57,292][78123] Updated weights for policy 1, policy_version 39650 (0.0008) -[2023-10-12 04:49:57,657][78123] Updated weights for policy 1, policy_version 39660 (0.0009) -[2023-10-12 04:49:58,024][78123] Updated weights for policy 1, policy_version 39670 (0.0010) -[2023-10-12 04:49:58,398][78123] Updated weights for policy 1, policy_version 39680 (0.0009) -[2023-10-12 04:50:00,072][78091] Updated weights for policy 0, policy_version 39850 (0.0009) -[2023-10-12 04:50:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 81428480. Throughput: 0: 1586.0, 1: 1612.4. Samples: 20364030. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-12 04:50:00,201][77203] Avg episode reward: [(0, '45.020'), (1, '38.120')] -[2023-10-12 04:50:00,445][78091] Updated weights for policy 0, policy_version 39860 (0.0008) -[2023-10-12 04:50:00,826][78091] Updated weights for policy 0, policy_version 39870 (0.0008) -[2023-10-12 04:50:02,843][78123] Updated weights for policy 1, policy_version 39690 (0.0008) -[2023-10-12 04:50:03,212][78123] Updated weights for policy 1, policy_version 39700 (0.0007) -[2023-10-12 04:50:03,588][78123] Updated weights for policy 1, policy_version 39710 (0.0007) -[2023-10-12 04:50:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 81494016. Throughput: 0: 1591.0, 1: 1592.9. Samples: 20382774. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-12 04:50:05,201][77203] Avg episode reward: [(0, '38.710'), (1, '41.080')] -[2023-10-12 04:50:05,255][78091] Updated weights for policy 0, policy_version 39880 (0.0008) -[2023-10-12 04:50:05,636][78091] Updated weights for policy 0, policy_version 39890 (0.0009) -[2023-10-12 04:50:06,007][78091] Updated weights for policy 0, policy_version 39900 (0.0008) -[2023-10-12 04:50:08,052][78123] Updated weights for policy 1, policy_version 39720 (0.0007) -[2023-10-12 04:50:08,428][78123] Updated weights for policy 1, policy_version 39730 (0.0010) -[2023-10-12 04:50:08,799][78123] Updated weights for policy 1, policy_version 39740 (0.0008) -[2023-10-12 04:50:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 81559552. Throughput: 0: 1613.5, 1: 1587.3. Samples: 20402034. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-12 04:50:10,201][77203] Avg episode reward: [(0, '38.630'), (1, '44.990')] -[2023-10-12 04:50:10,249][78091] Updated weights for policy 0, policy_version 39910 (0.0008) -[2023-10-12 04:50:10,618][78091] Updated weights for policy 0, policy_version 39920 (0.0010) -[2023-10-12 04:50:10,988][78091] Updated weights for policy 0, policy_version 39930 (0.0010) -[2023-10-12 04:50:13,206][78123] Updated weights for policy 1, policy_version 39750 (0.0008) -[2023-10-12 04:50:13,585][78123] Updated weights for policy 1, policy_version 39760 (0.0007) -[2023-10-12 04:50:13,942][78123] Updated weights for policy 1, policy_version 39770 (0.0007) -[2023-10-12 04:50:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 81625088. Throughput: 0: 1584.4, 1: 1611.8. Samples: 20411842. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-12 04:50:15,201][77203] Avg episode reward: [(0, '42.860'), (1, '39.530')] -[2023-10-12 04:50:15,288][78091] Updated weights for policy 0, policy_version 39940 (0.0008) -[2023-10-12 04:50:15,661][78091] Updated weights for policy 0, policy_version 39950 (0.0010) -[2023-10-12 04:50:16,032][78091] Updated weights for policy 0, policy_version 39960 (0.0009) -[2023-10-12 04:50:18,358][78123] Updated weights for policy 1, policy_version 39780 (0.0009) -[2023-10-12 04:50:18,724][78123] Updated weights for policy 1, policy_version 39790 (0.0009) -[2023-10-12 04:50:19,098][78123] Updated weights for policy 1, policy_version 39800 (0.0009) -[2023-10-12 04:50:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 81690624. Throughput: 0: 1588.2, 1: 1604.5. Samples: 20430834. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-12 04:50:20,201][77203] Avg episode reward: [(0, '42.770'), (1, '41.270')] -[2023-10-12 04:50:20,353][78091] Updated weights for policy 0, policy_version 39970 (0.0010) -[2023-10-12 04:50:20,719][78091] Updated weights for policy 0, policy_version 39980 (0.0008) -[2023-10-12 04:50:21,084][78091] Updated weights for policy 0, policy_version 39990 (0.0009) -[2023-10-12 04:50:21,458][78091] Updated weights for policy 0, policy_version 40000 (0.0008) -[2023-10-12 04:50:23,299][78123] Updated weights for policy 1, policy_version 39810 (0.0008) -[2023-10-12 04:50:23,670][78123] Updated weights for policy 1, policy_version 39820 (0.0008) -[2023-10-12 04:50:24,027][78123] Updated weights for policy 1, policy_version 39830 (0.0010) -[2023-10-12 04:50:24,391][78123] Updated weights for policy 1, policy_version 39840 (0.0008) -[2023-10-12 04:50:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 81756160. Throughput: 0: 1604.7, 1: 1593.7. Samples: 20449994. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-12 04:50:25,202][77203] Avg episode reward: [(0, '45.890'), (1, '43.380')] -[2023-10-12 04:50:25,716][78091] Updated weights for policy 0, policy_version 40010 (0.0011) -[2023-10-12 04:50:26,094][78091] Updated weights for policy 0, policy_version 40020 (0.0008) -[2023-10-12 04:50:26,466][78091] Updated weights for policy 0, policy_version 40030 (0.0007) -[2023-10-12 04:50:28,795][78123] Updated weights for policy 1, policy_version 39850 (0.0007) -[2023-10-12 04:50:29,171][78123] Updated weights for policy 1, policy_version 39860 (0.0009) -[2023-10-12 04:50:29,528][78123] Updated weights for policy 1, policy_version 39870 (0.0009) -[2023-10-12 04:50:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 81821696. Throughput: 0: 1586.4, 1: 1604.0. Samples: 20459598. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-12 04:50:30,201][77203] Avg episode reward: [(0, '47.400'), (1, '41.810')] -[2023-10-12 04:50:30,825][78091] Updated weights for policy 0, policy_version 40040 (0.0007) -[2023-10-12 04:50:31,206][78091] Updated weights for policy 0, policy_version 40050 (0.0009) -[2023-10-12 04:50:31,574][78091] Updated weights for policy 0, policy_version 40060 (0.0009) -[2023-10-12 04:50:34,011][78123] Updated weights for policy 1, policy_version 39880 (0.0011) -[2023-10-12 04:50:34,386][78123] Updated weights for policy 1, policy_version 39890 (0.0011) -[2023-10-12 04:50:34,756][78123] Updated weights for policy 1, policy_version 39900 (0.0010) -[2023-10-12 04:50:35,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 81887232. Throughput: 0: 1590.1, 1: 1604.0. Samples: 20478866. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-12 04:50:35,202][77203] Avg episode reward: [(0, '41.680'), (1, '43.630')] -[2023-10-12 04:50:35,790][78091] Updated weights for policy 0, policy_version 40070 (0.0010) -[2023-10-12 04:50:36,153][78091] Updated weights for policy 0, policy_version 40080 (0.0007) -[2023-10-12 04:50:36,533][78091] Updated weights for policy 0, policy_version 40090 (0.0007) -[2023-10-12 04:50:39,039][78123] Updated weights for policy 1, policy_version 39910 (0.0010) -[2023-10-12 04:50:39,397][78123] Updated weights for policy 1, policy_version 39920 (0.0008) -[2023-10-12 04:50:39,760][78123] Updated weights for policy 1, policy_version 39930 (0.0008) -[2023-10-12 04:50:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 81952768. Throughput: 0: 1598.0, 1: 1581.9. Samples: 20497518. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-12 04:50:40,202][77203] Avg episode reward: [(0, '41.090'), (1, '37.420')] -[2023-10-12 04:50:40,998][78091] Updated weights for policy 0, policy_version 40100 (0.0008) -[2023-10-12 04:50:41,391][78091] Updated weights for policy 0, policy_version 40110 (0.0007) -[2023-10-12 04:50:41,765][78091] Updated weights for policy 0, policy_version 40120 (0.0007) -[2023-10-12 04:50:44,138][78123] Updated weights for policy 1, policy_version 39940 (0.0009) -[2023-10-12 04:50:44,512][78123] Updated weights for policy 1, policy_version 39950 (0.0011) -[2023-10-12 04:50:44,888][78123] Updated weights for policy 1, policy_version 39960 (0.0008) -[2023-10-12 04:50:45,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 82018304. Throughput: 0: 1588.6, 1: 1585.2. Samples: 20506850. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-12 04:50:45,201][77203] Avg episode reward: [(0, '41.150'), (1, '42.400')] -[2023-10-12 04:50:45,921][78091] Updated weights for policy 0, policy_version 40130 (0.0007) -[2023-10-12 04:50:46,290][78091] Updated weights for policy 0, policy_version 40140 (0.0008) -[2023-10-12 04:50:46,674][78091] Updated weights for policy 0, policy_version 40150 (0.0008) -[2023-10-12 04:50:47,045][78091] Updated weights for policy 0, policy_version 40160 (0.0008) -[2023-10-12 04:50:49,092][78123] Updated weights for policy 1, policy_version 39970 (0.0007) -[2023-10-12 04:50:49,459][78123] Updated weights for policy 1, policy_version 39980 (0.0008) -[2023-10-12 04:50:49,827][78123] Updated weights for policy 1, policy_version 39990 (0.0009) -[2023-10-12 04:50:50,196][78123] Updated weights for policy 1, policy_version 40000 (0.0009) -[2023-10-12 04:50:50,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 82083840. Throughput: 0: 1590.6, 1: 1600.3. Samples: 20526368. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-12 04:50:50,202][77203] Avg episode reward: [(0, '39.820'), (1, '43.600')] -[2023-10-12 04:50:51,369][78091] Updated weights for policy 0, policy_version 40170 (0.0009) -[2023-10-12 04:50:51,728][78091] Updated weights for policy 0, policy_version 40180 (0.0010) -[2023-10-12 04:50:52,098][78091] Updated weights for policy 0, policy_version 40190 (0.0009) -[2023-10-12 04:50:54,607][78123] Updated weights for policy 1, policy_version 40010 (0.0007) -[2023-10-12 04:50:54,970][78123] Updated weights for policy 1, policy_version 40020 (0.0007) -[2023-10-12 04:50:55,201][77203] Fps is (10 sec: 9830.2, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 82116608. Throughput: 0: 1591.4, 1: 1591.0. Samples: 20545240. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-12 04:50:55,202][77203] Avg episode reward: [(0, '39.480'), (1, '41.090')] -[2023-10-12 04:50:55,343][78123] Updated weights for policy 1, policy_version 40030 (0.0009) -[2023-10-12 04:50:56,382][78091] Updated weights for policy 0, policy_version 40200 (0.0008) -[2023-10-12 04:50:56,755][78091] Updated weights for policy 0, policy_version 40210 (0.0007) -[2023-10-12 04:50:57,132][78091] Updated weights for policy 0, policy_version 40220 (0.0008) -[2023-10-12 04:50:59,767][78123] Updated weights for policy 1, policy_version 40040 (0.0010) -[2023-10-12 04:51:00,143][78123] Updated weights for policy 1, policy_version 40050 (0.0009) -[2023-10-12 04:51:00,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 82182144. Throughput: 0: 1590.9, 1: 1571.8. Samples: 20554166. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-12 04:51:00,201][77203] Avg episode reward: [(0, '43.980'), (1, '43.350')] -[2023-10-12 04:51:00,499][78123] Updated weights for policy 1, policy_version 40060 (0.0009) -[2023-10-12 04:51:01,586][78091] Updated weights for policy 0, policy_version 40230 (0.0009) -[2023-10-12 04:51:01,968][78091] Updated weights for policy 0, policy_version 40240 (0.0009) -[2023-10-12 04:51:02,332][78091] Updated weights for policy 0, policy_version 40250 (0.0011) -[2023-10-12 04:51:04,980][78123] Updated weights for policy 1, policy_version 40070 (0.0009) -[2023-10-12 04:51:05,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 82247680. Throughput: 0: 1583.8, 1: 1583.6. Samples: 20573368. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-12 04:51:05,201][77203] Avg episode reward: [(0, '50.250'), (1, '42.760')] -[2023-10-12 04:51:05,348][78123] Updated weights for policy 1, policy_version 40080 (0.0009) -[2023-10-12 04:51:05,716][78123] Updated weights for policy 1, policy_version 40090 (0.0010) -[2023-10-12 04:51:06,756][78091] Updated weights for policy 0, policy_version 40260 (0.0009) -[2023-10-12 04:51:07,115][78091] Updated weights for policy 0, policy_version 40270 (0.0008) -[2023-10-12 04:51:07,494][78091] Updated weights for policy 0, policy_version 40280 (0.0009) -[2023-10-12 04:51:10,118][78123] Updated weights for policy 1, policy_version 40100 (0.0009) -[2023-10-12 04:51:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 82313216. Throughput: 0: 1583.3, 1: 1590.0. Samples: 20592794. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-12 04:51:10,201][77203] Avg episode reward: [(0, '49.860'), (1, '36.490')] -[2023-10-12 04:51:10,212][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000040288_41254912.pth... -[2023-10-12 04:51:10,248][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000038784_39714816.pth -[2023-10-12 04:51:10,478][78123] Updated weights for policy 1, policy_version 40110 (0.0009) -[2023-10-12 04:51:10,849][78123] Updated weights for policy 1, policy_version 40120 (0.0008) -[2023-10-12 04:51:11,134][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000040128_41091072.pth... -[2023-10-12 04:51:11,176][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000038624_39550976.pth -[2023-10-12 04:51:11,947][78091] Updated weights for policy 0, policy_version 40290 (0.0008) -[2023-10-12 04:51:12,319][78091] Updated weights for policy 0, policy_version 40300 (0.0008) -[2023-10-12 04:51:12,685][78091] Updated weights for policy 0, policy_version 40310 (0.0009) -[2023-10-12 04:51:13,061][78091] Updated weights for policy 0, policy_version 40320 (0.0007) -[2023-10-12 04:51:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 82378752. Throughput: 0: 1591.2, 1: 1562.4. Samples: 20601512. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-12 04:51:15,201][77203] Avg episode reward: [(0, '46.180'), (1, '42.620')] -[2023-10-12 04:51:15,290][78123] Updated weights for policy 1, policy_version 40130 (0.0009) -[2023-10-12 04:51:15,656][78123] Updated weights for policy 1, policy_version 40140 (0.0009) -[2023-10-12 04:51:16,024][78123] Updated weights for policy 1, policy_version 40150 (0.0010) -[2023-10-12 04:51:16,400][78123] Updated weights for policy 1, policy_version 40160 (0.0009) -[2023-10-12 04:51:17,220][78091] Updated weights for policy 0, policy_version 40330 (0.0008) -[2023-10-12 04:51:17,590][78091] Updated weights for policy 0, policy_version 40340 (0.0007) -[2023-10-12 04:51:17,971][78091] Updated weights for policy 0, policy_version 40350 (0.0009) -[2023-10-12 04:51:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 82444288. Throughput: 0: 1579.5, 1: 1568.2. Samples: 20620514. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-12 04:51:20,201][77203] Avg episode reward: [(0, '45.190'), (1, '42.190')] -[2023-10-12 04:51:20,733][78123] Updated weights for policy 1, policy_version 40170 (0.0008) -[2023-10-12 04:51:21,096][78123] Updated weights for policy 1, policy_version 40180 (0.0008) -[2023-10-12 04:51:21,473][78123] Updated weights for policy 1, policy_version 40190 (0.0008) -[2023-10-12 04:51:22,411][78091] Updated weights for policy 0, policy_version 40360 (0.0009) -[2023-10-12 04:51:22,797][78091] Updated weights for policy 0, policy_version 40370 (0.0008) -[2023-10-12 04:51:23,180][78091] Updated weights for policy 0, policy_version 40380 (0.0009) -[2023-10-12 04:51:25,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 82509824. Throughput: 0: 1579.5, 1: 1590.3. Samples: 20640160. Policy #0 lag: (min: 11.0, avg: 18.6, max: 43.0) -[2023-10-12 04:51:25,202][77203] Avg episode reward: [(0, '43.320'), (1, '37.170')] -[2023-10-12 04:51:25,804][78123] Updated weights for policy 1, policy_version 40200 (0.0007) -[2023-10-12 04:51:26,173][78123] Updated weights for policy 1, policy_version 40210 (0.0007) -[2023-10-12 04:51:26,547][78123] Updated weights for policy 1, policy_version 40220 (0.0007) -[2023-10-12 04:51:27,604][78091] Updated weights for policy 0, policy_version 40390 (0.0008) -[2023-10-12 04:51:27,986][78091] Updated weights for policy 0, policy_version 40400 (0.0010) -[2023-10-12 04:51:28,365][78091] Updated weights for policy 0, policy_version 40410 (0.0007) -[2023-10-12 04:51:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 82575360. Throughput: 0: 1598.1, 1: 1571.0. Samples: 20649462. Policy #0 lag: (min: 11.0, avg: 18.6, max: 43.0) -[2023-10-12 04:51:30,201][77203] Avg episode reward: [(0, '50.000'), (1, '42.450')] -[2023-10-12 04:51:31,004][78123] Updated weights for policy 1, policy_version 40230 (0.0008) -[2023-10-12 04:51:31,368][78123] Updated weights for policy 1, policy_version 40240 (0.0009) -[2023-10-12 04:51:31,746][78123] Updated weights for policy 1, policy_version 40250 (0.0008) -[2023-10-12 04:51:32,643][78091] Updated weights for policy 0, policy_version 40420 (0.0007) -[2023-10-12 04:51:33,023][78091] Updated weights for policy 0, policy_version 40430 (0.0008) -[2023-10-12 04:51:33,394][78091] Updated weights for policy 0, policy_version 40440 (0.0009) -[2023-10-12 04:51:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 82640896. Throughput: 0: 1579.4, 1: 1571.6. Samples: 20668164. Policy #0 lag: (min: 11.0, avg: 18.6, max: 43.0) -[2023-10-12 04:51:35,202][77203] Avg episode reward: [(0, '45.440'), (1, '41.890')] -[2023-10-12 04:51:35,957][78123] Updated weights for policy 1, policy_version 40260 (0.0008) -[2023-10-12 04:51:36,327][78123] Updated weights for policy 1, policy_version 40270 (0.0008) -[2023-10-12 04:51:36,702][78123] Updated weights for policy 1, policy_version 40280 (0.0008) -[2023-10-12 04:51:37,745][78091] Updated weights for policy 0, policy_version 40450 (0.0008) -[2023-10-12 04:51:38,111][78091] Updated weights for policy 0, policy_version 40460 (0.0007) -[2023-10-12 04:51:38,478][78091] Updated weights for policy 0, policy_version 40470 (0.0008) -[2023-10-12 04:51:38,855][78091] Updated weights for policy 0, policy_version 40480 (0.0008) -[2023-10-12 04:51:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 82706432. Throughput: 0: 1576.7, 1: 1584.4. Samples: 20687492. Policy #0 lag: (min: 11.0, avg: 18.6, max: 43.0) -[2023-10-12 04:51:40,202][77203] Avg episode reward: [(0, '47.430'), (1, '38.800')] -[2023-10-12 04:51:41,132][78123] Updated weights for policy 1, policy_version 40290 (0.0008) -[2023-10-12 04:51:41,540][78123] Updated weights for policy 1, policy_version 40300 (0.0011) -[2023-10-12 04:51:41,900][78123] Updated weights for policy 1, policy_version 40310 (0.0010) -[2023-10-12 04:51:42,263][78123] Updated weights for policy 1, policy_version 40320 (0.0009) -[2023-10-12 04:51:43,198][78091] Updated weights for policy 0, policy_version 40490 (0.0007) -[2023-10-12 04:51:43,578][78091] Updated weights for policy 0, policy_version 40500 (0.0009) -[2023-10-12 04:51:43,939][78091] Updated weights for policy 0, policy_version 40510 (0.0008) -[2023-10-12 04:51:45,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 82771968. Throughput: 0: 1605.6, 1: 1571.4. Samples: 20697130. Policy #0 lag: (min: 11.0, avg: 18.6, max: 43.0) -[2023-10-12 04:51:45,202][77203] Avg episode reward: [(0, '43.830'), (1, '40.490')] -[2023-10-12 04:51:46,690][78123] Updated weights for policy 1, policy_version 40330 (0.0009) -[2023-10-12 04:51:47,060][78123] Updated weights for policy 1, policy_version 40340 (0.0008) -[2023-10-12 04:51:47,418][78123] Updated weights for policy 1, policy_version 40350 (0.0008) -[2023-10-12 04:51:48,204][78091] Updated weights for policy 0, policy_version 40520 (0.0008) -[2023-10-12 04:51:48,576][78091] Updated weights for policy 0, policy_version 40530 (0.0007) -[2023-10-12 04:51:48,947][78091] Updated weights for policy 0, policy_version 40540 (0.0007) -[2023-10-12 04:51:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 82837504. Throughput: 0: 1592.0, 1: 1571.6. Samples: 20715726. Policy #0 lag: (min: 11.0, avg: 18.6, max: 43.0) -[2023-10-12 04:51:50,201][77203] Avg episode reward: [(0, '47.240'), (1, '41.520')] -[2023-10-12 04:51:51,663][78123] Updated weights for policy 1, policy_version 40360 (0.0010) -[2023-10-12 04:51:52,034][78123] Updated weights for policy 1, policy_version 40370 (0.0009) -[2023-10-12 04:51:52,394][78123] Updated weights for policy 1, policy_version 40380 (0.0007) -[2023-10-12 04:51:53,210][78091] Updated weights for policy 0, policy_version 40550 (0.0007) -[2023-10-12 04:51:53,569][78091] Updated weights for policy 0, policy_version 40560 (0.0008) -[2023-10-12 04:51:53,940][78091] Updated weights for policy 0, policy_version 40570 (0.0009) -[2023-10-12 04:51:55,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 82903040. Throughput: 0: 1583.5, 1: 1577.8. Samples: 20735050. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-12 04:51:55,202][77203] Avg episode reward: [(0, '52.570'), (1, '36.040')] -[2023-10-12 04:51:56,758][78123] Updated weights for policy 1, policy_version 40390 (0.0008) -[2023-10-12 04:51:57,124][78123] Updated weights for policy 1, policy_version 40400 (0.0007) -[2023-10-12 04:51:57,493][78123] Updated weights for policy 1, policy_version 40410 (0.0009) -[2023-10-12 04:51:58,220][78091] Updated weights for policy 0, policy_version 40580 (0.0010) -[2023-10-12 04:51:58,595][78091] Updated weights for policy 0, policy_version 40590 (0.0010) -[2023-10-12 04:51:58,970][78091] Updated weights for policy 0, policy_version 40600 (0.0008) -[2023-10-12 04:52:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 82968576. Throughput: 0: 1604.1, 1: 1581.8. Samples: 20744878. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-12 04:52:00,202][77203] Avg episode reward: [(0, '49.410'), (1, '37.890')] -[2023-10-12 04:52:01,822][78123] Updated weights for policy 1, policy_version 40420 (0.0008) -[2023-10-12 04:52:02,176][78123] Updated weights for policy 1, policy_version 40430 (0.0009) -[2023-10-12 04:52:02,552][78123] Updated weights for policy 1, policy_version 40440 (0.0008) -[2023-10-12 04:52:03,294][78091] Updated weights for policy 0, policy_version 40610 (0.0009) -[2023-10-12 04:52:03,674][78091] Updated weights for policy 0, policy_version 40620 (0.0007) -[2023-10-12 04:52:04,045][78091] Updated weights for policy 0, policy_version 40630 (0.0008) -[2023-10-12 04:52:04,414][78091] Updated weights for policy 0, policy_version 40640 (0.0008) -[2023-10-12 04:52:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 83034112. Throughput: 0: 1604.6, 1: 1585.3. Samples: 20764058. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-12 04:52:05,202][77203] Avg episode reward: [(0, '42.040'), (1, '39.260')] -[2023-10-12 04:52:06,789][78123] Updated weights for policy 1, policy_version 40450 (0.0008) -[2023-10-12 04:52:07,153][78123] Updated weights for policy 1, policy_version 40460 (0.0010) -[2023-10-12 04:52:07,517][78123] Updated weights for policy 1, policy_version 40470 (0.0009) -[2023-10-12 04:52:07,881][78123] Updated weights for policy 1, policy_version 40480 (0.0009) -[2023-10-12 04:52:08,662][78091] Updated weights for policy 0, policy_version 40650 (0.0008) -[2023-10-12 04:52:09,040][78091] Updated weights for policy 0, policy_version 40660 (0.0008) -[2023-10-12 04:52:09,410][78091] Updated weights for policy 0, policy_version 40670 (0.0010) -[2023-10-12 04:52:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 83099648. Throughput: 0: 1589.7, 1: 1583.7. Samples: 20782964. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-12 04:52:10,201][77203] Avg episode reward: [(0, '39.800'), (1, '35.510')] -[2023-10-12 04:52:12,179][78123] Updated weights for policy 1, policy_version 40490 (0.0009) -[2023-10-12 04:52:12,557][78123] Updated weights for policy 1, policy_version 40500 (0.0011) -[2023-10-12 04:52:12,925][78123] Updated weights for policy 1, policy_version 40510 (0.0009) -[2023-10-12 04:52:13,723][78091] Updated weights for policy 0, policy_version 40680 (0.0007) -[2023-10-12 04:52:14,106][78091] Updated weights for policy 0, policy_version 40690 (0.0009) -[2023-10-12 04:52:14,475][78091] Updated weights for policy 0, policy_version 40700 (0.0009) -[2023-10-12 04:52:15,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 83165184. Throughput: 0: 1602.7, 1: 1591.0. Samples: 20793176. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-12 04:52:15,201][77203] Avg episode reward: [(0, '48.230'), (1, '39.630')] -[2023-10-12 04:52:17,294][78123] Updated weights for policy 1, policy_version 40520 (0.0009) -[2023-10-12 04:52:17,656][78123] Updated weights for policy 1, policy_version 40530 (0.0007) -[2023-10-12 04:52:18,023][78123] Updated weights for policy 1, policy_version 40540 (0.0009) -[2023-10-12 04:52:18,807][78091] Updated weights for policy 0, policy_version 40710 (0.0009) -[2023-10-12 04:52:19,174][78091] Updated weights for policy 0, policy_version 40720 (0.0008) -[2023-10-12 04:52:19,542][78091] Updated weights for policy 0, policy_version 40730 (0.0008) -[2023-10-12 04:52:20,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 83230720. Throughput: 0: 1616.3, 1: 1582.7. Samples: 20812118. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-12 04:52:20,202][77203] Avg episode reward: [(0, '46.540'), (1, '41.140')] -[2023-10-12 04:52:22,373][78123] Updated weights for policy 1, policy_version 40550 (0.0009) -[2023-10-12 04:52:22,740][78123] Updated weights for policy 1, policy_version 40560 (0.0008) -[2023-10-12 04:52:23,114][78123] Updated weights for policy 1, policy_version 40570 (0.0008) -[2023-10-12 04:52:23,961][78091] Updated weights for policy 0, policy_version 40740 (0.0008) -[2023-10-12 04:52:24,336][78091] Updated weights for policy 0, policy_version 40750 (0.0009) -[2023-10-12 04:52:24,695][78091] Updated weights for policy 0, policy_version 40760 (0.0008) -[2023-10-12 04:52:25,201][77203] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 83296256. Throughput: 0: 1601.9, 1: 1584.0. Samples: 20830856. Policy #0 lag: (min: 31.0, avg: 32.1, max: 55.0) -[2023-10-12 04:52:25,202][77203] Avg episode reward: [(0, '45.980'), (1, '41.070')] -[2023-10-12 04:52:27,555][78123] Updated weights for policy 1, policy_version 40580 (0.0009) -[2023-10-12 04:52:27,957][78123] Updated weights for policy 1, policy_version 40590 (0.0008) -[2023-10-12 04:52:28,321][78123] Updated weights for policy 1, policy_version 40600 (0.0008) -[2023-10-12 04:52:29,047][78091] Updated weights for policy 0, policy_version 40770 (0.0007) -[2023-10-12 04:52:29,420][78091] Updated weights for policy 0, policy_version 40780 (0.0007) -[2023-10-12 04:52:29,793][78091] Updated weights for policy 0, policy_version 40790 (0.0009) -[2023-10-12 04:52:30,159][78091] Updated weights for policy 0, policy_version 40800 (0.0009) -[2023-10-12 04:52:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 83361792. Throughput: 0: 1594.2, 1: 1605.8. Samples: 20841128. Policy #0 lag: (min: 31.0, avg: 32.1, max: 55.0) -[2023-10-12 04:52:30,201][77203] Avg episode reward: [(0, '45.500'), (1, '38.370')] -[2023-10-12 04:52:32,620][78123] Updated weights for policy 1, policy_version 40610 (0.0008) -[2023-10-12 04:52:32,988][78123] Updated weights for policy 1, policy_version 40620 (0.0009) -[2023-10-12 04:52:33,361][78123] Updated weights for policy 1, policy_version 40630 (0.0009) -[2023-10-12 04:52:33,730][78123] Updated weights for policy 1, policy_version 40640 (0.0009) -[2023-10-12 04:52:34,368][78091] Updated weights for policy 0, policy_version 40810 (0.0010) -[2023-10-12 04:52:34,739][78091] Updated weights for policy 0, policy_version 40820 (0.0009) -[2023-10-12 04:52:35,109][78091] Updated weights for policy 0, policy_version 40830 (0.0008) -[2023-10-12 04:52:35,201][77203] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 83427328. Throughput: 0: 1613.4, 1: 1590.4. Samples: 20859900. Policy #0 lag: (min: 31.0, avg: 32.1, max: 55.0) -[2023-10-12 04:52:35,201][77203] Avg episode reward: [(0, '44.380'), (1, '40.980')] -[2023-10-12 04:52:38,040][78123] Updated weights for policy 1, policy_version 40650 (0.0008) -[2023-10-12 04:52:38,402][78123] Updated weights for policy 1, policy_version 40660 (0.0007) -[2023-10-12 04:52:38,775][78123] Updated weights for policy 1, policy_version 40670 (0.0008) -[2023-10-12 04:52:39,398][78091] Updated weights for policy 0, policy_version 40840 (0.0009) -[2023-10-12 04:52:39,765][78091] Updated weights for policy 0, policy_version 40850 (0.0009) -[2023-10-12 04:52:40,140][78091] Updated weights for policy 0, policy_version 40860 (0.0008) -[2023-10-12 04:52:40,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 83460096. Throughput: 0: 1609.6, 1: 1584.4. Samples: 20878780. Policy #0 lag: (min: 31.0, avg: 32.1, max: 55.0) -[2023-10-12 04:52:40,201][77203] Avg episode reward: [(0, '50.800'), (1, '42.600')] -[2023-10-12 04:52:43,107][78123] Updated weights for policy 1, policy_version 40680 (0.0007) -[2023-10-12 04:52:43,468][78123] Updated weights for policy 1, policy_version 40690 (0.0008) -[2023-10-12 04:52:43,836][78123] Updated weights for policy 1, policy_version 40700 (0.0010) -[2023-10-12 04:52:44,291][78091] Updated weights for policy 0, policy_version 40870 (0.0008) -[2023-10-12 04:52:44,655][78091] Updated weights for policy 0, policy_version 40880 (0.0008) -[2023-10-12 04:52:45,021][78091] Updated weights for policy 0, policy_version 40890 (0.0007) -[2023-10-12 04:52:45,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 83525632. Throughput: 0: 1600.4, 1: 1610.1. Samples: 20889354. Policy #0 lag: (min: 31.0, avg: 32.1, max: 55.0) -[2023-10-12 04:52:45,201][77203] Avg episode reward: [(0, '45.520'), (1, '39.680')] -[2023-10-12 04:52:48,189][78123] Updated weights for policy 1, policy_version 40710 (0.0010) -[2023-10-12 04:52:48,557][78123] Updated weights for policy 1, policy_version 40720 (0.0008) -[2023-10-12 04:52:48,935][78123] Updated weights for policy 1, policy_version 40730 (0.0009) -[2023-10-12 04:52:49,335][78091] Updated weights for policy 0, policy_version 40900 (0.0007) -[2023-10-12 04:52:49,713][78091] Updated weights for policy 0, policy_version 40910 (0.0009) -[2023-10-12 04:52:50,086][78091] Updated weights for policy 0, policy_version 40920 (0.0009) -[2023-10-12 04:52:50,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 83591168. Throughput: 0: 1615.2, 1: 1590.8. Samples: 20908328. Policy #0 lag: (min: 31.0, avg: 32.1, max: 55.0) -[2023-10-12 04:52:50,202][77203] Avg episode reward: [(0, '48.280'), (1, '42.940')] -[2023-10-12 04:52:53,314][78123] Updated weights for policy 1, policy_version 40740 (0.0008) -[2023-10-12 04:52:53,685][78123] Updated weights for policy 1, policy_version 40750 (0.0008) -[2023-10-12 04:52:54,046][78123] Updated weights for policy 1, policy_version 40760 (0.0010) -[2023-10-12 04:52:54,337][78091] Updated weights for policy 0, policy_version 40930 (0.0009) -[2023-10-12 04:52:54,704][78091] Updated weights for policy 0, policy_version 40940 (0.0010) -[2023-10-12 04:52:55,073][78091] Updated weights for policy 0, policy_version 40950 (0.0010) -[2023-10-12 04:52:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 83656704. Throughput: 0: 1616.5, 1: 1580.8. Samples: 20926842. Policy #0 lag: (min: 31.0, avg: 32.1, max: 55.0) -[2023-10-12 04:52:55,201][77203] Avg episode reward: [(0, '44.680'), (1, '39.610')] -[2023-10-12 04:52:55,441][78091] Updated weights for policy 0, policy_version 40960 (0.0011) -[2023-10-12 04:52:58,405][78123] Updated weights for policy 1, policy_version 40770 (0.0008) -[2023-10-12 04:52:58,774][78123] Updated weights for policy 1, policy_version 40780 (0.0007) -[2023-10-12 04:52:59,133][78123] Updated weights for policy 1, policy_version 40790 (0.0009) -[2023-10-12 04:52:59,509][78123] Updated weights for policy 1, policy_version 40800 (0.0009) -[2023-10-12 04:52:59,761][78091] Updated weights for policy 0, policy_version 40970 (0.0009) -[2023-10-12 04:53:00,131][78091] Updated weights for policy 0, policy_version 40980 (0.0009) -[2023-10-12 04:53:00,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 83722240. Throughput: 0: 1598.5, 1: 1599.0. Samples: 20937062. Policy #0 lag: (min: 18.0, avg: 30.2, max: 50.0) -[2023-10-12 04:53:00,203][77203] Avg episode reward: [(0, '44.740'), (1, '40.090')] -[2023-10-12 04:53:00,499][78091] Updated weights for policy 0, policy_version 40990 (0.0008) -[2023-10-12 04:53:03,964][78123] Updated weights for policy 1, policy_version 40810 (0.0008) -[2023-10-12 04:53:04,332][78123] Updated weights for policy 1, policy_version 40820 (0.0009) -[2023-10-12 04:53:04,695][78123] Updated weights for policy 1, policy_version 40830 (0.0009) -[2023-10-12 04:53:04,861][78091] Updated weights for policy 0, policy_version 41000 (0.0010) -[2023-10-12 04:53:05,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 83787776. Throughput: 0: 1601.1, 1: 1603.1. Samples: 20956312. Policy #0 lag: (min: 18.0, avg: 30.2, max: 50.0) -[2023-10-12 04:53:05,202][77203] Avg episode reward: [(0, '44.340'), (1, '43.490')] -[2023-10-12 04:53:05,237][78091] Updated weights for policy 0, policy_version 41010 (0.0009) -[2023-10-12 04:53:05,618][78091] Updated weights for policy 0, policy_version 41020 (0.0008) -[2023-10-12 04:53:09,119][78123] Updated weights for policy 1, policy_version 40840 (0.0008) -[2023-10-12 04:53:09,482][78123] Updated weights for policy 1, policy_version 40850 (0.0010) -[2023-10-12 04:53:09,758][78091] Updated weights for policy 0, policy_version 41030 (0.0008) -[2023-10-12 04:53:09,854][78123] Updated weights for policy 1, policy_version 40860 (0.0008) -[2023-10-12 04:53:10,119][78091] Updated weights for policy 0, policy_version 41040 (0.0008) -[2023-10-12 04:53:10,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 83853312. Throughput: 0: 1613.6, 1: 1586.4. Samples: 20974852. Policy #0 lag: (min: 18.0, avg: 30.2, max: 50.0) -[2023-10-12 04:53:10,202][77203] Avg episode reward: [(0, '41.890'), (1, '40.730')] -[2023-10-12 04:53:10,212][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000040864_41844736.pth... -[2023-10-12 04:53:10,246][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000039360_40304640.pth -[2023-10-12 04:53:10,498][78091] Updated weights for policy 0, policy_version 41050 (0.0008) -[2023-10-12 04:53:10,710][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000041056_42041344.pth... -[2023-10-12 04:53:10,739][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000039552_40501248.pth -[2023-10-12 04:53:14,248][78123] Updated weights for policy 1, policy_version 40870 (0.0009) -[2023-10-12 04:53:14,615][78123] Updated weights for policy 1, policy_version 40880 (0.0009) -[2023-10-12 04:53:14,870][78091] Updated weights for policy 0, policy_version 41060 (0.0009) -[2023-10-12 04:53:14,986][78123] Updated weights for policy 1, policy_version 40890 (0.0009) -[2023-10-12 04:53:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 83918848. Throughput: 0: 1599.9, 1: 1588.3. Samples: 20984596. Policy #0 lag: (min: 18.0, avg: 30.2, max: 50.0) -[2023-10-12 04:53:15,202][77203] Avg episode reward: [(0, '43.650'), (1, '40.150')] -[2023-10-12 04:53:15,238][78091] Updated weights for policy 0, policy_version 41070 (0.0007) -[2023-10-12 04:53:15,613][78091] Updated weights for policy 0, policy_version 41080 (0.0009) -[2023-10-12 04:53:19,367][78123] Updated weights for policy 1, policy_version 40900 (0.0010) -[2023-10-12 04:53:19,732][78123] Updated weights for policy 1, policy_version 40910 (0.0011) -[2023-10-12 04:53:19,912][78091] Updated weights for policy 0, policy_version 41090 (0.0010) -[2023-10-12 04:53:20,098][78123] Updated weights for policy 1, policy_version 40920 (0.0008) -[2023-10-12 04:53:20,201][77203] Fps is (10 sec: 9830.6, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 83951616. Throughput: 0: 1597.7, 1: 1604.2. Samples: 21003984. Policy #0 lag: (min: 18.0, avg: 30.2, max: 50.0) -[2023-10-12 04:53:20,201][77203] Avg episode reward: [(0, '51.040'), (1, '44.800')] -[2023-10-12 04:53:20,285][78091] Updated weights for policy 0, policy_version 41100 (0.0009) -[2023-10-12 04:53:20,650][78091] Updated weights for policy 0, policy_version 41110 (0.0008) -[2023-10-12 04:53:21,028][78091] Updated weights for policy 0, policy_version 41120 (0.0010) -[2023-10-12 04:53:24,114][78123] Updated weights for policy 1, policy_version 40930 (0.0008) -[2023-10-12 04:53:24,480][78123] Updated weights for policy 1, policy_version 40940 (0.0010) -[2023-10-12 04:53:24,838][78123] Updated weights for policy 1, policy_version 40950 (0.0008) -[2023-10-12 04:53:25,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 84017152. Throughput: 0: 1610.6, 1: 1591.2. Samples: 21022862. Policy #0 lag: (min: 18.0, avg: 30.2, max: 50.0) -[2023-10-12 04:53:25,202][77203] Avg episode reward: [(0, '51.000'), (1, '42.150')] -[2023-10-12 04:53:25,208][78123] Updated weights for policy 1, policy_version 40960 (0.0009) -[2023-10-12 04:53:25,390][78091] Updated weights for policy 0, policy_version 41130 (0.0008) -[2023-10-12 04:53:25,759][78091] Updated weights for policy 0, policy_version 41140 (0.0008) -[2023-10-12 04:53:26,121][78091] Updated weights for policy 0, policy_version 41150 (0.0009) -[2023-10-12 04:53:29,581][78123] Updated weights for policy 1, policy_version 40970 (0.0009) -[2023-10-12 04:53:29,942][78123] Updated weights for policy 1, policy_version 40980 (0.0008) -[2023-10-12 04:53:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 84082688. Throughput: 0: 1591.9, 1: 1578.5. Samples: 21032024. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-12 04:53:30,202][77203] Avg episode reward: [(0, '49.320'), (1, '41.890')] -[2023-10-12 04:53:30,313][78123] Updated weights for policy 1, policy_version 40990 (0.0009) -[2023-10-12 04:53:30,385][78091] Updated weights for policy 0, policy_version 41160 (0.0008) -[2023-10-12 04:53:30,763][78091] Updated weights for policy 0, policy_version 41170 (0.0011) -[2023-10-12 04:53:31,128][78091] Updated weights for policy 0, policy_version 41180 (0.0009) -[2023-10-12 04:53:34,529][78123] Updated weights for policy 1, policy_version 41000 (0.0009) -[2023-10-12 04:53:34,894][78123] Updated weights for policy 1, policy_version 41010 (0.0010) -[2023-10-12 04:53:35,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 84148224. Throughput: 0: 1589.3, 1: 1595.9. Samples: 21051662. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-12 04:53:35,201][77203] Avg episode reward: [(0, '44.430'), (1, '39.790')] -[2023-10-12 04:53:35,257][78123] Updated weights for policy 1, policy_version 41020 (0.0009) -[2023-10-12 04:53:35,390][78091] Updated weights for policy 0, policy_version 41190 (0.0007) -[2023-10-12 04:53:35,764][78091] Updated weights for policy 0, policy_version 41200 (0.0007) -[2023-10-12 04:53:36,128][78091] Updated weights for policy 0, policy_version 41210 (0.0008) -[2023-10-12 04:53:39,819][78123] Updated weights for policy 1, policy_version 41030 (0.0009) -[2023-10-12 04:53:40,180][78123] Updated weights for policy 1, policy_version 41040 (0.0009) -[2023-10-12 04:53:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 84213760. Throughput: 0: 1602.6, 1: 1597.9. Samples: 21070866. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-12 04:53:40,201][77203] Avg episode reward: [(0, '49.780'), (1, '45.590')] -[2023-10-12 04:53:40,467][78091] Updated weights for policy 0, policy_version 41220 (0.0008) -[2023-10-12 04:53:40,552][78123] Updated weights for policy 1, policy_version 41050 (0.0008) -[2023-10-12 04:53:40,842][78091] Updated weights for policy 0, policy_version 41230 (0.0009) -[2023-10-12 04:53:41,209][78091] Updated weights for policy 0, policy_version 41240 (0.0009) -[2023-10-12 04:53:45,154][78123] Updated weights for policy 1, policy_version 41060 (0.0009) -[2023-10-12 04:53:45,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 84279296. Throughput: 0: 1595.6, 1: 1573.5. Samples: 21079674. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-12 04:53:45,202][77203] Avg episode reward: [(0, '42.660'), (1, '41.430')] -[2023-10-12 04:53:45,431][78091] Updated weights for policy 0, policy_version 41250 (0.0009) -[2023-10-12 04:53:45,523][78123] Updated weights for policy 1, policy_version 41070 (0.0009) -[2023-10-12 04:53:45,798][78091] Updated weights for policy 0, policy_version 41260 (0.0007) -[2023-10-12 04:53:45,893][78123] Updated weights for policy 1, policy_version 41080 (0.0007) -[2023-10-12 04:53:46,175][78091] Updated weights for policy 0, policy_version 41270 (0.0008) -[2023-10-12 04:53:46,536][78091] Updated weights for policy 0, policy_version 41280 (0.0009) -[2023-10-12 04:53:50,130][78123] Updated weights for policy 1, policy_version 41090 (0.0008) -[2023-10-12 04:53:50,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 84344832. Throughput: 0: 1595.7, 1: 1574.9. Samples: 21098990. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-12 04:53:50,202][77203] Avg episode reward: [(0, '37.070'), (1, '38.540')] -[2023-10-12 04:53:50,496][78123] Updated weights for policy 1, policy_version 41100 (0.0009) -[2023-10-12 04:53:50,861][78123] Updated weights for policy 1, policy_version 41110 (0.0008) -[2023-10-12 04:53:50,985][78091] Updated weights for policy 0, policy_version 41290 (0.0008) -[2023-10-12 04:53:51,229][78123] Updated weights for policy 1, policy_version 41120 (0.0009) -[2023-10-12 04:53:51,357][78091] Updated weights for policy 0, policy_version 41300 (0.0008) -[2023-10-12 04:53:51,725][78091] Updated weights for policy 0, policy_version 41310 (0.0007) -[2023-10-12 04:53:55,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 84410368. Throughput: 0: 1598.5, 1: 1592.0. Samples: 21118424. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-12 04:53:55,202][77203] Avg episode reward: [(0, '39.620'), (1, '46.170')] -[2023-10-12 04:53:55,594][78123] Updated weights for policy 1, policy_version 41130 (0.0009) -[2023-10-12 04:53:55,957][78123] Updated weights for policy 1, policy_version 41140 (0.0009) -[2023-10-12 04:53:56,039][78091] Updated weights for policy 0, policy_version 41320 (0.0009) -[2023-10-12 04:53:56,316][78123] Updated weights for policy 1, policy_version 41150 (0.0009) -[2023-10-12 04:53:56,398][78091] Updated weights for policy 0, policy_version 41330 (0.0009) -[2023-10-12 04:53:56,769][78091] Updated weights for policy 0, policy_version 41340 (0.0010) -[2023-10-12 04:54:00,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 84475904. Throughput: 0: 1592.1, 1: 1571.9. Samples: 21126978. Policy #0 lag: (min: 11.0, avg: 13.9, max: 43.0) -[2023-10-12 04:54:00,201][77203] Avg episode reward: [(0, '47.020'), (1, '41.590')] -[2023-10-12 04:54:00,814][78123] Updated weights for policy 1, policy_version 41160 (0.0010) -[2023-10-12 04:54:01,185][78123] Updated weights for policy 1, policy_version 41170 (0.0008) -[2023-10-12 04:54:01,222][78091] Updated weights for policy 0, policy_version 41350 (0.0009) -[2023-10-12 04:54:01,550][78123] Updated weights for policy 1, policy_version 41180 (0.0008) -[2023-10-12 04:54:01,590][78091] Updated weights for policy 0, policy_version 41360 (0.0008) -[2023-10-12 04:54:01,960][78091] Updated weights for policy 0, policy_version 41370 (0.0008) -[2023-10-12 04:54:05,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 84541440. Throughput: 0: 1589.4, 1: 1570.0. Samples: 21146158. Policy #0 lag: (min: 11.0, avg: 13.9, max: 43.0) -[2023-10-12 04:54:05,201][77203] Avg episode reward: [(0, '50.250'), (1, '41.580')] -[2023-10-12 04:54:05,876][78123] Updated weights for policy 1, policy_version 41190 (0.0009) -[2023-10-12 04:54:06,210][78091] Updated weights for policy 0, policy_version 41380 (0.0009) -[2023-10-12 04:54:06,246][78123] Updated weights for policy 1, policy_version 41200 (0.0009) -[2023-10-12 04:54:06,592][78091] Updated weights for policy 0, policy_version 41390 (0.0010) -[2023-10-12 04:54:06,616][78123] Updated weights for policy 1, policy_version 41210 (0.0008) -[2023-10-12 04:54:06,965][78091] Updated weights for policy 0, policy_version 41400 (0.0007) -[2023-10-12 04:54:10,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 84606976. Throughput: 0: 1588.6, 1: 1587.8. Samples: 21165800. Policy #0 lag: (min: 11.0, avg: 13.9, max: 43.0) -[2023-10-12 04:54:10,202][77203] Avg episode reward: [(0, '45.420'), (1, '46.980')] -[2023-10-12 04:54:11,011][78123] Updated weights for policy 1, policy_version 41220 (0.0007) -[2023-10-12 04:54:11,199][78091] Updated weights for policy 0, policy_version 41410 (0.0007) -[2023-10-12 04:54:11,381][78123] Updated weights for policy 1, policy_version 41230 (0.0010) -[2023-10-12 04:54:11,567][78091] Updated weights for policy 0, policy_version 41420 (0.0010) -[2023-10-12 04:54:11,741][78123] Updated weights for policy 1, policy_version 41240 (0.0007) -[2023-10-12 04:54:11,936][78091] Updated weights for policy 0, policy_version 41430 (0.0007) -[2023-10-12 04:54:12,303][78091] Updated weights for policy 0, policy_version 41440 (0.0008) -[2023-10-12 04:54:15,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 84672512. Throughput: 0: 1587.7, 1: 1571.9. Samples: 21174210. Policy #0 lag: (min: 11.0, avg: 13.9, max: 43.0) -[2023-10-12 04:54:15,202][77203] Avg episode reward: [(0, '44.130'), (1, '45.550')] -[2023-10-12 04:54:15,974][78123] Updated weights for policy 1, policy_version 41250 (0.0007) -[2023-10-12 04:54:16,338][78123] Updated weights for policy 1, policy_version 41260 (0.0009) -[2023-10-12 04:54:16,670][78091] Updated weights for policy 0, policy_version 41450 (0.0010) -[2023-10-12 04:54:16,705][78123] Updated weights for policy 1, policy_version 41270 (0.0007) -[2023-10-12 04:54:17,053][78091] Updated weights for policy 0, policy_version 41460 (0.0010) -[2023-10-12 04:54:17,067][78123] Updated weights for policy 1, policy_version 41280 (0.0008) -[2023-10-12 04:54:17,414][78091] Updated weights for policy 0, policy_version 41470 (0.0010) -[2023-10-12 04:54:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.1, 300 sec: 12662.9). Total num frames: 84738048. Throughput: 0: 1583.8, 1: 1575.3. Samples: 21193822. Policy #0 lag: (min: 11.0, avg: 13.9, max: 43.0) -[2023-10-12 04:54:20,202][77203] Avg episode reward: [(0, '43.460'), (1, '41.340')] -[2023-10-12 04:54:21,572][78123] Updated weights for policy 1, policy_version 41290 (0.0007) -[2023-10-12 04:54:21,643][78091] Updated weights for policy 0, policy_version 41480 (0.0008) -[2023-10-12 04:54:21,939][78123] Updated weights for policy 1, policy_version 41300 (0.0009) -[2023-10-12 04:54:22,016][78091] Updated weights for policy 0, policy_version 41490 (0.0008) -[2023-10-12 04:54:22,304][78123] Updated weights for policy 1, policy_version 41310 (0.0008) -[2023-10-12 04:54:22,381][78091] Updated weights for policy 0, policy_version 41500 (0.0009) -[2023-10-12 04:54:25,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 84803584. Throughput: 0: 1588.9, 1: 1576.8. Samples: 21213324. Policy #0 lag: (min: 11.0, avg: 13.9, max: 43.0) -[2023-10-12 04:54:25,202][77203] Avg episode reward: [(0, '44.480'), (1, '39.500')] -[2023-10-12 04:54:26,610][78123] Updated weights for policy 1, policy_version 41320 (0.0010) -[2023-10-12 04:54:26,614][78091] Updated weights for policy 0, policy_version 41510 (0.0008) -[2023-10-12 04:54:26,980][78123] Updated weights for policy 1, policy_version 41330 (0.0009) -[2023-10-12 04:54:26,992][78091] Updated weights for policy 0, policy_version 41520 (0.0007) -[2023-10-12 04:54:27,348][78123] Updated weights for policy 1, policy_version 41340 (0.0008) -[2023-10-12 04:54:27,373][78091] Updated weights for policy 0, policy_version 41530 (0.0008) -[2023-10-12 04:54:30,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 84869120. Throughput: 0: 1585.5, 1: 1575.3. Samples: 21221912. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:54:30,201][77203] Avg episode reward: [(0, '44.050'), (1, '47.920')] -[2023-10-12 04:54:31,475][78123] Updated weights for policy 1, policy_version 41350 (0.0009) -[2023-10-12 04:54:31,844][78123] Updated weights for policy 1, policy_version 41360 (0.0008) -[2023-10-12 04:54:31,922][78091] Updated weights for policy 0, policy_version 41540 (0.0008) -[2023-10-12 04:54:32,204][78123] Updated weights for policy 1, policy_version 41370 (0.0009) -[2023-10-12 04:54:32,305][78091] Updated weights for policy 0, policy_version 41550 (0.0007) -[2023-10-12 04:54:32,688][78091] Updated weights for policy 0, policy_version 41560 (0.0010) -[2023-10-12 04:54:35,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 84934656. Throughput: 0: 1584.0, 1: 1579.5. Samples: 21241346. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:54:35,202][77203] Avg episode reward: [(0, '50.980'), (1, '40.320')] -[2023-10-12 04:54:36,813][78123] Updated weights for policy 1, policy_version 41380 (0.0008) -[2023-10-12 04:54:36,958][78091] Updated weights for policy 0, policy_version 41570 (0.0008) -[2023-10-12 04:54:37,179][78123] Updated weights for policy 1, policy_version 41390 (0.0007) -[2023-10-12 04:54:37,317][78091] Updated weights for policy 0, policy_version 41580 (0.0007) -[2023-10-12 04:54:37,538][78123] Updated weights for policy 1, policy_version 41400 (0.0007) -[2023-10-12 04:54:37,691][78091] Updated weights for policy 0, policy_version 41590 (0.0008) -[2023-10-12 04:54:38,061][78091] Updated weights for policy 0, policy_version 41600 (0.0010) -[2023-10-12 04:54:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 85000192. Throughput: 0: 1584.4, 1: 1577.7. Samples: 21260716. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:54:40,202][77203] Avg episode reward: [(0, '48.260'), (1, '35.270')] -[2023-10-12 04:54:41,826][78123] Updated weights for policy 1, policy_version 41410 (0.0009) -[2023-10-12 04:54:42,177][78123] Updated weights for policy 1, policy_version 41420 (0.0009) -[2023-10-12 04:54:42,511][78091] Updated weights for policy 0, policy_version 41610 (0.0009) -[2023-10-12 04:54:42,538][78123] Updated weights for policy 1, policy_version 41430 (0.0009) -[2023-10-12 04:54:42,878][78091] Updated weights for policy 0, policy_version 41620 (0.0009) -[2023-10-12 04:54:42,910][78123] Updated weights for policy 1, policy_version 41440 (0.0009) -[2023-10-12 04:54:43,256][78091] Updated weights for policy 0, policy_version 41630 (0.0008) -[2023-10-12 04:54:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 85065728. Throughput: 0: 1596.5, 1: 1583.1. Samples: 21270058. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:54:45,202][77203] Avg episode reward: [(0, '49.260'), (1, '49.330')] -[2023-10-12 04:54:45,203][77950] Saving new best policy, reward=49.330! -[2023-10-12 04:54:47,321][78123] Updated weights for policy 1, policy_version 41450 (0.0009) -[2023-10-12 04:54:47,382][78091] Updated weights for policy 0, policy_version 41640 (0.0008) -[2023-10-12 04:54:47,686][78123] Updated weights for policy 1, policy_version 41460 (0.0009) -[2023-10-12 04:54:47,751][78091] Updated weights for policy 0, policy_version 41650 (0.0010) -[2023-10-12 04:54:48,048][78123] Updated weights for policy 1, policy_version 41470 (0.0008) -[2023-10-12 04:54:48,122][78091] Updated weights for policy 0, policy_version 41660 (0.0008) -[2023-10-12 04:54:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 85131264. Throughput: 0: 1590.1, 1: 1580.8. Samples: 21288848. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:54:50,202][77203] Avg episode reward: [(0, '49.720'), (1, '42.500')] -[2023-10-12 04:54:52,553][78123] Updated weights for policy 1, policy_version 41480 (0.0009) -[2023-10-12 04:54:52,651][78091] Updated weights for policy 0, policy_version 41670 (0.0009) -[2023-10-12 04:54:52,922][78123] Updated weights for policy 1, policy_version 41490 (0.0010) -[2023-10-12 04:54:53,020][78091] Updated weights for policy 0, policy_version 41680 (0.0009) -[2023-10-12 04:54:53,286][78123] Updated weights for policy 1, policy_version 41500 (0.0009) -[2023-10-12 04:54:53,378][78091] Updated weights for policy 0, policy_version 41690 (0.0010) -[2023-10-12 04:54:55,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 85196800. Throughput: 0: 1590.4, 1: 1582.3. Samples: 21308574. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:54:55,202][77203] Avg episode reward: [(0, '46.620'), (1, '38.880')] -[2023-10-12 04:54:57,483][78123] Updated weights for policy 1, policy_version 41510 (0.0011) -[2023-10-12 04:54:57,616][78091] Updated weights for policy 0, policy_version 41700 (0.0009) -[2023-10-12 04:54:57,847][78123] Updated weights for policy 1, policy_version 41520 (0.0010) -[2023-10-12 04:54:57,989][78091] Updated weights for policy 0, policy_version 41710 (0.0010) -[2023-10-12 04:54:58,217][78123] Updated weights for policy 1, policy_version 41530 (0.0010) -[2023-10-12 04:54:58,364][78091] Updated weights for policy 0, policy_version 41720 (0.0008) -[2023-10-12 04:55:00,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 85262336. Throughput: 0: 1613.1, 1: 1599.1. Samples: 21318756. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-12 04:55:00,202][77203] Avg episode reward: [(0, '42.450'), (1, '46.560')] -[2023-10-12 04:55:02,454][78123] Updated weights for policy 1, policy_version 41540 (0.0009) -[2023-10-12 04:55:02,636][78091] Updated weights for policy 0, policy_version 41730 (0.0008) -[2023-10-12 04:55:02,817][78123] Updated weights for policy 1, policy_version 41550 (0.0009) -[2023-10-12 04:55:02,998][78091] Updated weights for policy 0, policy_version 41740 (0.0008) -[2023-10-12 04:55:03,181][78123] Updated weights for policy 1, policy_version 41560 (0.0009) -[2023-10-12 04:55:03,369][78091] Updated weights for policy 0, policy_version 41750 (0.0009) -[2023-10-12 04:55:03,745][78091] Updated weights for policy 0, policy_version 41760 (0.0009) -[2023-10-12 04:55:05,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 85327872. Throughput: 0: 1595.2, 1: 1580.8. Samples: 21336740. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-12 04:55:05,201][77203] Avg episode reward: [(0, '44.970'), (1, '41.630')] -[2023-10-12 04:55:07,419][78123] Updated weights for policy 1, policy_version 41570 (0.0008) -[2023-10-12 04:55:07,791][78123] Updated weights for policy 1, policy_version 41580 (0.0010) -[2023-10-12 04:55:07,956][78091] Updated weights for policy 0, policy_version 41770 (0.0009) -[2023-10-12 04:55:08,146][78123] Updated weights for policy 1, policy_version 41590 (0.0010) -[2023-10-12 04:55:08,320][78091] Updated weights for policy 0, policy_version 41780 (0.0009) -[2023-10-12 04:55:08,514][78123] Updated weights for policy 1, policy_version 41600 (0.0008) -[2023-10-12 04:55:08,694][78091] Updated weights for policy 0, policy_version 41790 (0.0008) -[2023-10-12 04:55:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 85393408. Throughput: 0: 1589.7, 1: 1588.0. Samples: 21356318. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-12 04:55:10,201][77203] Avg episode reward: [(0, '49.000'), (1, '38.140')] -[2023-10-12 04:55:10,208][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000041600_42598400.pth... -[2023-10-12 04:55:10,208][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000041792_42795008.pth... -[2023-10-12 04:55:10,248][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000040128_41091072.pth -[2023-10-12 04:55:10,250][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000040288_41254912.pth -[2023-10-12 04:55:12,761][78123] Updated weights for policy 1, policy_version 41610 (0.0009) -[2023-10-12 04:55:13,132][78123] Updated weights for policy 1, policy_version 41620 (0.0009) -[2023-10-12 04:55:13,223][78091] Updated weights for policy 0, policy_version 41800 (0.0008) -[2023-10-12 04:55:13,500][78123] Updated weights for policy 1, policy_version 41630 (0.0009) -[2023-10-12 04:55:13,598][78091] Updated weights for policy 0, policy_version 41810 (0.0007) -[2023-10-12 04:55:13,967][78091] Updated weights for policy 0, policy_version 41820 (0.0009) -[2023-10-12 04:55:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 85458944. Throughput: 0: 1614.4, 1: 1604.6. Samples: 21366764. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-12 04:55:15,202][77203] Avg episode reward: [(0, '43.450'), (1, '42.310')] -[2023-10-12 04:55:17,890][78123] Updated weights for policy 1, policy_version 41640 (0.0010) -[2023-10-12 04:55:18,261][78123] Updated weights for policy 1, policy_version 41650 (0.0008) -[2023-10-12 04:55:18,285][78091] Updated weights for policy 0, policy_version 41830 (0.0009) -[2023-10-12 04:55:18,625][78123] Updated weights for policy 1, policy_version 41660 (0.0009) -[2023-10-12 04:55:18,664][78091] Updated weights for policy 0, policy_version 41840 (0.0009) -[2023-10-12 04:55:19,040][78091] Updated weights for policy 0, policy_version 41850 (0.0008) -[2023-10-12 04:55:20,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 85524480. Throughput: 0: 1599.8, 1: 1584.1. Samples: 21384622. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-12 04:55:20,202][77203] Avg episode reward: [(0, '42.110'), (1, '38.930')] -[2023-10-12 04:55:23,166][78123] Updated weights for policy 1, policy_version 41670 (0.0008) -[2023-10-12 04:55:23,186][78091] Updated weights for policy 0, policy_version 41860 (0.0008) -[2023-10-12 04:55:23,537][78123] Updated weights for policy 1, policy_version 41680 (0.0008) -[2023-10-12 04:55:23,556][78091] Updated weights for policy 0, policy_version 41870 (0.0007) -[2023-10-12 04:55:23,896][78123] Updated weights for policy 1, policy_version 41690 (0.0008) -[2023-10-12 04:55:23,922][78091] Updated weights for policy 0, policy_version 41880 (0.0008) -[2023-10-12 04:55:25,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 85590016. Throughput: 0: 1592.6, 1: 1582.4. Samples: 21403592. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-12 04:55:25,202][77203] Avg episode reward: [(0, '48.160'), (1, '39.060')] -[2023-10-12 04:55:28,308][78123] Updated weights for policy 1, policy_version 41700 (0.0008) -[2023-10-12 04:55:28,369][78091] Updated weights for policy 0, policy_version 41890 (0.0007) -[2023-10-12 04:55:28,668][78123] Updated weights for policy 1, policy_version 41710 (0.0010) -[2023-10-12 04:55:28,737][78091] Updated weights for policy 0, policy_version 41900 (0.0008) -[2023-10-12 04:55:29,047][78123] Updated weights for policy 1, policy_version 41720 (0.0009) -[2023-10-12 04:55:29,110][78091] Updated weights for policy 0, policy_version 41910 (0.0009) -[2023-10-12 04:55:29,480][78091] Updated weights for policy 0, policy_version 41920 (0.0008) -[2023-10-12 04:55:30,201][77203] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 85655552. Throughput: 0: 1605.1, 1: 1601.2. Samples: 21414342. Policy #0 lag: (min: 6.0, avg: 13.8, max: 38.0) -[2023-10-12 04:55:30,202][77203] Avg episode reward: [(0, '49.740'), (1, '43.760')] -[2023-10-12 04:55:33,227][78123] Updated weights for policy 1, policy_version 41730 (0.0008) -[2023-10-12 04:55:33,592][78123] Updated weights for policy 1, policy_version 41740 (0.0008) -[2023-10-12 04:55:33,838][78091] Updated weights for policy 0, policy_version 41930 (0.0007) -[2023-10-12 04:55:33,947][78123] Updated weights for policy 1, policy_version 41750 (0.0007) -[2023-10-12 04:55:34,206][78091] Updated weights for policy 0, policy_version 41940 (0.0009) -[2023-10-12 04:55:34,314][78123] Updated weights for policy 1, policy_version 41760 (0.0008) -[2023-10-12 04:55:34,586][78091] Updated weights for policy 0, policy_version 41950 (0.0009) -[2023-10-12 04:55:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 85721088. Throughput: 0: 1608.7, 1: 1600.0. Samples: 21433240. Policy #0 lag: (min: 6.0, avg: 13.8, max: 38.0) -[2023-10-12 04:55:35,202][77203] Avg episode reward: [(0, '51.250'), (1, '38.920')] -[2023-10-12 04:55:38,642][78123] Updated weights for policy 1, policy_version 41770 (0.0009) -[2023-10-12 04:55:38,858][78091] Updated weights for policy 0, policy_version 41960 (0.0009) -[2023-10-12 04:55:38,996][78123] Updated weights for policy 1, policy_version 41780 (0.0008) -[2023-10-12 04:55:39,220][78091] Updated weights for policy 0, policy_version 41970 (0.0008) -[2023-10-12 04:55:39,367][78123] Updated weights for policy 1, policy_version 41790 (0.0009) -[2023-10-12 04:55:39,595][78091] Updated weights for policy 0, policy_version 41980 (0.0009) -[2023-10-12 04:55:40,201][77203] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 85786624. Throughput: 0: 1588.4, 1: 1583.2. Samples: 21451292. Policy #0 lag: (min: 6.0, avg: 13.8, max: 38.0) -[2023-10-12 04:55:40,202][77203] Avg episode reward: [(0, '46.060'), (1, '42.780')] -[2023-10-12 04:55:43,638][78123] Updated weights for policy 1, policy_version 41800 (0.0009) -[2023-10-12 04:55:43,909][78091] Updated weights for policy 0, policy_version 41990 (0.0008) -[2023-10-12 04:55:44,009][78123] Updated weights for policy 1, policy_version 41810 (0.0009) -[2023-10-12 04:55:44,272][78091] Updated weights for policy 0, policy_version 42000 (0.0010) -[2023-10-12 04:55:44,368][78123] Updated weights for policy 1, policy_version 41820 (0.0008) -[2023-10-12 04:55:44,641][78091] Updated weights for policy 0, policy_version 42010 (0.0009) -[2023-10-12 04:55:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 85852160. Throughput: 0: 1596.1, 1: 1592.4. Samples: 21462236. Policy #0 lag: (min: 6.0, avg: 13.8, max: 38.0) -[2023-10-12 04:55:45,202][77203] Avg episode reward: [(0, '40.980'), (1, '44.510')] -[2023-10-12 04:55:48,753][78123] Updated weights for policy 1, policy_version 41830 (0.0009) -[2023-10-12 04:55:49,115][78091] Updated weights for policy 0, policy_version 42020 (0.0011) -[2023-10-12 04:55:49,117][78123] Updated weights for policy 1, policy_version 41840 (0.0009) -[2023-10-12 04:55:49,474][78123] Updated weights for policy 1, policy_version 41850 (0.0007) -[2023-10-12 04:55:49,497][78091] Updated weights for policy 0, policy_version 42030 (0.0007) -[2023-10-12 04:55:49,861][78091] Updated weights for policy 0, policy_version 42040 (0.0007) -[2023-10-12 04:55:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 85917696. Throughput: 0: 1611.6, 1: 1601.6. Samples: 21481330. Policy #0 lag: (min: 6.0, avg: 13.8, max: 38.0) -[2023-10-12 04:55:50,201][77203] Avg episode reward: [(0, '40.840'), (1, '39.140')] -[2023-10-12 04:55:53,974][78091] Updated weights for policy 0, policy_version 42050 (0.0009) -[2023-10-12 04:55:53,979][78123] Updated weights for policy 1, policy_version 41860 (0.0008) -[2023-10-12 04:55:54,341][78091] Updated weights for policy 0, policy_version 42060 (0.0008) -[2023-10-12 04:55:54,344][78123] Updated weights for policy 1, policy_version 41870 (0.0009) -[2023-10-12 04:55:54,715][78123] Updated weights for policy 1, policy_version 41880 (0.0007) -[2023-10-12 04:55:54,721][78091] Updated weights for policy 0, policy_version 42070 (0.0007) -[2023-10-12 04:55:55,088][78091] Updated weights for policy 0, policy_version 42080 (0.0009) -[2023-10-12 04:55:55,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 85983232. Throughput: 0: 1596.2, 1: 1585.3. Samples: 21499484. Policy #0 lag: (min: 6.0, avg: 13.8, max: 38.0) -[2023-10-12 04:55:55,202][77203] Avg episode reward: [(0, '33.800'), (1, '39.030')] -[2023-10-12 04:55:59,145][78123] Updated weights for policy 1, policy_version 41890 (0.0007) -[2023-10-12 04:55:59,418][78091] Updated weights for policy 0, policy_version 42090 (0.0009) -[2023-10-12 04:55:59,519][78123] Updated weights for policy 1, policy_version 41900 (0.0007) -[2023-10-12 04:55:59,793][78091] Updated weights for policy 0, policy_version 42100 (0.0007) -[2023-10-12 04:55:59,881][78123] Updated weights for policy 1, policy_version 41910 (0.0007) -[2023-10-12 04:56:00,165][78091] Updated weights for policy 0, policy_version 42110 (0.0007) -[2023-10-12 04:56:00,201][77203] Fps is (10 sec: 6553.6, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 85983232. Throughput: 0: 1589.6, 1: 1587.4. Samples: 21509730. Policy #0 lag: (min: 6.0, avg: 13.8, max: 38.0) -[2023-10-12 04:56:00,201][77203] Avg episode reward: [(0, '33.810'), (1, '42.790')] -[2023-10-12 04:56:00,247][78123] Updated weights for policy 1, policy_version 41920 (0.0010) -[2023-10-12 04:56:04,424][78091] Updated weights for policy 0, policy_version 42120 (0.0008) -[2023-10-12 04:56:04,656][78123] Updated weights for policy 1, policy_version 41930 (0.0007) -[2023-10-12 04:56:04,802][78091] Updated weights for policy 0, policy_version 42130 (0.0009) -[2023-10-12 04:56:05,026][78123] Updated weights for policy 1, policy_version 41940 (0.0009) -[2023-10-12 04:56:05,169][78091] Updated weights for policy 0, policy_version 42140 (0.0007) -[2023-10-12 04:56:05,201][77203] Fps is (10 sec: 6553.8, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 86048768. Throughput: 0: 1614.0, 1: 1603.0. Samples: 21529388. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-12 04:56:05,201][77203] Avg episode reward: [(0, '34.530'), (1, '40.890')] -[2023-10-12 04:56:05,393][78123] Updated weights for policy 1, policy_version 41950 (0.0007) -[2023-10-12 04:56:09,442][78091] Updated weights for policy 0, policy_version 42150 (0.0010) -[2023-10-12 04:56:09,747][78123] Updated weights for policy 1, policy_version 41960 (0.0007) -[2023-10-12 04:56:09,812][78091] Updated weights for policy 0, policy_version 42160 (0.0007) -[2023-10-12 04:56:10,108][78123] Updated weights for policy 1, policy_version 41970 (0.0008) -[2023-10-12 04:56:10,175][78091] Updated weights for policy 0, policy_version 42170 (0.0007) -[2023-10-12 04:56:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 86114304. Throughput: 0: 1607.3, 1: 1596.5. Samples: 21547766. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-12 04:56:10,202][77203] Avg episode reward: [(0, '35.700'), (1, '39.060')] -[2023-10-12 04:56:10,471][78123] Updated weights for policy 1, policy_version 41980 (0.0008) -[2023-10-12 04:56:14,431][78091] Updated weights for policy 0, policy_version 42180 (0.0010) -[2023-10-12 04:56:14,716][78123] Updated weights for policy 1, policy_version 41990 (0.0007) -[2023-10-12 04:56:14,793][78091] Updated weights for policy 0, policy_version 42190 (0.0008) -[2023-10-12 04:56:15,085][78123] Updated weights for policy 1, policy_version 42000 (0.0007) -[2023-10-12 04:56:15,156][78091] Updated weights for policy 0, policy_version 42200 (0.0009) -[2023-10-12 04:56:15,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 86179840. Throughput: 0: 1597.4, 1: 1582.7. Samples: 21557446. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-12 04:56:15,202][77203] Avg episode reward: [(0, '44.960'), (1, '45.940')] -[2023-10-12 04:56:15,458][78123] Updated weights for policy 1, policy_version 42010 (0.0007) -[2023-10-12 04:56:19,413][78091] Updated weights for policy 0, policy_version 42210 (0.0009) -[2023-10-12 04:56:19,782][78091] Updated weights for policy 0, policy_version 42220 (0.0010) -[2023-10-12 04:56:19,954][78123] Updated weights for policy 1, policy_version 42020 (0.0010) -[2023-10-12 04:56:20,155][78091] Updated weights for policy 0, policy_version 42230 (0.0010) -[2023-10-12 04:56:20,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 86245376. Throughput: 0: 1607.3, 1: 1586.4. Samples: 21576958. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-12 04:56:20,202][77203] Avg episode reward: [(0, '43.400'), (1, '39.240')] -[2023-10-12 04:56:20,317][78123] Updated weights for policy 1, policy_version 42030 (0.0009) -[2023-10-12 04:56:20,518][78091] Updated weights for policy 0, policy_version 42240 (0.0008) -[2023-10-12 04:56:20,685][78123] Updated weights for policy 1, policy_version 42040 (0.0009) -[2023-10-12 04:56:24,758][78091] Updated weights for policy 0, policy_version 42250 (0.0008) -[2023-10-12 04:56:25,058][78123] Updated weights for policy 1, policy_version 42050 (0.0009) -[2023-10-12 04:56:25,127][78091] Updated weights for policy 0, policy_version 42260 (0.0008) -[2023-10-12 04:56:25,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 86310912. Throughput: 0: 1618.6, 1: 1600.4. Samples: 21596148. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-12 04:56:25,202][77203] Avg episode reward: [(0, '43.500'), (1, '36.820')] -[2023-10-12 04:56:25,464][78123] Updated weights for policy 1, policy_version 42060 (0.0008) -[2023-10-12 04:56:25,491][78091] Updated weights for policy 0, policy_version 42270 (0.0007) -[2023-10-12 04:56:25,833][78123] Updated weights for policy 1, policy_version 42070 (0.0010) -[2023-10-12 04:56:26,196][78123] Updated weights for policy 1, policy_version 42080 (0.0008) -[2023-10-12 04:56:29,944][78091] Updated weights for policy 0, policy_version 42280 (0.0010) -[2023-10-12 04:56:30,201][77203] Fps is (10 sec: 13107.6, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 86376448. Throughput: 0: 1600.4, 1: 1575.2. Samples: 21605136. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-12 04:56:30,201][77203] Avg episode reward: [(0, '42.920'), (1, '41.940')] -[2023-10-12 04:56:30,304][78091] Updated weights for policy 0, policy_version 42290 (0.0007) -[2023-10-12 04:56:30,411][78123] Updated weights for policy 1, policy_version 42090 (0.0007) -[2023-10-12 04:56:30,685][78091] Updated weights for policy 0, policy_version 42300 (0.0009) -[2023-10-12 04:56:30,785][78123] Updated weights for policy 1, policy_version 42100 (0.0007) -[2023-10-12 04:56:31,153][78123] Updated weights for policy 1, policy_version 42110 (0.0008) -[2023-10-12 04:56:34,964][78091] Updated weights for policy 0, policy_version 42310 (0.0008) -[2023-10-12 04:56:35,201][77203] Fps is (10 sec: 13107.7, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 86441984. Throughput: 0: 1604.6, 1: 1579.8. Samples: 21624628. Policy #0 lag: (min: 9.0, avg: 10.0, max: 27.0) -[2023-10-12 04:56:35,201][77203] Avg episode reward: [(0, '46.890'), (1, '39.080')] -[2023-10-12 04:56:35,345][78091] Updated weights for policy 0, policy_version 42320 (0.0007) -[2023-10-12 04:56:35,491][78123] Updated weights for policy 1, policy_version 42120 (0.0009) -[2023-10-12 04:56:35,713][78091] Updated weights for policy 0, policy_version 42330 (0.0008) -[2023-10-12 04:56:35,850][78123] Updated weights for policy 1, policy_version 42130 (0.0008) -[2023-10-12 04:56:36,220][78123] Updated weights for policy 1, policy_version 42140 (0.0010) -[2023-10-12 04:56:40,004][78091] Updated weights for policy 0, policy_version 42340 (0.0009) -[2023-10-12 04:56:40,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 86507520. Throughput: 0: 1616.4, 1: 1593.2. Samples: 21643914. Policy #0 lag: (min: 9.0, avg: 10.0, max: 27.0) -[2023-10-12 04:56:40,201][77203] Avg episode reward: [(0, '43.110'), (1, '41.050')] -[2023-10-12 04:56:40,364][78091] Updated weights for policy 0, policy_version 42350 (0.0010) -[2023-10-12 04:56:40,734][78091] Updated weights for policy 0, policy_version 42360 (0.0009) -[2023-10-12 04:56:40,804][78123] Updated weights for policy 1, policy_version 42150 (0.0007) -[2023-10-12 04:56:41,168][78123] Updated weights for policy 1, policy_version 42160 (0.0008) -[2023-10-12 04:56:41,528][78123] Updated weights for policy 1, policy_version 42170 (0.0009) -[2023-10-12 04:56:45,093][78091] Updated weights for policy 0, policy_version 42370 (0.0008) -[2023-10-12 04:56:45,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 86573056. Throughput: 0: 1601.8, 1: 1575.6. Samples: 21652710. Policy #0 lag: (min: 9.0, avg: 10.0, max: 27.0) -[2023-10-12 04:56:45,202][77203] Avg episode reward: [(0, '43.450'), (1, '41.990')] -[2023-10-12 04:56:45,475][78091] Updated weights for policy 0, policy_version 42380 (0.0010) -[2023-10-12 04:56:45,702][78123] Updated weights for policy 1, policy_version 42180 (0.0008) -[2023-10-12 04:56:45,853][78091] Updated weights for policy 0, policy_version 42390 (0.0009) -[2023-10-12 04:56:46,058][78123] Updated weights for policy 1, policy_version 42190 (0.0008) -[2023-10-12 04:56:46,217][78091] Updated weights for policy 0, policy_version 42400 (0.0010) -[2023-10-12 04:56:46,426][78123] Updated weights for policy 1, policy_version 42200 (0.0008) -[2023-10-12 04:56:50,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 86638592. Throughput: 0: 1591.5, 1: 1575.6. Samples: 21671908. Policy #0 lag: (min: 9.0, avg: 10.0, max: 27.0) -[2023-10-12 04:56:50,202][77203] Avg episode reward: [(0, '44.040'), (1, '45.460')] -[2023-10-12 04:56:50,621][78091] Updated weights for policy 0, policy_version 42410 (0.0010) -[2023-10-12 04:56:50,908][78123] Updated weights for policy 1, policy_version 42210 (0.0010) -[2023-10-12 04:56:50,996][78091] Updated weights for policy 0, policy_version 42420 (0.0009) -[2023-10-12 04:56:51,265][78123] Updated weights for policy 1, policy_version 42220 (0.0007) -[2023-10-12 04:56:51,356][78091] Updated weights for policy 0, policy_version 42430 (0.0009) -[2023-10-12 04:56:51,642][78123] Updated weights for policy 1, policy_version 42230 (0.0007) -[2023-10-12 04:56:52,011][78123] Updated weights for policy 1, policy_version 42240 (0.0009) -[2023-10-12 04:56:55,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 86704128. Throughput: 0: 1604.8, 1: 1584.3. Samples: 21691280. Policy #0 lag: (min: 9.0, avg: 10.0, max: 27.0) -[2023-10-12 04:56:55,202][77203] Avg episode reward: [(0, '48.270'), (1, '41.410')] -[2023-10-12 04:56:55,672][78091] Updated weights for policy 0, policy_version 42440 (0.0007) -[2023-10-12 04:56:56,034][78091] Updated weights for policy 0, policy_version 42450 (0.0008) -[2023-10-12 04:56:56,407][78091] Updated weights for policy 0, policy_version 42460 (0.0009) -[2023-10-12 04:56:56,490][78123] Updated weights for policy 1, policy_version 42250 (0.0008) -[2023-10-12 04:56:56,858][78123] Updated weights for policy 1, policy_version 42260 (0.0009) -[2023-10-12 04:56:57,215][78123] Updated weights for policy 1, policy_version 42270 (0.0008) -[2023-10-12 04:57:00,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 86769664. Throughput: 0: 1589.7, 1: 1575.9. Samples: 21699898. Policy #0 lag: (min: 9.0, avg: 10.0, max: 27.0) -[2023-10-12 04:57:00,202][77203] Avg episode reward: [(0, '46.210'), (1, '45.670')] -[2023-10-12 04:57:00,831][78091] Updated weights for policy 0, policy_version 42470 (0.0009) -[2023-10-12 04:57:01,208][78091] Updated weights for policy 0, policy_version 42480 (0.0008) -[2023-10-12 04:57:01,458][78123] Updated weights for policy 1, policy_version 42280 (0.0009) -[2023-10-12 04:57:01,575][78091] Updated weights for policy 0, policy_version 42490 (0.0007) -[2023-10-12 04:57:01,822][78123] Updated weights for policy 1, policy_version 42290 (0.0009) -[2023-10-12 04:57:02,187][78123] Updated weights for policy 1, policy_version 42300 (0.0009) -[2023-10-12 04:57:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 86835200. Throughput: 0: 1585.4, 1: 1579.0. Samples: 21719356. Policy #0 lag: (min: 22.0, avg: 45.0, max: 54.0) -[2023-10-12 04:57:05,202][77203] Avg episode reward: [(0, '44.400'), (1, '45.440')] -[2023-10-12 04:57:05,871][78091] Updated weights for policy 0, policy_version 42500 (0.0008) -[2023-10-12 04:57:06,234][78091] Updated weights for policy 0, policy_version 42510 (0.0010) -[2023-10-12 04:57:06,445][78123] Updated weights for policy 1, policy_version 42310 (0.0008) -[2023-10-12 04:57:06,603][78091] Updated weights for policy 0, policy_version 42520 (0.0007) -[2023-10-12 04:57:06,807][78123] Updated weights for policy 1, policy_version 42320 (0.0009) -[2023-10-12 04:57:07,178][78123] Updated weights for policy 1, policy_version 42330 (0.0010) -[2023-10-12 04:57:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 86900736. Throughput: 0: 1588.7, 1: 1585.2. Samples: 21738972. Policy #0 lag: (min: 22.0, avg: 45.0, max: 54.0) -[2023-10-12 04:57:10,202][77203] Avg episode reward: [(0, '44.220'), (1, '41.110')] -[2023-10-12 04:57:10,210][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000042528_43548672.pth... -[2023-10-12 04:57:10,210][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000042336_43352064.pth... -[2023-10-12 04:57:10,263][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000041056_42041344.pth -[2023-10-12 04:57:10,264][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000040864_41844736.pth -[2023-10-12 04:57:11,157][78091] Updated weights for policy 0, policy_version 42530 (0.0009) -[2023-10-12 04:57:11,517][78123] Updated weights for policy 1, policy_version 42340 (0.0010) -[2023-10-12 04:57:11,533][78091] Updated weights for policy 0, policy_version 42540 (0.0007) -[2023-10-12 04:57:11,899][78091] Updated weights for policy 0, policy_version 42550 (0.0007) -[2023-10-12 04:57:11,901][78123] Updated weights for policy 1, policy_version 42350 (0.0007) -[2023-10-12 04:57:12,266][78091] Updated weights for policy 0, policy_version 42560 (0.0008) -[2023-10-12 04:57:12,268][78123] Updated weights for policy 1, policy_version 42360 (0.0010) -[2023-10-12 04:57:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 86966272. Throughput: 0: 1580.7, 1: 1581.7. Samples: 21747446. Policy #0 lag: (min: 22.0, avg: 45.0, max: 54.0) -[2023-10-12 04:57:15,202][77203] Avg episode reward: [(0, '44.170'), (1, '43.990')] -[2023-10-12 04:57:16,360][78091] Updated weights for policy 0, policy_version 42570 (0.0008) -[2023-10-12 04:57:16,580][78123] Updated weights for policy 1, policy_version 42370 (0.0009) -[2023-10-12 04:57:16,736][78091] Updated weights for policy 0, policy_version 42580 (0.0009) -[2023-10-12 04:57:16,949][78123] Updated weights for policy 1, policy_version 42380 (0.0007) -[2023-10-12 04:57:17,095][78091] Updated weights for policy 0, policy_version 42590 (0.0007) -[2023-10-12 04:57:17,317][78123] Updated weights for policy 1, policy_version 42390 (0.0009) -[2023-10-12 04:57:17,687][78123] Updated weights for policy 1, policy_version 42400 (0.0007) -[2023-10-12 04:57:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 87031808. Throughput: 0: 1580.1, 1: 1580.5. Samples: 21766858. Policy #0 lag: (min: 22.0, avg: 45.0, max: 54.0) -[2023-10-12 04:57:20,202][77203] Avg episode reward: [(0, '39.790'), (1, '41.340')] -[2023-10-12 04:57:21,431][78091] Updated weights for policy 0, policy_version 42600 (0.0007) -[2023-10-12 04:57:21,806][78091] Updated weights for policy 0, policy_version 42610 (0.0007) -[2023-10-12 04:57:21,964][78123] Updated weights for policy 1, policy_version 42410 (0.0007) -[2023-10-12 04:57:22,172][78091] Updated weights for policy 0, policy_version 42620 (0.0008) -[2023-10-12 04:57:22,329][78123] Updated weights for policy 1, policy_version 42420 (0.0007) -[2023-10-12 04:57:22,692][78123] Updated weights for policy 1, policy_version 42430 (0.0008) -[2023-10-12 04:57:25,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 87097344. Throughput: 0: 1586.9, 1: 1580.3. Samples: 21786438. Policy #0 lag: (min: 22.0, avg: 45.0, max: 54.0) -[2023-10-12 04:57:25,202][77203] Avg episode reward: [(0, '49.100'), (1, '39.780')] -[2023-10-12 04:57:26,551][78091] Updated weights for policy 0, policy_version 42630 (0.0009) -[2023-10-12 04:57:26,916][78091] Updated weights for policy 0, policy_version 42640 (0.0010) -[2023-10-12 04:57:27,110][78123] Updated weights for policy 1, policy_version 42440 (0.0007) -[2023-10-12 04:57:27,297][78091] Updated weights for policy 0, policy_version 42650 (0.0009) -[2023-10-12 04:57:27,476][78123] Updated weights for policy 1, policy_version 42450 (0.0009) -[2023-10-12 04:57:27,854][78123] Updated weights for policy 1, policy_version 42460 (0.0009) -[2023-10-12 04:57:30,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 87162880. Throughput: 0: 1581.5, 1: 1586.8. Samples: 21795286. Policy #0 lag: (min: 22.0, avg: 45.0, max: 54.0) -[2023-10-12 04:57:30,201][77203] Avg episode reward: [(0, '51.310'), (1, '42.900')] -[2023-10-12 04:57:31,531][78091] Updated weights for policy 0, policy_version 42660 (0.0010) -[2023-10-12 04:57:31,908][78091] Updated weights for policy 0, policy_version 42670 (0.0010) -[2023-10-12 04:57:32,055][78123] Updated weights for policy 1, policy_version 42470 (0.0010) -[2023-10-12 04:57:32,277][78091] Updated weights for policy 0, policy_version 42680 (0.0010) -[2023-10-12 04:57:32,420][78123] Updated weights for policy 1, policy_version 42480 (0.0010) -[2023-10-12 04:57:32,796][78123] Updated weights for policy 1, policy_version 42490 (0.0008) -[2023-10-12 04:57:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 87228416. Throughput: 0: 1586.3, 1: 1584.8. Samples: 21814604. Policy #0 lag: (min: 31.0, avg: 32.9, max: 62.0) -[2023-10-12 04:57:35,202][77203] Avg episode reward: [(0, '49.120'), (1, '41.110')] -[2023-10-12 04:57:36,671][78091] Updated weights for policy 0, policy_version 42690 (0.0009) -[2023-10-12 04:57:37,062][78091] Updated weights for policy 0, policy_version 42700 (0.0008) -[2023-10-12 04:57:37,143][78123] Updated weights for policy 1, policy_version 42500 (0.0007) -[2023-10-12 04:57:37,437][78091] Updated weights for policy 0, policy_version 42710 (0.0009) -[2023-10-12 04:57:37,502][78123] Updated weights for policy 1, policy_version 42510 (0.0008) -[2023-10-12 04:57:37,795][78091] Updated weights for policy 0, policy_version 42720 (0.0007) -[2023-10-12 04:57:37,864][78123] Updated weights for policy 1, policy_version 42520 (0.0009) -[2023-10-12 04:57:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 87293952. Throughput: 0: 1585.6, 1: 1585.0. Samples: 21833958. Policy #0 lag: (min: 31.0, avg: 32.9, max: 62.0) -[2023-10-12 04:57:40,202][77203] Avg episode reward: [(0, '42.690'), (1, '41.760')] -[2023-10-12 04:57:42,136][78091] Updated weights for policy 0, policy_version 42730 (0.0010) -[2023-10-12 04:57:42,405][78123] Updated weights for policy 1, policy_version 42530 (0.0009) -[2023-10-12 04:57:42,505][78091] Updated weights for policy 0, policy_version 42740 (0.0009) -[2023-10-12 04:57:42,769][78123] Updated weights for policy 1, policy_version 42540 (0.0008) -[2023-10-12 04:57:42,882][78091] Updated weights for policy 0, policy_version 42750 (0.0009) -[2023-10-12 04:57:43,136][78123] Updated weights for policy 1, policy_version 42550 (0.0007) -[2023-10-12 04:57:43,500][78123] Updated weights for policy 1, policy_version 42560 (0.0008) -[2023-10-12 04:57:45,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 87359488. Throughput: 0: 1590.5, 1: 1596.0. Samples: 21843294. Policy #0 lag: (min: 31.0, avg: 32.9, max: 62.0) -[2023-10-12 04:57:45,202][77203] Avg episode reward: [(0, '45.380'), (1, '42.220')] -[2023-10-12 04:57:47,115][78091] Updated weights for policy 0, policy_version 42760 (0.0009) -[2023-10-12 04:57:47,476][78091] Updated weights for policy 0, policy_version 42770 (0.0008) -[2023-10-12 04:57:47,637][78123] Updated weights for policy 1, policy_version 42570 (0.0009) -[2023-10-12 04:57:47,849][78091] Updated weights for policy 0, policy_version 42780 (0.0008) -[2023-10-12 04:57:48,003][78123] Updated weights for policy 1, policy_version 42580 (0.0008) -[2023-10-12 04:57:48,374][78123] Updated weights for policy 1, policy_version 42590 (0.0008) -[2023-10-12 04:57:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 87425024. Throughput: 0: 1588.8, 1: 1580.7. Samples: 21861982. Policy #0 lag: (min: 31.0, avg: 32.9, max: 62.0) -[2023-10-12 04:57:50,201][77203] Avg episode reward: [(0, '42.530'), (1, '41.590')] -[2023-10-12 04:57:52,108][78091] Updated weights for policy 0, policy_version 42790 (0.0009) -[2023-10-12 04:57:52,462][78123] Updated weights for policy 1, policy_version 42600 (0.0008) -[2023-10-12 04:57:52,470][78091] Updated weights for policy 0, policy_version 42800 (0.0008) -[2023-10-12 04:57:52,831][78123] Updated weights for policy 1, policy_version 42610 (0.0008) -[2023-10-12 04:57:52,848][78091] Updated weights for policy 0, policy_version 42810 (0.0009) -[2023-10-12 04:57:53,204][78123] Updated weights for policy 1, policy_version 42620 (0.0007) -[2023-10-12 04:57:55,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 87490560. Throughput: 0: 1589.6, 1: 1578.0. Samples: 21881516. Policy #0 lag: (min: 31.0, avg: 32.9, max: 62.0) -[2023-10-12 04:57:55,202][77203] Avg episode reward: [(0, '40.550'), (1, '39.440')] -[2023-10-12 04:57:57,040][78091] Updated weights for policy 0, policy_version 42820 (0.0007) -[2023-10-12 04:57:57,422][78091] Updated weights for policy 0, policy_version 42830 (0.0009) -[2023-10-12 04:57:57,791][78091] Updated weights for policy 0, policy_version 42840 (0.0007) -[2023-10-12 04:57:57,844][78123] Updated weights for policy 1, policy_version 42630 (0.0009) -[2023-10-12 04:57:58,210][78123] Updated weights for policy 1, policy_version 42640 (0.0008) -[2023-10-12 04:57:58,580][78123] Updated weights for policy 1, policy_version 42650 (0.0008) -[2023-10-12 04:58:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 87556096. Throughput: 0: 1596.8, 1: 1605.9. Samples: 21891568. Policy #0 lag: (min: 31.0, avg: 32.9, max: 62.0) -[2023-10-12 04:58:00,201][77203] Avg episode reward: [(0, '41.990'), (1, '37.470')] -[2023-10-12 04:58:02,185][78091] Updated weights for policy 0, policy_version 42850 (0.0008) -[2023-10-12 04:58:02,551][78091] Updated weights for policy 0, policy_version 42860 (0.0009) -[2023-10-12 04:58:02,942][78091] Updated weights for policy 0, policy_version 42870 (0.0008) -[2023-10-12 04:58:03,095][78123] Updated weights for policy 1, policy_version 42660 (0.0007) -[2023-10-12 04:58:03,313][78091] Updated weights for policy 0, policy_version 42880 (0.0010) -[2023-10-12 04:58:03,467][78123] Updated weights for policy 1, policy_version 42670 (0.0009) -[2023-10-12 04:58:03,822][78123] Updated weights for policy 1, policy_version 42680 (0.0010) -[2023-10-12 04:58:05,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 87621632. Throughput: 0: 1588.1, 1: 1592.0. Samples: 21909964. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:58:05,202][77203] Avg episode reward: [(0, '52.130'), (1, '39.480')] -[2023-10-12 04:58:07,789][78091] Updated weights for policy 0, policy_version 42890 (0.0009) -[2023-10-12 04:58:08,149][78091] Updated weights for policy 0, policy_version 42900 (0.0009) -[2023-10-12 04:58:08,305][78123] Updated weights for policy 1, policy_version 42690 (0.0007) -[2023-10-12 04:58:08,527][78091] Updated weights for policy 0, policy_version 42910 (0.0007) -[2023-10-12 04:58:08,675][78123] Updated weights for policy 1, policy_version 42700 (0.0008) -[2023-10-12 04:58:09,039][78123] Updated weights for policy 1, policy_version 42710 (0.0010) -[2023-10-12 04:58:09,406][78123] Updated weights for policy 1, policy_version 42720 (0.0010) -[2023-10-12 04:58:10,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 87687168. Throughput: 0: 1580.8, 1: 1582.2. Samples: 21928776. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:58:10,202][77203] Avg episode reward: [(0, '48.800'), (1, '38.090')] -[2023-10-12 04:58:13,003][78091] Updated weights for policy 0, policy_version 42920 (0.0009) -[2023-10-12 04:58:13,373][78091] Updated weights for policy 0, policy_version 42930 (0.0011) -[2023-10-12 04:58:13,753][78091] Updated weights for policy 0, policy_version 42940 (0.0008) -[2023-10-12 04:58:13,784][78123] Updated weights for policy 1, policy_version 42730 (0.0007) -[2023-10-12 04:58:14,156][78123] Updated weights for policy 1, policy_version 42740 (0.0009) -[2023-10-12 04:58:14,531][78123] Updated weights for policy 1, policy_version 42750 (0.0009) -[2023-10-12 04:58:15,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 87752704. Throughput: 0: 1603.0, 1: 1602.5. Samples: 21939534. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:58:15,202][77203] Avg episode reward: [(0, '46.500'), (1, '40.640')] -[2023-10-12 04:58:17,879][78091] Updated weights for policy 0, policy_version 42950 (0.0010) -[2023-10-12 04:58:18,242][78091] Updated weights for policy 0, policy_version 42960 (0.0007) -[2023-10-12 04:58:18,617][78091] Updated weights for policy 0, policy_version 42970 (0.0008) -[2023-10-12 04:58:18,755][78123] Updated weights for policy 1, policy_version 42760 (0.0008) -[2023-10-12 04:58:19,127][78123] Updated weights for policy 1, policy_version 42770 (0.0009) -[2023-10-12 04:58:19,494][78123] Updated weights for policy 1, policy_version 42780 (0.0009) -[2023-10-12 04:58:20,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.1, 300 sec: 12885.0). Total num frames: 87818240. Throughput: 0: 1581.6, 1: 1600.4. Samples: 21957796. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:58:20,202][77203] Avg episode reward: [(0, '46.540'), (1, '40.150')] -[2023-10-12 04:58:23,081][78091] Updated weights for policy 0, policy_version 42980 (0.0009) -[2023-10-12 04:58:23,471][78091] Updated weights for policy 0, policy_version 42990 (0.0010) -[2023-10-12 04:58:23,835][78091] Updated weights for policy 0, policy_version 43000 (0.0008) -[2023-10-12 04:58:23,849][78123] Updated weights for policy 1, policy_version 42790 (0.0008) -[2023-10-12 04:58:24,204][78123] Updated weights for policy 1, policy_version 42800 (0.0009) -[2023-10-12 04:58:24,571][78123] Updated weights for policy 1, policy_version 42810 (0.0008) -[2023-10-12 04:58:25,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 87883776. Throughput: 0: 1582.0, 1: 1582.1. Samples: 21976344. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:58:25,202][77203] Avg episode reward: [(0, '47.040'), (1, '42.290')] -[2023-10-12 04:58:27,916][78091] Updated weights for policy 0, policy_version 43010 (0.0009) -[2023-10-12 04:58:28,296][78091] Updated weights for policy 0, policy_version 43020 (0.0008) -[2023-10-12 04:58:28,669][78091] Updated weights for policy 0, policy_version 43030 (0.0007) -[2023-10-12 04:58:29,028][78091] Updated weights for policy 0, policy_version 43040 (0.0009) -[2023-10-12 04:58:29,075][78123] Updated weights for policy 1, policy_version 42820 (0.0009) -[2023-10-12 04:58:29,444][78123] Updated weights for policy 1, policy_version 42830 (0.0009) -[2023-10-12 04:58:29,805][78123] Updated weights for policy 1, policy_version 42840 (0.0009) -[2023-10-12 04:58:30,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 87949312. Throughput: 0: 1606.4, 1: 1590.1. Samples: 21987136. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 04:58:30,201][77203] Avg episode reward: [(0, '42.270'), (1, '41.730')] -[2023-10-12 04:58:33,303][78091] Updated weights for policy 0, policy_version 43050 (0.0008) -[2023-10-12 04:58:33,673][78091] Updated weights for policy 0, policy_version 43060 (0.0008) -[2023-10-12 04:58:34,039][78091] Updated weights for policy 0, policy_version 43070 (0.0008) -[2023-10-12 04:58:34,109][78123] Updated weights for policy 1, policy_version 42850 (0.0007) -[2023-10-12 04:58:34,473][78123] Updated weights for policy 1, policy_version 42860 (0.0010) -[2023-10-12 04:58:34,853][78123] Updated weights for policy 1, policy_version 42870 (0.0009) -[2023-10-12 04:58:35,201][77203] Fps is (10 sec: 9830.7, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 87982080. Throughput: 0: 1593.2, 1: 1608.0. Samples: 22006038. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 04:58:35,201][77203] Avg episode reward: [(0, '42.570'), (1, '41.530')] -[2023-10-12 04:58:35,221][78123] Updated weights for policy 1, policy_version 42880 (0.0009) -[2023-10-12 04:58:38,491][78091] Updated weights for policy 0, policy_version 43080 (0.0009) -[2023-10-12 04:58:38,856][78091] Updated weights for policy 0, policy_version 43090 (0.0008) -[2023-10-12 04:58:39,234][78091] Updated weights for policy 0, policy_version 43100 (0.0007) -[2023-10-12 04:58:39,482][78123] Updated weights for policy 1, policy_version 42890 (0.0010) -[2023-10-12 04:58:39,847][78123] Updated weights for policy 1, policy_version 42900 (0.0008) -[2023-10-12 04:58:40,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 88047616. Throughput: 0: 1586.3, 1: 1592.2. Samples: 22024550. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 04:58:40,202][77203] Avg episode reward: [(0, '50.990'), (1, '41.250')] -[2023-10-12 04:58:40,214][78123] Updated weights for policy 1, policy_version 42910 (0.0008) -[2023-10-12 04:58:43,600][78091] Updated weights for policy 0, policy_version 43110 (0.0009) -[2023-10-12 04:58:43,967][78091] Updated weights for policy 0, policy_version 43120 (0.0008) -[2023-10-12 04:58:44,348][78091] Updated weights for policy 0, policy_version 43130 (0.0008) -[2023-10-12 04:58:44,868][78123] Updated weights for policy 1, policy_version 42920 (0.0010) -[2023-10-12 04:58:45,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 88113152. Throughput: 0: 1601.9, 1: 1579.0. Samples: 22034710. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 04:58:45,201][77203] Avg episode reward: [(0, '48.140'), (1, '43.400')] -[2023-10-12 04:58:45,243][78123] Updated weights for policy 1, policy_version 42930 (0.0011) -[2023-10-12 04:58:45,609][78123] Updated weights for policy 1, policy_version 42940 (0.0010) -[2023-10-12 04:58:48,552][78091] Updated weights for policy 0, policy_version 43140 (0.0008) -[2023-10-12 04:58:48,921][78091] Updated weights for policy 0, policy_version 43150 (0.0009) -[2023-10-12 04:58:49,284][78091] Updated weights for policy 0, policy_version 43160 (0.0010) -[2023-10-12 04:58:49,834][78123] Updated weights for policy 1, policy_version 42950 (0.0009) -[2023-10-12 04:58:50,195][78123] Updated weights for policy 1, policy_version 42960 (0.0007) -[2023-10-12 04:58:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 88178688. Throughput: 0: 1601.9, 1: 1589.4. Samples: 22053570. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 04:58:50,201][77203] Avg episode reward: [(0, '47.360'), (1, '41.000')] -[2023-10-12 04:58:50,572][78123] Updated weights for policy 1, policy_version 42970 (0.0009) -[2023-10-12 04:58:53,748][78091] Updated weights for policy 0, policy_version 43170 (0.0009) -[2023-10-12 04:58:54,115][78091] Updated weights for policy 0, policy_version 43180 (0.0008) -[2023-10-12 04:58:54,503][78091] Updated weights for policy 0, policy_version 43190 (0.0007) -[2023-10-12 04:58:54,871][78091] Updated weights for policy 0, policy_version 43200 (0.0007) -[2023-10-12 04:58:55,046][78123] Updated weights for policy 1, policy_version 42980 (0.0010) -[2023-10-12 04:58:55,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 88244224. Throughput: 0: 1588.3, 1: 1596.7. Samples: 22072098. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 04:58:55,201][77203] Avg episode reward: [(0, '49.890'), (1, '43.750')] -[2023-10-12 04:58:55,404][78123] Updated weights for policy 1, policy_version 42990 (0.0010) -[2023-10-12 04:58:55,776][78123] Updated weights for policy 1, policy_version 43000 (0.0010) -[2023-10-12 04:58:59,238][78091] Updated weights for policy 0, policy_version 43210 (0.0009) -[2023-10-12 04:58:59,608][78091] Updated weights for policy 0, policy_version 43220 (0.0009) -[2023-10-12 04:58:59,971][78091] Updated weights for policy 0, policy_version 43230 (0.0007) -[2023-10-12 04:58:59,976][78123] Updated weights for policy 1, policy_version 43010 (0.0008) -[2023-10-12 04:59:00,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 88309760. Throughput: 0: 1589.9, 1: 1566.2. Samples: 22081558. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 04:59:00,201][77203] Avg episode reward: [(0, '45.010'), (1, '39.120')] -[2023-10-12 04:59:00,332][78123] Updated weights for policy 1, policy_version 43020 (0.0008) -[2023-10-12 04:59:00,702][78123] Updated weights for policy 1, policy_version 43030 (0.0009) -[2023-10-12 04:59:01,072][78123] Updated weights for policy 1, policy_version 43040 (0.0010) -[2023-10-12 04:59:04,127][78091] Updated weights for policy 0, policy_version 43240 (0.0007) -[2023-10-12 04:59:04,514][78091] Updated weights for policy 0, policy_version 43250 (0.0008) -[2023-10-12 04:59:04,880][78091] Updated weights for policy 0, policy_version 43260 (0.0009) -[2023-10-12 04:59:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 88375296. Throughput: 0: 1610.9, 1: 1575.4. Samples: 22101178. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 04:59:05,201][77203] Avg episode reward: [(0, '40.800'), (1, '38.140')] -[2023-10-12 04:59:05,374][78123] Updated weights for policy 1, policy_version 43050 (0.0009) -[2023-10-12 04:59:05,745][78123] Updated weights for policy 1, policy_version 43060 (0.0007) -[2023-10-12 04:59:06,112][78123] Updated weights for policy 1, policy_version 43070 (0.0008) -[2023-10-12 04:59:09,349][78091] Updated weights for policy 0, policy_version 43270 (0.0008) -[2023-10-12 04:59:09,723][78091] Updated weights for policy 0, policy_version 43280 (0.0007) -[2023-10-12 04:59:10,100][78091] Updated weights for policy 0, policy_version 43290 (0.0008) -[2023-10-12 04:59:10,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 88408064. Throughput: 0: 1596.5, 1: 1592.4. Samples: 22119840. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 04:59:10,201][77203] Avg episode reward: [(0, '44.610'), (1, '41.610')] -[2023-10-12 04:59:10,315][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000043296_44335104.pth... -[2023-10-12 04:59:10,354][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000041792_42795008.pth -[2023-10-12 04:59:10,517][78123] Updated weights for policy 1, policy_version 43080 (0.0008) -[2023-10-12 04:59:10,875][78123] Updated weights for policy 1, policy_version 43090 (0.0007) -[2023-10-12 04:59:11,245][78123] Updated weights for policy 1, policy_version 43100 (0.0008) -[2023-10-12 04:59:11,390][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000043104_44138496.pth... -[2023-10-12 04:59:11,426][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000041600_42598400.pth -[2023-10-12 04:59:14,530][78091] Updated weights for policy 0, policy_version 43300 (0.0007) -[2023-10-12 04:59:14,894][78091] Updated weights for policy 0, policy_version 43310 (0.0008) -[2023-10-12 04:59:15,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 88473600. Throughput: 0: 1580.2, 1: 1571.8. Samples: 22128974. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 04:59:15,201][77203] Avg episode reward: [(0, '43.190'), (1, '39.420')] -[2023-10-12 04:59:15,260][78091] Updated weights for policy 0, policy_version 43320 (0.0008) -[2023-10-12 04:59:15,792][78123] Updated weights for policy 1, policy_version 43110 (0.0010) -[2023-10-12 04:59:16,163][78123] Updated weights for policy 1, policy_version 43120 (0.0011) -[2023-10-12 04:59:16,536][78123] Updated weights for policy 1, policy_version 43130 (0.0009) -[2023-10-12 04:59:19,608][78091] Updated weights for policy 0, policy_version 43330 (0.0009) -[2023-10-12 04:59:19,975][78091] Updated weights for policy 0, policy_version 43340 (0.0009) -[2023-10-12 04:59:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 88539136. Throughput: 0: 1596.7, 1: 1566.0. Samples: 22148356. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 04:59:20,204][77203] Avg episode reward: [(0, '47.010'), (1, '42.010')] -[2023-10-12 04:59:20,342][78091] Updated weights for policy 0, policy_version 43350 (0.0008) -[2023-10-12 04:59:20,706][78091] Updated weights for policy 0, policy_version 43360 (0.0007) -[2023-10-12 04:59:20,842][78123] Updated weights for policy 1, policy_version 43140 (0.0009) -[2023-10-12 04:59:21,208][78123] Updated weights for policy 1, policy_version 43150 (0.0009) -[2023-10-12 04:59:21,578][78123] Updated weights for policy 1, policy_version 43160 (0.0009) -[2023-10-12 04:59:25,159][78091] Updated weights for policy 0, policy_version 43370 (0.0007) -[2023-10-12 04:59:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 88604672. Throughput: 0: 1606.7, 1: 1575.4. Samples: 22167744. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 04:59:25,202][77203] Avg episode reward: [(0, '43.760'), (1, '44.670')] -[2023-10-12 04:59:25,540][78091] Updated weights for policy 0, policy_version 43380 (0.0007) -[2023-10-12 04:59:25,910][78091] Updated weights for policy 0, policy_version 43390 (0.0008) -[2023-10-12 04:59:26,052][78123] Updated weights for policy 1, policy_version 43170 (0.0008) -[2023-10-12 04:59:26,417][78123] Updated weights for policy 1, policy_version 43180 (0.0011) -[2023-10-12 04:59:26,777][78123] Updated weights for policy 1, policy_version 43190 (0.0010) -[2023-10-12 04:59:27,144][78123] Updated weights for policy 1, policy_version 43200 (0.0009) -[2023-10-12 04:59:30,152][78091] Updated weights for policy 0, policy_version 43400 (0.0008) -[2023-10-12 04:59:30,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 88670208. Throughput: 0: 1582.7, 1: 1565.0. Samples: 22176356. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 04:59:30,203][77203] Avg episode reward: [(0, '47.860'), (1, '38.100')] -[2023-10-12 04:59:30,521][78091] Updated weights for policy 0, policy_version 43410 (0.0007) -[2023-10-12 04:59:30,899][78091] Updated weights for policy 0, policy_version 43420 (0.0008) -[2023-10-12 04:59:31,732][78123] Updated weights for policy 1, policy_version 43210 (0.0009) -[2023-10-12 04:59:32,108][78123] Updated weights for policy 1, policy_version 43220 (0.0009) -[2023-10-12 04:59:32,474][78123] Updated weights for policy 1, policy_version 43230 (0.0007) -[2023-10-12 04:59:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 88735744. Throughput: 0: 1591.0, 1: 1567.3. Samples: 22195696. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 04:59:35,201][77203] Avg episode reward: [(0, '46.090'), (1, '35.740')] -[2023-10-12 04:59:35,254][78091] Updated weights for policy 0, policy_version 43430 (0.0009) -[2023-10-12 04:59:35,623][78091] Updated weights for policy 0, policy_version 43440 (0.0008) -[2023-10-12 04:59:35,990][78091] Updated weights for policy 0, policy_version 43450 (0.0010) -[2023-10-12 04:59:36,523][78123] Updated weights for policy 1, policy_version 43240 (0.0008) -[2023-10-12 04:59:36,893][78123] Updated weights for policy 1, policy_version 43250 (0.0008) -[2023-10-12 04:59:37,261][78123] Updated weights for policy 1, policy_version 43260 (0.0008) -[2023-10-12 04:59:40,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 88801280. Throughput: 0: 1607.9, 1: 1569.7. Samples: 22215090. Policy #0 lag: (min: 26.0, avg: 29.6, max: 58.0) -[2023-10-12 04:59:40,201][77203] Avg episode reward: [(0, '42.960'), (1, '25.830')] -[2023-10-12 04:59:40,213][78091] Updated weights for policy 0, policy_version 43460 (0.0009) -[2023-10-12 04:59:40,585][78091] Updated weights for policy 0, policy_version 43470 (0.0009) -[2023-10-12 04:59:40,955][78091] Updated weights for policy 0, policy_version 43480 (0.0009) -[2023-10-12 04:59:41,536][78123] Updated weights for policy 1, policy_version 43270 (0.0008) -[2023-10-12 04:59:41,911][78123] Updated weights for policy 1, policy_version 43280 (0.0009) -[2023-10-12 04:59:42,283][78123] Updated weights for policy 1, policy_version 43290 (0.0008) -[2023-10-12 04:59:45,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 88866816. Throughput: 0: 1586.3, 1: 1577.8. Samples: 22223940. Policy #0 lag: (min: 26.0, avg: 29.6, max: 58.0) -[2023-10-12 04:59:45,202][77203] Avg episode reward: [(0, '49.480'), (1, '33.490')] -[2023-10-12 04:59:45,323][78091] Updated weights for policy 0, policy_version 43490 (0.0009) -[2023-10-12 04:59:45,695][78091] Updated weights for policy 0, policy_version 43500 (0.0008) -[2023-10-12 04:59:46,080][78091] Updated weights for policy 0, policy_version 43510 (0.0008) -[2023-10-12 04:59:46,442][78091] Updated weights for policy 0, policy_version 43520 (0.0008) -[2023-10-12 04:59:46,442][78123] Updated weights for policy 1, policy_version 43300 (0.0007) -[2023-10-12 04:59:46,809][78123] Updated weights for policy 1, policy_version 43310 (0.0011) -[2023-10-12 04:59:47,176][78123] Updated weights for policy 1, policy_version 43320 (0.0009) -[2023-10-12 04:59:50,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 88932352. Throughput: 0: 1582.5, 1: 1581.5. Samples: 22243562. Policy #0 lag: (min: 26.0, avg: 29.6, max: 58.0) -[2023-10-12 04:59:50,205][77203] Avg episode reward: [(0, '51.810'), (1, '35.020')] -[2023-10-12 04:59:50,746][78091] Updated weights for policy 0, policy_version 43530 (0.0009) -[2023-10-12 04:59:51,116][78091] Updated weights for policy 0, policy_version 43540 (0.0009) -[2023-10-12 04:59:51,486][78091] Updated weights for policy 0, policy_version 43550 (0.0010) -[2023-10-12 04:59:51,613][78123] Updated weights for policy 1, policy_version 43330 (0.0008) -[2023-10-12 04:59:51,970][78123] Updated weights for policy 1, policy_version 43340 (0.0007) -[2023-10-12 04:59:52,334][78123] Updated weights for policy 1, policy_version 43350 (0.0009) -[2023-10-12 04:59:52,711][78123] Updated weights for policy 1, policy_version 43360 (0.0007) -[2023-10-12 04:59:55,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 88997888. Throughput: 0: 1596.5, 1: 1587.7. Samples: 22263132. Policy #0 lag: (min: 26.0, avg: 29.6, max: 58.0) -[2023-10-12 04:59:55,202][77203] Avg episode reward: [(0, '44.840'), (1, '35.160')] -[2023-10-12 04:59:56,005][78091] Updated weights for policy 0, policy_version 43560 (0.0007) -[2023-10-12 04:59:56,376][78091] Updated weights for policy 0, policy_version 43570 (0.0007) -[2023-10-12 04:59:56,751][78091] Updated weights for policy 0, policy_version 43580 (0.0007) -[2023-10-12 04:59:57,168][78123] Updated weights for policy 1, policy_version 43370 (0.0008) -[2023-10-12 04:59:57,533][78123] Updated weights for policy 1, policy_version 43380 (0.0010) -[2023-10-12 04:59:57,901][78123] Updated weights for policy 1, policy_version 43390 (0.0008) -[2023-10-12 05:00:00,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 89063424. Throughput: 0: 1581.5, 1: 1594.1. Samples: 22271876. Policy #0 lag: (min: 26.0, avg: 29.6, max: 58.0) -[2023-10-12 05:00:00,202][77203] Avg episode reward: [(0, '43.620'), (1, '41.570')] -[2023-10-12 05:00:00,825][78091] Updated weights for policy 0, policy_version 43590 (0.0007) -[2023-10-12 05:00:01,196][78091] Updated weights for policy 0, policy_version 43600 (0.0007) -[2023-10-12 05:00:01,568][78091] Updated weights for policy 0, policy_version 43610 (0.0009) -[2023-10-12 05:00:02,223][78123] Updated weights for policy 1, policy_version 43400 (0.0009) -[2023-10-12 05:00:02,600][78123] Updated weights for policy 1, policy_version 43410 (0.0011) -[2023-10-12 05:00:02,967][78123] Updated weights for policy 1, policy_version 43420 (0.0010) -[2023-10-12 05:00:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 89128960. Throughput: 0: 1585.9, 1: 1588.5. Samples: 22291206. Policy #0 lag: (min: 26.0, avg: 29.6, max: 58.0) -[2023-10-12 05:00:05,201][77203] Avg episode reward: [(0, '48.250'), (1, '40.650')] -[2023-10-12 05:00:05,866][78091] Updated weights for policy 0, policy_version 43620 (0.0009) -[2023-10-12 05:00:06,235][78091] Updated weights for policy 0, policy_version 43630 (0.0008) -[2023-10-12 05:00:06,603][78091] Updated weights for policy 0, policy_version 43640 (0.0009) -[2023-10-12 05:00:07,391][78123] Updated weights for policy 1, policy_version 43430 (0.0008) -[2023-10-12 05:00:07,762][78123] Updated weights for policy 1, policy_version 43440 (0.0010) -[2023-10-12 05:00:08,127][78123] Updated weights for policy 1, policy_version 43450 (0.0008) -[2023-10-12 05:00:10,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 89194496. Throughput: 0: 1582.9, 1: 1586.8. Samples: 22310382. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-12 05:00:10,202][77203] Avg episode reward: [(0, '45.390'), (1, '39.090')] -[2023-10-12 05:00:10,982][78091] Updated weights for policy 0, policy_version 43650 (0.0009) -[2023-10-12 05:00:11,353][78091] Updated weights for policy 0, policy_version 43660 (0.0009) -[2023-10-12 05:00:11,724][78091] Updated weights for policy 0, policy_version 43670 (0.0008) -[2023-10-12 05:00:12,096][78091] Updated weights for policy 0, policy_version 43680 (0.0009) -[2023-10-12 05:00:12,323][78123] Updated weights for policy 1, policy_version 43460 (0.0009) -[2023-10-12 05:00:12,678][78123] Updated weights for policy 1, policy_version 43470 (0.0010) -[2023-10-12 05:00:13,045][78123] Updated weights for policy 1, policy_version 43480 (0.0009) -[2023-10-12 05:00:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 89260032. Throughput: 0: 1582.2, 1: 1603.3. Samples: 22319700. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-12 05:00:15,201][77203] Avg episode reward: [(0, '40.200'), (1, '43.660')] -[2023-10-12 05:00:16,299][78091] Updated weights for policy 0, policy_version 43690 (0.0009) -[2023-10-12 05:00:16,664][78091] Updated weights for policy 0, policy_version 43700 (0.0008) -[2023-10-12 05:00:17,044][78091] Updated weights for policy 0, policy_version 43710 (0.0008) -[2023-10-12 05:00:17,486][78123] Updated weights for policy 1, policy_version 43490 (0.0009) -[2023-10-12 05:00:17,852][78123] Updated weights for policy 1, policy_version 43500 (0.0009) -[2023-10-12 05:00:18,209][78123] Updated weights for policy 1, policy_version 43510 (0.0008) -[2023-10-12 05:00:18,569][78123] Updated weights for policy 1, policy_version 43520 (0.0007) -[2023-10-12 05:00:20,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 89325568. Throughput: 0: 1588.8, 1: 1591.6. Samples: 22338814. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-12 05:00:20,202][77203] Avg episode reward: [(0, '42.540'), (1, '39.660')] -[2023-10-12 05:00:21,175][78091] Updated weights for policy 0, policy_version 43720 (0.0008) -[2023-10-12 05:00:21,548][78091] Updated weights for policy 0, policy_version 43730 (0.0008) -[2023-10-12 05:00:21,912][78091] Updated weights for policy 0, policy_version 43740 (0.0007) -[2023-10-12 05:00:22,913][78123] Updated weights for policy 1, policy_version 43530 (0.0009) -[2023-10-12 05:00:23,287][78123] Updated weights for policy 1, policy_version 43540 (0.0009) -[2023-10-12 05:00:23,653][78123] Updated weights for policy 1, policy_version 43550 (0.0007) -[2023-10-12 05:00:25,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 89391104. Throughput: 0: 1594.3, 1: 1590.3. Samples: 22358394. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-12 05:00:25,202][77203] Avg episode reward: [(0, '46.150'), (1, '34.780')] -[2023-10-12 05:00:26,201][78091] Updated weights for policy 0, policy_version 43750 (0.0008) -[2023-10-12 05:00:26,578][78091] Updated weights for policy 0, policy_version 43760 (0.0007) -[2023-10-12 05:00:26,954][78091] Updated weights for policy 0, policy_version 43770 (0.0009) -[2023-10-12 05:00:28,054][78123] Updated weights for policy 1, policy_version 43560 (0.0009) -[2023-10-12 05:00:28,425][78123] Updated weights for policy 1, policy_version 43570 (0.0008) -[2023-10-12 05:00:28,791][78123] Updated weights for policy 1, policy_version 43580 (0.0008) -[2023-10-12 05:00:30,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 12662.9). Total num frames: 89456640. Throughput: 0: 1592.1, 1: 1608.3. Samples: 22367960. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-12 05:00:30,201][77203] Avg episode reward: [(0, '44.740'), (1, '39.450')] -[2023-10-12 05:00:31,435][78091] Updated weights for policy 0, policy_version 43780 (0.0008) -[2023-10-12 05:00:31,804][78091] Updated weights for policy 0, policy_version 43790 (0.0007) -[2023-10-12 05:00:32,173][78091] Updated weights for policy 0, policy_version 43800 (0.0007) -[2023-10-12 05:00:33,176][78123] Updated weights for policy 1, policy_version 43590 (0.0008) -[2023-10-12 05:00:33,541][78123] Updated weights for policy 1, policy_version 43600 (0.0007) -[2023-10-12 05:00:33,900][78123] Updated weights for policy 1, policy_version 43610 (0.0008) -[2023-10-12 05:00:35,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 89522176. Throughput: 0: 1594.8, 1: 1582.9. Samples: 22386554. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-12 05:00:35,201][77203] Avg episode reward: [(0, '49.370'), (1, '38.200')] -[2023-10-12 05:00:36,433][78091] Updated weights for policy 0, policy_version 43810 (0.0008) -[2023-10-12 05:00:36,806][78091] Updated weights for policy 0, policy_version 43820 (0.0007) -[2023-10-12 05:00:37,177][78091] Updated weights for policy 0, policy_version 43830 (0.0007) -[2023-10-12 05:00:37,549][78091] Updated weights for policy 0, policy_version 43840 (0.0008) -[2023-10-12 05:00:38,205][78123] Updated weights for policy 1, policy_version 43620 (0.0008) -[2023-10-12 05:00:38,576][78123] Updated weights for policy 1, policy_version 43630 (0.0007) -[2023-10-12 05:00:38,943][78123] Updated weights for policy 1, policy_version 43640 (0.0009) -[2023-10-12 05:00:40,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 89587712. Throughput: 0: 1594.6, 1: 1570.6. Samples: 22405566. Policy #0 lag: (min: 22.0, avg: 26.5, max: 54.0) -[2023-10-12 05:00:40,202][77203] Avg episode reward: [(0, '47.260'), (1, '37.920')] -[2023-10-12 05:00:41,942][78091] Updated weights for policy 0, policy_version 43850 (0.0009) -[2023-10-12 05:00:42,325][78091] Updated weights for policy 0, policy_version 43860 (0.0009) -[2023-10-12 05:00:42,688][78091] Updated weights for policy 0, policy_version 43870 (0.0009) -[2023-10-12 05:00:43,438][78123] Updated weights for policy 1, policy_version 43650 (0.0009) -[2023-10-12 05:00:43,809][78123] Updated weights for policy 1, policy_version 43660 (0.0009) -[2023-10-12 05:00:44,172][78123] Updated weights for policy 1, policy_version 43670 (0.0010) -[2023-10-12 05:00:44,542][78123] Updated weights for policy 1, policy_version 43680 (0.0007) -[2023-10-12 05:00:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 89653248. Throughput: 0: 1595.8, 1: 1590.8. Samples: 22415274. Policy #0 lag: (min: 22.0, avg: 26.5, max: 54.0) -[2023-10-12 05:00:45,201][77203] Avg episode reward: [(0, '49.610'), (1, '44.060')] -[2023-10-12 05:00:47,079][78091] Updated weights for policy 0, policy_version 43880 (0.0008) -[2023-10-12 05:00:47,448][78091] Updated weights for policy 0, policy_version 43890 (0.0008) -[2023-10-12 05:00:47,825][78091] Updated weights for policy 0, policy_version 43900 (0.0007) -[2023-10-12 05:00:48,863][78123] Updated weights for policy 1, policy_version 43690 (0.0008) -[2023-10-12 05:00:49,230][78123] Updated weights for policy 1, policy_version 43700 (0.0011) -[2023-10-12 05:00:49,604][78123] Updated weights for policy 1, policy_version 43710 (0.0009) -[2023-10-12 05:00:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 89718784. Throughput: 0: 1588.5, 1: 1597.5. Samples: 22434578. Policy #0 lag: (min: 22.0, avg: 26.5, max: 54.0) -[2023-10-12 05:00:50,201][77203] Avg episode reward: [(0, '48.800'), (1, '39.020')] -[2023-10-12 05:00:52,163][78091] Updated weights for policy 0, policy_version 43910 (0.0009) -[2023-10-12 05:00:52,544][78091] Updated weights for policy 0, policy_version 43920 (0.0011) -[2023-10-12 05:00:52,914][78091] Updated weights for policy 0, policy_version 43930 (0.0010) -[2023-10-12 05:00:53,863][78123] Updated weights for policy 1, policy_version 43720 (0.0010) -[2023-10-12 05:00:54,234][78123] Updated weights for policy 1, policy_version 43730 (0.0008) -[2023-10-12 05:00:54,593][78123] Updated weights for policy 1, policy_version 43740 (0.0010) -[2023-10-12 05:00:55,201][77203] Fps is (10 sec: 13106.7, 60 sec: 13107.1, 300 sec: 12885.0). Total num frames: 89784320. Throughput: 0: 1594.5, 1: 1582.4. Samples: 22453342. Policy #0 lag: (min: 22.0, avg: 26.5, max: 54.0) -[2023-10-12 05:00:55,202][77203] Avg episode reward: [(0, '44.240'), (1, '40.190')] -[2023-10-12 05:00:57,220][78091] Updated weights for policy 0, policy_version 43940 (0.0008) -[2023-10-12 05:00:57,589][78091] Updated weights for policy 0, policy_version 43950 (0.0007) -[2023-10-12 05:00:57,951][78091] Updated weights for policy 0, policy_version 43960 (0.0007) -[2023-10-12 05:00:59,015][78123] Updated weights for policy 1, policy_version 43750 (0.0009) -[2023-10-12 05:00:59,381][78123] Updated weights for policy 1, policy_version 43760 (0.0009) -[2023-10-12 05:00:59,752][78123] Updated weights for policy 1, policy_version 43770 (0.0007) -[2023-10-12 05:01:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 12885.0). Total num frames: 89849856. Throughput: 0: 1605.3, 1: 1589.2. Samples: 22463454. Policy #0 lag: (min: 22.0, avg: 26.5, max: 54.0) -[2023-10-12 05:01:00,201][77203] Avg episode reward: [(0, '47.050'), (1, '40.970')] -[2023-10-12 05:01:02,199][78091] Updated weights for policy 0, policy_version 43970 (0.0008) -[2023-10-12 05:01:02,565][78091] Updated weights for policy 0, policy_version 43980 (0.0007) -[2023-10-12 05:01:02,935][78091] Updated weights for policy 0, policy_version 43990 (0.0007) -[2023-10-12 05:01:03,295][78091] Updated weights for policy 0, policy_version 44000 (0.0008) -[2023-10-12 05:01:03,787][78123] Updated weights for policy 1, policy_version 43780 (0.0009) -[2023-10-12 05:01:04,146][78123] Updated weights for policy 1, policy_version 43790 (0.0009) -[2023-10-12 05:01:04,515][78123] Updated weights for policy 1, policy_version 43800 (0.0007) -[2023-10-12 05:01:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 89915392. Throughput: 0: 1587.6, 1: 1603.6. Samples: 22482422. Policy #0 lag: (min: 22.0, avg: 26.5, max: 54.0) -[2023-10-12 05:01:05,202][77203] Avg episode reward: [(0, '44.810'), (1, '39.090')] -[2023-10-12 05:01:07,459][78091] Updated weights for policy 0, policy_version 44010 (0.0008) -[2023-10-12 05:01:07,829][78091] Updated weights for policy 0, policy_version 44020 (0.0007) -[2023-10-12 05:01:08,206][78091] Updated weights for policy 0, policy_version 44030 (0.0008) -[2023-10-12 05:01:08,847][78123] Updated weights for policy 1, policy_version 43810 (0.0009) -[2023-10-12 05:01:09,240][78123] Updated weights for policy 1, policy_version 43820 (0.0010) -[2023-10-12 05:01:09,603][78123] Updated weights for policy 1, policy_version 43830 (0.0010) -[2023-10-12 05:01:09,971][78123] Updated weights for policy 1, policy_version 43840 (0.0007) -[2023-10-12 05:01:10,201][77203] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 89980928. Throughput: 0: 1587.2, 1: 1590.7. Samples: 22501402. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:01:10,202][77203] Avg episode reward: [(0, '50.480'), (1, '41.640')] -[2023-10-12 05:01:10,210][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000043840_44892160.pth... -[2023-10-12 05:01:10,210][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000044032_45088768.pth... -[2023-10-12 05:01:10,240][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000042528_43548672.pth -[2023-10-12 05:01:10,241][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000042336_43352064.pth -[2023-10-12 05:01:12,524][78091] Updated weights for policy 0, policy_version 44040 (0.0008) -[2023-10-12 05:01:12,902][78091] Updated weights for policy 0, policy_version 44050 (0.0008) -[2023-10-12 05:01:13,278][78091] Updated weights for policy 0, policy_version 44060 (0.0008) -[2023-10-12 05:01:14,285][78123] Updated weights for policy 1, policy_version 43850 (0.0009) -[2023-10-12 05:01:14,660][78123] Updated weights for policy 1, policy_version 43860 (0.0009) -[2023-10-12 05:01:15,020][78123] Updated weights for policy 1, policy_version 43870 (0.0009) -[2023-10-12 05:01:15,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 90046464. Throughput: 0: 1601.1, 1: 1587.1. Samples: 22511428. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:01:15,201][77203] Avg episode reward: [(0, '48.610'), (1, '38.160')] -[2023-10-12 05:01:17,620][78091] Updated weights for policy 0, policy_version 44070 (0.0008) -[2023-10-12 05:01:17,987][78091] Updated weights for policy 0, policy_version 44080 (0.0009) -[2023-10-12 05:01:18,360][78091] Updated weights for policy 0, policy_version 44090 (0.0007) -[2023-10-12 05:01:19,288][78123] Updated weights for policy 1, policy_version 43880 (0.0008) -[2023-10-12 05:01:19,666][78123] Updated weights for policy 1, policy_version 43890 (0.0008) -[2023-10-12 05:01:20,039][78123] Updated weights for policy 1, policy_version 43900 (0.0011) -[2023-10-12 05:01:20,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 90112000. Throughput: 0: 1587.1, 1: 1612.7. Samples: 22530548. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:01:20,202][77203] Avg episode reward: [(0, '44.940'), (1, '40.740')] -[2023-10-12 05:01:22,653][78091] Updated weights for policy 0, policy_version 44100 (0.0007) -[2023-10-12 05:01:23,028][78091] Updated weights for policy 0, policy_version 44110 (0.0008) -[2023-10-12 05:01:23,407][78091] Updated weights for policy 0, policy_version 44120 (0.0007) -[2023-10-12 05:01:24,502][78123] Updated weights for policy 1, policy_version 43910 (0.0007) -[2023-10-12 05:01:24,864][78123] Updated weights for policy 1, policy_version 43920 (0.0007) -[2023-10-12 05:01:25,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 90144768. Throughput: 0: 1590.4, 1: 1608.4. Samples: 22549512. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:01:25,201][77203] Avg episode reward: [(0, '38.300'), (1, '39.460')] -[2023-10-12 05:01:25,217][78123] Updated weights for policy 1, policy_version 43930 (0.0008) -[2023-10-12 05:01:27,818][78091] Updated weights for policy 0, policy_version 44130 (0.0007) -[2023-10-12 05:01:28,225][78091] Updated weights for policy 0, policy_version 44140 (0.0008) -[2023-10-12 05:01:28,587][78091] Updated weights for policy 0, policy_version 44150 (0.0008) -[2023-10-12 05:01:28,951][78091] Updated weights for policy 0, policy_version 44160 (0.0009) -[2023-10-12 05:01:29,496][78123] Updated weights for policy 1, policy_version 43940 (0.0009) -[2023-10-12 05:01:29,866][78123] Updated weights for policy 1, policy_version 43950 (0.0007) -[2023-10-12 05:01:30,201][77203] Fps is (10 sec: 9830.6, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 90210304. Throughput: 0: 1621.6, 1: 1589.5. Samples: 22559772. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:01:30,201][77203] Avg episode reward: [(0, '43.340'), (1, '38.410')] -[2023-10-12 05:01:30,228][78123] Updated weights for policy 1, policy_version 43960 (0.0007) -[2023-10-12 05:01:33,342][78091] Updated weights for policy 0, policy_version 44170 (0.0007) -[2023-10-12 05:01:33,717][78091] Updated weights for policy 0, policy_version 44180 (0.0007) -[2023-10-12 05:01:34,095][78091] Updated weights for policy 0, policy_version 44190 (0.0008) -[2023-10-12 05:01:34,474][78123] Updated weights for policy 1, policy_version 43970 (0.0008) -[2023-10-12 05:01:34,832][78123] Updated weights for policy 1, policy_version 43980 (0.0009) -[2023-10-12 05:01:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 90275840. Throughput: 0: 1606.7, 1: 1595.8. Samples: 22578690. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:01:35,201][77203] Avg episode reward: [(0, '40.050'), (1, '40.040')] -[2023-10-12 05:01:35,204][78123] Updated weights for policy 1, policy_version 43990 (0.0008) -[2023-10-12 05:01:35,569][78123] Updated weights for policy 1, policy_version 44000 (0.0007) -[2023-10-12 05:01:38,245][78091] Updated weights for policy 0, policy_version 44200 (0.0008) -[2023-10-12 05:01:38,621][78091] Updated weights for policy 0, policy_version 44210 (0.0008) -[2023-10-12 05:01:38,988][78091] Updated weights for policy 0, policy_version 44220 (0.0007) -[2023-10-12 05:01:39,907][78123] Updated weights for policy 1, policy_version 44010 (0.0007) -[2023-10-12 05:01:40,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 90341376. Throughput: 0: 1596.5, 1: 1608.6. Samples: 22597568. Policy #0 lag: (min: 1.0, avg: 11.5, max: 33.0) -[2023-10-12 05:01:40,202][77203] Avg episode reward: [(0, '38.170'), (1, '39.420')] -[2023-10-12 05:01:40,270][78123] Updated weights for policy 1, policy_version 44020 (0.0008) -[2023-10-12 05:01:40,643][78123] Updated weights for policy 1, policy_version 44030 (0.0009) -[2023-10-12 05:01:43,437][78091] Updated weights for policy 0, policy_version 44230 (0.0007) -[2023-10-12 05:01:43,798][78091] Updated weights for policy 0, policy_version 44240 (0.0007) -[2023-10-12 05:01:44,170][78091] Updated weights for policy 0, policy_version 44250 (0.0007) -[2023-10-12 05:01:45,142][78123] Updated weights for policy 1, policy_version 44040 (0.0010) -[2023-10-12 05:01:45,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 90406912. Throughput: 0: 1612.4, 1: 1588.7. Samples: 22607500. Policy #0 lag: (min: 1.0, avg: 11.5, max: 33.0) -[2023-10-12 05:01:45,202][77203] Avg episode reward: [(0, '35.530'), (1, '39.630')] -[2023-10-12 05:01:45,509][78123] Updated weights for policy 1, policy_version 44050 (0.0009) -[2023-10-12 05:01:45,873][78123] Updated weights for policy 1, policy_version 44060 (0.0009) -[2023-10-12 05:01:48,496][78091] Updated weights for policy 0, policy_version 44260 (0.0007) -[2023-10-12 05:01:48,865][78091] Updated weights for policy 0, policy_version 44270 (0.0010) -[2023-10-12 05:01:49,227][78091] Updated weights for policy 0, policy_version 44280 (0.0009) -[2023-10-12 05:01:50,189][78123] Updated weights for policy 1, policy_version 44070 (0.0009) -[2023-10-12 05:01:50,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 90472448. Throughput: 0: 1614.0, 1: 1587.6. Samples: 22626494. Policy #0 lag: (min: 1.0, avg: 11.5, max: 33.0) -[2023-10-12 05:01:50,202][77203] Avg episode reward: [(0, '36.530'), (1, '41.820')] -[2023-10-12 05:01:50,561][78123] Updated weights for policy 1, policy_version 44080 (0.0008) -[2023-10-12 05:01:50,925][78123] Updated weights for policy 1, policy_version 44090 (0.0007) -[2023-10-12 05:01:53,488][78091] Updated weights for policy 0, policy_version 44290 (0.0007) -[2023-10-12 05:01:53,857][78091] Updated weights for policy 0, policy_version 44300 (0.0008) -[2023-10-12 05:01:54,230][78091] Updated weights for policy 0, policy_version 44310 (0.0009) -[2023-10-12 05:01:54,602][78091] Updated weights for policy 0, policy_version 44320 (0.0007) -[2023-10-12 05:01:55,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 90537984. Throughput: 0: 1597.3, 1: 1607.2. Samples: 22645602. Policy #0 lag: (min: 1.0, avg: 11.5, max: 33.0) -[2023-10-12 05:01:55,202][77203] Avg episode reward: [(0, '41.440'), (1, '38.070')] -[2023-10-12 05:01:55,430][78123] Updated weights for policy 1, policy_version 44100 (0.0007) -[2023-10-12 05:01:55,829][78123] Updated weights for policy 1, policy_version 44110 (0.0007) -[2023-10-12 05:01:56,196][78123] Updated weights for policy 1, policy_version 44120 (0.0007) -[2023-10-12 05:01:58,983][78091] Updated weights for policy 0, policy_version 44330 (0.0007) -[2023-10-12 05:01:59,343][78091] Updated weights for policy 0, policy_version 44340 (0.0007) -[2023-10-12 05:01:59,713][78091] Updated weights for policy 0, policy_version 44350 (0.0007) -[2023-10-12 05:02:00,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 90603520. Throughput: 0: 1614.9, 1: 1583.4. Samples: 22655352. Policy #0 lag: (min: 1.0, avg: 11.5, max: 33.0) -[2023-10-12 05:02:00,202][77203] Avg episode reward: [(0, '40.250'), (1, '40.800')] -[2023-10-12 05:02:00,437][78123] Updated weights for policy 1, policy_version 44130 (0.0008) -[2023-10-12 05:02:00,809][78123] Updated weights for policy 1, policy_version 44140 (0.0010) -[2023-10-12 05:02:01,192][78123] Updated weights for policy 1, policy_version 44150 (0.0007) -[2023-10-12 05:02:01,553][78123] Updated weights for policy 1, policy_version 44160 (0.0008) -[2023-10-12 05:02:03,763][78091] Updated weights for policy 0, policy_version 44360 (0.0009) -[2023-10-12 05:02:04,132][78091] Updated weights for policy 0, policy_version 44370 (0.0010) -[2023-10-12 05:02:04,503][78091] Updated weights for policy 0, policy_version 44380 (0.0008) -[2023-10-12 05:02:05,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 90669056. Throughput: 0: 1621.8, 1: 1577.1. Samples: 22674496. Policy #0 lag: (min: 1.0, avg: 11.5, max: 33.0) -[2023-10-12 05:02:05,202][77203] Avg episode reward: [(0, '37.490'), (1, '40.800')] -[2023-10-12 05:02:05,984][78123] Updated weights for policy 1, policy_version 44170 (0.0007) -[2023-10-12 05:02:06,347][78123] Updated weights for policy 1, policy_version 44180 (0.0007) -[2023-10-12 05:02:06,728][78123] Updated weights for policy 1, policy_version 44190 (0.0009) -[2023-10-12 05:02:08,950][78091] Updated weights for policy 0, policy_version 44390 (0.0009) -[2023-10-12 05:02:09,316][78091] Updated weights for policy 0, policy_version 44400 (0.0008) -[2023-10-12 05:02:09,679][78091] Updated weights for policy 0, policy_version 44410 (0.0009) -[2023-10-12 05:02:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 90734592. Throughput: 0: 1603.2, 1: 1589.3. Samples: 22693174. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:02:10,202][77203] Avg episode reward: [(0, '37.520'), (1, '36.290')] -[2023-10-12 05:02:11,074][78123] Updated weights for policy 1, policy_version 44200 (0.0008) -[2023-10-12 05:02:11,438][78123] Updated weights for policy 1, policy_version 44210 (0.0007) -[2023-10-12 05:02:11,809][78123] Updated weights for policy 1, policy_version 44220 (0.0008) -[2023-10-12 05:02:14,157][78091] Updated weights for policy 0, policy_version 44420 (0.0010) -[2023-10-12 05:02:14,547][78091] Updated weights for policy 0, policy_version 44430 (0.0008) -[2023-10-12 05:02:14,925][78091] Updated weights for policy 0, policy_version 44440 (0.0008) -[2023-10-12 05:02:15,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 90767360. Throughput: 0: 1596.8, 1: 1582.3. Samples: 22702830. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:02:15,201][77203] Avg episode reward: [(0, '39.730'), (1, '39.320')] -[2023-10-12 05:02:15,982][78123] Updated weights for policy 1, policy_version 44230 (0.0009) -[2023-10-12 05:02:16,350][78123] Updated weights for policy 1, policy_version 44240 (0.0008) -[2023-10-12 05:02:16,717][78123] Updated weights for policy 1, policy_version 44250 (0.0009) -[2023-10-12 05:02:19,071][78091] Updated weights for policy 0, policy_version 44450 (0.0009) -[2023-10-12 05:02:19,444][78091] Updated weights for policy 0, policy_version 44460 (0.0008) -[2023-10-12 05:02:19,811][78091] Updated weights for policy 0, policy_version 44470 (0.0009) -[2023-10-12 05:02:20,184][78091] Updated weights for policy 0, policy_version 44480 (0.0007) -[2023-10-12 05:02:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 90865664. Throughput: 0: 1611.3, 1: 1582.2. Samples: 22722400. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:02:20,202][77203] Avg episode reward: [(0, '40.730'), (1, '41.950')] -[2023-10-12 05:02:21,084][78123] Updated weights for policy 1, policy_version 44260 (0.0009) -[2023-10-12 05:02:21,456][78123] Updated weights for policy 1, policy_version 44270 (0.0009) -[2023-10-12 05:02:21,827][78123] Updated weights for policy 1, policy_version 44280 (0.0009) -[2023-10-12 05:02:24,575][78091] Updated weights for policy 0, policy_version 44490 (0.0009) -[2023-10-12 05:02:24,953][78091] Updated weights for policy 0, policy_version 44500 (0.0009) -[2023-10-12 05:02:25,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 90898432. Throughput: 0: 1607.1, 1: 1584.3. Samples: 22741182. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:02:25,202][77203] Avg episode reward: [(0, '36.920'), (1, '38.020')] -[2023-10-12 05:02:25,331][78091] Updated weights for policy 0, policy_version 44510 (0.0008) -[2023-10-12 05:02:26,245][78123] Updated weights for policy 1, policy_version 44290 (0.0009) -[2023-10-12 05:02:26,608][78123] Updated weights for policy 1, policy_version 44300 (0.0009) -[2023-10-12 05:02:26,969][78123] Updated weights for policy 1, policy_version 44310 (0.0008) -[2023-10-12 05:02:27,340][78123] Updated weights for policy 1, policy_version 44320 (0.0008) -[2023-10-12 05:02:29,687][78091] Updated weights for policy 0, policy_version 44520 (0.0009) -[2023-10-12 05:02:30,059][78091] Updated weights for policy 0, policy_version 44530 (0.0007) -[2023-10-12 05:02:30,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 90963968. Throughput: 0: 1593.5, 1: 1580.1. Samples: 22750312. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:02:30,201][77203] Avg episode reward: [(0, '37.480'), (1, '37.290')] -[2023-10-12 05:02:30,432][78091] Updated weights for policy 0, policy_version 44540 (0.0008) -[2023-10-12 05:02:31,707][78123] Updated weights for policy 1, policy_version 44330 (0.0008) -[2023-10-12 05:02:32,082][78123] Updated weights for policy 1, policy_version 44340 (0.0009) -[2023-10-12 05:02:32,439][78123] Updated weights for policy 1, policy_version 44350 (0.0010) -[2023-10-12 05:02:34,623][78091] Updated weights for policy 0, policy_version 44550 (0.0010) -[2023-10-12 05:02:34,989][78091] Updated weights for policy 0, policy_version 44560 (0.0011) -[2023-10-12 05:02:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 91029504. Throughput: 0: 1605.1, 1: 1583.9. Samples: 22769996. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:02:35,202][77203] Avg episode reward: [(0, '40.390'), (1, '42.880')] -[2023-10-12 05:02:35,368][78091] Updated weights for policy 0, policy_version 44570 (0.0009) -[2023-10-12 05:02:36,701][78123] Updated weights for policy 1, policy_version 44360 (0.0009) -[2023-10-12 05:02:37,076][78123] Updated weights for policy 1, policy_version 44370 (0.0009) -[2023-10-12 05:02:37,445][78123] Updated weights for policy 1, policy_version 44380 (0.0008) -[2023-10-12 05:02:39,561][78091] Updated weights for policy 0, policy_version 44580 (0.0010) -[2023-10-12 05:02:39,935][78091] Updated weights for policy 0, policy_version 44590 (0.0009) -[2023-10-12 05:02:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 91095040. Throughput: 0: 1610.2, 1: 1586.5. Samples: 22789450. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:02:40,201][77203] Avg episode reward: [(0, '39.770'), (1, '38.130')] -[2023-10-12 05:02:40,306][78091] Updated weights for policy 0, policy_version 44600 (0.0010) -[2023-10-12 05:02:41,589][78123] Updated weights for policy 1, policy_version 44390 (0.0008) -[2023-10-12 05:02:41,967][78123] Updated weights for policy 1, policy_version 44400 (0.0009) -[2023-10-12 05:02:42,345][78123] Updated weights for policy 1, policy_version 44410 (0.0010) -[2023-10-12 05:02:44,659][78091] Updated weights for policy 0, policy_version 44610 (0.0008) -[2023-10-12 05:02:45,035][78091] Updated weights for policy 0, policy_version 44620 (0.0008) -[2023-10-12 05:02:45,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 91160576. Throughput: 0: 1591.1, 1: 1590.5. Samples: 22798524. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 05:02:45,201][77203] Avg episode reward: [(0, '41.250'), (1, '39.560')] -[2023-10-12 05:02:45,401][78091] Updated weights for policy 0, policy_version 44630 (0.0010) -[2023-10-12 05:02:45,772][78091] Updated weights for policy 0, policy_version 44640 (0.0007) -[2023-10-12 05:02:46,584][78123] Updated weights for policy 1, policy_version 44420 (0.0009) -[2023-10-12 05:02:46,957][78123] Updated weights for policy 1, policy_version 44430 (0.0009) -[2023-10-12 05:02:47,331][78123] Updated weights for policy 1, policy_version 44440 (0.0007) -[2023-10-12 05:02:50,128][78091] Updated weights for policy 0, policy_version 44650 (0.0008) -[2023-10-12 05:02:50,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 91226112. Throughput: 0: 1598.1, 1: 1595.2. Samples: 22818196. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 05:02:50,201][77203] Avg episode reward: [(0, '46.310'), (1, '43.380')] -[2023-10-12 05:02:50,494][78091] Updated weights for policy 0, policy_version 44660 (0.0009) -[2023-10-12 05:02:50,867][78091] Updated weights for policy 0, policy_version 44670 (0.0008) -[2023-10-12 05:02:51,506][78123] Updated weights for policy 1, policy_version 44450 (0.0008) -[2023-10-12 05:02:51,866][78123] Updated weights for policy 1, policy_version 44460 (0.0009) -[2023-10-12 05:02:52,226][78123] Updated weights for policy 1, policy_version 44470 (0.0009) -[2023-10-12 05:02:52,593][78123] Updated weights for policy 1, policy_version 44480 (0.0009) -[2023-10-12 05:02:55,065][78091] Updated weights for policy 0, policy_version 44680 (0.0008) -[2023-10-12 05:02:55,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 91291648. Throughput: 0: 1617.6, 1: 1593.3. Samples: 22837668. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 05:02:55,201][77203] Avg episode reward: [(0, '46.920'), (1, '36.000')] -[2023-10-12 05:02:55,436][78091] Updated weights for policy 0, policy_version 44690 (0.0009) -[2023-10-12 05:02:55,800][78091] Updated weights for policy 0, policy_version 44700 (0.0009) -[2023-10-12 05:02:57,034][78123] Updated weights for policy 1, policy_version 44490 (0.0007) -[2023-10-12 05:02:57,407][78123] Updated weights for policy 1, policy_version 44500 (0.0010) -[2023-10-12 05:02:57,780][78123] Updated weights for policy 1, policy_version 44510 (0.0010) -[2023-10-12 05:03:00,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 91357184. Throughput: 0: 1598.2, 1: 1600.3. Samples: 22846764. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 05:03:00,202][77203] Avg episode reward: [(0, '42.120'), (1, '38.120')] -[2023-10-12 05:03:00,220][78091] Updated weights for policy 0, policy_version 44710 (0.0009) -[2023-10-12 05:03:00,600][78091] Updated weights for policy 0, policy_version 44720 (0.0008) -[2023-10-12 05:03:00,968][78091] Updated weights for policy 0, policy_version 44730 (0.0008) -[2023-10-12 05:03:02,174][78123] Updated weights for policy 1, policy_version 44520 (0.0011) -[2023-10-12 05:03:02,540][78123] Updated weights for policy 1, policy_version 44530 (0.0011) -[2023-10-12 05:03:02,906][78123] Updated weights for policy 1, policy_version 44540 (0.0010) -[2023-10-12 05:03:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 91422720. Throughput: 0: 1594.4, 1: 1590.4. Samples: 22865718. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 05:03:05,202][77203] Avg episode reward: [(0, '42.510'), (1, '41.480')] -[2023-10-12 05:03:05,346][78091] Updated weights for policy 0, policy_version 44740 (0.0008) -[2023-10-12 05:03:05,714][78091] Updated weights for policy 0, policy_version 44750 (0.0007) -[2023-10-12 05:03:06,091][78091] Updated weights for policy 0, policy_version 44760 (0.0008) -[2023-10-12 05:03:07,307][78123] Updated weights for policy 1, policy_version 44550 (0.0010) -[2023-10-12 05:03:07,679][78123] Updated weights for policy 1, policy_version 44560 (0.0010) -[2023-10-12 05:03:08,041][78123] Updated weights for policy 1, policy_version 44570 (0.0009) -[2023-10-12 05:03:10,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 91488256. Throughput: 0: 1604.1, 1: 1598.5. Samples: 22885300. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 05:03:10,201][77203] Avg episode reward: [(0, '46.340'), (1, '34.010')] -[2023-10-12 05:03:10,208][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000044576_45645824.pth... -[2023-10-12 05:03:10,243][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000043104_44138496.pth -[2023-10-12 05:03:10,249][77950] Saving a milestone ./train_atari/atari_hero_APPO/checkpoint_p1/milestones/checkpoint_000044576_45645824.pth -[2023-10-12 05:03:10,357][78091] Updated weights for policy 0, policy_version 44770 (0.0007) -[2023-10-12 05:03:10,731][78091] Updated weights for policy 0, policy_version 44780 (0.0008) -[2023-10-12 05:03:11,108][78091] Updated weights for policy 0, policy_version 44790 (0.0008) -[2023-10-12 05:03:11,479][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000044800_45875200.pth... -[2023-10-12 05:03:11,480][78091] Updated weights for policy 0, policy_version 44800 (0.0009) -[2023-10-12 05:03:11,517][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000043296_44335104.pth -[2023-10-12 05:03:11,523][77792] Saving a milestone ./train_atari/atari_hero_APPO/checkpoint_p0/milestones/checkpoint_000044800_45875200.pth -[2023-10-12 05:03:12,341][78123] Updated weights for policy 1, policy_version 44580 (0.0007) -[2023-10-12 05:03:12,708][78123] Updated weights for policy 1, policy_version 44590 (0.0007) -[2023-10-12 05:03:13,081][78123] Updated weights for policy 1, policy_version 44600 (0.0007) -[2023-10-12 05:03:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 91553792. Throughput: 0: 1589.1, 1: 1615.8. Samples: 22894530. Policy #0 lag: (min: 31.0, avg: 42.0, max: 63.0) -[2023-10-12 05:03:15,202][77203] Avg episode reward: [(0, '40.220'), (1, '41.050')] -[2023-10-12 05:03:15,803][78091] Updated weights for policy 0, policy_version 44810 (0.0009) -[2023-10-12 05:03:16,175][78091] Updated weights for policy 0, policy_version 44820 (0.0008) -[2023-10-12 05:03:16,555][78091] Updated weights for policy 0, policy_version 44830 (0.0009) -[2023-10-12 05:03:17,212][78123] Updated weights for policy 1, policy_version 44610 (0.0007) -[2023-10-12 05:03:17,580][78123] Updated weights for policy 1, policy_version 44620 (0.0010) -[2023-10-12 05:03:17,945][78123] Updated weights for policy 1, policy_version 44630 (0.0007) -[2023-10-12 05:03:18,317][78123] Updated weights for policy 1, policy_version 44640 (0.0009) -[2023-10-12 05:03:20,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 91619328. Throughput: 0: 1591.1, 1: 1601.6. Samples: 22913666. Policy #0 lag: (min: 31.0, avg: 42.0, max: 63.0) -[2023-10-12 05:03:20,202][77203] Avg episode reward: [(0, '42.560'), (1, '43.870')] -[2023-10-12 05:03:20,861][78091] Updated weights for policy 0, policy_version 44840 (0.0010) -[2023-10-12 05:03:21,240][78091] Updated weights for policy 0, policy_version 44850 (0.0009) -[2023-10-12 05:03:21,607][78091] Updated weights for policy 0, policy_version 44860 (0.0007) -[2023-10-12 05:03:22,729][78123] Updated weights for policy 1, policy_version 44650 (0.0010) -[2023-10-12 05:03:23,101][78123] Updated weights for policy 1, policy_version 44660 (0.0008) -[2023-10-12 05:03:23,461][78123] Updated weights for policy 1, policy_version 44670 (0.0009) -[2023-10-12 05:03:25,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 91684864. Throughput: 0: 1603.9, 1: 1592.7. Samples: 22933298. Policy #0 lag: (min: 31.0, avg: 42.0, max: 63.0) -[2023-10-12 05:03:25,202][77203] Avg episode reward: [(0, '53.550'), (1, '36.690')] -[2023-10-12 05:03:25,757][78091] Updated weights for policy 0, policy_version 44870 (0.0011) -[2023-10-12 05:03:26,121][78091] Updated weights for policy 0, policy_version 44880 (0.0010) -[2023-10-12 05:03:26,489][78091] Updated weights for policy 0, policy_version 44890 (0.0008) -[2023-10-12 05:03:28,120][78123] Updated weights for policy 1, policy_version 44680 (0.0010) -[2023-10-12 05:03:28,486][78123] Updated weights for policy 1, policy_version 44690 (0.0011) -[2023-10-12 05:03:28,854][78123] Updated weights for policy 1, policy_version 44700 (0.0011) -[2023-10-12 05:03:30,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 91750400. Throughput: 0: 1590.6, 1: 1617.3. Samples: 22942882. Policy #0 lag: (min: 31.0, avg: 42.0, max: 63.0) -[2023-10-12 05:03:30,202][77203] Avg episode reward: [(0, '41.200'), (1, '43.360')] -[2023-10-12 05:03:30,933][78091] Updated weights for policy 0, policy_version 44900 (0.0010) -[2023-10-12 05:03:31,303][78091] Updated weights for policy 0, policy_version 44910 (0.0008) -[2023-10-12 05:03:31,678][78091] Updated weights for policy 0, policy_version 44920 (0.0007) -[2023-10-12 05:03:33,192][78123] Updated weights for policy 1, policy_version 44710 (0.0008) -[2023-10-12 05:03:33,554][78123] Updated weights for policy 1, policy_version 44720 (0.0009) -[2023-10-12 05:03:33,929][78123] Updated weights for policy 1, policy_version 44730 (0.0010) -[2023-10-12 05:03:35,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 91815936. Throughput: 0: 1587.7, 1: 1591.6. Samples: 22961266. Policy #0 lag: (min: 31.0, avg: 42.0, max: 63.0) -[2023-10-12 05:03:35,202][77203] Avg episode reward: [(0, '43.540'), (1, '43.010')] -[2023-10-12 05:03:36,089][78091] Updated weights for policy 0, policy_version 44930 (0.0008) -[2023-10-12 05:03:36,453][78091] Updated weights for policy 0, policy_version 44940 (0.0008) -[2023-10-12 05:03:36,823][78091] Updated weights for policy 0, policy_version 44950 (0.0008) -[2023-10-12 05:03:37,203][78091] Updated weights for policy 0, policy_version 44960 (0.0007) -[2023-10-12 05:03:38,105][78123] Updated weights for policy 1, policy_version 44740 (0.0009) -[2023-10-12 05:03:38,483][78123] Updated weights for policy 1, policy_version 44750 (0.0008) -[2023-10-12 05:03:38,844][78123] Updated weights for policy 1, policy_version 44760 (0.0008) -[2023-10-12 05:03:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 91881472. Throughput: 0: 1589.6, 1: 1585.6. Samples: 22980552. Policy #0 lag: (min: 31.0, avg: 42.0, max: 63.0) -[2023-10-12 05:03:40,201][77203] Avg episode reward: [(0, '51.660'), (1, '38.710')] -[2023-10-12 05:03:41,357][78091] Updated weights for policy 0, policy_version 44970 (0.0009) -[2023-10-12 05:03:41,730][78091] Updated weights for policy 0, policy_version 44980 (0.0008) -[2023-10-12 05:03:42,103][78091] Updated weights for policy 0, policy_version 44990 (0.0009) -[2023-10-12 05:03:43,207][78123] Updated weights for policy 1, policy_version 44770 (0.0011) -[2023-10-12 05:03:43,571][78123] Updated weights for policy 1, policy_version 44780 (0.0010) -[2023-10-12 05:03:43,950][78123] Updated weights for policy 1, policy_version 44790 (0.0011) -[2023-10-12 05:03:44,320][78123] Updated weights for policy 1, policy_version 44800 (0.0009) -[2023-10-12 05:03:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 91947008. Throughput: 0: 1586.8, 1: 1606.7. Samples: 22990470. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 05:03:45,201][77203] Avg episode reward: [(0, '44.530'), (1, '46.020')] -[2023-10-12 05:03:46,383][78091] Updated weights for policy 0, policy_version 45000 (0.0009) -[2023-10-12 05:03:46,759][78091] Updated weights for policy 0, policy_version 45010 (0.0008) -[2023-10-12 05:03:47,121][78091] Updated weights for policy 0, policy_version 45020 (0.0007) -[2023-10-12 05:03:48,599][78123] Updated weights for policy 1, policy_version 44810 (0.0008) -[2023-10-12 05:03:48,965][78123] Updated weights for policy 1, policy_version 44820 (0.0009) -[2023-10-12 05:03:49,336][78123] Updated weights for policy 1, policy_version 44830 (0.0011) -[2023-10-12 05:03:50,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 92012544. Throughput: 0: 1593.8, 1: 1600.1. Samples: 23009444. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 05:03:50,202][77203] Avg episode reward: [(0, '42.100'), (1, '42.310')] -[2023-10-12 05:03:51,503][78091] Updated weights for policy 0, policy_version 45030 (0.0010) -[2023-10-12 05:03:51,885][78091] Updated weights for policy 0, policy_version 45040 (0.0008) -[2023-10-12 05:03:52,269][78091] Updated weights for policy 0, policy_version 45050 (0.0007) -[2023-10-12 05:03:53,643][78123] Updated weights for policy 1, policy_version 44840 (0.0009) -[2023-10-12 05:03:54,007][78123] Updated weights for policy 1, policy_version 44850 (0.0010) -[2023-10-12 05:03:54,385][78123] Updated weights for policy 1, policy_version 44860 (0.0007) -[2023-10-12 05:03:55,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 92078080. Throughput: 0: 1599.8, 1: 1578.8. Samples: 23028336. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 05:03:55,202][77203] Avg episode reward: [(0, '49.760'), (1, '40.490')] -[2023-10-12 05:03:56,235][78091] Updated weights for policy 0, policy_version 45060 (0.0009) -[2023-10-12 05:03:56,608][78091] Updated weights for policy 0, policy_version 45070 (0.0009) -[2023-10-12 05:03:56,990][78091] Updated weights for policy 0, policy_version 45080 (0.0009) -[2023-10-12 05:03:58,818][78123] Updated weights for policy 1, policy_version 44870 (0.0008) -[2023-10-12 05:03:59,192][78123] Updated weights for policy 1, policy_version 44880 (0.0008) -[2023-10-12 05:03:59,562][78123] Updated weights for policy 1, policy_version 44890 (0.0008) -[2023-10-12 05:04:00,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 92143616. Throughput: 0: 1604.2, 1: 1589.3. Samples: 23038238. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 05:04:00,201][77203] Avg episode reward: [(0, '45.550'), (1, '43.350')] -[2023-10-12 05:04:01,366][78091] Updated weights for policy 0, policy_version 45090 (0.0008) -[2023-10-12 05:04:01,736][78091] Updated weights for policy 0, policy_version 45100 (0.0007) -[2023-10-12 05:04:02,097][78091] Updated weights for policy 0, policy_version 45110 (0.0007) -[2023-10-12 05:04:02,468][78091] Updated weights for policy 0, policy_version 45120 (0.0009) -[2023-10-12 05:04:03,695][78123] Updated weights for policy 1, policy_version 44900 (0.0009) -[2023-10-12 05:04:04,064][78123] Updated weights for policy 1, policy_version 44910 (0.0009) -[2023-10-12 05:04:04,420][78123] Updated weights for policy 1, policy_version 44920 (0.0008) -[2023-10-12 05:04:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 92209152. Throughput: 0: 1604.1, 1: 1599.3. Samples: 23057818. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 05:04:05,202][77203] Avg episode reward: [(0, '43.670'), (1, '39.640')] -[2023-10-12 05:04:06,599][78091] Updated weights for policy 0, policy_version 45130 (0.0008) -[2023-10-12 05:04:06,972][78091] Updated weights for policy 0, policy_version 45140 (0.0008) -[2023-10-12 05:04:07,339][78091] Updated weights for policy 0, policy_version 45150 (0.0007) -[2023-10-12 05:04:08,715][78123] Updated weights for policy 1, policy_version 44930 (0.0007) -[2023-10-12 05:04:09,083][78123] Updated weights for policy 1, policy_version 44940 (0.0009) -[2023-10-12 05:04:09,454][78123] Updated weights for policy 1, policy_version 44950 (0.0010) -[2023-10-12 05:04:09,809][78123] Updated weights for policy 1, policy_version 44960 (0.0010) -[2023-10-12 05:04:10,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 92274688. Throughput: 0: 1603.8, 1: 1588.9. Samples: 23076972. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 05:04:10,201][77203] Avg episode reward: [(0, '44.160'), (1, '38.790')] -[2023-10-12 05:04:11,685][78091] Updated weights for policy 0, policy_version 45160 (0.0008) -[2023-10-12 05:04:12,051][78091] Updated weights for policy 0, policy_version 45170 (0.0010) -[2023-10-12 05:04:12,418][78091] Updated weights for policy 0, policy_version 45180 (0.0009) -[2023-10-12 05:04:14,144][78123] Updated weights for policy 1, policy_version 44970 (0.0010) -[2023-10-12 05:04:14,508][78123] Updated weights for policy 1, policy_version 44980 (0.0008) -[2023-10-12 05:04:14,877][78123] Updated weights for policy 1, policy_version 44990 (0.0007) -[2023-10-12 05:04:15,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 92340224. Throughput: 0: 1609.6, 1: 1587.3. Samples: 23086744. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:04:15,201][77203] Avg episode reward: [(0, '45.770'), (1, '38.220')] -[2023-10-12 05:04:16,580][78091] Updated weights for policy 0, policy_version 45190 (0.0008) -[2023-10-12 05:04:16,949][78091] Updated weights for policy 0, policy_version 45200 (0.0008) -[2023-10-12 05:04:17,314][78091] Updated weights for policy 0, policy_version 45210 (0.0008) -[2023-10-12 05:04:19,212][78123] Updated weights for policy 1, policy_version 45000 (0.0008) -[2023-10-12 05:04:19,575][78123] Updated weights for policy 1, policy_version 45010 (0.0009) -[2023-10-12 05:04:19,941][78123] Updated weights for policy 1, policy_version 45020 (0.0008) -[2023-10-12 05:04:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 92405760. Throughput: 0: 1618.4, 1: 1614.4. Samples: 23106742. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:04:20,201][77203] Avg episode reward: [(0, '44.720'), (1, '43.480')] -[2023-10-12 05:04:21,571][78091] Updated weights for policy 0, policy_version 45220 (0.0009) -[2023-10-12 05:04:21,938][78091] Updated weights for policy 0, policy_version 45230 (0.0009) -[2023-10-12 05:04:22,311][78091] Updated weights for policy 0, policy_version 45240 (0.0009) -[2023-10-12 05:04:24,328][78123] Updated weights for policy 1, policy_version 45030 (0.0008) -[2023-10-12 05:04:24,698][78123] Updated weights for policy 1, policy_version 45040 (0.0007) -[2023-10-12 05:04:25,065][78123] Updated weights for policy 1, policy_version 45050 (0.0008) -[2023-10-12 05:04:25,201][77203] Fps is (10 sec: 9830.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 92438528. Throughput: 0: 1615.2, 1: 1609.6. Samples: 23125668. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:04:25,202][77203] Avg episode reward: [(0, '44.310'), (1, '37.620')] -[2023-10-12 05:04:26,454][78091] Updated weights for policy 0, policy_version 45250 (0.0008) -[2023-10-12 05:04:26,824][78091] Updated weights for policy 0, policy_version 45260 (0.0008) -[2023-10-12 05:04:27,200][78091] Updated weights for policy 0, policy_version 45270 (0.0009) -[2023-10-12 05:04:27,570][78091] Updated weights for policy 0, policy_version 45280 (0.0009) -[2023-10-12 05:04:29,290][78123] Updated weights for policy 1, policy_version 45060 (0.0008) -[2023-10-12 05:04:29,651][78123] Updated weights for policy 1, policy_version 45070 (0.0007) -[2023-10-12 05:04:30,017][78123] Updated weights for policy 1, policy_version 45080 (0.0007) -[2023-10-12 05:04:30,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 92504064. Throughput: 0: 1616.4, 1: 1597.6. Samples: 23135100. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:04:30,201][77203] Avg episode reward: [(0, '45.340'), (1, '44.150')] -[2023-10-12 05:04:31,860][78091] Updated weights for policy 0, policy_version 45290 (0.0008) -[2023-10-12 05:04:32,233][78091] Updated weights for policy 0, policy_version 45300 (0.0007) -[2023-10-12 05:04:32,600][78091] Updated weights for policy 0, policy_version 45310 (0.0010) -[2023-10-12 05:04:34,484][78123] Updated weights for policy 1, policy_version 45090 (0.0009) -[2023-10-12 05:04:34,847][78123] Updated weights for policy 1, policy_version 45100 (0.0008) -[2023-10-12 05:04:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 92569600. Throughput: 0: 1616.6, 1: 1607.7. Samples: 23154536. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:04:35,202][77203] Avg episode reward: [(0, '43.300'), (1, '42.260')] -[2023-10-12 05:04:35,215][78123] Updated weights for policy 1, policy_version 45110 (0.0007) -[2023-10-12 05:04:35,590][78123] Updated weights for policy 1, policy_version 45120 (0.0008) -[2023-10-12 05:04:37,099][78091] Updated weights for policy 0, policy_version 45320 (0.0008) -[2023-10-12 05:04:37,470][78091] Updated weights for policy 0, policy_version 45330 (0.0009) -[2023-10-12 05:04:37,849][78091] Updated weights for policy 0, policy_version 45340 (0.0010) -[2023-10-12 05:04:39,906][78123] Updated weights for policy 1, policy_version 45130 (0.0010) -[2023-10-12 05:04:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 92635136. Throughput: 0: 1606.8, 1: 1622.0. Samples: 23173630. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:04:40,201][77203] Avg episode reward: [(0, '48.950'), (1, '39.530')] -[2023-10-12 05:04:40,274][78123] Updated weights for policy 1, policy_version 45140 (0.0009) -[2023-10-12 05:04:40,647][78123] Updated weights for policy 1, policy_version 45150 (0.0008) -[2023-10-12 05:04:42,220][78091] Updated weights for policy 0, policy_version 45350 (0.0007) -[2023-10-12 05:04:42,596][78091] Updated weights for policy 0, policy_version 45360 (0.0007) -[2023-10-12 05:04:42,979][78091] Updated weights for policy 0, policy_version 45370 (0.0007) -[2023-10-12 05:04:45,048][78123] Updated weights for policy 1, policy_version 45160 (0.0008) -[2023-10-12 05:04:45,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 92700672. Throughput: 0: 1613.2, 1: 1601.3. Samples: 23182890. Policy #0 lag: (min: 30.0, avg: 47.0, max: 48.0) -[2023-10-12 05:04:45,202][77203] Avg episode reward: [(0, '48.000'), (1, '45.610')] -[2023-10-12 05:04:45,420][78123] Updated weights for policy 1, policy_version 45170 (0.0009) -[2023-10-12 05:04:45,777][78123] Updated weights for policy 1, policy_version 45180 (0.0010) -[2023-10-12 05:04:47,304][78091] Updated weights for policy 0, policy_version 45380 (0.0009) -[2023-10-12 05:04:47,672][78091] Updated weights for policy 0, policy_version 45390 (0.0010) -[2023-10-12 05:04:48,043][78091] Updated weights for policy 0, policy_version 45400 (0.0009) -[2023-10-12 05:04:50,135][78123] Updated weights for policy 1, policy_version 45190 (0.0011) -[2023-10-12 05:04:50,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 92766208. Throughput: 0: 1599.5, 1: 1599.5. Samples: 23201774. Policy #0 lag: (min: 30.0, avg: 47.0, max: 48.0) -[2023-10-12 05:04:50,201][77203] Avg episode reward: [(0, '47.760'), (1, '42.230')] -[2023-10-12 05:04:50,501][78123] Updated weights for policy 1, policy_version 45200 (0.0011) -[2023-10-12 05:04:50,868][78123] Updated weights for policy 1, policy_version 45210 (0.0008) -[2023-10-12 05:04:52,325][78091] Updated weights for policy 0, policy_version 45410 (0.0008) -[2023-10-12 05:04:52,693][78091] Updated weights for policy 0, policy_version 45420 (0.0007) -[2023-10-12 05:04:53,068][78091] Updated weights for policy 0, policy_version 45430 (0.0008) -[2023-10-12 05:04:53,432][78091] Updated weights for policy 0, policy_version 45440 (0.0007) -[2023-10-12 05:04:55,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 92831744. Throughput: 0: 1597.6, 1: 1612.1. Samples: 23221412. Policy #0 lag: (min: 30.0, avg: 47.0, max: 48.0) -[2023-10-12 05:04:55,202][77203] Avg episode reward: [(0, '39.000'), (1, '37.240')] -[2023-10-12 05:04:55,215][78123] Updated weights for policy 1, policy_version 45220 (0.0009) -[2023-10-12 05:04:55,583][78123] Updated weights for policy 1, policy_version 45230 (0.0010) -[2023-10-12 05:04:55,946][78123] Updated weights for policy 1, policy_version 45240 (0.0011) -[2023-10-12 05:04:57,643][78091] Updated weights for policy 0, policy_version 45450 (0.0007) -[2023-10-12 05:04:58,013][78091] Updated weights for policy 0, policy_version 45460 (0.0007) -[2023-10-12 05:04:58,386][78091] Updated weights for policy 0, policy_version 45470 (0.0008) -[2023-10-12 05:05:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 92897280. Throughput: 0: 1614.1, 1: 1584.0. Samples: 23230656. Policy #0 lag: (min: 30.0, avg: 47.0, max: 48.0) -[2023-10-12 05:05:00,201][77203] Avg episode reward: [(0, '45.590'), (1, '45.620')] -[2023-10-12 05:05:00,275][78123] Updated weights for policy 1, policy_version 45250 (0.0010) -[2023-10-12 05:05:00,683][78123] Updated weights for policy 1, policy_version 45260 (0.0007) -[2023-10-12 05:05:01,059][78123] Updated weights for policy 1, policy_version 45270 (0.0007) -[2023-10-12 05:05:01,416][78123] Updated weights for policy 1, policy_version 45280 (0.0008) -[2023-10-12 05:05:02,754][78091] Updated weights for policy 0, policy_version 45480 (0.0007) -[2023-10-12 05:05:03,133][78091] Updated weights for policy 0, policy_version 45490 (0.0008) -[2023-10-12 05:05:03,497][78091] Updated weights for policy 0, policy_version 45500 (0.0009) -[2023-10-12 05:05:05,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 92962816. Throughput: 0: 1593.9, 1: 1575.2. Samples: 23249354. Policy #0 lag: (min: 30.0, avg: 47.0, max: 48.0) -[2023-10-12 05:05:05,202][77203] Avg episode reward: [(0, '49.810'), (1, '42.060')] -[2023-10-12 05:05:05,845][78123] Updated weights for policy 1, policy_version 45290 (0.0008) -[2023-10-12 05:05:06,212][78123] Updated weights for policy 1, policy_version 45300 (0.0007) -[2023-10-12 05:05:06,576][78123] Updated weights for policy 1, policy_version 45310 (0.0009) -[2023-10-12 05:05:07,887][78091] Updated weights for policy 0, policy_version 45510 (0.0009) -[2023-10-12 05:05:08,265][78091] Updated weights for policy 0, policy_version 45520 (0.0009) -[2023-10-12 05:05:08,638][78091] Updated weights for policy 0, policy_version 45530 (0.0007) -[2023-10-12 05:05:10,201][77203] Fps is (10 sec: 13106.8, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 93028352. Throughput: 0: 1593.1, 1: 1584.9. Samples: 23268678. Policy #0 lag: (min: 30.0, avg: 47.0, max: 48.0) -[2023-10-12 05:05:10,202][77203] Avg episode reward: [(0, '43.350'), (1, '40.220')] -[2023-10-12 05:05:10,213][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000045536_46628864.pth... -[2023-10-12 05:05:10,214][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000045312_46399488.pth... -[2023-10-12 05:05:10,248][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000043840_44892160.pth -[2023-10-12 05:05:10,256][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000044032_45088768.pth -[2023-10-12 05:05:10,840][78123] Updated weights for policy 1, policy_version 45320 (0.0008) -[2023-10-12 05:05:11,209][78123] Updated weights for policy 1, policy_version 45330 (0.0008) -[2023-10-12 05:05:11,574][78123] Updated weights for policy 1, policy_version 45340 (0.0007) -[2023-10-12 05:05:12,893][78091] Updated weights for policy 0, policy_version 45540 (0.0010) -[2023-10-12 05:05:13,269][78091] Updated weights for policy 0, policy_version 45550 (0.0010) -[2023-10-12 05:05:13,652][78091] Updated weights for policy 0, policy_version 45560 (0.0010) -[2023-10-12 05:05:15,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 93093888. Throughput: 0: 1618.0, 1: 1570.9. Samples: 23278598. Policy #0 lag: (min: 31.0, avg: 31.3, max: 42.0) -[2023-10-12 05:05:15,201][77203] Avg episode reward: [(0, '44.270'), (1, '45.930')] -[2023-10-12 05:05:15,795][78123] Updated weights for policy 1, policy_version 45350 (0.0008) -[2023-10-12 05:05:16,166][78123] Updated weights for policy 1, policy_version 45360 (0.0008) -[2023-10-12 05:05:16,530][78123] Updated weights for policy 1, policy_version 45370 (0.0009) -[2023-10-12 05:05:17,870][78091] Updated weights for policy 0, policy_version 45570 (0.0008) -[2023-10-12 05:05:18,254][78091] Updated weights for policy 0, policy_version 45580 (0.0008) -[2023-10-12 05:05:18,622][78091] Updated weights for policy 0, policy_version 45590 (0.0011) -[2023-10-12 05:05:18,994][78091] Updated weights for policy 0, policy_version 45600 (0.0008) -[2023-10-12 05:05:20,201][77203] Fps is (10 sec: 13107.6, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 93159424. Throughput: 0: 1600.1, 1: 1578.3. Samples: 23297562. Policy #0 lag: (min: 31.0, avg: 31.3, max: 42.0) -[2023-10-12 05:05:20,201][77203] Avg episode reward: [(0, '47.080'), (1, '40.790')] -[2023-10-12 05:05:20,811][78123] Updated weights for policy 1, policy_version 45380 (0.0009) -[2023-10-12 05:05:21,181][78123] Updated weights for policy 1, policy_version 45390 (0.0008) -[2023-10-12 05:05:21,547][78123] Updated weights for policy 1, policy_version 45400 (0.0009) -[2023-10-12 05:05:23,235][78091] Updated weights for policy 0, policy_version 45610 (0.0007) -[2023-10-12 05:05:23,597][78091] Updated weights for policy 0, policy_version 45620 (0.0007) -[2023-10-12 05:05:23,972][78091] Updated weights for policy 0, policy_version 45630 (0.0009) -[2023-10-12 05:05:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 93224960. Throughput: 0: 1595.6, 1: 1585.2. Samples: 23316762. Policy #0 lag: (min: 31.0, avg: 31.3, max: 42.0) -[2023-10-12 05:05:25,201][77203] Avg episode reward: [(0, '40.050'), (1, '42.540')] -[2023-10-12 05:05:25,794][78123] Updated weights for policy 1, policy_version 45410 (0.0009) -[2023-10-12 05:05:26,165][78123] Updated weights for policy 1, policy_version 45420 (0.0008) -[2023-10-12 05:05:26,537][78123] Updated weights for policy 1, policy_version 45430 (0.0010) -[2023-10-12 05:05:26,899][78123] Updated weights for policy 1, policy_version 45440 (0.0009) -[2023-10-12 05:05:28,374][78091] Updated weights for policy 0, policy_version 45640 (0.0009) -[2023-10-12 05:05:28,759][78091] Updated weights for policy 0, policy_version 45650 (0.0008) -[2023-10-12 05:05:29,126][78091] Updated weights for policy 0, policy_version 45660 (0.0009) -[2023-10-12 05:05:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 93290496. Throughput: 0: 1612.7, 1: 1581.7. Samples: 23326638. Policy #0 lag: (min: 31.0, avg: 31.3, max: 42.0) -[2023-10-12 05:05:30,202][77203] Avg episode reward: [(0, '41.520'), (1, '39.550')] -[2023-10-12 05:05:31,217][78123] Updated weights for policy 1, policy_version 45450 (0.0007) -[2023-10-12 05:05:31,593][78123] Updated weights for policy 1, policy_version 45460 (0.0008) -[2023-10-12 05:05:31,952][78123] Updated weights for policy 1, policy_version 45470 (0.0007) -[2023-10-12 05:05:33,489][78091] Updated weights for policy 0, policy_version 45670 (0.0009) -[2023-10-12 05:05:33,868][78091] Updated weights for policy 0, policy_version 45680 (0.0009) -[2023-10-12 05:05:34,235][78091] Updated weights for policy 0, policy_version 45690 (0.0009) -[2023-10-12 05:05:35,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 93356032. Throughput: 0: 1611.0, 1: 1585.6. Samples: 23345620. Policy #0 lag: (min: 31.0, avg: 31.3, max: 42.0) -[2023-10-12 05:05:35,202][77203] Avg episode reward: [(0, '49.100'), (1, '39.400')] -[2023-10-12 05:05:36,339][78123] Updated weights for policy 1, policy_version 45480 (0.0009) -[2023-10-12 05:05:36,707][78123] Updated weights for policy 1, policy_version 45490 (0.0008) -[2023-10-12 05:05:37,072][78123] Updated weights for policy 1, policy_version 45500 (0.0008) -[2023-10-12 05:05:38,456][78091] Updated weights for policy 0, policy_version 45700 (0.0007) -[2023-10-12 05:05:38,823][78091] Updated weights for policy 0, policy_version 45710 (0.0008) -[2023-10-12 05:05:39,195][78091] Updated weights for policy 0, policy_version 45720 (0.0010) -[2023-10-12 05:05:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 93421568. Throughput: 0: 1594.0, 1: 1588.9. Samples: 23364640. Policy #0 lag: (min: 31.0, avg: 31.3, max: 42.0) -[2023-10-12 05:05:40,202][77203] Avg episode reward: [(0, '55.750'), (1, '43.210')] -[2023-10-12 05:05:41,426][78123] Updated weights for policy 1, policy_version 45510 (0.0007) -[2023-10-12 05:05:41,803][78123] Updated weights for policy 1, policy_version 45520 (0.0007) -[2023-10-12 05:05:42,164][78123] Updated weights for policy 1, policy_version 45530 (0.0007) -[2023-10-12 05:05:43,617][78091] Updated weights for policy 0, policy_version 45730 (0.0009) -[2023-10-12 05:05:43,995][78091] Updated weights for policy 0, policy_version 45740 (0.0009) -[2023-10-12 05:05:44,357][78091] Updated weights for policy 0, policy_version 45750 (0.0008) -[2023-10-12 05:05:44,733][78091] Updated weights for policy 0, policy_version 45760 (0.0007) -[2023-10-12 05:05:45,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 93487104. Throughput: 0: 1601.6, 1: 1594.5. Samples: 23374482. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:05:45,202][77203] Avg episode reward: [(0, '42.520'), (1, '42.130')] -[2023-10-12 05:05:46,481][78123] Updated weights for policy 1, policy_version 45540 (0.0008) -[2023-10-12 05:05:46,851][78123] Updated weights for policy 1, policy_version 45550 (0.0009) -[2023-10-12 05:05:47,229][78123] Updated weights for policy 1, policy_version 45560 (0.0008) -[2023-10-12 05:05:48,938][78091] Updated weights for policy 0, policy_version 45770 (0.0010) -[2023-10-12 05:05:49,299][78091] Updated weights for policy 0, policy_version 45780 (0.0010) -[2023-10-12 05:05:49,672][78091] Updated weights for policy 0, policy_version 45790 (0.0007) -[2023-10-12 05:05:50,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 93552640. Throughput: 0: 1615.7, 1: 1596.3. Samples: 23393890. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:05:50,201][77203] Avg episode reward: [(0, '44.900'), (1, '46.450')] -[2023-10-12 05:05:51,759][78123] Updated weights for policy 1, policy_version 45570 (0.0007) -[2023-10-12 05:05:52,151][78123] Updated weights for policy 1, policy_version 45580 (0.0007) -[2023-10-12 05:05:52,524][78123] Updated weights for policy 1, policy_version 45590 (0.0010) -[2023-10-12 05:05:52,894][78123] Updated weights for policy 1, policy_version 45600 (0.0010) -[2023-10-12 05:05:53,825][78091] Updated weights for policy 0, policy_version 45800 (0.0008) -[2023-10-12 05:05:54,196][78091] Updated weights for policy 0, policy_version 45810 (0.0007) -[2023-10-12 05:05:54,582][78091] Updated weights for policy 0, policy_version 45820 (0.0007) -[2023-10-12 05:05:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 12774.0). Total num frames: 93618176. Throughput: 0: 1593.7, 1: 1599.0. Samples: 23412346. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:05:55,201][77203] Avg episode reward: [(0, '47.610'), (1, '45.990')] -[2023-10-12 05:05:57,092][78123] Updated weights for policy 1, policy_version 45610 (0.0009) -[2023-10-12 05:05:57,458][78123] Updated weights for policy 1, policy_version 45620 (0.0009) -[2023-10-12 05:05:57,820][78123] Updated weights for policy 1, policy_version 45630 (0.0010) -[2023-10-12 05:05:58,891][78091] Updated weights for policy 0, policy_version 45830 (0.0008) -[2023-10-12 05:05:59,270][78091] Updated weights for policy 0, policy_version 45840 (0.0010) -[2023-10-12 05:05:59,639][78091] Updated weights for policy 0, policy_version 45850 (0.0009) -[2023-10-12 05:06:00,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 93683712. Throughput: 0: 1592.0, 1: 1599.4. Samples: 23422208. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:06:00,202][77203] Avg episode reward: [(0, '39.580'), (1, '41.370')] -[2023-10-12 05:06:02,028][78123] Updated weights for policy 1, policy_version 45640 (0.0011) -[2023-10-12 05:06:02,391][78123] Updated weights for policy 1, policy_version 45650 (0.0009) -[2023-10-12 05:06:02,776][78123] Updated weights for policy 1, policy_version 45660 (0.0010) -[2023-10-12 05:06:04,184][78091] Updated weights for policy 0, policy_version 45860 (0.0009) -[2023-10-12 05:06:04,549][78091] Updated weights for policy 0, policy_version 45870 (0.0008) -[2023-10-12 05:06:04,934][78091] Updated weights for policy 0, policy_version 45880 (0.0008) -[2023-10-12 05:06:05,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 93716480. Throughput: 0: 1607.3, 1: 1588.8. Samples: 23441388. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:06:05,201][77203] Avg episode reward: [(0, '42.050'), (1, '42.310')] -[2023-10-12 05:06:07,168][78123] Updated weights for policy 1, policy_version 45670 (0.0008) -[2023-10-12 05:06:07,541][78123] Updated weights for policy 1, policy_version 45680 (0.0008) -[2023-10-12 05:06:07,899][78123] Updated weights for policy 1, policy_version 45690 (0.0009) -[2023-10-12 05:06:09,246][78091] Updated weights for policy 0, policy_version 45890 (0.0009) -[2023-10-12 05:06:09,641][78091] Updated weights for policy 0, policy_version 45900 (0.0010) -[2023-10-12 05:06:10,007][78091] Updated weights for policy 0, policy_version 45910 (0.0007) -[2023-10-12 05:06:10,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 93782016. Throughput: 0: 1605.0, 1: 1586.9. Samples: 23460398. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:06:10,201][77203] Avg episode reward: [(0, '48.710'), (1, '41.770')] -[2023-10-12 05:06:10,382][78091] Updated weights for policy 0, policy_version 45920 (0.0007) -[2023-10-12 05:06:12,176][78123] Updated weights for policy 1, policy_version 45700 (0.0010) -[2023-10-12 05:06:12,547][78123] Updated weights for policy 1, policy_version 45710 (0.0009) -[2023-10-12 05:06:12,911][78123] Updated weights for policy 1, policy_version 45720 (0.0009) -[2023-10-12 05:06:14,525][78091] Updated weights for policy 0, policy_version 45930 (0.0009) -[2023-10-12 05:06:14,890][78091] Updated weights for policy 0, policy_version 45940 (0.0007) -[2023-10-12 05:06:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 93847552. Throughput: 0: 1592.5, 1: 1594.3. Samples: 23470046. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:06:15,201][77203] Avg episode reward: [(0, '43.030'), (1, '39.530')] -[2023-10-12 05:06:15,267][78091] Updated weights for policy 0, policy_version 45950 (0.0007) -[2023-10-12 05:06:17,209][78123] Updated weights for policy 1, policy_version 45730 (0.0008) -[2023-10-12 05:06:17,576][78123] Updated weights for policy 1, policy_version 45740 (0.0008) -[2023-10-12 05:06:17,938][78123] Updated weights for policy 1, policy_version 45750 (0.0009) -[2023-10-12 05:06:18,305][78123] Updated weights for policy 1, policy_version 45760 (0.0007) -[2023-10-12 05:06:19,562][78091] Updated weights for policy 0, policy_version 45960 (0.0010) -[2023-10-12 05:06:19,922][78091] Updated weights for policy 0, policy_version 45970 (0.0007) -[2023-10-12 05:06:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 93913088. Throughput: 0: 1604.3, 1: 1588.4. Samples: 23489292. Policy #0 lag: (min: 0.0, avg: 24.8, max: 32.0) -[2023-10-12 05:06:20,202][77203] Avg episode reward: [(0, '45.410'), (1, '42.540')] -[2023-10-12 05:06:20,296][78091] Updated weights for policy 0, policy_version 45980 (0.0008) -[2023-10-12 05:06:22,639][78123] Updated weights for policy 1, policy_version 45770 (0.0011) -[2023-10-12 05:06:22,996][78123] Updated weights for policy 1, policy_version 45780 (0.0011) -[2023-10-12 05:06:23,368][78123] Updated weights for policy 1, policy_version 45790 (0.0011) -[2023-10-12 05:06:24,595][78091] Updated weights for policy 0, policy_version 45990 (0.0010) -[2023-10-12 05:06:24,970][78091] Updated weights for policy 0, policy_version 46000 (0.0007) -[2023-10-12 05:06:25,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 93978624. Throughput: 0: 1613.2, 1: 1585.1. Samples: 23508566. Policy #0 lag: (min: 0.0, avg: 24.8, max: 32.0) -[2023-10-12 05:06:25,202][77203] Avg episode reward: [(0, '50.140'), (1, '43.540')] -[2023-10-12 05:06:25,354][78091] Updated weights for policy 0, policy_version 46010 (0.0007) -[2023-10-12 05:06:27,637][78123] Updated weights for policy 1, policy_version 45800 (0.0010) -[2023-10-12 05:06:28,009][78123] Updated weights for policy 1, policy_version 45810 (0.0009) -[2023-10-12 05:06:28,376][78123] Updated weights for policy 1, policy_version 45820 (0.0008) -[2023-10-12 05:06:29,500][78091] Updated weights for policy 0, policy_version 46020 (0.0008) -[2023-10-12 05:06:29,875][78091] Updated weights for policy 0, policy_version 46030 (0.0012) -[2023-10-12 05:06:30,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 94044160. Throughput: 0: 1596.9, 1: 1604.7. Samples: 23518554. Policy #0 lag: (min: 0.0, avg: 24.8, max: 32.0) -[2023-10-12 05:06:30,201][77203] Avg episode reward: [(0, '51.070'), (1, '42.740')] -[2023-10-12 05:06:30,244][78091] Updated weights for policy 0, policy_version 46040 (0.0010) -[2023-10-12 05:06:32,853][78123] Updated weights for policy 1, policy_version 45830 (0.0008) -[2023-10-12 05:06:33,210][78123] Updated weights for policy 1, policy_version 45840 (0.0010) -[2023-10-12 05:06:33,582][78123] Updated weights for policy 1, policy_version 45850 (0.0007) -[2023-10-12 05:06:34,706][78091] Updated weights for policy 0, policy_version 46050 (0.0010) -[2023-10-12 05:06:35,085][78091] Updated weights for policy 0, policy_version 46060 (0.0008) -[2023-10-12 05:06:35,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 94109696. Throughput: 0: 1596.5, 1: 1590.0. Samples: 23537280. Policy #0 lag: (min: 0.0, avg: 24.8, max: 32.0) -[2023-10-12 05:06:35,201][77203] Avg episode reward: [(0, '51.130'), (1, '40.180')] -[2023-10-12 05:06:35,446][78091] Updated weights for policy 0, policy_version 46070 (0.0009) -[2023-10-12 05:06:35,824][78091] Updated weights for policy 0, policy_version 46080 (0.0007) -[2023-10-12 05:06:37,851][78123] Updated weights for policy 1, policy_version 45860 (0.0008) -[2023-10-12 05:06:38,243][78123] Updated weights for policy 1, policy_version 45870 (0.0008) -[2023-10-12 05:06:38,604][78123] Updated weights for policy 1, policy_version 45880 (0.0008) -[2023-10-12 05:06:40,148][78091] Updated weights for policy 0, policy_version 46090 (0.0008) -[2023-10-12 05:06:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 94175232. Throughput: 0: 1619.8, 1: 1588.0. Samples: 23556698. Policy #0 lag: (min: 0.0, avg: 24.8, max: 32.0) -[2023-10-12 05:06:40,201][77203] Avg episode reward: [(0, '47.410'), (1, '44.050')] -[2023-10-12 05:06:40,516][78091] Updated weights for policy 0, policy_version 46100 (0.0008) -[2023-10-12 05:06:40,888][78091] Updated weights for policy 0, policy_version 46110 (0.0009) -[2023-10-12 05:06:42,959][78123] Updated weights for policy 1, policy_version 45890 (0.0008) -[2023-10-12 05:06:43,327][78123] Updated weights for policy 1, policy_version 45900 (0.0007) -[2023-10-12 05:06:43,700][78123] Updated weights for policy 1, policy_version 45910 (0.0008) -[2023-10-12 05:06:44,064][78123] Updated weights for policy 1, policy_version 45920 (0.0011) -[2023-10-12 05:06:45,038][78091] Updated weights for policy 0, policy_version 46120 (0.0007) -[2023-10-12 05:06:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 94240768. Throughput: 0: 1594.9, 1: 1616.2. Samples: 23566708. Policy #0 lag: (min: 0.0, avg: 24.8, max: 32.0) -[2023-10-12 05:06:45,201][77203] Avg episode reward: [(0, '49.910'), (1, '46.510')] -[2023-10-12 05:06:45,410][78091] Updated weights for policy 0, policy_version 46130 (0.0007) -[2023-10-12 05:06:45,776][78091] Updated weights for policy 0, policy_version 46140 (0.0008) -[2023-10-12 05:06:48,377][78123] Updated weights for policy 1, policy_version 45930 (0.0007) -[2023-10-12 05:06:48,753][78123] Updated weights for policy 1, policy_version 45940 (0.0008) -[2023-10-12 05:06:49,117][78123] Updated weights for policy 1, policy_version 45950 (0.0009) -[2023-10-12 05:06:50,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 94306304. Throughput: 0: 1597.0, 1: 1603.5. Samples: 23585412. Policy #0 lag: (min: 31.0, avg: 31.5, max: 47.0) -[2023-10-12 05:06:50,202][77203] Avg episode reward: [(0, '47.600'), (1, '40.980')] -[2023-10-12 05:06:50,205][78091] Updated weights for policy 0, policy_version 46150 (0.0011) -[2023-10-12 05:06:50,566][78091] Updated weights for policy 0, policy_version 46160 (0.0010) -[2023-10-12 05:06:50,950][78091] Updated weights for policy 0, policy_version 46170 (0.0011) -[2023-10-12 05:06:53,511][78123] Updated weights for policy 1, policy_version 45960 (0.0009) -[2023-10-12 05:06:53,875][78123] Updated weights for policy 1, policy_version 45970 (0.0011) -[2023-10-12 05:06:54,246][78123] Updated weights for policy 1, policy_version 45980 (0.0010) -[2023-10-12 05:06:55,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 94371840. Throughput: 0: 1609.4, 1: 1591.9. Samples: 23604456. Policy #0 lag: (min: 31.0, avg: 31.5, max: 47.0) -[2023-10-12 05:06:55,202][77203] Avg episode reward: [(0, '45.250'), (1, '41.790')] -[2023-10-12 05:06:55,382][78091] Updated weights for policy 0, policy_version 46180 (0.0010) -[2023-10-12 05:06:55,766][78091] Updated weights for policy 0, policy_version 46190 (0.0007) -[2023-10-12 05:06:56,139][78091] Updated weights for policy 0, policy_version 46200 (0.0008) -[2023-10-12 05:06:58,444][78123] Updated weights for policy 1, policy_version 45990 (0.0010) -[2023-10-12 05:06:58,806][78123] Updated weights for policy 1, policy_version 46000 (0.0008) -[2023-10-12 05:06:59,176][78123] Updated weights for policy 1, policy_version 46010 (0.0008) -[2023-10-12 05:07:00,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 94437376. Throughput: 0: 1594.3, 1: 1608.9. Samples: 23614190. Policy #0 lag: (min: 31.0, avg: 31.5, max: 47.0) -[2023-10-12 05:07:00,201][77203] Avg episode reward: [(0, '49.510'), (1, '48.880')] -[2023-10-12 05:07:00,325][78091] Updated weights for policy 0, policy_version 46210 (0.0009) -[2023-10-12 05:07:00,691][78091] Updated weights for policy 0, policy_version 46220 (0.0007) -[2023-10-12 05:07:01,058][78091] Updated weights for policy 0, policy_version 46230 (0.0008) -[2023-10-12 05:07:01,432][78091] Updated weights for policy 0, policy_version 46240 (0.0008) -[2023-10-12 05:07:03,518][78123] Updated weights for policy 1, policy_version 46020 (0.0008) -[2023-10-12 05:07:03,876][78123] Updated weights for policy 1, policy_version 46030 (0.0008) -[2023-10-12 05:07:04,244][78123] Updated weights for policy 1, policy_version 46040 (0.0008) -[2023-10-12 05:07:05,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 94502912. Throughput: 0: 1598.3, 1: 1605.9. Samples: 23633482. Policy #0 lag: (min: 31.0, avg: 31.5, max: 47.0) -[2023-10-12 05:07:05,202][77203] Avg episode reward: [(0, '52.680'), (1, '41.930')] -[2023-10-12 05:07:05,699][78091] Updated weights for policy 0, policy_version 46250 (0.0010) -[2023-10-12 05:07:06,074][78091] Updated weights for policy 0, policy_version 46260 (0.0010) -[2023-10-12 05:07:06,460][78091] Updated weights for policy 0, policy_version 46270 (0.0008) -[2023-10-12 05:07:08,591][78123] Updated weights for policy 1, policy_version 46050 (0.0009) -[2023-10-12 05:07:08,951][78123] Updated weights for policy 1, policy_version 46060 (0.0008) -[2023-10-12 05:07:09,324][78123] Updated weights for policy 1, policy_version 46070 (0.0008) -[2023-10-12 05:07:09,681][78123] Updated weights for policy 1, policy_version 46080 (0.0008) -[2023-10-12 05:07:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 94568448. Throughput: 0: 1599.7, 1: 1588.3. Samples: 23652026. Policy #0 lag: (min: 31.0, avg: 31.5, max: 47.0) -[2023-10-12 05:07:10,201][77203] Avg episode reward: [(0, '45.550'), (1, '40.220')] -[2023-10-12 05:07:10,211][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000046080_47185920.pth... -[2023-10-12 05:07:10,211][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000046272_47382528.pth... -[2023-10-12 05:07:10,241][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000044800_45875200.pth -[2023-10-12 05:07:10,246][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000044576_45645824.pth -[2023-10-12 05:07:10,940][78091] Updated weights for policy 0, policy_version 46280 (0.0008) -[2023-10-12 05:07:11,312][78091] Updated weights for policy 0, policy_version 46290 (0.0009) -[2023-10-12 05:07:11,674][78091] Updated weights for policy 0, policy_version 46300 (0.0008) -[2023-10-12 05:07:13,990][78123] Updated weights for policy 1, policy_version 46090 (0.0009) -[2023-10-12 05:07:14,353][78123] Updated weights for policy 1, policy_version 46100 (0.0007) -[2023-10-12 05:07:14,717][78123] Updated weights for policy 1, policy_version 46110 (0.0009) -[2023-10-12 05:07:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 94633984. Throughput: 0: 1587.9, 1: 1592.3. Samples: 23661662. Policy #0 lag: (min: 31.0, avg: 31.5, max: 47.0) -[2023-10-12 05:07:15,202][77203] Avg episode reward: [(0, '45.530'), (1, '45.060')] -[2023-10-12 05:07:15,836][78091] Updated weights for policy 0, policy_version 46310 (0.0009) -[2023-10-12 05:07:16,211][78091] Updated weights for policy 0, policy_version 46320 (0.0009) -[2023-10-12 05:07:16,593][78091] Updated weights for policy 0, policy_version 46330 (0.0008) -[2023-10-12 05:07:19,149][78123] Updated weights for policy 1, policy_version 46120 (0.0007) -[2023-10-12 05:07:19,508][78123] Updated weights for policy 1, policy_version 46130 (0.0008) -[2023-10-12 05:07:19,884][78123] Updated weights for policy 1, policy_version 46140 (0.0007) -[2023-10-12 05:07:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 94699520. Throughput: 0: 1590.5, 1: 1606.1. Samples: 23681128. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-10-12 05:07:20,203][77203] Avg episode reward: [(0, '50.430'), (1, '47.250')] -[2023-10-12 05:07:20,823][78091] Updated weights for policy 0, policy_version 46340 (0.0007) -[2023-10-12 05:07:21,204][78091] Updated weights for policy 0, policy_version 46350 (0.0008) -[2023-10-12 05:07:21,575][78091] Updated weights for policy 0, policy_version 46360 (0.0010) -[2023-10-12 05:07:24,478][78123] Updated weights for policy 1, policy_version 46150 (0.0008) -[2023-10-12 05:07:24,862][78123] Updated weights for policy 1, policy_version 46160 (0.0007) -[2023-10-12 05:07:25,201][77203] Fps is (10 sec: 9830.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 94732288. Throughput: 0: 1590.3, 1: 1594.4. Samples: 23700008. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-10-12 05:07:25,202][77203] Avg episode reward: [(0, '45.710'), (1, '38.640')] -[2023-10-12 05:07:25,222][78123] Updated weights for policy 1, policy_version 46170 (0.0009) -[2023-10-12 05:07:25,942][78091] Updated weights for policy 0, policy_version 46370 (0.0010) -[2023-10-12 05:07:26,312][78091] Updated weights for policy 0, policy_version 46380 (0.0010) -[2023-10-12 05:07:26,690][78091] Updated weights for policy 0, policy_version 46390 (0.0010) -[2023-10-12 05:07:27,054][78091] Updated weights for policy 0, policy_version 46400 (0.0009) -[2023-10-12 05:07:29,573][78123] Updated weights for policy 1, policy_version 46180 (0.0007) -[2023-10-12 05:07:29,939][78123] Updated weights for policy 1, policy_version 46190 (0.0009) -[2023-10-12 05:07:30,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 94797824. Throughput: 0: 1588.5, 1: 1572.9. Samples: 23708974. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-10-12 05:07:30,201][77203] Avg episode reward: [(0, '50.730'), (1, '45.350')] -[2023-10-12 05:07:30,307][78123] Updated weights for policy 1, policy_version 46200 (0.0010) -[2023-10-12 05:07:31,347][78091] Updated weights for policy 0, policy_version 46410 (0.0008) -[2023-10-12 05:07:31,718][78091] Updated weights for policy 0, policy_version 46420 (0.0008) -[2023-10-12 05:07:32,092][78091] Updated weights for policy 0, policy_version 46430 (0.0009) -[2023-10-12 05:07:34,698][78123] Updated weights for policy 1, policy_version 46210 (0.0009) -[2023-10-12 05:07:35,061][78123] Updated weights for policy 1, policy_version 46220 (0.0008) -[2023-10-12 05:07:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 94863360. Throughput: 0: 1591.8, 1: 1590.5. Samples: 23728614. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-10-12 05:07:35,202][77203] Avg episode reward: [(0, '45.130'), (1, '45.660')] -[2023-10-12 05:07:35,423][78123] Updated weights for policy 1, policy_version 46230 (0.0009) -[2023-10-12 05:07:35,784][78123] Updated weights for policy 1, policy_version 46240 (0.0009) -[2023-10-12 05:07:36,478][78091] Updated weights for policy 0, policy_version 46440 (0.0008) -[2023-10-12 05:07:36,839][78091] Updated weights for policy 0, policy_version 46450 (0.0011) -[2023-10-12 05:07:37,221][78091] Updated weights for policy 0, policy_version 46460 (0.0011) -[2023-10-12 05:07:40,163][78123] Updated weights for policy 1, policy_version 46250 (0.0009) -[2023-10-12 05:07:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 94928896. Throughput: 0: 1589.0, 1: 1596.0. Samples: 23747780. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-10-12 05:07:40,201][77203] Avg episode reward: [(0, '45.230'), (1, '41.330')] -[2023-10-12 05:07:40,521][78123] Updated weights for policy 1, policy_version 46260 (0.0009) -[2023-10-12 05:07:40,887][78123] Updated weights for policy 1, policy_version 46270 (0.0008) -[2023-10-12 05:07:41,552][78091] Updated weights for policy 0, policy_version 46470 (0.0007) -[2023-10-12 05:07:41,935][78091] Updated weights for policy 0, policy_version 46480 (0.0007) -[2023-10-12 05:07:42,310][78091] Updated weights for policy 0, policy_version 46490 (0.0008) -[2023-10-12 05:07:45,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 94994432. Throughput: 0: 1590.9, 1: 1570.3. Samples: 23756442. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-10-12 05:07:45,202][77203] Avg episode reward: [(0, '45.230'), (1, '43.860')] -[2023-10-12 05:07:45,321][78123] Updated weights for policy 1, policy_version 46280 (0.0010) -[2023-10-12 05:07:45,684][78123] Updated weights for policy 1, policy_version 46290 (0.0010) -[2023-10-12 05:07:46,058][78123] Updated weights for policy 1, policy_version 46300 (0.0010) -[2023-10-12 05:07:46,425][78091] Updated weights for policy 0, policy_version 46500 (0.0010) -[2023-10-12 05:07:46,796][78091] Updated weights for policy 0, policy_version 46510 (0.0008) -[2023-10-12 05:07:47,163][78091] Updated weights for policy 0, policy_version 46520 (0.0007) -[2023-10-12 05:07:50,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 95059968. Throughput: 0: 1588.1, 1: 1581.1. Samples: 23776096. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-12 05:07:50,202][77203] Avg episode reward: [(0, '49.450'), (1, '47.470')] -[2023-10-12 05:07:50,244][78123] Updated weights for policy 1, policy_version 46310 (0.0009) -[2023-10-12 05:07:50,611][78123] Updated weights for policy 1, policy_version 46320 (0.0007) -[2023-10-12 05:07:50,981][78123] Updated weights for policy 1, policy_version 46330 (0.0007) -[2023-10-12 05:07:51,529][78091] Updated weights for policy 0, policy_version 46530 (0.0008) -[2023-10-12 05:07:51,898][78091] Updated weights for policy 0, policy_version 46540 (0.0010) -[2023-10-12 05:07:52,264][78091] Updated weights for policy 0, policy_version 46550 (0.0010) -[2023-10-12 05:07:52,635][78091] Updated weights for policy 0, policy_version 46560 (0.0009) -[2023-10-12 05:07:55,159][78123] Updated weights for policy 1, policy_version 46340 (0.0008) -[2023-10-12 05:07:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 95125504. Throughput: 0: 1587.8, 1: 1603.2. Samples: 23795622. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-12 05:07:55,201][77203] Avg episode reward: [(0, '42.400'), (1, '42.440')] -[2023-10-12 05:07:55,520][78123] Updated weights for policy 1, policy_version 46350 (0.0010) -[2023-10-12 05:07:55,897][78123] Updated weights for policy 1, policy_version 46360 (0.0010) -[2023-10-12 05:07:57,065][78091] Updated weights for policy 0, policy_version 46570 (0.0010) -[2023-10-12 05:07:57,442][78091] Updated weights for policy 0, policy_version 46580 (0.0009) -[2023-10-12 05:07:57,815][78091] Updated weights for policy 0, policy_version 46590 (0.0009) -[2023-10-12 05:08:00,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 95191040. Throughput: 0: 1591.5, 1: 1579.0. Samples: 23804334. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-12 05:08:00,201][77203] Avg episode reward: [(0, '49.530'), (1, '45.710')] -[2023-10-12 05:08:00,340][78123] Updated weights for policy 1, policy_version 46370 (0.0011) -[2023-10-12 05:08:00,717][78123] Updated weights for policy 1, policy_version 46380 (0.0007) -[2023-10-12 05:08:01,083][78123] Updated weights for policy 1, policy_version 46390 (0.0009) -[2023-10-12 05:08:01,452][78123] Updated weights for policy 1, policy_version 46400 (0.0011) -[2023-10-12 05:08:02,107][78091] Updated weights for policy 0, policy_version 46600 (0.0007) -[2023-10-12 05:08:02,470][78091] Updated weights for policy 0, policy_version 46610 (0.0009) -[2023-10-12 05:08:02,846][78091] Updated weights for policy 0, policy_version 46620 (0.0009) -[2023-10-12 05:08:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 95256576. Throughput: 0: 1586.6, 1: 1577.6. Samples: 23823516. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-12 05:08:05,202][77203] Avg episode reward: [(0, '47.160'), (1, '43.350')] -[2023-10-12 05:08:05,797][78123] Updated weights for policy 1, policy_version 46410 (0.0007) -[2023-10-12 05:08:06,167][78123] Updated weights for policy 1, policy_version 46420 (0.0007) -[2023-10-12 05:08:06,541][78123] Updated weights for policy 1, policy_version 46430 (0.0008) -[2023-10-12 05:08:07,175][78091] Updated weights for policy 0, policy_version 46630 (0.0009) -[2023-10-12 05:08:07,553][78091] Updated weights for policy 0, policy_version 46640 (0.0008) -[2023-10-12 05:08:07,930][78091] Updated weights for policy 0, policy_version 46650 (0.0010) -[2023-10-12 05:08:10,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 95322112. Throughput: 0: 1577.6, 1: 1592.9. Samples: 23842682. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-12 05:08:10,202][77203] Avg episode reward: [(0, '49.650'), (1, '38.150')] -[2023-10-12 05:08:10,912][78123] Updated weights for policy 1, policy_version 46440 (0.0009) -[2023-10-12 05:08:11,283][78123] Updated weights for policy 1, policy_version 46450 (0.0010) -[2023-10-12 05:08:11,659][78123] Updated weights for policy 1, policy_version 46460 (0.0008) -[2023-10-12 05:08:12,407][78091] Updated weights for policy 0, policy_version 46660 (0.0009) -[2023-10-12 05:08:12,789][78091] Updated weights for policy 0, policy_version 46670 (0.0008) -[2023-10-12 05:08:13,169][78091] Updated weights for policy 0, policy_version 46680 (0.0008) -[2023-10-12 05:08:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 95387648. Throughput: 0: 1593.1, 1: 1582.6. Samples: 23851878. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-12 05:08:15,202][77203] Avg episode reward: [(0, '50.700'), (1, '43.380')] -[2023-10-12 05:08:15,921][78123] Updated weights for policy 1, policy_version 46470 (0.0008) -[2023-10-12 05:08:16,289][78123] Updated weights for policy 1, policy_version 46480 (0.0007) -[2023-10-12 05:08:16,649][78123] Updated weights for policy 1, policy_version 46490 (0.0007) -[2023-10-12 05:08:17,514][78091] Updated weights for policy 0, policy_version 46690 (0.0010) -[2023-10-12 05:08:17,892][78091] Updated weights for policy 0, policy_version 46700 (0.0009) -[2023-10-12 05:08:18,263][78091] Updated weights for policy 0, policy_version 46710 (0.0008) -[2023-10-12 05:08:18,644][78091] Updated weights for policy 0, policy_version 46720 (0.0007) -[2023-10-12 05:08:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 95453184. Throughput: 0: 1571.6, 1: 1584.7. Samples: 23870650. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:08:20,201][77203] Avg episode reward: [(0, '49.800'), (1, '43.440')] -[2023-10-12 05:08:20,937][78123] Updated weights for policy 1, policy_version 46500 (0.0010) -[2023-10-12 05:08:21,309][78123] Updated weights for policy 1, policy_version 46510 (0.0009) -[2023-10-12 05:08:21,679][78123] Updated weights for policy 1, policy_version 46520 (0.0008) -[2023-10-12 05:08:22,973][78091] Updated weights for policy 0, policy_version 46730 (0.0010) -[2023-10-12 05:08:23,335][78091] Updated weights for policy 0, policy_version 46740 (0.0008) -[2023-10-12 05:08:23,714][78091] Updated weights for policy 0, policy_version 46750 (0.0007) -[2023-10-12 05:08:25,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 95518720. Throughput: 0: 1570.8, 1: 1592.0. Samples: 23890108. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:08:25,202][77203] Avg episode reward: [(0, '47.600'), (1, '39.730')] -[2023-10-12 05:08:25,968][78123] Updated weights for policy 1, policy_version 46530 (0.0011) -[2023-10-12 05:08:26,336][78123] Updated weights for policy 1, policy_version 46540 (0.0008) -[2023-10-12 05:08:26,707][78123] Updated weights for policy 1, policy_version 46550 (0.0008) -[2023-10-12 05:08:27,061][78123] Updated weights for policy 1, policy_version 46560 (0.0009) -[2023-10-12 05:08:28,081][78091] Updated weights for policy 0, policy_version 46760 (0.0009) -[2023-10-12 05:08:28,444][78091] Updated weights for policy 0, policy_version 46770 (0.0009) -[2023-10-12 05:08:28,821][78091] Updated weights for policy 0, policy_version 46780 (0.0007) -[2023-10-12 05:08:30,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 95584256. Throughput: 0: 1596.3, 1: 1590.3. Samples: 23899836. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:08:30,202][77203] Avg episode reward: [(0, '46.680'), (1, '42.580')] -[2023-10-12 05:08:31,358][78123] Updated weights for policy 1, policy_version 46570 (0.0007) -[2023-10-12 05:08:31,725][78123] Updated weights for policy 1, policy_version 46580 (0.0007) -[2023-10-12 05:08:32,092][78123] Updated weights for policy 1, policy_version 46590 (0.0008) -[2023-10-12 05:08:32,922][78091] Updated weights for policy 0, policy_version 46790 (0.0008) -[2023-10-12 05:08:33,292][78091] Updated weights for policy 0, policy_version 46800 (0.0008) -[2023-10-12 05:08:33,663][78091] Updated weights for policy 0, policy_version 46810 (0.0008) -[2023-10-12 05:08:35,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 95649792. Throughput: 0: 1576.3, 1: 1586.4. Samples: 23918420. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:08:35,202][77203] Avg episode reward: [(0, '49.040'), (1, '43.430')] -[2023-10-12 05:08:36,549][78123] Updated weights for policy 1, policy_version 46600 (0.0011) -[2023-10-12 05:08:36,905][78123] Updated weights for policy 1, policy_version 46610 (0.0009) -[2023-10-12 05:08:37,286][78123] Updated weights for policy 1, policy_version 46620 (0.0009) -[2023-10-12 05:08:38,166][78091] Updated weights for policy 0, policy_version 46820 (0.0009) -[2023-10-12 05:08:38,528][78091] Updated weights for policy 0, policy_version 46830 (0.0009) -[2023-10-12 05:08:38,900][78091] Updated weights for policy 0, policy_version 46840 (0.0007) -[2023-10-12 05:08:40,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 95715328. Throughput: 0: 1573.1, 1: 1581.1. Samples: 23937562. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:08:40,201][77203] Avg episode reward: [(0, '52.120'), (1, '42.360')] -[2023-10-12 05:08:41,845][78123] Updated weights for policy 1, policy_version 46630 (0.0010) -[2023-10-12 05:08:42,202][78123] Updated weights for policy 1, policy_version 46640 (0.0009) -[2023-10-12 05:08:42,572][78123] Updated weights for policy 1, policy_version 46650 (0.0008) -[2023-10-12 05:08:43,288][78091] Updated weights for policy 0, policy_version 46850 (0.0008) -[2023-10-12 05:08:43,653][78091] Updated weights for policy 0, policy_version 46860 (0.0007) -[2023-10-12 05:08:44,033][78091] Updated weights for policy 0, policy_version 46870 (0.0007) -[2023-10-12 05:08:44,395][78091] Updated weights for policy 0, policy_version 46880 (0.0007) -[2023-10-12 05:08:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 95780864. Throughput: 0: 1597.1, 1: 1582.8. Samples: 23947430. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:08:45,202][77203] Avg episode reward: [(0, '46.870'), (1, '45.970')] -[2023-10-12 05:08:46,834][78123] Updated weights for policy 1, policy_version 46660 (0.0009) -[2023-10-12 05:08:47,208][78123] Updated weights for policy 1, policy_version 46670 (0.0010) -[2023-10-12 05:08:47,573][78123] Updated weights for policy 1, policy_version 46680 (0.0009) -[2023-10-12 05:08:48,758][78091] Updated weights for policy 0, policy_version 46890 (0.0008) -[2023-10-12 05:08:49,129][78091] Updated weights for policy 0, policy_version 46900 (0.0008) -[2023-10-12 05:08:49,499][78091] Updated weights for policy 0, policy_version 46910 (0.0007) -[2023-10-12 05:08:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 95846400. Throughput: 0: 1586.8, 1: 1584.3. Samples: 23966214. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-12 05:08:50,201][77203] Avg episode reward: [(0, '43.900'), (1, '44.700')] -[2023-10-12 05:08:51,924][78123] Updated weights for policy 1, policy_version 46690 (0.0009) -[2023-10-12 05:08:52,292][78123] Updated weights for policy 1, policy_version 46700 (0.0008) -[2023-10-12 05:08:52,668][78123] Updated weights for policy 1, policy_version 46710 (0.0007) -[2023-10-12 05:08:53,033][78123] Updated weights for policy 1, policy_version 46720 (0.0007) -[2023-10-12 05:08:53,666][78091] Updated weights for policy 0, policy_version 46920 (0.0009) -[2023-10-12 05:08:54,038][78091] Updated weights for policy 0, policy_version 46930 (0.0010) -[2023-10-12 05:08:54,419][78091] Updated weights for policy 0, policy_version 46940 (0.0009) -[2023-10-12 05:08:55,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 95911936. Throughput: 0: 1579.2, 1: 1590.0. Samples: 23985296. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-12 05:08:55,202][77203] Avg episode reward: [(0, '39.800'), (1, '44.410')] -[2023-10-12 05:08:57,463][78123] Updated weights for policy 1, policy_version 46730 (0.0009) -[2023-10-12 05:08:57,827][78123] Updated weights for policy 1, policy_version 46740 (0.0007) -[2023-10-12 05:08:58,202][78123] Updated weights for policy 1, policy_version 46750 (0.0007) -[2023-10-12 05:08:58,765][78091] Updated weights for policy 0, policy_version 46950 (0.0009) -[2023-10-12 05:08:59,137][78091] Updated weights for policy 0, policy_version 46960 (0.0010) -[2023-10-12 05:08:59,513][78091] Updated weights for policy 0, policy_version 46970 (0.0009) -[2023-10-12 05:09:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 95977472. Throughput: 0: 1590.6, 1: 1600.2. Samples: 23995462. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-12 05:09:00,201][77203] Avg episode reward: [(0, '38.560'), (1, '42.130')] -[2023-10-12 05:09:02,412][78123] Updated weights for policy 1, policy_version 46760 (0.0008) -[2023-10-12 05:09:02,788][78123] Updated weights for policy 1, policy_version 46770 (0.0010) -[2023-10-12 05:09:03,146][78123] Updated weights for policy 1, policy_version 46780 (0.0010) -[2023-10-12 05:09:03,699][78091] Updated weights for policy 0, policy_version 46980 (0.0007) -[2023-10-12 05:09:04,066][78091] Updated weights for policy 0, policy_version 46990 (0.0008) -[2023-10-12 05:09:04,433][78091] Updated weights for policy 0, policy_version 47000 (0.0008) -[2023-10-12 05:09:05,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 96043008. Throughput: 0: 1606.4, 1: 1586.1. Samples: 24014312. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-12 05:09:05,202][77203] Avg episode reward: [(0, '39.580'), (1, '43.600')] -[2023-10-12 05:09:07,335][78123] Updated weights for policy 1, policy_version 46790 (0.0007) -[2023-10-12 05:09:07,707][78123] Updated weights for policy 1, policy_version 46800 (0.0010) -[2023-10-12 05:09:08,076][78123] Updated weights for policy 1, policy_version 46810 (0.0007) -[2023-10-12 05:09:08,818][78091] Updated weights for policy 0, policy_version 47010 (0.0008) -[2023-10-12 05:09:09,183][78091] Updated weights for policy 0, policy_version 47020 (0.0008) -[2023-10-12 05:09:09,553][78091] Updated weights for policy 0, policy_version 47030 (0.0008) -[2023-10-12 05:09:09,920][78091] Updated weights for policy 0, policy_version 47040 (0.0008) -[2023-10-12 05:09:10,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 96108544. Throughput: 0: 1592.5, 1: 1587.3. Samples: 24033198. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-12 05:09:10,202][77203] Avg episode reward: [(0, '38.600'), (1, '44.530')] -[2023-10-12 05:09:10,209][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000047040_48168960.pth... -[2023-10-12 05:09:10,209][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000046816_47939584.pth... -[2023-10-12 05:09:10,240][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000045536_46628864.pth -[2023-10-12 05:09:10,252][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000045312_46399488.pth -[2023-10-12 05:09:12,440][78123] Updated weights for policy 1, policy_version 46820 (0.0010) -[2023-10-12 05:09:12,811][78123] Updated weights for policy 1, policy_version 46830 (0.0009) -[2023-10-12 05:09:13,187][78123] Updated weights for policy 1, policy_version 46840 (0.0010) -[2023-10-12 05:09:14,406][78091] Updated weights for policy 0, policy_version 47050 (0.0011) -[2023-10-12 05:09:14,767][78091] Updated weights for policy 0, policy_version 47060 (0.0007) -[2023-10-12 05:09:15,133][78091] Updated weights for policy 0, policy_version 47070 (0.0009) -[2023-10-12 05:09:15,201][77203] Fps is (10 sec: 9830.6, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 96141312. Throughput: 0: 1590.5, 1: 1606.4. Samples: 24043692. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-12 05:09:15,201][77203] Avg episode reward: [(0, '39.320'), (1, '42.370')] -[2023-10-12 05:09:17,540][78123] Updated weights for policy 1, policy_version 46850 (0.0009) -[2023-10-12 05:09:17,891][78123] Updated weights for policy 1, policy_version 46860 (0.0009) -[2023-10-12 05:09:18,253][78123] Updated weights for policy 1, policy_version 46870 (0.0010) -[2023-10-12 05:09:18,617][78123] Updated weights for policy 1, policy_version 46880 (0.0011) -[2023-10-12 05:09:19,400][78091] Updated weights for policy 0, policy_version 47080 (0.0008) -[2023-10-12 05:09:19,776][78091] Updated weights for policy 0, policy_version 47090 (0.0008) -[2023-10-12 05:09:20,144][78091] Updated weights for policy 0, policy_version 47100 (0.0008) -[2023-10-12 05:09:20,201][77203] Fps is (10 sec: 9830.6, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 96206848. Throughput: 0: 1608.9, 1: 1584.6. Samples: 24062130. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-12 05:09:20,201][77203] Avg episode reward: [(0, '40.990'), (1, '43.830')] -[2023-10-12 05:09:22,916][78123] Updated weights for policy 1, policy_version 46890 (0.0008) -[2023-10-12 05:09:23,279][78123] Updated weights for policy 1, policy_version 46900 (0.0011) -[2023-10-12 05:09:23,645][78123] Updated weights for policy 1, policy_version 46910 (0.0010) -[2023-10-12 05:09:24,516][78091] Updated weights for policy 0, policy_version 47110 (0.0010) -[2023-10-12 05:09:24,883][78091] Updated weights for policy 0, policy_version 47120 (0.0007) -[2023-10-12 05:09:25,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 96272384. Throughput: 0: 1606.6, 1: 1588.6. Samples: 24081346. Policy #0 lag: (min: 15.0, avg: 20.2, max: 47.0) -[2023-10-12 05:09:25,202][77203] Avg episode reward: [(0, '42.260'), (1, '48.440')] -[2023-10-12 05:09:25,262][78091] Updated weights for policy 0, policy_version 47130 (0.0007) -[2023-10-12 05:09:28,000][78123] Updated weights for policy 1, policy_version 46920 (0.0010) -[2023-10-12 05:09:28,375][78123] Updated weights for policy 1, policy_version 46930 (0.0009) -[2023-10-12 05:09:28,751][78123] Updated weights for policy 1, policy_version 46940 (0.0009) -[2023-10-12 05:09:29,528][78091] Updated weights for policy 0, policy_version 47140 (0.0007) -[2023-10-12 05:09:29,901][78091] Updated weights for policy 0, policy_version 47150 (0.0008) -[2023-10-12 05:09:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 96337920. Throughput: 0: 1593.5, 1: 1610.8. Samples: 24091620. Policy #0 lag: (min: 15.0, avg: 20.2, max: 47.0) -[2023-10-12 05:09:30,202][77203] Avg episode reward: [(0, '41.700'), (1, '42.110')] -[2023-10-12 05:09:30,260][78091] Updated weights for policy 0, policy_version 47160 (0.0008) -[2023-10-12 05:09:33,199][78123] Updated weights for policy 1, policy_version 46950 (0.0009) -[2023-10-12 05:09:33,558][78123] Updated weights for policy 1, policy_version 46960 (0.0009) -[2023-10-12 05:09:33,920][78123] Updated weights for policy 1, policy_version 46970 (0.0008) -[2023-10-12 05:09:34,532][78091] Updated weights for policy 0, policy_version 47170 (0.0009) -[2023-10-12 05:09:34,902][78091] Updated weights for policy 0, policy_version 47180 (0.0007) -[2023-10-12 05:09:35,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 96403456. Throughput: 0: 1608.8, 1: 1595.4. Samples: 24110402. Policy #0 lag: (min: 15.0, avg: 20.2, max: 47.0) -[2023-10-12 05:09:35,201][77203] Avg episode reward: [(0, '45.060'), (1, '39.340')] -[2023-10-12 05:09:35,268][78091] Updated weights for policy 0, policy_version 47190 (0.0008) -[2023-10-12 05:09:35,645][78091] Updated weights for policy 0, policy_version 47200 (0.0009) -[2023-10-12 05:09:38,169][78123] Updated weights for policy 1, policy_version 46980 (0.0008) -[2023-10-12 05:09:38,535][78123] Updated weights for policy 1, policy_version 46990 (0.0007) -[2023-10-12 05:09:38,905][78123] Updated weights for policy 1, policy_version 47000 (0.0008) -[2023-10-12 05:09:40,129][78091] Updated weights for policy 0, policy_version 47210 (0.0008) -[2023-10-12 05:09:40,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 96468992. Throughput: 0: 1618.7, 1: 1578.6. Samples: 24129174. Policy #0 lag: (min: 15.0, avg: 20.2, max: 47.0) -[2023-10-12 05:09:40,201][77203] Avg episode reward: [(0, '51.240'), (1, '45.310')] -[2023-10-12 05:09:40,495][78091] Updated weights for policy 0, policy_version 47220 (0.0009) -[2023-10-12 05:09:40,871][78091] Updated weights for policy 0, policy_version 47230 (0.0009) -[2023-10-12 05:09:43,545][78123] Updated weights for policy 1, policy_version 47010 (0.0008) -[2023-10-12 05:09:43,945][78123] Updated weights for policy 1, policy_version 47020 (0.0008) -[2023-10-12 05:09:44,298][78123] Updated weights for policy 1, policy_version 47030 (0.0010) -[2023-10-12 05:09:44,667][78123] Updated weights for policy 1, policy_version 47040 (0.0008) -[2023-10-12 05:09:45,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 96534528. Throughput: 0: 1595.2, 1: 1596.6. Samples: 24139092. Policy #0 lag: (min: 15.0, avg: 20.2, max: 47.0) -[2023-10-12 05:09:45,201][77203] Avg episode reward: [(0, '46.680'), (1, '44.770')] -[2023-10-12 05:09:45,224][78091] Updated weights for policy 0, policy_version 47240 (0.0009) -[2023-10-12 05:09:45,593][78091] Updated weights for policy 0, policy_version 47250 (0.0009) -[2023-10-12 05:09:45,971][78091] Updated weights for policy 0, policy_version 47260 (0.0009) -[2023-10-12 05:09:49,000][78123] Updated weights for policy 1, policy_version 47050 (0.0009) -[2023-10-12 05:09:49,366][78123] Updated weights for policy 1, policy_version 47060 (0.0009) -[2023-10-12 05:09:49,730][78123] Updated weights for policy 1, policy_version 47070 (0.0007) -[2023-10-12 05:09:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 96600064. Throughput: 0: 1595.9, 1: 1607.1. Samples: 24158446. Policy #0 lag: (min: 15.0, avg: 20.2, max: 47.0) -[2023-10-12 05:09:50,201][77203] Avg episode reward: [(0, '45.370'), (1, '43.890')] -[2023-10-12 05:09:50,287][78091] Updated weights for policy 0, policy_version 47270 (0.0008) -[2023-10-12 05:09:50,658][78091] Updated weights for policy 0, policy_version 47280 (0.0010) -[2023-10-12 05:09:51,027][78091] Updated weights for policy 0, policy_version 47290 (0.0007) -[2023-10-12 05:09:53,861][78123] Updated weights for policy 1, policy_version 47080 (0.0008) -[2023-10-12 05:09:54,237][78123] Updated weights for policy 1, policy_version 47090 (0.0009) -[2023-10-12 05:09:54,613][78123] Updated weights for policy 1, policy_version 47100 (0.0008) -[2023-10-12 05:09:55,186][78091] Updated weights for policy 0, policy_version 47300 (0.0009) -[2023-10-12 05:09:55,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 96665600. Throughput: 0: 1619.6, 1: 1583.1. Samples: 24177320. Policy #0 lag: (min: 27.0, avg: 31.0, max: 59.0) -[2023-10-12 05:09:55,201][77203] Avg episode reward: [(0, '47.500'), (1, '41.190')] -[2023-10-12 05:09:55,554][78091] Updated weights for policy 0, policy_version 47310 (0.0007) -[2023-10-12 05:09:55,919][78091] Updated weights for policy 0, policy_version 47320 (0.0008) -[2023-10-12 05:09:58,726][78123] Updated weights for policy 1, policy_version 47110 (0.0008) -[2023-10-12 05:09:59,089][78123] Updated weights for policy 1, policy_version 47120 (0.0009) -[2023-10-12 05:09:59,446][78123] Updated weights for policy 1, policy_version 47130 (0.0009) -[2023-10-12 05:10:00,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 96731136. Throughput: 0: 1594.6, 1: 1588.2. Samples: 24186918. Policy #0 lag: (min: 27.0, avg: 31.0, max: 59.0) -[2023-10-12 05:10:00,202][77203] Avg episode reward: [(0, '44.610'), (1, '46.360')] -[2023-10-12 05:10:00,315][78091] Updated weights for policy 0, policy_version 47330 (0.0008) -[2023-10-12 05:10:00,694][78091] Updated weights for policy 0, policy_version 47340 (0.0009) -[2023-10-12 05:10:01,070][78091] Updated weights for policy 0, policy_version 47350 (0.0011) -[2023-10-12 05:10:01,444][78091] Updated weights for policy 0, policy_version 47360 (0.0008) -[2023-10-12 05:10:03,540][78123] Updated weights for policy 1, policy_version 47140 (0.0008) -[2023-10-12 05:10:03,902][78123] Updated weights for policy 1, policy_version 47150 (0.0009) -[2023-10-12 05:10:04,271][78123] Updated weights for policy 1, policy_version 47160 (0.0009) -[2023-10-12 05:10:05,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 96796672. Throughput: 0: 1593.8, 1: 1608.4. Samples: 24206230. Policy #0 lag: (min: 27.0, avg: 31.0, max: 59.0) -[2023-10-12 05:10:05,202][77203] Avg episode reward: [(0, '40.590'), (1, '38.160')] -[2023-10-12 05:10:05,700][78091] Updated weights for policy 0, policy_version 47370 (0.0009) -[2023-10-12 05:10:06,078][78091] Updated weights for policy 0, policy_version 47380 (0.0007) -[2023-10-12 05:10:06,447][78091] Updated weights for policy 0, policy_version 47390 (0.0007) -[2023-10-12 05:10:08,708][78123] Updated weights for policy 1, policy_version 47170 (0.0008) -[2023-10-12 05:10:09,085][78123] Updated weights for policy 1, policy_version 47180 (0.0009) -[2023-10-12 05:10:09,458][78123] Updated weights for policy 1, policy_version 47190 (0.0009) -[2023-10-12 05:10:09,820][78123] Updated weights for policy 1, policy_version 47200 (0.0008) -[2023-10-12 05:10:10,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 96862208. Throughput: 0: 1603.4, 1: 1589.6. Samples: 24225032. Policy #0 lag: (min: 27.0, avg: 31.0, max: 59.0) -[2023-10-12 05:10:10,201][77203] Avg episode reward: [(0, '42.450'), (1, '40.230')] -[2023-10-12 05:10:10,696][78091] Updated weights for policy 0, policy_version 47400 (0.0008) -[2023-10-12 05:10:11,064][78091] Updated weights for policy 0, policy_version 47410 (0.0007) -[2023-10-12 05:10:11,432][78091] Updated weights for policy 0, policy_version 47420 (0.0009) -[2023-10-12 05:10:14,437][78123] Updated weights for policy 1, policy_version 47210 (0.0009) -[2023-10-12 05:10:14,794][78123] Updated weights for policy 1, policy_version 47220 (0.0010) -[2023-10-12 05:10:15,161][78123] Updated weights for policy 1, policy_version 47230 (0.0010) -[2023-10-12 05:10:15,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 96894976. Throughput: 0: 1589.2, 1: 1587.0. Samples: 24234552. Policy #0 lag: (min: 27.0, avg: 31.0, max: 59.0) -[2023-10-12 05:10:15,202][77203] Avg episode reward: [(0, '46.750'), (1, '49.430')] -[2023-10-12 05:10:15,232][77950] Saving new best policy, reward=49.430! -[2023-10-12 05:10:15,796][78091] Updated weights for policy 0, policy_version 47430 (0.0008) -[2023-10-12 05:10:16,159][78091] Updated weights for policy 0, policy_version 47440 (0.0011) -[2023-10-12 05:10:16,541][78091] Updated weights for policy 0, policy_version 47450 (0.0009) -[2023-10-12 05:10:19,329][78123] Updated weights for policy 1, policy_version 47240 (0.0009) -[2023-10-12 05:10:19,692][78123] Updated weights for policy 1, policy_version 47250 (0.0008) -[2023-10-12 05:10:20,065][78123] Updated weights for policy 1, policy_version 47260 (0.0008) -[2023-10-12 05:10:20,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 96960512. Throughput: 0: 1588.6, 1: 1604.0. Samples: 24254066. Policy #0 lag: (min: 27.0, avg: 31.0, max: 59.0) -[2023-10-12 05:10:20,201][77203] Avg episode reward: [(0, '51.790'), (1, '44.580')] -[2023-10-12 05:10:20,590][78091] Updated weights for policy 0, policy_version 47460 (0.0008) -[2023-10-12 05:10:20,971][78091] Updated weights for policy 0, policy_version 47470 (0.0008) -[2023-10-12 05:10:21,338][78091] Updated weights for policy 0, policy_version 47480 (0.0007) -[2023-10-12 05:10:24,476][78123] Updated weights for policy 1, policy_version 47270 (0.0008) -[2023-10-12 05:10:24,843][78123] Updated weights for policy 1, policy_version 47280 (0.0009) -[2023-10-12 05:10:25,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 97026048. Throughput: 0: 1598.9, 1: 1606.4. Samples: 24273416. Policy #0 lag: (min: 27.0, avg: 31.0, max: 59.0) -[2023-10-12 05:10:25,202][77203] Avg episode reward: [(0, '49.770'), (1, '39.060')] -[2023-10-12 05:10:25,206][78123] Updated weights for policy 1, policy_version 47290 (0.0008) -[2023-10-12 05:10:25,683][78091] Updated weights for policy 0, policy_version 47490 (0.0009) -[2023-10-12 05:10:26,051][78091] Updated weights for policy 0, policy_version 47500 (0.0007) -[2023-10-12 05:10:26,418][78091] Updated weights for policy 0, policy_version 47510 (0.0009) -[2023-10-12 05:10:26,783][78091] Updated weights for policy 0, policy_version 47520 (0.0009) -[2023-10-12 05:10:29,601][78123] Updated weights for policy 1, policy_version 47300 (0.0007) -[2023-10-12 05:10:29,990][78123] Updated weights for policy 1, policy_version 47310 (0.0007) -[2023-10-12 05:10:30,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 97091584. Throughput: 0: 1596.4, 1: 1591.0. Samples: 24282526. Policy #0 lag: (min: 7.0, avg: 13.5, max: 39.0) -[2023-10-12 05:10:30,201][77203] Avg episode reward: [(0, '48.150'), (1, '47.480')] -[2023-10-12 05:10:30,362][78123] Updated weights for policy 1, policy_version 47320 (0.0008) -[2023-10-12 05:10:31,188][78091] Updated weights for policy 0, policy_version 47530 (0.0009) -[2023-10-12 05:10:31,565][78091] Updated weights for policy 0, policy_version 47540 (0.0009) -[2023-10-12 05:10:31,951][78091] Updated weights for policy 0, policy_version 47550 (0.0009) -[2023-10-12 05:10:34,772][78123] Updated weights for policy 1, policy_version 47330 (0.0009) -[2023-10-12 05:10:35,131][78123] Updated weights for policy 1, policy_version 47340 (0.0007) -[2023-10-12 05:10:35,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 97157120. Throughput: 0: 1602.9, 1: 1592.6. Samples: 24302246. Policy #0 lag: (min: 7.0, avg: 13.5, max: 39.0) -[2023-10-12 05:10:35,201][77203] Avg episode reward: [(0, '47.190'), (1, '40.690')] -[2023-10-12 05:10:35,500][78123] Updated weights for policy 1, policy_version 47350 (0.0008) -[2023-10-12 05:10:35,866][78123] Updated weights for policy 1, policy_version 47360 (0.0009) -[2023-10-12 05:10:36,015][78091] Updated weights for policy 0, policy_version 47560 (0.0008) -[2023-10-12 05:10:36,385][78091] Updated weights for policy 0, policy_version 47570 (0.0008) -[2023-10-12 05:10:36,767][78091] Updated weights for policy 0, policy_version 47580 (0.0010) -[2023-10-12 05:10:40,201][77203] Fps is (10 sec: 13106.8, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 97222656. Throughput: 0: 1594.7, 1: 1609.8. Samples: 24321526. Policy #0 lag: (min: 7.0, avg: 13.5, max: 39.0) -[2023-10-12 05:10:40,202][77203] Avg episode reward: [(0, '45.700'), (1, '40.540')] -[2023-10-12 05:10:40,222][78123] Updated weights for policy 1, policy_version 47370 (0.0010) -[2023-10-12 05:10:40,587][78123] Updated weights for policy 1, policy_version 47380 (0.0009) -[2023-10-12 05:10:40,955][78123] Updated weights for policy 1, policy_version 47390 (0.0008) -[2023-10-12 05:10:41,463][78091] Updated weights for policy 0, policy_version 47590 (0.0007) -[2023-10-12 05:10:41,834][78091] Updated weights for policy 0, policy_version 47600 (0.0007) -[2023-10-12 05:10:42,200][78091] Updated weights for policy 0, policy_version 47610 (0.0007) -[2023-10-12 05:10:45,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 97288192. Throughput: 0: 1595.2, 1: 1584.8. Samples: 24330018. Policy #0 lag: (min: 7.0, avg: 13.5, max: 39.0) -[2023-10-12 05:10:45,202][77203] Avg episode reward: [(0, '51.440'), (1, '42.280')] -[2023-10-12 05:10:45,295][78123] Updated weights for policy 1, policy_version 47400 (0.0008) -[2023-10-12 05:10:45,669][78123] Updated weights for policy 1, policy_version 47410 (0.0009) -[2023-10-12 05:10:46,030][78123] Updated weights for policy 1, policy_version 47420 (0.0008) -[2023-10-12 05:10:46,397][78091] Updated weights for policy 0, policy_version 47620 (0.0009) -[2023-10-12 05:10:46,764][78091] Updated weights for policy 0, policy_version 47630 (0.0008) -[2023-10-12 05:10:47,143][78091] Updated weights for policy 0, policy_version 47640 (0.0008) -[2023-10-12 05:10:50,201][77203] Fps is (10 sec: 13107.6, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 97353728. Throughput: 0: 1600.8, 1: 1588.8. Samples: 24349764. Policy #0 lag: (min: 7.0, avg: 13.5, max: 39.0) -[2023-10-12 05:10:50,201][77203] Avg episode reward: [(0, '45.000'), (1, '44.830')] -[2023-10-12 05:10:50,416][78123] Updated weights for policy 1, policy_version 47430 (0.0008) -[2023-10-12 05:10:50,784][78123] Updated weights for policy 1, policy_version 47440 (0.0007) -[2023-10-12 05:10:51,147][78123] Updated weights for policy 1, policy_version 47450 (0.0007) -[2023-10-12 05:10:51,428][78091] Updated weights for policy 0, policy_version 47650 (0.0009) -[2023-10-12 05:10:51,828][78091] Updated weights for policy 0, policy_version 47660 (0.0009) -[2023-10-12 05:10:52,205][78091] Updated weights for policy 0, policy_version 47670 (0.0010) -[2023-10-12 05:10:52,576][78091] Updated weights for policy 0, policy_version 47680 (0.0009) -[2023-10-12 05:10:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 97419264. Throughput: 0: 1600.0, 1: 1603.1. Samples: 24369174. Policy #0 lag: (min: 7.0, avg: 13.5, max: 39.0) -[2023-10-12 05:10:55,202][77203] Avg episode reward: [(0, '48.980'), (1, '43.190')] -[2023-10-12 05:10:55,519][78123] Updated weights for policy 1, policy_version 47460 (0.0008) -[2023-10-12 05:10:55,898][78123] Updated weights for policy 1, policy_version 47470 (0.0011) -[2023-10-12 05:10:56,262][78123] Updated weights for policy 1, policy_version 47480 (0.0010) -[2023-10-12 05:10:56,681][78091] Updated weights for policy 0, policy_version 47690 (0.0009) -[2023-10-12 05:10:57,063][78091] Updated weights for policy 0, policy_version 47700 (0.0010) -[2023-10-12 05:10:57,434][78091] Updated weights for policy 0, policy_version 47710 (0.0009) -[2023-10-12 05:11:00,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 97484800. Throughput: 0: 1602.0, 1: 1581.7. Samples: 24377818. Policy #0 lag: (min: 9.0, avg: 15.8, max: 41.0) -[2023-10-12 05:11:00,201][77203] Avg episode reward: [(0, '45.240'), (1, '48.320')] -[2023-10-12 05:11:00,579][78123] Updated weights for policy 1, policy_version 47490 (0.0008) -[2023-10-12 05:11:00,959][78123] Updated weights for policy 1, policy_version 47500 (0.0008) -[2023-10-12 05:11:01,316][78123] Updated weights for policy 1, policy_version 47510 (0.0007) -[2023-10-12 05:11:01,692][78123] Updated weights for policy 1, policy_version 47520 (0.0008) -[2023-10-12 05:11:01,724][78091] Updated weights for policy 0, policy_version 47720 (0.0007) -[2023-10-12 05:11:02,089][78091] Updated weights for policy 0, policy_version 47730 (0.0010) -[2023-10-12 05:11:02,465][78091] Updated weights for policy 0, policy_version 47740 (0.0009) -[2023-10-12 05:11:05,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 97550336. Throughput: 0: 1602.8, 1: 1587.4. Samples: 24397628. Policy #0 lag: (min: 9.0, avg: 15.8, max: 41.0) -[2023-10-12 05:11:05,202][77203] Avg episode reward: [(0, '48.160'), (1, '43.540')] -[2023-10-12 05:11:05,848][78123] Updated weights for policy 1, policy_version 47530 (0.0007) -[2023-10-12 05:11:06,217][78123] Updated weights for policy 1, policy_version 47540 (0.0007) -[2023-10-12 05:11:06,591][78123] Updated weights for policy 1, policy_version 47550 (0.0008) -[2023-10-12 05:11:06,810][78091] Updated weights for policy 0, policy_version 47750 (0.0008) -[2023-10-12 05:11:07,189][78091] Updated weights for policy 0, policy_version 47760 (0.0007) -[2023-10-12 05:11:07,566][78091] Updated weights for policy 0, policy_version 47770 (0.0009) -[2023-10-12 05:11:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 97615872. Throughput: 0: 1600.3, 1: 1595.4. Samples: 24417222. Policy #0 lag: (min: 9.0, avg: 15.8, max: 41.0) -[2023-10-12 05:11:10,202][77203] Avg episode reward: [(0, '47.010'), (1, '39.230')] -[2023-10-12 05:11:10,210][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000047776_48922624.pth... -[2023-10-12 05:11:10,211][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000047552_48693248.pth... -[2023-10-12 05:11:10,241][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000046080_47185920.pth -[2023-10-12 05:11:10,250][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000046272_47382528.pth -[2023-10-12 05:11:10,758][78123] Updated weights for policy 1, policy_version 47560 (0.0007) -[2023-10-12 05:11:11,137][78123] Updated weights for policy 1, policy_version 47570 (0.0007) -[2023-10-12 05:11:11,506][78123] Updated weights for policy 1, policy_version 47580 (0.0008) -[2023-10-12 05:11:11,752][78091] Updated weights for policy 0, policy_version 47780 (0.0008) -[2023-10-12 05:11:12,137][78091] Updated weights for policy 0, policy_version 47790 (0.0008) -[2023-10-12 05:11:12,499][78091] Updated weights for policy 0, policy_version 47800 (0.0010) -[2023-10-12 05:11:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 97681408. Throughput: 0: 1602.7, 1: 1585.5. Samples: 24425996. Policy #0 lag: (min: 9.0, avg: 15.8, max: 41.0) -[2023-10-12 05:11:15,201][77203] Avg episode reward: [(0, '44.640'), (1, '40.940')] -[2023-10-12 05:11:15,878][78123] Updated weights for policy 1, policy_version 47590 (0.0009) -[2023-10-12 05:11:16,237][78123] Updated weights for policy 1, policy_version 47600 (0.0008) -[2023-10-12 05:11:16,604][78123] Updated weights for policy 1, policy_version 47610 (0.0007) -[2023-10-12 05:11:16,836][78091] Updated weights for policy 0, policy_version 47810 (0.0009) -[2023-10-12 05:11:17,210][78091] Updated weights for policy 0, policy_version 47820 (0.0011) -[2023-10-12 05:11:17,583][78091] Updated weights for policy 0, policy_version 47830 (0.0009) -[2023-10-12 05:11:17,948][78091] Updated weights for policy 0, policy_version 47840 (0.0010) -[2023-10-12 05:11:20,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 97746944. Throughput: 0: 1596.2, 1: 1584.9. Samples: 24445394. Policy #0 lag: (min: 9.0, avg: 15.8, max: 41.0) -[2023-10-12 05:11:20,202][77203] Avg episode reward: [(0, '47.390'), (1, '45.040')] -[2023-10-12 05:11:21,116][78123] Updated weights for policy 1, policy_version 47620 (0.0008) -[2023-10-12 05:11:21,484][78123] Updated weights for policy 1, policy_version 47630 (0.0010) -[2023-10-12 05:11:21,858][78123] Updated weights for policy 1, policy_version 47640 (0.0009) -[2023-10-12 05:11:22,321][78091] Updated weights for policy 0, policy_version 47850 (0.0010) -[2023-10-12 05:11:22,702][78091] Updated weights for policy 0, policy_version 47860 (0.0010) -[2023-10-12 05:11:23,069][78091] Updated weights for policy 0, policy_version 47870 (0.0009) -[2023-10-12 05:11:25,201][77203] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 12773.9). Total num frames: 97812480. Throughput: 0: 1598.8, 1: 1584.4. Samples: 24464768. Policy #0 lag: (min: 9.0, avg: 15.8, max: 41.0) -[2023-10-12 05:11:25,202][77203] Avg episode reward: [(0, '48.530'), (1, '39.580')] -[2023-10-12 05:11:26,099][78123] Updated weights for policy 1, policy_version 47650 (0.0009) -[2023-10-12 05:11:26,470][78123] Updated weights for policy 1, policy_version 47660 (0.0007) -[2023-10-12 05:11:26,830][78123] Updated weights for policy 1, policy_version 47670 (0.0009) -[2023-10-12 05:11:27,196][78123] Updated weights for policy 1, policy_version 47680 (0.0009) -[2023-10-12 05:11:27,434][78091] Updated weights for policy 0, policy_version 47880 (0.0009) -[2023-10-12 05:11:27,806][78091] Updated weights for policy 0, policy_version 47890 (0.0008) -[2023-10-12 05:11:28,184][78091] Updated weights for policy 0, policy_version 47900 (0.0009) -[2023-10-12 05:11:30,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 97878016. Throughput: 0: 1609.9, 1: 1584.5. Samples: 24473764. Policy #0 lag: (min: 20.0, avg: 20.7, max: 39.0) -[2023-10-12 05:11:30,201][77203] Avg episode reward: [(0, '43.280'), (1, '44.600')] -[2023-10-12 05:11:31,550][78123] Updated weights for policy 1, policy_version 47690 (0.0007) -[2023-10-12 05:11:31,914][78123] Updated weights for policy 1, policy_version 47700 (0.0007) -[2023-10-12 05:11:32,279][78123] Updated weights for policy 1, policy_version 47710 (0.0007) -[2023-10-12 05:11:32,436][78091] Updated weights for policy 0, policy_version 47910 (0.0009) -[2023-10-12 05:11:32,804][78091] Updated weights for policy 0, policy_version 47920 (0.0009) -[2023-10-12 05:11:33,169][78091] Updated weights for policy 0, policy_version 47930 (0.0007) -[2023-10-12 05:11:35,201][77203] Fps is (10 sec: 13107.8, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 97943552. Throughput: 0: 1597.9, 1: 1588.9. Samples: 24493168. Policy #0 lag: (min: 20.0, avg: 20.7, max: 39.0) -[2023-10-12 05:11:35,201][77203] Avg episode reward: [(0, '43.350'), (1, '47.330')] -[2023-10-12 05:11:36,674][78123] Updated weights for policy 1, policy_version 47720 (0.0009) -[2023-10-12 05:11:37,041][78123] Updated weights for policy 1, policy_version 47730 (0.0010) -[2023-10-12 05:11:37,411][78123] Updated weights for policy 1, policy_version 47740 (0.0010) -[2023-10-12 05:11:37,455][78091] Updated weights for policy 0, policy_version 47940 (0.0008) -[2023-10-12 05:11:37,828][78091] Updated weights for policy 0, policy_version 47950 (0.0008) -[2023-10-12 05:11:38,211][78091] Updated weights for policy 0, policy_version 47960 (0.0009) -[2023-10-12 05:11:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 98009088. Throughput: 0: 1599.4, 1: 1589.5. Samples: 24512674. Policy #0 lag: (min: 20.0, avg: 20.7, max: 39.0) -[2023-10-12 05:11:40,201][77203] Avg episode reward: [(0, '46.750'), (1, '40.730')] -[2023-10-12 05:11:41,779][78123] Updated weights for policy 1, policy_version 47750 (0.0008) -[2023-10-12 05:11:42,134][78123] Updated weights for policy 1, policy_version 47760 (0.0008) -[2023-10-12 05:11:42,509][78123] Updated weights for policy 1, policy_version 47770 (0.0008) -[2023-10-12 05:11:42,619][78091] Updated weights for policy 0, policy_version 47970 (0.0009) -[2023-10-12 05:11:42,985][78091] Updated weights for policy 0, policy_version 47980 (0.0009) -[2023-10-12 05:11:43,363][78091] Updated weights for policy 0, policy_version 47990 (0.0009) -[2023-10-12 05:11:43,731][78091] Updated weights for policy 0, policy_version 48000 (0.0007) -[2023-10-12 05:11:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 98074624. Throughput: 0: 1615.1, 1: 1589.2. Samples: 24522012. Policy #0 lag: (min: 20.0, avg: 20.7, max: 39.0) -[2023-10-12 05:11:45,201][77203] Avg episode reward: [(0, '41.870'), (1, '40.410')] -[2023-10-12 05:11:46,934][78123] Updated weights for policy 1, policy_version 47780 (0.0009) -[2023-10-12 05:11:47,300][78123] Updated weights for policy 1, policy_version 47790 (0.0011) -[2023-10-12 05:11:47,669][78123] Updated weights for policy 1, policy_version 47800 (0.0009) -[2023-10-12 05:11:47,915][78091] Updated weights for policy 0, policy_version 48010 (0.0009) -[2023-10-12 05:11:48,273][78091] Updated weights for policy 0, policy_version 48020 (0.0010) -[2023-10-12 05:11:48,643][78091] Updated weights for policy 0, policy_version 48030 (0.0009) -[2023-10-12 05:11:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 98140160. Throughput: 0: 1591.2, 1: 1583.5. Samples: 24540490. Policy #0 lag: (min: 20.0, avg: 20.7, max: 39.0) -[2023-10-12 05:11:50,201][77203] Avg episode reward: [(0, '45.150'), (1, '44.810')] -[2023-10-12 05:11:52,045][78123] Updated weights for policy 1, policy_version 47810 (0.0007) -[2023-10-12 05:11:52,415][78123] Updated weights for policy 1, policy_version 47820 (0.0008) -[2023-10-12 05:11:52,796][78123] Updated weights for policy 1, policy_version 47830 (0.0008) -[2023-10-12 05:11:53,037][78091] Updated weights for policy 0, policy_version 48040 (0.0008) -[2023-10-12 05:11:53,164][78123] Updated weights for policy 1, policy_version 47840 (0.0009) -[2023-10-12 05:11:53,410][78091] Updated weights for policy 0, policy_version 48050 (0.0009) -[2023-10-12 05:11:53,783][78091] Updated weights for policy 0, policy_version 48060 (0.0008) -[2023-10-12 05:11:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 98205696. Throughput: 0: 1591.4, 1: 1582.5. Samples: 24560048. Policy #0 lag: (min: 20.0, avg: 20.7, max: 39.0) -[2023-10-12 05:11:55,201][77203] Avg episode reward: [(0, '50.460'), (1, '48.970')] -[2023-10-12 05:11:57,405][78123] Updated weights for policy 1, policy_version 47850 (0.0008) -[2023-10-12 05:11:57,768][78123] Updated weights for policy 1, policy_version 47860 (0.0007) -[2023-10-12 05:11:57,989][78091] Updated weights for policy 0, policy_version 48070 (0.0007) -[2023-10-12 05:11:58,139][78123] Updated weights for policy 1, policy_version 47870 (0.0009) -[2023-10-12 05:11:58,360][78091] Updated weights for policy 0, policy_version 48080 (0.0009) -[2023-10-12 05:11:58,728][78091] Updated weights for policy 0, policy_version 48090 (0.0011) -[2023-10-12 05:12:00,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 98271232. Throughput: 0: 1615.6, 1: 1594.2. Samples: 24570436. Policy #0 lag: (min: 20.0, avg: 20.7, max: 39.0) -[2023-10-12 05:12:00,202][77203] Avg episode reward: [(0, '51.410'), (1, '39.970')] -[2023-10-12 05:12:02,286][78123] Updated weights for policy 1, policy_version 47880 (0.0009) -[2023-10-12 05:12:02,656][78123] Updated weights for policy 1, policy_version 47890 (0.0008) -[2023-10-12 05:12:03,021][78123] Updated weights for policy 1, policy_version 47900 (0.0010) -[2023-10-12 05:12:03,124][78091] Updated weights for policy 0, policy_version 48100 (0.0009) -[2023-10-12 05:12:03,497][78091] Updated weights for policy 0, policy_version 48110 (0.0009) -[2023-10-12 05:12:03,872][78091] Updated weights for policy 0, policy_version 48120 (0.0009) -[2023-10-12 05:12:05,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 98336768. Throughput: 0: 1597.9, 1: 1587.5. Samples: 24588738. Policy #0 lag: (min: 15.0, avg: 18.0, max: 47.0) -[2023-10-12 05:12:05,202][77203] Avg episode reward: [(0, '48.670'), (1, '44.930')] -[2023-10-12 05:12:07,103][78123] Updated weights for policy 1, policy_version 47910 (0.0008) -[2023-10-12 05:12:07,471][78123] Updated weights for policy 1, policy_version 47920 (0.0008) -[2023-10-12 05:12:07,845][78123] Updated weights for policy 1, policy_version 47930 (0.0008) -[2023-10-12 05:12:08,244][78091] Updated weights for policy 0, policy_version 48130 (0.0010) -[2023-10-12 05:12:08,617][78091] Updated weights for policy 0, policy_version 48140 (0.0007) -[2023-10-12 05:12:08,985][78091] Updated weights for policy 0, policy_version 48150 (0.0008) -[2023-10-12 05:12:09,348][78091] Updated weights for policy 0, policy_version 48160 (0.0008) -[2023-10-12 05:12:10,201][77203] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 98402304. Throughput: 0: 1591.7, 1: 1601.2. Samples: 24608452. Policy #0 lag: (min: 15.0, avg: 18.0, max: 47.0) -[2023-10-12 05:12:10,202][77203] Avg episode reward: [(0, '50.490'), (1, '48.370')] -[2023-10-12 05:12:12,086][78123] Updated weights for policy 1, policy_version 47940 (0.0007) -[2023-10-12 05:12:12,449][78123] Updated weights for policy 1, policy_version 47950 (0.0009) -[2023-10-12 05:12:12,822][78123] Updated weights for policy 1, policy_version 47960 (0.0011) -[2023-10-12 05:12:13,589][78091] Updated weights for policy 0, policy_version 48170 (0.0007) -[2023-10-12 05:12:13,953][78091] Updated weights for policy 0, policy_version 48180 (0.0007) -[2023-10-12 05:12:14,328][78091] Updated weights for policy 0, policy_version 48190 (0.0009) -[2023-10-12 05:12:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 98467840. Throughput: 0: 1611.2, 1: 1614.8. Samples: 24618934. Policy #0 lag: (min: 15.0, avg: 18.0, max: 47.0) -[2023-10-12 05:12:15,201][77203] Avg episode reward: [(0, '45.060'), (1, '43.860')] -[2023-10-12 05:12:17,185][78123] Updated weights for policy 1, policy_version 47970 (0.0009) -[2023-10-12 05:12:17,558][78123] Updated weights for policy 1, policy_version 47980 (0.0008) -[2023-10-12 05:12:17,926][78123] Updated weights for policy 1, policy_version 47990 (0.0009) -[2023-10-12 05:12:18,294][78123] Updated weights for policy 1, policy_version 48000 (0.0009) -[2023-10-12 05:12:18,715][78091] Updated weights for policy 0, policy_version 48200 (0.0010) -[2023-10-12 05:12:19,078][78091] Updated weights for policy 0, policy_version 48210 (0.0008) -[2023-10-12 05:12:19,446][78091] Updated weights for policy 0, policy_version 48220 (0.0008) -[2023-10-12 05:12:20,201][77203] Fps is (10 sec: 13107.8, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 98533376. Throughput: 0: 1612.1, 1: 1601.3. Samples: 24637772. Policy #0 lag: (min: 15.0, avg: 18.0, max: 47.0) -[2023-10-12 05:12:20,201][77203] Avg episode reward: [(0, '42.430'), (1, '42.720')] -[2023-10-12 05:12:22,599][78123] Updated weights for policy 1, policy_version 48010 (0.0011) -[2023-10-12 05:12:22,958][78123] Updated weights for policy 1, policy_version 48020 (0.0011) -[2023-10-12 05:12:23,322][78123] Updated weights for policy 1, policy_version 48030 (0.0009) -[2023-10-12 05:12:23,636][78091] Updated weights for policy 0, policy_version 48230 (0.0008) -[2023-10-12 05:12:24,015][78091] Updated weights for policy 0, policy_version 48240 (0.0010) -[2023-10-12 05:12:24,392][78091] Updated weights for policy 0, policy_version 48250 (0.0009) -[2023-10-12 05:12:25,201][77203] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 98598912. Throughput: 0: 1597.8, 1: 1601.9. Samples: 24656662. Policy #0 lag: (min: 15.0, avg: 18.0, max: 47.0) -[2023-10-12 05:12:25,202][77203] Avg episode reward: [(0, '42.790'), (1, '45.210')] -[2023-10-12 05:12:27,713][78123] Updated weights for policy 1, policy_version 48040 (0.0008) -[2023-10-12 05:12:28,091][78123] Updated weights for policy 1, policy_version 48050 (0.0008) -[2023-10-12 05:12:28,455][78123] Updated weights for policy 1, policy_version 48060 (0.0010) -[2023-10-12 05:12:28,631][78091] Updated weights for policy 0, policy_version 48260 (0.0007) -[2023-10-12 05:12:28,998][78091] Updated weights for policy 0, policy_version 48270 (0.0010) -[2023-10-12 05:12:29,365][78091] Updated weights for policy 0, policy_version 48280 (0.0010) -[2023-10-12 05:12:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 98664448. Throughput: 0: 1606.9, 1: 1620.8. Samples: 24667260. Policy #0 lag: (min: 15.0, avg: 18.0, max: 47.0) -[2023-10-12 05:12:30,201][77203] Avg episode reward: [(0, '43.250'), (1, '45.990')] -[2023-10-12 05:12:32,851][78123] Updated weights for policy 1, policy_version 48070 (0.0009) -[2023-10-12 05:12:33,230][78123] Updated weights for policy 1, policy_version 48080 (0.0010) -[2023-10-12 05:12:33,601][78123] Updated weights for policy 1, policy_version 48090 (0.0009) -[2023-10-12 05:12:33,625][78091] Updated weights for policy 0, policy_version 48290 (0.0007) -[2023-10-12 05:12:33,991][78091] Updated weights for policy 0, policy_version 48300 (0.0008) -[2023-10-12 05:12:34,359][78091] Updated weights for policy 0, policy_version 48310 (0.0011) -[2023-10-12 05:12:34,734][78091] Updated weights for policy 0, policy_version 48320 (0.0008) -[2023-10-12 05:12:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.1, 300 sec: 12885.0). Total num frames: 98729984. Throughput: 0: 1626.0, 1: 1604.5. Samples: 24685864. Policy #0 lag: (min: 15.0, avg: 18.0, max: 47.0) -[2023-10-12 05:12:35,202][77203] Avg episode reward: [(0, '48.030'), (1, '43.920')] -[2023-10-12 05:12:38,154][78123] Updated weights for policy 1, policy_version 48100 (0.0008) -[2023-10-12 05:12:38,522][78123] Updated weights for policy 1, policy_version 48110 (0.0009) -[2023-10-12 05:12:38,885][78123] Updated weights for policy 1, policy_version 48120 (0.0008) -[2023-10-12 05:12:38,982][78091] Updated weights for policy 0, policy_version 48330 (0.0008) -[2023-10-12 05:12:39,347][78091] Updated weights for policy 0, policy_version 48340 (0.0009) -[2023-10-12 05:12:39,716][78091] Updated weights for policy 0, policy_version 48350 (0.0010) -[2023-10-12 05:12:40,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 98795520. Throughput: 0: 1606.3, 1: 1597.9. Samples: 24704242. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-10-12 05:12:40,202][77203] Avg episode reward: [(0, '47.780'), (1, '43.090')] -[2023-10-12 05:12:43,173][78123] Updated weights for policy 1, policy_version 48130 (0.0007) -[2023-10-12 05:12:43,546][78123] Updated weights for policy 1, policy_version 48140 (0.0007) -[2023-10-12 05:12:43,907][78123] Updated weights for policy 1, policy_version 48150 (0.0008) -[2023-10-12 05:12:44,156][78091] Updated weights for policy 0, policy_version 48360 (0.0008) -[2023-10-12 05:12:44,275][78123] Updated weights for policy 1, policy_version 48160 (0.0009) -[2023-10-12 05:12:44,526][78091] Updated weights for policy 0, policy_version 48370 (0.0010) -[2023-10-12 05:12:44,910][78091] Updated weights for policy 0, policy_version 48380 (0.0010) -[2023-10-12 05:12:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.1, 300 sec: 12885.0). Total num frames: 98861056. Throughput: 0: 1601.6, 1: 1609.1. Samples: 24714916. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-10-12 05:12:45,202][77203] Avg episode reward: [(0, '46.840'), (1, '45.610')] -[2023-10-12 05:12:48,608][78123] Updated weights for policy 1, policy_version 48170 (0.0010) -[2023-10-12 05:12:48,974][78123] Updated weights for policy 1, policy_version 48180 (0.0009) -[2023-10-12 05:12:49,167][78091] Updated weights for policy 0, policy_version 48390 (0.0009) -[2023-10-12 05:12:49,351][78123] Updated weights for policy 1, policy_version 48190 (0.0008) -[2023-10-12 05:12:49,541][78091] Updated weights for policy 0, policy_version 48400 (0.0009) -[2023-10-12 05:12:49,905][78091] Updated weights for policy 0, policy_version 48410 (0.0009) -[2023-10-12 05:12:50,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 98926592. Throughput: 0: 1619.4, 1: 1606.7. Samples: 24733912. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-10-12 05:12:50,202][77203] Avg episode reward: [(0, '50.870'), (1, '48.270')] -[2023-10-12 05:12:53,646][78123] Updated weights for policy 1, policy_version 48200 (0.0010) -[2023-10-12 05:12:54,015][78123] Updated weights for policy 1, policy_version 48210 (0.0010) -[2023-10-12 05:12:54,139][78091] Updated weights for policy 0, policy_version 48420 (0.0009) -[2023-10-12 05:12:54,376][78123] Updated weights for policy 1, policy_version 48220 (0.0008) -[2023-10-12 05:12:54,498][78091] Updated weights for policy 0, policy_version 48430 (0.0007) -[2023-10-12 05:12:54,876][78091] Updated weights for policy 0, policy_version 48440 (0.0008) -[2023-10-12 05:12:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.1, 300 sec: 12885.0). Total num frames: 98992128. Throughput: 0: 1607.2, 1: 1578.2. Samples: 24751794. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-10-12 05:12:55,202][77203] Avg episode reward: [(0, '47.590'), (1, '41.400')] -[2023-10-12 05:12:58,660][78123] Updated weights for policy 1, policy_version 48230 (0.0008) -[2023-10-12 05:12:59,030][78123] Updated weights for policy 1, policy_version 48240 (0.0007) -[2023-10-12 05:12:59,114][78091] Updated weights for policy 0, policy_version 48450 (0.0008) -[2023-10-12 05:12:59,402][78123] Updated weights for policy 1, policy_version 48250 (0.0007) -[2023-10-12 05:12:59,484][78091] Updated weights for policy 0, policy_version 48460 (0.0009) -[2023-10-12 05:12:59,852][78091] Updated weights for policy 0, policy_version 48470 (0.0010) -[2023-10-12 05:13:00,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 99024896. Throughput: 0: 1593.7, 1: 1592.5. Samples: 24762314. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-10-12 05:13:00,201][77203] Avg episode reward: [(0, '44.240'), (1, '43.540')] -[2023-10-12 05:13:00,234][78091] Updated weights for policy 0, policy_version 48480 (0.0008) -[2023-10-12 05:13:03,803][78123] Updated weights for policy 1, policy_version 48260 (0.0008) -[2023-10-12 05:13:04,157][78123] Updated weights for policy 1, policy_version 48270 (0.0008) -[2023-10-12 05:13:04,530][78123] Updated weights for policy 1, policy_version 48280 (0.0007) -[2023-10-12 05:13:04,542][78091] Updated weights for policy 0, policy_version 48490 (0.0008) -[2023-10-12 05:13:04,927][78091] Updated weights for policy 0, policy_version 48500 (0.0008) -[2023-10-12 05:13:05,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 99090432. Throughput: 0: 1603.1, 1: 1599.5. Samples: 24781888. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-10-12 05:13:05,202][77203] Avg episode reward: [(0, '44.330'), (1, '47.440')] -[2023-10-12 05:13:05,301][78091] Updated weights for policy 0, policy_version 48510 (0.0009) -[2023-10-12 05:13:08,673][78123] Updated weights for policy 1, policy_version 48290 (0.0008) -[2023-10-12 05:13:09,046][78123] Updated weights for policy 1, policy_version 48300 (0.0012) -[2023-10-12 05:13:09,403][78123] Updated weights for policy 1, policy_version 48310 (0.0009) -[2023-10-12 05:13:09,770][78123] Updated weights for policy 1, policy_version 48320 (0.0008) -[2023-10-12 05:13:09,787][78091] Updated weights for policy 0, policy_version 48520 (0.0009) -[2023-10-12 05:13:10,154][78091] Updated weights for policy 0, policy_version 48530 (0.0010) -[2023-10-12 05:13:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 99155968. Throughput: 0: 1610.9, 1: 1582.1. Samples: 24800348. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-10-12 05:13:10,201][77203] Avg episode reward: [(0, '52.800'), (1, '43.740')] -[2023-10-12 05:13:10,208][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000048320_49479680.pth... -[2023-10-12 05:13:10,244][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000046816_47939584.pth -[2023-10-12 05:13:10,526][78091] Updated weights for policy 0, policy_version 48540 (0.0009) -[2023-10-12 05:13:10,673][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000048544_49709056.pth... -[2023-10-12 05:13:10,710][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000047040_48168960.pth -[2023-10-12 05:13:14,110][78123] Updated weights for policy 1, policy_version 48330 (0.0009) -[2023-10-12 05:13:14,476][78123] Updated weights for policy 1, policy_version 48340 (0.0009) -[2023-10-12 05:13:14,786][78091] Updated weights for policy 0, policy_version 48550 (0.0008) -[2023-10-12 05:13:14,845][78123] Updated weights for policy 1, policy_version 48350 (0.0007) -[2023-10-12 05:13:15,151][78091] Updated weights for policy 0, policy_version 48560 (0.0008) -[2023-10-12 05:13:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 99221504. Throughput: 0: 1592.4, 1: 1587.4. Samples: 24810350. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-10-12 05:13:15,202][77203] Avg episode reward: [(0, '50.850'), (1, '45.230')] -[2023-10-12 05:13:15,526][78091] Updated weights for policy 0, policy_version 48570 (0.0009) -[2023-10-12 05:13:19,333][78123] Updated weights for policy 1, policy_version 48360 (0.0009) -[2023-10-12 05:13:19,695][78123] Updated weights for policy 1, policy_version 48370 (0.0009) -[2023-10-12 05:13:19,759][78091] Updated weights for policy 0, policy_version 48580 (0.0007) -[2023-10-12 05:13:20,067][78123] Updated weights for policy 1, policy_version 48380 (0.0009) -[2023-10-12 05:13:20,132][78091] Updated weights for policy 0, policy_version 48590 (0.0007) -[2023-10-12 05:13:20,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 99254272. Throughput: 0: 1596.6, 1: 1604.6. Samples: 24829918. Policy #0 lag: (min: 31.0, avg: 46.8, max: 63.0) -[2023-10-12 05:13:20,201][77203] Avg episode reward: [(0, '44.190'), (1, '46.010')] -[2023-10-12 05:13:20,504][78091] Updated weights for policy 0, policy_version 48600 (0.0009) -[2023-10-12 05:13:24,606][78123] Updated weights for policy 1, policy_version 48390 (0.0008) -[2023-10-12 05:13:24,701][78091] Updated weights for policy 0, policy_version 48610 (0.0009) -[2023-10-12 05:13:24,965][78123] Updated weights for policy 1, policy_version 48400 (0.0008) -[2023-10-12 05:13:25,079][78091] Updated weights for policy 0, policy_version 48620 (0.0007) -[2023-10-12 05:13:25,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 99319808. Throughput: 0: 1614.0, 1: 1600.9. Samples: 24848916. Policy #0 lag: (min: 31.0, avg: 46.8, max: 63.0) -[2023-10-12 05:13:25,202][77203] Avg episode reward: [(0, '48.460'), (1, '50.060')] -[2023-10-12 05:13:25,328][78123] Updated weights for policy 1, policy_version 48410 (0.0007) -[2023-10-12 05:13:25,443][78091] Updated weights for policy 0, policy_version 48630 (0.0008) -[2023-10-12 05:13:25,548][77950] Saving new best policy, reward=50.060! -[2023-10-12 05:13:25,811][78091] Updated weights for policy 0, policy_version 48640 (0.0011) -[2023-10-12 05:13:29,600][78123] Updated weights for policy 1, policy_version 48420 (0.0007) -[2023-10-12 05:13:29,980][78123] Updated weights for policy 1, policy_version 48430 (0.0008) -[2023-10-12 05:13:30,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 99385344. Throughput: 0: 1591.9, 1: 1582.6. Samples: 24857766. Policy #0 lag: (min: 31.0, avg: 46.8, max: 63.0) -[2023-10-12 05:13:30,202][77203] Avg episode reward: [(0, '45.210'), (1, '44.590')] -[2023-10-12 05:13:30,213][78091] Updated weights for policy 0, policy_version 48650 (0.0009) -[2023-10-12 05:13:30,346][78123] Updated weights for policy 1, policy_version 48440 (0.0009) -[2023-10-12 05:13:30,583][78091] Updated weights for policy 0, policy_version 48660 (0.0008) -[2023-10-12 05:13:30,956][78091] Updated weights for policy 0, policy_version 48670 (0.0008) -[2023-10-12 05:13:34,754][78123] Updated weights for policy 1, policy_version 48450 (0.0009) -[2023-10-12 05:13:35,145][78123] Updated weights for policy 1, policy_version 48460 (0.0010) -[2023-10-12 05:13:35,157][78091] Updated weights for policy 0, policy_version 48680 (0.0008) -[2023-10-12 05:13:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 99450880. Throughput: 0: 1595.2, 1: 1591.9. Samples: 24877334. Policy #0 lag: (min: 31.0, avg: 46.8, max: 63.0) -[2023-10-12 05:13:35,202][77203] Avg episode reward: [(0, '39.640'), (1, '44.690')] -[2023-10-12 05:13:35,513][78123] Updated weights for policy 1, policy_version 48470 (0.0008) -[2023-10-12 05:13:35,523][78091] Updated weights for policy 0, policy_version 48690 (0.0007) -[2023-10-12 05:13:35,878][78123] Updated weights for policy 1, policy_version 48480 (0.0009) -[2023-10-12 05:13:35,897][78091] Updated weights for policy 0, policy_version 48700 (0.0008) -[2023-10-12 05:13:40,190][78091] Updated weights for policy 0, policy_version 48710 (0.0009) -[2023-10-12 05:13:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 99516416. Throughput: 0: 1617.6, 1: 1607.1. Samples: 24896902. Policy #0 lag: (min: 31.0, avg: 46.8, max: 63.0) -[2023-10-12 05:13:40,201][77203] Avg episode reward: [(0, '39.090'), (1, '46.480')] -[2023-10-12 05:13:40,288][78123] Updated weights for policy 1, policy_version 48490 (0.0009) -[2023-10-12 05:13:40,559][78091] Updated weights for policy 0, policy_version 48720 (0.0010) -[2023-10-12 05:13:40,648][78123] Updated weights for policy 1, policy_version 48500 (0.0008) -[2023-10-12 05:13:40,942][78091] Updated weights for policy 0, policy_version 48730 (0.0008) -[2023-10-12 05:13:41,015][78123] Updated weights for policy 1, policy_version 48510 (0.0008) -[2023-10-12 05:13:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 99581952. Throughput: 0: 1600.7, 1: 1578.1. Samples: 24905362. Policy #0 lag: (min: 31.0, avg: 46.8, max: 63.0) -[2023-10-12 05:13:45,202][77203] Avg episode reward: [(0, '44.700'), (1, '41.470')] -[2023-10-12 05:13:45,291][78091] Updated weights for policy 0, policy_version 48740 (0.0008) -[2023-10-12 05:13:45,339][78123] Updated weights for policy 1, policy_version 48520 (0.0010) -[2023-10-12 05:13:45,654][78091] Updated weights for policy 0, policy_version 48750 (0.0009) -[2023-10-12 05:13:45,701][78123] Updated weights for policy 1, policy_version 48530 (0.0009) -[2023-10-12 05:13:46,023][78091] Updated weights for policy 0, policy_version 48760 (0.0009) -[2023-10-12 05:13:46,067][78123] Updated weights for policy 1, policy_version 48540 (0.0009) -[2023-10-12 05:13:50,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 99647488. Throughput: 0: 1596.8, 1: 1582.1. Samples: 24924938. Policy #0 lag: (min: 31.0, avg: 46.8, max: 63.0) -[2023-10-12 05:13:50,202][77203] Avg episode reward: [(0, '49.570'), (1, '43.620')] -[2023-10-12 05:13:50,322][78091] Updated weights for policy 0, policy_version 48770 (0.0010) -[2023-10-12 05:13:50,362][78123] Updated weights for policy 1, policy_version 48550 (0.0007) -[2023-10-12 05:13:50,694][78091] Updated weights for policy 0, policy_version 48780 (0.0008) -[2023-10-12 05:13:50,735][78123] Updated weights for policy 1, policy_version 48560 (0.0008) -[2023-10-12 05:13:51,071][78091] Updated weights for policy 0, policy_version 48790 (0.0009) -[2023-10-12 05:13:51,102][78123] Updated weights for policy 1, policy_version 48570 (0.0007) -[2023-10-12 05:13:51,446][78091] Updated weights for policy 0, policy_version 48800 (0.0009) -[2023-10-12 05:13:55,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 99713024. Throughput: 0: 1600.0, 1: 1604.0. Samples: 24944532. Policy #0 lag: (min: 7.0, avg: 15.0, max: 39.0) -[2023-10-12 05:13:55,202][77203] Avg episode reward: [(0, '44.990'), (1, '43.960')] -[2023-10-12 05:13:55,327][78123] Updated weights for policy 1, policy_version 48580 (0.0008) -[2023-10-12 05:13:55,686][78123] Updated weights for policy 1, policy_version 48590 (0.0008) -[2023-10-12 05:13:55,911][78091] Updated weights for policy 0, policy_version 48810 (0.0008) -[2023-10-12 05:13:56,042][78123] Updated weights for policy 1, policy_version 48600 (0.0008) -[2023-10-12 05:13:56,283][78091] Updated weights for policy 0, policy_version 48820 (0.0009) -[2023-10-12 05:13:56,664][78091] Updated weights for policy 0, policy_version 48830 (0.0008) -[2023-10-12 05:14:00,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 99778560. Throughput: 0: 1592.6, 1: 1584.4. Samples: 24953312. Policy #0 lag: (min: 7.0, avg: 15.0, max: 39.0) -[2023-10-12 05:14:00,201][77203] Avg episode reward: [(0, '43.710'), (1, '46.060')] -[2023-10-12 05:14:00,394][78123] Updated weights for policy 1, policy_version 48610 (0.0009) -[2023-10-12 05:14:00,765][78123] Updated weights for policy 1, policy_version 48620 (0.0009) -[2023-10-12 05:14:00,944][78091] Updated weights for policy 0, policy_version 48840 (0.0009) -[2023-10-12 05:14:01,138][78123] Updated weights for policy 1, policy_version 48630 (0.0009) -[2023-10-12 05:14:01,308][78091] Updated weights for policy 0, policy_version 48850 (0.0009) -[2023-10-12 05:14:01,505][78123] Updated weights for policy 1, policy_version 48640 (0.0010) -[2023-10-12 05:14:01,670][78091] Updated weights for policy 0, policy_version 48860 (0.0009) -[2023-10-12 05:14:05,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 99844096. Throughput: 0: 1586.0, 1: 1581.3. Samples: 24972450. Policy #0 lag: (min: 7.0, avg: 15.0, max: 39.0) -[2023-10-12 05:14:05,202][77203] Avg episode reward: [(0, '44.460'), (1, '44.170')] -[2023-10-12 05:14:05,929][78123] Updated weights for policy 1, policy_version 48650 (0.0008) -[2023-10-12 05:14:06,135][78091] Updated weights for policy 0, policy_version 48870 (0.0009) -[2023-10-12 05:14:06,291][78123] Updated weights for policy 1, policy_version 48660 (0.0007) -[2023-10-12 05:14:06,503][78091] Updated weights for policy 0, policy_version 48880 (0.0008) -[2023-10-12 05:14:06,661][78123] Updated weights for policy 1, policy_version 48670 (0.0008) -[2023-10-12 05:14:06,880][78091] Updated weights for policy 0, policy_version 48890 (0.0008) -[2023-10-12 05:14:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 99909632. Throughput: 0: 1583.5, 1: 1591.1. Samples: 24991770. Policy #0 lag: (min: 7.0, avg: 15.0, max: 39.0) -[2023-10-12 05:14:10,202][77203] Avg episode reward: [(0, '53.060'), (1, '44.550')] -[2023-10-12 05:14:11,124][78123] Updated weights for policy 1, policy_version 48680 (0.0008) -[2023-10-12 05:14:11,177][78091] Updated weights for policy 0, policy_version 48900 (0.0009) -[2023-10-12 05:14:11,494][78123] Updated weights for policy 1, policy_version 48690 (0.0008) -[2023-10-12 05:14:11,546][78091] Updated weights for policy 0, policy_version 48910 (0.0007) -[2023-10-12 05:14:11,862][78123] Updated weights for policy 1, policy_version 48700 (0.0009) -[2023-10-12 05:14:11,912][78091] Updated weights for policy 0, policy_version 48920 (0.0007) -[2023-10-12 05:14:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 99975168. Throughput: 0: 1584.1, 1: 1582.7. Samples: 25000270. Policy #0 lag: (min: 7.0, avg: 15.0, max: 39.0) -[2023-10-12 05:14:15,201][77203] Avg episode reward: [(0, '47.500'), (1, '48.730')] -[2023-10-12 05:14:16,185][78091] Updated weights for policy 0, policy_version 48930 (0.0008) -[2023-10-12 05:14:16,232][78123] Updated weights for policy 1, policy_version 48710 (0.0008) -[2023-10-12 05:14:16,560][78091] Updated weights for policy 0, policy_version 48940 (0.0008) -[2023-10-12 05:14:16,586][78123] Updated weights for policy 1, policy_version 48720 (0.0009) -[2023-10-12 05:14:16,925][78091] Updated weights for policy 0, policy_version 48950 (0.0010) -[2023-10-12 05:14:16,951][78123] Updated weights for policy 1, policy_version 48730 (0.0008) -[2023-10-12 05:14:17,301][78091] Updated weights for policy 0, policy_version 48960 (0.0007) -[2023-10-12 05:14:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 100040704. Throughput: 0: 1584.2, 1: 1585.0. Samples: 25019946. Policy #0 lag: (min: 7.0, avg: 15.0, max: 39.0) -[2023-10-12 05:14:20,201][77203] Avg episode reward: [(0, '49.050'), (1, '44.100')] -[2023-10-12 05:14:21,346][78123] Updated weights for policy 1, policy_version 48740 (0.0008) -[2023-10-12 05:14:21,722][78091] Updated weights for policy 0, policy_version 48970 (0.0007) -[2023-10-12 05:14:21,723][78123] Updated weights for policy 1, policy_version 48750 (0.0009) -[2023-10-12 05:14:22,087][78091] Updated weights for policy 0, policy_version 48980 (0.0008) -[2023-10-12 05:14:22,096][78123] Updated weights for policy 1, policy_version 48760 (0.0008) -[2023-10-12 05:14:22,460][78091] Updated weights for policy 0, policy_version 48990 (0.0009) -[2023-10-12 05:14:25,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 12774.0). Total num frames: 100106240. Throughput: 0: 1579.7, 1: 1583.7. Samples: 25039256. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:14:25,201][77203] Avg episode reward: [(0, '48.170'), (1, '43.170')] -[2023-10-12 05:14:26,271][78123] Updated weights for policy 1, policy_version 48770 (0.0008) -[2023-10-12 05:14:26,635][78123] Updated weights for policy 1, policy_version 48780 (0.0009) -[2023-10-12 05:14:26,838][78091] Updated weights for policy 0, policy_version 49000 (0.0009) -[2023-10-12 05:14:27,001][78123] Updated weights for policy 1, policy_version 48790 (0.0008) -[2023-10-12 05:14:27,200][78091] Updated weights for policy 0, policy_version 49010 (0.0007) -[2023-10-12 05:14:27,367][78123] Updated weights for policy 1, policy_version 48800 (0.0007) -[2023-10-12 05:14:27,570][78091] Updated weights for policy 0, policy_version 49020 (0.0009) -[2023-10-12 05:14:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 100171776. Throughput: 0: 1580.0, 1: 1587.7. Samples: 25047912. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:14:30,201][77203] Avg episode reward: [(0, '41.900'), (1, '44.510')] -[2023-10-12 05:14:31,689][78123] Updated weights for policy 1, policy_version 48810 (0.0009) -[2023-10-12 05:14:31,904][78091] Updated weights for policy 0, policy_version 49030 (0.0008) -[2023-10-12 05:14:32,063][78123] Updated weights for policy 1, policy_version 48820 (0.0009) -[2023-10-12 05:14:32,266][78091] Updated weights for policy 0, policy_version 49040 (0.0010) -[2023-10-12 05:14:32,420][78123] Updated weights for policy 1, policy_version 48830 (0.0007) -[2023-10-12 05:14:32,637][78091] Updated weights for policy 0, policy_version 49050 (0.0010) -[2023-10-12 05:14:35,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 100237312. Throughput: 0: 1578.8, 1: 1581.7. Samples: 25067162. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:14:35,202][77203] Avg episode reward: [(0, '45.250'), (1, '48.220')] -[2023-10-12 05:14:36,779][78091] Updated weights for policy 0, policy_version 49060 (0.0010) -[2023-10-12 05:14:36,875][78123] Updated weights for policy 1, policy_version 48840 (0.0008) -[2023-10-12 05:14:37,151][78091] Updated weights for policy 0, policy_version 49070 (0.0009) -[2023-10-12 05:14:37,241][78123] Updated weights for policy 1, policy_version 48850 (0.0007) -[2023-10-12 05:14:37,514][78091] Updated weights for policy 0, policy_version 49080 (0.0008) -[2023-10-12 05:14:37,600][78123] Updated weights for policy 1, policy_version 48860 (0.0007) -[2023-10-12 05:14:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 100302848. Throughput: 0: 1582.7, 1: 1579.2. Samples: 25086816. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:14:40,201][77203] Avg episode reward: [(0, '49.510'), (1, '43.150')] -[2023-10-12 05:14:41,911][78123] Updated weights for policy 1, policy_version 48870 (0.0008) -[2023-10-12 05:14:41,911][78091] Updated weights for policy 0, policy_version 49090 (0.0007) -[2023-10-12 05:14:42,274][78123] Updated weights for policy 1, policy_version 48880 (0.0009) -[2023-10-12 05:14:42,311][78091] Updated weights for policy 0, policy_version 49100 (0.0009) -[2023-10-12 05:14:42,642][78123] Updated weights for policy 1, policy_version 48890 (0.0010) -[2023-10-12 05:14:42,680][78091] Updated weights for policy 0, policy_version 49110 (0.0007) -[2023-10-12 05:14:43,050][78091] Updated weights for policy 0, policy_version 49120 (0.0007) -[2023-10-12 05:14:45,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 100368384. Throughput: 0: 1587.9, 1: 1579.2. Samples: 25095832. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:14:45,202][77203] Avg episode reward: [(0, '48.080'), (1, '44.610')] -[2023-10-12 05:14:46,898][78123] Updated weights for policy 1, policy_version 48900 (0.0010) -[2023-10-12 05:14:47,263][78123] Updated weights for policy 1, policy_version 48910 (0.0010) -[2023-10-12 05:14:47,376][78091] Updated weights for policy 0, policy_version 49130 (0.0009) -[2023-10-12 05:14:47,634][78123] Updated weights for policy 1, policy_version 48920 (0.0008) -[2023-10-12 05:14:47,743][78091] Updated weights for policy 0, policy_version 49140 (0.0008) -[2023-10-12 05:14:48,119][78091] Updated weights for policy 0, policy_version 49150 (0.0010) -[2023-10-12 05:14:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 12774.0). Total num frames: 100433920. Throughput: 0: 1585.4, 1: 1578.0. Samples: 25114802. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:14:50,201][77203] Avg episode reward: [(0, '44.660'), (1, '44.590')] -[2023-10-12 05:14:51,939][78123] Updated weights for policy 1, policy_version 48930 (0.0008) -[2023-10-12 05:14:52,311][78123] Updated weights for policy 1, policy_version 48940 (0.0007) -[2023-10-12 05:14:52,556][78091] Updated weights for policy 0, policy_version 49160 (0.0008) -[2023-10-12 05:14:52,682][78123] Updated weights for policy 1, policy_version 48950 (0.0007) -[2023-10-12 05:14:52,934][78091] Updated weights for policy 0, policy_version 49170 (0.0009) -[2023-10-12 05:14:53,042][78123] Updated weights for policy 1, policy_version 48960 (0.0007) -[2023-10-12 05:14:53,308][78091] Updated weights for policy 0, policy_version 49180 (0.0010) -[2023-10-12 05:14:55,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 100499456. Throughput: 0: 1585.6, 1: 1581.8. Samples: 25134304. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:14:55,202][77203] Avg episode reward: [(0, '49.780'), (1, '51.020')] -[2023-10-12 05:14:55,211][77950] Saving new best policy, reward=51.020! -[2023-10-12 05:14:57,332][78123] Updated weights for policy 1, policy_version 48970 (0.0010) -[2023-10-12 05:14:57,588][78091] Updated weights for policy 0, policy_version 49190 (0.0008) -[2023-10-12 05:14:57,685][78123] Updated weights for policy 1, policy_version 48980 (0.0009) -[2023-10-12 05:14:57,951][78091] Updated weights for policy 0, policy_version 49200 (0.0009) -[2023-10-12 05:14:58,049][78123] Updated weights for policy 1, policy_version 48990 (0.0008) -[2023-10-12 05:14:58,327][78091] Updated weights for policy 0, policy_version 49210 (0.0008) -[2023-10-12 05:15:00,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 100564992. Throughput: 0: 1602.8, 1: 1594.2. Samples: 25144136. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-10-12 05:15:00,202][77203] Avg episode reward: [(0, '51.870'), (1, '46.800')] -[2023-10-12 05:15:02,252][78123] Updated weights for policy 1, policy_version 49000 (0.0010) -[2023-10-12 05:15:02,626][78123] Updated weights for policy 1, policy_version 49010 (0.0009) -[2023-10-12 05:15:02,687][78091] Updated weights for policy 0, policy_version 49220 (0.0008) -[2023-10-12 05:15:02,991][78123] Updated weights for policy 1, policy_version 49020 (0.0010) -[2023-10-12 05:15:03,057][78091] Updated weights for policy 0, policy_version 49230 (0.0007) -[2023-10-12 05:15:03,419][78091] Updated weights for policy 0, policy_version 49240 (0.0008) -[2023-10-12 05:15:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 100630528. Throughput: 0: 1585.2, 1: 1587.6. Samples: 25162722. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-10-12 05:15:05,202][77203] Avg episode reward: [(0, '42.950'), (1, '47.290')] -[2023-10-12 05:15:07,255][78123] Updated weights for policy 1, policy_version 49030 (0.0008) -[2023-10-12 05:15:07,633][78123] Updated weights for policy 1, policy_version 49040 (0.0009) -[2023-10-12 05:15:07,775][78091] Updated weights for policy 0, policy_version 49250 (0.0010) -[2023-10-12 05:15:07,987][78123] Updated weights for policy 1, policy_version 49050 (0.0008) -[2023-10-12 05:15:08,142][78091] Updated weights for policy 0, policy_version 49260 (0.0008) -[2023-10-12 05:15:08,514][78091] Updated weights for policy 0, policy_version 49270 (0.0010) -[2023-10-12 05:15:08,888][78091] Updated weights for policy 0, policy_version 49280 (0.0009) -[2023-10-12 05:15:10,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 100696064. Throughput: 0: 1584.0, 1: 1591.5. Samples: 25182150. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-10-12 05:15:10,201][77203] Avg episode reward: [(0, '43.350'), (1, '47.690')] -[2023-10-12 05:15:10,209][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000049056_50233344.pth... -[2023-10-12 05:15:10,209][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000049280_50462720.pth... -[2023-10-12 05:15:10,247][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000047552_48693248.pth -[2023-10-12 05:15:10,248][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000047776_48922624.pth -[2023-10-12 05:15:12,447][78123] Updated weights for policy 1, policy_version 49060 (0.0009) -[2023-10-12 05:15:12,808][78123] Updated weights for policy 1, policy_version 49070 (0.0010) -[2023-10-12 05:15:13,173][78123] Updated weights for policy 1, policy_version 49080 (0.0009) -[2023-10-12 05:15:13,226][78091] Updated weights for policy 0, policy_version 49290 (0.0010) -[2023-10-12 05:15:13,600][78091] Updated weights for policy 0, policy_version 49300 (0.0008) -[2023-10-12 05:15:13,975][78091] Updated weights for policy 0, policy_version 49310 (0.0008) -[2023-10-12 05:15:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 100761600. Throughput: 0: 1609.4, 1: 1606.1. Samples: 25192608. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-10-12 05:15:15,202][77203] Avg episode reward: [(0, '47.170'), (1, '47.500')] -[2023-10-12 05:15:17,499][78123] Updated weights for policy 1, policy_version 49090 (0.0008) -[2023-10-12 05:15:17,869][78123] Updated weights for policy 1, policy_version 49100 (0.0009) -[2023-10-12 05:15:18,231][78123] Updated weights for policy 1, policy_version 49110 (0.0007) -[2023-10-12 05:15:18,253][78091] Updated weights for policy 0, policy_version 49320 (0.0007) -[2023-10-12 05:15:18,596][78123] Updated weights for policy 1, policy_version 49120 (0.0009) -[2023-10-12 05:15:18,637][78091] Updated weights for policy 0, policy_version 49330 (0.0007) -[2023-10-12 05:15:19,009][78091] Updated weights for policy 0, policy_version 49340 (0.0007) -[2023-10-12 05:15:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 100827136. Throughput: 0: 1596.3, 1: 1588.6. Samples: 25210482. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-10-12 05:15:20,201][77203] Avg episode reward: [(0, '49.500'), (1, '42.680')] -[2023-10-12 05:15:23,116][78123] Updated weights for policy 1, policy_version 49130 (0.0007) -[2023-10-12 05:15:23,292][78091] Updated weights for policy 0, policy_version 49350 (0.0007) -[2023-10-12 05:15:23,476][78123] Updated weights for policy 1, policy_version 49140 (0.0008) -[2023-10-12 05:15:23,661][78091] Updated weights for policy 0, policy_version 49360 (0.0010) -[2023-10-12 05:15:23,840][78123] Updated weights for policy 1, policy_version 49150 (0.0009) -[2023-10-12 05:15:24,032][78091] Updated weights for policy 0, policy_version 49370 (0.0010) -[2023-10-12 05:15:25,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.1, 300 sec: 12885.0). Total num frames: 100892672. Throughput: 0: 1586.5, 1: 1586.3. Samples: 25229592. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-10-12 05:15:25,202][77203] Avg episode reward: [(0, '44.600'), (1, '43.140')] -[2023-10-12 05:15:28,386][78123] Updated weights for policy 1, policy_version 49160 (0.0008) -[2023-10-12 05:15:28,445][78091] Updated weights for policy 0, policy_version 49380 (0.0010) -[2023-10-12 05:15:28,744][78123] Updated weights for policy 1, policy_version 49170 (0.0009) -[2023-10-12 05:15:28,831][78091] Updated weights for policy 0, policy_version 49390 (0.0009) -[2023-10-12 05:15:29,114][78123] Updated weights for policy 1, policy_version 49180 (0.0010) -[2023-10-12 05:15:29,199][78091] Updated weights for policy 0, policy_version 49400 (0.0008) -[2023-10-12 05:15:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 100958208. Throughput: 0: 1608.8, 1: 1605.0. Samples: 25240452. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-10-12 05:15:30,202][77203] Avg episode reward: [(0, '50.680'), (1, '44.140')] -[2023-10-12 05:15:33,265][78091] Updated weights for policy 0, policy_version 49410 (0.0009) -[2023-10-12 05:15:33,359][78123] Updated weights for policy 1, policy_version 49190 (0.0008) -[2023-10-12 05:15:33,642][78091] Updated weights for policy 0, policy_version 49420 (0.0007) -[2023-10-12 05:15:33,718][78123] Updated weights for policy 1, policy_version 49200 (0.0009) -[2023-10-12 05:15:34,015][78091] Updated weights for policy 0, policy_version 49430 (0.0009) -[2023-10-12 05:15:34,084][78123] Updated weights for policy 1, policy_version 49210 (0.0009) -[2023-10-12 05:15:34,380][78091] Updated weights for policy 0, policy_version 49440 (0.0009) -[2023-10-12 05:15:35,201][77203] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 101023744. Throughput: 0: 1604.8, 1: 1596.8. Samples: 25258872. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:15:35,201][77203] Avg episode reward: [(0, '46.160'), (1, '45.180')] -[2023-10-12 05:15:38,619][78123] Updated weights for policy 1, policy_version 49220 (0.0007) -[2023-10-12 05:15:38,655][78091] Updated weights for policy 0, policy_version 49450 (0.0008) -[2023-10-12 05:15:38,985][78123] Updated weights for policy 1, policy_version 49230 (0.0009) -[2023-10-12 05:15:39,012][78091] Updated weights for policy 0, policy_version 49460 (0.0007) -[2023-10-12 05:15:39,350][78123] Updated weights for policy 1, policy_version 49240 (0.0009) -[2023-10-12 05:15:39,382][78091] Updated weights for policy 0, policy_version 49470 (0.0008) -[2023-10-12 05:15:40,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 101089280. Throughput: 0: 1595.1, 1: 1579.6. Samples: 25277162. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:15:40,201][77203] Avg episode reward: [(0, '42.410'), (1, '45.640')] -[2023-10-12 05:15:43,613][78091] Updated weights for policy 0, policy_version 49480 (0.0008) -[2023-10-12 05:15:43,789][78123] Updated weights for policy 1, policy_version 49250 (0.0010) -[2023-10-12 05:15:43,979][78091] Updated weights for policy 0, policy_version 49490 (0.0008) -[2023-10-12 05:15:44,142][78123] Updated weights for policy 1, policy_version 49260 (0.0008) -[2023-10-12 05:15:44,343][78091] Updated weights for policy 0, policy_version 49500 (0.0010) -[2023-10-12 05:15:44,511][78123] Updated weights for policy 1, policy_version 49270 (0.0009) -[2023-10-12 05:15:44,879][78123] Updated weights for policy 1, policy_version 49280 (0.0007) -[2023-10-12 05:15:45,201][77203] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 101154816. Throughput: 0: 1605.6, 1: 1590.6. Samples: 25287962. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:15:45,202][77203] Avg episode reward: [(0, '44.190'), (1, '46.450')] -[2023-10-12 05:15:48,590][78091] Updated weights for policy 0, policy_version 49510 (0.0009) -[2023-10-12 05:15:48,961][78091] Updated weights for policy 0, policy_version 49520 (0.0010) -[2023-10-12 05:15:49,053][78123] Updated weights for policy 1, policy_version 49290 (0.0008) -[2023-10-12 05:15:49,331][78091] Updated weights for policy 0, policy_version 49530 (0.0008) -[2023-10-12 05:15:49,414][78123] Updated weights for policy 1, policy_version 49300 (0.0007) -[2023-10-12 05:15:49,775][78123] Updated weights for policy 1, policy_version 49310 (0.0007) -[2023-10-12 05:15:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 101220352. Throughput: 0: 1609.9, 1: 1595.6. Samples: 25306968. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:15:50,201][77203] Avg episode reward: [(0, '50.300'), (1, '47.480')] -[2023-10-12 05:15:53,766][78091] Updated weights for policy 0, policy_version 49540 (0.0009) -[2023-10-12 05:15:54,134][78091] Updated weights for policy 0, policy_version 49550 (0.0008) -[2023-10-12 05:15:54,259][78123] Updated weights for policy 1, policy_version 49320 (0.0007) -[2023-10-12 05:15:54,516][78091] Updated weights for policy 0, policy_version 49560 (0.0008) -[2023-10-12 05:15:54,629][78123] Updated weights for policy 1, policy_version 49330 (0.0007) -[2023-10-12 05:15:55,002][78123] Updated weights for policy 1, policy_version 49340 (0.0009) -[2023-10-12 05:15:55,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 101285888. Throughput: 0: 1596.0, 1: 1580.4. Samples: 25325092. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:15:55,202][77203] Avg episode reward: [(0, '45.920'), (1, '44.340')] -[2023-10-12 05:15:58,919][78091] Updated weights for policy 0, policy_version 49570 (0.0009) -[2023-10-12 05:15:59,286][78091] Updated weights for policy 0, policy_version 49580 (0.0010) -[2023-10-12 05:15:59,360][78123] Updated weights for policy 1, policy_version 49350 (0.0008) -[2023-10-12 05:15:59,661][78091] Updated weights for policy 0, policy_version 49590 (0.0007) -[2023-10-12 05:15:59,723][78123] Updated weights for policy 1, policy_version 49360 (0.0009) -[2023-10-12 05:16:00,026][78091] Updated weights for policy 0, policy_version 49600 (0.0008) -[2023-10-12 05:16:00,091][78123] Updated weights for policy 1, policy_version 49370 (0.0008) -[2023-10-12 05:16:00,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 101318656. Throughput: 0: 1594.0, 1: 1578.8. Samples: 25335382. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:16:00,201][77203] Avg episode reward: [(0, '47.520'), (1, '43.660')] -[2023-10-12 05:16:04,253][78123] Updated weights for policy 1, policy_version 49380 (0.0009) -[2023-10-12 05:16:04,290][78091] Updated weights for policy 0, policy_version 49610 (0.0007) -[2023-10-12 05:16:04,612][78123] Updated weights for policy 1, policy_version 49390 (0.0007) -[2023-10-12 05:16:04,662][78091] Updated weights for policy 0, policy_version 49620 (0.0007) -[2023-10-12 05:16:04,981][78123] Updated weights for policy 1, policy_version 49400 (0.0008) -[2023-10-12 05:16:05,025][78091] Updated weights for policy 0, policy_version 49630 (0.0008) -[2023-10-12 05:16:05,201][77203] Fps is (10 sec: 9830.7, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 101384192. Throughput: 0: 1615.0, 1: 1604.5. Samples: 25355360. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:16:05,201][77203] Avg episode reward: [(0, '43.050'), (1, '47.760')] -[2023-10-12 05:16:09,381][78123] Updated weights for policy 1, policy_version 49410 (0.0010) -[2023-10-12 05:16:09,387][78091] Updated weights for policy 0, policy_version 49640 (0.0010) -[2023-10-12 05:16:09,751][78123] Updated weights for policy 1, policy_version 49420 (0.0009) -[2023-10-12 05:16:09,756][78091] Updated weights for policy 0, policy_version 49650 (0.0007) -[2023-10-12 05:16:10,114][78123] Updated weights for policy 1, policy_version 49430 (0.0008) -[2023-10-12 05:16:10,130][78091] Updated weights for policy 0, policy_version 49660 (0.0007) -[2023-10-12 05:16:10,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 101416960. Throughput: 0: 1609.5, 1: 1592.6. Samples: 25373686. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:16:10,201][77203] Avg episode reward: [(0, '48.420'), (1, '46.270')] -[2023-10-12 05:16:10,474][78123] Updated weights for policy 1, policy_version 49440 (0.0008) -[2023-10-12 05:16:14,552][78091] Updated weights for policy 0, policy_version 49670 (0.0010) -[2023-10-12 05:16:14,726][78123] Updated weights for policy 1, policy_version 49450 (0.0007) -[2023-10-12 05:16:14,941][78091] Updated weights for policy 0, policy_version 49680 (0.0010) -[2023-10-12 05:16:15,099][78123] Updated weights for policy 1, policy_version 49460 (0.0007) -[2023-10-12 05:16:15,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 101482496. Throughput: 0: 1597.4, 1: 1577.7. Samples: 25383332. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-12 05:16:15,201][77203] Avg episode reward: [(0, '44.240'), (1, '44.580')] -[2023-10-12 05:16:15,315][78091] Updated weights for policy 0, policy_version 49690 (0.0009) -[2023-10-12 05:16:15,455][78123] Updated weights for policy 1, policy_version 49470 (0.0008) -[2023-10-12 05:16:19,425][78091] Updated weights for policy 0, policy_version 49700 (0.0007) -[2023-10-12 05:16:19,646][78123] Updated weights for policy 1, policy_version 49480 (0.0009) -[2023-10-12 05:16:19,797][78091] Updated weights for policy 0, policy_version 49710 (0.0008) -[2023-10-12 05:16:20,004][78123] Updated weights for policy 1, policy_version 49490 (0.0010) -[2023-10-12 05:16:20,154][78091] Updated weights for policy 0, policy_version 49720 (0.0007) -[2023-10-12 05:16:20,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 101548032. Throughput: 0: 1608.2, 1: 1591.5. Samples: 25402858. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-12 05:16:20,202][77203] Avg episode reward: [(0, '47.590'), (1, '40.940')] -[2023-10-12 05:16:20,376][78123] Updated weights for policy 1, policy_version 49500 (0.0008) -[2023-10-12 05:16:24,482][78091] Updated weights for policy 0, policy_version 49730 (0.0010) -[2023-10-12 05:16:24,665][78123] Updated weights for policy 1, policy_version 49510 (0.0008) -[2023-10-12 05:16:24,851][78091] Updated weights for policy 0, policy_version 49740 (0.0009) -[2023-10-12 05:16:25,034][78123] Updated weights for policy 1, policy_version 49520 (0.0009) -[2023-10-12 05:16:25,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 101613568. Throughput: 0: 1613.3, 1: 1599.6. Samples: 25421740. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-12 05:16:25,201][77203] Avg episode reward: [(0, '44.430'), (1, '49.410')] -[2023-10-12 05:16:25,227][78091] Updated weights for policy 0, policy_version 49750 (0.0009) -[2023-10-12 05:16:25,407][78123] Updated weights for policy 1, policy_version 49530 (0.0007) -[2023-10-12 05:16:25,595][78091] Updated weights for policy 0, policy_version 49760 (0.0008) -[2023-10-12 05:16:29,905][78091] Updated weights for policy 0, policy_version 49770 (0.0009) -[2023-10-12 05:16:29,937][78123] Updated weights for policy 1, policy_version 49540 (0.0009) -[2023-10-12 05:16:30,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 101679104. Throughput: 0: 1591.2, 1: 1581.1. Samples: 25430712. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-12 05:16:30,201][77203] Avg episode reward: [(0, '52.390'), (1, '46.060')] -[2023-10-12 05:16:30,261][78091] Updated weights for policy 0, policy_version 49780 (0.0009) -[2023-10-12 05:16:30,293][78123] Updated weights for policy 1, policy_version 49550 (0.0009) -[2023-10-12 05:16:30,627][78091] Updated weights for policy 0, policy_version 49790 (0.0009) -[2023-10-12 05:16:30,668][78123] Updated weights for policy 1, policy_version 49560 (0.0007) -[2023-10-12 05:16:34,826][78091] Updated weights for policy 0, policy_version 49800 (0.0007) -[2023-10-12 05:16:35,182][78123] Updated weights for policy 1, policy_version 49570 (0.0009) -[2023-10-12 05:16:35,189][78091] Updated weights for policy 0, policy_version 49810 (0.0007) -[2023-10-12 05:16:35,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 101744640. Throughput: 0: 1605.0, 1: 1581.6. Samples: 25450362. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-12 05:16:35,202][77203] Avg episode reward: [(0, '49.470'), (1, '44.280')] -[2023-10-12 05:16:35,556][78091] Updated weights for policy 0, policy_version 49820 (0.0007) -[2023-10-12 05:16:35,560][78123] Updated weights for policy 1, policy_version 49580 (0.0009) -[2023-10-12 05:16:35,924][78123] Updated weights for policy 1, policy_version 49590 (0.0008) -[2023-10-12 05:16:36,281][78123] Updated weights for policy 1, policy_version 49600 (0.0009) -[2023-10-12 05:16:40,024][78091] Updated weights for policy 0, policy_version 49830 (0.0008) -[2023-10-12 05:16:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 101810176. Throughput: 0: 1614.9, 1: 1591.4. Samples: 25469376. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-12 05:16:40,202][77203] Avg episode reward: [(0, '45.910'), (1, '45.090')] -[2023-10-12 05:16:40,409][78091] Updated weights for policy 0, policy_version 49840 (0.0009) -[2023-10-12 05:16:40,772][78091] Updated weights for policy 0, policy_version 49850 (0.0009) -[2023-10-12 05:16:40,983][78123] Updated weights for policy 1, policy_version 49610 (0.0007) -[2023-10-12 05:16:41,349][78123] Updated weights for policy 1, policy_version 49620 (0.0007) -[2023-10-12 05:16:41,707][78123] Updated weights for policy 1, policy_version 49630 (0.0010) -[2023-10-12 05:16:45,069][78091] Updated weights for policy 0, policy_version 49860 (0.0009) -[2023-10-12 05:16:45,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 101875712. Throughput: 0: 1593.9, 1: 1572.4. Samples: 25477864. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-12 05:16:45,202][77203] Avg episode reward: [(0, '46.490'), (1, '47.770')] -[2023-10-12 05:16:45,440][78091] Updated weights for policy 0, policy_version 49870 (0.0008) -[2023-10-12 05:16:45,814][78091] Updated weights for policy 0, policy_version 49880 (0.0008) -[2023-10-12 05:16:45,948][78123] Updated weights for policy 1, policy_version 49640 (0.0009) -[2023-10-12 05:16:46,305][78123] Updated weights for policy 1, policy_version 49650 (0.0008) -[2023-10-12 05:16:46,670][78123] Updated weights for policy 1, policy_version 49660 (0.0011) -[2023-10-12 05:16:50,176][78091] Updated weights for policy 0, policy_version 49890 (0.0009) -[2023-10-12 05:16:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 101941248. Throughput: 0: 1588.0, 1: 1568.6. Samples: 25497410. Policy #0 lag: (min: 24.0, avg: 47.0, max: 56.0) -[2023-10-12 05:16:50,201][77203] Avg episode reward: [(0, '47.600'), (1, '45.880')] -[2023-10-12 05:16:50,541][78091] Updated weights for policy 0, policy_version 49900 (0.0009) -[2023-10-12 05:16:50,903][78091] Updated weights for policy 0, policy_version 49910 (0.0009) -[2023-10-12 05:16:51,186][78123] Updated weights for policy 1, policy_version 49670 (0.0008) -[2023-10-12 05:16:51,271][78091] Updated weights for policy 0, policy_version 49920 (0.0009) -[2023-10-12 05:16:51,554][78123] Updated weights for policy 1, policy_version 49680 (0.0007) -[2023-10-12 05:16:51,918][78123] Updated weights for policy 1, policy_version 49690 (0.0007) -[2023-10-12 05:16:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 102006784. Throughput: 0: 1600.6, 1: 1578.5. Samples: 25516746. Policy #0 lag: (min: 24.0, avg: 47.0, max: 56.0) -[2023-10-12 05:16:55,202][77203] Avg episode reward: [(0, '48.570'), (1, '35.400')] -[2023-10-12 05:16:55,640][78091] Updated weights for policy 0, policy_version 49930 (0.0009) -[2023-10-12 05:16:56,017][78091] Updated weights for policy 0, policy_version 49940 (0.0008) -[2023-10-12 05:16:56,184][78123] Updated weights for policy 1, policy_version 49700 (0.0008) -[2023-10-12 05:16:56,397][78091] Updated weights for policy 0, policy_version 49950 (0.0009) -[2023-10-12 05:16:56,556][78123] Updated weights for policy 1, policy_version 49710 (0.0008) -[2023-10-12 05:16:56,931][78123] Updated weights for policy 1, policy_version 49720 (0.0009) -[2023-10-12 05:17:00,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 102072320. Throughput: 0: 1586.2, 1: 1573.1. Samples: 25525502. Policy #0 lag: (min: 24.0, avg: 47.0, max: 56.0) -[2023-10-12 05:17:00,202][77203] Avg episode reward: [(0, '51.270'), (1, '39.230')] -[2023-10-12 05:17:00,818][78091] Updated weights for policy 0, policy_version 49960 (0.0007) -[2023-10-12 05:17:01,190][78091] Updated weights for policy 0, policy_version 49970 (0.0007) -[2023-10-12 05:17:01,275][78123] Updated weights for policy 1, policy_version 49730 (0.0007) -[2023-10-12 05:17:01,554][78091] Updated weights for policy 0, policy_version 49980 (0.0008) -[2023-10-12 05:17:01,644][78123] Updated weights for policy 1, policy_version 49740 (0.0007) -[2023-10-12 05:17:02,012][78123] Updated weights for policy 1, policy_version 49750 (0.0008) -[2023-10-12 05:17:02,378][78123] Updated weights for policy 1, policy_version 49760 (0.0008) -[2023-10-12 05:17:05,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 102137856. Throughput: 0: 1583.9, 1: 1566.5. Samples: 25544626. Policy #0 lag: (min: 24.0, avg: 47.0, max: 56.0) -[2023-10-12 05:17:05,201][77203] Avg episode reward: [(0, '49.970'), (1, '45.490')] -[2023-10-12 05:17:05,760][78091] Updated weights for policy 0, policy_version 49990 (0.0009) -[2023-10-12 05:17:06,128][78091] Updated weights for policy 0, policy_version 50000 (0.0009) -[2023-10-12 05:17:06,499][78091] Updated weights for policy 0, policy_version 50010 (0.0007) -[2023-10-12 05:17:06,814][78123] Updated weights for policy 1, policy_version 49770 (0.0010) -[2023-10-12 05:17:07,177][78123] Updated weights for policy 1, policy_version 49780 (0.0009) -[2023-10-12 05:17:07,539][78123] Updated weights for policy 1, policy_version 49790 (0.0009) -[2023-10-12 05:17:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.1, 300 sec: 12662.9). Total num frames: 102203392. Throughput: 0: 1593.6, 1: 1573.4. Samples: 25564254. Policy #0 lag: (min: 24.0, avg: 47.0, max: 56.0) -[2023-10-12 05:17:10,202][77203] Avg episode reward: [(0, '45.740'), (1, '41.830')] -[2023-10-12 05:17:10,215][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000049792_50987008.pth... -[2023-10-12 05:17:10,216][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000050016_51216384.pth... -[2023-10-12 05:17:10,253][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000048320_49479680.pth -[2023-10-12 05:17:10,256][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000048544_49709056.pth -[2023-10-12 05:17:10,860][78091] Updated weights for policy 0, policy_version 50020 (0.0008) -[2023-10-12 05:17:11,228][78091] Updated weights for policy 0, policy_version 50030 (0.0009) -[2023-10-12 05:17:11,603][78091] Updated weights for policy 0, policy_version 50040 (0.0010) -[2023-10-12 05:17:11,822][78123] Updated weights for policy 1, policy_version 49800 (0.0008) -[2023-10-12 05:17:12,195][78123] Updated weights for policy 1, policy_version 49810 (0.0007) -[2023-10-12 05:17:12,564][78123] Updated weights for policy 1, policy_version 49820 (0.0009) -[2023-10-12 05:17:15,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 102268928. Throughput: 0: 1590.9, 1: 1570.8. Samples: 25572990. Policy #0 lag: (min: 24.0, avg: 47.0, max: 56.0) -[2023-10-12 05:17:15,202][77203] Avg episode reward: [(0, '49.230'), (1, '39.160')] -[2023-10-12 05:17:15,925][78091] Updated weights for policy 0, policy_version 50050 (0.0008) -[2023-10-12 05:17:16,290][78091] Updated weights for policy 0, policy_version 50060 (0.0008) -[2023-10-12 05:17:16,658][78091] Updated weights for policy 0, policy_version 50070 (0.0008) -[2023-10-12 05:17:16,931][78123] Updated weights for policy 1, policy_version 49830 (0.0007) -[2023-10-12 05:17:17,030][78091] Updated weights for policy 0, policy_version 50080 (0.0008) -[2023-10-12 05:17:17,295][78123] Updated weights for policy 1, policy_version 49840 (0.0008) -[2023-10-12 05:17:17,660][78123] Updated weights for policy 1, policy_version 49850 (0.0010) -[2023-10-12 05:17:20,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 102334464. Throughput: 0: 1590.0, 1: 1567.6. Samples: 25592452. Policy #0 lag: (min: 24.0, avg: 47.0, max: 56.0) -[2023-10-12 05:17:20,202][77203] Avg episode reward: [(0, '47.310'), (1, '50.820')] -[2023-10-12 05:17:21,319][78091] Updated weights for policy 0, policy_version 50090 (0.0007) -[2023-10-12 05:17:21,696][78091] Updated weights for policy 0, policy_version 50100 (0.0008) -[2023-10-12 05:17:22,066][78091] Updated weights for policy 0, policy_version 50110 (0.0007) -[2023-10-12 05:17:22,112][78123] Updated weights for policy 1, policy_version 49860 (0.0009) -[2023-10-12 05:17:22,471][78123] Updated weights for policy 1, policy_version 49870 (0.0007) -[2023-10-12 05:17:22,839][78123] Updated weights for policy 1, policy_version 49880 (0.0010) -[2023-10-12 05:17:25,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 102400000. Throughput: 0: 1592.3, 1: 1571.9. Samples: 25611770. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:17:25,202][77203] Avg episode reward: [(0, '48.480'), (1, '44.880')] -[2023-10-12 05:17:26,553][78091] Updated weights for policy 0, policy_version 50120 (0.0010) -[2023-10-12 05:17:26,924][78091] Updated weights for policy 0, policy_version 50130 (0.0008) -[2023-10-12 05:17:27,191][78123] Updated weights for policy 1, policy_version 49890 (0.0010) -[2023-10-12 05:17:27,303][78091] Updated weights for policy 0, policy_version 50140 (0.0009) -[2023-10-12 05:17:27,598][78123] Updated weights for policy 1, policy_version 49900 (0.0007) -[2023-10-12 05:17:27,968][78123] Updated weights for policy 1, policy_version 49910 (0.0008) -[2023-10-12 05:17:28,334][78123] Updated weights for policy 1, policy_version 49920 (0.0009) -[2023-10-12 05:17:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 102465536. Throughput: 0: 1589.0, 1: 1587.6. Samples: 25620808. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:17:30,201][77203] Avg episode reward: [(0, '48.070'), (1, '47.150')] -[2023-10-12 05:17:31,559][78091] Updated weights for policy 0, policy_version 50150 (0.0009) -[2023-10-12 05:17:31,944][78091] Updated weights for policy 0, policy_version 50160 (0.0010) -[2023-10-12 05:17:32,324][78091] Updated weights for policy 0, policy_version 50170 (0.0008) -[2023-10-12 05:17:32,641][78123] Updated weights for policy 1, policy_version 49930 (0.0007) -[2023-10-12 05:17:33,011][78123] Updated weights for policy 1, policy_version 49940 (0.0009) -[2023-10-12 05:17:33,385][78123] Updated weights for policy 1, policy_version 49950 (0.0008) -[2023-10-12 05:17:35,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 102531072. Throughput: 0: 1591.5, 1: 1572.7. Samples: 25639800. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:17:35,202][77203] Avg episode reward: [(0, '42.480'), (1, '40.770')] -[2023-10-12 05:17:36,507][78091] Updated weights for policy 0, policy_version 50180 (0.0009) -[2023-10-12 05:17:36,880][78091] Updated weights for policy 0, policy_version 50190 (0.0008) -[2023-10-12 05:17:37,252][78091] Updated weights for policy 0, policy_version 50200 (0.0008) -[2023-10-12 05:17:37,740][78123] Updated weights for policy 1, policy_version 49960 (0.0009) -[2023-10-12 05:17:38,109][78123] Updated weights for policy 1, policy_version 49970 (0.0007) -[2023-10-12 05:17:38,490][78123] Updated weights for policy 1, policy_version 49980 (0.0008) -[2023-10-12 05:17:40,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 102596608. Throughput: 0: 1597.3, 1: 1575.5. Samples: 25659522. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:17:40,201][77203] Avg episode reward: [(0, '44.690'), (1, '50.860')] -[2023-10-12 05:17:41,531][78091] Updated weights for policy 0, policy_version 50210 (0.0008) -[2023-10-12 05:17:41,903][78091] Updated weights for policy 0, policy_version 50220 (0.0009) -[2023-10-12 05:17:42,271][78091] Updated weights for policy 0, policy_version 50230 (0.0009) -[2023-10-12 05:17:42,641][78091] Updated weights for policy 0, policy_version 50240 (0.0009) -[2023-10-12 05:17:42,817][78123] Updated weights for policy 1, policy_version 49990 (0.0008) -[2023-10-12 05:17:43,183][78123] Updated weights for policy 1, policy_version 50000 (0.0009) -[2023-10-12 05:17:43,549][78123] Updated weights for policy 1, policy_version 50010 (0.0009) -[2023-10-12 05:17:45,201][77203] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 102662144. Throughput: 0: 1596.8, 1: 1595.3. Samples: 25669146. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:17:45,202][77203] Avg episode reward: [(0, '47.000'), (1, '44.980')] -[2023-10-12 05:17:46,981][78091] Updated weights for policy 0, policy_version 50250 (0.0008) -[2023-10-12 05:17:47,340][78091] Updated weights for policy 0, policy_version 50260 (0.0007) -[2023-10-12 05:17:47,708][78091] Updated weights for policy 0, policy_version 50270 (0.0008) -[2023-10-12 05:17:47,714][78123] Updated weights for policy 1, policy_version 50020 (0.0009) -[2023-10-12 05:17:48,083][78123] Updated weights for policy 1, policy_version 50030 (0.0010) -[2023-10-12 05:17:48,441][78123] Updated weights for policy 1, policy_version 50040 (0.0010) -[2023-10-12 05:17:50,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 102727680. Throughput: 0: 1599.4, 1: 1579.8. Samples: 25687690. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:17:50,202][77203] Avg episode reward: [(0, '46.260'), (1, '41.680')] -[2023-10-12 05:17:52,212][78091] Updated weights for policy 0, policy_version 50280 (0.0010) -[2023-10-12 05:17:52,592][78091] Updated weights for policy 0, policy_version 50290 (0.0007) -[2023-10-12 05:17:52,921][78123] Updated weights for policy 1, policy_version 50050 (0.0008) -[2023-10-12 05:17:52,965][78091] Updated weights for policy 0, policy_version 50300 (0.0008) -[2023-10-12 05:17:53,281][78123] Updated weights for policy 1, policy_version 50060 (0.0008) -[2023-10-12 05:17:53,645][78123] Updated weights for policy 1, policy_version 50070 (0.0010) -[2023-10-12 05:17:54,016][78123] Updated weights for policy 1, policy_version 50080 (0.0010) -[2023-10-12 05:17:55,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 102793216. Throughput: 0: 1593.1, 1: 1575.1. Samples: 25706822. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:17:55,202][77203] Avg episode reward: [(0, '49.280'), (1, '42.480')] -[2023-10-12 05:17:57,214][78091] Updated weights for policy 0, policy_version 50310 (0.0009) -[2023-10-12 05:17:57,581][78091] Updated weights for policy 0, policy_version 50320 (0.0010) -[2023-10-12 05:17:57,947][78091] Updated weights for policy 0, policy_version 50330 (0.0010) -[2023-10-12 05:17:58,447][78123] Updated weights for policy 1, policy_version 50090 (0.0008) -[2023-10-12 05:17:58,814][78123] Updated weights for policy 1, policy_version 50100 (0.0009) -[2023-10-12 05:17:59,189][78123] Updated weights for policy 1, policy_version 50110 (0.0007) -[2023-10-12 05:18:00,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 102858752. Throughput: 0: 1601.1, 1: 1601.5. Samples: 25717106. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-12 05:18:00,201][77203] Avg episode reward: [(0, '50.750'), (1, '50.710')] -[2023-10-12 05:18:02,145][78091] Updated weights for policy 0, policy_version 50340 (0.0009) -[2023-10-12 05:18:02,515][78091] Updated weights for policy 0, policy_version 50350 (0.0009) -[2023-10-12 05:18:02,888][78091] Updated weights for policy 0, policy_version 50360 (0.0008) -[2023-10-12 05:18:03,596][78123] Updated weights for policy 1, policy_version 50120 (0.0008) -[2023-10-12 05:18:03,967][78123] Updated weights for policy 1, policy_version 50130 (0.0011) -[2023-10-12 05:18:04,338][78123] Updated weights for policy 1, policy_version 50140 (0.0011) -[2023-10-12 05:18:05,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 102924288. Throughput: 0: 1589.5, 1: 1595.1. Samples: 25735758. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-12 05:18:05,201][77203] Avg episode reward: [(0, '52.920'), (1, '50.310')] -[2023-10-12 05:18:06,851][78091] Updated weights for policy 0, policy_version 50370 (0.0008) -[2023-10-12 05:18:07,232][78091] Updated weights for policy 0, policy_version 50380 (0.0008) -[2023-10-12 05:18:07,593][78091] Updated weights for policy 0, policy_version 50390 (0.0010) -[2023-10-12 05:18:07,960][78091] Updated weights for policy 0, policy_version 50400 (0.0007) -[2023-10-12 05:18:08,825][78123] Updated weights for policy 1, policy_version 50150 (0.0009) -[2023-10-12 05:18:09,192][78123] Updated weights for policy 1, policy_version 50160 (0.0007) -[2023-10-12 05:18:09,565][78123] Updated weights for policy 1, policy_version 50170 (0.0009) -[2023-10-12 05:18:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 102989824. Throughput: 0: 1597.9, 1: 1580.0. Samples: 25754776. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-12 05:18:10,202][77203] Avg episode reward: [(0, '48.650'), (1, '42.910')] -[2023-10-12 05:18:12,351][78091] Updated weights for policy 0, policy_version 50410 (0.0009) -[2023-10-12 05:18:12,714][78091] Updated weights for policy 0, policy_version 50420 (0.0009) -[2023-10-12 05:18:13,092][78091] Updated weights for policy 0, policy_version 50430 (0.0009) -[2023-10-12 05:18:13,956][78123] Updated weights for policy 1, policy_version 50180 (0.0008) -[2023-10-12 05:18:14,345][78123] Updated weights for policy 1, policy_version 50190 (0.0009) -[2023-10-12 05:18:14,716][78123] Updated weights for policy 1, policy_version 50200 (0.0010) -[2023-10-12 05:18:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 103055360. Throughput: 0: 1607.2, 1: 1594.5. Samples: 25764882. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-12 05:18:15,201][77203] Avg episode reward: [(0, '46.220'), (1, '42.850')] -[2023-10-12 05:18:17,607][78091] Updated weights for policy 0, policy_version 50440 (0.0011) -[2023-10-12 05:18:17,976][78091] Updated weights for policy 0, policy_version 50450 (0.0011) -[2023-10-12 05:18:18,354][78091] Updated weights for policy 0, policy_version 50460 (0.0008) -[2023-10-12 05:18:19,095][78123] Updated weights for policy 1, policy_version 50210 (0.0009) -[2023-10-12 05:18:19,455][78123] Updated weights for policy 1, policy_version 50220 (0.0011) -[2023-10-12 05:18:19,818][78123] Updated weights for policy 1, policy_version 50230 (0.0010) -[2023-10-12 05:18:20,190][78123] Updated weights for policy 1, policy_version 50240 (0.0008) -[2023-10-12 05:18:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 103120896. Throughput: 0: 1591.3, 1: 1602.0. Samples: 25783494. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-12 05:18:20,202][77203] Avg episode reward: [(0, '46.120'), (1, '52.210')] -[2023-10-12 05:18:20,202][77950] Saving new best policy, reward=52.210! -[2023-10-12 05:18:22,647][78091] Updated weights for policy 0, policy_version 50470 (0.0009) -[2023-10-12 05:18:23,024][78091] Updated weights for policy 0, policy_version 50480 (0.0010) -[2023-10-12 05:18:23,394][78091] Updated weights for policy 0, policy_version 50490 (0.0007) -[2023-10-12 05:18:24,576][78123] Updated weights for policy 1, policy_version 50250 (0.0007) -[2023-10-12 05:18:24,938][78123] Updated weights for policy 1, policy_version 50260 (0.0008) -[2023-10-12 05:18:25,201][77203] Fps is (10 sec: 9830.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 103153664. Throughput: 0: 1592.4, 1: 1589.3. Samples: 25802698. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-12 05:18:25,202][77203] Avg episode reward: [(0, '46.040'), (1, '40.400')] -[2023-10-12 05:18:25,319][78123] Updated weights for policy 1, policy_version 50270 (0.0008) -[2023-10-12 05:18:27,665][78091] Updated weights for policy 0, policy_version 50500 (0.0010) -[2023-10-12 05:18:28,030][78091] Updated weights for policy 0, policy_version 50510 (0.0007) -[2023-10-12 05:18:28,411][78091] Updated weights for policy 0, policy_version 50520 (0.0007) -[2023-10-12 05:18:29,897][78123] Updated weights for policy 1, policy_version 50280 (0.0010) -[2023-10-12 05:18:30,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 103219200. Throughput: 0: 1616.4, 1: 1573.0. Samples: 25812666. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-12 05:18:30,202][77203] Avg episode reward: [(0, '46.540'), (1, '42.670')] -[2023-10-12 05:18:30,268][78123] Updated weights for policy 1, policy_version 50290 (0.0010) -[2023-10-12 05:18:30,645][78123] Updated weights for policy 1, policy_version 50300 (0.0008) -[2023-10-12 05:18:32,713][78091] Updated weights for policy 0, policy_version 50530 (0.0009) -[2023-10-12 05:18:33,084][78091] Updated weights for policy 0, policy_version 50540 (0.0007) -[2023-10-12 05:18:33,459][78091] Updated weights for policy 0, policy_version 50550 (0.0008) -[2023-10-12 05:18:33,833][78091] Updated weights for policy 0, policy_version 50560 (0.0009) -[2023-10-12 05:18:34,890][78123] Updated weights for policy 1, policy_version 50310 (0.0008) -[2023-10-12 05:18:35,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 103284736. Throughput: 0: 1597.6, 1: 1593.8. Samples: 25831302. Policy #0 lag: (min: 10.0, avg: 14.2, max: 42.0) -[2023-10-12 05:18:35,201][77203] Avg episode reward: [(0, '49.690'), (1, '46.820')] -[2023-10-12 05:18:35,260][78123] Updated weights for policy 1, policy_version 50320 (0.0007) -[2023-10-12 05:18:35,629][78123] Updated weights for policy 1, policy_version 50330 (0.0007) -[2023-10-12 05:18:38,207][78091] Updated weights for policy 0, policy_version 50570 (0.0007) -[2023-10-12 05:18:38,586][78091] Updated weights for policy 0, policy_version 50580 (0.0007) -[2023-10-12 05:18:38,953][78091] Updated weights for policy 0, policy_version 50590 (0.0007) -[2023-10-12 05:18:39,975][78123] Updated weights for policy 1, policy_version 50340 (0.0008) -[2023-10-12 05:18:40,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 103350272. Throughput: 0: 1599.5, 1: 1596.4. Samples: 25850636. Policy #0 lag: (min: 10.0, avg: 14.2, max: 42.0) -[2023-10-12 05:18:40,201][77203] Avg episode reward: [(0, '47.960'), (1, '48.710')] -[2023-10-12 05:18:40,330][78123] Updated weights for policy 1, policy_version 50350 (0.0008) -[2023-10-12 05:18:40,697][78123] Updated weights for policy 1, policy_version 50360 (0.0011) -[2023-10-12 05:18:43,301][78091] Updated weights for policy 0, policy_version 50600 (0.0010) -[2023-10-12 05:18:43,674][78091] Updated weights for policy 0, policy_version 50610 (0.0010) -[2023-10-12 05:18:44,058][78091] Updated weights for policy 0, policy_version 50620 (0.0010) -[2023-10-12 05:18:44,921][78123] Updated weights for policy 1, policy_version 50370 (0.0009) -[2023-10-12 05:18:45,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 103415808. Throughput: 0: 1615.3, 1: 1570.6. Samples: 25860472. Policy #0 lag: (min: 10.0, avg: 14.2, max: 42.0) -[2023-10-12 05:18:45,202][77203] Avg episode reward: [(0, '49.010'), (1, '39.880')] -[2023-10-12 05:18:45,288][78123] Updated weights for policy 1, policy_version 50380 (0.0008) -[2023-10-12 05:18:45,660][78123] Updated weights for policy 1, policy_version 50390 (0.0010) -[2023-10-12 05:18:46,024][78123] Updated weights for policy 1, policy_version 50400 (0.0009) -[2023-10-12 05:18:48,265][78091] Updated weights for policy 0, policy_version 50630 (0.0009) -[2023-10-12 05:18:48,635][78091] Updated weights for policy 0, policy_version 50640 (0.0007) -[2023-10-12 05:18:49,012][78091] Updated weights for policy 0, policy_version 50650 (0.0009) -[2023-10-12 05:18:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 103481344. Throughput: 0: 1609.2, 1: 1579.8. Samples: 25879260. Policy #0 lag: (min: 10.0, avg: 14.2, max: 42.0) -[2023-10-12 05:18:50,201][77203] Avg episode reward: [(0, '50.250'), (1, '44.560')] -[2023-10-12 05:18:50,310][78123] Updated weights for policy 1, policy_version 50410 (0.0008) -[2023-10-12 05:18:50,674][78123] Updated weights for policy 1, policy_version 50420 (0.0010) -[2023-10-12 05:18:51,040][78123] Updated weights for policy 1, policy_version 50430 (0.0007) -[2023-10-12 05:18:53,294][78091] Updated weights for policy 0, policy_version 50660 (0.0009) -[2023-10-12 05:18:53,651][78091] Updated weights for policy 0, policy_version 50670 (0.0009) -[2023-10-12 05:18:54,027][78091] Updated weights for policy 0, policy_version 50680 (0.0009) -[2023-10-12 05:18:55,201][77203] Fps is (10 sec: 13107.6, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 103546880. Throughput: 0: 1596.3, 1: 1598.6. Samples: 25898546. Policy #0 lag: (min: 10.0, avg: 14.2, max: 42.0) -[2023-10-12 05:18:55,201][77203] Avg episode reward: [(0, '51.570'), (1, '47.670')] -[2023-10-12 05:18:55,305][78123] Updated weights for policy 1, policy_version 50440 (0.0010) -[2023-10-12 05:18:55,670][78123] Updated weights for policy 1, policy_version 50450 (0.0007) -[2023-10-12 05:18:56,037][78123] Updated weights for policy 1, policy_version 50460 (0.0010) -[2023-10-12 05:18:58,160][78091] Updated weights for policy 0, policy_version 50690 (0.0009) -[2023-10-12 05:18:58,526][78091] Updated weights for policy 0, policy_version 50700 (0.0011) -[2023-10-12 05:18:58,897][78091] Updated weights for policy 0, policy_version 50710 (0.0008) -[2023-10-12 05:18:59,265][78091] Updated weights for policy 0, policy_version 50720 (0.0007) -[2023-10-12 05:19:00,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 103612416. Throughput: 0: 1618.9, 1: 1572.9. Samples: 25908516. Policy #0 lag: (min: 10.0, avg: 14.2, max: 42.0) -[2023-10-12 05:19:00,201][77203] Avg episode reward: [(0, '45.790'), (1, '43.500')] -[2023-10-12 05:19:00,341][78123] Updated weights for policy 1, policy_version 50470 (0.0009) -[2023-10-12 05:19:00,710][78123] Updated weights for policy 1, policy_version 50480 (0.0010) -[2023-10-12 05:19:01,081][78123] Updated weights for policy 1, policy_version 50490 (0.0008) -[2023-10-12 05:19:03,557][78091] Updated weights for policy 0, policy_version 50730 (0.0009) -[2023-10-12 05:19:03,931][78091] Updated weights for policy 0, policy_version 50740 (0.0009) -[2023-10-12 05:19:04,302][78091] Updated weights for policy 0, policy_version 50750 (0.0009) -[2023-10-12 05:19:05,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 103677952. Throughput: 0: 1620.3, 1: 1578.4. Samples: 25927438. Policy #0 lag: (min: 10.0, avg: 14.2, max: 42.0) -[2023-10-12 05:19:05,202][77203] Avg episode reward: [(0, '47.210'), (1, '45.800')] -[2023-10-12 05:19:05,313][78123] Updated weights for policy 1, policy_version 50500 (0.0007) -[2023-10-12 05:19:05,678][78123] Updated weights for policy 1, policy_version 50510 (0.0008) -[2023-10-12 05:19:06,050][78123] Updated weights for policy 1, policy_version 50520 (0.0008) -[2023-10-12 05:19:08,496][78091] Updated weights for policy 0, policy_version 50760 (0.0008) -[2023-10-12 05:19:08,872][78091] Updated weights for policy 0, policy_version 50770 (0.0009) -[2023-10-12 05:19:09,234][78091] Updated weights for policy 0, policy_version 50780 (0.0008) -[2023-10-12 05:19:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 103743488. Throughput: 0: 1604.5, 1: 1590.9. Samples: 25946488. Policy #0 lag: (min: 31.0, avg: 31.7, max: 49.0) -[2023-10-12 05:19:10,201][77203] Avg episode reward: [(0, '41.520'), (1, '47.220')] -[2023-10-12 05:19:10,210][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000050528_51740672.pth... -[2023-10-12 05:19:10,210][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000050784_52002816.pth... -[2023-10-12 05:19:10,251][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000049280_50462720.pth -[2023-10-12 05:19:10,251][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000049056_50233344.pth -[2023-10-12 05:19:10,542][78123] Updated weights for policy 1, policy_version 50530 (0.0008) -[2023-10-12 05:19:10,912][78123] Updated weights for policy 1, policy_version 50540 (0.0009) -[2023-10-12 05:19:11,272][78123] Updated weights for policy 1, policy_version 50550 (0.0008) -[2023-10-12 05:19:11,642][78123] Updated weights for policy 1, policy_version 50560 (0.0010) -[2023-10-12 05:19:13,520][78091] Updated weights for policy 0, policy_version 50790 (0.0008) -[2023-10-12 05:19:13,891][78091] Updated weights for policy 0, policy_version 50800 (0.0007) -[2023-10-12 05:19:14,264][78091] Updated weights for policy 0, policy_version 50810 (0.0007) -[2023-10-12 05:19:15,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 103809024. Throughput: 0: 1610.5, 1: 1583.8. Samples: 25956410. Policy #0 lag: (min: 31.0, avg: 31.7, max: 49.0) -[2023-10-12 05:19:15,201][77203] Avg episode reward: [(0, '45.240'), (1, '43.000')] -[2023-10-12 05:19:15,941][78123] Updated weights for policy 1, policy_version 50570 (0.0008) -[2023-10-12 05:19:16,310][78123] Updated weights for policy 1, policy_version 50580 (0.0008) -[2023-10-12 05:19:16,680][78123] Updated weights for policy 1, policy_version 50590 (0.0008) -[2023-10-12 05:19:18,445][78091] Updated weights for policy 0, policy_version 50820 (0.0007) -[2023-10-12 05:19:18,813][78091] Updated weights for policy 0, policy_version 50830 (0.0007) -[2023-10-12 05:19:19,185][78091] Updated weights for policy 0, policy_version 50840 (0.0008) -[2023-10-12 05:19:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 103874560. Throughput: 0: 1623.9, 1: 1583.6. Samples: 25975638. Policy #0 lag: (min: 31.0, avg: 31.7, max: 49.0) -[2023-10-12 05:19:20,202][77203] Avg episode reward: [(0, '44.820'), (1, '43.630')] -[2023-10-12 05:19:21,197][78123] Updated weights for policy 1, policy_version 50600 (0.0008) -[2023-10-12 05:19:21,565][78123] Updated weights for policy 1, policy_version 50610 (0.0011) -[2023-10-12 05:19:21,934][78123] Updated weights for policy 1, policy_version 50620 (0.0009) -[2023-10-12 05:19:23,542][78091] Updated weights for policy 0, policy_version 50850 (0.0009) -[2023-10-12 05:19:23,937][78091] Updated weights for policy 0, policy_version 50860 (0.0007) -[2023-10-12 05:19:24,311][78091] Updated weights for policy 0, policy_version 50870 (0.0010) -[2023-10-12 05:19:24,675][78091] Updated weights for policy 0, policy_version 50880 (0.0009) -[2023-10-12 05:19:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 103940096. Throughput: 0: 1609.4, 1: 1585.7. Samples: 25994414. Policy #0 lag: (min: 31.0, avg: 31.7, max: 49.0) -[2023-10-12 05:19:25,202][77203] Avg episode reward: [(0, '44.700'), (1, '42.820')] -[2023-10-12 05:19:26,209][78123] Updated weights for policy 1, policy_version 50630 (0.0009) -[2023-10-12 05:19:26,569][78123] Updated weights for policy 1, policy_version 50640 (0.0008) -[2023-10-12 05:19:26,946][78123] Updated weights for policy 1, policy_version 50650 (0.0009) -[2023-10-12 05:19:28,757][78091] Updated weights for policy 0, policy_version 50890 (0.0007) -[2023-10-12 05:19:29,130][78091] Updated weights for policy 0, policy_version 50900 (0.0007) -[2023-10-12 05:19:29,499][78091] Updated weights for policy 0, policy_version 50910 (0.0007) -[2023-10-12 05:19:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 104005632. Throughput: 0: 1611.3, 1: 1584.8. Samples: 26004294. Policy #0 lag: (min: 31.0, avg: 31.7, max: 49.0) -[2023-10-12 05:19:30,201][77203] Avg episode reward: [(0, '42.350'), (1, '46.400')] -[2023-10-12 05:19:31,417][78123] Updated weights for policy 1, policy_version 50660 (0.0008) -[2023-10-12 05:19:31,776][78123] Updated weights for policy 1, policy_version 50670 (0.0007) -[2023-10-12 05:19:32,154][78123] Updated weights for policy 1, policy_version 50680 (0.0008) -[2023-10-12 05:19:33,779][78091] Updated weights for policy 0, policy_version 50920 (0.0009) -[2023-10-12 05:19:34,155][78091] Updated weights for policy 0, policy_version 50930 (0.0010) -[2023-10-12 05:19:34,518][78091] Updated weights for policy 0, policy_version 50940 (0.0008) -[2023-10-12 05:19:35,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 104071168. Throughput: 0: 1624.6, 1: 1580.6. Samples: 26023494. Policy #0 lag: (min: 31.0, avg: 31.7, max: 49.0) -[2023-10-12 05:19:35,202][77203] Avg episode reward: [(0, '49.480'), (1, '39.030')] -[2023-10-12 05:19:36,390][78123] Updated weights for policy 1, policy_version 50690 (0.0008) -[2023-10-12 05:19:36,749][78123] Updated weights for policy 1, policy_version 50700 (0.0009) -[2023-10-12 05:19:37,119][78123] Updated weights for policy 1, policy_version 50710 (0.0007) -[2023-10-12 05:19:37,487][78123] Updated weights for policy 1, policy_version 50720 (0.0009) -[2023-10-12 05:19:39,013][78091] Updated weights for policy 0, policy_version 50950 (0.0009) -[2023-10-12 05:19:39,386][78091] Updated weights for policy 0, policy_version 50960 (0.0007) -[2023-10-12 05:19:39,752][78091] Updated weights for policy 0, policy_version 50970 (0.0008) -[2023-10-12 05:19:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 104136704. Throughput: 0: 1614.5, 1: 1582.4. Samples: 26042406. Policy #0 lag: (min: 31.0, avg: 31.7, max: 49.0) -[2023-10-12 05:19:40,202][77203] Avg episode reward: [(0, '53.260'), (1, '46.790')] -[2023-10-12 05:19:41,816][78123] Updated weights for policy 1, policy_version 50730 (0.0008) -[2023-10-12 05:19:42,192][78123] Updated weights for policy 1, policy_version 50740 (0.0007) -[2023-10-12 05:19:42,555][78123] Updated weights for policy 1, policy_version 50750 (0.0008) -[2023-10-12 05:19:43,925][78091] Updated weights for policy 0, policy_version 50980 (0.0008) -[2023-10-12 05:19:44,290][78091] Updated weights for policy 0, policy_version 50990 (0.0010) -[2023-10-12 05:19:44,654][78091] Updated weights for policy 0, policy_version 51000 (0.0009) -[2023-10-12 05:19:45,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.3, 300 sec: 12774.0). Total num frames: 104202240. Throughput: 0: 1607.8, 1: 1580.4. Samples: 26051986. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-12 05:19:45,201][77203] Avg episode reward: [(0, '46.360'), (1, '48.220')] -[2023-10-12 05:19:46,780][78123] Updated weights for policy 1, policy_version 50760 (0.0008) -[2023-10-12 05:19:47,144][78123] Updated weights for policy 1, policy_version 50770 (0.0008) -[2023-10-12 05:19:47,523][78123] Updated weights for policy 1, policy_version 50780 (0.0008) -[2023-10-12 05:19:48,945][78091] Updated weights for policy 0, policy_version 51010 (0.0009) -[2023-10-12 05:19:49,313][78091] Updated weights for policy 0, policy_version 51020 (0.0008) -[2023-10-12 05:19:49,684][78091] Updated weights for policy 0, policy_version 51030 (0.0007) -[2023-10-12 05:19:50,062][78091] Updated weights for policy 0, policy_version 51040 (0.0007) -[2023-10-12 05:19:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 104267776. Throughput: 0: 1616.5, 1: 1585.8. Samples: 26071540. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-12 05:19:50,202][77203] Avg episode reward: [(0, '45.380'), (1, '43.940')] -[2023-10-12 05:19:51,835][78123] Updated weights for policy 1, policy_version 50790 (0.0011) -[2023-10-12 05:19:52,201][78123] Updated weights for policy 1, policy_version 50800 (0.0008) -[2023-10-12 05:19:52,573][78123] Updated weights for policy 1, policy_version 50810 (0.0007) -[2023-10-12 05:19:54,446][78091] Updated weights for policy 0, policy_version 51050 (0.0007) -[2023-10-12 05:19:54,815][78091] Updated weights for policy 0, policy_version 51060 (0.0008) -[2023-10-12 05:19:55,189][78091] Updated weights for policy 0, policy_version 51070 (0.0008) -[2023-10-12 05:19:55,201][77203] Fps is (10 sec: 9830.1, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 104300544. Throughput: 0: 1611.2, 1: 1585.7. Samples: 26090350. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-12 05:19:55,202][77203] Avg episode reward: [(0, '52.160'), (1, '42.910')] -[2023-10-12 05:19:56,927][78123] Updated weights for policy 1, policy_version 50820 (0.0010) -[2023-10-12 05:19:57,293][78123] Updated weights for policy 1, policy_version 50830 (0.0009) -[2023-10-12 05:19:57,668][78123] Updated weights for policy 1, policy_version 50840 (0.0010) -[2023-10-12 05:19:59,427][78091] Updated weights for policy 0, policy_version 51080 (0.0009) -[2023-10-12 05:19:59,794][78091] Updated weights for policy 0, policy_version 51090 (0.0010) -[2023-10-12 05:20:00,169][78091] Updated weights for policy 0, policy_version 51100 (0.0008) -[2023-10-12 05:20:00,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 104366080. Throughput: 0: 1596.2, 1: 1593.3. Samples: 26099938. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-12 05:20:00,202][77203] Avg episode reward: [(0, '48.180'), (1, '47.810')] -[2023-10-12 05:20:01,947][78123] Updated weights for policy 1, policy_version 50850 (0.0008) -[2023-10-12 05:20:02,309][78123] Updated weights for policy 1, policy_version 50860 (0.0008) -[2023-10-12 05:20:02,679][78123] Updated weights for policy 1, policy_version 50870 (0.0008) -[2023-10-12 05:20:03,047][78123] Updated weights for policy 1, policy_version 50880 (0.0008) -[2023-10-12 05:20:04,567][78091] Updated weights for policy 0, policy_version 51110 (0.0008) -[2023-10-12 05:20:04,938][78091] Updated weights for policy 0, policy_version 51120 (0.0008) -[2023-10-12 05:20:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 104431616. Throughput: 0: 1601.5, 1: 1585.6. Samples: 26119056. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-12 05:20:05,202][77203] Avg episode reward: [(0, '45.880'), (1, '46.350')] -[2023-10-12 05:20:05,322][78091] Updated weights for policy 0, policy_version 51130 (0.0009) -[2023-10-12 05:20:07,446][78123] Updated weights for policy 1, policy_version 50890 (0.0011) -[2023-10-12 05:20:07,815][78123] Updated weights for policy 1, policy_version 50900 (0.0010) -[2023-10-12 05:20:08,179][78123] Updated weights for policy 1, policy_version 50910 (0.0008) -[2023-10-12 05:20:09,835][78091] Updated weights for policy 0, policy_version 51140 (0.0010) -[2023-10-12 05:20:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 104497152. Throughput: 0: 1608.7, 1: 1587.2. Samples: 26138228. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-12 05:20:10,202][77203] Avg episode reward: [(0, '47.380'), (1, '44.080')] -[2023-10-12 05:20:10,226][78091] Updated weights for policy 0, policy_version 51150 (0.0008) -[2023-10-12 05:20:10,597][78091] Updated weights for policy 0, policy_version 51160 (0.0009) -[2023-10-12 05:20:12,483][78123] Updated weights for policy 1, policy_version 50920 (0.0007) -[2023-10-12 05:20:12,854][78123] Updated weights for policy 1, policy_version 50930 (0.0009) -[2023-10-12 05:20:13,229][78123] Updated weights for policy 1, policy_version 50940 (0.0008) -[2023-10-12 05:20:14,925][78091] Updated weights for policy 0, policy_version 51170 (0.0009) -[2023-10-12 05:20:15,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 104562688. Throughput: 0: 1578.7, 1: 1604.8. Samples: 26147548. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-12 05:20:15,202][77203] Avg episode reward: [(0, '47.260'), (1, '43.320')] -[2023-10-12 05:20:15,307][78091] Updated weights for policy 0, policy_version 51180 (0.0010) -[2023-10-12 05:20:15,666][78091] Updated weights for policy 0, policy_version 51190 (0.0010) -[2023-10-12 05:20:16,036][78091] Updated weights for policy 0, policy_version 51200 (0.0009) -[2023-10-12 05:20:17,585][78123] Updated weights for policy 1, policy_version 50950 (0.0007) -[2023-10-12 05:20:17,946][78123] Updated weights for policy 1, policy_version 50960 (0.0010) -[2023-10-12 05:20:18,317][78123] Updated weights for policy 1, policy_version 50970 (0.0009) -[2023-10-12 05:20:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 104628224. Throughput: 0: 1583.8, 1: 1592.2. Samples: 26166414. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-12 05:20:20,202][77203] Avg episode reward: [(0, '47.330'), (1, '46.460')] -[2023-10-12 05:20:20,218][78091] Updated weights for policy 0, policy_version 51210 (0.0009) -[2023-10-12 05:20:20,591][78091] Updated weights for policy 0, policy_version 51220 (0.0009) -[2023-10-12 05:20:20,969][78091] Updated weights for policy 0, policy_version 51230 (0.0007) -[2023-10-12 05:20:22,880][78123] Updated weights for policy 1, policy_version 50980 (0.0011) -[2023-10-12 05:20:23,244][78123] Updated weights for policy 1, policy_version 50990 (0.0010) -[2023-10-12 05:20:23,613][78123] Updated weights for policy 1, policy_version 51000 (0.0010) -[2023-10-12 05:20:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 104693760. Throughput: 0: 1603.2, 1: 1582.1. Samples: 26185742. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-12 05:20:25,202][77203] Avg episode reward: [(0, '43.010'), (1, '42.630')] -[2023-10-12 05:20:25,332][78091] Updated weights for policy 0, policy_version 51240 (0.0007) -[2023-10-12 05:20:25,693][78091] Updated weights for policy 0, policy_version 51250 (0.0008) -[2023-10-12 05:20:26,073][78091] Updated weights for policy 0, policy_version 51260 (0.0008) -[2023-10-12 05:20:28,096][78123] Updated weights for policy 1, policy_version 51010 (0.0007) -[2023-10-12 05:20:28,467][78123] Updated weights for policy 1, policy_version 51020 (0.0007) -[2023-10-12 05:20:28,831][78123] Updated weights for policy 1, policy_version 51030 (0.0009) -[2023-10-12 05:20:29,205][78123] Updated weights for policy 1, policy_version 51040 (0.0011) -[2023-10-12 05:20:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 104759296. Throughput: 0: 1577.9, 1: 1606.4. Samples: 26195278. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-12 05:20:30,202][77203] Avg episode reward: [(0, '53.870'), (1, '45.110')] -[2023-10-12 05:20:30,389][78091] Updated weights for policy 0, policy_version 51270 (0.0009) -[2023-10-12 05:20:30,763][78091] Updated weights for policy 0, policy_version 51280 (0.0007) -[2023-10-12 05:20:31,134][78091] Updated weights for policy 0, policy_version 51290 (0.0007) -[2023-10-12 05:20:33,566][78123] Updated weights for policy 1, policy_version 51050 (0.0008) -[2023-10-12 05:20:33,933][78123] Updated weights for policy 1, policy_version 51060 (0.0007) -[2023-10-12 05:20:34,306][78123] Updated weights for policy 1, policy_version 51070 (0.0007) -[2023-10-12 05:20:35,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 104824832. Throughput: 0: 1581.5, 1: 1589.6. Samples: 26214238. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-12 05:20:35,202][77203] Avg episode reward: [(0, '49.990'), (1, '40.800')] -[2023-10-12 05:20:35,527][78091] Updated weights for policy 0, policy_version 51300 (0.0009) -[2023-10-12 05:20:35,899][78091] Updated weights for policy 0, policy_version 51310 (0.0009) -[2023-10-12 05:20:36,276][78091] Updated weights for policy 0, policy_version 51320 (0.0009) -[2023-10-12 05:20:38,453][78123] Updated weights for policy 1, policy_version 51080 (0.0008) -[2023-10-12 05:20:38,820][78123] Updated weights for policy 1, policy_version 51090 (0.0008) -[2023-10-12 05:20:39,185][78123] Updated weights for policy 1, policy_version 51100 (0.0011) -[2023-10-12 05:20:40,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 104890368. Throughput: 0: 1599.9, 1: 1574.9. Samples: 26233214. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-12 05:20:40,201][77203] Avg episode reward: [(0, '46.180'), (1, '47.850')] -[2023-10-12 05:20:40,741][78091] Updated weights for policy 0, policy_version 51330 (0.0008) -[2023-10-12 05:20:41,122][78091] Updated weights for policy 0, policy_version 51340 (0.0010) -[2023-10-12 05:20:41,487][78091] Updated weights for policy 0, policy_version 51350 (0.0008) -[2023-10-12 05:20:41,858][78091] Updated weights for policy 0, policy_version 51360 (0.0008) -[2023-10-12 05:20:43,514][78123] Updated weights for policy 1, policy_version 51110 (0.0009) -[2023-10-12 05:20:43,882][78123] Updated weights for policy 1, policy_version 51120 (0.0007) -[2023-10-12 05:20:44,258][78123] Updated weights for policy 1, policy_version 51130 (0.0009) -[2023-10-12 05:20:45,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 104955904. Throughput: 0: 1580.8, 1: 1595.2. Samples: 26242858. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-12 05:20:45,201][77203] Avg episode reward: [(0, '51.090'), (1, '39.990')] -[2023-10-12 05:20:46,329][78091] Updated weights for policy 0, policy_version 51370 (0.0008) -[2023-10-12 05:20:46,707][78091] Updated weights for policy 0, policy_version 51380 (0.0010) -[2023-10-12 05:20:47,071][78091] Updated weights for policy 0, policy_version 51390 (0.0008) -[2023-10-12 05:20:48,590][78123] Updated weights for policy 1, policy_version 51140 (0.0007) -[2023-10-12 05:20:48,952][78123] Updated weights for policy 1, policy_version 51150 (0.0009) -[2023-10-12 05:20:49,316][78123] Updated weights for policy 1, policy_version 51160 (0.0010) -[2023-10-12 05:20:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 105021440. Throughput: 0: 1577.4, 1: 1598.9. Samples: 26261990. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-12 05:20:50,201][77203] Avg episode reward: [(0, '53.510'), (1, '46.140')] -[2023-10-12 05:20:51,198][78091] Updated weights for policy 0, policy_version 51400 (0.0008) -[2023-10-12 05:20:51,568][78091] Updated weights for policy 0, policy_version 51410 (0.0007) -[2023-10-12 05:20:51,936][78091] Updated weights for policy 0, policy_version 51420 (0.0008) -[2023-10-12 05:20:53,664][78123] Updated weights for policy 1, policy_version 51170 (0.0010) -[2023-10-12 05:20:54,033][78123] Updated weights for policy 1, policy_version 51180 (0.0008) -[2023-10-12 05:20:54,404][78123] Updated weights for policy 1, policy_version 51190 (0.0010) -[2023-10-12 05:20:54,784][78123] Updated weights for policy 1, policy_version 51200 (0.0008) -[2023-10-12 05:20:55,201][77203] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 105086976. Throughput: 0: 1589.7, 1: 1577.8. Samples: 26280768. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-12 05:20:55,202][77203] Avg episode reward: [(0, '51.080'), (1, '43.770')] -[2023-10-12 05:20:56,295][78091] Updated weights for policy 0, policy_version 51430 (0.0007) -[2023-10-12 05:20:56,671][78091] Updated weights for policy 0, policy_version 51440 (0.0008) -[2023-10-12 05:20:57,045][78091] Updated weights for policy 0, policy_version 51450 (0.0008) -[2023-10-12 05:20:59,180][78123] Updated weights for policy 1, policy_version 51210 (0.0008) -[2023-10-12 05:20:59,561][78123] Updated weights for policy 1, policy_version 51220 (0.0008) -[2023-10-12 05:20:59,926][78123] Updated weights for policy 1, policy_version 51230 (0.0008) -[2023-10-12 05:21:00,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 105152512. Throughput: 0: 1591.1, 1: 1584.1. Samples: 26290432. Policy #0 lag: (min: 21.0, avg: 27.4, max: 53.0) -[2023-10-12 05:21:00,201][77203] Avg episode reward: [(0, '48.690'), (1, '45.020')] -[2023-10-12 05:21:01,221][78091] Updated weights for policy 0, policy_version 51460 (0.0008) -[2023-10-12 05:21:01,599][78091] Updated weights for policy 0, policy_version 51470 (0.0009) -[2023-10-12 05:21:01,970][78091] Updated weights for policy 0, policy_version 51480 (0.0008) -[2023-10-12 05:21:04,224][78123] Updated weights for policy 1, policy_version 51240 (0.0008) -[2023-10-12 05:21:04,587][78123] Updated weights for policy 1, policy_version 51250 (0.0008) -[2023-10-12 05:21:04,960][78123] Updated weights for policy 1, policy_version 51260 (0.0009) -[2023-10-12 05:21:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 105218048. Throughput: 0: 1592.0, 1: 1603.9. Samples: 26310228. Policy #0 lag: (min: 21.0, avg: 27.4, max: 53.0) -[2023-10-12 05:21:05,202][77203] Avg episode reward: [(0, '48.880'), (1, '44.890')] -[2023-10-12 05:21:06,197][78091] Updated weights for policy 0, policy_version 51490 (0.0008) -[2023-10-12 05:21:06,565][78091] Updated weights for policy 0, policy_version 51500 (0.0008) -[2023-10-12 05:21:06,947][78091] Updated weights for policy 0, policy_version 51510 (0.0007) -[2023-10-12 05:21:07,318][78091] Updated weights for policy 0, policy_version 51520 (0.0007) -[2023-10-12 05:21:09,456][78123] Updated weights for policy 1, policy_version 51270 (0.0009) -[2023-10-12 05:21:09,828][78123] Updated weights for policy 1, policy_version 51280 (0.0011) -[2023-10-12 05:21:10,193][78123] Updated weights for policy 1, policy_version 51290 (0.0009) -[2023-10-12 05:21:10,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 105250816. Throughput: 0: 1594.5, 1: 1598.4. Samples: 26329424. Policy #0 lag: (min: 21.0, avg: 27.4, max: 53.0) -[2023-10-12 05:21:10,201][77203] Avg episode reward: [(0, '54.140'), (1, '46.770')] -[2023-10-12 05:21:10,209][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000051520_52756480.pth... -[2023-10-12 05:21:10,238][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000050016_51216384.pth -[2023-10-12 05:21:10,412][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000051296_52527104.pth... -[2023-10-12 05:21:10,441][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000049792_50987008.pth -[2023-10-12 05:21:11,643][78091] Updated weights for policy 0, policy_version 51530 (0.0007) -[2023-10-12 05:21:12,016][78091] Updated weights for policy 0, policy_version 51540 (0.0008) -[2023-10-12 05:21:12,395][78091] Updated weights for policy 0, policy_version 51550 (0.0007) -[2023-10-12 05:21:14,584][78123] Updated weights for policy 1, policy_version 51300 (0.0010) -[2023-10-12 05:21:14,954][78123] Updated weights for policy 1, policy_version 51310 (0.0009) -[2023-10-12 05:21:15,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 105316352. Throughput: 0: 1594.0, 1: 1584.6. Samples: 26338314. Policy #0 lag: (min: 21.0, avg: 27.4, max: 53.0) -[2023-10-12 05:21:15,202][77203] Avg episode reward: [(0, '47.390'), (1, '45.300')] -[2023-10-12 05:21:15,316][78123] Updated weights for policy 1, policy_version 51320 (0.0009) -[2023-10-12 05:21:16,664][78091] Updated weights for policy 0, policy_version 51560 (0.0008) -[2023-10-12 05:21:17,032][78091] Updated weights for policy 0, policy_version 51570 (0.0010) -[2023-10-12 05:21:17,407][78091] Updated weights for policy 0, policy_version 51580 (0.0011) -[2023-10-12 05:21:19,757][78123] Updated weights for policy 1, policy_version 51330 (0.0009) -[2023-10-12 05:21:20,155][78123] Updated weights for policy 1, policy_version 51340 (0.0010) -[2023-10-12 05:21:20,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 105381888. Throughput: 0: 1598.7, 1: 1592.5. Samples: 26357840. Policy #0 lag: (min: 21.0, avg: 27.4, max: 53.0) -[2023-10-12 05:21:20,201][77203] Avg episode reward: [(0, '49.790'), (1, '42.750')] -[2023-10-12 05:21:20,516][78123] Updated weights for policy 1, policy_version 51350 (0.0007) -[2023-10-12 05:21:20,874][78123] Updated weights for policy 1, policy_version 51360 (0.0007) -[2023-10-12 05:21:21,695][78091] Updated weights for policy 0, policy_version 51590 (0.0008) -[2023-10-12 05:21:22,066][78091] Updated weights for policy 0, policy_version 51600 (0.0010) -[2023-10-12 05:21:22,446][78091] Updated weights for policy 0, policy_version 51610 (0.0009) -[2023-10-12 05:21:25,013][78123] Updated weights for policy 1, policy_version 51370 (0.0009) -[2023-10-12 05:21:25,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 105447424. Throughput: 0: 1596.3, 1: 1601.9. Samples: 26377136. Policy #0 lag: (min: 21.0, avg: 27.4, max: 53.0) -[2023-10-12 05:21:25,202][77203] Avg episode reward: [(0, '47.670'), (1, '43.340')] -[2023-10-12 05:21:25,371][78123] Updated weights for policy 1, policy_version 51380 (0.0009) -[2023-10-12 05:21:25,750][78123] Updated weights for policy 1, policy_version 51390 (0.0010) -[2023-10-12 05:21:26,655][78091] Updated weights for policy 0, policy_version 51620 (0.0010) -[2023-10-12 05:21:27,024][78091] Updated weights for policy 0, policy_version 51630 (0.0009) -[2023-10-12 05:21:27,390][78091] Updated weights for policy 0, policy_version 51640 (0.0009) -[2023-10-12 05:21:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 105512960. Throughput: 0: 1601.8, 1: 1576.1. Samples: 26385864. Policy #0 lag: (min: 21.0, avg: 27.4, max: 53.0) -[2023-10-12 05:21:30,201][77203] Avg episode reward: [(0, '50.070'), (1, '40.410')] -[2023-10-12 05:21:30,236][78123] Updated weights for policy 1, policy_version 51400 (0.0008) -[2023-10-12 05:21:30,603][78123] Updated weights for policy 1, policy_version 51410 (0.0008) -[2023-10-12 05:21:30,966][78123] Updated weights for policy 1, policy_version 51420 (0.0007) -[2023-10-12 05:21:31,687][78091] Updated weights for policy 0, policy_version 51650 (0.0009) -[2023-10-12 05:21:32,056][78091] Updated weights for policy 0, policy_version 51660 (0.0009) -[2023-10-12 05:21:32,426][78091] Updated weights for policy 0, policy_version 51670 (0.0009) -[2023-10-12 05:21:32,803][78091] Updated weights for policy 0, policy_version 51680 (0.0009) -[2023-10-12 05:21:35,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 105578496. Throughput: 0: 1601.7, 1: 1580.1. Samples: 26405170. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:21:35,201][77203] Avg episode reward: [(0, '48.610'), (1, '42.680')] -[2023-10-12 05:21:35,250][78123] Updated weights for policy 1, policy_version 51430 (0.0009) -[2023-10-12 05:21:35,612][78123] Updated weights for policy 1, policy_version 51440 (0.0008) -[2023-10-12 05:21:35,974][78123] Updated weights for policy 1, policy_version 51450 (0.0008) -[2023-10-12 05:21:37,054][78091] Updated weights for policy 0, policy_version 51690 (0.0009) -[2023-10-12 05:21:37,434][78091] Updated weights for policy 0, policy_version 51700 (0.0008) -[2023-10-12 05:21:37,804][78091] Updated weights for policy 0, policy_version 51710 (0.0009) -[2023-10-12 05:21:40,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 105644032. Throughput: 0: 1598.0, 1: 1598.4. Samples: 26424608. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:21:40,202][77203] Avg episode reward: [(0, '45.550'), (1, '40.440')] -[2023-10-12 05:21:40,320][78123] Updated weights for policy 1, policy_version 51460 (0.0008) -[2023-10-12 05:21:40,684][78123] Updated weights for policy 1, policy_version 51470 (0.0010) -[2023-10-12 05:21:41,052][78123] Updated weights for policy 1, policy_version 51480 (0.0009) -[2023-10-12 05:21:42,068][78091] Updated weights for policy 0, policy_version 51720 (0.0009) -[2023-10-12 05:21:42,450][78091] Updated weights for policy 0, policy_version 51730 (0.0009) -[2023-10-12 05:21:42,820][78091] Updated weights for policy 0, policy_version 51740 (0.0009) -[2023-10-12 05:21:45,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 105709568. Throughput: 0: 1605.1, 1: 1576.2. Samples: 26433590. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:21:45,202][77203] Avg episode reward: [(0, '56.140'), (1, '48.130')] -[2023-10-12 05:21:45,203][77792] Saving new best policy, reward=56.140! -[2023-10-12 05:21:45,353][78123] Updated weights for policy 1, policy_version 51490 (0.0008) -[2023-10-12 05:21:45,718][78123] Updated weights for policy 1, policy_version 51500 (0.0007) -[2023-10-12 05:21:46,091][78123] Updated weights for policy 1, policy_version 51510 (0.0009) -[2023-10-12 05:21:46,463][78123] Updated weights for policy 1, policy_version 51520 (0.0008) -[2023-10-12 05:21:47,093][78091] Updated weights for policy 0, policy_version 51750 (0.0008) -[2023-10-12 05:21:47,459][78091] Updated weights for policy 0, policy_version 51760 (0.0010) -[2023-10-12 05:21:47,834][78091] Updated weights for policy 0, policy_version 51770 (0.0008) -[2023-10-12 05:21:50,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 105775104. Throughput: 0: 1599.6, 1: 1570.9. Samples: 26452898. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:21:50,201][77203] Avg episode reward: [(0, '54.170'), (1, '41.900')] -[2023-10-12 05:21:50,848][78123] Updated weights for policy 1, policy_version 51530 (0.0010) -[2023-10-12 05:21:51,212][78123] Updated weights for policy 1, policy_version 51540 (0.0008) -[2023-10-12 05:21:51,584][78123] Updated weights for policy 1, policy_version 51550 (0.0009) -[2023-10-12 05:21:52,056][78091] Updated weights for policy 0, policy_version 51780 (0.0008) -[2023-10-12 05:21:52,424][78091] Updated weights for policy 0, policy_version 51790 (0.0008) -[2023-10-12 05:21:52,797][78091] Updated weights for policy 0, policy_version 51800 (0.0009) -[2023-10-12 05:21:55,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 105840640. Throughput: 0: 1598.5, 1: 1577.7. Samples: 26472354. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:21:55,202][77203] Avg episode reward: [(0, '51.340'), (1, '48.020')] -[2023-10-12 05:21:56,006][78123] Updated weights for policy 1, policy_version 51560 (0.0011) -[2023-10-12 05:21:56,371][78123] Updated weights for policy 1, policy_version 51570 (0.0008) -[2023-10-12 05:21:56,752][78123] Updated weights for policy 1, policy_version 51580 (0.0011) -[2023-10-12 05:21:57,039][78091] Updated weights for policy 0, policy_version 51810 (0.0009) -[2023-10-12 05:21:57,411][78091] Updated weights for policy 0, policy_version 51820 (0.0008) -[2023-10-12 05:21:57,785][78091] Updated weights for policy 0, policy_version 51830 (0.0009) -[2023-10-12 05:21:58,156][78091] Updated weights for policy 0, policy_version 51840 (0.0008) -[2023-10-12 05:22:00,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 105906176. Throughput: 0: 1612.1, 1: 1568.9. Samples: 26481462. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:22:00,202][77203] Avg episode reward: [(0, '45.190'), (1, '45.750')] -[2023-10-12 05:22:01,049][78123] Updated weights for policy 1, policy_version 51590 (0.0009) -[2023-10-12 05:22:01,410][78123] Updated weights for policy 1, policy_version 51600 (0.0007) -[2023-10-12 05:22:01,781][78123] Updated weights for policy 1, policy_version 51610 (0.0008) -[2023-10-12 05:22:02,531][78091] Updated weights for policy 0, policy_version 51850 (0.0009) -[2023-10-12 05:22:02,895][78091] Updated weights for policy 0, policy_version 51860 (0.0008) -[2023-10-12 05:22:03,262][78091] Updated weights for policy 0, policy_version 51870 (0.0007) -[2023-10-12 05:22:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 105971712. Throughput: 0: 1596.6, 1: 1574.7. Samples: 26500548. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:22:05,202][77203] Avg episode reward: [(0, '42.880'), (1, '49.460')] -[2023-10-12 05:22:06,203][78123] Updated weights for policy 1, policy_version 51620 (0.0007) -[2023-10-12 05:22:06,596][78123] Updated weights for policy 1, policy_version 51630 (0.0009) -[2023-10-12 05:22:06,961][78123] Updated weights for policy 1, policy_version 51640 (0.0011) -[2023-10-12 05:22:07,648][78091] Updated weights for policy 0, policy_version 51880 (0.0008) -[2023-10-12 05:22:08,026][78091] Updated weights for policy 0, policy_version 51890 (0.0007) -[2023-10-12 05:22:08,389][78091] Updated weights for policy 0, policy_version 51900 (0.0009) -[2023-10-12 05:22:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 106037248. Throughput: 0: 1595.2, 1: 1580.2. Samples: 26520030. Policy #0 lag: (min: 6.0, avg: 13.7, max: 38.0) -[2023-10-12 05:22:10,201][77203] Avg episode reward: [(0, '55.930'), (1, '44.350')] -[2023-10-12 05:22:11,395][78123] Updated weights for policy 1, policy_version 51650 (0.0009) -[2023-10-12 05:22:11,768][78123] Updated weights for policy 1, policy_version 51660 (0.0007) -[2023-10-12 05:22:12,130][78123] Updated weights for policy 1, policy_version 51670 (0.0008) -[2023-10-12 05:22:12,495][78123] Updated weights for policy 1, policy_version 51680 (0.0008) -[2023-10-12 05:22:12,735][78091] Updated weights for policy 0, policy_version 51910 (0.0008) -[2023-10-12 05:22:13,110][78091] Updated weights for policy 0, policy_version 51920 (0.0011) -[2023-10-12 05:22:13,491][78091] Updated weights for policy 0, policy_version 51930 (0.0010) -[2023-10-12 05:22:15,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 106102784. Throughput: 0: 1610.8, 1: 1576.9. Samples: 26529314. Policy #0 lag: (min: 6.0, avg: 13.7, max: 38.0) -[2023-10-12 05:22:15,202][77203] Avg episode reward: [(0, '49.440'), (1, '45.210')] -[2023-10-12 05:22:16,706][78123] Updated weights for policy 1, policy_version 51690 (0.0007) -[2023-10-12 05:22:17,071][78123] Updated weights for policy 1, policy_version 51700 (0.0007) -[2023-10-12 05:22:17,447][78123] Updated weights for policy 1, policy_version 51710 (0.0008) -[2023-10-12 05:22:17,970][78091] Updated weights for policy 0, policy_version 51940 (0.0010) -[2023-10-12 05:22:18,348][78091] Updated weights for policy 0, policy_version 51950 (0.0008) -[2023-10-12 05:22:18,734][78091] Updated weights for policy 0, policy_version 51960 (0.0008) -[2023-10-12 05:22:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 106168320. Throughput: 0: 1597.5, 1: 1584.3. Samples: 26548350. Policy #0 lag: (min: 6.0, avg: 13.7, max: 38.0) -[2023-10-12 05:22:20,201][77203] Avg episode reward: [(0, '45.690'), (1, '44.900')] -[2023-10-12 05:22:21,674][78123] Updated weights for policy 1, policy_version 51720 (0.0008) -[2023-10-12 05:22:22,049][78123] Updated weights for policy 1, policy_version 51730 (0.0008) -[2023-10-12 05:22:22,422][78123] Updated weights for policy 1, policy_version 51740 (0.0009) -[2023-10-12 05:22:22,981][78091] Updated weights for policy 0, policy_version 51970 (0.0009) -[2023-10-12 05:22:23,357][78091] Updated weights for policy 0, policy_version 51980 (0.0009) -[2023-10-12 05:22:23,735][78091] Updated weights for policy 0, policy_version 51990 (0.0009) -[2023-10-12 05:22:24,099][78091] Updated weights for policy 0, policy_version 52000 (0.0009) -[2023-10-12 05:22:25,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 106233856. Throughput: 0: 1590.2, 1: 1584.4. Samples: 26567464. Policy #0 lag: (min: 6.0, avg: 13.7, max: 38.0) -[2023-10-12 05:22:25,202][77203] Avg episode reward: [(0, '46.530'), (1, '44.380')] -[2023-10-12 05:22:26,737][78123] Updated weights for policy 1, policy_version 51750 (0.0009) -[2023-10-12 05:22:27,104][78123] Updated weights for policy 1, policy_version 51760 (0.0009) -[2023-10-12 05:22:27,474][78123] Updated weights for policy 1, policy_version 51770 (0.0008) -[2023-10-12 05:22:28,352][78091] Updated weights for policy 0, policy_version 52010 (0.0010) -[2023-10-12 05:22:28,730][78091] Updated weights for policy 0, policy_version 52020 (0.0010) -[2023-10-12 05:22:29,093][78091] Updated weights for policy 0, policy_version 52030 (0.0010) -[2023-10-12 05:22:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 106299392. Throughput: 0: 1614.8, 1: 1583.6. Samples: 26577520. Policy #0 lag: (min: 6.0, avg: 13.7, max: 38.0) -[2023-10-12 05:22:30,202][77203] Avg episode reward: [(0, '51.830'), (1, '46.650')] -[2023-10-12 05:22:31,771][78123] Updated weights for policy 1, policy_version 51780 (0.0008) -[2023-10-12 05:22:32,127][78123] Updated weights for policy 1, policy_version 51790 (0.0009) -[2023-10-12 05:22:32,497][78123] Updated weights for policy 1, policy_version 51800 (0.0008) -[2023-10-12 05:22:33,423][78091] Updated weights for policy 0, policy_version 52040 (0.0010) -[2023-10-12 05:22:33,792][78091] Updated weights for policy 0, policy_version 52050 (0.0009) -[2023-10-12 05:22:34,161][78091] Updated weights for policy 0, policy_version 52060 (0.0008) -[2023-10-12 05:22:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 106364928. Throughput: 0: 1598.4, 1: 1591.4. Samples: 26596440. Policy #0 lag: (min: 6.0, avg: 13.7, max: 38.0) -[2023-10-12 05:22:35,202][77203] Avg episode reward: [(0, '48.850'), (1, '51.350')] -[2023-10-12 05:22:36,679][78123] Updated weights for policy 1, policy_version 51810 (0.0009) -[2023-10-12 05:22:37,037][78123] Updated weights for policy 1, policy_version 51820 (0.0007) -[2023-10-12 05:22:37,405][78123] Updated weights for policy 1, policy_version 51830 (0.0008) -[2023-10-12 05:22:37,777][78123] Updated weights for policy 1, policy_version 51840 (0.0008) -[2023-10-12 05:22:38,399][78091] Updated weights for policy 0, policy_version 52070 (0.0008) -[2023-10-12 05:22:38,761][78091] Updated weights for policy 0, policy_version 52080 (0.0010) -[2023-10-12 05:22:39,136][78091] Updated weights for policy 0, policy_version 52090 (0.0010) -[2023-10-12 05:22:40,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 106430464. Throughput: 0: 1585.2, 1: 1594.5. Samples: 26615442. Policy #0 lag: (min: 6.0, avg: 13.7, max: 38.0) -[2023-10-12 05:22:40,201][77203] Avg episode reward: [(0, '43.090'), (1, '48.530')] -[2023-10-12 05:22:42,157][78123] Updated weights for policy 1, policy_version 51850 (0.0009) -[2023-10-12 05:22:42,525][78123] Updated weights for policy 1, policy_version 51860 (0.0008) -[2023-10-12 05:22:42,894][78123] Updated weights for policy 1, policy_version 51870 (0.0009) -[2023-10-12 05:22:43,505][78091] Updated weights for policy 0, policy_version 52100 (0.0010) -[2023-10-12 05:22:43,875][78091] Updated weights for policy 0, policy_version 52110 (0.0010) -[2023-10-12 05:22:44,249][78091] Updated weights for policy 0, policy_version 52120 (0.0009) -[2023-10-12 05:22:45,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 106496000. Throughput: 0: 1602.4, 1: 1599.2. Samples: 26625536. Policy #0 lag: (min: 22.0, avg: 25.9, max: 54.0) -[2023-10-12 05:22:45,201][77203] Avg episode reward: [(0, '46.880'), (1, '45.390')] -[2023-10-12 05:22:47,347][78123] Updated weights for policy 1, policy_version 51880 (0.0008) -[2023-10-12 05:22:47,725][78123] Updated weights for policy 1, policy_version 51890 (0.0011) -[2023-10-12 05:22:48,089][78123] Updated weights for policy 1, policy_version 51900 (0.0010) -[2023-10-12 05:22:48,723][78091] Updated weights for policy 0, policy_version 52130 (0.0010) -[2023-10-12 05:22:49,097][78091] Updated weights for policy 0, policy_version 52140 (0.0008) -[2023-10-12 05:22:49,459][78091] Updated weights for policy 0, policy_version 52150 (0.0009) -[2023-10-12 05:22:49,830][78091] Updated weights for policy 0, policy_version 52160 (0.0007) -[2023-10-12 05:22:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 106561536. Throughput: 0: 1611.2, 1: 1589.5. Samples: 26644580. Policy #0 lag: (min: 22.0, avg: 25.9, max: 54.0) -[2023-10-12 05:22:50,201][77203] Avg episode reward: [(0, '48.690'), (1, '44.230')] -[2023-10-12 05:22:52,527][78123] Updated weights for policy 1, policy_version 51910 (0.0010) -[2023-10-12 05:22:52,905][78123] Updated weights for policy 1, policy_version 51920 (0.0008) -[2023-10-12 05:22:53,270][78123] Updated weights for policy 1, policy_version 51930 (0.0008) -[2023-10-12 05:22:54,181][78091] Updated weights for policy 0, policy_version 52170 (0.0010) -[2023-10-12 05:22:54,550][78091] Updated weights for policy 0, policy_version 52180 (0.0010) -[2023-10-12 05:22:54,926][78091] Updated weights for policy 0, policy_version 52190 (0.0010) -[2023-10-12 05:22:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 106627072. Throughput: 0: 1595.6, 1: 1589.4. Samples: 26663358. Policy #0 lag: (min: 22.0, avg: 25.9, max: 54.0) -[2023-10-12 05:22:55,201][77203] Avg episode reward: [(0, '50.180'), (1, '42.990')] -[2023-10-12 05:22:57,472][78123] Updated weights for policy 1, policy_version 51940 (0.0008) -[2023-10-12 05:22:57,844][78123] Updated weights for policy 1, policy_version 51950 (0.0010) -[2023-10-12 05:22:58,201][78123] Updated weights for policy 1, policy_version 51960 (0.0011) -[2023-10-12 05:22:59,092][78091] Updated weights for policy 0, policy_version 52200 (0.0011) -[2023-10-12 05:22:59,457][78091] Updated weights for policy 0, policy_version 52210 (0.0011) -[2023-10-12 05:22:59,830][78091] Updated weights for policy 0, policy_version 52220 (0.0009) -[2023-10-12 05:23:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 106692608. Throughput: 0: 1598.7, 1: 1607.3. Samples: 26673586. Policy #0 lag: (min: 22.0, avg: 25.9, max: 54.0) -[2023-10-12 05:23:00,202][77203] Avg episode reward: [(0, '53.670'), (1, '36.870')] -[2023-10-12 05:23:02,540][78123] Updated weights for policy 1, policy_version 51970 (0.0008) -[2023-10-12 05:23:02,909][78123] Updated weights for policy 1, policy_version 51980 (0.0009) -[2023-10-12 05:23:03,284][78123] Updated weights for policy 1, policy_version 51990 (0.0008) -[2023-10-12 05:23:03,645][78123] Updated weights for policy 1, policy_version 52000 (0.0010) -[2023-10-12 05:23:03,861][78091] Updated weights for policy 0, policy_version 52230 (0.0010) -[2023-10-12 05:23:04,233][78091] Updated weights for policy 0, policy_version 52240 (0.0009) -[2023-10-12 05:23:04,603][78091] Updated weights for policy 0, policy_version 52250 (0.0009) -[2023-10-12 05:23:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 106758144. Throughput: 0: 1618.1, 1: 1580.2. Samples: 26692274. Policy #0 lag: (min: 22.0, avg: 25.9, max: 54.0) -[2023-10-12 05:23:05,202][77203] Avg episode reward: [(0, '45.030'), (1, '36.680')] -[2023-10-12 05:23:08,062][78123] Updated weights for policy 1, policy_version 52010 (0.0008) -[2023-10-12 05:23:08,428][78123] Updated weights for policy 1, policy_version 52020 (0.0010) -[2023-10-12 05:23:08,794][78123] Updated weights for policy 1, policy_version 52030 (0.0010) -[2023-10-12 05:23:09,027][78091] Updated weights for policy 0, policy_version 52260 (0.0008) -[2023-10-12 05:23:09,392][78091] Updated weights for policy 0, policy_version 52270 (0.0007) -[2023-10-12 05:23:09,778][78091] Updated weights for policy 0, policy_version 52280 (0.0007) -[2023-10-12 05:23:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 106823680. Throughput: 0: 1607.9, 1: 1582.7. Samples: 26711040. Policy #0 lag: (min: 22.0, avg: 25.9, max: 54.0) -[2023-10-12 05:23:10,202][77203] Avg episode reward: [(0, '45.990'), (1, '39.840')] -[2023-10-12 05:23:10,210][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000052032_53280768.pth... -[2023-10-12 05:23:10,211][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000052288_53542912.pth... -[2023-10-12 05:23:10,239][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000050528_51740672.pth -[2023-10-12 05:23:10,242][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000050784_52002816.pth -[2023-10-12 05:23:10,243][77950] Saving a milestone ./train_atari/atari_hero_APPO/checkpoint_p1/milestones/checkpoint_000052032_53280768.pth -[2023-10-12 05:23:10,246][77792] Saving a milestone ./train_atari/atari_hero_APPO/checkpoint_p0/milestones/checkpoint_000052288_53542912.pth -[2023-10-12 05:23:13,230][78123] Updated weights for policy 1, policy_version 52040 (0.0008) -[2023-10-12 05:23:13,601][78123] Updated weights for policy 1, policy_version 52050 (0.0009) -[2023-10-12 05:23:13,806][78091] Updated weights for policy 0, policy_version 52290 (0.0009) -[2023-10-12 05:23:13,963][78123] Updated weights for policy 1, policy_version 52060 (0.0008) -[2023-10-12 05:23:14,172][78091] Updated weights for policy 0, policy_version 52300 (0.0010) -[2023-10-12 05:23:14,559][78091] Updated weights for policy 0, policy_version 52310 (0.0010) -[2023-10-12 05:23:14,935][78091] Updated weights for policy 0, policy_version 52320 (0.0007) -[2023-10-12 05:23:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 106889216. Throughput: 0: 1601.3, 1: 1606.9. Samples: 26721890. Policy #0 lag: (min: 22.0, avg: 25.9, max: 54.0) -[2023-10-12 05:23:15,201][77203] Avg episode reward: [(0, '46.510'), (1, '40.710')] -[2023-10-12 05:23:18,284][78123] Updated weights for policy 1, policy_version 52070 (0.0010) -[2023-10-12 05:23:18,654][78123] Updated weights for policy 1, policy_version 52080 (0.0008) -[2023-10-12 05:23:19,020][78123] Updated weights for policy 1, policy_version 52090 (0.0007) -[2023-10-12 05:23:19,440][78091] Updated weights for policy 0, policy_version 52330 (0.0008) -[2023-10-12 05:23:19,819][78091] Updated weights for policy 0, policy_version 52340 (0.0007) -[2023-10-12 05:23:20,179][78091] Updated weights for policy 0, policy_version 52350 (0.0007) -[2023-10-12 05:23:20,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 106921984. Throughput: 0: 1616.5, 1: 1592.0. Samples: 26740824. Policy #0 lag: (min: 22.0, avg: 25.9, max: 54.0) -[2023-10-12 05:23:20,202][77203] Avg episode reward: [(0, '45.150'), (1, '42.360')] -[2023-10-12 05:23:23,317][78123] Updated weights for policy 1, policy_version 52100 (0.0008) -[2023-10-12 05:23:23,688][78123] Updated weights for policy 1, policy_version 52110 (0.0008) -[2023-10-12 05:23:24,048][78123] Updated weights for policy 1, policy_version 52120 (0.0011) -[2023-10-12 05:23:24,628][78091] Updated weights for policy 0, policy_version 52360 (0.0010) -[2023-10-12 05:23:24,995][78091] Updated weights for policy 0, policy_version 52370 (0.0009) -[2023-10-12 05:23:25,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 106987520. Throughput: 0: 1617.4, 1: 1582.1. Samples: 26759418. Policy #0 lag: (min: 31.0, avg: 35.8, max: 63.0) -[2023-10-12 05:23:25,202][77203] Avg episode reward: [(0, '45.850'), (1, '43.020')] -[2023-10-12 05:23:25,372][78091] Updated weights for policy 0, policy_version 52380 (0.0009) -[2023-10-12 05:23:28,318][78123] Updated weights for policy 1, policy_version 52130 (0.0009) -[2023-10-12 05:23:28,685][78123] Updated weights for policy 1, policy_version 52140 (0.0007) -[2023-10-12 05:23:29,046][78123] Updated weights for policy 1, policy_version 52150 (0.0008) -[2023-10-12 05:23:29,416][78123] Updated weights for policy 1, policy_version 52160 (0.0009) -[2023-10-12 05:23:29,602][78091] Updated weights for policy 0, policy_version 52390 (0.0010) -[2023-10-12 05:23:29,973][78091] Updated weights for policy 0, policy_version 52400 (0.0010) -[2023-10-12 05:23:30,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 107053056. Throughput: 0: 1597.8, 1: 1602.4. Samples: 26769544. Policy #0 lag: (min: 31.0, avg: 35.8, max: 63.0) -[2023-10-12 05:23:30,201][77203] Avg episode reward: [(0, '48.200'), (1, '41.830')] -[2023-10-12 05:23:30,334][78091] Updated weights for policy 0, policy_version 52410 (0.0010) -[2023-10-12 05:23:33,787][78123] Updated weights for policy 1, policy_version 52170 (0.0008) -[2023-10-12 05:23:34,159][78123] Updated weights for policy 1, policy_version 52180 (0.0008) -[2023-10-12 05:23:34,526][78123] Updated weights for policy 1, policy_version 52190 (0.0011) -[2023-10-12 05:23:34,762][78091] Updated weights for policy 0, policy_version 52420 (0.0007) -[2023-10-12 05:23:35,132][78091] Updated weights for policy 0, policy_version 52430 (0.0007) -[2023-10-12 05:23:35,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 107118592. Throughput: 0: 1600.0, 1: 1602.8. Samples: 26788706. Policy #0 lag: (min: 31.0, avg: 35.8, max: 63.0) -[2023-10-12 05:23:35,202][77203] Avg episode reward: [(0, '55.570'), (1, '46.160')] -[2023-10-12 05:23:35,502][78091] Updated weights for policy 0, policy_version 52440 (0.0007) -[2023-10-12 05:23:38,951][78123] Updated weights for policy 1, policy_version 52200 (0.0010) -[2023-10-12 05:23:39,328][78123] Updated weights for policy 1, policy_version 52210 (0.0008) -[2023-10-12 05:23:39,686][78123] Updated weights for policy 1, policy_version 52220 (0.0009) -[2023-10-12 05:23:39,816][78091] Updated weights for policy 0, policy_version 52450 (0.0007) -[2023-10-12 05:23:40,192][78091] Updated weights for policy 0, policy_version 52460 (0.0009) -[2023-10-12 05:23:40,201][77203] Fps is (10 sec: 13106.7, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 107184128. Throughput: 0: 1612.1, 1: 1585.9. Samples: 26807270. Policy #0 lag: (min: 31.0, avg: 35.8, max: 63.0) -[2023-10-12 05:23:40,202][77203] Avg episode reward: [(0, '43.720'), (1, '44.360')] -[2023-10-12 05:23:40,557][78091] Updated weights for policy 0, policy_version 52470 (0.0010) -[2023-10-12 05:23:40,940][78091] Updated weights for policy 0, policy_version 52480 (0.0007) -[2023-10-12 05:23:44,083][78123] Updated weights for policy 1, policy_version 52230 (0.0008) -[2023-10-12 05:23:44,445][78123] Updated weights for policy 1, policy_version 52240 (0.0007) -[2023-10-12 05:23:44,824][78123] Updated weights for policy 1, policy_version 52250 (0.0008) -[2023-10-12 05:23:45,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 107249664. Throughput: 0: 1592.4, 1: 1591.7. Samples: 26816872. Policy #0 lag: (min: 31.0, avg: 35.8, max: 63.0) -[2023-10-12 05:23:45,202][77203] Avg episode reward: [(0, '46.200'), (1, '47.660')] -[2023-10-12 05:23:45,248][78091] Updated weights for policy 0, policy_version 52490 (0.0010) -[2023-10-12 05:23:45,625][78091] Updated weights for policy 0, policy_version 52500 (0.0009) -[2023-10-12 05:23:45,997][78091] Updated weights for policy 0, policy_version 52510 (0.0008) -[2023-10-12 05:23:48,900][78123] Updated weights for policy 1, policy_version 52260 (0.0010) -[2023-10-12 05:23:49,270][78123] Updated weights for policy 1, policy_version 52270 (0.0008) -[2023-10-12 05:23:49,635][78123] Updated weights for policy 1, policy_version 52280 (0.0009) -[2023-10-12 05:23:50,201][77203] Fps is (10 sec: 13107.6, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 107315200. Throughput: 0: 1587.2, 1: 1614.4. Samples: 26836344. Policy #0 lag: (min: 31.0, avg: 35.8, max: 63.0) -[2023-10-12 05:23:50,201][77203] Avg episode reward: [(0, '48.520'), (1, '39.180')] -[2023-10-12 05:23:50,325][78091] Updated weights for policy 0, policy_version 52520 (0.0010) -[2023-10-12 05:23:50,698][78091] Updated weights for policy 0, policy_version 52530 (0.0011) -[2023-10-12 05:23:51,062][78091] Updated weights for policy 0, policy_version 52540 (0.0010) -[2023-10-12 05:23:54,102][78123] Updated weights for policy 1, policy_version 52290 (0.0007) -[2023-10-12 05:23:54,470][78123] Updated weights for policy 1, policy_version 52300 (0.0007) -[2023-10-12 05:23:54,846][78123] Updated weights for policy 1, policy_version 52310 (0.0008) -[2023-10-12 05:23:55,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 107347968. Throughput: 0: 1600.0, 1: 1596.4. Samples: 26854880. Policy #0 lag: (min: 31.0, avg: 35.8, max: 63.0) -[2023-10-12 05:23:55,201][77203] Avg episode reward: [(0, '55.820'), (1, '42.730')] -[2023-10-12 05:23:55,213][78123] Updated weights for policy 1, policy_version 52320 (0.0007) -[2023-10-12 05:23:55,603][78091] Updated weights for policy 0, policy_version 52550 (0.0009) -[2023-10-12 05:23:55,976][78091] Updated weights for policy 0, policy_version 52560 (0.0010) -[2023-10-12 05:23:56,352][78091] Updated weights for policy 0, policy_version 52570 (0.0010) -[2023-10-12 05:23:59,510][78123] Updated weights for policy 1, policy_version 52330 (0.0007) -[2023-10-12 05:23:59,884][78123] Updated weights for policy 1, policy_version 52340 (0.0011) -[2023-10-12 05:24:00,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 107413504. Throughput: 0: 1572.8, 1: 1590.1. Samples: 26864218. Policy #0 lag: (min: 31.0, avg: 32.1, max: 55.0) -[2023-10-12 05:24:00,201][77203] Avg episode reward: [(0, '38.570'), (1, '46.470')] -[2023-10-12 05:24:00,250][78123] Updated weights for policy 1, policy_version 52350 (0.0008) -[2023-10-12 05:24:00,594][78091] Updated weights for policy 0, policy_version 52580 (0.0009) -[2023-10-12 05:24:00,983][78091] Updated weights for policy 0, policy_version 52590 (0.0009) -[2023-10-12 05:24:01,354][78091] Updated weights for policy 0, policy_version 52600 (0.0007) -[2023-10-12 05:24:04,633][78123] Updated weights for policy 1, policy_version 52360 (0.0009) -[2023-10-12 05:24:05,007][78123] Updated weights for policy 1, policy_version 52370 (0.0009) -[2023-10-12 05:24:05,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 107479040. Throughput: 0: 1577.2, 1: 1597.5. Samples: 26883684. Policy #0 lag: (min: 31.0, avg: 32.1, max: 55.0) -[2023-10-12 05:24:05,202][77203] Avg episode reward: [(0, '48.300'), (1, '48.250')] -[2023-10-12 05:24:05,366][78123] Updated weights for policy 1, policy_version 52380 (0.0009) -[2023-10-12 05:24:05,770][78091] Updated weights for policy 0, policy_version 52610 (0.0009) -[2023-10-12 05:24:06,151][78091] Updated weights for policy 0, policy_version 52620 (0.0009) -[2023-10-12 05:24:06,509][78091] Updated weights for policy 0, policy_version 52630 (0.0009) -[2023-10-12 05:24:06,888][78091] Updated weights for policy 0, policy_version 52640 (0.0009) -[2023-10-12 05:24:09,645][78123] Updated weights for policy 1, policy_version 52390 (0.0008) -[2023-10-12 05:24:10,015][78123] Updated weights for policy 1, policy_version 52400 (0.0009) -[2023-10-12 05:24:10,201][77203] Fps is (10 sec: 13106.8, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 107544576. Throughput: 0: 1586.3, 1: 1605.6. Samples: 26903056. Policy #0 lag: (min: 31.0, avg: 32.1, max: 55.0) -[2023-10-12 05:24:10,202][77203] Avg episode reward: [(0, '43.480'), (1, '41.730')] -[2023-10-12 05:24:10,395][78123] Updated weights for policy 1, policy_version 52410 (0.0007) -[2023-10-12 05:24:11,121][78091] Updated weights for policy 0, policy_version 52650 (0.0007) -[2023-10-12 05:24:11,489][78091] Updated weights for policy 0, policy_version 52660 (0.0007) -[2023-10-12 05:24:11,858][78091] Updated weights for policy 0, policy_version 52670 (0.0007) -[2023-10-12 05:24:14,752][78123] Updated weights for policy 1, policy_version 52420 (0.0010) -[2023-10-12 05:24:15,120][78123] Updated weights for policy 1, policy_version 52430 (0.0009) -[2023-10-12 05:24:15,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 107610112. Throughput: 0: 1579.6, 1: 1583.0. Samples: 26911862. Policy #0 lag: (min: 31.0, avg: 32.1, max: 55.0) -[2023-10-12 05:24:15,201][77203] Avg episode reward: [(0, '50.200'), (1, '42.540')] -[2023-10-12 05:24:15,489][78123] Updated weights for policy 1, policy_version 52440 (0.0007) -[2023-10-12 05:24:16,180][78091] Updated weights for policy 0, policy_version 52680 (0.0010) -[2023-10-12 05:24:16,559][78091] Updated weights for policy 0, policy_version 52690 (0.0008) -[2023-10-12 05:24:16,943][78091] Updated weights for policy 0, policy_version 52700 (0.0010) -[2023-10-12 05:24:19,956][78123] Updated weights for policy 1, policy_version 52450 (0.0009) -[2023-10-12 05:24:20,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 107675648. Throughput: 0: 1575.2, 1: 1595.9. Samples: 26931404. Policy #0 lag: (min: 31.0, avg: 32.1, max: 55.0) -[2023-10-12 05:24:20,201][77203] Avg episode reward: [(0, '41.460'), (1, '53.910')] -[2023-10-12 05:24:20,313][78123] Updated weights for policy 1, policy_version 52460 (0.0008) -[2023-10-12 05:24:20,683][78123] Updated weights for policy 1, policy_version 52470 (0.0009) -[2023-10-12 05:24:21,045][77950] Saving new best policy, reward=53.910! -[2023-10-12 05:24:21,049][78123] Updated weights for policy 1, policy_version 52480 (0.0009) -[2023-10-12 05:24:21,223][78091] Updated weights for policy 0, policy_version 52710 (0.0008) -[2023-10-12 05:24:21,590][78091] Updated weights for policy 0, policy_version 52720 (0.0008) -[2023-10-12 05:24:21,954][78091] Updated weights for policy 0, policy_version 52730 (0.0007) -[2023-10-12 05:24:25,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 107741184. Throughput: 0: 1577.7, 1: 1610.9. Samples: 26950758. Policy #0 lag: (min: 31.0, avg: 32.1, max: 55.0) -[2023-10-12 05:24:25,201][77203] Avg episode reward: [(0, '51.630'), (1, '40.190')] -[2023-10-12 05:24:25,454][78123] Updated weights for policy 1, policy_version 52490 (0.0007) -[2023-10-12 05:24:25,832][78123] Updated weights for policy 1, policy_version 52500 (0.0007) -[2023-10-12 05:24:26,192][78123] Updated weights for policy 1, policy_version 52510 (0.0007) -[2023-10-12 05:24:26,437][78091] Updated weights for policy 0, policy_version 52740 (0.0008) -[2023-10-12 05:24:26,810][78091] Updated weights for policy 0, policy_version 52750 (0.0008) -[2023-10-12 05:24:27,187][78091] Updated weights for policy 0, policy_version 52760 (0.0007) -[2023-10-12 05:24:30,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 107806720. Throughput: 0: 1576.1, 1: 1586.8. Samples: 26959202. Policy #0 lag: (min: 31.0, avg: 32.1, max: 55.0) -[2023-10-12 05:24:30,202][77203] Avg episode reward: [(0, '46.810'), (1, '37.910')] -[2023-10-12 05:24:30,521][78123] Updated weights for policy 1, policy_version 52520 (0.0007) -[2023-10-12 05:24:30,890][78123] Updated weights for policy 1, policy_version 52530 (0.0007) -[2023-10-12 05:24:31,248][78123] Updated weights for policy 1, policy_version 52540 (0.0007) -[2023-10-12 05:24:31,537][78091] Updated weights for policy 0, policy_version 52770 (0.0009) -[2023-10-12 05:24:31,914][78091] Updated weights for policy 0, policy_version 52780 (0.0010) -[2023-10-12 05:24:32,285][78091] Updated weights for policy 0, policy_version 52790 (0.0010) -[2023-10-12 05:24:32,651][78091] Updated weights for policy 0, policy_version 52800 (0.0010) -[2023-10-12 05:24:35,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 107872256. Throughput: 0: 1578.9, 1: 1585.7. Samples: 26978752. Policy #0 lag: (min: 7.0, avg: 10.4, max: 39.0) -[2023-10-12 05:24:35,202][77203] Avg episode reward: [(0, '56.230'), (1, '40.270')] -[2023-10-12 05:24:35,204][77792] Saving new best policy, reward=56.230! -[2023-10-12 05:24:35,664][78123] Updated weights for policy 1, policy_version 52550 (0.0008) -[2023-10-12 05:24:36,034][78123] Updated weights for policy 1, policy_version 52560 (0.0007) -[2023-10-12 05:24:36,395][78123] Updated weights for policy 1, policy_version 52570 (0.0008) -[2023-10-12 05:24:36,975][78091] Updated weights for policy 0, policy_version 52810 (0.0007) -[2023-10-12 05:24:37,353][78091] Updated weights for policy 0, policy_version 52820 (0.0009) -[2023-10-12 05:24:37,724][78091] Updated weights for policy 0, policy_version 52830 (0.0009) -[2023-10-12 05:24:40,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 107937792. Throughput: 0: 1585.7, 1: 1601.6. Samples: 26998310. Policy #0 lag: (min: 7.0, avg: 10.4, max: 39.0) -[2023-10-12 05:24:40,201][77203] Avg episode reward: [(0, '40.840'), (1, '43.210')] -[2023-10-12 05:24:40,657][78123] Updated weights for policy 1, policy_version 52580 (0.0008) -[2023-10-12 05:24:41,019][78123] Updated weights for policy 1, policy_version 52590 (0.0009) -[2023-10-12 05:24:41,388][78123] Updated weights for policy 1, policy_version 52600 (0.0010) -[2023-10-12 05:24:41,872][78091] Updated weights for policy 0, policy_version 52840 (0.0010) -[2023-10-12 05:24:42,238][78091] Updated weights for policy 0, policy_version 52850 (0.0009) -[2023-10-12 05:24:42,609][78091] Updated weights for policy 0, policy_version 52860 (0.0009) -[2023-10-12 05:24:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 108003328. Throughput: 0: 1589.2, 1: 1582.3. Samples: 27006936. Policy #0 lag: (min: 7.0, avg: 10.4, max: 39.0) -[2023-10-12 05:24:45,202][77203] Avg episode reward: [(0, '51.950'), (1, '41.000')] -[2023-10-12 05:24:45,721][78123] Updated weights for policy 1, policy_version 52610 (0.0008) -[2023-10-12 05:24:46,088][78123] Updated weights for policy 1, policy_version 52620 (0.0010) -[2023-10-12 05:24:46,457][78123] Updated weights for policy 1, policy_version 52630 (0.0008) -[2023-10-12 05:24:46,832][78123] Updated weights for policy 1, policy_version 52640 (0.0009) -[2023-10-12 05:24:47,067][78091] Updated weights for policy 0, policy_version 52870 (0.0008) -[2023-10-12 05:24:47,436][78091] Updated weights for policy 0, policy_version 52880 (0.0008) -[2023-10-12 05:24:47,806][78091] Updated weights for policy 0, policy_version 52890 (0.0008) -[2023-10-12 05:24:50,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 108068864. Throughput: 0: 1589.4, 1: 1580.6. Samples: 27026334. Policy #0 lag: (min: 7.0, avg: 10.4, max: 39.0) -[2023-10-12 05:24:50,202][77203] Avg episode reward: [(0, '55.230'), (1, '41.020')] -[2023-10-12 05:24:51,237][78123] Updated weights for policy 1, policy_version 52650 (0.0008) -[2023-10-12 05:24:51,599][78123] Updated weights for policy 1, policy_version 52660 (0.0007) -[2023-10-12 05:24:51,966][78123] Updated weights for policy 1, policy_version 52670 (0.0008) -[2023-10-12 05:24:52,147][78091] Updated weights for policy 0, policy_version 52900 (0.0009) -[2023-10-12 05:24:52,528][78091] Updated weights for policy 0, policy_version 52910 (0.0008) -[2023-10-12 05:24:52,899][78091] Updated weights for policy 0, policy_version 52920 (0.0008) -[2023-10-12 05:24:55,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 108134400. Throughput: 0: 1588.2, 1: 1583.0. Samples: 27045758. Policy #0 lag: (min: 7.0, avg: 10.4, max: 39.0) -[2023-10-12 05:24:55,201][77203] Avg episode reward: [(0, '56.610'), (1, '41.500')] -[2023-10-12 05:24:55,209][77792] Saving new best policy, reward=56.610! -[2023-10-12 05:24:56,166][78123] Updated weights for policy 1, policy_version 52680 (0.0008) -[2023-10-12 05:24:56,537][78123] Updated weights for policy 1, policy_version 52690 (0.0007) -[2023-10-12 05:24:56,904][78123] Updated weights for policy 1, policy_version 52700 (0.0009) -[2023-10-12 05:24:57,208][78091] Updated weights for policy 0, policy_version 52930 (0.0008) -[2023-10-12 05:24:57,572][78091] Updated weights for policy 0, policy_version 52940 (0.0010) -[2023-10-12 05:24:57,946][78091] Updated weights for policy 0, policy_version 52950 (0.0009) -[2023-10-12 05:24:58,324][78091] Updated weights for policy 0, policy_version 52960 (0.0010) -[2023-10-12 05:25:00,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 108199936. Throughput: 0: 1596.0, 1: 1580.3. Samples: 27054794. Policy #0 lag: (min: 7.0, avg: 10.4, max: 39.0) -[2023-10-12 05:25:00,203][77203] Avg episode reward: [(0, '46.970'), (1, '47.430')] -[2023-10-12 05:25:01,489][78123] Updated weights for policy 1, policy_version 52710 (0.0008) -[2023-10-12 05:25:01,856][78123] Updated weights for policy 1, policy_version 52720 (0.0008) -[2023-10-12 05:25:02,230][78123] Updated weights for policy 1, policy_version 52730 (0.0009) -[2023-10-12 05:25:02,623][78091] Updated weights for policy 0, policy_version 52970 (0.0008) -[2023-10-12 05:25:03,005][78091] Updated weights for policy 0, policy_version 52980 (0.0009) -[2023-10-12 05:25:03,370][78091] Updated weights for policy 0, policy_version 52990 (0.0007) -[2023-10-12 05:25:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 108265472. Throughput: 0: 1587.2, 1: 1570.7. Samples: 27073508. Policy #0 lag: (min: 7.0, avg: 10.4, max: 39.0) -[2023-10-12 05:25:05,201][77203] Avg episode reward: [(0, '51.430'), (1, '37.920')] -[2023-10-12 05:25:06,734][78123] Updated weights for policy 1, policy_version 52740 (0.0010) -[2023-10-12 05:25:07,093][78123] Updated weights for policy 1, policy_version 52750 (0.0008) -[2023-10-12 05:25:07,465][78123] Updated weights for policy 1, policy_version 52760 (0.0009) -[2023-10-12 05:25:07,682][78091] Updated weights for policy 0, policy_version 53000 (0.0008) -[2023-10-12 05:25:08,039][78091] Updated weights for policy 0, policy_version 53010 (0.0011) -[2023-10-12 05:25:08,421][78091] Updated weights for policy 0, policy_version 53020 (0.0010) -[2023-10-12 05:25:10,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 108331008. Throughput: 0: 1588.8, 1: 1567.9. Samples: 27092808. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-12 05:25:10,202][77203] Avg episode reward: [(0, '55.180'), (1, '40.220')] -[2023-10-12 05:25:10,211][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000052768_54034432.pth... -[2023-10-12 05:25:10,212][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000053024_54296576.pth... -[2023-10-12 05:25:10,246][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000051520_52756480.pth -[2023-10-12 05:25:10,247][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000051296_52527104.pth -[2023-10-12 05:25:11,780][78123] Updated weights for policy 1, policy_version 52770 (0.0008) -[2023-10-12 05:25:12,184][78123] Updated weights for policy 1, policy_version 52780 (0.0008) -[2023-10-12 05:25:12,560][78123] Updated weights for policy 1, policy_version 52790 (0.0009) -[2023-10-12 05:25:12,644][78091] Updated weights for policy 0, policy_version 53030 (0.0009) -[2023-10-12 05:25:12,922][78123] Updated weights for policy 1, policy_version 52800 (0.0009) -[2023-10-12 05:25:13,013][78091] Updated weights for policy 0, policy_version 53040 (0.0009) -[2023-10-12 05:25:13,378][78091] Updated weights for policy 0, policy_version 53050 (0.0008) -[2023-10-12 05:25:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 108396544. Throughput: 0: 1609.7, 1: 1573.6. Samples: 27102454. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-12 05:25:15,201][77203] Avg episode reward: [(0, '42.520'), (1, '44.250')] -[2023-10-12 05:25:17,112][78123] Updated weights for policy 1, policy_version 52810 (0.0007) -[2023-10-12 05:25:17,477][78123] Updated weights for policy 1, policy_version 52820 (0.0008) -[2023-10-12 05:25:17,707][78091] Updated weights for policy 0, policy_version 53060 (0.0008) -[2023-10-12 05:25:17,848][78123] Updated weights for policy 1, policy_version 52830 (0.0008) -[2023-10-12 05:25:18,086][78091] Updated weights for policy 0, policy_version 53070 (0.0007) -[2023-10-12 05:25:18,457][78091] Updated weights for policy 0, policy_version 53080 (0.0010) -[2023-10-12 05:25:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 108462080. Throughput: 0: 1590.7, 1: 1571.4. Samples: 27121048. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-12 05:25:20,201][77203] Avg episode reward: [(0, '37.180'), (1, '41.990')] -[2023-10-12 05:25:22,169][78123] Updated weights for policy 1, policy_version 52840 (0.0009) -[2023-10-12 05:25:22,540][78123] Updated weights for policy 1, policy_version 52850 (0.0011) -[2023-10-12 05:25:22,839][78091] Updated weights for policy 0, policy_version 53090 (0.0009) -[2023-10-12 05:25:22,898][78123] Updated weights for policy 1, policy_version 52860 (0.0010) -[2023-10-12 05:25:23,202][78091] Updated weights for policy 0, policy_version 53100 (0.0008) -[2023-10-12 05:25:23,576][78091] Updated weights for policy 0, policy_version 53110 (0.0007) -[2023-10-12 05:25:23,950][78091] Updated weights for policy 0, policy_version 53120 (0.0010) -[2023-10-12 05:25:25,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 108527616. Throughput: 0: 1585.3, 1: 1569.8. Samples: 27140290. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-12 05:25:25,202][77203] Avg episode reward: [(0, '43.890'), (1, '45.600')] -[2023-10-12 05:25:27,192][78123] Updated weights for policy 1, policy_version 52870 (0.0007) -[2023-10-12 05:25:27,561][78123] Updated weights for policy 1, policy_version 52880 (0.0008) -[2023-10-12 05:25:27,926][78123] Updated weights for policy 1, policy_version 52890 (0.0007) -[2023-10-12 05:25:28,263][78091] Updated weights for policy 0, policy_version 53130 (0.0008) -[2023-10-12 05:25:28,634][78091] Updated weights for policy 0, policy_version 53140 (0.0009) -[2023-10-12 05:25:29,005][78091] Updated weights for policy 0, policy_version 53150 (0.0007) -[2023-10-12 05:25:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 108593152. Throughput: 0: 1609.7, 1: 1582.0. Samples: 27150560. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-12 05:25:30,202][77203] Avg episode reward: [(0, '52.230'), (1, '48.830')] -[2023-10-12 05:25:32,335][78123] Updated weights for policy 1, policy_version 52900 (0.0009) -[2023-10-12 05:25:32,704][78123] Updated weights for policy 1, policy_version 52910 (0.0008) -[2023-10-12 05:25:33,072][78123] Updated weights for policy 1, policy_version 52920 (0.0008) -[2023-10-12 05:25:33,378][78091] Updated weights for policy 0, policy_version 53160 (0.0007) -[2023-10-12 05:25:33,761][78091] Updated weights for policy 0, policy_version 53170 (0.0008) -[2023-10-12 05:25:34,122][78091] Updated weights for policy 0, policy_version 53180 (0.0009) -[2023-10-12 05:25:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 108658688. Throughput: 0: 1595.2, 1: 1572.0. Samples: 27168856. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-12 05:25:35,202][77203] Avg episode reward: [(0, '49.740'), (1, '49.300')] -[2023-10-12 05:25:37,465][78123] Updated weights for policy 1, policy_version 52930 (0.0008) -[2023-10-12 05:25:37,838][78123] Updated weights for policy 1, policy_version 52940 (0.0007) -[2023-10-12 05:25:38,207][78123] Updated weights for policy 1, policy_version 52950 (0.0009) -[2023-10-12 05:25:38,560][78091] Updated weights for policy 0, policy_version 53190 (0.0008) -[2023-10-12 05:25:38,572][78123] Updated weights for policy 1, policy_version 52960 (0.0010) -[2023-10-12 05:25:38,933][78091] Updated weights for policy 0, policy_version 53200 (0.0008) -[2023-10-12 05:25:39,307][78091] Updated weights for policy 0, policy_version 53210 (0.0008) -[2023-10-12 05:25:40,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 108724224. Throughput: 0: 1580.2, 1: 1567.1. Samples: 27187388. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-12 05:25:40,202][77203] Avg episode reward: [(0, '46.920'), (1, '43.840')] -[2023-10-12 05:25:42,913][78123] Updated weights for policy 1, policy_version 52970 (0.0007) -[2023-10-12 05:25:43,274][78123] Updated weights for policy 1, policy_version 52980 (0.0007) -[2023-10-12 05:25:43,591][78091] Updated weights for policy 0, policy_version 53220 (0.0009) -[2023-10-12 05:25:43,636][78123] Updated weights for policy 1, policy_version 52990 (0.0008) -[2023-10-12 05:25:43,964][78091] Updated weights for policy 0, policy_version 53230 (0.0009) -[2023-10-12 05:25:44,321][78091] Updated weights for policy 0, policy_version 53240 (0.0008) -[2023-10-12 05:25:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 108789760. Throughput: 0: 1597.4, 1: 1589.0. Samples: 27198184. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 05:25:45,202][77203] Avg episode reward: [(0, '46.030'), (1, '43.840')] -[2023-10-12 05:25:48,052][78123] Updated weights for policy 1, policy_version 53000 (0.0009) -[2023-10-12 05:25:48,422][78123] Updated weights for policy 1, policy_version 53010 (0.0008) -[2023-10-12 05:25:48,586][78091] Updated weights for policy 0, policy_version 53250 (0.0010) -[2023-10-12 05:25:48,796][78123] Updated weights for policy 1, policy_version 53020 (0.0009) -[2023-10-12 05:25:48,956][78091] Updated weights for policy 0, policy_version 53260 (0.0008) -[2023-10-12 05:25:49,334][78091] Updated weights for policy 0, policy_version 53270 (0.0011) -[2023-10-12 05:25:49,694][78091] Updated weights for policy 0, policy_version 53280 (0.0009) -[2023-10-12 05:25:50,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 108855296. Throughput: 0: 1604.8, 1: 1580.6. Samples: 27216852. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 05:25:50,201][77203] Avg episode reward: [(0, '46.140'), (1, '48.460')] -[2023-10-12 05:25:53,120][78123] Updated weights for policy 1, policy_version 53030 (0.0008) -[2023-10-12 05:25:53,485][78123] Updated weights for policy 1, policy_version 53040 (0.0007) -[2023-10-12 05:25:53,852][78123] Updated weights for policy 1, policy_version 53050 (0.0009) -[2023-10-12 05:25:53,898][78091] Updated weights for policy 0, policy_version 53290 (0.0010) -[2023-10-12 05:25:54,275][78091] Updated weights for policy 0, policy_version 53300 (0.0008) -[2023-10-12 05:25:54,637][78091] Updated weights for policy 0, policy_version 53310 (0.0011) -[2023-10-12 05:25:55,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 108920832. Throughput: 0: 1590.5, 1: 1578.0. Samples: 27235390. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 05:25:55,202][77203] Avg episode reward: [(0, '52.250'), (1, '53.190')] -[2023-10-12 05:25:58,283][78123] Updated weights for policy 1, policy_version 53060 (0.0008) -[2023-10-12 05:25:58,654][78123] Updated weights for policy 1, policy_version 53070 (0.0010) -[2023-10-12 05:25:58,906][78091] Updated weights for policy 0, policy_version 53320 (0.0008) -[2023-10-12 05:25:59,021][78123] Updated weights for policy 1, policy_version 53080 (0.0009) -[2023-10-12 05:25:59,265][78091] Updated weights for policy 0, policy_version 53330 (0.0008) -[2023-10-12 05:25:59,644][78091] Updated weights for policy 0, policy_version 53340 (0.0010) -[2023-10-12 05:26:00,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 12774.0). Total num frames: 108986368. Throughput: 0: 1599.2, 1: 1599.5. Samples: 27246396. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 05:26:00,201][77203] Avg episode reward: [(0, '49.610'), (1, '51.900')] -[2023-10-12 05:26:03,481][78123] Updated weights for policy 1, policy_version 53090 (0.0009) -[2023-10-12 05:26:03,852][78123] Updated weights for policy 1, policy_version 53100 (0.0008) -[2023-10-12 05:26:03,992][78091] Updated weights for policy 0, policy_version 53350 (0.0008) -[2023-10-12 05:26:04,208][78123] Updated weights for policy 1, policy_version 53110 (0.0008) -[2023-10-12 05:26:04,358][78091] Updated weights for policy 0, policy_version 53360 (0.0008) -[2023-10-12 05:26:04,576][78123] Updated weights for policy 1, policy_version 53120 (0.0007) -[2023-10-12 05:26:04,721][78091] Updated weights for policy 0, policy_version 53370 (0.0009) -[2023-10-12 05:26:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 109051904. Throughput: 0: 1620.4, 1: 1592.2. Samples: 27265614. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 05:26:05,201][77203] Avg episode reward: [(0, '43.320'), (1, '44.970')] -[2023-10-12 05:26:08,923][78123] Updated weights for policy 1, policy_version 53130 (0.0009) -[2023-10-12 05:26:09,092][78091] Updated weights for policy 0, policy_version 53380 (0.0009) -[2023-10-12 05:26:09,300][78123] Updated weights for policy 1, policy_version 53140 (0.0008) -[2023-10-12 05:26:09,459][78091] Updated weights for policy 0, policy_version 53390 (0.0009) -[2023-10-12 05:26:09,661][78123] Updated weights for policy 1, policy_version 53150 (0.0007) -[2023-10-12 05:26:09,827][78091] Updated weights for policy 0, policy_version 53400 (0.0009) -[2023-10-12 05:26:10,201][77203] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 109117440. Throughput: 0: 1605.4, 1: 1573.2. Samples: 27283328. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 05:26:10,202][77203] Avg episode reward: [(0, '51.010'), (1, '43.890')] -[2023-10-12 05:26:14,103][78123] Updated weights for policy 1, policy_version 53160 (0.0008) -[2023-10-12 05:26:14,249][78091] Updated weights for policy 0, policy_version 53410 (0.0008) -[2023-10-12 05:26:14,464][78123] Updated weights for policy 1, policy_version 53170 (0.0008) -[2023-10-12 05:26:14,628][78091] Updated weights for policy 0, policy_version 53420 (0.0008) -[2023-10-12 05:26:14,833][78123] Updated weights for policy 1, policy_version 53180 (0.0007) -[2023-10-12 05:26:14,992][78091] Updated weights for policy 0, policy_version 53430 (0.0008) -[2023-10-12 05:26:15,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 109150208. Throughput: 0: 1598.0, 1: 1583.5. Samples: 27293728. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 05:26:15,201][77203] Avg episode reward: [(0, '55.660'), (1, '50.740')] -[2023-10-12 05:26:15,368][78091] Updated weights for policy 0, policy_version 53440 (0.0008) -[2023-10-12 05:26:18,983][78123] Updated weights for policy 1, policy_version 53190 (0.0009) -[2023-10-12 05:26:19,345][78123] Updated weights for policy 1, policy_version 53200 (0.0009) -[2023-10-12 05:26:19,696][78091] Updated weights for policy 0, policy_version 53450 (0.0008) -[2023-10-12 05:26:19,709][78123] Updated weights for policy 1, policy_version 53210 (0.0007) -[2023-10-12 05:26:20,071][78091] Updated weights for policy 0, policy_version 53460 (0.0008) -[2023-10-12 05:26:20,201][77203] Fps is (10 sec: 9830.7, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 109215744. Throughput: 0: 1609.5, 1: 1598.2. Samples: 27313200. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 05:26:20,201][77203] Avg episode reward: [(0, '47.140'), (1, '47.800')] -[2023-10-12 05:26:20,442][78091] Updated weights for policy 0, policy_version 53470 (0.0010) -[2023-10-12 05:26:23,942][78123] Updated weights for policy 1, policy_version 53220 (0.0008) -[2023-10-12 05:26:24,311][78123] Updated weights for policy 1, policy_version 53230 (0.0010) -[2023-10-12 05:26:24,669][78123] Updated weights for policy 1, policy_version 53240 (0.0009) -[2023-10-12 05:26:24,862][78091] Updated weights for policy 0, policy_version 53480 (0.0008) -[2023-10-12 05:26:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 109281280. Throughput: 0: 1618.5, 1: 1588.5. Samples: 27331698. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 05:26:25,201][77203] Avg episode reward: [(0, '39.830'), (1, '43.660')] -[2023-10-12 05:26:25,233][78091] Updated weights for policy 0, policy_version 53490 (0.0007) -[2023-10-12 05:26:25,615][78091] Updated weights for policy 0, policy_version 53500 (0.0007) -[2023-10-12 05:26:29,058][78123] Updated weights for policy 1, policy_version 53250 (0.0010) -[2023-10-12 05:26:29,420][78123] Updated weights for policy 1, policy_version 53260 (0.0008) -[2023-10-12 05:26:29,790][78123] Updated weights for policy 1, policy_version 53270 (0.0007) -[2023-10-12 05:26:29,948][78091] Updated weights for policy 0, policy_version 53510 (0.0009) -[2023-10-12 05:26:30,154][78123] Updated weights for policy 1, policy_version 53280 (0.0010) -[2023-10-12 05:26:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 109346816. Throughput: 0: 1596.4, 1: 1586.1. Samples: 27341394. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 05:26:30,201][77203] Avg episode reward: [(0, '46.690'), (1, '39.000')] -[2023-10-12 05:26:30,317][78091] Updated weights for policy 0, policy_version 53520 (0.0007) -[2023-10-12 05:26:30,687][78091] Updated weights for policy 0, policy_version 53530 (0.0009) -[2023-10-12 05:26:34,471][78123] Updated weights for policy 1, policy_version 53290 (0.0008) -[2023-10-12 05:26:34,830][78123] Updated weights for policy 1, policy_version 53300 (0.0008) -[2023-10-12 05:26:35,017][78091] Updated weights for policy 0, policy_version 53540 (0.0008) -[2023-10-12 05:26:35,194][78123] Updated weights for policy 1, policy_version 53310 (0.0008) -[2023-10-12 05:26:35,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 109379584. Throughput: 0: 1597.6, 1: 1600.4. Samples: 27360762. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 05:26:35,201][77203] Avg episode reward: [(0, '51.140'), (1, '45.010')] -[2023-10-12 05:26:35,389][78091] Updated weights for policy 0, policy_version 53550 (0.0008) -[2023-10-12 05:26:35,760][78091] Updated weights for policy 0, policy_version 53560 (0.0008) -[2023-10-12 05:26:39,624][78123] Updated weights for policy 1, policy_version 53320 (0.0010) -[2023-10-12 05:26:40,001][78091] Updated weights for policy 0, policy_version 53570 (0.0008) -[2023-10-12 05:26:40,002][78123] Updated weights for policy 1, policy_version 53330 (0.0009) -[2023-10-12 05:26:40,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 109445120. Throughput: 0: 1607.8, 1: 1598.0. Samples: 27379650. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 05:26:40,201][77203] Avg episode reward: [(0, '52.150'), (1, '48.100')] -[2023-10-12 05:26:40,361][78123] Updated weights for policy 1, policy_version 53340 (0.0009) -[2023-10-12 05:26:40,374][78091] Updated weights for policy 0, policy_version 53580 (0.0008) -[2023-10-12 05:26:40,747][78091] Updated weights for policy 0, policy_version 53590 (0.0008) -[2023-10-12 05:26:41,108][78091] Updated weights for policy 0, policy_version 53600 (0.0008) -[2023-10-12 05:26:44,851][78123] Updated weights for policy 1, policy_version 53350 (0.0010) -[2023-10-12 05:26:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 109510656. Throughput: 0: 1577.2, 1: 1583.0. Samples: 27388604. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 05:26:45,201][77203] Avg episode reward: [(0, '41.580'), (1, '46.210')] -[2023-10-12 05:26:45,229][78123] Updated weights for policy 1, policy_version 53360 (0.0009) -[2023-10-12 05:26:45,417][78091] Updated weights for policy 0, policy_version 53610 (0.0009) -[2023-10-12 05:26:45,605][78123] Updated weights for policy 1, policy_version 53370 (0.0007) -[2023-10-12 05:26:45,795][78091] Updated weights for policy 0, policy_version 53620 (0.0009) -[2023-10-12 05:26:46,162][78091] Updated weights for policy 0, policy_version 53630 (0.0009) -[2023-10-12 05:26:49,925][78123] Updated weights for policy 1, policy_version 53380 (0.0008) -[2023-10-12 05:26:50,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 109576192. Throughput: 0: 1574.0, 1: 1589.1. Samples: 27407954. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 05:26:50,202][77203] Avg episode reward: [(0, '46.590'), (1, '46.160')] -[2023-10-12 05:26:50,288][78123] Updated weights for policy 1, policy_version 53390 (0.0010) -[2023-10-12 05:26:50,652][78123] Updated weights for policy 1, policy_version 53400 (0.0009) -[2023-10-12 05:26:50,726][78091] Updated weights for policy 0, policy_version 53640 (0.0008) -[2023-10-12 05:26:51,112][78091] Updated weights for policy 0, policy_version 53650 (0.0007) -[2023-10-12 05:26:51,482][78091] Updated weights for policy 0, policy_version 53660 (0.0008) -[2023-10-12 05:26:55,139][78123] Updated weights for policy 1, policy_version 53410 (0.0009) -[2023-10-12 05:26:55,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 109641728. Throughput: 0: 1590.5, 1: 1605.8. Samples: 27427160. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 05:26:55,201][77203] Avg episode reward: [(0, '51.410'), (1, '39.810')] -[2023-10-12 05:26:55,499][78123] Updated weights for policy 1, policy_version 53420 (0.0010) -[2023-10-12 05:26:55,633][78091] Updated weights for policy 0, policy_version 53670 (0.0007) -[2023-10-12 05:26:55,863][78123] Updated weights for policy 1, policy_version 53430 (0.0009) -[2023-10-12 05:26:56,002][78091] Updated weights for policy 0, policy_version 53680 (0.0009) -[2023-10-12 05:26:56,228][78123] Updated weights for policy 1, policy_version 53440 (0.0009) -[2023-10-12 05:26:56,374][78091] Updated weights for policy 0, policy_version 53690 (0.0009) -[2023-10-12 05:27:00,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 109707264. Throughput: 0: 1572.7, 1: 1582.8. Samples: 27435722. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-12 05:27:00,202][77203] Avg episode reward: [(0, '53.690'), (1, '42.890')] -[2023-10-12 05:27:00,574][78123] Updated weights for policy 1, policy_version 53450 (0.0009) -[2023-10-12 05:27:00,795][78091] Updated weights for policy 0, policy_version 53700 (0.0007) -[2023-10-12 05:27:00,949][78123] Updated weights for policy 1, policy_version 53460 (0.0008) -[2023-10-12 05:27:01,159][78091] Updated weights for policy 0, policy_version 53710 (0.0007) -[2023-10-12 05:27:01,322][78123] Updated weights for policy 1, policy_version 53470 (0.0010) -[2023-10-12 05:27:01,533][78091] Updated weights for policy 0, policy_version 53720 (0.0008) -[2023-10-12 05:27:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 109772800. Throughput: 0: 1572.8, 1: 1582.0. Samples: 27455166. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-12 05:27:05,201][77203] Avg episode reward: [(0, '46.570'), (1, '42.290')] -[2023-10-12 05:27:05,574][78123] Updated weights for policy 1, policy_version 53480 (0.0009) -[2023-10-12 05:27:05,910][78091] Updated weights for policy 0, policy_version 53730 (0.0008) -[2023-10-12 05:27:05,936][78123] Updated weights for policy 1, policy_version 53490 (0.0008) -[2023-10-12 05:27:06,284][78091] Updated weights for policy 0, policy_version 53740 (0.0009) -[2023-10-12 05:27:06,305][78123] Updated weights for policy 1, policy_version 53500 (0.0009) -[2023-10-12 05:27:06,657][78091] Updated weights for policy 0, policy_version 53750 (0.0008) -[2023-10-12 05:27:07,028][78091] Updated weights for policy 0, policy_version 53760 (0.0009) -[2023-10-12 05:27:10,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 109838336. Throughput: 0: 1576.8, 1: 1593.1. Samples: 27474346. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-12 05:27:10,202][77203] Avg episode reward: [(0, '43.900'), (1, '41.960')] -[2023-10-12 05:27:10,211][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000053760_55050240.pth... -[2023-10-12 05:27:10,211][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000053504_54788096.pth... -[2023-10-12 05:27:10,251][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000052288_53542912.pth -[2023-10-12 05:27:10,251][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000052032_53280768.pth -[2023-10-12 05:27:10,616][78123] Updated weights for policy 1, policy_version 53510 (0.0008) -[2023-10-12 05:27:10,979][78123] Updated weights for policy 1, policy_version 53520 (0.0007) -[2023-10-12 05:27:11,347][78123] Updated weights for policy 1, policy_version 53530 (0.0009) -[2023-10-12 05:27:11,384][78091] Updated weights for policy 0, policy_version 53770 (0.0008) -[2023-10-12 05:27:11,761][78091] Updated weights for policy 0, policy_version 53780 (0.0008) -[2023-10-12 05:27:12,124][78091] Updated weights for policy 0, policy_version 53790 (0.0008) -[2023-10-12 05:27:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 109903872. Throughput: 0: 1570.8, 1: 1575.5. Samples: 27482978. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-12 05:27:15,202][77203] Avg episode reward: [(0, '53.280'), (1, '43.540')] -[2023-10-12 05:27:15,717][78123] Updated weights for policy 1, policy_version 53540 (0.0008) -[2023-10-12 05:27:16,084][78123] Updated weights for policy 1, policy_version 53550 (0.0010) -[2023-10-12 05:27:16,258][78091] Updated weights for policy 0, policy_version 53800 (0.0008) -[2023-10-12 05:27:16,443][78123] Updated weights for policy 1, policy_version 53560 (0.0009) -[2023-10-12 05:27:16,637][78091] Updated weights for policy 0, policy_version 53810 (0.0009) -[2023-10-12 05:27:17,007][78091] Updated weights for policy 0, policy_version 53820 (0.0008) -[2023-10-12 05:27:20,201][77203] Fps is (10 sec: 13107.6, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 109969408. Throughput: 0: 1575.8, 1: 1572.8. Samples: 27502448. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-12 05:27:20,201][77203] Avg episode reward: [(0, '48.340'), (1, '45.300')] -[2023-10-12 05:27:20,990][78123] Updated weights for policy 1, policy_version 53570 (0.0009) -[2023-10-12 05:27:21,354][78123] Updated weights for policy 1, policy_version 53580 (0.0007) -[2023-10-12 05:27:21,381][78091] Updated weights for policy 0, policy_version 53830 (0.0008) -[2023-10-12 05:27:21,713][78123] Updated weights for policy 1, policy_version 53590 (0.0008) -[2023-10-12 05:27:21,752][78091] Updated weights for policy 0, policy_version 53840 (0.0009) -[2023-10-12 05:27:22,085][78123] Updated weights for policy 1, policy_version 53600 (0.0009) -[2023-10-12 05:27:22,122][78091] Updated weights for policy 0, policy_version 53850 (0.0007) -[2023-10-12 05:27:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 110034944. Throughput: 0: 1579.4, 1: 1576.0. Samples: 27521640. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-12 05:27:25,202][77203] Avg episode reward: [(0, '53.200'), (1, '51.810')] -[2023-10-12 05:27:26,363][78091] Updated weights for policy 0, policy_version 53860 (0.0008) -[2023-10-12 05:27:26,643][78123] Updated weights for policy 1, policy_version 53610 (0.0009) -[2023-10-12 05:27:26,723][78091] Updated weights for policy 0, policy_version 53870 (0.0008) -[2023-10-12 05:27:27,000][78123] Updated weights for policy 1, policy_version 53620 (0.0009) -[2023-10-12 05:27:27,092][78091] Updated weights for policy 0, policy_version 53880 (0.0007) -[2023-10-12 05:27:27,358][78123] Updated weights for policy 1, policy_version 53630 (0.0010) -[2023-10-12 05:27:30,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 110100480. Throughput: 0: 1582.4, 1: 1564.5. Samples: 27530214. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-12 05:27:30,201][77203] Avg episode reward: [(0, '44.210'), (1, '45.950')] -[2023-10-12 05:27:31,355][78091] Updated weights for policy 0, policy_version 53890 (0.0008) -[2023-10-12 05:27:31,706][78123] Updated weights for policy 1, policy_version 53640 (0.0008) -[2023-10-12 05:27:31,728][78091] Updated weights for policy 0, policy_version 53900 (0.0008) -[2023-10-12 05:27:32,082][78123] Updated weights for policy 1, policy_version 53650 (0.0008) -[2023-10-12 05:27:32,089][78091] Updated weights for policy 0, policy_version 53910 (0.0009) -[2023-10-12 05:27:32,440][78123] Updated weights for policy 1, policy_version 53660 (0.0009) -[2023-10-12 05:27:32,456][78091] Updated weights for policy 0, policy_version 53920 (0.0008) -[2023-10-12 05:27:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 110166016. Throughput: 0: 1585.0, 1: 1565.0. Samples: 27549704. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-12 05:27:35,202][77203] Avg episode reward: [(0, '48.940'), (1, '50.540')] -[2023-10-12 05:27:36,717][78123] Updated weights for policy 1, policy_version 53670 (0.0008) -[2023-10-12 05:27:36,943][78091] Updated weights for policy 0, policy_version 53930 (0.0008) -[2023-10-12 05:27:37,080][78123] Updated weights for policy 1, policy_version 53680 (0.0008) -[2023-10-12 05:27:37,304][78091] Updated weights for policy 0, policy_version 53940 (0.0009) -[2023-10-12 05:27:37,442][78123] Updated weights for policy 1, policy_version 53690 (0.0007) -[2023-10-12 05:27:37,683][78091] Updated weights for policy 0, policy_version 53950 (0.0009) -[2023-10-12 05:27:40,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 110231552. Throughput: 0: 1584.3, 1: 1566.1. Samples: 27568930. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-12 05:27:40,202][77203] Avg episode reward: [(0, '49.070'), (1, '52.460')] -[2023-10-12 05:27:41,828][78123] Updated weights for policy 1, policy_version 53700 (0.0007) -[2023-10-12 05:27:42,028][78091] Updated weights for policy 0, policy_version 53960 (0.0009) -[2023-10-12 05:27:42,207][78123] Updated weights for policy 1, policy_version 53710 (0.0007) -[2023-10-12 05:27:42,399][78091] Updated weights for policy 0, policy_version 53970 (0.0009) -[2023-10-12 05:27:42,570][78123] Updated weights for policy 1, policy_version 53720 (0.0010) -[2023-10-12 05:27:42,764][78091] Updated weights for policy 0, policy_version 53980 (0.0009) -[2023-10-12 05:27:45,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 110297088. Throughput: 0: 1587.0, 1: 1572.4. Samples: 27577898. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-12 05:27:45,201][77203] Avg episode reward: [(0, '56.710'), (1, '41.790')] -[2023-10-12 05:27:45,202][77792] Saving new best policy, reward=56.710! -[2023-10-12 05:27:46,891][78123] Updated weights for policy 1, policy_version 53730 (0.0008) -[2023-10-12 05:27:47,097][78091] Updated weights for policy 0, policy_version 53990 (0.0008) -[2023-10-12 05:27:47,261][78123] Updated weights for policy 1, policy_version 53740 (0.0008) -[2023-10-12 05:27:47,459][78091] Updated weights for policy 0, policy_version 54000 (0.0009) -[2023-10-12 05:27:47,617][78123] Updated weights for policy 1, policy_version 53750 (0.0008) -[2023-10-12 05:27:47,838][78091] Updated weights for policy 0, policy_version 54010 (0.0009) -[2023-10-12 05:27:47,986][78123] Updated weights for policy 1, policy_version 53760 (0.0010) -[2023-10-12 05:27:50,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 110362624. Throughput: 0: 1583.6, 1: 1568.4. Samples: 27597008. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-12 05:27:50,201][77203] Avg episode reward: [(0, '52.450'), (1, '49.020')] -[2023-10-12 05:27:52,276][78091] Updated weights for policy 0, policy_version 54020 (0.0009) -[2023-10-12 05:27:52,427][78123] Updated weights for policy 1, policy_version 53770 (0.0009) -[2023-10-12 05:27:52,637][78091] Updated weights for policy 0, policy_version 54030 (0.0009) -[2023-10-12 05:27:52,801][78123] Updated weights for policy 1, policy_version 53780 (0.0007) -[2023-10-12 05:27:53,014][78091] Updated weights for policy 0, policy_version 54040 (0.0009) -[2023-10-12 05:27:53,163][78123] Updated weights for policy 1, policy_version 53790 (0.0008) -[2023-10-12 05:27:55,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 110428160. Throughput: 0: 1584.7, 1: 1568.8. Samples: 27616252. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-12 05:27:55,202][77203] Avg episode reward: [(0, '49.420'), (1, '44.870')] -[2023-10-12 05:27:57,263][78091] Updated weights for policy 0, policy_version 54050 (0.0007) -[2023-10-12 05:27:57,534][78123] Updated weights for policy 1, policy_version 53800 (0.0008) -[2023-10-12 05:27:57,674][78091] Updated weights for policy 0, policy_version 54060 (0.0008) -[2023-10-12 05:27:57,898][78123] Updated weights for policy 1, policy_version 53810 (0.0008) -[2023-10-12 05:27:58,042][78091] Updated weights for policy 0, policy_version 54070 (0.0008) -[2023-10-12 05:27:58,261][78123] Updated weights for policy 1, policy_version 53820 (0.0007) -[2023-10-12 05:27:58,408][78091] Updated weights for policy 0, policy_version 54080 (0.0007) -[2023-10-12 05:28:00,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 110493696. Throughput: 0: 1596.7, 1: 1583.0. Samples: 27626064. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-12 05:28:00,201][77203] Avg episode reward: [(0, '54.470'), (1, '39.420')] -[2023-10-12 05:28:02,640][78123] Updated weights for policy 1, policy_version 53830 (0.0008) -[2023-10-12 05:28:02,677][78091] Updated weights for policy 0, policy_version 54090 (0.0009) -[2023-10-12 05:28:03,012][78123] Updated weights for policy 1, policy_version 53840 (0.0007) -[2023-10-12 05:28:03,046][78091] Updated weights for policy 0, policy_version 54100 (0.0007) -[2023-10-12 05:28:03,379][78123] Updated weights for policy 1, policy_version 53850 (0.0009) -[2023-10-12 05:28:03,414][78091] Updated weights for policy 0, policy_version 54110 (0.0007) -[2023-10-12 05:28:05,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 110559232. Throughput: 0: 1586.4, 1: 1568.5. Samples: 27644416. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-12 05:28:05,201][77203] Avg episode reward: [(0, '57.060'), (1, '31.980')] -[2023-10-12 05:28:05,202][77792] Saving new best policy, reward=57.060! -[2023-10-12 05:28:07,483][78123] Updated weights for policy 1, policy_version 53860 (0.0010) -[2023-10-12 05:28:07,806][78091] Updated weights for policy 0, policy_version 54120 (0.0008) -[2023-10-12 05:28:07,853][78123] Updated weights for policy 1, policy_version 53870 (0.0007) -[2023-10-12 05:28:08,167][78091] Updated weights for policy 0, policy_version 54130 (0.0008) -[2023-10-12 05:28:08,221][78123] Updated weights for policy 1, policy_version 53880 (0.0007) -[2023-10-12 05:28:08,540][78091] Updated weights for policy 0, policy_version 54140 (0.0008) -[2023-10-12 05:28:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 110624768. Throughput: 0: 1583.4, 1: 1578.4. Samples: 27663922. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-12 05:28:10,202][77203] Avg episode reward: [(0, '51.450'), (1, '36.580')] -[2023-10-12 05:28:12,589][78123] Updated weights for policy 1, policy_version 53890 (0.0007) -[2023-10-12 05:28:12,955][78123] Updated weights for policy 1, policy_version 53900 (0.0007) -[2023-10-12 05:28:13,027][78091] Updated weights for policy 0, policy_version 54150 (0.0009) -[2023-10-12 05:28:13,315][78123] Updated weights for policy 1, policy_version 53910 (0.0008) -[2023-10-12 05:28:13,391][78091] Updated weights for policy 0, policy_version 54160 (0.0008) -[2023-10-12 05:28:13,681][78123] Updated weights for policy 1, policy_version 53920 (0.0007) -[2023-10-12 05:28:13,762][78091] Updated weights for policy 0, policy_version 54170 (0.0008) -[2023-10-12 05:28:15,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 110690304. Throughput: 0: 1606.0, 1: 1600.5. Samples: 27674506. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-12 05:28:15,201][77203] Avg episode reward: [(0, '42.980'), (1, '42.680')] -[2023-10-12 05:28:17,946][78091] Updated weights for policy 0, policy_version 54180 (0.0011) -[2023-10-12 05:28:18,264][78123] Updated weights for policy 1, policy_version 53930 (0.0007) -[2023-10-12 05:28:18,320][78091] Updated weights for policy 0, policy_version 54190 (0.0009) -[2023-10-12 05:28:18,640][78123] Updated weights for policy 1, policy_version 53940 (0.0007) -[2023-10-12 05:28:18,696][78091] Updated weights for policy 0, policy_version 54200 (0.0008) -[2023-10-12 05:28:19,002][78123] Updated weights for policy 1, policy_version 53950 (0.0009) -[2023-10-12 05:28:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 110755840. Throughput: 0: 1589.7, 1: 1586.2. Samples: 27692622. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-12 05:28:20,201][77203] Avg episode reward: [(0, '43.070'), (1, '33.250')] -[2023-10-12 05:28:23,021][78091] Updated weights for policy 0, policy_version 54210 (0.0009) -[2023-10-12 05:28:23,295][78123] Updated weights for policy 1, policy_version 53960 (0.0009) -[2023-10-12 05:28:23,377][78091] Updated weights for policy 0, policy_version 54220 (0.0007) -[2023-10-12 05:28:23,673][78123] Updated weights for policy 1, policy_version 53970 (0.0010) -[2023-10-12 05:28:23,755][78091] Updated weights for policy 0, policy_version 54230 (0.0008) -[2023-10-12 05:28:24,038][78123] Updated weights for policy 1, policy_version 53980 (0.0009) -[2023-10-12 05:28:24,128][78091] Updated weights for policy 0, policy_version 54240 (0.0010) -[2023-10-12 05:28:25,201][77203] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 110821376. Throughput: 0: 1587.3, 1: 1582.0. Samples: 27711552. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-12 05:28:25,202][77203] Avg episode reward: [(0, '47.850'), (1, '36.470')] -[2023-10-12 05:28:28,338][78091] Updated weights for policy 0, policy_version 54250 (0.0009) -[2023-10-12 05:28:28,411][78123] Updated weights for policy 1, policy_version 53990 (0.0009) -[2023-10-12 05:28:28,715][78091] Updated weights for policy 0, policy_version 54260 (0.0008) -[2023-10-12 05:28:28,771][78123] Updated weights for policy 1, policy_version 54000 (0.0009) -[2023-10-12 05:28:29,080][78091] Updated weights for policy 0, policy_version 54270 (0.0008) -[2023-10-12 05:28:29,136][78123] Updated weights for policy 1, policy_version 54010 (0.0010) -[2023-10-12 05:28:30,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 110886912. Throughput: 0: 1611.6, 1: 1601.0. Samples: 27722464. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-12 05:28:30,201][77203] Avg episode reward: [(0, '50.000'), (1, '48.560')] -[2023-10-12 05:28:33,417][78123] Updated weights for policy 1, policy_version 54020 (0.0007) -[2023-10-12 05:28:33,504][78091] Updated weights for policy 0, policy_version 54280 (0.0009) -[2023-10-12 05:28:33,787][78123] Updated weights for policy 1, policy_version 54030 (0.0007) -[2023-10-12 05:28:33,877][78091] Updated weights for policy 0, policy_version 54290 (0.0007) -[2023-10-12 05:28:34,150][78123] Updated weights for policy 1, policy_version 54040 (0.0008) -[2023-10-12 05:28:34,236][78091] Updated weights for policy 0, policy_version 54300 (0.0009) -[2023-10-12 05:28:35,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 110952448. Throughput: 0: 1603.5, 1: 1598.6. Samples: 27741102. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-12 05:28:35,201][77203] Avg episode reward: [(0, '49.340'), (1, '44.540')] -[2023-10-12 05:28:38,477][78123] Updated weights for policy 1, policy_version 54050 (0.0007) -[2023-10-12 05:28:38,486][78091] Updated weights for policy 0, policy_version 54310 (0.0007) -[2023-10-12 05:28:38,846][78123] Updated weights for policy 1, policy_version 54060 (0.0008) -[2023-10-12 05:28:38,856][78091] Updated weights for policy 0, policy_version 54320 (0.0008) -[2023-10-12 05:28:39,216][78091] Updated weights for policy 0, policy_version 54330 (0.0010) -[2023-10-12 05:28:39,219][78123] Updated weights for policy 1, policy_version 54070 (0.0010) -[2023-10-12 05:28:39,583][78123] Updated weights for policy 1, policy_version 54080 (0.0008) -[2023-10-12 05:28:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 111017984. Throughput: 0: 1592.1, 1: 1589.6. Samples: 27759428. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-12 05:28:40,202][77203] Avg episode reward: [(0, '49.660'), (1, '43.230')] -[2023-10-12 05:28:43,554][78091] Updated weights for policy 0, policy_version 54340 (0.0009) -[2023-10-12 05:28:43,704][78123] Updated weights for policy 1, policy_version 54090 (0.0007) -[2023-10-12 05:28:43,933][78091] Updated weights for policy 0, policy_version 54350 (0.0009) -[2023-10-12 05:28:44,068][78123] Updated weights for policy 1, policy_version 54100 (0.0008) -[2023-10-12 05:28:44,303][78091] Updated weights for policy 0, policy_version 54360 (0.0010) -[2023-10-12 05:28:44,436][78123] Updated weights for policy 1, policy_version 54110 (0.0009) -[2023-10-12 05:28:45,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 111083520. Throughput: 0: 1608.2, 1: 1604.4. Samples: 27770632. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:28:45,202][77203] Avg episode reward: [(0, '46.010'), (1, '46.090')] -[2023-10-12 05:28:48,460][78091] Updated weights for policy 0, policy_version 54370 (0.0010) -[2023-10-12 05:28:48,825][78091] Updated weights for policy 0, policy_version 54380 (0.0009) -[2023-10-12 05:28:48,868][78123] Updated weights for policy 1, policy_version 54120 (0.0010) -[2023-10-12 05:28:49,198][78091] Updated weights for policy 0, policy_version 54390 (0.0010) -[2023-10-12 05:28:49,230][78123] Updated weights for policy 1, policy_version 54130 (0.0010) -[2023-10-12 05:28:49,558][78091] Updated weights for policy 0, policy_version 54400 (0.0010) -[2023-10-12 05:28:49,595][78123] Updated weights for policy 1, policy_version 54140 (0.0009) -[2023-10-12 05:28:50,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 111149056. Throughput: 0: 1613.7, 1: 1613.8. Samples: 27789652. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:28:50,202][77203] Avg episode reward: [(0, '48.440'), (1, '50.770')] -[2023-10-12 05:28:53,946][78091] Updated weights for policy 0, policy_version 54410 (0.0008) -[2023-10-12 05:28:54,047][78123] Updated weights for policy 1, policy_version 54150 (0.0009) -[2023-10-12 05:28:54,306][78091] Updated weights for policy 0, policy_version 54420 (0.0010) -[2023-10-12 05:28:54,410][78123] Updated weights for policy 1, policy_version 54160 (0.0010) -[2023-10-12 05:28:54,677][78091] Updated weights for policy 0, policy_version 54430 (0.0008) -[2023-10-12 05:28:54,773][78123] Updated weights for policy 1, policy_version 54170 (0.0007) -[2023-10-12 05:28:55,201][77203] Fps is (10 sec: 13106.7, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 111214592. Throughput: 0: 1599.9, 1: 1590.9. Samples: 27807512. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:28:55,203][77203] Avg episode reward: [(0, '49.160'), (1, '48.030')] -[2023-10-12 05:28:59,024][78091] Updated weights for policy 0, policy_version 54440 (0.0009) -[2023-10-12 05:28:59,138][78123] Updated weights for policy 1, policy_version 54180 (0.0009) -[2023-10-12 05:28:59,400][78091] Updated weights for policy 0, policy_version 54450 (0.0008) -[2023-10-12 05:28:59,494][78123] Updated weights for policy 1, policy_version 54190 (0.0008) -[2023-10-12 05:28:59,778][78091] Updated weights for policy 0, policy_version 54460 (0.0009) -[2023-10-12 05:28:59,863][78123] Updated weights for policy 1, policy_version 54200 (0.0009) -[2023-10-12 05:29:00,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 111280128. Throughput: 0: 1600.4, 1: 1589.5. Samples: 27818052. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:29:00,201][77203] Avg episode reward: [(0, '49.240'), (1, '45.810')] -[2023-10-12 05:29:04,040][78091] Updated weights for policy 0, policy_version 54470 (0.0009) -[2023-10-12 05:29:04,334][78123] Updated weights for policy 1, policy_version 54210 (0.0009) -[2023-10-12 05:29:04,412][78091] Updated weights for policy 0, policy_version 54480 (0.0008) -[2023-10-12 05:29:04,734][78123] Updated weights for policy 1, policy_version 54220 (0.0007) -[2023-10-12 05:29:04,779][78091] Updated weights for policy 0, policy_version 54490 (0.0008) -[2023-10-12 05:29:05,104][78123] Updated weights for policy 1, policy_version 54230 (0.0007) -[2023-10-12 05:29:05,201][77203] Fps is (10 sec: 9830.8, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 111312896. Throughput: 0: 1621.8, 1: 1604.3. Samples: 27837796. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:29:05,201][77203] Avg episode reward: [(0, '46.740'), (1, '50.250')] -[2023-10-12 05:29:05,470][78123] Updated weights for policy 1, policy_version 54240 (0.0008) -[2023-10-12 05:29:09,099][78091] Updated weights for policy 0, policy_version 54500 (0.0009) -[2023-10-12 05:29:09,465][78091] Updated weights for policy 0, policy_version 54510 (0.0009) -[2023-10-12 05:29:09,736][78123] Updated weights for policy 1, policy_version 54250 (0.0008) -[2023-10-12 05:29:09,827][78091] Updated weights for policy 0, policy_version 54520 (0.0009) -[2023-10-12 05:29:10,099][78123] Updated weights for policy 1, policy_version 54260 (0.0009) -[2023-10-12 05:29:10,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 111378432. Throughput: 0: 1607.6, 1: 1599.7. Samples: 27855880. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:29:10,202][77203] Avg episode reward: [(0, '49.540'), (1, '41.880')] -[2023-10-12 05:29:10,209][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000054528_55836672.pth... -[2023-10-12 05:29:10,249][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000053024_54296576.pth -[2023-10-12 05:29:10,458][78123] Updated weights for policy 1, policy_version 54270 (0.0008) -[2023-10-12 05:29:10,530][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000054272_55574528.pth... -[2023-10-12 05:29:10,571][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000052768_54034432.pth -[2023-10-12 05:29:14,031][78091] Updated weights for policy 0, policy_version 54530 (0.0008) -[2023-10-12 05:29:14,398][78091] Updated weights for policy 0, policy_version 54540 (0.0008) -[2023-10-12 05:29:14,763][78091] Updated weights for policy 0, policy_version 54550 (0.0009) -[2023-10-12 05:29:14,836][78123] Updated weights for policy 1, policy_version 54280 (0.0008) -[2023-10-12 05:29:15,128][78091] Updated weights for policy 0, policy_version 54560 (0.0008) -[2023-10-12 05:29:15,199][78123] Updated weights for policy 1, policy_version 54290 (0.0010) -[2023-10-12 05:29:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 111443968. Throughput: 0: 1598.3, 1: 1582.5. Samples: 27865600. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:29:15,202][77203] Avg episode reward: [(0, '51.470'), (1, '43.770')] -[2023-10-12 05:29:15,564][78123] Updated weights for policy 1, policy_version 54300 (0.0009) -[2023-10-12 05:29:19,615][78091] Updated weights for policy 0, policy_version 54570 (0.0010) -[2023-10-12 05:29:19,838][78123] Updated weights for policy 1, policy_version 54310 (0.0008) -[2023-10-12 05:29:19,978][78091] Updated weights for policy 0, policy_version 54580 (0.0008) -[2023-10-12 05:29:20,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 111476736. Throughput: 0: 1608.7, 1: 1589.3. Samples: 27885012. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:29:20,202][77203] Avg episode reward: [(0, '43.890'), (1, '42.860')] -[2023-10-12 05:29:20,213][78123] Updated weights for policy 1, policy_version 54320 (0.0008) -[2023-10-12 05:29:20,348][78091] Updated weights for policy 0, policy_version 54590 (0.0009) -[2023-10-12 05:29:20,570][78123] Updated weights for policy 1, policy_version 54330 (0.0009) -[2023-10-12 05:29:24,843][78091] Updated weights for policy 0, policy_version 54600 (0.0010) -[2023-10-12 05:29:25,158][78123] Updated weights for policy 1, policy_version 54340 (0.0008) -[2023-10-12 05:29:25,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 111542272. Throughput: 0: 1615.8, 1: 1600.9. Samples: 27904182. Policy #0 lag: (min: 6.0, avg: 10.0, max: 38.0) -[2023-10-12 05:29:25,201][77203] Avg episode reward: [(0, '43.350'), (1, '46.600')] -[2023-10-12 05:29:25,212][78091] Updated weights for policy 0, policy_version 54610 (0.0009) -[2023-10-12 05:29:25,522][78123] Updated weights for policy 1, policy_version 54350 (0.0009) -[2023-10-12 05:29:25,586][78091] Updated weights for policy 0, policy_version 54620 (0.0008) -[2023-10-12 05:29:25,895][78123] Updated weights for policy 1, policy_version 54360 (0.0007) -[2023-10-12 05:29:29,879][78091] Updated weights for policy 0, policy_version 54630 (0.0007) -[2023-10-12 05:29:30,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 111607808. Throughput: 0: 1596.8, 1: 1568.0. Samples: 27913046. Policy #0 lag: (min: 6.0, avg: 10.0, max: 38.0) -[2023-10-12 05:29:30,202][77203] Avg episode reward: [(0, '48.060'), (1, '44.090')] -[2023-10-12 05:29:30,246][78123] Updated weights for policy 1, policy_version 54370 (0.0009) -[2023-10-12 05:29:30,268][78091] Updated weights for policy 0, policy_version 54640 (0.0008) -[2023-10-12 05:29:30,620][78123] Updated weights for policy 1, policy_version 54380 (0.0009) -[2023-10-12 05:29:30,640][78091] Updated weights for policy 0, policy_version 54650 (0.0008) -[2023-10-12 05:29:30,988][78123] Updated weights for policy 1, policy_version 54390 (0.0007) -[2023-10-12 05:29:31,356][78123] Updated weights for policy 1, policy_version 54400 (0.0008) -[2023-10-12 05:29:34,832][78091] Updated weights for policy 0, policy_version 54660 (0.0007) -[2023-10-12 05:29:35,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 111673344. Throughput: 0: 1598.9, 1: 1575.3. Samples: 27932492. Policy #0 lag: (min: 6.0, avg: 10.0, max: 38.0) -[2023-10-12 05:29:35,202][77203] Avg episode reward: [(0, '52.580'), (1, '46.520')] -[2023-10-12 05:29:35,203][78091] Updated weights for policy 0, policy_version 54670 (0.0008) -[2023-10-12 05:29:35,547][78123] Updated weights for policy 1, policy_version 54410 (0.0009) -[2023-10-12 05:29:35,568][78091] Updated weights for policy 0, policy_version 54680 (0.0008) -[2023-10-12 05:29:35,899][78123] Updated weights for policy 1, policy_version 54420 (0.0008) -[2023-10-12 05:29:36,261][78123] Updated weights for policy 1, policy_version 54430 (0.0010) -[2023-10-12 05:29:39,826][78091] Updated weights for policy 0, policy_version 54690 (0.0008) -[2023-10-12 05:29:40,199][78091] Updated weights for policy 0, policy_version 54700 (0.0009) -[2023-10-12 05:29:40,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 111738880. Throughput: 0: 1612.8, 1: 1592.5. Samples: 27951750. Policy #0 lag: (min: 6.0, avg: 10.0, max: 38.0) -[2023-10-12 05:29:40,201][77203] Avg episode reward: [(0, '53.670'), (1, '46.540')] -[2023-10-12 05:29:40,567][78091] Updated weights for policy 0, policy_version 54710 (0.0008) -[2023-10-12 05:29:40,691][78123] Updated weights for policy 1, policy_version 54440 (0.0009) -[2023-10-12 05:29:40,935][78091] Updated weights for policy 0, policy_version 54720 (0.0011) -[2023-10-12 05:29:41,061][78123] Updated weights for policy 1, policy_version 54450 (0.0009) -[2023-10-12 05:29:41,420][78123] Updated weights for policy 1, policy_version 54460 (0.0009) -[2023-10-12 05:29:45,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 111804416. Throughput: 0: 1590.4, 1: 1572.7. Samples: 27960390. Policy #0 lag: (min: 6.0, avg: 10.0, max: 38.0) -[2023-10-12 05:29:45,201][77203] Avg episode reward: [(0, '53.750'), (1, '46.570')] -[2023-10-12 05:29:45,331][78091] Updated weights for policy 0, policy_version 54730 (0.0008) -[2023-10-12 05:29:45,695][78091] Updated weights for policy 0, policy_version 54740 (0.0008) -[2023-10-12 05:29:45,884][78123] Updated weights for policy 1, policy_version 54470 (0.0008) -[2023-10-12 05:29:46,069][78091] Updated weights for policy 0, policy_version 54750 (0.0008) -[2023-10-12 05:29:46,257][78123] Updated weights for policy 1, policy_version 54480 (0.0009) -[2023-10-12 05:29:46,612][78123] Updated weights for policy 1, policy_version 54490 (0.0007) -[2023-10-12 05:29:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 111869952. Throughput: 0: 1580.7, 1: 1570.1. Samples: 27979584. Policy #0 lag: (min: 6.0, avg: 10.0, max: 38.0) -[2023-10-12 05:29:50,201][77203] Avg episode reward: [(0, '46.830'), (1, '45.750')] -[2023-10-12 05:29:50,456][78091] Updated weights for policy 0, policy_version 54760 (0.0008) -[2023-10-12 05:29:50,829][78091] Updated weights for policy 0, policy_version 54770 (0.0009) -[2023-10-12 05:29:50,831][78123] Updated weights for policy 1, policy_version 54500 (0.0008) -[2023-10-12 05:29:51,198][78091] Updated weights for policy 0, policy_version 54780 (0.0008) -[2023-10-12 05:29:51,213][78123] Updated weights for policy 1, policy_version 54510 (0.0010) -[2023-10-12 05:29:51,577][78123] Updated weights for policy 1, policy_version 54520 (0.0008) -[2023-10-12 05:29:55,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 111935488. Throughput: 0: 1600.0, 1: 1583.2. Samples: 27999122. Policy #0 lag: (min: 6.0, avg: 10.0, max: 38.0) -[2023-10-12 05:29:55,201][77203] Avg episode reward: [(0, '56.530'), (1, '48.840')] -[2023-10-12 05:29:55,334][78091] Updated weights for policy 0, policy_version 54790 (0.0008) -[2023-10-12 05:29:55,703][78091] Updated weights for policy 0, policy_version 54800 (0.0007) -[2023-10-12 05:29:55,948][78123] Updated weights for policy 1, policy_version 54530 (0.0008) -[2023-10-12 05:29:56,071][78091] Updated weights for policy 0, policy_version 54810 (0.0008) -[2023-10-12 05:29:56,330][78123] Updated weights for policy 1, policy_version 54540 (0.0007) -[2023-10-12 05:29:56,694][78123] Updated weights for policy 1, policy_version 54550 (0.0009) -[2023-10-12 05:29:57,067][78123] Updated weights for policy 1, policy_version 54560 (0.0008) -[2023-10-12 05:30:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 112001024. Throughput: 0: 1582.0, 1: 1577.7. Samples: 28007786. Policy #0 lag: (min: 29.0, avg: 33.3, max: 61.0) -[2023-10-12 05:30:00,201][77203] Avg episode reward: [(0, '52.550'), (1, '46.580')] -[2023-10-12 05:30:00,366][78091] Updated weights for policy 0, policy_version 54820 (0.0008) -[2023-10-12 05:30:00,741][78091] Updated weights for policy 0, policy_version 54830 (0.0009) -[2023-10-12 05:30:01,117][78091] Updated weights for policy 0, policy_version 54840 (0.0007) -[2023-10-12 05:30:01,373][78123] Updated weights for policy 1, policy_version 54570 (0.0009) -[2023-10-12 05:30:01,738][78123] Updated weights for policy 1, policy_version 54580 (0.0008) -[2023-10-12 05:30:02,103][78123] Updated weights for policy 1, policy_version 54590 (0.0008) -[2023-10-12 05:30:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 112066560. Throughput: 0: 1589.9, 1: 1579.6. Samples: 28027638. Policy #0 lag: (min: 29.0, avg: 33.3, max: 61.0) -[2023-10-12 05:30:05,201][77203] Avg episode reward: [(0, '51.340'), (1, '48.940')] -[2023-10-12 05:30:05,456][78091] Updated weights for policy 0, policy_version 54850 (0.0007) -[2023-10-12 05:30:05,820][78091] Updated weights for policy 0, policy_version 54860 (0.0008) -[2023-10-12 05:30:06,196][78091] Updated weights for policy 0, policy_version 54870 (0.0008) -[2023-10-12 05:30:06,442][78123] Updated weights for policy 1, policy_version 54600 (0.0008) -[2023-10-12 05:30:06,555][78091] Updated weights for policy 0, policy_version 54880 (0.0010) -[2023-10-12 05:30:06,804][78123] Updated weights for policy 1, policy_version 54610 (0.0007) -[2023-10-12 05:30:07,168][78123] Updated weights for policy 1, policy_version 54620 (0.0010) -[2023-10-12 05:30:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 112132096. Throughput: 0: 1592.3, 1: 1577.8. Samples: 28046838. Policy #0 lag: (min: 29.0, avg: 33.3, max: 61.0) -[2023-10-12 05:30:10,201][77203] Avg episode reward: [(0, '46.050'), (1, '50.740')] -[2023-10-12 05:30:10,934][78091] Updated weights for policy 0, policy_version 54890 (0.0007) -[2023-10-12 05:30:11,301][78091] Updated weights for policy 0, policy_version 54900 (0.0008) -[2023-10-12 05:30:11,582][78123] Updated weights for policy 1, policy_version 54630 (0.0007) -[2023-10-12 05:30:11,678][78091] Updated weights for policy 0, policy_version 54910 (0.0007) -[2023-10-12 05:30:11,953][78123] Updated weights for policy 1, policy_version 54640 (0.0008) -[2023-10-12 05:30:12,321][78123] Updated weights for policy 1, policy_version 54650 (0.0007) -[2023-10-12 05:30:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 112197632. Throughput: 0: 1586.0, 1: 1581.8. Samples: 28055596. Policy #0 lag: (min: 29.0, avg: 33.3, max: 61.0) -[2023-10-12 05:30:15,202][77203] Avg episode reward: [(0, '51.680'), (1, '46.550')] -[2023-10-12 05:30:16,147][78091] Updated weights for policy 0, policy_version 54920 (0.0007) -[2023-10-12 05:30:16,511][78091] Updated weights for policy 0, policy_version 54930 (0.0009) -[2023-10-12 05:30:16,883][78091] Updated weights for policy 0, policy_version 54940 (0.0008) -[2023-10-12 05:30:16,893][78123] Updated weights for policy 1, policy_version 54660 (0.0007) -[2023-10-12 05:30:17,257][78123] Updated weights for policy 1, policy_version 54670 (0.0007) -[2023-10-12 05:30:17,615][78123] Updated weights for policy 1, policy_version 54680 (0.0010) -[2023-10-12 05:30:20,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 112263168. Throughput: 0: 1588.9, 1: 1579.8. Samples: 28075084. Policy #0 lag: (min: 29.0, avg: 33.3, max: 61.0) -[2023-10-12 05:30:20,202][77203] Avg episode reward: [(0, '47.270'), (1, '45.110')] -[2023-10-12 05:30:20,967][78091] Updated weights for policy 0, policy_version 54950 (0.0008) -[2023-10-12 05:30:21,338][78091] Updated weights for policy 0, policy_version 54960 (0.0008) -[2023-10-12 05:30:21,710][78091] Updated weights for policy 0, policy_version 54970 (0.0007) -[2023-10-12 05:30:21,960][78123] Updated weights for policy 1, policy_version 54690 (0.0008) -[2023-10-12 05:30:22,330][78123] Updated weights for policy 1, policy_version 54700 (0.0010) -[2023-10-12 05:30:22,697][78123] Updated weights for policy 1, policy_version 54710 (0.0009) -[2023-10-12 05:30:23,068][78123] Updated weights for policy 1, policy_version 54720 (0.0010) -[2023-10-12 05:30:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 112328704. Throughput: 0: 1590.2, 1: 1578.3. Samples: 28094330. Policy #0 lag: (min: 29.0, avg: 33.3, max: 61.0) -[2023-10-12 05:30:25,201][77203] Avg episode reward: [(0, '47.310'), (1, '46.100')] -[2023-10-12 05:30:26,010][78091] Updated weights for policy 0, policy_version 54980 (0.0008) -[2023-10-12 05:30:26,383][78091] Updated weights for policy 0, policy_version 54990 (0.0008) -[2023-10-12 05:30:26,752][78091] Updated weights for policy 0, policy_version 55000 (0.0007) -[2023-10-12 05:30:27,457][78123] Updated weights for policy 1, policy_version 54730 (0.0008) -[2023-10-12 05:30:27,820][78123] Updated weights for policy 1, policy_version 54740 (0.0009) -[2023-10-12 05:30:28,189][78123] Updated weights for policy 1, policy_version 54750 (0.0007) -[2023-10-12 05:30:30,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 112394240. Throughput: 0: 1590.0, 1: 1590.0. Samples: 28103490. Policy #0 lag: (min: 29.0, avg: 33.3, max: 61.0) -[2023-10-12 05:30:30,201][77203] Avg episode reward: [(0, '43.280'), (1, '50.280')] -[2023-10-12 05:30:31,146][78091] Updated weights for policy 0, policy_version 55010 (0.0009) -[2023-10-12 05:30:31,521][78091] Updated weights for policy 0, policy_version 55020 (0.0007) -[2023-10-12 05:30:31,895][78091] Updated weights for policy 0, policy_version 55030 (0.0007) -[2023-10-12 05:30:32,266][78091] Updated weights for policy 0, policy_version 55040 (0.0007) -[2023-10-12 05:30:32,710][78123] Updated weights for policy 1, policy_version 54760 (0.0007) -[2023-10-12 05:30:33,070][78123] Updated weights for policy 1, policy_version 54770 (0.0008) -[2023-10-12 05:30:33,438][78123] Updated weights for policy 1, policy_version 54780 (0.0009) -[2023-10-12 05:30:35,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 112459776. Throughput: 0: 1592.4, 1: 1581.1. Samples: 28122392. Policy #0 lag: (min: 31.0, avg: 40.1, max: 63.0) -[2023-10-12 05:30:35,202][77203] Avg episode reward: [(0, '50.130'), (1, '42.100')] -[2023-10-12 05:30:36,656][78091] Updated weights for policy 0, policy_version 55050 (0.0007) -[2023-10-12 05:30:37,035][78091] Updated weights for policy 0, policy_version 55060 (0.0010) -[2023-10-12 05:30:37,404][78091] Updated weights for policy 0, policy_version 55070 (0.0008) -[2023-10-12 05:30:37,737][78123] Updated weights for policy 1, policy_version 54790 (0.0009) -[2023-10-12 05:30:38,120][78123] Updated weights for policy 1, policy_version 54800 (0.0011) -[2023-10-12 05:30:38,484][78123] Updated weights for policy 1, policy_version 54810 (0.0009) -[2023-10-12 05:30:40,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 112525312. Throughput: 0: 1590.6, 1: 1574.4. Samples: 28141550. Policy #0 lag: (min: 31.0, avg: 40.1, max: 63.0) -[2023-10-12 05:30:40,201][77203] Avg episode reward: [(0, '52.850'), (1, '40.240')] -[2023-10-12 05:30:41,789][78091] Updated weights for policy 0, policy_version 55080 (0.0007) -[2023-10-12 05:30:42,155][78091] Updated weights for policy 0, policy_version 55090 (0.0007) -[2023-10-12 05:30:42,526][78091] Updated weights for policy 0, policy_version 55100 (0.0008) -[2023-10-12 05:30:42,731][78123] Updated weights for policy 1, policy_version 54820 (0.0009) -[2023-10-12 05:30:43,095][78123] Updated weights for policy 1, policy_version 54830 (0.0007) -[2023-10-12 05:30:43,466][78123] Updated weights for policy 1, policy_version 54840 (0.0007) -[2023-10-12 05:30:45,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 112590848. Throughput: 0: 1590.7, 1: 1596.5. Samples: 28151214. Policy #0 lag: (min: 31.0, avg: 40.1, max: 63.0) -[2023-10-12 05:30:45,202][77203] Avg episode reward: [(0, '48.570'), (1, '43.580')] -[2023-10-12 05:30:46,798][78091] Updated weights for policy 0, policy_version 55110 (0.0009) -[2023-10-12 05:30:47,179][78091] Updated weights for policy 0, policy_version 55120 (0.0007) -[2023-10-12 05:30:47,546][78091] Updated weights for policy 0, policy_version 55130 (0.0009) -[2023-10-12 05:30:47,708][78123] Updated weights for policy 1, policy_version 54850 (0.0007) -[2023-10-12 05:30:48,078][78123] Updated weights for policy 1, policy_version 54860 (0.0008) -[2023-10-12 05:30:48,439][78123] Updated weights for policy 1, policy_version 54870 (0.0010) -[2023-10-12 05:30:48,799][78123] Updated weights for policy 1, policy_version 54880 (0.0011) -[2023-10-12 05:30:50,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 12662.9). Total num frames: 112656384. Throughput: 0: 1589.9, 1: 1572.6. Samples: 28169950. Policy #0 lag: (min: 31.0, avg: 40.1, max: 63.0) -[2023-10-12 05:30:50,202][77203] Avg episode reward: [(0, '53.410'), (1, '43.890')] -[2023-10-12 05:30:51,794][78091] Updated weights for policy 0, policy_version 55140 (0.0009) -[2023-10-12 05:30:52,165][78091] Updated weights for policy 0, policy_version 55150 (0.0009) -[2023-10-12 05:30:52,544][78091] Updated weights for policy 0, policy_version 55160 (0.0009) -[2023-10-12 05:30:53,345][78123] Updated weights for policy 1, policy_version 54890 (0.0007) -[2023-10-12 05:30:53,712][78123] Updated weights for policy 1, policy_version 54900 (0.0009) -[2023-10-12 05:30:54,078][78123] Updated weights for policy 1, policy_version 54910 (0.0009) -[2023-10-12 05:30:55,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 112721920. Throughput: 0: 1593.9, 1: 1569.1. Samples: 28189170. Policy #0 lag: (min: 31.0, avg: 40.1, max: 63.0) -[2023-10-12 05:30:55,201][77203] Avg episode reward: [(0, '51.560'), (1, '41.160')] -[2023-10-12 05:30:56,778][78091] Updated weights for policy 0, policy_version 55170 (0.0009) -[2023-10-12 05:30:57,146][78091] Updated weights for policy 0, policy_version 55180 (0.0007) -[2023-10-12 05:30:57,513][78091] Updated weights for policy 0, policy_version 55190 (0.0008) -[2023-10-12 05:30:57,883][78091] Updated weights for policy 0, policy_version 55200 (0.0008) -[2023-10-12 05:30:58,314][78123] Updated weights for policy 1, policy_version 54920 (0.0010) -[2023-10-12 05:30:58,690][78123] Updated weights for policy 1, policy_version 54930 (0.0011) -[2023-10-12 05:30:59,056][78123] Updated weights for policy 1, policy_version 54940 (0.0010) -[2023-10-12 05:31:00,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 112787456. Throughput: 0: 1595.8, 1: 1596.0. Samples: 28199226. Policy #0 lag: (min: 31.0, avg: 40.1, max: 63.0) -[2023-10-12 05:31:00,201][77203] Avg episode reward: [(0, '54.600'), (1, '46.140')] -[2023-10-12 05:31:02,147][78091] Updated weights for policy 0, policy_version 55210 (0.0007) -[2023-10-12 05:31:02,507][78091] Updated weights for policy 0, policy_version 55220 (0.0009) -[2023-10-12 05:31:02,882][78091] Updated weights for policy 0, policy_version 55230 (0.0008) -[2023-10-12 05:31:03,443][78123] Updated weights for policy 1, policy_version 54950 (0.0010) -[2023-10-12 05:31:03,808][78123] Updated weights for policy 1, policy_version 54960 (0.0007) -[2023-10-12 05:31:04,164][78123] Updated weights for policy 1, policy_version 54970 (0.0010) -[2023-10-12 05:31:05,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 112852992. Throughput: 0: 1594.3, 1: 1585.5. Samples: 28218172. Policy #0 lag: (min: 31.0, avg: 40.1, max: 63.0) -[2023-10-12 05:31:05,201][77203] Avg episode reward: [(0, '53.910'), (1, '45.700')] -[2023-10-12 05:31:07,028][78091] Updated weights for policy 0, policy_version 55240 (0.0008) -[2023-10-12 05:31:07,406][78091] Updated weights for policy 0, policy_version 55250 (0.0009) -[2023-10-12 05:31:07,774][78091] Updated weights for policy 0, policy_version 55260 (0.0010) -[2023-10-12 05:31:08,540][78123] Updated weights for policy 1, policy_version 54980 (0.0010) -[2023-10-12 05:31:08,904][78123] Updated weights for policy 1, policy_version 54990 (0.0010) -[2023-10-12 05:31:09,273][78123] Updated weights for policy 1, policy_version 55000 (0.0009) -[2023-10-12 05:31:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 112918528. Throughput: 0: 1605.8, 1: 1571.8. Samples: 28237320. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:31:10,201][77203] Avg episode reward: [(0, '49.430'), (1, '46.190')] -[2023-10-12 05:31:10,209][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000055264_56590336.pth... -[2023-10-12 05:31:10,210][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000055008_56328192.pth... -[2023-10-12 05:31:10,241][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000053504_54788096.pth -[2023-10-12 05:31:10,249][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000053760_55050240.pth -[2023-10-12 05:31:11,988][78091] Updated weights for policy 0, policy_version 55270 (0.0008) -[2023-10-12 05:31:12,367][78091] Updated weights for policy 0, policy_version 55280 (0.0008) -[2023-10-12 05:31:12,740][78091] Updated weights for policy 0, policy_version 55290 (0.0008) -[2023-10-12 05:31:13,725][78123] Updated weights for policy 1, policy_version 55010 (0.0010) -[2023-10-12 05:31:14,092][78123] Updated weights for policy 1, policy_version 55020 (0.0008) -[2023-10-12 05:31:14,459][78123] Updated weights for policy 1, policy_version 55030 (0.0009) -[2023-10-12 05:31:14,812][78123] Updated weights for policy 1, policy_version 55040 (0.0009) -[2023-10-12 05:31:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 112984064. Throughput: 0: 1610.0, 1: 1587.0. Samples: 28247352. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:31:15,202][77203] Avg episode reward: [(0, '52.170'), (1, '41.670')] -[2023-10-12 05:31:17,107][78091] Updated weights for policy 0, policy_version 55300 (0.0008) -[2023-10-12 05:31:17,477][78091] Updated weights for policy 0, policy_version 55310 (0.0008) -[2023-10-12 05:31:17,848][78091] Updated weights for policy 0, policy_version 55320 (0.0007) -[2023-10-12 05:31:18,891][78123] Updated weights for policy 1, policy_version 55050 (0.0008) -[2023-10-12 05:31:19,262][78123] Updated weights for policy 1, policy_version 55060 (0.0009) -[2023-10-12 05:31:19,631][78123] Updated weights for policy 1, policy_version 55070 (0.0011) -[2023-10-12 05:31:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 113049600. Throughput: 0: 1605.6, 1: 1597.5. Samples: 28266532. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:31:20,201][77203] Avg episode reward: [(0, '45.410'), (1, '48.100')] -[2023-10-12 05:31:22,026][78091] Updated weights for policy 0, policy_version 55330 (0.0007) -[2023-10-12 05:31:22,406][78091] Updated weights for policy 0, policy_version 55340 (0.0008) -[2023-10-12 05:31:22,773][78091] Updated weights for policy 0, policy_version 55350 (0.0007) -[2023-10-12 05:31:23,134][78091] Updated weights for policy 0, policy_version 55360 (0.0010) -[2023-10-12 05:31:24,052][78123] Updated weights for policy 1, policy_version 55080 (0.0009) -[2023-10-12 05:31:24,412][78123] Updated weights for policy 1, policy_version 55090 (0.0008) -[2023-10-12 05:31:24,790][78123] Updated weights for policy 1, policy_version 55100 (0.0011) -[2023-10-12 05:31:25,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 113115136. Throughput: 0: 1613.8, 1: 1586.7. Samples: 28285570. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:31:25,201][77203] Avg episode reward: [(0, '49.450'), (1, '44.350')] -[2023-10-12 05:31:27,495][78091] Updated weights for policy 0, policy_version 55370 (0.0009) -[2023-10-12 05:31:27,862][78091] Updated weights for policy 0, policy_version 55380 (0.0008) -[2023-10-12 05:31:28,239][78091] Updated weights for policy 0, policy_version 55390 (0.0008) -[2023-10-12 05:31:29,134][78123] Updated weights for policy 1, policy_version 55110 (0.0010) -[2023-10-12 05:31:29,506][78123] Updated weights for policy 1, policy_version 55120 (0.0009) -[2023-10-12 05:31:29,881][78123] Updated weights for policy 1, policy_version 55130 (0.0007) -[2023-10-12 05:31:30,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 113180672. Throughput: 0: 1627.5, 1: 1581.7. Samples: 28295630. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:31:30,202][77203] Avg episode reward: [(0, '45.650'), (1, '53.780')] -[2023-10-12 05:31:32,660][78091] Updated weights for policy 0, policy_version 55400 (0.0010) -[2023-10-12 05:31:33,034][78091] Updated weights for policy 0, policy_version 55410 (0.0011) -[2023-10-12 05:31:33,414][78091] Updated weights for policy 0, policy_version 55420 (0.0011) -[2023-10-12 05:31:34,233][78123] Updated weights for policy 1, policy_version 55140 (0.0008) -[2023-10-12 05:31:34,601][78123] Updated weights for policy 1, policy_version 55150 (0.0010) -[2023-10-12 05:31:34,970][78123] Updated weights for policy 1, policy_version 55160 (0.0009) -[2023-10-12 05:31:35,201][77203] Fps is (10 sec: 9830.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 113213440. Throughput: 0: 1607.3, 1: 1607.8. Samples: 28314628. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:31:35,203][77203] Avg episode reward: [(0, '50.950'), (1, '49.200')] -[2023-10-12 05:31:37,573][78091] Updated weights for policy 0, policy_version 55430 (0.0007) -[2023-10-12 05:31:37,937][78091] Updated weights for policy 0, policy_version 55440 (0.0007) -[2023-10-12 05:31:38,316][78091] Updated weights for policy 0, policy_version 55450 (0.0007) -[2023-10-12 05:31:39,092][78123] Updated weights for policy 1, policy_version 55170 (0.0009) -[2023-10-12 05:31:39,467][78123] Updated weights for policy 1, policy_version 55180 (0.0009) -[2023-10-12 05:31:39,824][78123] Updated weights for policy 1, policy_version 55190 (0.0010) -[2023-10-12 05:31:40,186][78123] Updated weights for policy 1, policy_version 55200 (0.0010) -[2023-10-12 05:31:40,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 113311744. Throughput: 0: 1613.3, 1: 1602.6. Samples: 28333884. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:31:40,202][77203] Avg episode reward: [(0, '48.720'), (1, '43.540')] -[2023-10-12 05:31:42,761][78091] Updated weights for policy 0, policy_version 55460 (0.0007) -[2023-10-12 05:31:43,136][78091] Updated weights for policy 0, policy_version 55470 (0.0007) -[2023-10-12 05:31:43,501][78091] Updated weights for policy 0, policy_version 55480 (0.0008) -[2023-10-12 05:31:44,767][78123] Updated weights for policy 1, policy_version 55210 (0.0008) -[2023-10-12 05:31:45,134][78123] Updated weights for policy 1, policy_version 55220 (0.0009) -[2023-10-12 05:31:45,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 113344512. Throughput: 0: 1628.1, 1: 1586.6. Samples: 28343890. Policy #0 lag: (min: 4.0, avg: 6.8, max: 36.0) -[2023-10-12 05:31:45,202][77203] Avg episode reward: [(0, '51.080'), (1, '41.770')] -[2023-10-12 05:31:45,510][78123] Updated weights for policy 1, policy_version 55230 (0.0009) -[2023-10-12 05:31:47,828][78091] Updated weights for policy 0, policy_version 55490 (0.0009) -[2023-10-12 05:31:48,204][78091] Updated weights for policy 0, policy_version 55500 (0.0008) -[2023-10-12 05:31:48,572][78091] Updated weights for policy 0, policy_version 55510 (0.0009) -[2023-10-12 05:31:48,945][78091] Updated weights for policy 0, policy_version 55520 (0.0008) -[2023-10-12 05:31:49,854][78123] Updated weights for policy 1, policy_version 55240 (0.0009) -[2023-10-12 05:31:50,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 113410048. Throughput: 0: 1611.1, 1: 1597.5. Samples: 28362558. Policy #0 lag: (min: 4.0, avg: 6.8, max: 36.0) -[2023-10-12 05:31:50,201][77203] Avg episode reward: [(0, '52.350'), (1, '45.500')] -[2023-10-12 05:31:50,229][78123] Updated weights for policy 1, policy_version 55250 (0.0009) -[2023-10-12 05:31:50,596][78123] Updated weights for policy 1, policy_version 55260 (0.0007) -[2023-10-12 05:31:53,236][78091] Updated weights for policy 0, policy_version 55530 (0.0009) -[2023-10-12 05:31:53,597][78091] Updated weights for policy 0, policy_version 55540 (0.0007) -[2023-10-12 05:31:53,970][78091] Updated weights for policy 0, policy_version 55550 (0.0008) -[2023-10-12 05:31:54,993][78123] Updated weights for policy 1, policy_version 55270 (0.0007) -[2023-10-12 05:31:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 113475584. Throughput: 0: 1596.8, 1: 1612.3. Samples: 28381732. Policy #0 lag: (min: 4.0, avg: 6.8, max: 36.0) -[2023-10-12 05:31:55,202][77203] Avg episode reward: [(0, '53.940'), (1, '36.690')] -[2023-10-12 05:31:55,366][78123] Updated weights for policy 1, policy_version 55280 (0.0009) -[2023-10-12 05:31:55,726][78123] Updated weights for policy 1, policy_version 55290 (0.0007) -[2023-10-12 05:31:58,114][78091] Updated weights for policy 0, policy_version 55560 (0.0007) -[2023-10-12 05:31:58,477][78091] Updated weights for policy 0, policy_version 55570 (0.0009) -[2023-10-12 05:31:58,854][78091] Updated weights for policy 0, policy_version 55580 (0.0008) -[2023-10-12 05:32:00,072][78123] Updated weights for policy 1, policy_version 55300 (0.0007) -[2023-10-12 05:32:00,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 113541120. Throughput: 0: 1620.1, 1: 1585.5. Samples: 28391604. Policy #0 lag: (min: 4.0, avg: 6.8, max: 36.0) -[2023-10-12 05:32:00,201][77203] Avg episode reward: [(0, '52.220'), (1, '45.490')] -[2023-10-12 05:32:00,436][78123] Updated weights for policy 1, policy_version 55310 (0.0008) -[2023-10-12 05:32:00,796][78123] Updated weights for policy 1, policy_version 55320 (0.0009) -[2023-10-12 05:32:03,022][78091] Updated weights for policy 0, policy_version 55590 (0.0008) -[2023-10-12 05:32:03,393][78091] Updated weights for policy 0, policy_version 55600 (0.0011) -[2023-10-12 05:32:03,758][78091] Updated weights for policy 0, policy_version 55610 (0.0011) -[2023-10-12 05:32:05,111][78123] Updated weights for policy 1, policy_version 55330 (0.0009) -[2023-10-12 05:32:05,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 113606656. Throughput: 0: 1603.1, 1: 1591.5. Samples: 28410290. Policy #0 lag: (min: 4.0, avg: 6.8, max: 36.0) -[2023-10-12 05:32:05,202][77203] Avg episode reward: [(0, '51.790'), (1, '48.020')] -[2023-10-12 05:32:05,471][78123] Updated weights for policy 1, policy_version 55340 (0.0012) -[2023-10-12 05:32:05,837][78123] Updated weights for policy 1, policy_version 55350 (0.0010) -[2023-10-12 05:32:06,206][78123] Updated weights for policy 1, policy_version 55360 (0.0009) -[2023-10-12 05:32:08,258][78091] Updated weights for policy 0, policy_version 55620 (0.0009) -[2023-10-12 05:32:08,633][78091] Updated weights for policy 0, policy_version 55630 (0.0010) -[2023-10-12 05:32:09,003][78091] Updated weights for policy 0, policy_version 55640 (0.0011) -[2023-10-12 05:32:10,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 113672192. Throughput: 0: 1592.8, 1: 1605.2. Samples: 28429482. Policy #0 lag: (min: 4.0, avg: 6.8, max: 36.0) -[2023-10-12 05:32:10,202][77203] Avg episode reward: [(0, '45.290'), (1, '39.110')] -[2023-10-12 05:32:10,592][78123] Updated weights for policy 1, policy_version 55370 (0.0010) -[2023-10-12 05:32:10,954][78123] Updated weights for policy 1, policy_version 55380 (0.0010) -[2023-10-12 05:32:11,315][78123] Updated weights for policy 1, policy_version 55390 (0.0011) -[2023-10-12 05:32:13,305][78091] Updated weights for policy 0, policy_version 55650 (0.0008) -[2023-10-12 05:32:13,678][78091] Updated weights for policy 0, policy_version 55660 (0.0007) -[2023-10-12 05:32:14,042][78091] Updated weights for policy 0, policy_version 55670 (0.0008) -[2023-10-12 05:32:14,408][78091] Updated weights for policy 0, policy_version 55680 (0.0009) -[2023-10-12 05:32:15,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 113737728. Throughput: 0: 1608.0, 1: 1581.9. Samples: 28439176. Policy #0 lag: (min: 4.0, avg: 6.8, max: 36.0) -[2023-10-12 05:32:15,202][77203] Avg episode reward: [(0, '47.720'), (1, '43.660')] -[2023-10-12 05:32:15,796][78123] Updated weights for policy 1, policy_version 55400 (0.0008) -[2023-10-12 05:32:16,171][78123] Updated weights for policy 1, policy_version 55410 (0.0008) -[2023-10-12 05:32:16,540][78123] Updated weights for policy 1, policy_version 55420 (0.0008) -[2023-10-12 05:32:18,739][78091] Updated weights for policy 0, policy_version 55690 (0.0008) -[2023-10-12 05:32:19,115][78091] Updated weights for policy 0, policy_version 55700 (0.0010) -[2023-10-12 05:32:19,487][78091] Updated weights for policy 0, policy_version 55710 (0.0007) -[2023-10-12 05:32:20,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 113803264. Throughput: 0: 1615.9, 1: 1578.1. Samples: 28458360. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:32:20,202][77203] Avg episode reward: [(0, '49.980'), (1, '45.980')] -[2023-10-12 05:32:20,944][78123] Updated weights for policy 1, policy_version 55430 (0.0009) -[2023-10-12 05:32:21,308][78123] Updated weights for policy 1, policy_version 55440 (0.0010) -[2023-10-12 05:32:21,682][78123] Updated weights for policy 1, policy_version 55450 (0.0009) -[2023-10-12 05:32:23,767][78091] Updated weights for policy 0, policy_version 55720 (0.0007) -[2023-10-12 05:32:24,135][78091] Updated weights for policy 0, policy_version 55730 (0.0008) -[2023-10-12 05:32:24,501][78091] Updated weights for policy 0, policy_version 55740 (0.0009) -[2023-10-12 05:32:25,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 113868800. Throughput: 0: 1590.7, 1: 1588.2. Samples: 28476936. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:32:25,202][77203] Avg episode reward: [(0, '51.790'), (1, '52.960')] -[2023-10-12 05:32:26,005][78123] Updated weights for policy 1, policy_version 55460 (0.0010) -[2023-10-12 05:32:26,364][78123] Updated weights for policy 1, policy_version 55470 (0.0007) -[2023-10-12 05:32:26,724][78123] Updated weights for policy 1, policy_version 55480 (0.0008) -[2023-10-12 05:32:28,738][78091] Updated weights for policy 0, policy_version 55750 (0.0007) -[2023-10-12 05:32:29,101][78091] Updated weights for policy 0, policy_version 55760 (0.0007) -[2023-10-12 05:32:29,466][78091] Updated weights for policy 0, policy_version 55770 (0.0009) -[2023-10-12 05:32:30,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 113934336. Throughput: 0: 1602.0, 1: 1576.2. Samples: 28486908. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:32:30,201][77203] Avg episode reward: [(0, '52.020'), (1, '49.130')] -[2023-10-12 05:32:31,085][78123] Updated weights for policy 1, policy_version 55490 (0.0009) -[2023-10-12 05:32:31,466][78123] Updated weights for policy 1, policy_version 55500 (0.0009) -[2023-10-12 05:32:31,840][78123] Updated weights for policy 1, policy_version 55510 (0.0008) -[2023-10-12 05:32:32,199][78123] Updated weights for policy 1, policy_version 55520 (0.0010) -[2023-10-12 05:32:33,810][78091] Updated weights for policy 0, policy_version 55780 (0.0009) -[2023-10-12 05:32:34,180][78091] Updated weights for policy 0, policy_version 55790 (0.0009) -[2023-10-12 05:32:34,548][78091] Updated weights for policy 0, policy_version 55800 (0.0009) -[2023-10-12 05:32:35,201][77203] Fps is (10 sec: 13107.6, 60 sec: 13107.3, 300 sec: 12774.0). Total num frames: 113999872. Throughput: 0: 1615.8, 1: 1578.6. Samples: 28506304. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:32:35,201][77203] Avg episode reward: [(0, '59.570'), (1, '46.460')] -[2023-10-12 05:32:35,202][77792] Saving new best policy, reward=59.570! -[2023-10-12 05:32:36,406][78123] Updated weights for policy 1, policy_version 55530 (0.0008) -[2023-10-12 05:32:36,771][78123] Updated weights for policy 1, policy_version 55540 (0.0007) -[2023-10-12 05:32:37,140][78123] Updated weights for policy 1, policy_version 55550 (0.0007) -[2023-10-12 05:32:39,020][78091] Updated weights for policy 0, policy_version 55810 (0.0008) -[2023-10-12 05:32:39,386][78091] Updated weights for policy 0, policy_version 55820 (0.0008) -[2023-10-12 05:32:39,758][78091] Updated weights for policy 0, policy_version 55830 (0.0007) -[2023-10-12 05:32:40,129][78091] Updated weights for policy 0, policy_version 55840 (0.0008) -[2023-10-12 05:32:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 114065408. Throughput: 0: 1603.0, 1: 1579.3. Samples: 28524938. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:32:40,201][77203] Avg episode reward: [(0, '47.650'), (1, '45.740')] -[2023-10-12 05:32:41,486][78123] Updated weights for policy 1, policy_version 55560 (0.0010) -[2023-10-12 05:32:41,863][78123] Updated weights for policy 1, policy_version 55570 (0.0007) -[2023-10-12 05:32:42,224][78123] Updated weights for policy 1, policy_version 55580 (0.0008) -[2023-10-12 05:32:44,348][78091] Updated weights for policy 0, policy_version 55850 (0.0010) -[2023-10-12 05:32:44,717][78091] Updated weights for policy 0, policy_version 55860 (0.0009) -[2023-10-12 05:32:45,092][78091] Updated weights for policy 0, policy_version 55870 (0.0009) -[2023-10-12 05:32:45,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 114130944. Throughput: 0: 1594.8, 1: 1581.4. Samples: 28534536. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:32:45,202][77203] Avg episode reward: [(0, '50.360'), (1, '46.320')] -[2023-10-12 05:32:46,390][78123] Updated weights for policy 1, policy_version 55590 (0.0009) -[2023-10-12 05:32:46,750][78123] Updated weights for policy 1, policy_version 55600 (0.0010) -[2023-10-12 05:32:47,120][78123] Updated weights for policy 1, policy_version 55610 (0.0008) -[2023-10-12 05:32:49,470][78091] Updated weights for policy 0, policy_version 55880 (0.0008) -[2023-10-12 05:32:49,852][78091] Updated weights for policy 0, policy_version 55890 (0.0009) -[2023-10-12 05:32:50,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 114163712. Throughput: 0: 1610.2, 1: 1579.8. Samples: 28553838. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:32:50,201][77203] Avg episode reward: [(0, '49.750'), (1, '37.750')] -[2023-10-12 05:32:50,223][78091] Updated weights for policy 0, policy_version 55900 (0.0010) -[2023-10-12 05:32:51,386][78123] Updated weights for policy 1, policy_version 55620 (0.0008) -[2023-10-12 05:32:51,757][78123] Updated weights for policy 1, policy_version 55630 (0.0008) -[2023-10-12 05:32:52,122][78123] Updated weights for policy 1, policy_version 55640 (0.0007) -[2023-10-12 05:32:54,413][78091] Updated weights for policy 0, policy_version 55910 (0.0008) -[2023-10-12 05:32:54,786][78091] Updated weights for policy 0, policy_version 55920 (0.0008) -[2023-10-12 05:32:55,171][78091] Updated weights for policy 0, policy_version 55930 (0.0008) -[2023-10-12 05:32:55,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 114229248. Throughput: 0: 1598.6, 1: 1587.0. Samples: 28572834. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:32:55,202][77203] Avg episode reward: [(0, '51.270'), (1, '37.120')] -[2023-10-12 05:32:56,244][78123] Updated weights for policy 1, policy_version 55650 (0.0008) -[2023-10-12 05:32:56,630][78123] Updated weights for policy 1, policy_version 55660 (0.0008) -[2023-10-12 05:32:57,011][78123] Updated weights for policy 1, policy_version 55670 (0.0009) -[2023-10-12 05:32:57,374][78123] Updated weights for policy 1, policy_version 55680 (0.0009) -[2023-10-12 05:32:59,430][78091] Updated weights for policy 0, policy_version 55940 (0.0008) -[2023-10-12 05:32:59,801][78091] Updated weights for policy 0, policy_version 55950 (0.0010) -[2023-10-12 05:33:00,167][78091] Updated weights for policy 0, policy_version 55960 (0.0007) -[2023-10-12 05:33:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 114294784. Throughput: 0: 1584.6, 1: 1593.8. Samples: 28582204. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-12 05:33:00,201][77203] Avg episode reward: [(0, '53.710'), (1, '48.100')] -[2023-10-12 05:33:01,689][78123] Updated weights for policy 1, policy_version 55690 (0.0007) -[2023-10-12 05:33:02,047][78123] Updated weights for policy 1, policy_version 55700 (0.0008) -[2023-10-12 05:33:02,420][78123] Updated weights for policy 1, policy_version 55710 (0.0008) -[2023-10-12 05:33:04,534][78091] Updated weights for policy 0, policy_version 55970 (0.0010) -[2023-10-12 05:33:04,908][78091] Updated weights for policy 0, policy_version 55980 (0.0011) -[2023-10-12 05:33:05,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 114360320. Throughput: 0: 1594.4, 1: 1594.5. Samples: 28601860. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-12 05:33:05,202][77203] Avg episode reward: [(0, '49.630'), (1, '46.480')] -[2023-10-12 05:33:05,275][78091] Updated weights for policy 0, policy_version 55990 (0.0009) -[2023-10-12 05:33:05,635][78091] Updated weights for policy 0, policy_version 56000 (0.0007) -[2023-10-12 05:33:06,752][78123] Updated weights for policy 1, policy_version 55720 (0.0009) -[2023-10-12 05:33:07,119][78123] Updated weights for policy 1, policy_version 55730 (0.0010) -[2023-10-12 05:33:07,484][78123] Updated weights for policy 1, policy_version 55740 (0.0008) -[2023-10-12 05:33:09,940][78091] Updated weights for policy 0, policy_version 56010 (0.0009) -[2023-10-12 05:33:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 114425856. Throughput: 0: 1610.8, 1: 1599.7. Samples: 28621406. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-12 05:33:10,201][77203] Avg episode reward: [(0, '40.780'), (1, '46.400')] -[2023-10-12 05:33:10,209][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000055744_57081856.pth... -[2023-10-12 05:33:10,239][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000054272_55574528.pth -[2023-10-12 05:33:10,306][78091] Updated weights for policy 0, policy_version 56020 (0.0009) -[2023-10-12 05:33:10,676][78091] Updated weights for policy 0, policy_version 56030 (0.0008) -[2023-10-12 05:33:10,750][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000056032_57376768.pth... -[2023-10-12 05:33:10,778][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000054528_55836672.pth -[2023-10-12 05:33:11,835][78123] Updated weights for policy 1, policy_version 55750 (0.0007) -[2023-10-12 05:33:12,190][78123] Updated weights for policy 1, policy_version 55760 (0.0008) -[2023-10-12 05:33:12,559][78123] Updated weights for policy 1, policy_version 55770 (0.0008) -[2023-10-12 05:33:14,963][78091] Updated weights for policy 0, policy_version 56040 (0.0009) -[2023-10-12 05:33:15,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 114491392. Throughput: 0: 1585.0, 1: 1606.0. Samples: 28630504. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-12 05:33:15,201][77203] Avg episode reward: [(0, '43.320'), (1, '49.740')] -[2023-10-12 05:33:15,329][78091] Updated weights for policy 0, policy_version 56050 (0.0007) -[2023-10-12 05:33:15,703][78091] Updated weights for policy 0, policy_version 56060 (0.0007) -[2023-10-12 05:33:16,681][78123] Updated weights for policy 1, policy_version 55780 (0.0009) -[2023-10-12 05:33:17,045][78123] Updated weights for policy 1, policy_version 55790 (0.0010) -[2023-10-12 05:33:17,413][78123] Updated weights for policy 1, policy_version 55800 (0.0012) -[2023-10-12 05:33:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 114556928. Throughput: 0: 1584.2, 1: 1602.8. Samples: 28649720. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-12 05:33:20,201][77203] Avg episode reward: [(0, '49.680'), (1, '50.570')] -[2023-10-12 05:33:20,244][78091] Updated weights for policy 0, policy_version 56070 (0.0010) -[2023-10-12 05:33:20,614][78091] Updated weights for policy 0, policy_version 56080 (0.0011) -[2023-10-12 05:33:20,986][78091] Updated weights for policy 0, policy_version 56090 (0.0011) -[2023-10-12 05:33:21,929][78123] Updated weights for policy 1, policy_version 55810 (0.0010) -[2023-10-12 05:33:22,300][78123] Updated weights for policy 1, policy_version 55820 (0.0009) -[2023-10-12 05:33:22,662][78123] Updated weights for policy 1, policy_version 55830 (0.0010) -[2023-10-12 05:33:23,027][78123] Updated weights for policy 1, policy_version 55840 (0.0009) -[2023-10-12 05:33:25,130][78091] Updated weights for policy 0, policy_version 56100 (0.0008) -[2023-10-12 05:33:25,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 114622464. Throughput: 0: 1604.4, 1: 1602.8. Samples: 28669264. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-12 05:33:25,202][77203] Avg episode reward: [(0, '54.420'), (1, '42.330')] -[2023-10-12 05:33:25,497][78091] Updated weights for policy 0, policy_version 56110 (0.0009) -[2023-10-12 05:33:25,878][78091] Updated weights for policy 0, policy_version 56120 (0.0011) -[2023-10-12 05:33:27,349][78123] Updated weights for policy 1, policy_version 55850 (0.0007) -[2023-10-12 05:33:27,713][78123] Updated weights for policy 1, policy_version 55860 (0.0007) -[2023-10-12 05:33:28,079][78123] Updated weights for policy 1, policy_version 55870 (0.0007) -[2023-10-12 05:33:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 114688000. Throughput: 0: 1583.5, 1: 1611.6. Samples: 28678314. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-12 05:33:30,201][77203] Avg episode reward: [(0, '51.030'), (1, '47.540')] -[2023-10-12 05:33:30,259][78091] Updated weights for policy 0, policy_version 56130 (0.0008) -[2023-10-12 05:33:30,633][78091] Updated weights for policy 0, policy_version 56140 (0.0008) -[2023-10-12 05:33:31,010][78091] Updated weights for policy 0, policy_version 56150 (0.0008) -[2023-10-12 05:33:31,376][78091] Updated weights for policy 0, policy_version 56160 (0.0009) -[2023-10-12 05:33:32,381][78123] Updated weights for policy 1, policy_version 55880 (0.0008) -[2023-10-12 05:33:32,757][78123] Updated weights for policy 1, policy_version 55890 (0.0007) -[2023-10-12 05:33:33,129][78123] Updated weights for policy 1, policy_version 55900 (0.0009) -[2023-10-12 05:33:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 114753536. Throughput: 0: 1593.1, 1: 1603.8. Samples: 28697702. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:33:35,202][77203] Avg episode reward: [(0, '49.600'), (1, '47.050')] -[2023-10-12 05:33:35,656][78091] Updated weights for policy 0, policy_version 56170 (0.0007) -[2023-10-12 05:33:36,023][78091] Updated weights for policy 0, policy_version 56180 (0.0007) -[2023-10-12 05:33:36,403][78091] Updated weights for policy 0, policy_version 56190 (0.0007) -[2023-10-12 05:33:37,405][78123] Updated weights for policy 1, policy_version 55910 (0.0008) -[2023-10-12 05:33:37,765][78123] Updated weights for policy 1, policy_version 55920 (0.0008) -[2023-10-12 05:33:38,135][78123] Updated weights for policy 1, policy_version 55930 (0.0008) -[2023-10-12 05:33:40,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 114819072. Throughput: 0: 1612.0, 1: 1600.6. Samples: 28717398. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:33:40,202][77203] Avg episode reward: [(0, '47.780'), (1, '42.940')] -[2023-10-12 05:33:40,711][78091] Updated weights for policy 0, policy_version 56200 (0.0009) -[2023-10-12 05:33:41,079][78091] Updated weights for policy 0, policy_version 56210 (0.0010) -[2023-10-12 05:33:41,451][78091] Updated weights for policy 0, policy_version 56220 (0.0007) -[2023-10-12 05:33:42,436][78123] Updated weights for policy 1, policy_version 55940 (0.0009) -[2023-10-12 05:33:42,826][78123] Updated weights for policy 1, policy_version 55950 (0.0007) -[2023-10-12 05:33:43,199][78123] Updated weights for policy 1, policy_version 55960 (0.0009) -[2023-10-12 05:33:45,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 114884608. Throughput: 0: 1593.3, 1: 1614.4. Samples: 28726550. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:33:45,201][77203] Avg episode reward: [(0, '50.410'), (1, '40.240')] -[2023-10-12 05:33:45,792][78091] Updated weights for policy 0, policy_version 56230 (0.0008) -[2023-10-12 05:33:46,152][78091] Updated weights for policy 0, policy_version 56240 (0.0009) -[2023-10-12 05:33:46,525][78091] Updated weights for policy 0, policy_version 56250 (0.0010) -[2023-10-12 05:33:47,520][78123] Updated weights for policy 1, policy_version 55970 (0.0009) -[2023-10-12 05:33:47,883][78123] Updated weights for policy 1, policy_version 55980 (0.0010) -[2023-10-12 05:33:48,242][78123] Updated weights for policy 1, policy_version 55990 (0.0010) -[2023-10-12 05:33:48,606][78123] Updated weights for policy 1, policy_version 56000 (0.0008) -[2023-10-12 05:33:50,201][77203] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 114950144. Throughput: 0: 1599.0, 1: 1595.5. Samples: 28745612. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:33:50,201][77203] Avg episode reward: [(0, '44.920'), (1, '41.660')] -[2023-10-12 05:33:50,758][78091] Updated weights for policy 0, policy_version 56260 (0.0009) -[2023-10-12 05:33:51,129][78091] Updated weights for policy 0, policy_version 56270 (0.0007) -[2023-10-12 05:33:51,495][78091] Updated weights for policy 0, policy_version 56280 (0.0008) -[2023-10-12 05:33:52,902][78123] Updated weights for policy 1, policy_version 56010 (0.0007) -[2023-10-12 05:33:53,279][78123] Updated weights for policy 1, policy_version 56020 (0.0011) -[2023-10-12 05:33:53,657][78123] Updated weights for policy 1, policy_version 56030 (0.0009) -[2023-10-12 05:33:55,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 115015680. Throughput: 0: 1601.8, 1: 1596.8. Samples: 28765346. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:33:55,201][77203] Avg episode reward: [(0, '49.900'), (1, '47.650')] -[2023-10-12 05:33:55,742][78091] Updated weights for policy 0, policy_version 56290 (0.0008) -[2023-10-12 05:33:56,111][78091] Updated weights for policy 0, policy_version 56300 (0.0009) -[2023-10-12 05:33:56,488][78091] Updated weights for policy 0, policy_version 56310 (0.0009) -[2023-10-12 05:33:56,864][78091] Updated weights for policy 0, policy_version 56320 (0.0007) -[2023-10-12 05:33:57,979][78123] Updated weights for policy 1, policy_version 56040 (0.0008) -[2023-10-12 05:33:58,352][78123] Updated weights for policy 1, policy_version 56050 (0.0010) -[2023-10-12 05:33:58,725][78123] Updated weights for policy 1, policy_version 56060 (0.0009) -[2023-10-12 05:34:00,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 115081216. Throughput: 0: 1598.0, 1: 1615.7. Samples: 28775120. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:34:00,202][77203] Avg episode reward: [(0, '47.600'), (1, '50.520')] -[2023-10-12 05:34:01,000][78091] Updated weights for policy 0, policy_version 56330 (0.0008) -[2023-10-12 05:34:01,373][78091] Updated weights for policy 0, policy_version 56340 (0.0009) -[2023-10-12 05:34:01,747][78091] Updated weights for policy 0, policy_version 56350 (0.0008) -[2023-10-12 05:34:03,186][78123] Updated weights for policy 1, policy_version 56070 (0.0008) -[2023-10-12 05:34:03,557][78123] Updated weights for policy 1, policy_version 56080 (0.0007) -[2023-10-12 05:34:03,920][78123] Updated weights for policy 1, policy_version 56090 (0.0009) -[2023-10-12 05:34:05,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 115146752. Throughput: 0: 1608.6, 1: 1597.5. Samples: 28793992. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:34:05,202][77203] Avg episode reward: [(0, '52.350'), (1, '45.840')] -[2023-10-12 05:34:06,168][78091] Updated weights for policy 0, policy_version 56360 (0.0009) -[2023-10-12 05:34:06,533][78091] Updated weights for policy 0, policy_version 56370 (0.0008) -[2023-10-12 05:34:06,907][78091] Updated weights for policy 0, policy_version 56380 (0.0007) -[2023-10-12 05:34:08,148][78123] Updated weights for policy 1, policy_version 56100 (0.0009) -[2023-10-12 05:34:08,511][78123] Updated weights for policy 1, policy_version 56110 (0.0008) -[2023-10-12 05:34:08,886][78123] Updated weights for policy 1, policy_version 56120 (0.0009) -[2023-10-12 05:34:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 115212288. Throughput: 0: 1604.0, 1: 1592.4. Samples: 28813100. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:34:10,201][77203] Avg episode reward: [(0, '47.820'), (1, '45.610')] -[2023-10-12 05:34:11,192][78091] Updated weights for policy 0, policy_version 56390 (0.0010) -[2023-10-12 05:34:11,559][78091] Updated weights for policy 0, policy_version 56400 (0.0008) -[2023-10-12 05:34:11,928][78091] Updated weights for policy 0, policy_version 56410 (0.0008) -[2023-10-12 05:34:13,192][78123] Updated weights for policy 1, policy_version 56130 (0.0010) -[2023-10-12 05:34:13,563][78123] Updated weights for policy 1, policy_version 56140 (0.0009) -[2023-10-12 05:34:13,936][78123] Updated weights for policy 1, policy_version 56150 (0.0008) -[2023-10-12 05:34:14,295][78123] Updated weights for policy 1, policy_version 56160 (0.0010) -[2023-10-12 05:34:15,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 12885.0). Total num frames: 115277824. Throughput: 0: 1605.7, 1: 1609.7. Samples: 28823008. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-10-12 05:34:15,203][77203] Avg episode reward: [(0, '49.890'), (1, '51.220')] -[2023-10-12 05:34:16,251][78091] Updated weights for policy 0, policy_version 56420 (0.0008) -[2023-10-12 05:34:16,624][78091] Updated weights for policy 0, policy_version 56430 (0.0008) -[2023-10-12 05:34:16,992][78091] Updated weights for policy 0, policy_version 56440 (0.0009) -[2023-10-12 05:34:18,668][78123] Updated weights for policy 1, policy_version 56170 (0.0009) -[2023-10-12 05:34:19,033][78123] Updated weights for policy 1, policy_version 56180 (0.0009) -[2023-10-12 05:34:19,401][78123] Updated weights for policy 1, policy_version 56190 (0.0009) -[2023-10-12 05:34:20,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 115343360. Throughput: 0: 1602.8, 1: 1608.4. Samples: 28842204. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-10-12 05:34:20,201][77203] Avg episode reward: [(0, '54.880'), (1, '47.050')] -[2023-10-12 05:34:21,385][78091] Updated weights for policy 0, policy_version 56450 (0.0007) -[2023-10-12 05:34:21,747][78091] Updated weights for policy 0, policy_version 56460 (0.0008) -[2023-10-12 05:34:22,122][78091] Updated weights for policy 0, policy_version 56470 (0.0007) -[2023-10-12 05:34:22,501][78091] Updated weights for policy 0, policy_version 56480 (0.0007) -[2023-10-12 05:34:23,839][78123] Updated weights for policy 1, policy_version 56200 (0.0010) -[2023-10-12 05:34:24,209][78123] Updated weights for policy 1, policy_version 56210 (0.0007) -[2023-10-12 05:34:24,567][78123] Updated weights for policy 1, policy_version 56220 (0.0010) -[2023-10-12 05:34:25,201][77203] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 115408896. Throughput: 0: 1597.1, 1: 1589.5. Samples: 28860796. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-10-12 05:34:25,201][77203] Avg episode reward: [(0, '48.950'), (1, '50.820')] -[2023-10-12 05:34:26,803][78091] Updated weights for policy 0, policy_version 56490 (0.0010) -[2023-10-12 05:34:27,169][78091] Updated weights for policy 0, policy_version 56500 (0.0010) -[2023-10-12 05:34:27,535][78091] Updated weights for policy 0, policy_version 56510 (0.0009) -[2023-10-12 05:34:28,907][78123] Updated weights for policy 1, policy_version 56230 (0.0011) -[2023-10-12 05:34:29,281][78123] Updated weights for policy 1, policy_version 56240 (0.0011) -[2023-10-12 05:34:29,645][78123] Updated weights for policy 1, policy_version 56250 (0.0007) -[2023-10-12 05:34:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 115474432. Throughput: 0: 1600.7, 1: 1596.2. Samples: 28870408. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-10-12 05:34:30,201][77203] Avg episode reward: [(0, '43.610'), (1, '44.650')] -[2023-10-12 05:34:31,755][78091] Updated weights for policy 0, policy_version 56520 (0.0008) -[2023-10-12 05:34:32,132][78091] Updated weights for policy 0, policy_version 56530 (0.0009) -[2023-10-12 05:34:32,499][78091] Updated weights for policy 0, policy_version 56540 (0.0009) -[2023-10-12 05:34:33,920][78123] Updated weights for policy 1, policy_version 56260 (0.0010) -[2023-10-12 05:34:34,282][78123] Updated weights for policy 1, policy_version 56270 (0.0009) -[2023-10-12 05:34:34,659][78123] Updated weights for policy 1, policy_version 56280 (0.0009) -[2023-10-12 05:34:35,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 115539968. Throughput: 0: 1599.8, 1: 1618.3. Samples: 28890428. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-10-12 05:34:35,202][77203] Avg episode reward: [(0, '45.770'), (1, '43.270')] -[2023-10-12 05:34:36,799][78091] Updated weights for policy 0, policy_version 56550 (0.0008) -[2023-10-12 05:34:37,172][78091] Updated weights for policy 0, policy_version 56560 (0.0009) -[2023-10-12 05:34:37,550][78091] Updated weights for policy 0, policy_version 56570 (0.0009) -[2023-10-12 05:34:38,693][78123] Updated weights for policy 1, policy_version 56290 (0.0009) -[2023-10-12 05:34:39,051][78123] Updated weights for policy 1, policy_version 56300 (0.0008) -[2023-10-12 05:34:39,425][78123] Updated weights for policy 1, policy_version 56310 (0.0007) -[2023-10-12 05:34:39,788][78123] Updated weights for policy 1, policy_version 56320 (0.0008) -[2023-10-12 05:34:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 12885.0). Total num frames: 115605504. Throughput: 0: 1598.3, 1: 1594.1. Samples: 28909004. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-10-12 05:34:40,201][77203] Avg episode reward: [(0, '49.080'), (1, '41.460')] -[2023-10-12 05:34:41,781][78091] Updated weights for policy 0, policy_version 56580 (0.0009) -[2023-10-12 05:34:42,155][78091] Updated weights for policy 0, policy_version 56590 (0.0008) -[2023-10-12 05:34:42,536][78091] Updated weights for policy 0, policy_version 56600 (0.0009) -[2023-10-12 05:34:44,173][78123] Updated weights for policy 1, policy_version 56330 (0.0008) -[2023-10-12 05:34:44,535][78123] Updated weights for policy 1, policy_version 56340 (0.0007) -[2023-10-12 05:34:44,899][78123] Updated weights for policy 1, policy_version 56350 (0.0007) -[2023-10-12 05:34:45,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 115671040. Throughput: 0: 1600.4, 1: 1590.2. Samples: 28918696. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-10-12 05:34:45,201][77203] Avg episode reward: [(0, '48.620'), (1, '42.250')] -[2023-10-12 05:34:46,916][78091] Updated weights for policy 0, policy_version 56610 (0.0009) -[2023-10-12 05:34:47,288][78091] Updated weights for policy 0, policy_version 56620 (0.0008) -[2023-10-12 05:34:47,657][78091] Updated weights for policy 0, policy_version 56630 (0.0010) -[2023-10-12 05:34:48,023][78091] Updated weights for policy 0, policy_version 56640 (0.0010) -[2023-10-12 05:34:49,255][78123] Updated weights for policy 1, policy_version 56360 (0.0009) -[2023-10-12 05:34:49,615][78123] Updated weights for policy 1, policy_version 56370 (0.0011) -[2023-10-12 05:34:49,982][78123] Updated weights for policy 1, policy_version 56380 (0.0010) -[2023-10-12 05:34:50,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 115736576. Throughput: 0: 1591.2, 1: 1610.0. Samples: 28938048. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-10-12 05:34:50,201][77203] Avg episode reward: [(0, '44.350'), (1, '39.740')] -[2023-10-12 05:34:52,446][78091] Updated weights for policy 0, policy_version 56650 (0.0008) -[2023-10-12 05:34:52,813][78091] Updated weights for policy 0, policy_version 56660 (0.0009) -[2023-10-12 05:34:53,189][78091] Updated weights for policy 0, policy_version 56670 (0.0008) -[2023-10-12 05:34:54,144][78123] Updated weights for policy 1, policy_version 56390 (0.0009) -[2023-10-12 05:34:54,521][78123] Updated weights for policy 1, policy_version 56400 (0.0010) -[2023-10-12 05:34:54,901][78123] Updated weights for policy 1, policy_version 56410 (0.0011) -[2023-10-12 05:34:55,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 12885.0). Total num frames: 115802112. Throughput: 0: 1589.9, 1: 1602.7. Samples: 28956768. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-12 05:34:55,202][77203] Avg episode reward: [(0, '46.190'), (1, '40.820')] -[2023-10-12 05:34:57,507][78091] Updated weights for policy 0, policy_version 56680 (0.0007) -[2023-10-12 05:34:57,885][78091] Updated weights for policy 0, policy_version 56690 (0.0007) -[2023-10-12 05:34:58,248][78091] Updated weights for policy 0, policy_version 56700 (0.0010) -[2023-10-12 05:34:59,330][78123] Updated weights for policy 1, policy_version 56420 (0.0010) -[2023-10-12 05:34:59,692][78123] Updated weights for policy 1, policy_version 56430 (0.0007) -[2023-10-12 05:35:00,062][78123] Updated weights for policy 1, policy_version 56440 (0.0008) -[2023-10-12 05:35:00,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 115834880. Throughput: 0: 1599.4, 1: 1592.5. Samples: 28966646. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-12 05:35:00,201][77203] Avg episode reward: [(0, '53.400'), (1, '48.370')] -[2023-10-12 05:35:02,596][78091] Updated weights for policy 0, policy_version 56710 (0.0010) -[2023-10-12 05:35:02,967][78091] Updated weights for policy 0, policy_version 56720 (0.0009) -[2023-10-12 05:35:03,349][78091] Updated weights for policy 0, policy_version 56730 (0.0009) -[2023-10-12 05:35:04,419][78123] Updated weights for policy 1, policy_version 56450 (0.0008) -[2023-10-12 05:35:04,777][78123] Updated weights for policy 1, policy_version 56460 (0.0007) -[2023-10-12 05:35:05,148][78123] Updated weights for policy 1, policy_version 56470 (0.0007) -[2023-10-12 05:35:05,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 115900416. Throughput: 0: 1581.4, 1: 1599.2. Samples: 28985330. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-12 05:35:05,202][77203] Avg episode reward: [(0, '55.690'), (1, '46.530')] -[2023-10-12 05:35:05,519][78123] Updated weights for policy 1, policy_version 56480 (0.0007) -[2023-10-12 05:35:07,726][78091] Updated weights for policy 0, policy_version 56740 (0.0010) -[2023-10-12 05:35:08,102][78091] Updated weights for policy 0, policy_version 56750 (0.0007) -[2023-10-12 05:35:08,473][78091] Updated weights for policy 0, policy_version 56760 (0.0008) -[2023-10-12 05:35:09,755][78123] Updated weights for policy 1, policy_version 56490 (0.0011) -[2023-10-12 05:35:10,127][78123] Updated weights for policy 1, policy_version 56500 (0.0007) -[2023-10-12 05:35:10,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 115965952. Throughput: 0: 1586.2, 1: 1614.1. Samples: 29004812. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-12 05:35:10,202][77203] Avg episode reward: [(0, '46.780'), (1, '47.590')] -[2023-10-12 05:35:10,211][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000056768_58130432.pth... -[2023-10-12 05:35:10,243][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000055264_56590336.pth -[2023-10-12 05:35:10,488][78123] Updated weights for policy 1, policy_version 56510 (0.0008) -[2023-10-12 05:35:10,561][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000056512_57868288.pth... -[2023-10-12 05:35:10,602][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000055008_56328192.pth -[2023-10-12 05:35:12,704][78091] Updated weights for policy 0, policy_version 56770 (0.0009) -[2023-10-12 05:35:13,081][78091] Updated weights for policy 0, policy_version 56780 (0.0007) -[2023-10-12 05:35:13,461][78091] Updated weights for policy 0, policy_version 56790 (0.0008) -[2023-10-12 05:35:13,837][78091] Updated weights for policy 0, policy_version 56800 (0.0009) -[2023-10-12 05:35:14,998][78123] Updated weights for policy 1, policy_version 56520 (0.0007) -[2023-10-12 05:35:15,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 116031488. Throughput: 0: 1608.8, 1: 1600.0. Samples: 29014806. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-12 05:35:15,201][77203] Avg episode reward: [(0, '45.250'), (1, '46.240')] -[2023-10-12 05:35:15,378][78123] Updated weights for policy 1, policy_version 56530 (0.0008) -[2023-10-12 05:35:15,757][78123] Updated weights for policy 1, policy_version 56540 (0.0009) -[2023-10-12 05:35:18,103][78091] Updated weights for policy 0, policy_version 56810 (0.0008) -[2023-10-12 05:35:18,466][78091] Updated weights for policy 0, policy_version 56820 (0.0007) -[2023-10-12 05:35:18,834][78091] Updated weights for policy 0, policy_version 56830 (0.0008) -[2023-10-12 05:35:20,097][78123] Updated weights for policy 1, policy_version 56550 (0.0008) -[2023-10-12 05:35:20,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 116097024. Throughput: 0: 1585.8, 1: 1588.9. Samples: 29033290. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-12 05:35:20,201][77203] Avg episode reward: [(0, '49.470'), (1, '53.070')] -[2023-10-12 05:35:20,467][78123] Updated weights for policy 1, policy_version 56560 (0.0009) -[2023-10-12 05:35:20,843][78123] Updated weights for policy 1, policy_version 56570 (0.0009) -[2023-10-12 05:35:23,122][78091] Updated weights for policy 0, policy_version 56840 (0.0009) -[2023-10-12 05:35:23,495][78091] Updated weights for policy 0, policy_version 56850 (0.0009) -[2023-10-12 05:35:23,877][78091] Updated weights for policy 0, policy_version 56860 (0.0008) -[2023-10-12 05:35:24,977][78123] Updated weights for policy 1, policy_version 56580 (0.0009) -[2023-10-12 05:35:25,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 116162560. Throughput: 0: 1586.8, 1: 1613.0. Samples: 29052994. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-12 05:35:25,202][77203] Avg episode reward: [(0, '61.610'), (1, '43.770')] -[2023-10-12 05:35:25,212][77792] Saving new best policy, reward=61.610! -[2023-10-12 05:35:25,362][78123] Updated weights for policy 1, policy_version 56590 (0.0009) -[2023-10-12 05:35:25,719][78123] Updated weights for policy 1, policy_version 56600 (0.0009) -[2023-10-12 05:35:28,086][78091] Updated weights for policy 0, policy_version 56870 (0.0010) -[2023-10-12 05:35:28,468][78091] Updated weights for policy 0, policy_version 56880 (0.0009) -[2023-10-12 05:35:28,832][78091] Updated weights for policy 0, policy_version 56890 (0.0009) -[2023-10-12 05:35:30,103][78123] Updated weights for policy 1, policy_version 56610 (0.0010) -[2023-10-12 05:35:30,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 116228096. Throughput: 0: 1612.2, 1: 1590.2. Samples: 29062806. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-12 05:35:30,202][77203] Avg episode reward: [(0, '54.400'), (1, '46.090')] -[2023-10-12 05:35:30,467][78123] Updated weights for policy 1, policy_version 56620 (0.0007) -[2023-10-12 05:35:30,835][78123] Updated weights for policy 1, policy_version 56630 (0.0007) -[2023-10-12 05:35:31,207][78123] Updated weights for policy 1, policy_version 56640 (0.0007) -[2023-10-12 05:35:33,324][78091] Updated weights for policy 0, policy_version 56900 (0.0009) -[2023-10-12 05:35:33,698][78091] Updated weights for policy 0, policy_version 56910 (0.0007) -[2023-10-12 05:35:34,065][78091] Updated weights for policy 0, policy_version 56920 (0.0009) -[2023-10-12 05:35:35,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 116293632. Throughput: 0: 1600.7, 1: 1590.5. Samples: 29081654. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-12 05:35:35,202][77203] Avg episode reward: [(0, '49.760'), (1, '47.470')] -[2023-10-12 05:35:35,481][78123] Updated weights for policy 1, policy_version 56650 (0.0009) -[2023-10-12 05:35:35,839][78123] Updated weights for policy 1, policy_version 56660 (0.0008) -[2023-10-12 05:35:36,211][78123] Updated weights for policy 1, policy_version 56670 (0.0009) -[2023-10-12 05:35:38,436][78091] Updated weights for policy 0, policy_version 56930 (0.0010) -[2023-10-12 05:35:38,848][78091] Updated weights for policy 0, policy_version 56940 (0.0009) -[2023-10-12 05:35:39,216][78091] Updated weights for policy 0, policy_version 56950 (0.0010) -[2023-10-12 05:35:39,588][78091] Updated weights for policy 0, policy_version 56960 (0.0010) -[2023-10-12 05:35:40,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 116359168. Throughput: 0: 1589.7, 1: 1604.7. Samples: 29100512. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-12 05:35:40,201][77203] Avg episode reward: [(0, '45.300'), (1, '46.640')] -[2023-10-12 05:35:40,569][78123] Updated weights for policy 1, policy_version 56680 (0.0009) -[2023-10-12 05:35:40,939][78123] Updated weights for policy 1, policy_version 56690 (0.0009) -[2023-10-12 05:35:41,308][78123] Updated weights for policy 1, policy_version 56700 (0.0008) -[2023-10-12 05:35:43,859][78091] Updated weights for policy 0, policy_version 56970 (0.0009) -[2023-10-12 05:35:44,222][78091] Updated weights for policy 0, policy_version 56980 (0.0009) -[2023-10-12 05:35:44,600][78091] Updated weights for policy 0, policy_version 56990 (0.0009) -[2023-10-12 05:35:45,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 116424704. Throughput: 0: 1605.5, 1: 1589.6. Samples: 29110424. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-12 05:35:45,202][77203] Avg episode reward: [(0, '55.130'), (1, '43.480')] -[2023-10-12 05:35:45,746][78123] Updated weights for policy 1, policy_version 56710 (0.0007) -[2023-10-12 05:35:46,112][78123] Updated weights for policy 1, policy_version 56720 (0.0007) -[2023-10-12 05:35:46,479][78123] Updated weights for policy 1, policy_version 56730 (0.0007) -[2023-10-12 05:35:48,876][78091] Updated weights for policy 0, policy_version 57000 (0.0009) -[2023-10-12 05:35:49,247][78091] Updated weights for policy 0, policy_version 57010 (0.0007) -[2023-10-12 05:35:49,626][78091] Updated weights for policy 0, policy_version 57020 (0.0008) -[2023-10-12 05:35:50,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 116490240. Throughput: 0: 1616.7, 1: 1591.1. Samples: 29129680. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-12 05:35:50,202][77203] Avg episode reward: [(0, '55.860'), (1, '45.360')] -[2023-10-12 05:35:50,964][78123] Updated weights for policy 1, policy_version 56740 (0.0009) -[2023-10-12 05:35:51,335][78123] Updated weights for policy 1, policy_version 56750 (0.0009) -[2023-10-12 05:35:51,704][78123] Updated weights for policy 1, policy_version 56760 (0.0008) -[2023-10-12 05:35:53,667][78091] Updated weights for policy 0, policy_version 57030 (0.0008) -[2023-10-12 05:35:54,045][78091] Updated weights for policy 0, policy_version 57040 (0.0008) -[2023-10-12 05:35:54,415][78091] Updated weights for policy 0, policy_version 57050 (0.0011) -[2023-10-12 05:35:55,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 116555776. Throughput: 0: 1594.0, 1: 1594.4. Samples: 29148292. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-12 05:35:55,202][77203] Avg episode reward: [(0, '45.270'), (1, '46.760')] -[2023-10-12 05:35:55,888][78123] Updated weights for policy 1, policy_version 56770 (0.0008) -[2023-10-12 05:35:56,259][78123] Updated weights for policy 1, policy_version 56780 (0.0007) -[2023-10-12 05:35:56,633][78123] Updated weights for policy 1, policy_version 56790 (0.0008) -[2023-10-12 05:35:57,002][78123] Updated weights for policy 1, policy_version 56800 (0.0008) -[2023-10-12 05:35:58,675][78091] Updated weights for policy 0, policy_version 57060 (0.0010) -[2023-10-12 05:35:59,038][78091] Updated weights for policy 0, policy_version 57070 (0.0008) -[2023-10-12 05:35:59,417][78091] Updated weights for policy 0, policy_version 57080 (0.0010) -[2023-10-12 05:36:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 116621312. Throughput: 0: 1598.7, 1: 1587.7. Samples: 29158194. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-12 05:36:00,202][77203] Avg episode reward: [(0, '50.410'), (1, '45.660')] -[2023-10-12 05:36:01,411][78123] Updated weights for policy 1, policy_version 56810 (0.0009) -[2023-10-12 05:36:01,784][78123] Updated weights for policy 1, policy_version 56820 (0.0010) -[2023-10-12 05:36:02,144][78123] Updated weights for policy 1, policy_version 56830 (0.0008) -[2023-10-12 05:36:03,836][78091] Updated weights for policy 0, policy_version 57090 (0.0010) -[2023-10-12 05:36:04,202][78091] Updated weights for policy 0, policy_version 57100 (0.0009) -[2023-10-12 05:36:04,567][78091] Updated weights for policy 0, policy_version 57110 (0.0009) -[2023-10-12 05:36:04,945][78091] Updated weights for policy 0, policy_version 57120 (0.0009) -[2023-10-12 05:36:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 116686848. Throughput: 0: 1615.7, 1: 1590.8. Samples: 29177584. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-12 05:36:05,202][77203] Avg episode reward: [(0, '48.980'), (1, '44.180')] -[2023-10-12 05:36:06,447][78123] Updated weights for policy 1, policy_version 56840 (0.0009) -[2023-10-12 05:36:06,807][78123] Updated weights for policy 1, policy_version 56850 (0.0009) -[2023-10-12 05:36:07,193][78123] Updated weights for policy 1, policy_version 56860 (0.0008) -[2023-10-12 05:36:09,221][78091] Updated weights for policy 0, policy_version 57130 (0.0011) -[2023-10-12 05:36:09,587][78091] Updated weights for policy 0, policy_version 57140 (0.0011) -[2023-10-12 05:36:09,957][78091] Updated weights for policy 0, policy_version 57150 (0.0010) -[2023-10-12 05:36:10,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 116752384. Throughput: 0: 1598.5, 1: 1583.9. Samples: 29196202. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-12 05:36:10,201][77203] Avg episode reward: [(0, '55.810'), (1, '46.980')] -[2023-10-12 05:36:11,702][78123] Updated weights for policy 1, policy_version 56870 (0.0008) -[2023-10-12 05:36:12,064][78123] Updated weights for policy 1, policy_version 56880 (0.0009) -[2023-10-12 05:36:12,430][78123] Updated weights for policy 1, policy_version 56890 (0.0009) -[2023-10-12 05:36:14,337][78091] Updated weights for policy 0, policy_version 57160 (0.0008) -[2023-10-12 05:36:14,705][78091] Updated weights for policy 0, policy_version 57170 (0.0007) -[2023-10-12 05:36:15,074][78091] Updated weights for policy 0, policy_version 57180 (0.0010) -[2023-10-12 05:36:15,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 116785152. Throughput: 0: 1590.3, 1: 1584.6. Samples: 29205676. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-12 05:36:15,202][77203] Avg episode reward: [(0, '51.330'), (1, '44.320')] -[2023-10-12 05:36:16,651][78123] Updated weights for policy 1, policy_version 56900 (0.0007) -[2023-10-12 05:36:17,025][78123] Updated weights for policy 1, policy_version 56910 (0.0007) -[2023-10-12 05:36:17,391][78123] Updated weights for policy 1, policy_version 56920 (0.0008) -[2023-10-12 05:36:19,517][78091] Updated weights for policy 0, policy_version 57190 (0.0008) -[2023-10-12 05:36:19,885][78091] Updated weights for policy 0, policy_version 57200 (0.0009) -[2023-10-12 05:36:20,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 116850688. Throughput: 0: 1605.4, 1: 1586.5. Samples: 29225290. Policy #0 lag: (min: 9.0, avg: 16.3, max: 41.0) -[2023-10-12 05:36:20,202][77203] Avg episode reward: [(0, '52.560'), (1, '39.640')] -[2023-10-12 05:36:20,256][78091] Updated weights for policy 0, policy_version 57210 (0.0011) -[2023-10-12 05:36:21,647][78123] Updated weights for policy 1, policy_version 56930 (0.0007) -[2023-10-12 05:36:22,004][78123] Updated weights for policy 1, policy_version 56940 (0.0008) -[2023-10-12 05:36:22,379][78123] Updated weights for policy 1, policy_version 56950 (0.0009) -[2023-10-12 05:36:22,737][78123] Updated weights for policy 1, policy_version 56960 (0.0008) -[2023-10-12 05:36:24,621][78091] Updated weights for policy 0, policy_version 57220 (0.0010) -[2023-10-12 05:36:24,998][78091] Updated weights for policy 0, policy_version 57230 (0.0008) -[2023-10-12 05:36:25,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 116916224. Throughput: 0: 1610.7, 1: 1590.1. Samples: 29244548. Policy #0 lag: (min: 9.0, avg: 16.3, max: 41.0) -[2023-10-12 05:36:25,201][77203] Avg episode reward: [(0, '54.330'), (1, '44.330')] -[2023-10-12 05:36:25,374][78091] Updated weights for policy 0, policy_version 57240 (0.0007) -[2023-10-12 05:36:26,922][78123] Updated weights for policy 1, policy_version 56970 (0.0009) -[2023-10-12 05:36:27,296][78123] Updated weights for policy 1, policy_version 56980 (0.0009) -[2023-10-12 05:36:27,653][78123] Updated weights for policy 1, policy_version 56990 (0.0009) -[2023-10-12 05:36:29,792][78091] Updated weights for policy 0, policy_version 57250 (0.0007) -[2023-10-12 05:36:30,159][78091] Updated weights for policy 0, policy_version 57260 (0.0008) -[2023-10-12 05:36:30,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 116981760. Throughput: 0: 1590.7, 1: 1589.0. Samples: 29253512. Policy #0 lag: (min: 9.0, avg: 16.3, max: 41.0) -[2023-10-12 05:36:30,201][77203] Avg episode reward: [(0, '54.680'), (1, '45.280')] -[2023-10-12 05:36:30,522][78091] Updated weights for policy 0, policy_version 57270 (0.0010) -[2023-10-12 05:36:30,893][78091] Updated weights for policy 0, policy_version 57280 (0.0009) -[2023-10-12 05:36:31,959][78123] Updated weights for policy 1, policy_version 57000 (0.0007) -[2023-10-12 05:36:32,316][78123] Updated weights for policy 1, policy_version 57010 (0.0008) -[2023-10-12 05:36:32,687][78123] Updated weights for policy 1, policy_version 57020 (0.0010) -[2023-10-12 05:36:35,061][78091] Updated weights for policy 0, policy_version 57290 (0.0010) -[2023-10-12 05:36:35,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 117047296. Throughput: 0: 1597.3, 1: 1589.2. Samples: 29273070. Policy #0 lag: (min: 9.0, avg: 16.3, max: 41.0) -[2023-10-12 05:36:35,202][77203] Avg episode reward: [(0, '54.290'), (1, '50.070')] -[2023-10-12 05:36:35,439][78091] Updated weights for policy 0, policy_version 57300 (0.0010) -[2023-10-12 05:36:35,821][78091] Updated weights for policy 0, policy_version 57310 (0.0009) -[2023-10-12 05:36:37,153][78123] Updated weights for policy 1, policy_version 57030 (0.0010) -[2023-10-12 05:36:37,513][78123] Updated weights for policy 1, policy_version 57040 (0.0010) -[2023-10-12 05:36:37,888][78123] Updated weights for policy 1, policy_version 57050 (0.0009) -[2023-10-12 05:36:39,822][78091] Updated weights for policy 0, policy_version 57320 (0.0008) -[2023-10-12 05:36:40,193][78091] Updated weights for policy 0, policy_version 57330 (0.0010) -[2023-10-12 05:36:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 117112832. Throughput: 0: 1613.5, 1: 1582.7. Samples: 29292120. Policy #0 lag: (min: 9.0, avg: 16.3, max: 41.0) -[2023-10-12 05:36:40,202][77203] Avg episode reward: [(0, '58.540'), (1, '44.100')] -[2023-10-12 05:36:40,570][78091] Updated weights for policy 0, policy_version 57340 (0.0008) -[2023-10-12 05:36:42,347][78123] Updated weights for policy 1, policy_version 57060 (0.0009) -[2023-10-12 05:36:42,715][78123] Updated weights for policy 1, policy_version 57070 (0.0008) -[2023-10-12 05:36:43,094][78123] Updated weights for policy 1, policy_version 57080 (0.0007) -[2023-10-12 05:36:45,061][78091] Updated weights for policy 0, policy_version 57350 (0.0009) -[2023-10-12 05:36:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 117178368. Throughput: 0: 1589.7, 1: 1593.2. Samples: 29301428. Policy #0 lag: (min: 9.0, avg: 16.3, max: 41.0) -[2023-10-12 05:36:45,202][77203] Avg episode reward: [(0, '56.000'), (1, '48.940')] -[2023-10-12 05:36:45,428][78091] Updated weights for policy 0, policy_version 57360 (0.0007) -[2023-10-12 05:36:45,802][78091] Updated weights for policy 0, policy_version 57370 (0.0007) -[2023-10-12 05:36:47,382][78123] Updated weights for policy 1, policy_version 57090 (0.0008) -[2023-10-12 05:36:47,744][78123] Updated weights for policy 1, policy_version 57100 (0.0010) -[2023-10-12 05:36:48,107][78123] Updated weights for policy 1, policy_version 57110 (0.0010) -[2023-10-12 05:36:48,476][78123] Updated weights for policy 1, policy_version 57120 (0.0010) -[2023-10-12 05:36:49,937][78091] Updated weights for policy 0, policy_version 57380 (0.0008) -[2023-10-12 05:36:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 117243904. Throughput: 0: 1593.7, 1: 1581.7. Samples: 29320476. Policy #0 lag: (min: 9.0, avg: 16.3, max: 41.0) -[2023-10-12 05:36:50,201][77203] Avg episode reward: [(0, '46.480'), (1, '53.110')] -[2023-10-12 05:36:50,312][78091] Updated weights for policy 0, policy_version 57390 (0.0009) -[2023-10-12 05:36:50,689][78091] Updated weights for policy 0, policy_version 57400 (0.0008) -[2023-10-12 05:36:52,918][78123] Updated weights for policy 1, policy_version 57130 (0.0008) -[2023-10-12 05:36:53,288][78123] Updated weights for policy 1, policy_version 57140 (0.0007) -[2023-10-12 05:36:53,650][78123] Updated weights for policy 1, policy_version 57150 (0.0007) -[2023-10-12 05:36:55,036][78091] Updated weights for policy 0, policy_version 57410 (0.0009) -[2023-10-12 05:36:55,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 117309440. Throughput: 0: 1612.0, 1: 1581.5. Samples: 29339906. Policy #0 lag: (min: 9.0, avg: 19.2, max: 41.0) -[2023-10-12 05:36:55,201][77203] Avg episode reward: [(0, '49.440'), (1, '47.360')] -[2023-10-12 05:36:55,407][78091] Updated weights for policy 0, policy_version 57420 (0.0008) -[2023-10-12 05:36:55,785][78091] Updated weights for policy 0, policy_version 57430 (0.0008) -[2023-10-12 05:36:56,150][78091] Updated weights for policy 0, policy_version 57440 (0.0007) -[2023-10-12 05:36:58,132][78123] Updated weights for policy 1, policy_version 57160 (0.0009) -[2023-10-12 05:36:58,494][78123] Updated weights for policy 1, policy_version 57170 (0.0008) -[2023-10-12 05:36:58,860][78123] Updated weights for policy 1, policy_version 57180 (0.0010) -[2023-10-12 05:37:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 117374976. Throughput: 0: 1591.9, 1: 1605.3. Samples: 29349552. Policy #0 lag: (min: 9.0, avg: 19.2, max: 41.0) -[2023-10-12 05:37:00,201][77203] Avg episode reward: [(0, '48.700'), (1, '41.740')] -[2023-10-12 05:37:00,664][78091] Updated weights for policy 0, policy_version 57450 (0.0010) -[2023-10-12 05:37:01,035][78091] Updated weights for policy 0, policy_version 57460 (0.0010) -[2023-10-12 05:37:01,412][78091] Updated weights for policy 0, policy_version 57470 (0.0008) -[2023-10-12 05:37:03,180][78123] Updated weights for policy 1, policy_version 57190 (0.0008) -[2023-10-12 05:37:03,543][78123] Updated weights for policy 1, policy_version 57200 (0.0007) -[2023-10-12 05:37:03,916][78123] Updated weights for policy 1, policy_version 57210 (0.0007) -[2023-10-12 05:37:05,201][77203] Fps is (10 sec: 13106.8, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 117440512. Throughput: 0: 1593.7, 1: 1591.5. Samples: 29368628. Policy #0 lag: (min: 9.0, avg: 19.2, max: 41.0) -[2023-10-12 05:37:05,203][77203] Avg episode reward: [(0, '55.500'), (1, '39.610')] -[2023-10-12 05:37:05,704][78091] Updated weights for policy 0, policy_version 57480 (0.0009) -[2023-10-12 05:37:06,082][78091] Updated weights for policy 0, policy_version 57490 (0.0010) -[2023-10-12 05:37:06,461][78091] Updated weights for policy 0, policy_version 57500 (0.0008) -[2023-10-12 05:37:08,302][78123] Updated weights for policy 1, policy_version 57220 (0.0008) -[2023-10-12 05:37:08,669][78123] Updated weights for policy 1, policy_version 57230 (0.0008) -[2023-10-12 05:37:09,030][78123] Updated weights for policy 1, policy_version 57240 (0.0009) -[2023-10-12 05:37:10,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 117506048. Throughput: 0: 1603.0, 1: 1575.3. Samples: 29387570. Policy #0 lag: (min: 9.0, avg: 19.2, max: 41.0) -[2023-10-12 05:37:10,202][77203] Avg episode reward: [(0, '53.170'), (1, '43.690')] -[2023-10-12 05:37:10,212][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000057248_58621952.pth... -[2023-10-12 05:37:10,212][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000057504_58884096.pth... -[2023-10-12 05:37:10,244][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000056032_57376768.pth -[2023-10-12 05:37:10,252][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000055744_57081856.pth -[2023-10-12 05:37:10,775][78091] Updated weights for policy 0, policy_version 57510 (0.0008) -[2023-10-12 05:37:11,152][78091] Updated weights for policy 0, policy_version 57520 (0.0007) -[2023-10-12 05:37:11,517][78091] Updated weights for policy 0, policy_version 57530 (0.0007) -[2023-10-12 05:37:13,346][78123] Updated weights for policy 1, policy_version 57250 (0.0009) -[2023-10-12 05:37:13,708][78123] Updated weights for policy 1, policy_version 57260 (0.0008) -[2023-10-12 05:37:14,078][78123] Updated weights for policy 1, policy_version 57270 (0.0008) -[2023-10-12 05:37:14,434][78123] Updated weights for policy 1, policy_version 57280 (0.0009) -[2023-10-12 05:37:15,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 117571584. Throughput: 0: 1594.1, 1: 1598.2. Samples: 29397164. Policy #0 lag: (min: 9.0, avg: 19.2, max: 41.0) -[2023-10-12 05:37:15,202][77203] Avg episode reward: [(0, '49.300'), (1, '40.260')] -[2023-10-12 05:37:15,846][78091] Updated weights for policy 0, policy_version 57540 (0.0007) -[2023-10-12 05:37:16,214][78091] Updated weights for policy 0, policy_version 57550 (0.0009) -[2023-10-12 05:37:16,575][78091] Updated weights for policy 0, policy_version 57560 (0.0009) -[2023-10-12 05:37:18,716][78123] Updated weights for policy 1, policy_version 57290 (0.0008) -[2023-10-12 05:37:19,086][78123] Updated weights for policy 1, policy_version 57300 (0.0009) -[2023-10-12 05:37:19,457][78123] Updated weights for policy 1, policy_version 57310 (0.0008) -[2023-10-12 05:37:20,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 117637120. Throughput: 0: 1596.7, 1: 1591.2. Samples: 29416524. Policy #0 lag: (min: 9.0, avg: 19.2, max: 41.0) -[2023-10-12 05:37:20,201][77203] Avg episode reward: [(0, '49.510'), (1, '42.640')] -[2023-10-12 05:37:20,837][78091] Updated weights for policy 0, policy_version 57570 (0.0007) -[2023-10-12 05:37:21,215][78091] Updated weights for policy 0, policy_version 57580 (0.0010) -[2023-10-12 05:37:21,587][78091] Updated weights for policy 0, policy_version 57590 (0.0007) -[2023-10-12 05:37:21,970][78091] Updated weights for policy 0, policy_version 57600 (0.0008) -[2023-10-12 05:37:23,969][78123] Updated weights for policy 1, policy_version 57320 (0.0009) -[2023-10-12 05:37:24,339][78123] Updated weights for policy 1, policy_version 57330 (0.0009) -[2023-10-12 05:37:24,704][78123] Updated weights for policy 1, policy_version 57340 (0.0010) -[2023-10-12 05:37:25,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 117702656. Throughput: 0: 1602.0, 1: 1579.9. Samples: 29435308. Policy #0 lag: (min: 9.0, avg: 19.2, max: 41.0) -[2023-10-12 05:37:25,202][77203] Avg episode reward: [(0, '48.950'), (1, '43.590')] -[2023-10-12 05:37:26,122][78091] Updated weights for policy 0, policy_version 57610 (0.0011) -[2023-10-12 05:37:26,497][78091] Updated weights for policy 0, policy_version 57620 (0.0008) -[2023-10-12 05:37:26,868][78091] Updated weights for policy 0, policy_version 57630 (0.0007) -[2023-10-12 05:37:28,983][78123] Updated weights for policy 1, policy_version 57350 (0.0010) -[2023-10-12 05:37:29,355][78123] Updated weights for policy 1, policy_version 57360 (0.0010) -[2023-10-12 05:37:29,719][78123] Updated weights for policy 1, policy_version 57370 (0.0009) -[2023-10-12 05:37:30,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 117768192. Throughput: 0: 1598.5, 1: 1591.2. Samples: 29444966. Policy #0 lag: (min: 15.0, avg: 23.3, max: 47.0) -[2023-10-12 05:37:30,201][77203] Avg episode reward: [(0, '52.090'), (1, '45.740')] -[2023-10-12 05:37:31,240][78091] Updated weights for policy 0, policy_version 57640 (0.0007) -[2023-10-12 05:37:31,606][78091] Updated weights for policy 0, policy_version 57650 (0.0007) -[2023-10-12 05:37:31,976][78091] Updated weights for policy 0, policy_version 57660 (0.0007) -[2023-10-12 05:37:33,852][78123] Updated weights for policy 1, policy_version 57380 (0.0011) -[2023-10-12 05:37:34,224][78123] Updated weights for policy 1, policy_version 57390 (0.0011) -[2023-10-12 05:37:34,596][78123] Updated weights for policy 1, policy_version 57400 (0.0007) -[2023-10-12 05:37:35,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 117833728. Throughput: 0: 1589.7, 1: 1607.4. Samples: 29464346. Policy #0 lag: (min: 15.0, avg: 23.3, max: 47.0) -[2023-10-12 05:37:35,202][77203] Avg episode reward: [(0, '48.420'), (1, '45.560')] -[2023-10-12 05:37:36,385][78091] Updated weights for policy 0, policy_version 57670 (0.0008) -[2023-10-12 05:37:36,752][78091] Updated weights for policy 0, policy_version 57680 (0.0011) -[2023-10-12 05:37:37,126][78091] Updated weights for policy 0, policy_version 57690 (0.0009) -[2023-10-12 05:37:38,947][78123] Updated weights for policy 1, policy_version 57410 (0.0009) -[2023-10-12 05:37:39,339][78123] Updated weights for policy 1, policy_version 57420 (0.0009) -[2023-10-12 05:37:39,707][78123] Updated weights for policy 1, policy_version 57430 (0.0007) -[2023-10-12 05:37:40,069][78123] Updated weights for policy 1, policy_version 57440 (0.0007) -[2023-10-12 05:37:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 117899264. Throughput: 0: 1587.7, 1: 1589.9. Samples: 29482898. Policy #0 lag: (min: 15.0, avg: 23.3, max: 47.0) -[2023-10-12 05:37:40,201][77203] Avg episode reward: [(0, '48.600'), (1, '50.670')] -[2023-10-12 05:37:41,373][78091] Updated weights for policy 0, policy_version 57700 (0.0007) -[2023-10-12 05:37:41,746][78091] Updated weights for policy 0, policy_version 57710 (0.0010) -[2023-10-12 05:37:42,119][78091] Updated weights for policy 0, policy_version 57720 (0.0007) -[2023-10-12 05:37:44,352][78123] Updated weights for policy 1, policy_version 57450 (0.0009) -[2023-10-12 05:37:44,731][78123] Updated weights for policy 1, policy_version 57460 (0.0008) -[2023-10-12 05:37:45,095][78123] Updated weights for policy 1, policy_version 57470 (0.0009) -[2023-10-12 05:37:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 117964800. Throughput: 0: 1587.8, 1: 1585.1. Samples: 29492332. Policy #0 lag: (min: 15.0, avg: 23.3, max: 47.0) -[2023-10-12 05:37:45,202][77203] Avg episode reward: [(0, '48.560'), (1, '47.540')] -[2023-10-12 05:37:46,425][78091] Updated weights for policy 0, policy_version 57730 (0.0008) -[2023-10-12 05:37:46,798][78091] Updated weights for policy 0, policy_version 57740 (0.0008) -[2023-10-12 05:37:47,177][78091] Updated weights for policy 0, policy_version 57750 (0.0007) -[2023-10-12 05:37:47,550][78091] Updated weights for policy 0, policy_version 57760 (0.0009) -[2023-10-12 05:37:49,441][78123] Updated weights for policy 1, policy_version 57480 (0.0008) -[2023-10-12 05:37:49,807][78123] Updated weights for policy 1, policy_version 57490 (0.0008) -[2023-10-12 05:37:50,183][78123] Updated weights for policy 1, policy_version 57500 (0.0009) -[2023-10-12 05:37:50,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 117997568. Throughput: 0: 1587.8, 1: 1597.1. Samples: 29511946. Policy #0 lag: (min: 15.0, avg: 23.3, max: 47.0) -[2023-10-12 05:37:50,202][77203] Avg episode reward: [(0, '52.470'), (1, '48.680')] -[2023-10-12 05:37:51,869][78091] Updated weights for policy 0, policy_version 57770 (0.0008) -[2023-10-12 05:37:52,249][78091] Updated weights for policy 0, policy_version 57780 (0.0007) -[2023-10-12 05:37:52,610][78091] Updated weights for policy 0, policy_version 57790 (0.0010) -[2023-10-12 05:37:54,609][78123] Updated weights for policy 1, policy_version 57510 (0.0007) -[2023-10-12 05:37:54,981][78123] Updated weights for policy 1, policy_version 57520 (0.0008) -[2023-10-12 05:37:55,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 118063104. Throughput: 0: 1584.4, 1: 1604.2. Samples: 29531060. Policy #0 lag: (min: 15.0, avg: 23.3, max: 47.0) -[2023-10-12 05:37:55,201][77203] Avg episode reward: [(0, '48.390'), (1, '49.170')] -[2023-10-12 05:37:55,345][78123] Updated weights for policy 1, policy_version 57530 (0.0009) -[2023-10-12 05:37:57,031][78091] Updated weights for policy 0, policy_version 57800 (0.0010) -[2023-10-12 05:37:57,406][78091] Updated weights for policy 0, policy_version 57810 (0.0010) -[2023-10-12 05:37:57,771][78091] Updated weights for policy 0, policy_version 57820 (0.0011) -[2023-10-12 05:37:59,623][78123] Updated weights for policy 1, policy_version 57540 (0.0009) -[2023-10-12 05:37:59,989][78123] Updated weights for policy 1, policy_version 57550 (0.0010) -[2023-10-12 05:38:00,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 118128640. Throughput: 0: 1589.0, 1: 1588.4. Samples: 29540150. Policy #0 lag: (min: 15.0, avg: 23.3, max: 47.0) -[2023-10-12 05:38:00,202][77203] Avg episode reward: [(0, '47.660'), (1, '43.530')] -[2023-10-12 05:38:00,355][78123] Updated weights for policy 1, policy_version 57560 (0.0008) -[2023-10-12 05:38:02,108][78091] Updated weights for policy 0, policy_version 57830 (0.0009) -[2023-10-12 05:38:02,481][78091] Updated weights for policy 0, policy_version 57840 (0.0007) -[2023-10-12 05:38:02,848][78091] Updated weights for policy 0, policy_version 57850 (0.0007) -[2023-10-12 05:38:04,838][78123] Updated weights for policy 1, policy_version 57570 (0.0007) -[2023-10-12 05:38:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 118194176. Throughput: 0: 1587.6, 1: 1595.2. Samples: 29559750. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-12 05:38:05,201][77203] Avg episode reward: [(0, '49.430'), (1, '44.860')] -[2023-10-12 05:38:05,208][78123] Updated weights for policy 1, policy_version 57580 (0.0008) -[2023-10-12 05:38:05,567][78123] Updated weights for policy 1, policy_version 57590 (0.0008) -[2023-10-12 05:38:05,942][78123] Updated weights for policy 1, policy_version 57600 (0.0008) -[2023-10-12 05:38:06,964][78091] Updated weights for policy 0, policy_version 57860 (0.0007) -[2023-10-12 05:38:07,343][78091] Updated weights for policy 0, policy_version 57870 (0.0007) -[2023-10-12 05:38:07,725][78091] Updated weights for policy 0, policy_version 57880 (0.0007) -[2023-10-12 05:38:10,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 118259712. Throughput: 0: 1584.4, 1: 1610.4. Samples: 29579070. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-12 05:38:10,201][77203] Avg episode reward: [(0, '52.280'), (1, '44.690')] -[2023-10-12 05:38:10,298][78123] Updated weights for policy 1, policy_version 57610 (0.0010) -[2023-10-12 05:38:10,671][78123] Updated weights for policy 1, policy_version 57620 (0.0011) -[2023-10-12 05:38:11,054][78123] Updated weights for policy 1, policy_version 57630 (0.0008) -[2023-10-12 05:38:12,110][78091] Updated weights for policy 0, policy_version 57890 (0.0008) -[2023-10-12 05:38:12,476][78091] Updated weights for policy 0, policy_version 57900 (0.0008) -[2023-10-12 05:38:12,852][78091] Updated weights for policy 0, policy_version 57910 (0.0010) -[2023-10-12 05:38:13,216][78091] Updated weights for policy 0, policy_version 57920 (0.0008) -[2023-10-12 05:38:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 118325248. Throughput: 0: 1597.3, 1: 1585.6. Samples: 29588198. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-12 05:38:15,201][77203] Avg episode reward: [(0, '51.070'), (1, '47.190')] -[2023-10-12 05:38:15,211][78123] Updated weights for policy 1, policy_version 57640 (0.0009) -[2023-10-12 05:38:15,581][78123] Updated weights for policy 1, policy_version 57650 (0.0009) -[2023-10-12 05:38:15,951][78123] Updated weights for policy 1, policy_version 57660 (0.0011) -[2023-10-12 05:38:17,445][78091] Updated weights for policy 0, policy_version 57930 (0.0008) -[2023-10-12 05:38:17,802][78091] Updated weights for policy 0, policy_version 57940 (0.0009) -[2023-10-12 05:38:18,184][78091] Updated weights for policy 0, policy_version 57950 (0.0011) -[2023-10-12 05:38:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 118390784. Throughput: 0: 1590.6, 1: 1589.6. Samples: 29607456. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-12 05:38:20,201][77203] Avg episode reward: [(0, '55.310'), (1, '43.520')] -[2023-10-12 05:38:20,220][78123] Updated weights for policy 1, policy_version 57670 (0.0008) -[2023-10-12 05:38:20,579][78123] Updated weights for policy 1, policy_version 57680 (0.0008) -[2023-10-12 05:38:20,944][78123] Updated weights for policy 1, policy_version 57690 (0.0009) -[2023-10-12 05:38:22,562][78091] Updated weights for policy 0, policy_version 57960 (0.0008) -[2023-10-12 05:38:22,941][78091] Updated weights for policy 0, policy_version 57970 (0.0009) -[2023-10-12 05:38:23,319][78091] Updated weights for policy 0, policy_version 57980 (0.0009) -[2023-10-12 05:38:25,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 118456320. Throughput: 0: 1589.9, 1: 1608.8. Samples: 29626840. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-12 05:38:25,202][77203] Avg episode reward: [(0, '50.180'), (1, '47.040')] -[2023-10-12 05:38:25,516][78123] Updated weights for policy 1, policy_version 57700 (0.0008) -[2023-10-12 05:38:25,914][78123] Updated weights for policy 1, policy_version 57710 (0.0009) -[2023-10-12 05:38:26,287][78123] Updated weights for policy 1, policy_version 57720 (0.0009) -[2023-10-12 05:38:27,665][78091] Updated weights for policy 0, policy_version 57990 (0.0008) -[2023-10-12 05:38:28,030][78091] Updated weights for policy 0, policy_version 58000 (0.0007) -[2023-10-12 05:38:28,410][78091] Updated weights for policy 0, policy_version 58010 (0.0007) -[2023-10-12 05:38:30,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 118521856. Throughput: 0: 1610.8, 1: 1586.1. Samples: 29636196. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-12 05:38:30,201][77203] Avg episode reward: [(0, '44.610'), (1, '53.430')] -[2023-10-12 05:38:30,326][78123] Updated weights for policy 1, policy_version 57730 (0.0007) -[2023-10-12 05:38:30,704][78123] Updated weights for policy 1, policy_version 57740 (0.0009) -[2023-10-12 05:38:31,067][78123] Updated weights for policy 1, policy_version 57750 (0.0010) -[2023-10-12 05:38:31,441][78123] Updated weights for policy 1, policy_version 57760 (0.0008) -[2023-10-12 05:38:32,627][78091] Updated weights for policy 0, policy_version 58020 (0.0008) -[2023-10-12 05:38:33,001][78091] Updated weights for policy 0, policy_version 58030 (0.0009) -[2023-10-12 05:38:33,369][78091] Updated weights for policy 0, policy_version 58040 (0.0010) -[2023-10-12 05:38:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 118587392. Throughput: 0: 1592.2, 1: 1586.1. Samples: 29654970. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-12 05:38:35,202][77203] Avg episode reward: [(0, '47.220'), (1, '46.950')] -[2023-10-12 05:38:36,005][78123] Updated weights for policy 1, policy_version 57770 (0.0009) -[2023-10-12 05:38:36,387][78123] Updated weights for policy 1, policy_version 57780 (0.0007) -[2023-10-12 05:38:36,754][78123] Updated weights for policy 1, policy_version 57790 (0.0008) -[2023-10-12 05:38:37,587][78091] Updated weights for policy 0, policy_version 58050 (0.0008) -[2023-10-12 05:38:37,954][78091] Updated weights for policy 0, policy_version 58060 (0.0009) -[2023-10-12 05:38:38,322][78091] Updated weights for policy 0, policy_version 58070 (0.0009) -[2023-10-12 05:38:38,686][78091] Updated weights for policy 0, policy_version 58080 (0.0008) -[2023-10-12 05:38:40,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 118652928. Throughput: 0: 1596.5, 1: 1590.9. Samples: 29674494. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-12 05:38:40,201][77203] Avg episode reward: [(0, '52.670'), (1, '44.870')] -[2023-10-12 05:38:41,000][78123] Updated weights for policy 1, policy_version 57800 (0.0008) -[2023-10-12 05:38:41,359][78123] Updated weights for policy 1, policy_version 57810 (0.0007) -[2023-10-12 05:38:41,743][78123] Updated weights for policy 1, policy_version 57820 (0.0009) -[2023-10-12 05:38:43,145][78091] Updated weights for policy 0, policy_version 58090 (0.0012) -[2023-10-12 05:38:43,532][78091] Updated weights for policy 0, policy_version 58100 (0.0009) -[2023-10-12 05:38:43,897][78091] Updated weights for policy 0, policy_version 58110 (0.0009) -[2023-10-12 05:38:45,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 118718464. Throughput: 0: 1619.6, 1: 1579.8. Samples: 29684122. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-12 05:38:45,201][77203] Avg episode reward: [(0, '44.210'), (1, '45.220')] -[2023-10-12 05:38:46,087][78123] Updated weights for policy 1, policy_version 57830 (0.0007) -[2023-10-12 05:38:46,456][78123] Updated weights for policy 1, policy_version 57840 (0.0008) -[2023-10-12 05:38:46,822][78123] Updated weights for policy 1, policy_version 57850 (0.0008) -[2023-10-12 05:38:48,134][78091] Updated weights for policy 0, policy_version 58120 (0.0010) -[2023-10-12 05:38:48,501][78091] Updated weights for policy 0, policy_version 58130 (0.0008) -[2023-10-12 05:38:48,868][78091] Updated weights for policy 0, policy_version 58140 (0.0010) -[2023-10-12 05:38:50,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 118784000. Throughput: 0: 1598.9, 1: 1579.6. Samples: 29702786. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-12 05:38:50,202][77203] Avg episode reward: [(0, '40.650'), (1, '52.080')] -[2023-10-12 05:38:51,242][78123] Updated weights for policy 1, policy_version 57860 (0.0007) -[2023-10-12 05:38:51,611][78123] Updated weights for policy 1, policy_version 57870 (0.0008) -[2023-10-12 05:38:51,969][78123] Updated weights for policy 1, policy_version 57880 (0.0011) -[2023-10-12 05:38:53,276][78091] Updated weights for policy 0, policy_version 58150 (0.0009) -[2023-10-12 05:38:53,656][78091] Updated weights for policy 0, policy_version 58160 (0.0008) -[2023-10-12 05:38:54,019][78091] Updated weights for policy 0, policy_version 58170 (0.0009) -[2023-10-12 05:38:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 118849536. Throughput: 0: 1596.1, 1: 1579.8. Samples: 29721984. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-12 05:38:55,201][77203] Avg episode reward: [(0, '45.200'), (1, '51.940')] -[2023-10-12 05:38:56,428][78123] Updated weights for policy 1, policy_version 57890 (0.0009) -[2023-10-12 05:38:56,801][78123] Updated weights for policy 1, policy_version 57900 (0.0008) -[2023-10-12 05:38:57,157][78123] Updated weights for policy 1, policy_version 57910 (0.0008) -[2023-10-12 05:38:57,530][78123] Updated weights for policy 1, policy_version 57920 (0.0008) -[2023-10-12 05:38:58,446][78091] Updated weights for policy 0, policy_version 58180 (0.0009) -[2023-10-12 05:38:58,817][78091] Updated weights for policy 0, policy_version 58190 (0.0010) -[2023-10-12 05:38:59,188][78091] Updated weights for policy 0, policy_version 58200 (0.0010) -[2023-10-12 05:39:00,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 118915072. Throughput: 0: 1608.1, 1: 1580.0. Samples: 29731664. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-12 05:39:00,201][77203] Avg episode reward: [(0, '46.990'), (1, '44.900')] -[2023-10-12 05:39:01,927][78123] Updated weights for policy 1, policy_version 57930 (0.0009) -[2023-10-12 05:39:02,292][78123] Updated weights for policy 1, policy_version 57940 (0.0008) -[2023-10-12 05:39:02,667][78123] Updated weights for policy 1, policy_version 57950 (0.0009) -[2023-10-12 05:39:03,504][78091] Updated weights for policy 0, policy_version 58210 (0.0009) -[2023-10-12 05:39:03,872][78091] Updated weights for policy 0, policy_version 58220 (0.0008) -[2023-10-12 05:39:04,244][78091] Updated weights for policy 0, policy_version 58230 (0.0008) -[2023-10-12 05:39:04,609][78091] Updated weights for policy 0, policy_version 58240 (0.0008) -[2023-10-12 05:39:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 118980608. Throughput: 0: 1615.4, 1: 1576.4. Samples: 29751090. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-12 05:39:05,201][77203] Avg episode reward: [(0, '49.080'), (1, '48.770')] -[2023-10-12 05:39:06,892][78123] Updated weights for policy 1, policy_version 57960 (0.0009) -[2023-10-12 05:39:07,264][78123] Updated weights for policy 1, policy_version 57970 (0.0008) -[2023-10-12 05:39:07,637][78123] Updated weights for policy 1, policy_version 57980 (0.0011) -[2023-10-12 05:39:08,980][78091] Updated weights for policy 0, policy_version 58250 (0.0007) -[2023-10-12 05:39:09,349][78091] Updated weights for policy 0, policy_version 58260 (0.0010) -[2023-10-12 05:39:09,717][78091] Updated weights for policy 0, policy_version 58270 (0.0007) -[2023-10-12 05:39:10,201][77203] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 119046144. Throughput: 0: 1599.5, 1: 1577.4. Samples: 29769800. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-12 05:39:10,202][77203] Avg episode reward: [(0, '48.630'), (1, '47.270')] -[2023-10-12 05:39:10,215][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000057984_59375616.pth... -[2023-10-12 05:39:10,215][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000058272_59670528.pth... -[2023-10-12 05:39:10,249][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000056768_58130432.pth -[2023-10-12 05:39:10,250][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000056512_57868288.pth -[2023-10-12 05:39:12,152][78123] Updated weights for policy 1, policy_version 57990 (0.0008) -[2023-10-12 05:39:12,535][78123] Updated weights for policy 1, policy_version 58000 (0.0009) -[2023-10-12 05:39:12,899][78123] Updated weights for policy 1, policy_version 58010 (0.0010) -[2023-10-12 05:39:13,890][78091] Updated weights for policy 0, policy_version 58280 (0.0009) -[2023-10-12 05:39:14,260][78091] Updated weights for policy 0, policy_version 58290 (0.0008) -[2023-10-12 05:39:14,636][78091] Updated weights for policy 0, policy_version 58300 (0.0008) -[2023-10-12 05:39:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 119111680. Throughput: 0: 1606.2, 1: 1586.4. Samples: 29779862. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-12 05:39:15,201][77203] Avg episode reward: [(0, '48.790'), (1, '50.530')] -[2023-10-12 05:39:17,185][78123] Updated weights for policy 1, policy_version 58020 (0.0009) -[2023-10-12 05:39:17,542][78123] Updated weights for policy 1, policy_version 58030 (0.0009) -[2023-10-12 05:39:17,916][78123] Updated weights for policy 1, policy_version 58040 (0.0007) -[2023-10-12 05:39:19,095][78091] Updated weights for policy 0, policy_version 58310 (0.0009) -[2023-10-12 05:39:19,465][78091] Updated weights for policy 0, policy_version 58320 (0.0007) -[2023-10-12 05:39:19,829][78091] Updated weights for policy 0, policy_version 58330 (0.0008) -[2023-10-12 05:39:20,201][77203] Fps is (10 sec: 13107.7, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 119177216. Throughput: 0: 1619.5, 1: 1576.5. Samples: 29798790. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-12 05:39:20,201][77203] Avg episode reward: [(0, '51.770'), (1, '48.310')] -[2023-10-12 05:39:22,063][78123] Updated weights for policy 1, policy_version 58050 (0.0008) -[2023-10-12 05:39:22,439][78123] Updated weights for policy 1, policy_version 58060 (0.0009) -[2023-10-12 05:39:22,809][78123] Updated weights for policy 1, policy_version 58070 (0.0009) -[2023-10-12 05:39:23,183][78123] Updated weights for policy 1, policy_version 58080 (0.0010) -[2023-10-12 05:39:24,104][78091] Updated weights for policy 0, policy_version 58340 (0.0009) -[2023-10-12 05:39:24,489][78091] Updated weights for policy 0, policy_version 58350 (0.0009) -[2023-10-12 05:39:24,868][78091] Updated weights for policy 0, policy_version 58360 (0.0008) -[2023-10-12 05:39:25,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 119242752. Throughput: 0: 1600.7, 1: 1576.1. Samples: 29817450. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) -[2023-10-12 05:39:25,202][77203] Avg episode reward: [(0, '53.600'), (1, '48.900')] -[2023-10-12 05:39:27,508][78123] Updated weights for policy 1, policy_version 58090 (0.0008) -[2023-10-12 05:39:27,886][78123] Updated weights for policy 1, policy_version 58100 (0.0008) -[2023-10-12 05:39:28,243][78123] Updated weights for policy 1, policy_version 58110 (0.0009) -[2023-10-12 05:39:29,359][78091] Updated weights for policy 0, policy_version 58370 (0.0010) -[2023-10-12 05:39:29,761][78091] Updated weights for policy 0, policy_version 58380 (0.0007) -[2023-10-12 05:39:30,120][78091] Updated weights for policy 0, policy_version 58390 (0.0007) -[2023-10-12 05:39:30,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 119275520. Throughput: 0: 1588.3, 1: 1592.3. Samples: 29827248. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) -[2023-10-12 05:39:30,201][77203] Avg episode reward: [(0, '47.960'), (1, '51.840')] -[2023-10-12 05:39:30,493][78091] Updated weights for policy 0, policy_version 58400 (0.0007) -[2023-10-12 05:39:32,574][78123] Updated weights for policy 1, policy_version 58120 (0.0007) -[2023-10-12 05:39:32,935][78123] Updated weights for policy 1, policy_version 58130 (0.0007) -[2023-10-12 05:39:33,307][78123] Updated weights for policy 1, policy_version 58140 (0.0009) -[2023-10-12 05:39:34,726][78091] Updated weights for policy 0, policy_version 58410 (0.0008) -[2023-10-12 05:39:35,090][78091] Updated weights for policy 0, policy_version 58420 (0.0007) -[2023-10-12 05:39:35,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 119341056. Throughput: 0: 1604.1, 1: 1578.6. Samples: 29846008. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) -[2023-10-12 05:39:35,201][77203] Avg episode reward: [(0, '47.160'), (1, '46.570')] -[2023-10-12 05:39:35,459][78091] Updated weights for policy 0, policy_version 58430 (0.0008) -[2023-10-12 05:39:37,715][78123] Updated weights for policy 1, policy_version 58150 (0.0008) -[2023-10-12 05:39:38,082][78123] Updated weights for policy 1, policy_version 58160 (0.0007) -[2023-10-12 05:39:38,450][78123] Updated weights for policy 1, policy_version 58170 (0.0009) -[2023-10-12 05:39:39,676][78091] Updated weights for policy 0, policy_version 58440 (0.0010) -[2023-10-12 05:39:40,052][78091] Updated weights for policy 0, policy_version 58450 (0.0007) -[2023-10-12 05:39:40,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 119406592. Throughput: 0: 1600.4, 1: 1578.0. Samples: 29865014. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) -[2023-10-12 05:39:40,201][77203] Avg episode reward: [(0, '49.660'), (1, '46.790')] -[2023-10-12 05:39:40,422][78091] Updated weights for policy 0, policy_version 58460 (0.0009) -[2023-10-12 05:39:42,738][78123] Updated weights for policy 1, policy_version 58180 (0.0009) -[2023-10-12 05:39:43,100][78123] Updated weights for policy 1, policy_version 58190 (0.0010) -[2023-10-12 05:39:43,465][78123] Updated weights for policy 1, policy_version 58200 (0.0009) -[2023-10-12 05:39:44,844][78091] Updated weights for policy 0, policy_version 58470 (0.0007) -[2023-10-12 05:39:45,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 119472128. Throughput: 0: 1584.0, 1: 1605.4. Samples: 29875190. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) -[2023-10-12 05:39:45,201][77203] Avg episode reward: [(0, '44.710'), (1, '47.660')] -[2023-10-12 05:39:45,207][78091] Updated weights for policy 0, policy_version 58480 (0.0007) -[2023-10-12 05:39:45,585][78091] Updated weights for policy 0, policy_version 58490 (0.0009) -[2023-10-12 05:39:47,728][78123] Updated weights for policy 1, policy_version 58210 (0.0009) -[2023-10-12 05:39:48,088][78123] Updated weights for policy 1, policy_version 58220 (0.0009) -[2023-10-12 05:39:48,455][78123] Updated weights for policy 1, policy_version 58230 (0.0011) -[2023-10-12 05:39:48,825][78123] Updated weights for policy 1, policy_version 58240 (0.0009) -[2023-10-12 05:39:50,072][78091] Updated weights for policy 0, policy_version 58500 (0.0009) -[2023-10-12 05:39:50,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 119537664. Throughput: 0: 1587.6, 1: 1585.4. Samples: 29893876. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) -[2023-10-12 05:39:50,202][77203] Avg episode reward: [(0, '44.050'), (1, '47.120')] -[2023-10-12 05:39:50,433][78091] Updated weights for policy 0, policy_version 58510 (0.0008) -[2023-10-12 05:39:50,806][78091] Updated weights for policy 0, policy_version 58520 (0.0008) -[2023-10-12 05:39:53,336][78123] Updated weights for policy 1, policy_version 58250 (0.0008) -[2023-10-12 05:39:53,713][78123] Updated weights for policy 1, policy_version 58260 (0.0007) -[2023-10-12 05:39:54,072][78123] Updated weights for policy 1, policy_version 58270 (0.0009) -[2023-10-12 05:39:55,189][78091] Updated weights for policy 0, policy_version 58530 (0.0007) -[2023-10-12 05:39:55,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 119603200. Throughput: 0: 1602.5, 1: 1579.1. Samples: 29912974. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) -[2023-10-12 05:39:55,202][77203] Avg episode reward: [(0, '42.060'), (1, '46.970')] -[2023-10-12 05:39:55,552][78091] Updated weights for policy 0, policy_version 58540 (0.0007) -[2023-10-12 05:39:55,926][78091] Updated weights for policy 0, policy_version 58550 (0.0007) -[2023-10-12 05:39:56,300][78091] Updated weights for policy 0, policy_version 58560 (0.0007) -[2023-10-12 05:39:58,484][78123] Updated weights for policy 1, policy_version 58280 (0.0009) -[2023-10-12 05:39:58,850][78123] Updated weights for policy 1, policy_version 58290 (0.0007) -[2023-10-12 05:39:59,223][78123] Updated weights for policy 1, policy_version 58300 (0.0008) -[2023-10-12 05:40:00,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 119668736. Throughput: 0: 1576.4, 1: 1598.6. Samples: 29922734. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) -[2023-10-12 05:40:00,201][77203] Avg episode reward: [(0, '43.810'), (1, '47.550')] -[2023-10-12 05:40:00,674][78091] Updated weights for policy 0, policy_version 58570 (0.0009) -[2023-10-12 05:40:01,061][78091] Updated weights for policy 0, policy_version 58580 (0.0007) -[2023-10-12 05:40:01,435][78091] Updated weights for policy 0, policy_version 58590 (0.0007) -[2023-10-12 05:40:03,537][78123] Updated weights for policy 1, policy_version 58310 (0.0009) -[2023-10-12 05:40:03,913][78123] Updated weights for policy 1, policy_version 58320 (0.0009) -[2023-10-12 05:40:04,273][78123] Updated weights for policy 1, policy_version 58330 (0.0011) -[2023-10-12 05:40:05,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 119734272. Throughput: 0: 1576.8, 1: 1597.4. Samples: 29941628. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) -[2023-10-12 05:40:05,201][77203] Avg episode reward: [(0, '44.160'), (1, '44.000')] -[2023-10-12 05:40:05,786][78091] Updated weights for policy 0, policy_version 58600 (0.0008) -[2023-10-12 05:40:06,159][78091] Updated weights for policy 0, policy_version 58610 (0.0009) -[2023-10-12 05:40:06,523][78091] Updated weights for policy 0, policy_version 58620 (0.0008) -[2023-10-12 05:40:08,632][78123] Updated weights for policy 1, policy_version 58340 (0.0010) -[2023-10-12 05:40:09,002][78123] Updated weights for policy 1, policy_version 58350 (0.0009) -[2023-10-12 05:40:09,369][78123] Updated weights for policy 1, policy_version 58360 (0.0007) -[2023-10-12 05:40:10,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 119799808. Throughput: 0: 1592.9, 1: 1584.4. Samples: 29960430. Policy #0 lag: (min: 31.0, avg: 32.7, max: 59.0) -[2023-10-12 05:40:10,202][77203] Avg episode reward: [(0, '48.010'), (1, '51.550')] -[2023-10-12 05:40:10,793][78091] Updated weights for policy 0, policy_version 58630 (0.0009) -[2023-10-12 05:40:11,169][78091] Updated weights for policy 0, policy_version 58640 (0.0010) -[2023-10-12 05:40:11,537][78091] Updated weights for policy 0, policy_version 58650 (0.0007) -[2023-10-12 05:40:13,688][78123] Updated weights for policy 1, policy_version 58370 (0.0008) -[2023-10-12 05:40:14,054][78123] Updated weights for policy 1, policy_version 58380 (0.0009) -[2023-10-12 05:40:14,431][78123] Updated weights for policy 1, policy_version 58390 (0.0008) -[2023-10-12 05:40:14,801][78123] Updated weights for policy 1, policy_version 58400 (0.0009) -[2023-10-12 05:40:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 119865344. Throughput: 0: 1578.9, 1: 1596.4. Samples: 29970140. Policy #0 lag: (min: 31.0, avg: 32.7, max: 59.0) -[2023-10-12 05:40:15,202][77203] Avg episode reward: [(0, '53.790'), (1, '42.550')] -[2023-10-12 05:40:15,813][78091] Updated weights for policy 0, policy_version 58660 (0.0010) -[2023-10-12 05:40:16,171][78091] Updated weights for policy 0, policy_version 58670 (0.0010) -[2023-10-12 05:40:16,539][78091] Updated weights for policy 0, policy_version 58680 (0.0010) -[2023-10-12 05:40:19,131][78123] Updated weights for policy 1, policy_version 58410 (0.0007) -[2023-10-12 05:40:19,496][78123] Updated weights for policy 1, policy_version 58420 (0.0009) -[2023-10-12 05:40:19,868][78123] Updated weights for policy 1, policy_version 58430 (0.0011) -[2023-10-12 05:40:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 119930880. Throughput: 0: 1582.3, 1: 1612.0. Samples: 29989750. Policy #0 lag: (min: 31.0, avg: 32.7, max: 59.0) -[2023-10-12 05:40:20,202][77203] Avg episode reward: [(0, '49.340'), (1, '52.260')] -[2023-10-12 05:40:20,714][78091] Updated weights for policy 0, policy_version 58690 (0.0009) -[2023-10-12 05:40:21,077][78091] Updated weights for policy 0, policy_version 58700 (0.0009) -[2023-10-12 05:40:21,458][78091] Updated weights for policy 0, policy_version 58710 (0.0008) -[2023-10-12 05:40:21,824][78091] Updated weights for policy 0, policy_version 58720 (0.0008) -[2023-10-12 05:40:24,237][78123] Updated weights for policy 1, policy_version 58440 (0.0008) -[2023-10-12 05:40:24,606][78123] Updated weights for policy 1, policy_version 58450 (0.0010) -[2023-10-12 05:40:24,969][78123] Updated weights for policy 1, policy_version 58460 (0.0010) -[2023-10-12 05:40:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 119996416. Throughput: 0: 1595.7, 1: 1598.9. Samples: 30008770. Policy #0 lag: (min: 31.0, avg: 32.7, max: 59.0) -[2023-10-12 05:40:25,201][77203] Avg episode reward: [(0, '49.030'), (1, '47.280')] -[2023-10-12 05:40:26,207][78091] Updated weights for policy 0, policy_version 58730 (0.0007) -[2023-10-12 05:40:26,572][78091] Updated weights for policy 0, policy_version 58740 (0.0011) -[2023-10-12 05:40:26,956][78091] Updated weights for policy 0, policy_version 58750 (0.0010) -[2023-10-12 05:40:29,370][78123] Updated weights for policy 1, policy_version 58470 (0.0010) -[2023-10-12 05:40:29,730][78123] Updated weights for policy 1, policy_version 58480 (0.0009) -[2023-10-12 05:40:30,095][78123] Updated weights for policy 1, policy_version 58490 (0.0009) -[2023-10-12 05:40:30,201][77203] Fps is (10 sec: 9830.6, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 120029184. Throughput: 0: 1583.7, 1: 1586.8. Samples: 30017862. Policy #0 lag: (min: 31.0, avg: 32.7, max: 59.0) -[2023-10-12 05:40:30,201][77203] Avg episode reward: [(0, '50.530'), (1, '47.780')] -[2023-10-12 05:40:31,304][78091] Updated weights for policy 0, policy_version 58760 (0.0008) -[2023-10-12 05:40:31,677][78091] Updated weights for policy 0, policy_version 58770 (0.0007) -[2023-10-12 05:40:32,046][78091] Updated weights for policy 0, policy_version 58780 (0.0008) -[2023-10-12 05:40:34,326][78123] Updated weights for policy 1, policy_version 58500 (0.0008) -[2023-10-12 05:40:34,689][78123] Updated weights for policy 1, policy_version 58510 (0.0007) -[2023-10-12 05:40:35,055][78123] Updated weights for policy 1, policy_version 58520 (0.0008) -[2023-10-12 05:40:35,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 120094720. Throughput: 0: 1578.5, 1: 1608.3. Samples: 30037284. Policy #0 lag: (min: 31.0, avg: 32.7, max: 59.0) -[2023-10-12 05:40:35,202][77203] Avg episode reward: [(0, '51.620'), (1, '47.590')] -[2023-10-12 05:40:36,311][78091] Updated weights for policy 0, policy_version 58790 (0.0007) -[2023-10-12 05:40:36,690][78091] Updated weights for policy 0, policy_version 58800 (0.0010) -[2023-10-12 05:40:37,055][78091] Updated weights for policy 0, policy_version 58810 (0.0008) -[2023-10-12 05:40:39,387][78123] Updated weights for policy 1, policy_version 58530 (0.0007) -[2023-10-12 05:40:39,751][78123] Updated weights for policy 1, policy_version 58540 (0.0007) -[2023-10-12 05:40:40,125][78123] Updated weights for policy 1, policy_version 58550 (0.0008) -[2023-10-12 05:40:40,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 120160256. Throughput: 0: 1581.6, 1: 1605.1. Samples: 30056374. Policy #0 lag: (min: 31.0, avg: 32.7, max: 59.0) -[2023-10-12 05:40:40,202][77203] Avg episode reward: [(0, '49.150'), (1, '46.210')] -[2023-10-12 05:40:40,493][78123] Updated weights for policy 1, policy_version 58560 (0.0009) -[2023-10-12 05:40:41,573][78091] Updated weights for policy 0, policy_version 58820 (0.0008) -[2023-10-12 05:40:41,951][78091] Updated weights for policy 0, policy_version 58830 (0.0009) -[2023-10-12 05:40:42,329][78091] Updated weights for policy 0, policy_version 58840 (0.0011) -[2023-10-12 05:40:44,980][78123] Updated weights for policy 1, policy_version 58570 (0.0010) -[2023-10-12 05:40:45,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 120225792. Throughput: 0: 1576.4, 1: 1589.6. Samples: 30065204. Policy #0 lag: (min: 31.0, avg: 32.7, max: 59.0) -[2023-10-12 05:40:45,201][77203] Avg episode reward: [(0, '45.180'), (1, '39.030')] -[2023-10-12 05:40:45,340][78123] Updated weights for policy 1, policy_version 58580 (0.0008) -[2023-10-12 05:40:45,710][78123] Updated weights for policy 1, policy_version 58590 (0.0010) -[2023-10-12 05:40:46,642][78091] Updated weights for policy 0, policy_version 58850 (0.0010) -[2023-10-12 05:40:47,022][78091] Updated weights for policy 0, policy_version 58860 (0.0007) -[2023-10-12 05:40:47,390][78091] Updated weights for policy 0, policy_version 58870 (0.0009) -[2023-10-12 05:40:47,762][78091] Updated weights for policy 0, policy_version 58880 (0.0011) -[2023-10-12 05:40:49,917][78123] Updated weights for policy 1, policy_version 58600 (0.0008) -[2023-10-12 05:40:50,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 120291328. Throughput: 0: 1579.9, 1: 1597.5. Samples: 30084608. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:40:50,202][77203] Avg episode reward: [(0, '47.770'), (1, '48.270')] -[2023-10-12 05:40:50,285][78123] Updated weights for policy 1, policy_version 58610 (0.0009) -[2023-10-12 05:40:50,655][78123] Updated weights for policy 1, policy_version 58620 (0.0009) -[2023-10-12 05:40:52,029][78091] Updated weights for policy 0, policy_version 58890 (0.0010) -[2023-10-12 05:40:52,410][78091] Updated weights for policy 0, policy_version 58900 (0.0011) -[2023-10-12 05:40:52,783][78091] Updated weights for policy 0, policy_version 58910 (0.0009) -[2023-10-12 05:40:54,855][78123] Updated weights for policy 1, policy_version 58630 (0.0007) -[2023-10-12 05:40:55,201][77203] Fps is (10 sec: 13106.8, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 120356864. Throughput: 0: 1582.0, 1: 1612.8. Samples: 30104198. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:40:55,202][77203] Avg episode reward: [(0, '51.990'), (1, '46.130')] -[2023-10-12 05:40:55,221][78123] Updated weights for policy 1, policy_version 58640 (0.0007) -[2023-10-12 05:40:55,589][78123] Updated weights for policy 1, policy_version 58650 (0.0008) -[2023-10-12 05:40:57,030][78091] Updated weights for policy 0, policy_version 58920 (0.0008) -[2023-10-12 05:40:57,409][78091] Updated weights for policy 0, policy_version 58930 (0.0007) -[2023-10-12 05:40:57,781][78091] Updated weights for policy 0, policy_version 58940 (0.0007) -[2023-10-12 05:41:00,047][78123] Updated weights for policy 1, policy_version 58660 (0.0009) -[2023-10-12 05:41:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 120422400. Throughput: 0: 1588.2, 1: 1587.8. Samples: 30113060. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:41:00,202][77203] Avg episode reward: [(0, '50.360'), (1, '50.450')] -[2023-10-12 05:41:00,414][78123] Updated weights for policy 1, policy_version 58670 (0.0009) -[2023-10-12 05:41:00,780][78123] Updated weights for policy 1, policy_version 58680 (0.0007) -[2023-10-12 05:41:02,066][78091] Updated weights for policy 0, policy_version 58950 (0.0009) -[2023-10-12 05:41:02,450][78091] Updated weights for policy 0, policy_version 58960 (0.0009) -[2023-10-12 05:41:02,812][78091] Updated weights for policy 0, policy_version 58970 (0.0010) -[2023-10-12 05:41:05,006][78123] Updated weights for policy 1, policy_version 58690 (0.0008) -[2023-10-12 05:41:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 120487936. Throughput: 0: 1585.6, 1: 1585.5. Samples: 30132448. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:41:05,202][77203] Avg episode reward: [(0, '43.500'), (1, '45.790')] -[2023-10-12 05:41:05,377][78123] Updated weights for policy 1, policy_version 58700 (0.0009) -[2023-10-12 05:41:05,739][78123] Updated weights for policy 1, policy_version 58710 (0.0007) -[2023-10-12 05:41:06,109][78123] Updated weights for policy 1, policy_version 58720 (0.0009) -[2023-10-12 05:41:07,007][78091] Updated weights for policy 0, policy_version 58980 (0.0009) -[2023-10-12 05:41:07,376][78091] Updated weights for policy 0, policy_version 58990 (0.0007) -[2023-10-12 05:41:07,740][78091] Updated weights for policy 0, policy_version 59000 (0.0008) -[2023-10-12 05:41:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 120553472. Throughput: 0: 1584.7, 1: 1598.0. Samples: 30151990. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:41:10,202][77203] Avg episode reward: [(0, '41.900'), (1, '51.470')] -[2023-10-12 05:41:10,211][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000059008_60424192.pth... -[2023-10-12 05:41:10,247][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000057504_58884096.pth -[2023-10-12 05:41:10,315][78123] Updated weights for policy 1, policy_version 58730 (0.0008) -[2023-10-12 05:41:10,674][78123] Updated weights for policy 1, policy_version 58740 (0.0011) -[2023-10-12 05:41:11,033][78123] Updated weights for policy 1, policy_version 58750 (0.0007) -[2023-10-12 05:41:11,104][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000058752_60162048.pth... -[2023-10-12 05:41:11,133][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000057248_58621952.pth -[2023-10-12 05:41:11,917][78091] Updated weights for policy 0, policy_version 59010 (0.0008) -[2023-10-12 05:41:12,282][78091] Updated weights for policy 0, policy_version 59020 (0.0010) -[2023-10-12 05:41:12,653][78091] Updated weights for policy 0, policy_version 59030 (0.0010) -[2023-10-12 05:41:13,033][78091] Updated weights for policy 0, policy_version 59040 (0.0008) -[2023-10-12 05:41:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 120619008. Throughput: 0: 1598.6, 1: 1583.5. Samples: 30161056. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:41:15,202][77203] Avg episode reward: [(0, '45.350'), (1, '45.220')] -[2023-10-12 05:41:15,540][78123] Updated weights for policy 1, policy_version 58760 (0.0010) -[2023-10-12 05:41:15,910][78123] Updated weights for policy 1, policy_version 58770 (0.0009) -[2023-10-12 05:41:16,284][78123] Updated weights for policy 1, policy_version 58780 (0.0008) -[2023-10-12 05:41:17,125][78091] Updated weights for policy 0, policy_version 59050 (0.0007) -[2023-10-12 05:41:17,492][78091] Updated weights for policy 0, policy_version 59060 (0.0008) -[2023-10-12 05:41:17,864][78091] Updated weights for policy 0, policy_version 59070 (0.0008) -[2023-10-12 05:41:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 120684544. Throughput: 0: 1604.3, 1: 1576.7. Samples: 30180428. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:41:20,201][77203] Avg episode reward: [(0, '51.730'), (1, '48.140')] -[2023-10-12 05:41:20,706][78123] Updated weights for policy 1, policy_version 58790 (0.0008) -[2023-10-12 05:41:21,068][78123] Updated weights for policy 1, policy_version 58800 (0.0007) -[2023-10-12 05:41:21,442][78123] Updated weights for policy 1, policy_version 58810 (0.0008) -[2023-10-12 05:41:22,092][78091] Updated weights for policy 0, policy_version 59080 (0.0007) -[2023-10-12 05:41:22,457][78091] Updated weights for policy 0, policy_version 59090 (0.0008) -[2023-10-12 05:41:22,822][78091] Updated weights for policy 0, policy_version 59100 (0.0009) -[2023-10-12 05:41:25,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 120750080. Throughput: 0: 1610.5, 1: 1583.6. Samples: 30200106. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:41:25,201][77203] Avg episode reward: [(0, '50.290'), (1, '48.710')] -[2023-10-12 05:41:25,915][78123] Updated weights for policy 1, policy_version 58820 (0.0009) -[2023-10-12 05:41:26,288][78123] Updated weights for policy 1, policy_version 58830 (0.0008) -[2023-10-12 05:41:26,647][78123] Updated weights for policy 1, policy_version 58840 (0.0011) -[2023-10-12 05:41:27,055][78091] Updated weights for policy 0, policy_version 59110 (0.0007) -[2023-10-12 05:41:27,423][78091] Updated weights for policy 0, policy_version 59120 (0.0007) -[2023-10-12 05:41:27,794][78091] Updated weights for policy 0, policy_version 59130 (0.0007) -[2023-10-12 05:41:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 120815616. Throughput: 0: 1620.9, 1: 1574.0. Samples: 30208972. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 05:41:30,201][77203] Avg episode reward: [(0, '44.930'), (1, '43.250')] -[2023-10-12 05:41:31,144][78123] Updated weights for policy 1, policy_version 58850 (0.0010) -[2023-10-12 05:41:31,558][78123] Updated weights for policy 1, policy_version 58860 (0.0009) -[2023-10-12 05:41:31,926][78123] Updated weights for policy 1, policy_version 58870 (0.0008) -[2023-10-12 05:41:32,253][78091] Updated weights for policy 0, policy_version 59140 (0.0009) -[2023-10-12 05:41:32,293][78123] Updated weights for policy 1, policy_version 58880 (0.0008) -[2023-10-12 05:41:32,625][78091] Updated weights for policy 0, policy_version 59150 (0.0008) -[2023-10-12 05:41:32,995][78091] Updated weights for policy 0, policy_version 59160 (0.0007) -[2023-10-12 05:41:35,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 120881152. Throughput: 0: 1613.0, 1: 1572.1. Samples: 30227938. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 05:41:35,202][77203] Avg episode reward: [(0, '47.380'), (1, '43.140')] -[2023-10-12 05:41:36,695][78123] Updated weights for policy 1, policy_version 58890 (0.0009) -[2023-10-12 05:41:37,055][78123] Updated weights for policy 1, policy_version 58900 (0.0009) -[2023-10-12 05:41:37,281][78091] Updated weights for policy 0, policy_version 59170 (0.0008) -[2023-10-12 05:41:37,415][78123] Updated weights for policy 1, policy_version 58910 (0.0009) -[2023-10-12 05:41:37,655][78091] Updated weights for policy 0, policy_version 59180 (0.0010) -[2023-10-12 05:41:38,019][78091] Updated weights for policy 0, policy_version 59190 (0.0010) -[2023-10-12 05:41:38,395][78091] Updated weights for policy 0, policy_version 59200 (0.0010) -[2023-10-12 05:41:40,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 12774.0). Total num frames: 120946688. Throughput: 0: 1610.7, 1: 1573.5. Samples: 30247484. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 05:41:40,201][77203] Avg episode reward: [(0, '53.990'), (1, '45.200')] -[2023-10-12 05:41:41,631][78123] Updated weights for policy 1, policy_version 58920 (0.0010) -[2023-10-12 05:41:41,995][78123] Updated weights for policy 1, policy_version 58930 (0.0009) -[2023-10-12 05:41:42,360][78123] Updated weights for policy 1, policy_version 58940 (0.0008) -[2023-10-12 05:41:42,756][78091] Updated weights for policy 0, policy_version 59210 (0.0009) -[2023-10-12 05:41:43,123][78091] Updated weights for policy 0, policy_version 59220 (0.0007) -[2023-10-12 05:41:43,487][78091] Updated weights for policy 0, policy_version 59230 (0.0008) -[2023-10-12 05:41:45,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 121012224. Throughput: 0: 1622.5, 1: 1574.2. Samples: 30256914. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 05:41:45,201][77203] Avg episode reward: [(0, '56.010'), (1, '48.950')] -[2023-10-12 05:41:46,683][78123] Updated weights for policy 1, policy_version 58950 (0.0007) -[2023-10-12 05:41:47,054][78123] Updated weights for policy 1, policy_version 58960 (0.0007) -[2023-10-12 05:41:47,413][78123] Updated weights for policy 1, policy_version 58970 (0.0007) -[2023-10-12 05:41:47,846][78091] Updated weights for policy 0, policy_version 59240 (0.0010) -[2023-10-12 05:41:48,218][78091] Updated weights for policy 0, policy_version 59250 (0.0009) -[2023-10-12 05:41:48,589][78091] Updated weights for policy 0, policy_version 59260 (0.0007) -[2023-10-12 05:41:50,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 121077760. Throughput: 0: 1607.6, 1: 1575.8. Samples: 30275702. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 05:41:50,202][77203] Avg episode reward: [(0, '54.890'), (1, '54.050')] -[2023-10-12 05:41:50,203][77950] Saving new best policy, reward=54.050! -[2023-10-12 05:41:51,816][78123] Updated weights for policy 1, policy_version 58980 (0.0008) -[2023-10-12 05:41:52,184][78123] Updated weights for policy 1, policy_version 58990 (0.0009) -[2023-10-12 05:41:52,553][78123] Updated weights for policy 1, policy_version 59000 (0.0008) -[2023-10-12 05:41:52,813][78091] Updated weights for policy 0, policy_version 59270 (0.0007) -[2023-10-12 05:41:53,193][78091] Updated weights for policy 0, policy_version 59280 (0.0007) -[2023-10-12 05:41:53,557][78091] Updated weights for policy 0, policy_version 59290 (0.0009) -[2023-10-12 05:41:55,201][77203] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 121143296. Throughput: 0: 1606.0, 1: 1580.7. Samples: 30295390. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 05:41:55,202][77203] Avg episode reward: [(0, '47.910'), (1, '49.080')] -[2023-10-12 05:41:56,930][78123] Updated weights for policy 1, policy_version 59010 (0.0007) -[2023-10-12 05:41:57,298][78123] Updated weights for policy 1, policy_version 59020 (0.0009) -[2023-10-12 05:41:57,670][78123] Updated weights for policy 1, policy_version 59030 (0.0010) -[2023-10-12 05:41:57,683][78091] Updated weights for policy 0, policy_version 59300 (0.0009) -[2023-10-12 05:41:58,030][78123] Updated weights for policy 1, policy_version 59040 (0.0009) -[2023-10-12 05:41:58,052][78091] Updated weights for policy 0, policy_version 59310 (0.0007) -[2023-10-12 05:41:58,420][78091] Updated weights for policy 0, policy_version 59320 (0.0009) -[2023-10-12 05:42:00,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 121208832. Throughput: 0: 1619.4, 1: 1587.1. Samples: 30305348. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 05:42:00,202][77203] Avg episode reward: [(0, '52.000'), (1, '49.840')] -[2023-10-12 05:42:02,246][78123] Updated weights for policy 1, policy_version 59050 (0.0007) -[2023-10-12 05:42:02,617][78123] Updated weights for policy 1, policy_version 59060 (0.0008) -[2023-10-12 05:42:02,869][78091] Updated weights for policy 0, policy_version 59330 (0.0008) -[2023-10-12 05:42:02,973][78123] Updated weights for policy 1, policy_version 59070 (0.0010) -[2023-10-12 05:42:03,233][78091] Updated weights for policy 0, policy_version 59340 (0.0010) -[2023-10-12 05:42:03,597][78091] Updated weights for policy 0, policy_version 59350 (0.0009) -[2023-10-12 05:42:03,971][78091] Updated weights for policy 0, policy_version 59360 (0.0009) -[2023-10-12 05:42:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 121274368. Throughput: 0: 1601.5, 1: 1588.3. Samples: 30323968. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-12 05:42:05,202][77203] Avg episode reward: [(0, '52.790'), (1, '52.070')] -[2023-10-12 05:42:07,330][78123] Updated weights for policy 1, policy_version 59080 (0.0007) -[2023-10-12 05:42:07,696][78123] Updated weights for policy 1, policy_version 59090 (0.0008) -[2023-10-12 05:42:08,059][78123] Updated weights for policy 1, policy_version 59100 (0.0009) -[2023-10-12 05:42:08,243][78091] Updated weights for policy 0, policy_version 59370 (0.0009) -[2023-10-12 05:42:08,623][78091] Updated weights for policy 0, policy_version 59380 (0.0008) -[2023-10-12 05:42:08,993][78091] Updated weights for policy 0, policy_version 59390 (0.0010) -[2023-10-12 05:42:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 121339904. Throughput: 0: 1587.6, 1: 1590.2. Samples: 30343108. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 05:42:10,201][77203] Avg episode reward: [(0, '49.660'), (1, '52.800')] -[2023-10-12 05:42:12,344][78123] Updated weights for policy 1, policy_version 59110 (0.0010) -[2023-10-12 05:42:12,713][78123] Updated weights for policy 1, policy_version 59120 (0.0010) -[2023-10-12 05:42:13,077][78123] Updated weights for policy 1, policy_version 59130 (0.0008) -[2023-10-12 05:42:13,378][78091] Updated weights for policy 0, policy_version 59400 (0.0009) -[2023-10-12 05:42:13,756][78091] Updated weights for policy 0, policy_version 59410 (0.0009) -[2023-10-12 05:42:14,127][78091] Updated weights for policy 0, policy_version 59420 (0.0009) -[2023-10-12 05:42:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 121405440. Throughput: 0: 1610.6, 1: 1602.4. Samples: 30353558. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 05:42:15,202][77203] Avg episode reward: [(0, '49.580'), (1, '44.050')] -[2023-10-12 05:42:17,515][78123] Updated weights for policy 1, policy_version 59140 (0.0010) -[2023-10-12 05:42:17,888][78123] Updated weights for policy 1, policy_version 59150 (0.0008) -[2023-10-12 05:42:18,254][78123] Updated weights for policy 1, policy_version 59160 (0.0009) -[2023-10-12 05:42:18,350][78091] Updated weights for policy 0, policy_version 59430 (0.0008) -[2023-10-12 05:42:18,727][78091] Updated weights for policy 0, policy_version 59440 (0.0008) -[2023-10-12 05:42:19,103][78091] Updated weights for policy 0, policy_version 59450 (0.0009) -[2023-10-12 05:42:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 121470976. Throughput: 0: 1601.3, 1: 1590.9. Samples: 30371586. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 05:42:20,201][77203] Avg episode reward: [(0, '52.570'), (1, '49.430')] -[2023-10-12 05:42:22,497][78123] Updated weights for policy 1, policy_version 59170 (0.0010) -[2023-10-12 05:42:22,863][78123] Updated weights for policy 1, policy_version 59180 (0.0009) -[2023-10-12 05:42:23,235][78123] Updated weights for policy 1, policy_version 59190 (0.0008) -[2023-10-12 05:42:23,484][78091] Updated weights for policy 0, policy_version 59460 (0.0008) -[2023-10-12 05:42:23,604][78123] Updated weights for policy 1, policy_version 59200 (0.0010) -[2023-10-12 05:42:23,848][78091] Updated weights for policy 0, policy_version 59470 (0.0007) -[2023-10-12 05:42:24,221][78091] Updated weights for policy 0, policy_version 59480 (0.0009) -[2023-10-12 05:42:25,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 121536512. Throughput: 0: 1590.4, 1: 1592.7. Samples: 30390726. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 05:42:25,202][77203] Avg episode reward: [(0, '45.090'), (1, '51.260')] -[2023-10-12 05:42:27,875][78123] Updated weights for policy 1, policy_version 59210 (0.0009) -[2023-10-12 05:42:28,256][78123] Updated weights for policy 1, policy_version 59220 (0.0010) -[2023-10-12 05:42:28,628][78091] Updated weights for policy 0, policy_version 59490 (0.0009) -[2023-10-12 05:42:28,630][78123] Updated weights for policy 1, policy_version 59230 (0.0009) -[2023-10-12 05:42:28,997][78091] Updated weights for policy 0, policy_version 59500 (0.0007) -[2023-10-12 05:42:29,373][78091] Updated weights for policy 0, policy_version 59510 (0.0009) -[2023-10-12 05:42:29,735][78091] Updated weights for policy 0, policy_version 59520 (0.0009) -[2023-10-12 05:42:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 121602048. Throughput: 0: 1601.1, 1: 1612.6. Samples: 30401532. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 05:42:30,202][77203] Avg episode reward: [(0, '49.740'), (1, '55.890')] -[2023-10-12 05:42:30,203][77950] Saving new best policy, reward=55.890! -[2023-10-12 05:42:33,082][78123] Updated weights for policy 1, policy_version 59240 (0.0010) -[2023-10-12 05:42:33,455][78123] Updated weights for policy 1, policy_version 59250 (0.0010) -[2023-10-12 05:42:33,827][78123] Updated weights for policy 1, policy_version 59260 (0.0009) -[2023-10-12 05:42:34,055][78091] Updated weights for policy 0, policy_version 59530 (0.0010) -[2023-10-12 05:42:34,433][78091] Updated weights for policy 0, policy_version 59540 (0.0008) -[2023-10-12 05:42:34,799][78091] Updated weights for policy 0, policy_version 59550 (0.0008) -[2023-10-12 05:42:35,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 121667584. Throughput: 0: 1618.3, 1: 1590.5. Samples: 30420096. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 05:42:35,202][77203] Avg episode reward: [(0, '49.720'), (1, '46.660')] -[2023-10-12 05:42:38,090][78123] Updated weights for policy 1, policy_version 59270 (0.0009) -[2023-10-12 05:42:38,449][78123] Updated weights for policy 1, policy_version 59280 (0.0008) -[2023-10-12 05:42:38,827][78123] Updated weights for policy 1, policy_version 59290 (0.0007) -[2023-10-12 05:42:39,126][78091] Updated weights for policy 0, policy_version 59560 (0.0008) -[2023-10-12 05:42:39,497][78091] Updated weights for policy 0, policy_version 59570 (0.0010) -[2023-10-12 05:42:39,868][78091] Updated weights for policy 0, policy_version 59580 (0.0009) -[2023-10-12 05:42:40,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 121733120. Throughput: 0: 1595.7, 1: 1583.6. Samples: 30438458. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 05:42:40,202][77203] Avg episode reward: [(0, '55.930'), (1, '53.500')] -[2023-10-12 05:42:43,063][78123] Updated weights for policy 1, policy_version 59300 (0.0008) -[2023-10-12 05:42:43,417][78123] Updated weights for policy 1, policy_version 59310 (0.0010) -[2023-10-12 05:42:43,789][78123] Updated weights for policy 1, policy_version 59320 (0.0009) -[2023-10-12 05:42:44,331][78091] Updated weights for policy 0, policy_version 59590 (0.0009) -[2023-10-12 05:42:44,688][78091] Updated weights for policy 0, policy_version 59600 (0.0011) -[2023-10-12 05:42:45,054][78091] Updated weights for policy 0, policy_version 59610 (0.0011) -[2023-10-12 05:42:45,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 121765888. Throughput: 0: 1591.3, 1: 1604.4. Samples: 30449156. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 05:42:45,201][77203] Avg episode reward: [(0, '52.480'), (1, '58.250')] -[2023-10-12 05:42:45,202][77950] Saving new best policy, reward=58.250! -[2023-10-12 05:42:48,052][78123] Updated weights for policy 1, policy_version 59330 (0.0008) -[2023-10-12 05:42:48,416][78123] Updated weights for policy 1, policy_version 59340 (0.0008) -[2023-10-12 05:42:48,781][78123] Updated weights for policy 1, policy_version 59350 (0.0008) -[2023-10-12 05:42:49,150][78123] Updated weights for policy 1, policy_version 59360 (0.0008) -[2023-10-12 05:42:49,392][78091] Updated weights for policy 0, policy_version 59620 (0.0008) -[2023-10-12 05:42:49,766][78091] Updated weights for policy 0, policy_version 59630 (0.0008) -[2023-10-12 05:42:50,131][78091] Updated weights for policy 0, policy_version 59640 (0.0007) -[2023-10-12 05:42:50,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 121831424. Throughput: 0: 1606.8, 1: 1591.9. Samples: 30467908. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 05:42:50,202][77203] Avg episode reward: [(0, '45.090'), (1, '47.430')] -[2023-10-12 05:42:53,567][78123] Updated weights for policy 1, policy_version 59370 (0.0007) -[2023-10-12 05:42:53,928][78123] Updated weights for policy 1, policy_version 59380 (0.0008) -[2023-10-12 05:42:54,197][78091] Updated weights for policy 0, policy_version 59650 (0.0007) -[2023-10-12 05:42:54,289][78123] Updated weights for policy 1, policy_version 59390 (0.0009) -[2023-10-12 05:42:54,560][78091] Updated weights for policy 0, policy_version 59660 (0.0008) -[2023-10-12 05:42:54,922][78091] Updated weights for policy 0, policy_version 59670 (0.0008) -[2023-10-12 05:42:55,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 121896960. Throughput: 0: 1606.4, 1: 1582.7. Samples: 30486618. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-12 05:42:55,202][77203] Avg episode reward: [(0, '47.530'), (1, '50.600')] -[2023-10-12 05:42:55,300][78091] Updated weights for policy 0, policy_version 59680 (0.0009) -[2023-10-12 05:42:58,567][78123] Updated weights for policy 1, policy_version 59400 (0.0011) -[2023-10-12 05:42:58,936][78123] Updated weights for policy 1, policy_version 59410 (0.0009) -[2023-10-12 05:42:59,299][78123] Updated weights for policy 1, policy_version 59420 (0.0009) -[2023-10-12 05:42:59,742][78091] Updated weights for policy 0, policy_version 59690 (0.0009) -[2023-10-12 05:43:00,110][78091] Updated weights for policy 0, policy_version 59700 (0.0009) -[2023-10-12 05:43:00,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 121962496. Throughput: 0: 1593.2, 1: 1595.4. Samples: 30497048. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-12 05:43:00,202][77203] Avg episode reward: [(0, '54.910'), (1, '48.020')] -[2023-10-12 05:43:00,476][78091] Updated weights for policy 0, policy_version 59710 (0.0008) -[2023-10-12 05:43:03,825][78123] Updated weights for policy 1, policy_version 59430 (0.0009) -[2023-10-12 05:43:04,196][78123] Updated weights for policy 1, policy_version 59440 (0.0010) -[2023-10-12 05:43:04,565][78123] Updated weights for policy 1, policy_version 59450 (0.0008) -[2023-10-12 05:43:04,725][78091] Updated weights for policy 0, policy_version 59720 (0.0009) -[2023-10-12 05:43:05,094][78091] Updated weights for policy 0, policy_version 59730 (0.0008) -[2023-10-12 05:43:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 122028032. Throughput: 0: 1607.6, 1: 1606.5. Samples: 30516224. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-12 05:43:05,202][77203] Avg episode reward: [(0, '57.120'), (1, '57.940')] -[2023-10-12 05:43:05,469][78091] Updated weights for policy 0, policy_version 59740 (0.0007) -[2023-10-12 05:43:08,956][78123] Updated weights for policy 1, policy_version 59460 (0.0009) -[2023-10-12 05:43:09,323][78123] Updated weights for policy 1, policy_version 59470 (0.0009) -[2023-10-12 05:43:09,684][78123] Updated weights for policy 1, policy_version 59480 (0.0010) -[2023-10-12 05:43:09,827][78091] Updated weights for policy 0, policy_version 59750 (0.0008) -[2023-10-12 05:43:10,200][78091] Updated weights for policy 0, policy_version 59760 (0.0010) -[2023-10-12 05:43:10,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 122093568. Throughput: 0: 1617.6, 1: 1585.1. Samples: 30534848. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-12 05:43:10,201][77203] Avg episode reward: [(0, '45.060'), (1, '46.140')] -[2023-10-12 05:43:10,210][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000059488_60915712.pth... -[2023-10-12 05:43:10,242][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000057984_59375616.pth -[2023-10-12 05:43:10,245][77950] Saving a milestone ./train_atari/atari_hero_APPO/checkpoint_p1/milestones/checkpoint_000059488_60915712.pth -[2023-10-12 05:43:10,570][78091] Updated weights for policy 0, policy_version 59770 (0.0008) -[2023-10-12 05:43:10,780][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000059776_61210624.pth... -[2023-10-12 05:43:10,809][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000058272_59670528.pth -[2023-10-12 05:43:10,813][77792] Saving a milestone ./train_atari/atari_hero_APPO/checkpoint_p0/milestones/checkpoint_000059776_61210624.pth -[2023-10-12 05:43:14,165][78123] Updated weights for policy 1, policy_version 59490 (0.0009) -[2023-10-12 05:43:14,531][78123] Updated weights for policy 1, policy_version 59500 (0.0009) -[2023-10-12 05:43:14,896][78123] Updated weights for policy 1, policy_version 59510 (0.0009) -[2023-10-12 05:43:14,973][78091] Updated weights for policy 0, policy_version 59780 (0.0009) -[2023-10-12 05:43:15,201][77203] Fps is (10 sec: 9830.6, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 122126336. Throughput: 0: 1595.6, 1: 1582.6. Samples: 30544552. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-12 05:43:15,201][77203] Avg episode reward: [(0, '45.550'), (1, '49.120')] -[2023-10-12 05:43:15,269][78123] Updated weights for policy 1, policy_version 59520 (0.0007) -[2023-10-12 05:43:15,337][78091] Updated weights for policy 0, policy_version 59790 (0.0009) -[2023-10-12 05:43:15,708][78091] Updated weights for policy 0, policy_version 59800 (0.0011) -[2023-10-12 05:43:19,565][78123] Updated weights for policy 1, policy_version 59530 (0.0007) -[2023-10-12 05:43:19,932][78123] Updated weights for policy 1, policy_version 59540 (0.0007) -[2023-10-12 05:43:20,048][78091] Updated weights for policy 0, policy_version 59810 (0.0010) -[2023-10-12 05:43:20,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 122191872. Throughput: 0: 1594.9, 1: 1597.5. Samples: 30563756. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-12 05:43:20,201][77203] Avg episode reward: [(0, '51.510'), (1, '48.650')] -[2023-10-12 05:43:20,304][78123] Updated weights for policy 1, policy_version 59550 (0.0008) -[2023-10-12 05:43:20,421][78091] Updated weights for policy 0, policy_version 59820 (0.0009) -[2023-10-12 05:43:20,790][78091] Updated weights for policy 0, policy_version 59830 (0.0009) -[2023-10-12 05:43:21,163][78091] Updated weights for policy 0, policy_version 59840 (0.0008) -[2023-10-12 05:43:24,662][78123] Updated weights for policy 1, policy_version 59560 (0.0010) -[2023-10-12 05:43:25,025][78123] Updated weights for policy 1, policy_version 59570 (0.0010) -[2023-10-12 05:43:25,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 122257408. Throughput: 0: 1614.2, 1: 1596.7. Samples: 30582950. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-12 05:43:25,202][77203] Avg episode reward: [(0, '53.210'), (1, '55.760')] -[2023-10-12 05:43:25,390][78123] Updated weights for policy 1, policy_version 59580 (0.0010) -[2023-10-12 05:43:25,657][78091] Updated weights for policy 0, policy_version 59850 (0.0008) -[2023-10-12 05:43:26,038][78091] Updated weights for policy 0, policy_version 59860 (0.0008) -[2023-10-12 05:43:26,403][78091] Updated weights for policy 0, policy_version 59870 (0.0007) -[2023-10-12 05:43:29,736][78123] Updated weights for policy 1, policy_version 59590 (0.0010) -[2023-10-12 05:43:30,109][78123] Updated weights for policy 1, policy_version 59600 (0.0009) -[2023-10-12 05:43:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 122322944. Throughput: 0: 1592.8, 1: 1574.7. Samples: 30591696. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-12 05:43:30,201][77203] Avg episode reward: [(0, '51.490'), (1, '44.010')] -[2023-10-12 05:43:30,463][78123] Updated weights for policy 1, policy_version 59610 (0.0008) -[2023-10-12 05:43:30,553][78091] Updated weights for policy 0, policy_version 59880 (0.0009) -[2023-10-12 05:43:30,922][78091] Updated weights for policy 0, policy_version 59890 (0.0008) -[2023-10-12 05:43:31,296][78091] Updated weights for policy 0, policy_version 59900 (0.0009) -[2023-10-12 05:43:34,821][78123] Updated weights for policy 1, policy_version 59620 (0.0008) -[2023-10-12 05:43:35,176][78123] Updated weights for policy 1, policy_version 59630 (0.0009) -[2023-10-12 05:43:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 122388480. Throughput: 0: 1596.9, 1: 1587.7. Samples: 30611216. Policy #0 lag: (min: 31.0, avg: 44.9, max: 63.0) -[2023-10-12 05:43:35,202][77203] Avg episode reward: [(0, '48.030'), (1, '46.010')] -[2023-10-12 05:43:35,530][78091] Updated weights for policy 0, policy_version 59910 (0.0009) -[2023-10-12 05:43:35,544][78123] Updated weights for policy 1, policy_version 59640 (0.0007) -[2023-10-12 05:43:35,899][78091] Updated weights for policy 0, policy_version 59920 (0.0009) -[2023-10-12 05:43:36,268][78091] Updated weights for policy 0, policy_version 59930 (0.0009) -[2023-10-12 05:43:39,967][78123] Updated weights for policy 1, policy_version 59650 (0.0007) -[2023-10-12 05:43:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 122454016. Throughput: 0: 1606.6, 1: 1595.2. Samples: 30630696. Policy #0 lag: (min: 31.0, avg: 44.9, max: 63.0) -[2023-10-12 05:43:40,202][77203] Avg episode reward: [(0, '52.970'), (1, '48.330')] -[2023-10-12 05:43:40,336][78123] Updated weights for policy 1, policy_version 59660 (0.0009) -[2023-10-12 05:43:40,567][78091] Updated weights for policy 0, policy_version 59940 (0.0008) -[2023-10-12 05:43:40,718][78123] Updated weights for policy 1, policy_version 59670 (0.0008) -[2023-10-12 05:43:40,942][78091] Updated weights for policy 0, policy_version 59950 (0.0009) -[2023-10-12 05:43:41,092][78123] Updated weights for policy 1, policy_version 59680 (0.0008) -[2023-10-12 05:43:41,306][78091] Updated weights for policy 0, policy_version 59960 (0.0010) -[2023-10-12 05:43:45,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 122519552. Throughput: 0: 1589.7, 1: 1570.0. Samples: 30639232. Policy #0 lag: (min: 31.0, avg: 44.9, max: 63.0) -[2023-10-12 05:43:45,202][77203] Avg episode reward: [(0, '47.500'), (1, '50.250')] -[2023-10-12 05:43:45,482][78123] Updated weights for policy 1, policy_version 59690 (0.0008) -[2023-10-12 05:43:45,554][78091] Updated weights for policy 0, policy_version 59970 (0.0011) -[2023-10-12 05:43:45,860][78123] Updated weights for policy 1, policy_version 59700 (0.0007) -[2023-10-12 05:43:45,930][78091] Updated weights for policy 0, policy_version 59980 (0.0010) -[2023-10-12 05:43:46,218][78123] Updated weights for policy 1, policy_version 59710 (0.0008) -[2023-10-12 05:43:46,295][78091] Updated weights for policy 0, policy_version 59990 (0.0010) -[2023-10-12 05:43:46,663][78091] Updated weights for policy 0, policy_version 60000 (0.0010) -[2023-10-12 05:43:50,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 122585088. Throughput: 0: 1587.9, 1: 1575.9. Samples: 30658594. Policy #0 lag: (min: 31.0, avg: 44.9, max: 63.0) -[2023-10-12 05:43:50,202][77203] Avg episode reward: [(0, '52.670'), (1, '42.520')] -[2023-10-12 05:43:50,540][78123] Updated weights for policy 1, policy_version 59720 (0.0007) -[2023-10-12 05:43:50,913][78123] Updated weights for policy 1, policy_version 59730 (0.0009) -[2023-10-12 05:43:51,081][78091] Updated weights for policy 0, policy_version 60010 (0.0007) -[2023-10-12 05:43:51,284][78123] Updated weights for policy 1, policy_version 59740 (0.0007) -[2023-10-12 05:43:51,448][78091] Updated weights for policy 0, policy_version 60020 (0.0008) -[2023-10-12 05:43:51,813][78091] Updated weights for policy 0, policy_version 60030 (0.0010) -[2023-10-12 05:43:55,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 122650624. Throughput: 0: 1591.9, 1: 1590.4. Samples: 30678054. Policy #0 lag: (min: 31.0, avg: 44.9, max: 63.0) -[2023-10-12 05:43:55,201][77203] Avg episode reward: [(0, '52.320'), (1, '46.630')] -[2023-10-12 05:43:55,770][78123] Updated weights for policy 1, policy_version 59750 (0.0007) -[2023-10-12 05:43:55,994][78091] Updated weights for policy 0, policy_version 60040 (0.0009) -[2023-10-12 05:43:56,135][78123] Updated weights for policy 1, policy_version 59760 (0.0007) -[2023-10-12 05:43:56,352][78091] Updated weights for policy 0, policy_version 60050 (0.0009) -[2023-10-12 05:43:56,504][78123] Updated weights for policy 1, policy_version 59770 (0.0007) -[2023-10-12 05:43:56,725][78091] Updated weights for policy 0, policy_version 60060 (0.0009) -[2023-10-12 05:44:00,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 122716160. Throughput: 0: 1584.8, 1: 1571.4. Samples: 30686580. Policy #0 lag: (min: 31.0, avg: 44.9, max: 63.0) -[2023-10-12 05:44:00,202][77203] Avg episode reward: [(0, '55.410'), (1, '48.400')] -[2023-10-12 05:44:00,877][78123] Updated weights for policy 1, policy_version 59780 (0.0008) -[2023-10-12 05:44:01,166][78091] Updated weights for policy 0, policy_version 60070 (0.0008) -[2023-10-12 05:44:01,240][78123] Updated weights for policy 1, policy_version 59790 (0.0008) -[2023-10-12 05:44:01,532][78091] Updated weights for policy 0, policy_version 60080 (0.0008) -[2023-10-12 05:44:01,609][78123] Updated weights for policy 1, policy_version 59800 (0.0008) -[2023-10-12 05:44:01,896][78091] Updated weights for policy 0, policy_version 60090 (0.0009) -[2023-10-12 05:44:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 122781696. Throughput: 0: 1585.1, 1: 1574.4. Samples: 30705932. Policy #0 lag: (min: 31.0, avg: 44.9, max: 63.0) -[2023-10-12 05:44:05,202][77203] Avg episode reward: [(0, '51.340'), (1, '48.850')] -[2023-10-12 05:44:05,762][78123] Updated weights for policy 1, policy_version 59810 (0.0007) -[2023-10-12 05:44:06,121][78123] Updated weights for policy 1, policy_version 59820 (0.0007) -[2023-10-12 05:44:06,140][78091] Updated weights for policy 0, policy_version 60100 (0.0007) -[2023-10-12 05:44:06,490][78123] Updated weights for policy 1, policy_version 59830 (0.0009) -[2023-10-12 05:44:06,517][78091] Updated weights for policy 0, policy_version 60110 (0.0008) -[2023-10-12 05:44:06,853][78123] Updated weights for policy 1, policy_version 59840 (0.0008) -[2023-10-12 05:44:06,886][78091] Updated weights for policy 0, policy_version 60120 (0.0007) -[2023-10-12 05:44:10,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 122847232. Throughput: 0: 1589.5, 1: 1585.1. Samples: 30725806. Policy #0 lag: (min: 31.0, avg: 44.9, max: 63.0) -[2023-10-12 05:44:10,202][77203] Avg episode reward: [(0, '53.070'), (1, '46.420')] -[2023-10-12 05:44:11,165][78123] Updated weights for policy 1, policy_version 59850 (0.0009) -[2023-10-12 05:44:11,243][78091] Updated weights for policy 0, policy_version 60130 (0.0009) -[2023-10-12 05:44:11,530][78123] Updated weights for policy 1, policy_version 59860 (0.0009) -[2023-10-12 05:44:11,643][78091] Updated weights for policy 0, policy_version 60140 (0.0008) -[2023-10-12 05:44:11,890][78123] Updated weights for policy 1, policy_version 59870 (0.0008) -[2023-10-12 05:44:12,018][78091] Updated weights for policy 0, policy_version 60150 (0.0007) -[2023-10-12 05:44:12,388][78091] Updated weights for policy 0, policy_version 60160 (0.0008) -[2023-10-12 05:44:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 122912768. Throughput: 0: 1587.9, 1: 1582.0. Samples: 30734338. Policy #0 lag: (min: 19.0, avg: 38.1, max: 40.0) -[2023-10-12 05:44:15,202][77203] Avg episode reward: [(0, '55.270'), (1, '48.890')] -[2023-10-12 05:44:15,996][78123] Updated weights for policy 1, policy_version 59880 (0.0010) -[2023-10-12 05:44:16,373][78123] Updated weights for policy 1, policy_version 59890 (0.0009) -[2023-10-12 05:44:16,665][78091] Updated weights for policy 0, policy_version 60170 (0.0007) -[2023-10-12 05:44:16,742][78123] Updated weights for policy 1, policy_version 59900 (0.0009) -[2023-10-12 05:44:17,044][78091] Updated weights for policy 0, policy_version 60180 (0.0007) -[2023-10-12 05:44:17,407][78091] Updated weights for policy 0, policy_version 60190 (0.0009) -[2023-10-12 05:44:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 122978304. Throughput: 0: 1586.6, 1: 1583.6. Samples: 30753878. Policy #0 lag: (min: 19.0, avg: 38.1, max: 40.0) -[2023-10-12 05:44:20,202][77203] Avg episode reward: [(0, '52.940'), (1, '53.520')] -[2023-10-12 05:44:21,095][78123] Updated weights for policy 1, policy_version 59910 (0.0008) -[2023-10-12 05:44:21,458][78123] Updated weights for policy 1, policy_version 59920 (0.0008) -[2023-10-12 05:44:21,749][78091] Updated weights for policy 0, policy_version 60200 (0.0009) -[2023-10-12 05:44:21,818][78123] Updated weights for policy 1, policy_version 59930 (0.0010) -[2023-10-12 05:44:22,124][78091] Updated weights for policy 0, policy_version 60210 (0.0008) -[2023-10-12 05:44:22,488][78091] Updated weights for policy 0, policy_version 60220 (0.0009) -[2023-10-12 05:44:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 123043840. Throughput: 0: 1586.3, 1: 1584.0. Samples: 30773358. Policy #0 lag: (min: 19.0, avg: 38.1, max: 40.0) -[2023-10-12 05:44:25,201][77203] Avg episode reward: [(0, '49.170'), (1, '52.700')] -[2023-10-12 05:44:26,270][78123] Updated weights for policy 1, policy_version 59940 (0.0008) -[2023-10-12 05:44:26,632][78123] Updated weights for policy 1, policy_version 59950 (0.0008) -[2023-10-12 05:44:26,728][78091] Updated weights for policy 0, policy_version 60230 (0.0010) -[2023-10-12 05:44:27,004][78123] Updated weights for policy 1, policy_version 59960 (0.0007) -[2023-10-12 05:44:27,096][78091] Updated weights for policy 0, policy_version 60240 (0.0007) -[2023-10-12 05:44:27,465][78091] Updated weights for policy 0, policy_version 60250 (0.0007) -[2023-10-12 05:44:30,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 123109376. Throughput: 0: 1587.3, 1: 1585.8. Samples: 30782024. Policy #0 lag: (min: 19.0, avg: 38.1, max: 40.0) -[2023-10-12 05:44:30,201][77203] Avg episode reward: [(0, '46.400'), (1, '50.870')] -[2023-10-12 05:44:31,297][78123] Updated weights for policy 1, policy_version 59970 (0.0008) -[2023-10-12 05:44:31,668][78123] Updated weights for policy 1, policy_version 59980 (0.0009) -[2023-10-12 05:44:31,834][78091] Updated weights for policy 0, policy_version 60260 (0.0007) -[2023-10-12 05:44:32,037][78123] Updated weights for policy 1, policy_version 59990 (0.0008) -[2023-10-12 05:44:32,199][78091] Updated weights for policy 0, policy_version 60270 (0.0007) -[2023-10-12 05:44:32,400][78123] Updated weights for policy 1, policy_version 60000 (0.0009) -[2023-10-12 05:44:32,576][78091] Updated weights for policy 0, policy_version 60280 (0.0009) -[2023-10-12 05:44:35,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 123174912. Throughput: 0: 1589.7, 1: 1592.4. Samples: 30801790. Policy #0 lag: (min: 19.0, avg: 38.1, max: 40.0) -[2023-10-12 05:44:35,202][77203] Avg episode reward: [(0, '52.210'), (1, '51.740')] -[2023-10-12 05:44:36,867][78123] Updated weights for policy 1, policy_version 60010 (0.0010) -[2023-10-12 05:44:36,874][78091] Updated weights for policy 0, policy_version 60290 (0.0009) -[2023-10-12 05:44:37,228][78123] Updated weights for policy 1, policy_version 60020 (0.0007) -[2023-10-12 05:44:37,253][78091] Updated weights for policy 0, policy_version 60300 (0.0007) -[2023-10-12 05:44:37,600][78123] Updated weights for policy 1, policy_version 60030 (0.0008) -[2023-10-12 05:44:37,613][78091] Updated weights for policy 0, policy_version 60310 (0.0009) -[2023-10-12 05:44:37,987][78091] Updated weights for policy 0, policy_version 60320 (0.0008) -[2023-10-12 05:44:40,201][77203] Fps is (10 sec: 13106.7, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 123240448. Throughput: 0: 1587.5, 1: 1595.0. Samples: 30821270. Policy #0 lag: (min: 19.0, avg: 38.1, max: 40.0) -[2023-10-12 05:44:40,202][77203] Avg episode reward: [(0, '50.340'), (1, '51.220')] -[2023-10-12 05:44:41,887][78123] Updated weights for policy 1, policy_version 60040 (0.0008) -[2023-10-12 05:44:42,242][78123] Updated weights for policy 1, policy_version 60050 (0.0009) -[2023-10-12 05:44:42,318][78091] Updated weights for policy 0, policy_version 60330 (0.0009) -[2023-10-12 05:44:42,614][78123] Updated weights for policy 1, policy_version 60060 (0.0007) -[2023-10-12 05:44:42,690][78091] Updated weights for policy 0, policy_version 60340 (0.0008) -[2023-10-12 05:44:43,061][78091] Updated weights for policy 0, policy_version 60350 (0.0010) -[2023-10-12 05:44:45,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 123305984. Throughput: 0: 1597.7, 1: 1594.8. Samples: 30830242. Policy #0 lag: (min: 19.0, avg: 38.1, max: 40.0) -[2023-10-12 05:44:45,201][77203] Avg episode reward: [(0, '52.000'), (1, '50.210')] -[2023-10-12 05:44:46,876][78123] Updated weights for policy 1, policy_version 60070 (0.0008) -[2023-10-12 05:44:47,235][78123] Updated weights for policy 1, policy_version 60080 (0.0009) -[2023-10-12 05:44:47,320][78091] Updated weights for policy 0, policy_version 60360 (0.0008) -[2023-10-12 05:44:47,607][78123] Updated weights for policy 1, policy_version 60090 (0.0008) -[2023-10-12 05:44:47,689][78091] Updated weights for policy 0, policy_version 60370 (0.0009) -[2023-10-12 05:44:48,056][78091] Updated weights for policy 0, policy_version 60380 (0.0009) -[2023-10-12 05:44:50,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 123371520. Throughput: 0: 1591.6, 1: 1594.6. Samples: 30849312. Policy #0 lag: (min: 19.0, avg: 38.1, max: 40.0) -[2023-10-12 05:44:50,202][77203] Avg episode reward: [(0, '48.110'), (1, '49.450')] -[2023-10-12 05:44:52,051][78123] Updated weights for policy 1, policy_version 60100 (0.0008) -[2023-10-12 05:44:52,285][78091] Updated weights for policy 0, policy_version 60390 (0.0008) -[2023-10-12 05:44:52,420][78123] Updated weights for policy 1, policy_version 60110 (0.0008) -[2023-10-12 05:44:52,649][78091] Updated weights for policy 0, policy_version 60400 (0.0007) -[2023-10-12 05:44:52,792][78123] Updated weights for policy 1, policy_version 60120 (0.0007) -[2023-10-12 05:44:53,024][78091] Updated weights for policy 0, policy_version 60410 (0.0007) -[2023-10-12 05:44:55,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 123437056. Throughput: 0: 1593.2, 1: 1588.7. Samples: 30868990. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-12 05:44:55,201][77203] Avg episode reward: [(0, '48.410'), (1, '49.090')] -[2023-10-12 05:44:57,153][78123] Updated weights for policy 1, policy_version 60130 (0.0008) -[2023-10-12 05:44:57,468][78091] Updated weights for policy 0, policy_version 60420 (0.0008) -[2023-10-12 05:44:57,515][78123] Updated weights for policy 1, policy_version 60140 (0.0007) -[2023-10-12 05:44:57,863][78091] Updated weights for policy 0, policy_version 60430 (0.0008) -[2023-10-12 05:44:57,889][78123] Updated weights for policy 1, policy_version 60150 (0.0008) -[2023-10-12 05:44:58,240][78091] Updated weights for policy 0, policy_version 60440 (0.0009) -[2023-10-12 05:44:58,264][78123] Updated weights for policy 1, policy_version 60160 (0.0008) -[2023-10-12 05:45:00,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 123502592. Throughput: 0: 1609.6, 1: 1598.1. Samples: 30878682. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-12 05:45:00,201][77203] Avg episode reward: [(0, '53.660'), (1, '46.240')] -[2023-10-12 05:45:02,461][78123] Updated weights for policy 1, policy_version 60170 (0.0008) -[2023-10-12 05:45:02,697][78091] Updated weights for policy 0, policy_version 60450 (0.0009) -[2023-10-12 05:45:02,826][78123] Updated weights for policy 1, policy_version 60180 (0.0007) -[2023-10-12 05:45:03,060][78091] Updated weights for policy 0, policy_version 60460 (0.0008) -[2023-10-12 05:45:03,197][78123] Updated weights for policy 1, policy_version 60190 (0.0008) -[2023-10-12 05:45:03,430][78091] Updated weights for policy 0, policy_version 60470 (0.0008) -[2023-10-12 05:45:03,800][78091] Updated weights for policy 0, policy_version 60480 (0.0008) -[2023-10-12 05:45:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 123568128. Throughput: 0: 1589.6, 1: 1588.7. Samples: 30896900. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-12 05:45:05,201][77203] Avg episode reward: [(0, '51.830'), (1, '54.060')] -[2023-10-12 05:45:07,606][78123] Updated weights for policy 1, policy_version 60200 (0.0009) -[2023-10-12 05:45:07,973][78123] Updated weights for policy 1, policy_version 60210 (0.0010) -[2023-10-12 05:45:07,990][78091] Updated weights for policy 0, policy_version 60490 (0.0008) -[2023-10-12 05:45:08,335][78123] Updated weights for policy 1, policy_version 60220 (0.0007) -[2023-10-12 05:45:08,361][78091] Updated weights for policy 0, policy_version 60500 (0.0007) -[2023-10-12 05:45:08,740][78091] Updated weights for policy 0, policy_version 60510 (0.0009) -[2023-10-12 05:45:10,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 123633664. Throughput: 0: 1588.3, 1: 1592.4. Samples: 30916492. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-12 05:45:10,202][77203] Avg episode reward: [(0, '52.050'), (1, '51.690')] -[2023-10-12 05:45:10,211][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000060512_61964288.pth... -[2023-10-12 05:45:10,211][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000060224_61669376.pth... -[2023-10-12 05:45:10,247][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000058752_60162048.pth -[2023-10-12 05:45:10,252][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000059008_60424192.pth -[2023-10-12 05:45:12,673][78123] Updated weights for policy 1, policy_version 60230 (0.0007) -[2023-10-12 05:45:13,028][78123] Updated weights for policy 1, policy_version 60240 (0.0008) -[2023-10-12 05:45:13,085][78091] Updated weights for policy 0, policy_version 60520 (0.0010) -[2023-10-12 05:45:13,395][78123] Updated weights for policy 1, policy_version 60250 (0.0007) -[2023-10-12 05:45:13,464][78091] Updated weights for policy 0, policy_version 60530 (0.0008) -[2023-10-12 05:45:13,829][78091] Updated weights for policy 0, policy_version 60540 (0.0010) -[2023-10-12 05:45:15,201][77203] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 123699200. Throughput: 0: 1612.5, 1: 1606.2. Samples: 30926868. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-12 05:45:15,202][77203] Avg episode reward: [(0, '48.220'), (1, '46.910')] -[2023-10-12 05:45:17,719][78123] Updated weights for policy 1, policy_version 60260 (0.0009) -[2023-10-12 05:45:18,082][78123] Updated weights for policy 1, policy_version 60270 (0.0009) -[2023-10-12 05:45:18,355][78091] Updated weights for policy 0, policy_version 60550 (0.0008) -[2023-10-12 05:45:18,459][78123] Updated weights for policy 1, policy_version 60280 (0.0009) -[2023-10-12 05:45:18,724][78091] Updated weights for policy 0, policy_version 60560 (0.0008) -[2023-10-12 05:45:19,088][78091] Updated weights for policy 0, policy_version 60570 (0.0008) -[2023-10-12 05:45:20,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 123764736. Throughput: 0: 1595.2, 1: 1579.7. Samples: 30944658. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-12 05:45:20,202][77203] Avg episode reward: [(0, '47.180'), (1, '48.840')] -[2023-10-12 05:45:23,003][78123] Updated weights for policy 1, policy_version 60290 (0.0010) -[2023-10-12 05:45:23,402][78123] Updated weights for policy 1, policy_version 60300 (0.0008) -[2023-10-12 05:45:23,505][78091] Updated weights for policy 0, policy_version 60580 (0.0009) -[2023-10-12 05:45:23,761][78123] Updated weights for policy 1, policy_version 60310 (0.0008) -[2023-10-12 05:45:23,877][78091] Updated weights for policy 0, policy_version 60590 (0.0008) -[2023-10-12 05:45:24,129][78123] Updated weights for policy 1, policy_version 60320 (0.0009) -[2023-10-12 05:45:24,244][78091] Updated weights for policy 0, policy_version 60600 (0.0010) -[2023-10-12 05:45:25,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 123830272. Throughput: 0: 1582.7, 1: 1574.9. Samples: 30963362. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-12 05:45:25,201][77203] Avg episode reward: [(0, '55.790'), (1, '56.230')] -[2023-10-12 05:45:28,393][78091] Updated weights for policy 0, policy_version 60610 (0.0008) -[2023-10-12 05:45:28,510][78123] Updated weights for policy 1, policy_version 60330 (0.0008) -[2023-10-12 05:45:28,757][78091] Updated weights for policy 0, policy_version 60620 (0.0007) -[2023-10-12 05:45:28,878][78123] Updated weights for policy 1, policy_version 60340 (0.0008) -[2023-10-12 05:45:29,129][78091] Updated weights for policy 0, policy_version 60630 (0.0008) -[2023-10-12 05:45:29,231][78123] Updated weights for policy 1, policy_version 60350 (0.0009) -[2023-10-12 05:45:29,490][78091] Updated weights for policy 0, policy_version 60640 (0.0008) -[2023-10-12 05:45:30,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 123895808. Throughput: 0: 1599.6, 1: 1601.4. Samples: 30974290. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-12 05:45:30,202][77203] Avg episode reward: [(0, '52.880'), (1, '57.330')] -[2023-10-12 05:45:33,620][78123] Updated weights for policy 1, policy_version 60360 (0.0007) -[2023-10-12 05:45:33,875][78091] Updated weights for policy 0, policy_version 60650 (0.0009) -[2023-10-12 05:45:33,993][78123] Updated weights for policy 1, policy_version 60370 (0.0009) -[2023-10-12 05:45:34,246][78091] Updated weights for policy 0, policy_version 60660 (0.0010) -[2023-10-12 05:45:34,354][78123] Updated weights for policy 1, policy_version 60380 (0.0007) -[2023-10-12 05:45:34,613][78091] Updated weights for policy 0, policy_version 60670 (0.0010) -[2023-10-12 05:45:35,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 123961344. Throughput: 0: 1604.8, 1: 1590.5. Samples: 30993100. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 05:45:35,202][77203] Avg episode reward: [(0, '46.000'), (1, '47.900')] -[2023-10-12 05:45:38,839][78123] Updated weights for policy 1, policy_version 60390 (0.0009) -[2023-10-12 05:45:38,874][78091] Updated weights for policy 0, policy_version 60680 (0.0008) -[2023-10-12 05:45:39,203][78123] Updated weights for policy 1, policy_version 60400 (0.0009) -[2023-10-12 05:45:39,253][78091] Updated weights for policy 0, policy_version 60690 (0.0008) -[2023-10-12 05:45:39,572][78123] Updated weights for policy 1, policy_version 60410 (0.0008) -[2023-10-12 05:45:39,620][78091] Updated weights for policy 0, policy_version 60700 (0.0008) -[2023-10-12 05:45:40,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 12885.0). Total num frames: 124026880. Throughput: 0: 1585.4, 1: 1573.6. Samples: 31011146. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 05:45:40,201][77203] Avg episode reward: [(0, '50.790'), (1, '49.890')] -[2023-10-12 05:45:43,748][78123] Updated weights for policy 1, policy_version 60420 (0.0008) -[2023-10-12 05:45:44,094][78091] Updated weights for policy 0, policy_version 60710 (0.0008) -[2023-10-12 05:45:44,120][78123] Updated weights for policy 1, policy_version 60430 (0.0009) -[2023-10-12 05:45:44,474][78091] Updated weights for policy 0, policy_version 60720 (0.0007) -[2023-10-12 05:45:44,482][78123] Updated weights for policy 1, policy_version 60440 (0.0008) -[2023-10-12 05:45:44,851][78091] Updated weights for policy 0, policy_version 60730 (0.0007) -[2023-10-12 05:45:45,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 124092416. Throughput: 0: 1596.8, 1: 1590.2. Samples: 31022100. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 05:45:45,202][77203] Avg episode reward: [(0, '52.230'), (1, '54.020')] -[2023-10-12 05:45:48,756][78123] Updated weights for policy 1, policy_version 60450 (0.0008) -[2023-10-12 05:45:49,093][78091] Updated weights for policy 0, policy_version 60740 (0.0010) -[2023-10-12 05:45:49,123][78123] Updated weights for policy 1, policy_version 60460 (0.0008) -[2023-10-12 05:45:49,462][78091] Updated weights for policy 0, policy_version 60750 (0.0008) -[2023-10-12 05:45:49,495][78123] Updated weights for policy 1, policy_version 60470 (0.0007) -[2023-10-12 05:45:49,827][78091] Updated weights for policy 0, policy_version 60760 (0.0008) -[2023-10-12 05:45:49,859][78123] Updated weights for policy 1, policy_version 60480 (0.0007) -[2023-10-12 05:45:50,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 124157952. Throughput: 0: 1610.4, 1: 1599.7. Samples: 31041356. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 05:45:50,201][77203] Avg episode reward: [(0, '51.830'), (1, '53.120')] -[2023-10-12 05:45:54,027][78091] Updated weights for policy 0, policy_version 60770 (0.0008) -[2023-10-12 05:45:54,190][78123] Updated weights for policy 1, policy_version 60490 (0.0009) -[2023-10-12 05:45:54,402][78091] Updated weights for policy 0, policy_version 60780 (0.0009) -[2023-10-12 05:45:54,563][78123] Updated weights for policy 1, policy_version 60500 (0.0009) -[2023-10-12 05:45:54,780][78091] Updated weights for policy 0, policy_version 60790 (0.0008) -[2023-10-12 05:45:54,934][78123] Updated weights for policy 1, policy_version 60510 (0.0008) -[2023-10-12 05:45:55,147][78091] Updated weights for policy 0, policy_version 60800 (0.0009) -[2023-10-12 05:45:55,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 12885.0). Total num frames: 124223488. Throughput: 0: 1591.9, 1: 1581.0. Samples: 31059276. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 05:45:55,202][77203] Avg episode reward: [(0, '49.220'), (1, '49.090')] -[2023-10-12 05:45:59,259][78123] Updated weights for policy 1, policy_version 60520 (0.0009) -[2023-10-12 05:45:59,571][78091] Updated weights for policy 0, policy_version 60810 (0.0010) -[2023-10-12 05:45:59,629][78123] Updated weights for policy 1, policy_version 60530 (0.0009) -[2023-10-12 05:45:59,944][78091] Updated weights for policy 0, policy_version 60820 (0.0009) -[2023-10-12 05:45:59,997][78123] Updated weights for policy 1, policy_version 60540 (0.0007) -[2023-10-12 05:46:00,201][77203] Fps is (10 sec: 9830.2, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 124256256. Throughput: 0: 1583.2, 1: 1581.5. Samples: 31069278. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 05:46:00,202][77203] Avg episode reward: [(0, '46.930'), (1, '47.500')] -[2023-10-12 05:46:00,309][78091] Updated weights for policy 0, policy_version 60830 (0.0009) -[2023-10-12 05:46:04,428][78123] Updated weights for policy 1, policy_version 60550 (0.0009) -[2023-10-12 05:46:04,646][78091] Updated weights for policy 0, policy_version 60840 (0.0010) -[2023-10-12 05:46:04,800][78123] Updated weights for policy 1, policy_version 60560 (0.0009) -[2023-10-12 05:46:05,017][78091] Updated weights for policy 0, policy_version 60850 (0.0010) -[2023-10-12 05:46:05,160][78123] Updated weights for policy 1, policy_version 60570 (0.0007) -[2023-10-12 05:46:05,201][77203] Fps is (10 sec: 6553.7, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 124289024. Throughput: 0: 1600.0, 1: 1602.9. Samples: 31088790. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 05:46:05,202][77203] Avg episode reward: [(0, '53.730'), (1, '56.560')] -[2023-10-12 05:46:05,382][78091] Updated weights for policy 0, policy_version 60860 (0.0009) -[2023-10-12 05:46:09,446][78123] Updated weights for policy 1, policy_version 60580 (0.0009) -[2023-10-12 05:46:09,735][78091] Updated weights for policy 0, policy_version 60870 (0.0009) -[2023-10-12 05:46:09,832][78123] Updated weights for policy 1, policy_version 60590 (0.0009) -[2023-10-12 05:46:10,110][78091] Updated weights for policy 0, policy_version 60880 (0.0010) -[2023-10-12 05:46:10,197][78123] Updated weights for policy 1, policy_version 60600 (0.0009) -[2023-10-12 05:46:10,201][77203] Fps is (10 sec: 9830.6, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 124354560. Throughput: 0: 1606.3, 1: 1597.8. Samples: 31107546. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 05:46:10,201][77203] Avg episode reward: [(0, '49.930'), (1, '57.830')] -[2023-10-12 05:46:10,468][78091] Updated weights for policy 0, policy_version 60890 (0.0011) -[2023-10-12 05:46:14,782][78123] Updated weights for policy 1, policy_version 60610 (0.0008) -[2023-10-12 05:46:14,881][78091] Updated weights for policy 0, policy_version 60900 (0.0009) -[2023-10-12 05:46:15,152][78123] Updated weights for policy 1, policy_version 60620 (0.0007) -[2023-10-12 05:46:15,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 124420096. Throughput: 0: 1586.3, 1: 1577.8. Samples: 31116674. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 05:46:15,201][77203] Avg episode reward: [(0, '50.530'), (1, '47.940')] -[2023-10-12 05:46:15,256][78091] Updated weights for policy 0, policy_version 60910 (0.0009) -[2023-10-12 05:46:15,514][78123] Updated weights for policy 1, policy_version 60630 (0.0008) -[2023-10-12 05:46:15,629][78091] Updated weights for policy 0, policy_version 60920 (0.0007) -[2023-10-12 05:46:15,894][78123] Updated weights for policy 1, policy_version 60640 (0.0007) -[2023-10-12 05:46:20,056][78091] Updated weights for policy 0, policy_version 60930 (0.0007) -[2023-10-12 05:46:20,137][78123] Updated weights for policy 1, policy_version 60650 (0.0009) -[2023-10-12 05:46:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 124485632. Throughput: 0: 1587.9, 1: 1591.0. Samples: 31136150. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:46:20,201][77203] Avg episode reward: [(0, '47.280'), (1, '51.120')] -[2023-10-12 05:46:20,414][78091] Updated weights for policy 0, policy_version 60940 (0.0009) -[2023-10-12 05:46:20,495][78123] Updated weights for policy 1, policy_version 60660 (0.0009) -[2023-10-12 05:46:20,789][78091] Updated weights for policy 0, policy_version 60950 (0.0007) -[2023-10-12 05:46:20,863][78123] Updated weights for policy 1, policy_version 60670 (0.0010) -[2023-10-12 05:46:21,153][78091] Updated weights for policy 0, policy_version 60960 (0.0007) -[2023-10-12 05:46:25,188][78123] Updated weights for policy 1, policy_version 60680 (0.0008) -[2023-10-12 05:46:25,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 124551168. Throughput: 0: 1599.4, 1: 1606.4. Samples: 31155408. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:46:25,202][77203] Avg episode reward: [(0, '51.470'), (1, '50.390')] -[2023-10-12 05:46:25,386][78091] Updated weights for policy 0, policy_version 60970 (0.0008) -[2023-10-12 05:46:25,555][78123] Updated weights for policy 1, policy_version 60690 (0.0007) -[2023-10-12 05:46:25,753][78091] Updated weights for policy 0, policy_version 60980 (0.0009) -[2023-10-12 05:46:25,929][78123] Updated weights for policy 1, policy_version 60700 (0.0008) -[2023-10-12 05:46:26,118][78091] Updated weights for policy 0, policy_version 60990 (0.0011) -[2023-10-12 05:46:30,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 124616704. Throughput: 0: 1575.3, 1: 1578.0. Samples: 31164002. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:46:30,202][77203] Avg episode reward: [(0, '50.560'), (1, '49.990')] -[2023-10-12 05:46:30,438][78123] Updated weights for policy 1, policy_version 60710 (0.0008) -[2023-10-12 05:46:30,447][78091] Updated weights for policy 0, policy_version 61000 (0.0009) -[2023-10-12 05:46:30,810][78123] Updated weights for policy 1, policy_version 60720 (0.0008) -[2023-10-12 05:46:30,819][78091] Updated weights for policy 0, policy_version 61010 (0.0010) -[2023-10-12 05:46:31,178][78123] Updated weights for policy 1, policy_version 60730 (0.0007) -[2023-10-12 05:46:31,195][78091] Updated weights for policy 0, policy_version 61020 (0.0009) -[2023-10-12 05:46:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 124682240. Throughput: 0: 1580.2, 1: 1581.6. Samples: 31183640. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:46:35,202][77203] Avg episode reward: [(0, '48.500'), (1, '47.620')] -[2023-10-12 05:46:35,447][78123] Updated weights for policy 1, policy_version 60740 (0.0007) -[2023-10-12 05:46:35,462][78091] Updated weights for policy 0, policy_version 61030 (0.0007) -[2023-10-12 05:46:35,818][78123] Updated weights for policy 1, policy_version 60750 (0.0010) -[2023-10-12 05:46:35,830][78091] Updated weights for policy 0, policy_version 61040 (0.0007) -[2023-10-12 05:46:36,181][78123] Updated weights for policy 1, policy_version 60760 (0.0009) -[2023-10-12 05:46:36,206][78091] Updated weights for policy 0, policy_version 61050 (0.0007) -[2023-10-12 05:46:40,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 124747776. Throughput: 0: 1598.2, 1: 1593.2. Samples: 31202888. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:46:40,202][77203] Avg episode reward: [(0, '54.450'), (1, '52.820')] -[2023-10-12 05:46:40,492][78123] Updated weights for policy 1, policy_version 60770 (0.0008) -[2023-10-12 05:46:40,535][78091] Updated weights for policy 0, policy_version 61060 (0.0009) -[2023-10-12 05:46:40,853][78123] Updated weights for policy 1, policy_version 60780 (0.0007) -[2023-10-12 05:46:40,902][78091] Updated weights for policy 0, policy_version 61070 (0.0007) -[2023-10-12 05:46:41,227][78123] Updated weights for policy 1, policy_version 60790 (0.0008) -[2023-10-12 05:46:41,272][78091] Updated weights for policy 0, policy_version 61080 (0.0007) -[2023-10-12 05:46:41,581][78123] Updated weights for policy 1, policy_version 60800 (0.0008) -[2023-10-12 05:46:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 124813312. Throughput: 0: 1583.3, 1: 1575.8. Samples: 31211438. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:46:45,202][77203] Avg episode reward: [(0, '48.260'), (1, '49.770')] -[2023-10-12 05:46:45,433][78091] Updated weights for policy 0, policy_version 61090 (0.0007) -[2023-10-12 05:46:45,802][78091] Updated weights for policy 0, policy_version 61100 (0.0009) -[2023-10-12 05:46:46,123][78123] Updated weights for policy 1, policy_version 60810 (0.0008) -[2023-10-12 05:46:46,176][78091] Updated weights for policy 0, policy_version 61110 (0.0009) -[2023-10-12 05:46:46,485][78123] Updated weights for policy 1, policy_version 60820 (0.0009) -[2023-10-12 05:46:46,533][78091] Updated weights for policy 0, policy_version 61120 (0.0008) -[2023-10-12 05:46:46,856][78123] Updated weights for policy 1, policy_version 60830 (0.0010) -[2023-10-12 05:46:50,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 124878848. Throughput: 0: 1585.0, 1: 1569.2. Samples: 31230728. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:46:50,201][77203] Avg episode reward: [(0, '49.950'), (1, '55.150')] -[2023-10-12 05:46:50,987][78091] Updated weights for policy 0, policy_version 61130 (0.0009) -[2023-10-12 05:46:51,105][78123] Updated weights for policy 1, policy_version 60840 (0.0009) -[2023-10-12 05:46:51,354][78091] Updated weights for policy 0, policy_version 61140 (0.0008) -[2023-10-12 05:46:51,481][78123] Updated weights for policy 1, policy_version 60850 (0.0008) -[2023-10-12 05:46:51,724][78091] Updated weights for policy 0, policy_version 61150 (0.0009) -[2023-10-12 05:46:51,856][78123] Updated weights for policy 1, policy_version 60860 (0.0009) -[2023-10-12 05:46:55,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 124944384. Throughput: 0: 1591.1, 1: 1577.7. Samples: 31250144. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:46:55,201][77203] Avg episode reward: [(0, '50.860'), (1, '54.140')] -[2023-10-12 05:46:56,232][78091] Updated weights for policy 0, policy_version 61160 (0.0008) -[2023-10-12 05:46:56,360][78123] Updated weights for policy 1, policy_version 60870 (0.0009) -[2023-10-12 05:46:56,597][78091] Updated weights for policy 0, policy_version 61170 (0.0009) -[2023-10-12 05:46:56,742][78123] Updated weights for policy 1, policy_version 60880 (0.0007) -[2023-10-12 05:46:56,962][78091] Updated weights for policy 0, policy_version 61180 (0.0010) -[2023-10-12 05:46:57,115][78123] Updated weights for policy 1, policy_version 60890 (0.0007) -[2023-10-12 05:47:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 125009920. Throughput: 0: 1585.0, 1: 1570.5. Samples: 31258672. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-12 05:47:00,201][77203] Avg episode reward: [(0, '52.790'), (1, '56.180')] -[2023-10-12 05:47:01,451][78123] Updated weights for policy 1, policy_version 60900 (0.0007) -[2023-10-12 05:47:01,469][78091] Updated weights for policy 0, policy_version 61190 (0.0008) -[2023-10-12 05:47:01,816][78123] Updated weights for policy 1, policy_version 60910 (0.0008) -[2023-10-12 05:47:01,838][78091] Updated weights for policy 0, policy_version 61200 (0.0008) -[2023-10-12 05:47:02,186][78123] Updated weights for policy 1, policy_version 60920 (0.0007) -[2023-10-12 05:47:02,220][78091] Updated weights for policy 0, policy_version 61210 (0.0009) -[2023-10-12 05:47:05,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 125075456. Throughput: 0: 1588.0, 1: 1571.3. Samples: 31278318. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-12 05:47:05,202][77203] Avg episode reward: [(0, '48.750'), (1, '46.360')] -[2023-10-12 05:47:06,290][78091] Updated weights for policy 0, policy_version 61220 (0.0007) -[2023-10-12 05:47:06,553][78123] Updated weights for policy 1, policy_version 60930 (0.0009) -[2023-10-12 05:47:06,666][78091] Updated weights for policy 0, policy_version 61230 (0.0008) -[2023-10-12 05:47:06,914][78123] Updated weights for policy 1, policy_version 60940 (0.0007) -[2023-10-12 05:47:07,031][78091] Updated weights for policy 0, policy_version 61240 (0.0008) -[2023-10-12 05:47:07,283][78123] Updated weights for policy 1, policy_version 60950 (0.0007) -[2023-10-12 05:47:07,645][78123] Updated weights for policy 1, policy_version 60960 (0.0009) -[2023-10-12 05:47:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 125140992. Throughput: 0: 1589.0, 1: 1572.9. Samples: 31297690. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-12 05:47:10,201][77203] Avg episode reward: [(0, '56.750'), (1, '48.120')] -[2023-10-12 05:47:10,212][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000060960_62423040.pth... -[2023-10-12 05:47:10,212][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000061248_62717952.pth... -[2023-10-12 05:47:10,264][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000059776_61210624.pth -[2023-10-12 05:47:10,264][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000059488_60915712.pth -[2023-10-12 05:47:11,273][78091] Updated weights for policy 0, policy_version 61250 (0.0008) -[2023-10-12 05:47:11,643][78091] Updated weights for policy 0, policy_version 61260 (0.0009) -[2023-10-12 05:47:11,999][78123] Updated weights for policy 1, policy_version 60970 (0.0010) -[2023-10-12 05:47:12,012][78091] Updated weights for policy 0, policy_version 61270 (0.0009) -[2023-10-12 05:47:12,362][78123] Updated weights for policy 1, policy_version 60980 (0.0008) -[2023-10-12 05:47:12,381][78091] Updated weights for policy 0, policy_version 61280 (0.0009) -[2023-10-12 05:47:12,735][78123] Updated weights for policy 1, policy_version 60990 (0.0009) -[2023-10-12 05:47:15,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 125206528. Throughput: 0: 1589.7, 1: 1577.3. Samples: 31306518. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-12 05:47:15,201][77203] Avg episode reward: [(0, '51.720'), (1, '47.620')] -[2023-10-12 05:47:16,505][78091] Updated weights for policy 0, policy_version 61290 (0.0008) -[2023-10-12 05:47:16,871][78091] Updated weights for policy 0, policy_version 61300 (0.0009) -[2023-10-12 05:47:17,051][78123] Updated weights for policy 1, policy_version 61000 (0.0008) -[2023-10-12 05:47:17,248][78091] Updated weights for policy 0, policy_version 61310 (0.0010) -[2023-10-12 05:47:17,419][78123] Updated weights for policy 1, policy_version 61010 (0.0009) -[2023-10-12 05:47:17,777][78123] Updated weights for policy 1, policy_version 61020 (0.0010) -[2023-10-12 05:47:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 125272064. Throughput: 0: 1592.6, 1: 1566.4. Samples: 31325794. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-12 05:47:20,201][77203] Avg episode reward: [(0, '50.650'), (1, '47.620')] -[2023-10-12 05:47:21,794][78091] Updated weights for policy 0, policy_version 61320 (0.0007) -[2023-10-12 05:47:22,163][78091] Updated weights for policy 0, policy_version 61330 (0.0007) -[2023-10-12 05:47:22,290][78123] Updated weights for policy 1, policy_version 61030 (0.0008) -[2023-10-12 05:47:22,532][78091] Updated weights for policy 0, policy_version 61340 (0.0008) -[2023-10-12 05:47:22,660][78123] Updated weights for policy 1, policy_version 61040 (0.0008) -[2023-10-12 05:47:23,031][78123] Updated weights for policy 1, policy_version 61050 (0.0009) -[2023-10-12 05:47:25,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 125337600. Throughput: 0: 1591.9, 1: 1564.4. Samples: 31344924. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-12 05:47:25,202][77203] Avg episode reward: [(0, '44.650'), (1, '47.200')] -[2023-10-12 05:47:26,827][78091] Updated weights for policy 0, policy_version 61350 (0.0010) -[2023-10-12 05:47:27,205][78091] Updated weights for policy 0, policy_version 61360 (0.0009) -[2023-10-12 05:47:27,459][78123] Updated weights for policy 1, policy_version 61060 (0.0009) -[2023-10-12 05:47:27,563][78091] Updated weights for policy 0, policy_version 61370 (0.0007) -[2023-10-12 05:47:27,826][78123] Updated weights for policy 1, policy_version 61070 (0.0009) -[2023-10-12 05:47:28,188][78123] Updated weights for policy 1, policy_version 61080 (0.0007) -[2023-10-12 05:47:30,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 125403136. Throughput: 0: 1590.9, 1: 1583.9. Samples: 31354302. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-12 05:47:30,202][77203] Avg episode reward: [(0, '48.360'), (1, '46.940')] -[2023-10-12 05:47:31,954][78091] Updated weights for policy 0, policy_version 61380 (0.0008) -[2023-10-12 05:47:32,332][78091] Updated weights for policy 0, policy_version 61390 (0.0007) -[2023-10-12 05:47:32,473][78123] Updated weights for policy 1, policy_version 61090 (0.0008) -[2023-10-12 05:47:32,711][78091] Updated weights for policy 0, policy_version 61400 (0.0008) -[2023-10-12 05:47:32,842][78123] Updated weights for policy 1, policy_version 61100 (0.0009) -[2023-10-12 05:47:33,214][78123] Updated weights for policy 1, policy_version 61110 (0.0009) -[2023-10-12 05:47:33,585][78123] Updated weights for policy 1, policy_version 61120 (0.0010) -[2023-10-12 05:47:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 125468672. Throughput: 0: 1593.0, 1: 1571.1. Samples: 31373110. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-12 05:47:35,202][77203] Avg episode reward: [(0, '47.800'), (1, '55.330')] -[2023-10-12 05:47:37,188][78091] Updated weights for policy 0, policy_version 61410 (0.0009) -[2023-10-12 05:47:37,551][78091] Updated weights for policy 0, policy_version 61420 (0.0008) -[2023-10-12 05:47:37,813][78123] Updated weights for policy 1, policy_version 61130 (0.0008) -[2023-10-12 05:47:37,918][78091] Updated weights for policy 0, policy_version 61430 (0.0009) -[2023-10-12 05:47:38,172][78123] Updated weights for policy 1, policy_version 61140 (0.0007) -[2023-10-12 05:47:38,294][78091] Updated weights for policy 0, policy_version 61440 (0.0007) -[2023-10-12 05:47:38,539][78123] Updated weights for policy 1, policy_version 61150 (0.0007) -[2023-10-12 05:47:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 125534208. Throughput: 0: 1590.1, 1: 1571.3. Samples: 31392408. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-12 05:47:40,202][77203] Avg episode reward: [(0, '48.090'), (1, '53.970')] -[2023-10-12 05:47:42,668][78091] Updated weights for policy 0, policy_version 61450 (0.0007) -[2023-10-12 05:47:42,946][78123] Updated weights for policy 1, policy_version 61160 (0.0010) -[2023-10-12 05:47:43,034][78091] Updated weights for policy 0, policy_version 61460 (0.0010) -[2023-10-12 05:47:43,326][78123] Updated weights for policy 1, policy_version 61170 (0.0009) -[2023-10-12 05:47:43,410][78091] Updated weights for policy 0, policy_version 61470 (0.0009) -[2023-10-12 05:47:43,692][78123] Updated weights for policy 1, policy_version 61180 (0.0009) -[2023-10-12 05:47:45,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 125599744. Throughput: 0: 1603.0, 1: 1595.7. Samples: 31402614. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-12 05:47:45,202][77203] Avg episode reward: [(0, '47.880'), (1, '49.390')] -[2023-10-12 05:47:47,701][78091] Updated weights for policy 0, policy_version 61480 (0.0008) -[2023-10-12 05:47:47,967][78123] Updated weights for policy 1, policy_version 61190 (0.0009) -[2023-10-12 05:47:48,074][78091] Updated weights for policy 0, policy_version 61490 (0.0007) -[2023-10-12 05:47:48,336][78123] Updated weights for policy 1, policy_version 61200 (0.0007) -[2023-10-12 05:47:48,440][78091] Updated weights for policy 0, policy_version 61500 (0.0009) -[2023-10-12 05:47:48,698][78123] Updated weights for policy 1, policy_version 61210 (0.0008) -[2023-10-12 05:47:50,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 125665280. Throughput: 0: 1583.8, 1: 1576.1. Samples: 31420514. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-12 05:47:50,201][77203] Avg episode reward: [(0, '51.540'), (1, '46.290')] -[2023-10-12 05:47:52,594][78091] Updated weights for policy 0, policy_version 61510 (0.0009) -[2023-10-12 05:47:52,968][78091] Updated weights for policy 0, policy_version 61520 (0.0010) -[2023-10-12 05:47:53,065][78123] Updated weights for policy 1, policy_version 61220 (0.0009) -[2023-10-12 05:47:53,340][78091] Updated weights for policy 0, policy_version 61530 (0.0010) -[2023-10-12 05:47:53,427][78123] Updated weights for policy 1, policy_version 61230 (0.0008) -[2023-10-12 05:47:53,804][78123] Updated weights for policy 1, policy_version 61240 (0.0009) -[2023-10-12 05:47:55,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 125730816. Throughput: 0: 1583.5, 1: 1573.5. Samples: 31439754. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-12 05:47:55,202][77203] Avg episode reward: [(0, '51.230'), (1, '46.280')] -[2023-10-12 05:47:57,741][78091] Updated weights for policy 0, policy_version 61540 (0.0009) -[2023-10-12 05:47:58,120][78091] Updated weights for policy 0, policy_version 61550 (0.0009) -[2023-10-12 05:47:58,148][78123] Updated weights for policy 1, policy_version 61250 (0.0009) -[2023-10-12 05:47:58,485][78091] Updated weights for policy 0, policy_version 61560 (0.0007) -[2023-10-12 05:47:58,517][78123] Updated weights for policy 1, policy_version 61260 (0.0009) -[2023-10-12 05:47:58,882][78123] Updated weights for policy 1, policy_version 61270 (0.0009) -[2023-10-12 05:47:59,257][78123] Updated weights for policy 1, policy_version 61280 (0.0011) -[2023-10-12 05:48:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 125796352. Throughput: 0: 1601.8, 1: 1594.5. Samples: 31450352. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-12 05:48:00,201][77203] Avg episode reward: [(0, '48.480'), (1, '57.140')] -[2023-10-12 05:48:02,909][78091] Updated weights for policy 0, policy_version 61570 (0.0008) -[2023-10-12 05:48:03,282][78091] Updated weights for policy 0, policy_version 61580 (0.0010) -[2023-10-12 05:48:03,620][78123] Updated weights for policy 1, policy_version 61290 (0.0010) -[2023-10-12 05:48:03,644][78091] Updated weights for policy 0, policy_version 61590 (0.0009) -[2023-10-12 05:48:03,987][78123] Updated weights for policy 1, policy_version 61300 (0.0010) -[2023-10-12 05:48:04,010][78091] Updated weights for policy 0, policy_version 61600 (0.0008) -[2023-10-12 05:48:04,347][78123] Updated weights for policy 1, policy_version 61310 (0.0008) -[2023-10-12 05:48:05,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 125861888. Throughput: 0: 1580.4, 1: 1591.4. Samples: 31468526. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-12 05:48:05,202][77203] Avg episode reward: [(0, '55.260'), (1, '45.920')] -[2023-10-12 05:48:08,444][78091] Updated weights for policy 0, policy_version 61610 (0.0008) -[2023-10-12 05:48:08,707][78123] Updated weights for policy 1, policy_version 61320 (0.0009) -[2023-10-12 05:48:08,829][78091] Updated weights for policy 0, policy_version 61620 (0.0007) -[2023-10-12 05:48:09,078][78123] Updated weights for policy 1, policy_version 61330 (0.0009) -[2023-10-12 05:48:09,202][78091] Updated weights for policy 0, policy_version 61630 (0.0008) -[2023-10-12 05:48:09,445][78123] Updated weights for policy 1, policy_version 61340 (0.0008) -[2023-10-12 05:48:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 125927424. Throughput: 0: 1574.2, 1: 1581.9. Samples: 31486946. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-12 05:48:10,201][77203] Avg episode reward: [(0, '54.360'), (1, '46.890')] -[2023-10-12 05:48:13,540][78091] Updated weights for policy 0, policy_version 61640 (0.0008) -[2023-10-12 05:48:13,730][78123] Updated weights for policy 1, policy_version 61350 (0.0010) -[2023-10-12 05:48:13,916][78091] Updated weights for policy 0, policy_version 61650 (0.0009) -[2023-10-12 05:48:14,097][78123] Updated weights for policy 1, policy_version 61360 (0.0008) -[2023-10-12 05:48:14,287][78091] Updated weights for policy 0, policy_version 61660 (0.0009) -[2023-10-12 05:48:14,459][78123] Updated weights for policy 1, policy_version 61370 (0.0009) -[2023-10-12 05:48:15,201][77203] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 125992960. Throughput: 0: 1601.1, 1: 1587.3. Samples: 31497776. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-12 05:48:15,201][77203] Avg episode reward: [(0, '48.000'), (1, '48.360')] -[2023-10-12 05:48:18,538][78091] Updated weights for policy 0, policy_version 61670 (0.0009) -[2023-10-12 05:48:18,830][78123] Updated weights for policy 1, policy_version 61380 (0.0007) -[2023-10-12 05:48:18,915][78091] Updated weights for policy 0, policy_version 61680 (0.0008) -[2023-10-12 05:48:19,199][78123] Updated weights for policy 1, policy_version 61390 (0.0008) -[2023-10-12 05:48:19,293][78091] Updated weights for policy 0, policy_version 61690 (0.0008) -[2023-10-12 05:48:19,562][78123] Updated weights for policy 1, policy_version 61400 (0.0008) -[2023-10-12 05:48:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 126058496. Throughput: 0: 1590.3, 1: 1604.6. Samples: 31516880. Policy #0 lag: (min: 22.0, avg: 26.8, max: 54.0) -[2023-10-12 05:48:20,201][77203] Avg episode reward: [(0, '51.430'), (1, '48.350')] -[2023-10-12 05:48:23,503][78091] Updated weights for policy 0, policy_version 61700 (0.0008) -[2023-10-12 05:48:23,873][78091] Updated weights for policy 0, policy_version 61710 (0.0009) -[2023-10-12 05:48:23,992][78123] Updated weights for policy 1, policy_version 61410 (0.0010) -[2023-10-12 05:48:24,243][78091] Updated weights for policy 0, policy_version 61720 (0.0008) -[2023-10-12 05:48:24,363][78123] Updated weights for policy 1, policy_version 61420 (0.0008) -[2023-10-12 05:48:24,730][78123] Updated weights for policy 1, policy_version 61430 (0.0007) -[2023-10-12 05:48:25,112][78123] Updated weights for policy 1, policy_version 61440 (0.0007) -[2023-10-12 05:48:25,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 126124032. Throughput: 0: 1580.0, 1: 1586.9. Samples: 31534920. Policy #0 lag: (min: 22.0, avg: 26.8, max: 54.0) -[2023-10-12 05:48:25,202][77203] Avg episode reward: [(0, '49.700'), (1, '40.370')] -[2023-10-12 05:48:28,631][78091] Updated weights for policy 0, policy_version 61730 (0.0009) -[2023-10-12 05:48:28,999][78091] Updated weights for policy 0, policy_version 61740 (0.0008) -[2023-10-12 05:48:29,372][78091] Updated weights for policy 0, policy_version 61750 (0.0008) -[2023-10-12 05:48:29,615][78123] Updated weights for policy 1, policy_version 61450 (0.0009) -[2023-10-12 05:48:29,736][78091] Updated weights for policy 0, policy_version 61760 (0.0009) -[2023-10-12 05:48:29,982][78123] Updated weights for policy 1, policy_version 61460 (0.0009) -[2023-10-12 05:48:30,201][77203] Fps is (10 sec: 9830.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 126156800. Throughput: 0: 1593.1, 1: 1582.4. Samples: 31545514. Policy #0 lag: (min: 22.0, avg: 26.8, max: 54.0) -[2023-10-12 05:48:30,202][77203] Avg episode reward: [(0, '57.640'), (1, '47.800')] -[2023-10-12 05:48:30,353][78123] Updated weights for policy 1, policy_version 61470 (0.0010) -[2023-10-12 05:48:34,125][78091] Updated weights for policy 0, policy_version 61770 (0.0011) -[2023-10-12 05:48:34,495][78091] Updated weights for policy 0, policy_version 61780 (0.0009) -[2023-10-12 05:48:34,769][78123] Updated weights for policy 1, policy_version 61480 (0.0008) -[2023-10-12 05:48:34,865][78091] Updated weights for policy 0, policy_version 61790 (0.0007) -[2023-10-12 05:48:35,131][78123] Updated weights for policy 1, policy_version 61490 (0.0009) -[2023-10-12 05:48:35,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 126222336. Throughput: 0: 1605.4, 1: 1601.3. Samples: 31564814. Policy #0 lag: (min: 22.0, avg: 26.8, max: 54.0) -[2023-10-12 05:48:35,202][77203] Avg episode reward: [(0, '50.290'), (1, '45.590')] -[2023-10-12 05:48:35,491][78123] Updated weights for policy 1, policy_version 61500 (0.0009) -[2023-10-12 05:48:39,002][78091] Updated weights for policy 0, policy_version 61800 (0.0010) -[2023-10-12 05:48:39,368][78091] Updated weights for policy 0, policy_version 61810 (0.0008) -[2023-10-12 05:48:39,745][78091] Updated weights for policy 0, policy_version 61820 (0.0008) -[2023-10-12 05:48:39,774][78123] Updated weights for policy 1, policy_version 61510 (0.0008) -[2023-10-12 05:48:40,160][78123] Updated weights for policy 1, policy_version 61520 (0.0009) -[2023-10-12 05:48:40,201][77203] Fps is (10 sec: 13107.6, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 126287872. Throughput: 0: 1588.2, 1: 1600.8. Samples: 31583258. Policy #0 lag: (min: 22.0, avg: 26.8, max: 54.0) -[2023-10-12 05:48:40,202][77203] Avg episode reward: [(0, '48.360'), (1, '47.040')] -[2023-10-12 05:48:40,517][78123] Updated weights for policy 1, policy_version 61530 (0.0011) -[2023-10-12 05:48:44,074][78091] Updated weights for policy 0, policy_version 61830 (0.0009) -[2023-10-12 05:48:44,444][78091] Updated weights for policy 0, policy_version 61840 (0.0009) -[2023-10-12 05:48:44,811][78091] Updated weights for policy 0, policy_version 61850 (0.0008) -[2023-10-12 05:48:44,867][78123] Updated weights for policy 1, policy_version 61540 (0.0010) -[2023-10-12 05:48:45,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 126353408. Throughput: 0: 1590.0, 1: 1579.0. Samples: 31592958. Policy #0 lag: (min: 22.0, avg: 26.8, max: 54.0) -[2023-10-12 05:48:45,201][77203] Avg episode reward: [(0, '50.960'), (1, '46.940')] -[2023-10-12 05:48:45,239][78123] Updated weights for policy 1, policy_version 61550 (0.0007) -[2023-10-12 05:48:45,614][78123] Updated weights for policy 1, policy_version 61560 (0.0009) -[2023-10-12 05:48:49,013][78091] Updated weights for policy 0, policy_version 61860 (0.0009) -[2023-10-12 05:48:49,379][78091] Updated weights for policy 0, policy_version 61870 (0.0009) -[2023-10-12 05:48:49,760][78091] Updated weights for policy 0, policy_version 61880 (0.0011) -[2023-10-12 05:48:49,885][78123] Updated weights for policy 1, policy_version 61570 (0.0008) -[2023-10-12 05:48:50,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 126418944. Throughput: 0: 1615.1, 1: 1591.9. Samples: 31612838. Policy #0 lag: (min: 22.0, avg: 26.8, max: 54.0) -[2023-10-12 05:48:50,202][77203] Avg episode reward: [(0, '46.080'), (1, '46.450')] -[2023-10-12 05:48:50,246][78123] Updated weights for policy 1, policy_version 61580 (0.0011) -[2023-10-12 05:48:50,616][78123] Updated weights for policy 1, policy_version 61590 (0.0009) -[2023-10-12 05:48:50,975][78123] Updated weights for policy 1, policy_version 61600 (0.0008) -[2023-10-12 05:48:54,072][78091] Updated weights for policy 0, policy_version 61890 (0.0008) -[2023-10-12 05:48:54,459][78091] Updated weights for policy 0, policy_version 61900 (0.0011) -[2023-10-12 05:48:54,840][78091] Updated weights for policy 0, policy_version 61910 (0.0010) -[2023-10-12 05:48:55,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 126451712. Throughput: 0: 1605.8, 1: 1609.8. Samples: 31631648. Policy #0 lag: (min: 22.0, avg: 26.8, max: 54.0) -[2023-10-12 05:48:55,202][77203] Avg episode reward: [(0, '45.600'), (1, '53.800')] -[2023-10-12 05:48:55,207][78091] Updated weights for policy 0, policy_version 61920 (0.0008) -[2023-10-12 05:48:55,389][78123] Updated weights for policy 1, policy_version 61610 (0.0007) -[2023-10-12 05:48:55,755][78123] Updated weights for policy 1, policy_version 61620 (0.0007) -[2023-10-12 05:48:56,116][78123] Updated weights for policy 1, policy_version 61630 (0.0009) -[2023-10-12 05:48:59,279][78091] Updated weights for policy 0, policy_version 61930 (0.0010) -[2023-10-12 05:48:59,652][78091] Updated weights for policy 0, policy_version 61940 (0.0011) -[2023-10-12 05:49:00,019][78091] Updated weights for policy 0, policy_version 61950 (0.0009) -[2023-10-12 05:49:00,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 126550016. Throughput: 0: 1600.7, 1: 1586.0. Samples: 31641174. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:49:00,201][77203] Avg episode reward: [(0, '45.540'), (1, '47.990')] -[2023-10-12 05:49:00,406][78123] Updated weights for policy 1, policy_version 61640 (0.0009) -[2023-10-12 05:49:00,775][78123] Updated weights for policy 1, policy_version 61650 (0.0009) -[2023-10-12 05:49:01,145][78123] Updated weights for policy 1, policy_version 61660 (0.0011) -[2023-10-12 05:49:04,536][78091] Updated weights for policy 0, policy_version 61960 (0.0007) -[2023-10-12 05:49:04,900][78091] Updated weights for policy 0, policy_version 61970 (0.0010) -[2023-10-12 05:49:05,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 126582784. Throughput: 0: 1607.7, 1: 1589.5. Samples: 31660754. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:49:05,202][77203] Avg episode reward: [(0, '52.660'), (1, '49.890')] -[2023-10-12 05:49:05,264][78091] Updated weights for policy 0, policy_version 61980 (0.0007) -[2023-10-12 05:49:05,504][78123] Updated weights for policy 1, policy_version 61670 (0.0011) -[2023-10-12 05:49:05,879][78123] Updated weights for policy 1, policy_version 61680 (0.0010) -[2023-10-12 05:49:06,246][78123] Updated weights for policy 1, policy_version 61690 (0.0010) -[2023-10-12 05:49:09,572][78091] Updated weights for policy 0, policy_version 61990 (0.0008) -[2023-10-12 05:49:09,957][78091] Updated weights for policy 0, policy_version 62000 (0.0009) -[2023-10-12 05:49:10,201][77203] Fps is (10 sec: 9830.1, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 126648320. Throughput: 0: 1611.5, 1: 1602.6. Samples: 31679556. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:49:10,202][77203] Avg episode reward: [(0, '55.320'), (1, '48.440')] -[2023-10-12 05:49:10,211][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000061696_63176704.pth... -[2023-10-12 05:49:10,242][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000060224_61669376.pth -[2023-10-12 05:49:10,326][78091] Updated weights for policy 0, policy_version 62010 (0.0010) -[2023-10-12 05:49:10,546][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000062016_63504384.pth... -[2023-10-12 05:49:10,576][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000060512_61964288.pth -[2023-10-12 05:49:10,669][78123] Updated weights for policy 1, policy_version 61700 (0.0008) -[2023-10-12 05:49:11,032][78123] Updated weights for policy 1, policy_version 61710 (0.0008) -[2023-10-12 05:49:11,401][78123] Updated weights for policy 1, policy_version 61720 (0.0007) -[2023-10-12 05:49:14,680][78091] Updated weights for policy 0, policy_version 62020 (0.0009) -[2023-10-12 05:49:15,053][78091] Updated weights for policy 0, policy_version 62030 (0.0009) -[2023-10-12 05:49:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 126713856. Throughput: 0: 1593.2, 1: 1583.5. Samples: 31688462. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:49:15,201][77203] Avg episode reward: [(0, '53.950'), (1, '45.230')] -[2023-10-12 05:49:15,424][78091] Updated weights for policy 0, policy_version 62040 (0.0008) -[2023-10-12 05:49:15,777][78123] Updated weights for policy 1, policy_version 61730 (0.0008) -[2023-10-12 05:49:16,160][78123] Updated weights for policy 1, policy_version 61740 (0.0009) -[2023-10-12 05:49:16,529][78123] Updated weights for policy 1, policy_version 61750 (0.0009) -[2023-10-12 05:49:16,894][78123] Updated weights for policy 1, policy_version 61760 (0.0010) -[2023-10-12 05:49:19,801][78091] Updated weights for policy 0, policy_version 62050 (0.0009) -[2023-10-12 05:49:20,177][78091] Updated weights for policy 0, policy_version 62060 (0.0010) -[2023-10-12 05:49:20,201][77203] Fps is (10 sec: 13107.6, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 126779392. Throughput: 0: 1597.4, 1: 1585.6. Samples: 31708046. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:49:20,201][77203] Avg episode reward: [(0, '52.500'), (1, '43.330')] -[2023-10-12 05:49:20,548][78091] Updated weights for policy 0, policy_version 62070 (0.0010) -[2023-10-12 05:49:20,926][78091] Updated weights for policy 0, policy_version 62080 (0.0008) -[2023-10-12 05:49:21,200][78123] Updated weights for policy 1, policy_version 61770 (0.0009) -[2023-10-12 05:49:21,558][78123] Updated weights for policy 1, policy_version 61780 (0.0010) -[2023-10-12 05:49:21,925][78123] Updated weights for policy 1, policy_version 61790 (0.0009) -[2023-10-12 05:49:25,201][77203] Fps is (10 sec: 13106.8, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 126844928. Throughput: 0: 1615.8, 1: 1586.8. Samples: 31727374. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:49:25,202][77203] Avg episode reward: [(0, '50.150'), (1, '48.820')] -[2023-10-12 05:49:25,331][78091] Updated weights for policy 0, policy_version 62090 (0.0007) -[2023-10-12 05:49:25,700][78091] Updated weights for policy 0, policy_version 62100 (0.0007) -[2023-10-12 05:49:26,071][78091] Updated weights for policy 0, policy_version 62110 (0.0008) -[2023-10-12 05:49:26,250][78123] Updated weights for policy 1, policy_version 61800 (0.0008) -[2023-10-12 05:49:26,620][78123] Updated weights for policy 1, policy_version 61810 (0.0008) -[2023-10-12 05:49:26,987][78123] Updated weights for policy 1, policy_version 61820 (0.0007) -[2023-10-12 05:49:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 126910464. Throughput: 0: 1595.6, 1: 1580.8. Samples: 31735894. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:49:30,201][77203] Avg episode reward: [(0, '55.040'), (1, '46.520')] -[2023-10-12 05:49:30,405][78091] Updated weights for policy 0, policy_version 62120 (0.0008) -[2023-10-12 05:49:30,773][78091] Updated weights for policy 0, policy_version 62130 (0.0007) -[2023-10-12 05:49:31,138][78123] Updated weights for policy 1, policy_version 61830 (0.0008) -[2023-10-12 05:49:31,141][78091] Updated weights for policy 0, policy_version 62140 (0.0009) -[2023-10-12 05:49:31,508][78123] Updated weights for policy 1, policy_version 61840 (0.0008) -[2023-10-12 05:49:31,874][78123] Updated weights for policy 1, policy_version 61850 (0.0007) -[2023-10-12 05:49:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 126976000. Throughput: 0: 1585.3, 1: 1581.4. Samples: 31755338. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:49:35,202][77203] Avg episode reward: [(0, '50.370'), (1, '46.050')] -[2023-10-12 05:49:35,532][78091] Updated weights for policy 0, policy_version 62150 (0.0008) -[2023-10-12 05:49:35,908][78091] Updated weights for policy 0, policy_version 62160 (0.0010) -[2023-10-12 05:49:36,274][78123] Updated weights for policy 1, policy_version 61860 (0.0008) -[2023-10-12 05:49:36,283][78091] Updated weights for policy 0, policy_version 62170 (0.0009) -[2023-10-12 05:49:36,632][78123] Updated weights for policy 1, policy_version 61870 (0.0009) -[2023-10-12 05:49:36,996][78123] Updated weights for policy 1, policy_version 61880 (0.0008) -[2023-10-12 05:49:40,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 127041536. Throughput: 0: 1599.7, 1: 1579.1. Samples: 31774696. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:49:40,202][77203] Avg episode reward: [(0, '54.300'), (1, '44.290')] -[2023-10-12 05:49:40,618][78091] Updated weights for policy 0, policy_version 62180 (0.0008) -[2023-10-12 05:49:41,000][78091] Updated weights for policy 0, policy_version 62190 (0.0007) -[2023-10-12 05:49:41,360][78123] Updated weights for policy 1, policy_version 61890 (0.0010) -[2023-10-12 05:49:41,378][78091] Updated weights for policy 0, policy_version 62200 (0.0007) -[2023-10-12 05:49:41,725][78123] Updated weights for policy 1, policy_version 61900 (0.0008) -[2023-10-12 05:49:42,102][78123] Updated weights for policy 1, policy_version 61910 (0.0008) -[2023-10-12 05:49:42,462][78123] Updated weights for policy 1, policy_version 61920 (0.0008) -[2023-10-12 05:49:45,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 127107072. Throughput: 0: 1577.1, 1: 1580.4. Samples: 31783264. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-12 05:49:45,202][77203] Avg episode reward: [(0, '49.260'), (1, '49.940')] -[2023-10-12 05:49:45,629][78091] Updated weights for policy 0, policy_version 62210 (0.0007) -[2023-10-12 05:49:45,999][78091] Updated weights for policy 0, policy_version 62220 (0.0008) -[2023-10-12 05:49:46,369][78091] Updated weights for policy 0, policy_version 62230 (0.0008) -[2023-10-12 05:49:46,738][78091] Updated weights for policy 0, policy_version 62240 (0.0008) -[2023-10-12 05:49:46,994][78123] Updated weights for policy 1, policy_version 61930 (0.0010) -[2023-10-12 05:49:47,360][78123] Updated weights for policy 1, policy_version 61940 (0.0010) -[2023-10-12 05:49:47,722][78123] Updated weights for policy 1, policy_version 61950 (0.0009) -[2023-10-12 05:49:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 127172608. Throughput: 0: 1581.9, 1: 1574.5. Samples: 31802792. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-12 05:49:50,202][77203] Avg episode reward: [(0, '48.650'), (1, '46.230')] -[2023-10-12 05:49:51,064][78091] Updated weights for policy 0, policy_version 62250 (0.0008) -[2023-10-12 05:49:51,436][78091] Updated weights for policy 0, policy_version 62260 (0.0009) -[2023-10-12 05:49:51,806][78091] Updated weights for policy 0, policy_version 62270 (0.0008) -[2023-10-12 05:49:52,129][78123] Updated weights for policy 1, policy_version 61960 (0.0008) -[2023-10-12 05:49:52,490][78123] Updated weights for policy 1, policy_version 61970 (0.0007) -[2023-10-12 05:49:52,864][78123] Updated weights for policy 1, policy_version 61980 (0.0007) -[2023-10-12 05:49:55,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 127238144. Throughput: 0: 1591.2, 1: 1579.6. Samples: 31822240. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-12 05:49:55,202][77203] Avg episode reward: [(0, '56.250'), (1, '51.640')] -[2023-10-12 05:49:56,057][78091] Updated weights for policy 0, policy_version 62280 (0.0007) -[2023-10-12 05:49:56,422][78091] Updated weights for policy 0, policy_version 62290 (0.0008) -[2023-10-12 05:49:56,786][78091] Updated weights for policy 0, policy_version 62300 (0.0009) -[2023-10-12 05:49:57,222][78123] Updated weights for policy 1, policy_version 61990 (0.0009) -[2023-10-12 05:49:57,592][78123] Updated weights for policy 1, policy_version 62000 (0.0009) -[2023-10-12 05:49:57,950][78123] Updated weights for policy 1, policy_version 62010 (0.0011) -[2023-10-12 05:50:00,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 127303680. Throughput: 0: 1583.5, 1: 1592.8. Samples: 31831398. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-12 05:50:00,201][77203] Avg episode reward: [(0, '56.740'), (1, '44.100')] -[2023-10-12 05:50:01,209][78091] Updated weights for policy 0, policy_version 62310 (0.0009) -[2023-10-12 05:50:01,586][78091] Updated weights for policy 0, policy_version 62320 (0.0007) -[2023-10-12 05:50:01,964][78091] Updated weights for policy 0, policy_version 62330 (0.0010) -[2023-10-12 05:50:02,330][78123] Updated weights for policy 1, policy_version 62020 (0.0009) -[2023-10-12 05:50:02,710][78123] Updated weights for policy 1, policy_version 62030 (0.0010) -[2023-10-12 05:50:03,084][78123] Updated weights for policy 1, policy_version 62040 (0.0007) -[2023-10-12 05:50:05,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 127369216. Throughput: 0: 1586.1, 1: 1577.2. Samples: 31850394. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-12 05:50:05,201][77203] Avg episode reward: [(0, '47.540'), (1, '50.990')] -[2023-10-12 05:50:06,130][78091] Updated weights for policy 0, policy_version 62340 (0.0007) -[2023-10-12 05:50:06,511][78091] Updated weights for policy 0, policy_version 62350 (0.0007) -[2023-10-12 05:50:06,886][78091] Updated weights for policy 0, policy_version 62360 (0.0009) -[2023-10-12 05:50:07,358][78123] Updated weights for policy 1, policy_version 62050 (0.0009) -[2023-10-12 05:50:07,735][78123] Updated weights for policy 1, policy_version 62060 (0.0009) -[2023-10-12 05:50:08,104][78123] Updated weights for policy 1, policy_version 62070 (0.0009) -[2023-10-12 05:50:08,485][78123] Updated weights for policy 1, policy_version 62080 (0.0009) -[2023-10-12 05:50:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.3, 300 sec: 12662.9). Total num frames: 127434752. Throughput: 0: 1589.3, 1: 1581.9. Samples: 31870078. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-12 05:50:10,201][77203] Avg episode reward: [(0, '53.650'), (1, '50.820')] -[2023-10-12 05:50:11,277][78091] Updated weights for policy 0, policy_version 62370 (0.0009) -[2023-10-12 05:50:11,657][78091] Updated weights for policy 0, policy_version 62380 (0.0007) -[2023-10-12 05:50:12,022][78091] Updated weights for policy 0, policy_version 62390 (0.0009) -[2023-10-12 05:50:12,394][78091] Updated weights for policy 0, policy_version 62400 (0.0011) -[2023-10-12 05:50:12,905][78123] Updated weights for policy 1, policy_version 62090 (0.0009) -[2023-10-12 05:50:13,281][78123] Updated weights for policy 1, policy_version 62100 (0.0009) -[2023-10-12 05:50:13,643][78123] Updated weights for policy 1, policy_version 62110 (0.0009) -[2023-10-12 05:50:15,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 127500288. Throughput: 0: 1590.4, 1: 1602.9. Samples: 31879592. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-12 05:50:15,202][77203] Avg episode reward: [(0, '52.020'), (1, '43.960')] -[2023-10-12 05:50:16,586][78091] Updated weights for policy 0, policy_version 62410 (0.0011) -[2023-10-12 05:50:16,962][78091] Updated weights for policy 0, policy_version 62420 (0.0010) -[2023-10-12 05:50:17,339][78091] Updated weights for policy 0, policy_version 62430 (0.0011) -[2023-10-12 05:50:17,912][78123] Updated weights for policy 1, policy_version 62120 (0.0007) -[2023-10-12 05:50:18,289][78123] Updated weights for policy 1, policy_version 62130 (0.0009) -[2023-10-12 05:50:18,648][78123] Updated weights for policy 1, policy_version 62140 (0.0007) -[2023-10-12 05:50:20,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 12662.9). Total num frames: 127565824. Throughput: 0: 1595.8, 1: 1584.5. Samples: 31898450. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-12 05:50:20,202][77203] Avg episode reward: [(0, '52.340'), (1, '48.060')] -[2023-10-12 05:50:21,591][78091] Updated weights for policy 0, policy_version 62440 (0.0009) -[2023-10-12 05:50:21,968][78091] Updated weights for policy 0, policy_version 62450 (0.0009) -[2023-10-12 05:50:22,335][78091] Updated weights for policy 0, policy_version 62460 (0.0008) -[2023-10-12 05:50:22,957][78123] Updated weights for policy 1, policy_version 62150 (0.0008) -[2023-10-12 05:50:23,314][78123] Updated weights for policy 1, policy_version 62160 (0.0009) -[2023-10-12 05:50:23,690][78123] Updated weights for policy 1, policy_version 62170 (0.0008) -[2023-10-12 05:50:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 127631360. Throughput: 0: 1595.6, 1: 1582.4. Samples: 31917710. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-12 05:50:25,202][77203] Avg episode reward: [(0, '46.250'), (1, '42.390')] -[2023-10-12 05:50:26,882][78091] Updated weights for policy 0, policy_version 62470 (0.0009) -[2023-10-12 05:50:27,257][78091] Updated weights for policy 0, policy_version 62480 (0.0009) -[2023-10-12 05:50:27,628][78091] Updated weights for policy 0, policy_version 62490 (0.0009) -[2023-10-12 05:50:27,701][78123] Updated weights for policy 1, policy_version 62180 (0.0009) -[2023-10-12 05:50:28,058][78123] Updated weights for policy 1, policy_version 62190 (0.0011) -[2023-10-12 05:50:28,427][78123] Updated weights for policy 1, policy_version 62200 (0.0011) -[2023-10-12 05:50:30,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 127696896. Throughput: 0: 1594.6, 1: 1606.7. Samples: 31927322. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-12 05:50:30,201][77203] Avg episode reward: [(0, '53.140'), (1, '49.750')] -[2023-10-12 05:50:31,911][78091] Updated weights for policy 0, policy_version 62500 (0.0009) -[2023-10-12 05:50:32,279][78091] Updated weights for policy 0, policy_version 62510 (0.0008) -[2023-10-12 05:50:32,659][78091] Updated weights for policy 0, policy_version 62520 (0.0009) -[2023-10-12 05:50:32,676][78123] Updated weights for policy 1, policy_version 62210 (0.0009) -[2023-10-12 05:50:33,047][78123] Updated weights for policy 1, policy_version 62220 (0.0007) -[2023-10-12 05:50:33,412][78123] Updated weights for policy 1, policy_version 62230 (0.0009) -[2023-10-12 05:50:33,773][78123] Updated weights for policy 1, policy_version 62240 (0.0009) -[2023-10-12 05:50:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 127762432. Throughput: 0: 1590.2, 1: 1589.6. Samples: 31945882. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-12 05:50:35,202][77203] Avg episode reward: [(0, '54.680'), (1, '52.540')] -[2023-10-12 05:50:36,914][78091] Updated weights for policy 0, policy_version 62530 (0.0008) -[2023-10-12 05:50:37,283][78091] Updated weights for policy 0, policy_version 62540 (0.0007) -[2023-10-12 05:50:37,653][78091] Updated weights for policy 0, policy_version 62550 (0.0008) -[2023-10-12 05:50:38,024][78091] Updated weights for policy 0, policy_version 62560 (0.0007) -[2023-10-12 05:50:38,153][78123] Updated weights for policy 1, policy_version 62250 (0.0007) -[2023-10-12 05:50:38,525][78123] Updated weights for policy 1, policy_version 62260 (0.0007) -[2023-10-12 05:50:38,881][78123] Updated weights for policy 1, policy_version 62270 (0.0008) -[2023-10-12 05:50:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 127827968. Throughput: 0: 1586.3, 1: 1583.0. Samples: 31964858. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-12 05:50:40,202][77203] Avg episode reward: [(0, '52.150'), (1, '45.880')] -[2023-10-12 05:50:42,499][78091] Updated weights for policy 0, policy_version 62570 (0.0008) -[2023-10-12 05:50:42,883][78091] Updated weights for policy 0, policy_version 62580 (0.0007) -[2023-10-12 05:50:43,253][78091] Updated weights for policy 0, policy_version 62590 (0.0007) -[2023-10-12 05:50:43,331][78123] Updated weights for policy 1, policy_version 62280 (0.0008) -[2023-10-12 05:50:43,694][78123] Updated weights for policy 1, policy_version 62290 (0.0007) -[2023-10-12 05:50:44,061][78123] Updated weights for policy 1, policy_version 62300 (0.0008) -[2023-10-12 05:50:45,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 127893504. Throughput: 0: 1597.0, 1: 1597.8. Samples: 31975162. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-12 05:50:45,201][77203] Avg episode reward: [(0, '50.680'), (1, '46.670')] -[2023-10-12 05:50:47,454][78091] Updated weights for policy 0, policy_version 62600 (0.0009) -[2023-10-12 05:50:47,816][78091] Updated weights for policy 0, policy_version 62610 (0.0008) -[2023-10-12 05:50:48,188][78091] Updated weights for policy 0, policy_version 62620 (0.0010) -[2023-10-12 05:50:48,531][78123] Updated weights for policy 1, policy_version 62310 (0.0009) -[2023-10-12 05:50:48,911][78123] Updated weights for policy 1, policy_version 62320 (0.0010) -[2023-10-12 05:50:49,283][78123] Updated weights for policy 1, policy_version 62330 (0.0010) -[2023-10-12 05:50:50,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 127959040. Throughput: 0: 1588.0, 1: 1596.6. Samples: 31993698. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-12 05:50:50,201][77203] Avg episode reward: [(0, '54.120'), (1, '50.000')] -[2023-10-12 05:50:52,465][78091] Updated weights for policy 0, policy_version 62630 (0.0009) -[2023-10-12 05:50:52,836][78091] Updated weights for policy 0, policy_version 62640 (0.0009) -[2023-10-12 05:50:53,209][78091] Updated weights for policy 0, policy_version 62650 (0.0010) -[2023-10-12 05:50:53,575][78123] Updated weights for policy 1, policy_version 62340 (0.0008) -[2023-10-12 05:50:53,940][78123] Updated weights for policy 1, policy_version 62350 (0.0007) -[2023-10-12 05:50:54,304][78123] Updated weights for policy 1, policy_version 62360 (0.0008) -[2023-10-12 05:50:55,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 128024576. Throughput: 0: 1585.6, 1: 1580.7. Samples: 32012560. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-12 05:50:55,202][77203] Avg episode reward: [(0, '61.660'), (1, '52.940')] -[2023-10-12 05:50:55,214][77792] Saving new best policy, reward=61.660! -[2023-10-12 05:50:57,625][78091] Updated weights for policy 0, policy_version 62660 (0.0009) -[2023-10-12 05:50:57,987][78091] Updated weights for policy 0, policy_version 62670 (0.0009) -[2023-10-12 05:50:58,359][78091] Updated weights for policy 0, policy_version 62680 (0.0009) -[2023-10-12 05:50:58,645][78123] Updated weights for policy 1, policy_version 62370 (0.0008) -[2023-10-12 05:50:59,002][78123] Updated weights for policy 1, policy_version 62380 (0.0009) -[2023-10-12 05:50:59,369][78123] Updated weights for policy 1, policy_version 62390 (0.0009) -[2023-10-12 05:50:59,731][78123] Updated weights for policy 1, policy_version 62400 (0.0007) -[2023-10-12 05:51:00,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 128090112. Throughput: 0: 1602.9, 1: 1587.7. Samples: 32023170. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-12 05:51:00,201][77203] Avg episode reward: [(0, '49.740'), (1, '51.080')] -[2023-10-12 05:51:02,549][78091] Updated weights for policy 0, policy_version 62690 (0.0009) -[2023-10-12 05:51:02,922][78091] Updated weights for policy 0, policy_version 62700 (0.0008) -[2023-10-12 05:51:03,301][78091] Updated weights for policy 0, policy_version 62710 (0.0009) -[2023-10-12 05:51:03,667][78091] Updated weights for policy 0, policy_version 62720 (0.0009) -[2023-10-12 05:51:04,183][78123] Updated weights for policy 1, policy_version 62410 (0.0009) -[2023-10-12 05:51:04,559][78123] Updated weights for policy 1, policy_version 62420 (0.0009) -[2023-10-12 05:51:04,924][78123] Updated weights for policy 1, policy_version 62430 (0.0010) -[2023-10-12 05:51:05,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 128155648. Throughput: 0: 1584.6, 1: 1604.4. Samples: 32041954. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-12 05:51:05,201][77203] Avg episode reward: [(0, '52.640'), (1, '42.070')] -[2023-10-12 05:51:07,888][78091] Updated weights for policy 0, policy_version 62730 (0.0010) -[2023-10-12 05:51:08,259][78091] Updated weights for policy 0, policy_version 62740 (0.0012) -[2023-10-12 05:51:08,635][78091] Updated weights for policy 0, policy_version 62750 (0.0009) -[2023-10-12 05:51:09,245][78123] Updated weights for policy 1, policy_version 62440 (0.0010) -[2023-10-12 05:51:09,624][78123] Updated weights for policy 1, policy_version 62450 (0.0010) -[2023-10-12 05:51:09,988][78123] Updated weights for policy 1, policy_version 62460 (0.0010) -[2023-10-12 05:51:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 128221184. Throughput: 0: 1588.3, 1: 1592.2. Samples: 32060832. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-12 05:51:10,202][77203] Avg episode reward: [(0, '54.680'), (1, '46.900')] -[2023-10-12 05:51:10,209][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000062464_63963136.pth... -[2023-10-12 05:51:10,209][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000062752_64258048.pth... -[2023-10-12 05:51:10,240][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000060960_62423040.pth -[2023-10-12 05:51:10,249][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000061248_62717952.pth -[2023-10-12 05:51:13,096][78091] Updated weights for policy 0, policy_version 62760 (0.0009) -[2023-10-12 05:51:13,480][78091] Updated weights for policy 0, policy_version 62770 (0.0008) -[2023-10-12 05:51:13,858][78091] Updated weights for policy 0, policy_version 62780 (0.0007) -[2023-10-12 05:51:14,298][78123] Updated weights for policy 1, policy_version 62470 (0.0011) -[2023-10-12 05:51:14,671][78123] Updated weights for policy 1, policy_version 62480 (0.0009) -[2023-10-12 05:51:15,042][78123] Updated weights for policy 1, policy_version 62490 (0.0010) -[2023-10-12 05:51:15,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 128253952. Throughput: 0: 1614.2, 1: 1586.4. Samples: 32071352. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-12 05:51:15,202][77203] Avg episode reward: [(0, '58.300'), (1, '47.960')] -[2023-10-12 05:51:17,991][78091] Updated weights for policy 0, policy_version 62790 (0.0008) -[2023-10-12 05:51:18,370][78091] Updated weights for policy 0, policy_version 62800 (0.0007) -[2023-10-12 05:51:18,741][78091] Updated weights for policy 0, policy_version 62810 (0.0009) -[2023-10-12 05:51:19,534][78123] Updated weights for policy 1, policy_version 62500 (0.0009) -[2023-10-12 05:51:19,897][78123] Updated weights for policy 1, policy_version 62510 (0.0009) -[2023-10-12 05:51:20,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 128319488. Throughput: 0: 1598.8, 1: 1601.4. Samples: 32089892. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-12 05:51:20,201][77203] Avg episode reward: [(0, '59.760'), (1, '46.070')] -[2023-10-12 05:51:20,263][78123] Updated weights for policy 1, policy_version 62520 (0.0009) -[2023-10-12 05:51:22,948][78091] Updated weights for policy 0, policy_version 62820 (0.0009) -[2023-10-12 05:51:23,313][78091] Updated weights for policy 0, policy_version 62830 (0.0010) -[2023-10-12 05:51:23,685][78091] Updated weights for policy 0, policy_version 62840 (0.0008) -[2023-10-12 05:51:24,588][78123] Updated weights for policy 1, policy_version 62530 (0.0008) -[2023-10-12 05:51:24,953][78123] Updated weights for policy 1, policy_version 62540 (0.0010) -[2023-10-12 05:51:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 128385024. Throughput: 0: 1602.1, 1: 1600.5. Samples: 32108976. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-12 05:51:25,202][77203] Avg episode reward: [(0, '48.650'), (1, '41.610')] -[2023-10-12 05:51:25,315][78123] Updated weights for policy 1, policy_version 62550 (0.0009) -[2023-10-12 05:51:25,680][78123] Updated weights for policy 1, policy_version 62560 (0.0007) -[2023-10-12 05:51:27,946][78091] Updated weights for policy 0, policy_version 62850 (0.0009) -[2023-10-12 05:51:28,318][78091] Updated weights for policy 0, policy_version 62860 (0.0007) -[2023-10-12 05:51:28,697][78091] Updated weights for policy 0, policy_version 62870 (0.0007) -[2023-10-12 05:51:29,070][78091] Updated weights for policy 0, policy_version 62880 (0.0010) -[2023-10-12 05:51:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 128450560. Throughput: 0: 1622.5, 1: 1575.0. Samples: 32119052. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-12 05:51:30,202][77203] Avg episode reward: [(0, '57.640'), (1, '46.360')] -[2023-10-12 05:51:30,208][78123] Updated weights for policy 1, policy_version 62570 (0.0009) -[2023-10-12 05:51:30,577][78123] Updated weights for policy 1, policy_version 62580 (0.0010) -[2023-10-12 05:51:30,941][78123] Updated weights for policy 1, policy_version 62590 (0.0009) -[2023-10-12 05:51:33,403][78091] Updated weights for policy 0, policy_version 62890 (0.0008) -[2023-10-12 05:51:33,785][78091] Updated weights for policy 0, policy_version 62900 (0.0009) -[2023-10-12 05:51:34,145][78091] Updated weights for policy 0, policy_version 62910 (0.0011) -[2023-10-12 05:51:35,137][78123] Updated weights for policy 1, policy_version 62600 (0.0008) -[2023-10-12 05:51:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 128516096. Throughput: 0: 1614.6, 1: 1589.6. Samples: 32137888. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-12 05:51:35,202][77203] Avg episode reward: [(0, '57.370'), (1, '48.480')] -[2023-10-12 05:51:35,496][78123] Updated weights for policy 1, policy_version 62610 (0.0007) -[2023-10-12 05:51:35,864][78123] Updated weights for policy 1, policy_version 62620 (0.0007) -[2023-10-12 05:51:38,452][78091] Updated weights for policy 0, policy_version 62920 (0.0007) -[2023-10-12 05:51:38,824][78091] Updated weights for policy 0, policy_version 62930 (0.0007) -[2023-10-12 05:51:39,196][78091] Updated weights for policy 0, policy_version 62940 (0.0007) -[2023-10-12 05:51:40,135][78123] Updated weights for policy 1, policy_version 62630 (0.0010) -[2023-10-12 05:51:40,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 128581632. Throughput: 0: 1610.0, 1: 1603.9. Samples: 32157184. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-12 05:51:40,201][77203] Avg episode reward: [(0, '55.810'), (1, '47.680')] -[2023-10-12 05:51:40,511][78123] Updated weights for policy 1, policy_version 62640 (0.0010) -[2023-10-12 05:51:40,880][78123] Updated weights for policy 1, policy_version 62650 (0.0007) -[2023-10-12 05:51:43,309][78091] Updated weights for policy 0, policy_version 62950 (0.0009) -[2023-10-12 05:51:43,678][78091] Updated weights for policy 0, policy_version 62960 (0.0008) -[2023-10-12 05:51:44,055][78091] Updated weights for policy 0, policy_version 62970 (0.0010) -[2023-10-12 05:51:45,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 128647168. Throughput: 0: 1619.1, 1: 1578.0. Samples: 32167038. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-12 05:51:45,201][77203] Avg episode reward: [(0, '46.850'), (1, '55.900')] -[2023-10-12 05:51:45,214][78123] Updated weights for policy 1, policy_version 62660 (0.0007) -[2023-10-12 05:51:45,580][78123] Updated weights for policy 1, policy_version 62670 (0.0007) -[2023-10-12 05:51:45,958][78123] Updated weights for policy 1, policy_version 62680 (0.0009) -[2023-10-12 05:51:48,546][78091] Updated weights for policy 0, policy_version 62980 (0.0008) -[2023-10-12 05:51:48,920][78091] Updated weights for policy 0, policy_version 62990 (0.0008) -[2023-10-12 05:51:49,280][78091] Updated weights for policy 0, policy_version 63000 (0.0009) -[2023-10-12 05:51:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 128712704. Throughput: 0: 1623.2, 1: 1576.9. Samples: 32185960. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-12 05:51:50,201][77203] Avg episode reward: [(0, '51.190'), (1, '49.320')] -[2023-10-12 05:51:50,356][78123] Updated weights for policy 1, policy_version 62690 (0.0008) -[2023-10-12 05:51:50,731][78123] Updated weights for policy 1, policy_version 62700 (0.0007) -[2023-10-12 05:51:51,095][78123] Updated weights for policy 1, policy_version 62710 (0.0008) -[2023-10-12 05:51:51,463][78123] Updated weights for policy 1, policy_version 62720 (0.0008) -[2023-10-12 05:51:53,495][78091] Updated weights for policy 0, policy_version 63010 (0.0009) -[2023-10-12 05:51:53,856][78091] Updated weights for policy 0, policy_version 63020 (0.0009) -[2023-10-12 05:51:54,225][78091] Updated weights for policy 0, policy_version 63030 (0.0008) -[2023-10-12 05:51:54,595][78091] Updated weights for policy 0, policy_version 63040 (0.0009) -[2023-10-12 05:51:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 128778240. Throughput: 0: 1604.7, 1: 1591.4. Samples: 32204656. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-12 05:51:55,201][77203] Avg episode reward: [(0, '52.200'), (1, '52.950')] -[2023-10-12 05:51:55,773][78123] Updated weights for policy 1, policy_version 62730 (0.0010) -[2023-10-12 05:51:56,150][78123] Updated weights for policy 1, policy_version 62740 (0.0009) -[2023-10-12 05:51:56,518][78123] Updated weights for policy 1, policy_version 62750 (0.0009) -[2023-10-12 05:51:58,986][78091] Updated weights for policy 0, policy_version 63050 (0.0008) -[2023-10-12 05:51:59,353][78091] Updated weights for policy 0, policy_version 63060 (0.0007) -[2023-10-12 05:51:59,725][78091] Updated weights for policy 0, policy_version 63070 (0.0007) -[2023-10-12 05:52:00,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 128843776. Throughput: 0: 1607.9, 1: 1571.9. Samples: 32214444. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-12 05:52:00,201][77203] Avg episode reward: [(0, '54.590'), (1, '43.850')] -[2023-10-12 05:52:00,996][78123] Updated weights for policy 1, policy_version 62760 (0.0008) -[2023-10-12 05:52:01,366][78123] Updated weights for policy 1, policy_version 62770 (0.0007) -[2023-10-12 05:52:01,737][78123] Updated weights for policy 1, policy_version 62780 (0.0008) -[2023-10-12 05:52:04,077][78091] Updated weights for policy 0, policy_version 63080 (0.0008) -[2023-10-12 05:52:04,450][78091] Updated weights for policy 0, policy_version 63090 (0.0008) -[2023-10-12 05:52:04,824][78091] Updated weights for policy 0, policy_version 63100 (0.0009) -[2023-10-12 05:52:05,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 128909312. Throughput: 0: 1623.0, 1: 1577.6. Samples: 32233920. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-12 05:52:05,202][77203] Avg episode reward: [(0, '52.810'), (1, '50.460')] -[2023-10-12 05:52:06,196][78123] Updated weights for policy 1, policy_version 62790 (0.0008) -[2023-10-12 05:52:06,560][78123] Updated weights for policy 1, policy_version 62800 (0.0010) -[2023-10-12 05:52:06,935][78123] Updated weights for policy 1, policy_version 62810 (0.0008) -[2023-10-12 05:52:08,973][78091] Updated weights for policy 0, policy_version 63110 (0.0009) -[2023-10-12 05:52:09,348][78091] Updated weights for policy 0, policy_version 63120 (0.0010) -[2023-10-12 05:52:09,717][78091] Updated weights for policy 0, policy_version 63130 (0.0009) -[2023-10-12 05:52:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 128974848. Throughput: 0: 1607.6, 1: 1582.7. Samples: 32252538. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-12 05:52:10,201][77203] Avg episode reward: [(0, '57.830'), (1, '50.390')] -[2023-10-12 05:52:11,271][78123] Updated weights for policy 1, policy_version 62820 (0.0009) -[2023-10-12 05:52:11,651][78123] Updated weights for policy 1, policy_version 62830 (0.0010) -[2023-10-12 05:52:12,030][78123] Updated weights for policy 1, policy_version 62840 (0.0009) -[2023-10-12 05:52:14,050][78091] Updated weights for policy 0, policy_version 63140 (0.0010) -[2023-10-12 05:52:14,423][78091] Updated weights for policy 0, policy_version 63150 (0.0010) -[2023-10-12 05:52:14,792][78091] Updated weights for policy 0, policy_version 63160 (0.0007) -[2023-10-12 05:52:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 129040384. Throughput: 0: 1598.9, 1: 1581.8. Samples: 32262184. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-12 05:52:15,202][77203] Avg episode reward: [(0, '55.430'), (1, '47.380')] -[2023-10-12 05:52:16,140][78123] Updated weights for policy 1, policy_version 62850 (0.0009) -[2023-10-12 05:52:16,505][78123] Updated weights for policy 1, policy_version 62860 (0.0007) -[2023-10-12 05:52:16,870][78123] Updated weights for policy 1, policy_version 62870 (0.0008) -[2023-10-12 05:52:17,234][78123] Updated weights for policy 1, policy_version 62880 (0.0009) -[2023-10-12 05:52:19,154][78091] Updated weights for policy 0, policy_version 63170 (0.0007) -[2023-10-12 05:52:19,519][78091] Updated weights for policy 0, policy_version 63180 (0.0010) -[2023-10-12 05:52:19,896][78091] Updated weights for policy 0, policy_version 63190 (0.0008) -[2023-10-12 05:52:20,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 129073152. Throughput: 0: 1612.4, 1: 1582.8. Samples: 32281670. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-12 05:52:20,201][77203] Avg episode reward: [(0, '56.380'), (1, '46.190')] -[2023-10-12 05:52:20,262][78091] Updated weights for policy 0, policy_version 63200 (0.0007) -[2023-10-12 05:52:21,817][78123] Updated weights for policy 1, policy_version 62890 (0.0008) -[2023-10-12 05:52:22,184][78123] Updated weights for policy 1, policy_version 62900 (0.0009) -[2023-10-12 05:52:22,550][78123] Updated weights for policy 1, policy_version 62910 (0.0011) -[2023-10-12 05:52:24,400][78091] Updated weights for policy 0, policy_version 63210 (0.0009) -[2023-10-12 05:52:24,778][78091] Updated weights for policy 0, policy_version 63220 (0.0008) -[2023-10-12 05:52:25,150][78091] Updated weights for policy 0, policy_version 63230 (0.0008) -[2023-10-12 05:52:25,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 129138688. Throughput: 0: 1606.3, 1: 1581.6. Samples: 32300644. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-12 05:52:25,202][77203] Avg episode reward: [(0, '55.390'), (1, '44.980')] -[2023-10-12 05:52:26,493][78123] Updated weights for policy 1, policy_version 62920 (0.0008) -[2023-10-12 05:52:26,857][78123] Updated weights for policy 1, policy_version 62930 (0.0010) -[2023-10-12 05:52:27,225][78123] Updated weights for policy 1, policy_version 62940 (0.0011) -[2023-10-12 05:52:29,362][78091] Updated weights for policy 0, policy_version 63240 (0.0008) -[2023-10-12 05:52:29,738][78091] Updated weights for policy 0, policy_version 63250 (0.0007) -[2023-10-12 05:52:30,110][78091] Updated weights for policy 0, policy_version 63260 (0.0008) -[2023-10-12 05:52:30,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 129204224. Throughput: 0: 1598.7, 1: 1583.2. Samples: 32310226. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-12 05:52:30,202][77203] Avg episode reward: [(0, '56.010'), (1, '46.640')] -[2023-10-12 05:52:31,685][78123] Updated weights for policy 1, policy_version 62950 (0.0008) -[2023-10-12 05:52:32,058][78123] Updated weights for policy 1, policy_version 62960 (0.0008) -[2023-10-12 05:52:32,417][78123] Updated weights for policy 1, policy_version 62970 (0.0008) -[2023-10-12 05:52:34,264][78091] Updated weights for policy 0, policy_version 63270 (0.0009) -[2023-10-12 05:52:34,643][78091] Updated weights for policy 0, policy_version 63280 (0.0009) -[2023-10-12 05:52:35,007][78091] Updated weights for policy 0, policy_version 63290 (0.0010) -[2023-10-12 05:52:35,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 129269760. Throughput: 0: 1616.6, 1: 1581.0. Samples: 32329850. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-12 05:52:35,201][77203] Avg episode reward: [(0, '56.640'), (1, '49.270')] -[2023-10-12 05:52:36,560][78123] Updated weights for policy 1, policy_version 62980 (0.0009) -[2023-10-12 05:52:36,933][78123] Updated weights for policy 1, policy_version 62990 (0.0009) -[2023-10-12 05:52:37,296][78123] Updated weights for policy 1, policy_version 63000 (0.0009) -[2023-10-12 05:52:39,456][78091] Updated weights for policy 0, policy_version 63300 (0.0007) -[2023-10-12 05:52:39,835][78091] Updated weights for policy 0, policy_version 63310 (0.0010) -[2023-10-12 05:52:40,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 129335296. Throughput: 0: 1622.2, 1: 1590.0. Samples: 32349202. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-12 05:52:40,201][77203] Avg episode reward: [(0, '51.780'), (1, '49.850')] -[2023-10-12 05:52:40,208][78091] Updated weights for policy 0, policy_version 63320 (0.0010) -[2023-10-12 05:52:41,573][78123] Updated weights for policy 1, policy_version 63010 (0.0007) -[2023-10-12 05:52:41,944][78123] Updated weights for policy 1, policy_version 63020 (0.0007) -[2023-10-12 05:52:42,313][78123] Updated weights for policy 1, policy_version 63030 (0.0008) -[2023-10-12 05:52:42,678][78123] Updated weights for policy 1, policy_version 63040 (0.0007) -[2023-10-12 05:52:44,570][78091] Updated weights for policy 0, policy_version 63330 (0.0010) -[2023-10-12 05:52:44,960][78091] Updated weights for policy 0, policy_version 63340 (0.0010) -[2023-10-12 05:52:45,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 129400832. Throughput: 0: 1606.2, 1: 1593.9. Samples: 32358446. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-12 05:52:45,202][77203] Avg episode reward: [(0, '59.430'), (1, '50.270')] -[2023-10-12 05:52:45,330][78091] Updated weights for policy 0, policy_version 63350 (0.0010) -[2023-10-12 05:52:45,705][78091] Updated weights for policy 0, policy_version 63360 (0.0010) -[2023-10-12 05:52:46,837][78123] Updated weights for policy 1, policy_version 63050 (0.0010) -[2023-10-12 05:52:47,208][78123] Updated weights for policy 1, policy_version 63060 (0.0008) -[2023-10-12 05:52:47,576][78123] Updated weights for policy 1, policy_version 63070 (0.0009) -[2023-10-12 05:52:49,987][78091] Updated weights for policy 0, policy_version 63370 (0.0010) -[2023-10-12 05:52:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 129466368. Throughput: 0: 1603.9, 1: 1596.4. Samples: 32377934. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-12 05:52:50,201][77203] Avg episode reward: [(0, '65.190'), (1, '46.390')] -[2023-10-12 05:52:50,362][78091] Updated weights for policy 0, policy_version 63380 (0.0009) -[2023-10-12 05:52:50,734][78091] Updated weights for policy 0, policy_version 63390 (0.0007) -[2023-10-12 05:52:50,805][77792] Saving new best policy, reward=65.190! -[2023-10-12 05:52:52,025][78123] Updated weights for policy 1, policy_version 63080 (0.0009) -[2023-10-12 05:52:52,392][78123] Updated weights for policy 1, policy_version 63090 (0.0009) -[2023-10-12 05:52:52,761][78123] Updated weights for policy 1, policy_version 63100 (0.0011) -[2023-10-12 05:52:54,974][78091] Updated weights for policy 0, policy_version 63400 (0.0007) -[2023-10-12 05:52:55,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 129531904. Throughput: 0: 1620.1, 1: 1599.4. Samples: 32397414. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-12 05:52:55,201][77203] Avg episode reward: [(0, '54.430'), (1, '48.210')] -[2023-10-12 05:52:55,347][78091] Updated weights for policy 0, policy_version 63410 (0.0007) -[2023-10-12 05:52:55,719][78091] Updated weights for policy 0, policy_version 63420 (0.0007) -[2023-10-12 05:52:56,956][78123] Updated weights for policy 1, policy_version 63110 (0.0010) -[2023-10-12 05:52:57,337][78123] Updated weights for policy 1, policy_version 63120 (0.0007) -[2023-10-12 05:52:57,708][78123] Updated weights for policy 1, policy_version 63130 (0.0008) -[2023-10-12 05:53:00,037][78091] Updated weights for policy 0, policy_version 63430 (0.0009) -[2023-10-12 05:53:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 129597440. Throughput: 0: 1603.7, 1: 1608.3. Samples: 32406722. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-12 05:53:00,201][77203] Avg episode reward: [(0, '48.190'), (1, '47.940')] -[2023-10-12 05:53:00,401][78091] Updated weights for policy 0, policy_version 63440 (0.0009) -[2023-10-12 05:53:00,777][78091] Updated weights for policy 0, policy_version 63450 (0.0011) -[2023-10-12 05:53:02,037][78123] Updated weights for policy 1, policy_version 63140 (0.0009) -[2023-10-12 05:53:02,402][78123] Updated weights for policy 1, policy_version 63150 (0.0009) -[2023-10-12 05:53:02,769][78123] Updated weights for policy 1, policy_version 63160 (0.0010) -[2023-10-12 05:53:04,907][78091] Updated weights for policy 0, policy_version 63460 (0.0010) -[2023-10-12 05:53:05,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 129662976. Throughput: 0: 1605.8, 1: 1603.5. Samples: 32426088. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-12 05:53:05,202][77203] Avg episode reward: [(0, '50.100'), (1, '47.780')] -[2023-10-12 05:53:05,283][78091] Updated weights for policy 0, policy_version 63470 (0.0007) -[2023-10-12 05:53:05,662][78091] Updated weights for policy 0, policy_version 63480 (0.0009) -[2023-10-12 05:53:07,282][78123] Updated weights for policy 1, policy_version 63170 (0.0009) -[2023-10-12 05:53:07,699][78123] Updated weights for policy 1, policy_version 63180 (0.0011) -[2023-10-12 05:53:08,074][78123] Updated weights for policy 1, policy_version 63190 (0.0008) -[2023-10-12 05:53:08,432][78123] Updated weights for policy 1, policy_version 63200 (0.0008) -[2023-10-12 05:53:09,914][78091] Updated weights for policy 0, policy_version 63490 (0.0009) -[2023-10-12 05:53:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 129728512. Throughput: 0: 1619.4, 1: 1597.8. Samples: 32445420. Policy #0 lag: (min: 31.0, avg: 43.6, max: 63.0) -[2023-10-12 05:53:10,201][77203] Avg episode reward: [(0, '55.810'), (1, '44.560')] -[2023-10-12 05:53:10,211][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000063200_64716800.pth... -[2023-10-12 05:53:10,250][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000061696_63176704.pth -[2023-10-12 05:53:10,280][78091] Updated weights for policy 0, policy_version 63500 (0.0008) -[2023-10-12 05:53:10,663][78091] Updated weights for policy 0, policy_version 63510 (0.0007) -[2023-10-12 05:53:11,039][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000063520_65044480.pth... -[2023-10-12 05:53:11,040][78091] Updated weights for policy 0, policy_version 63520 (0.0010) -[2023-10-12 05:53:11,081][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000062016_63504384.pth -[2023-10-12 05:53:12,659][78123] Updated weights for policy 1, policy_version 63210 (0.0009) -[2023-10-12 05:53:13,027][78123] Updated weights for policy 1, policy_version 63220 (0.0009) -[2023-10-12 05:53:13,402][78123] Updated weights for policy 1, policy_version 63230 (0.0007) -[2023-10-12 05:53:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 129794048. Throughput: 0: 1596.8, 1: 1616.5. Samples: 32454826. Policy #0 lag: (min: 31.0, avg: 43.6, max: 63.0) -[2023-10-12 05:53:15,202][77203] Avg episode reward: [(0, '51.390'), (1, '44.320')] -[2023-10-12 05:53:15,309][78091] Updated weights for policy 0, policy_version 63530 (0.0007) -[2023-10-12 05:53:15,679][78091] Updated weights for policy 0, policy_version 63540 (0.0009) -[2023-10-12 05:53:16,065][78091] Updated weights for policy 0, policy_version 63550 (0.0008) -[2023-10-12 05:53:17,900][78123] Updated weights for policy 1, policy_version 63240 (0.0010) -[2023-10-12 05:53:18,268][78123] Updated weights for policy 1, policy_version 63250 (0.0010) -[2023-10-12 05:53:18,634][78123] Updated weights for policy 1, policy_version 63260 (0.0011) -[2023-10-12 05:53:20,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 129859584. Throughput: 0: 1592.8, 1: 1601.4. Samples: 32473586. Policy #0 lag: (min: 31.0, avg: 43.6, max: 63.0) -[2023-10-12 05:53:20,201][77203] Avg episode reward: [(0, '48.930'), (1, '45.750')] -[2023-10-12 05:53:20,439][78091] Updated weights for policy 0, policy_version 63560 (0.0009) -[2023-10-12 05:53:20,805][78091] Updated weights for policy 0, policy_version 63570 (0.0009) -[2023-10-12 05:53:21,179][78091] Updated weights for policy 0, policy_version 63580 (0.0008) -[2023-10-12 05:53:22,969][78123] Updated weights for policy 1, policy_version 63270 (0.0008) -[2023-10-12 05:53:23,327][78123] Updated weights for policy 1, policy_version 63280 (0.0007) -[2023-10-12 05:53:23,698][78123] Updated weights for policy 1, policy_version 63290 (0.0007) -[2023-10-12 05:53:25,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 129925120. Throughput: 0: 1606.6, 1: 1593.1. Samples: 32493188. Policy #0 lag: (min: 31.0, avg: 43.6, max: 63.0) -[2023-10-12 05:53:25,201][77203] Avg episode reward: [(0, '48.900'), (1, '48.170')] -[2023-10-12 05:53:25,481][78091] Updated weights for policy 0, policy_version 63590 (0.0008) -[2023-10-12 05:53:25,851][78091] Updated weights for policy 0, policy_version 63600 (0.0008) -[2023-10-12 05:53:26,215][78091] Updated weights for policy 0, policy_version 63610 (0.0008) -[2023-10-12 05:53:28,143][78123] Updated weights for policy 1, policy_version 63300 (0.0009) -[2023-10-12 05:53:28,504][78123] Updated weights for policy 1, policy_version 63310 (0.0010) -[2023-10-12 05:53:28,872][78123] Updated weights for policy 1, policy_version 63320 (0.0009) -[2023-10-12 05:53:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 129990656. Throughput: 0: 1594.5, 1: 1617.2. Samples: 32502976. Policy #0 lag: (min: 31.0, avg: 43.6, max: 63.0) -[2023-10-12 05:53:30,201][77203] Avg episode reward: [(0, '56.280'), (1, '50.410')] -[2023-10-12 05:53:30,476][78091] Updated weights for policy 0, policy_version 63620 (0.0008) -[2023-10-12 05:53:30,865][78091] Updated weights for policy 0, policy_version 63630 (0.0009) -[2023-10-12 05:53:31,226][78091] Updated weights for policy 0, policy_version 63640 (0.0007) -[2023-10-12 05:53:33,165][78123] Updated weights for policy 1, policy_version 63330 (0.0009) -[2023-10-12 05:53:33,539][78123] Updated weights for policy 1, policy_version 63340 (0.0010) -[2023-10-12 05:53:33,904][78123] Updated weights for policy 1, policy_version 63350 (0.0009) -[2023-10-12 05:53:34,263][78123] Updated weights for policy 1, policy_version 63360 (0.0009) -[2023-10-12 05:53:35,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 130056192. Throughput: 0: 1598.8, 1: 1599.1. Samples: 32521840. Policy #0 lag: (min: 31.0, avg: 43.6, max: 63.0) -[2023-10-12 05:53:35,202][77203] Avg episode reward: [(0, '59.110'), (1, '44.000')] -[2023-10-12 05:53:35,575][78091] Updated weights for policy 0, policy_version 63650 (0.0008) -[2023-10-12 05:53:35,946][78091] Updated weights for policy 0, policy_version 63660 (0.0008) -[2023-10-12 05:53:36,330][78091] Updated weights for policy 0, policy_version 63670 (0.0012) -[2023-10-12 05:53:36,695][78091] Updated weights for policy 0, policy_version 63680 (0.0010) -[2023-10-12 05:53:38,385][78123] Updated weights for policy 1, policy_version 63370 (0.0007) -[2023-10-12 05:53:38,755][78123] Updated weights for policy 1, policy_version 63380 (0.0008) -[2023-10-12 05:53:39,126][78123] Updated weights for policy 1, policy_version 63390 (0.0009) -[2023-10-12 05:53:40,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 130121728. Throughput: 0: 1599.9, 1: 1585.7. Samples: 32540766. Policy #0 lag: (min: 31.0, avg: 43.6, max: 63.0) -[2023-10-12 05:53:40,202][77203] Avg episode reward: [(0, '53.750'), (1, '50.790')] -[2023-10-12 05:53:41,091][78091] Updated weights for policy 0, policy_version 63690 (0.0009) -[2023-10-12 05:53:41,464][78091] Updated weights for policy 0, policy_version 63700 (0.0007) -[2023-10-12 05:53:41,837][78091] Updated weights for policy 0, policy_version 63710 (0.0007) -[2023-10-12 05:53:43,479][78123] Updated weights for policy 1, policy_version 63400 (0.0010) -[2023-10-12 05:53:43,852][78123] Updated weights for policy 1, policy_version 63410 (0.0010) -[2023-10-12 05:53:44,207][78123] Updated weights for policy 1, policy_version 63420 (0.0010) -[2023-10-12 05:53:45,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 130187264. Throughput: 0: 1593.2, 1: 1600.5. Samples: 32550440. Policy #0 lag: (min: 31.0, avg: 43.6, max: 63.0) -[2023-10-12 05:53:45,201][77203] Avg episode reward: [(0, '50.930'), (1, '47.030')] -[2023-10-12 05:53:46,037][78091] Updated weights for policy 0, policy_version 63720 (0.0009) -[2023-10-12 05:53:46,403][78091] Updated weights for policy 0, policy_version 63730 (0.0009) -[2023-10-12 05:53:46,768][78091] Updated weights for policy 0, policy_version 63740 (0.0008) -[2023-10-12 05:53:48,662][78123] Updated weights for policy 1, policy_version 63430 (0.0009) -[2023-10-12 05:53:49,034][78123] Updated weights for policy 1, policy_version 63440 (0.0010) -[2023-10-12 05:53:49,401][78123] Updated weights for policy 1, policy_version 63450 (0.0009) -[2023-10-12 05:53:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 130252800. Throughput: 0: 1596.2, 1: 1595.9. Samples: 32569732. Policy #0 lag: (min: 21.0, avg: 30.3, max: 53.0) -[2023-10-12 05:53:50,202][77203] Avg episode reward: [(0, '58.960'), (1, '52.780')] -[2023-10-12 05:53:51,150][78091] Updated weights for policy 0, policy_version 63750 (0.0009) -[2023-10-12 05:53:51,507][78091] Updated weights for policy 0, policy_version 63760 (0.0011) -[2023-10-12 05:53:51,884][78091] Updated weights for policy 0, policy_version 63770 (0.0010) -[2023-10-12 05:53:53,870][78123] Updated weights for policy 1, policy_version 63460 (0.0008) -[2023-10-12 05:53:54,244][78123] Updated weights for policy 1, policy_version 63470 (0.0009) -[2023-10-12 05:53:54,608][78123] Updated weights for policy 1, policy_version 63480 (0.0009) -[2023-10-12 05:53:55,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 130318336. Throughput: 0: 1594.9, 1: 1589.3. Samples: 32588708. Policy #0 lag: (min: 21.0, avg: 30.3, max: 53.0) -[2023-10-12 05:53:55,202][77203] Avg episode reward: [(0, '61.590'), (1, '52.320')] -[2023-10-12 05:53:56,218][78091] Updated weights for policy 0, policy_version 63780 (0.0010) -[2023-10-12 05:53:56,584][78091] Updated weights for policy 0, policy_version 63790 (0.0008) -[2023-10-12 05:53:56,957][78091] Updated weights for policy 0, policy_version 63800 (0.0010) -[2023-10-12 05:53:58,820][78123] Updated weights for policy 1, policy_version 63490 (0.0008) -[2023-10-12 05:53:59,183][78123] Updated weights for policy 1, policy_version 63500 (0.0009) -[2023-10-12 05:53:59,552][78123] Updated weights for policy 1, policy_version 63510 (0.0008) -[2023-10-12 05:53:59,912][78123] Updated weights for policy 1, policy_version 63520 (0.0008) -[2023-10-12 05:54:00,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 130383872. Throughput: 0: 1596.0, 1: 1594.5. Samples: 32598394. Policy #0 lag: (min: 21.0, avg: 30.3, max: 53.0) -[2023-10-12 05:54:00,203][77203] Avg episode reward: [(0, '51.270'), (1, '43.450')] -[2023-10-12 05:54:01,294][78091] Updated weights for policy 0, policy_version 63810 (0.0009) -[2023-10-12 05:54:01,670][78091] Updated weights for policy 0, policy_version 63820 (0.0008) -[2023-10-12 05:54:02,036][78091] Updated weights for policy 0, policy_version 63830 (0.0007) -[2023-10-12 05:54:02,409][78091] Updated weights for policy 0, policy_version 63840 (0.0009) -[2023-10-12 05:54:04,281][78123] Updated weights for policy 1, policy_version 63530 (0.0007) -[2023-10-12 05:54:04,653][78123] Updated weights for policy 1, policy_version 63540 (0.0007) -[2023-10-12 05:54:05,014][78123] Updated weights for policy 1, policy_version 63550 (0.0007) -[2023-10-12 05:54:05,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 130449408. Throughput: 0: 1597.4, 1: 1610.4. Samples: 32617938. Policy #0 lag: (min: 21.0, avg: 30.3, max: 53.0) -[2023-10-12 05:54:05,202][77203] Avg episode reward: [(0, '52.950'), (1, '46.550')] -[2023-10-12 05:54:06,595][78091] Updated weights for policy 0, policy_version 63850 (0.0011) -[2023-10-12 05:54:06,968][78091] Updated weights for policy 0, policy_version 63860 (0.0011) -[2023-10-12 05:54:07,339][78091] Updated weights for policy 0, policy_version 63870 (0.0010) -[2023-10-12 05:54:09,280][78123] Updated weights for policy 1, policy_version 63560 (0.0010) -[2023-10-12 05:54:09,654][78123] Updated weights for policy 1, policy_version 63570 (0.0009) -[2023-10-12 05:54:10,018][78123] Updated weights for policy 1, policy_version 63580 (0.0009) -[2023-10-12 05:54:10,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 12885.0). Total num frames: 130514944. Throughput: 0: 1595.9, 1: 1595.5. Samples: 32636800. Policy #0 lag: (min: 21.0, avg: 30.3, max: 53.0) -[2023-10-12 05:54:10,202][77203] Avg episode reward: [(0, '56.480'), (1, '50.340')] -[2023-10-12 05:54:11,510][78091] Updated weights for policy 0, policy_version 63880 (0.0008) -[2023-10-12 05:54:11,879][78091] Updated weights for policy 0, policy_version 63890 (0.0009) -[2023-10-12 05:54:12,245][78091] Updated weights for policy 0, policy_version 63900 (0.0007) -[2023-10-12 05:54:14,305][78123] Updated weights for policy 1, policy_version 63590 (0.0010) -[2023-10-12 05:54:14,666][78123] Updated weights for policy 1, policy_version 63600 (0.0011) -[2023-10-12 05:54:15,029][78123] Updated weights for policy 1, policy_version 63610 (0.0009) -[2023-10-12 05:54:15,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 130547712. Throughput: 0: 1599.2, 1: 1585.3. Samples: 32646280. Policy #0 lag: (min: 21.0, avg: 30.3, max: 53.0) -[2023-10-12 05:54:15,202][77203] Avg episode reward: [(0, '55.340'), (1, '50.320')] -[2023-10-12 05:54:16,712][78091] Updated weights for policy 0, policy_version 63910 (0.0008) -[2023-10-12 05:54:17,088][78091] Updated weights for policy 0, policy_version 63920 (0.0008) -[2023-10-12 05:54:17,467][78091] Updated weights for policy 0, policy_version 63930 (0.0008) -[2023-10-12 05:54:19,204][78123] Updated weights for policy 1, policy_version 63620 (0.0008) -[2023-10-12 05:54:19,579][78123] Updated weights for policy 1, policy_version 63630 (0.0009) -[2023-10-12 05:54:19,947][78123] Updated weights for policy 1, policy_version 63640 (0.0007) -[2023-10-12 05:54:20,201][77203] Fps is (10 sec: 9830.6, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 130613248. Throughput: 0: 1599.7, 1: 1597.7. Samples: 32665726. Policy #0 lag: (min: 21.0, avg: 30.3, max: 53.0) -[2023-10-12 05:54:20,202][77203] Avg episode reward: [(0, '53.220'), (1, '49.200')] -[2023-10-12 05:54:21,757][78091] Updated weights for policy 0, policy_version 63940 (0.0009) -[2023-10-12 05:54:22,147][78091] Updated weights for policy 0, policy_version 63950 (0.0009) -[2023-10-12 05:54:22,518][78091] Updated weights for policy 0, policy_version 63960 (0.0008) -[2023-10-12 05:54:24,387][78123] Updated weights for policy 1, policy_version 63650 (0.0009) -[2023-10-12 05:54:24,762][78123] Updated weights for policy 1, policy_version 63660 (0.0008) -[2023-10-12 05:54:25,126][78123] Updated weights for policy 1, policy_version 63670 (0.0009) -[2023-10-12 05:54:25,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 130678784. Throughput: 0: 1602.2, 1: 1601.3. Samples: 32684922. Policy #0 lag: (min: 21.0, avg: 30.3, max: 53.0) -[2023-10-12 05:54:25,201][77203] Avg episode reward: [(0, '49.880'), (1, '47.460')] -[2023-10-12 05:54:25,491][78123] Updated weights for policy 1, policy_version 63680 (0.0007) -[2023-10-12 05:54:26,795][78091] Updated weights for policy 0, policy_version 63970 (0.0008) -[2023-10-12 05:54:27,157][78091] Updated weights for policy 0, policy_version 63980 (0.0008) -[2023-10-12 05:54:27,542][78091] Updated weights for policy 0, policy_version 63990 (0.0009) -[2023-10-12 05:54:27,918][78091] Updated weights for policy 0, policy_version 64000 (0.0010) -[2023-10-12 05:54:29,808][78123] Updated weights for policy 1, policy_version 63690 (0.0009) -[2023-10-12 05:54:30,170][78123] Updated weights for policy 1, policy_version 63700 (0.0012) -[2023-10-12 05:54:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 130744320. Throughput: 0: 1608.3, 1: 1587.6. Samples: 32694254. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:54:30,201][77203] Avg episode reward: [(0, '53.220'), (1, '51.540')] -[2023-10-12 05:54:30,532][78123] Updated weights for policy 1, policy_version 63710 (0.0008) -[2023-10-12 05:54:32,201][78091] Updated weights for policy 0, policy_version 64010 (0.0008) -[2023-10-12 05:54:32,559][78091] Updated weights for policy 0, policy_version 64020 (0.0008) -[2023-10-12 05:54:32,932][78091] Updated weights for policy 0, policy_version 64030 (0.0010) -[2023-10-12 05:54:34,976][78123] Updated weights for policy 1, policy_version 63720 (0.0009) -[2023-10-12 05:54:35,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 130809856. Throughput: 0: 1599.0, 1: 1597.5. Samples: 32713574. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:54:35,202][77203] Avg episode reward: [(0, '59.920'), (1, '50.030')] -[2023-10-12 05:54:35,347][78123] Updated weights for policy 1, policy_version 63730 (0.0008) -[2023-10-12 05:54:35,711][78123] Updated weights for policy 1, policy_version 63740 (0.0007) -[2023-10-12 05:54:37,040][78091] Updated weights for policy 0, policy_version 64040 (0.0008) -[2023-10-12 05:54:37,417][78091] Updated weights for policy 0, policy_version 64050 (0.0009) -[2023-10-12 05:54:37,783][78091] Updated weights for policy 0, policy_version 64060 (0.0008) -[2023-10-12 05:54:40,139][78123] Updated weights for policy 1, policy_version 63750 (0.0009) -[2023-10-12 05:54:40,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 130875392. Throughput: 0: 1598.4, 1: 1610.4. Samples: 32733102. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:54:40,201][77203] Avg episode reward: [(0, '65.550'), (1, '48.050')] -[2023-10-12 05:54:40,208][77792] Saving new best policy, reward=65.550! -[2023-10-12 05:54:40,524][78123] Updated weights for policy 1, policy_version 63760 (0.0009) -[2023-10-12 05:54:40,894][78123] Updated weights for policy 1, policy_version 63770 (0.0008) -[2023-10-12 05:54:42,204][78091] Updated weights for policy 0, policy_version 64070 (0.0008) -[2023-10-12 05:54:42,564][78091] Updated weights for policy 0, policy_version 64080 (0.0008) -[2023-10-12 05:54:42,943][78091] Updated weights for policy 0, policy_version 64090 (0.0008) -[2023-10-12 05:54:45,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 130940928. Throughput: 0: 1607.3, 1: 1586.4. Samples: 32742112. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:54:45,202][77203] Avg episode reward: [(0, '59.500'), (1, '48.600')] -[2023-10-12 05:54:45,276][78123] Updated weights for policy 1, policy_version 63780 (0.0008) -[2023-10-12 05:54:45,643][78123] Updated weights for policy 1, policy_version 63790 (0.0010) -[2023-10-12 05:54:46,003][78123] Updated weights for policy 1, policy_version 63800 (0.0009) -[2023-10-12 05:54:47,249][78091] Updated weights for policy 0, policy_version 64100 (0.0008) -[2023-10-12 05:54:47,616][78091] Updated weights for policy 0, policy_version 64110 (0.0009) -[2023-10-12 05:54:47,987][78091] Updated weights for policy 0, policy_version 64120 (0.0009) -[2023-10-12 05:54:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 131006464. Throughput: 0: 1594.4, 1: 1583.5. Samples: 32760942. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:54:50,201][77203] Avg episode reward: [(0, '58.170'), (1, '52.300')] -[2023-10-12 05:54:50,311][78123] Updated weights for policy 1, policy_version 63810 (0.0010) -[2023-10-12 05:54:50,688][78123] Updated weights for policy 1, policy_version 63820 (0.0010) -[2023-10-12 05:54:51,048][78123] Updated weights for policy 1, policy_version 63830 (0.0009) -[2023-10-12 05:54:51,411][78123] Updated weights for policy 1, policy_version 63840 (0.0010) -[2023-10-12 05:54:52,310][78091] Updated weights for policy 0, policy_version 64130 (0.0009) -[2023-10-12 05:54:52,683][78091] Updated weights for policy 0, policy_version 64140 (0.0007) -[2023-10-12 05:54:53,042][78091] Updated weights for policy 0, policy_version 64150 (0.0007) -[2023-10-12 05:54:53,414][78091] Updated weights for policy 0, policy_version 64160 (0.0009) -[2023-10-12 05:54:55,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 131072000. Throughput: 0: 1597.1, 1: 1594.9. Samples: 32780440. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:54:55,202][77203] Avg episode reward: [(0, '60.490'), (1, '49.560')] -[2023-10-12 05:54:55,761][78123] Updated weights for policy 1, policy_version 63850 (0.0008) -[2023-10-12 05:54:56,130][78123] Updated weights for policy 1, policy_version 63860 (0.0009) -[2023-10-12 05:54:56,498][78123] Updated weights for policy 1, policy_version 63870 (0.0008) -[2023-10-12 05:54:57,659][78091] Updated weights for policy 0, policy_version 64170 (0.0009) -[2023-10-12 05:54:58,034][78091] Updated weights for policy 0, policy_version 64180 (0.0009) -[2023-10-12 05:54:58,410][78091] Updated weights for policy 0, policy_version 64190 (0.0007) -[2023-10-12 05:55:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 131137536. Throughput: 0: 1611.8, 1: 1577.9. Samples: 32789814. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:55:00,201][77203] Avg episode reward: [(0, '57.710'), (1, '48.280')] -[2023-10-12 05:55:00,898][78123] Updated weights for policy 1, policy_version 63880 (0.0009) -[2023-10-12 05:55:01,257][78123] Updated weights for policy 1, policy_version 63890 (0.0008) -[2023-10-12 05:55:01,627][78123] Updated weights for policy 1, policy_version 63900 (0.0008) -[2023-10-12 05:55:02,775][78091] Updated weights for policy 0, policy_version 64200 (0.0008) -[2023-10-12 05:55:03,147][78091] Updated weights for policy 0, policy_version 64210 (0.0007) -[2023-10-12 05:55:03,513][78091] Updated weights for policy 0, policy_version 64220 (0.0007) -[2023-10-12 05:55:05,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 131203072. Throughput: 0: 1591.8, 1: 1586.8. Samples: 32808760. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:55:05,201][77203] Avg episode reward: [(0, '50.600'), (1, '47.040')] -[2023-10-12 05:55:05,863][78123] Updated weights for policy 1, policy_version 63910 (0.0009) -[2023-10-12 05:55:06,219][78123] Updated weights for policy 1, policy_version 63920 (0.0009) -[2023-10-12 05:55:06,587][78123] Updated weights for policy 1, policy_version 63930 (0.0007) -[2023-10-12 05:55:07,961][78091] Updated weights for policy 0, policy_version 64230 (0.0008) -[2023-10-12 05:55:08,334][78091] Updated weights for policy 0, policy_version 64240 (0.0007) -[2023-10-12 05:55:08,715][78091] Updated weights for policy 0, policy_version 64250 (0.0010) -[2023-10-12 05:55:10,201][77203] Fps is (10 sec: 13106.5, 60 sec: 12561.0, 300 sec: 12773.9). Total num frames: 131268608. Throughput: 0: 1585.8, 1: 1596.9. Samples: 32828144. Policy #0 lag: (min: 25.0, avg: 35.5, max: 57.0) -[2023-10-12 05:55:10,203][77203] Avg episode reward: [(0, '48.270'), (1, '53.880')] -[2023-10-12 05:55:10,214][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000063936_65470464.pth... -[2023-10-12 05:55:10,215][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000064256_65798144.pth... -[2023-10-12 05:55:10,253][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000062752_64258048.pth -[2023-10-12 05:55:10,255][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000062464_63963136.pth -[2023-10-12 05:55:10,962][78123] Updated weights for policy 1, policy_version 63940 (0.0009) -[2023-10-12 05:55:11,326][78123] Updated weights for policy 1, policy_version 63950 (0.0009) -[2023-10-12 05:55:11,693][78123] Updated weights for policy 1, policy_version 63960 (0.0010) -[2023-10-12 05:55:12,989][78091] Updated weights for policy 0, policy_version 64260 (0.0008) -[2023-10-12 05:55:13,353][78091] Updated weights for policy 0, policy_version 64270 (0.0009) -[2023-10-12 05:55:13,725][78091] Updated weights for policy 0, policy_version 64280 (0.0010) -[2023-10-12 05:55:15,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 131334144. Throughput: 0: 1606.6, 1: 1583.8. Samples: 32837824. Policy #0 lag: (min: 25.0, avg: 35.5, max: 57.0) -[2023-10-12 05:55:15,202][77203] Avg episode reward: [(0, '55.220'), (1, '42.500')] -[2023-10-12 05:55:16,116][78123] Updated weights for policy 1, policy_version 63970 (0.0008) -[2023-10-12 05:55:16,483][78123] Updated weights for policy 1, policy_version 63980 (0.0010) -[2023-10-12 05:55:16,837][78123] Updated weights for policy 1, policy_version 63990 (0.0008) -[2023-10-12 05:55:17,212][78123] Updated weights for policy 1, policy_version 64000 (0.0009) -[2023-10-12 05:55:18,054][78091] Updated weights for policy 0, policy_version 64290 (0.0009) -[2023-10-12 05:55:18,415][78091] Updated weights for policy 0, policy_version 64300 (0.0009) -[2023-10-12 05:55:18,790][78091] Updated weights for policy 0, policy_version 64310 (0.0007) -[2023-10-12 05:55:19,157][78091] Updated weights for policy 0, policy_version 64320 (0.0008) -[2023-10-12 05:55:20,201][77203] Fps is (10 sec: 13108.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 131399680. Throughput: 0: 1594.5, 1: 1583.1. Samples: 32856568. Policy #0 lag: (min: 25.0, avg: 35.5, max: 57.0) -[2023-10-12 05:55:20,201][77203] Avg episode reward: [(0, '51.380'), (1, '46.190')] -[2023-10-12 05:55:21,508][78123] Updated weights for policy 1, policy_version 64010 (0.0008) -[2023-10-12 05:55:21,877][78123] Updated weights for policy 1, policy_version 64020 (0.0010) -[2023-10-12 05:55:22,241][78123] Updated weights for policy 1, policy_version 64030 (0.0010) -[2023-10-12 05:55:23,488][78091] Updated weights for policy 0, policy_version 64330 (0.0007) -[2023-10-12 05:55:23,863][78091] Updated weights for policy 0, policy_version 64340 (0.0007) -[2023-10-12 05:55:24,225][78091] Updated weights for policy 0, policy_version 64350 (0.0007) -[2023-10-12 05:55:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 131465216. Throughput: 0: 1587.9, 1: 1582.4. Samples: 32875766. Policy #0 lag: (min: 25.0, avg: 35.5, max: 57.0) -[2023-10-12 05:55:25,202][77203] Avg episode reward: [(0, '62.020'), (1, '43.840')] -[2023-10-12 05:55:26,611][78123] Updated weights for policy 1, policy_version 64040 (0.0008) -[2023-10-12 05:55:26,984][78123] Updated weights for policy 1, policy_version 64050 (0.0008) -[2023-10-12 05:55:27,352][78123] Updated weights for policy 1, policy_version 64060 (0.0007) -[2023-10-12 05:55:28,567][78091] Updated weights for policy 0, policy_version 64360 (0.0008) -[2023-10-12 05:55:28,936][78091] Updated weights for policy 0, policy_version 64370 (0.0009) -[2023-10-12 05:55:29,304][78091] Updated weights for policy 0, policy_version 64380 (0.0009) -[2023-10-12 05:55:30,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 131530752. Throughput: 0: 1602.6, 1: 1580.2. Samples: 32885338. Policy #0 lag: (min: 25.0, avg: 35.5, max: 57.0) -[2023-10-12 05:55:30,202][77203] Avg episode reward: [(0, '56.880'), (1, '51.660')] -[2023-10-12 05:55:31,586][78123] Updated weights for policy 1, policy_version 64070 (0.0009) -[2023-10-12 05:55:31,955][78123] Updated weights for policy 1, policy_version 64080 (0.0008) -[2023-10-12 05:55:32,316][78123] Updated weights for policy 1, policy_version 64090 (0.0007) -[2023-10-12 05:55:33,719][78091] Updated weights for policy 0, policy_version 64390 (0.0008) -[2023-10-12 05:55:34,092][78091] Updated weights for policy 0, policy_version 64400 (0.0010) -[2023-10-12 05:55:34,467][78091] Updated weights for policy 0, policy_version 64410 (0.0008) -[2023-10-12 05:55:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 131596288. Throughput: 0: 1608.0, 1: 1583.6. Samples: 32904568. Policy #0 lag: (min: 25.0, avg: 35.5, max: 57.0) -[2023-10-12 05:55:35,202][77203] Avg episode reward: [(0, '58.480'), (1, '47.080')] -[2023-10-12 05:55:36,783][78123] Updated weights for policy 1, policy_version 64100 (0.0007) -[2023-10-12 05:55:37,153][78123] Updated weights for policy 1, policy_version 64110 (0.0008) -[2023-10-12 05:55:37,515][78123] Updated weights for policy 1, policy_version 64120 (0.0011) -[2023-10-12 05:55:38,693][78091] Updated weights for policy 0, policy_version 64420 (0.0007) -[2023-10-12 05:55:39,063][78091] Updated weights for policy 0, policy_version 64430 (0.0010) -[2023-10-12 05:55:39,436][78091] Updated weights for policy 0, policy_version 64440 (0.0011) -[2023-10-12 05:55:40,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 131661824. Throughput: 0: 1585.7, 1: 1583.7. Samples: 32923064. Policy #0 lag: (min: 25.0, avg: 35.5, max: 57.0) -[2023-10-12 05:55:40,201][77203] Avg episode reward: [(0, '59.950'), (1, '42.120')] -[2023-10-12 05:55:41,961][78123] Updated weights for policy 1, policy_version 64130 (0.0009) -[2023-10-12 05:55:42,326][78123] Updated weights for policy 1, policy_version 64140 (0.0008) -[2023-10-12 05:55:42,704][78123] Updated weights for policy 1, policy_version 64150 (0.0007) -[2023-10-12 05:55:43,064][78123] Updated weights for policy 1, policy_version 64160 (0.0008) -[2023-10-12 05:55:43,607][78091] Updated weights for policy 0, policy_version 64450 (0.0008) -[2023-10-12 05:55:43,968][78091] Updated weights for policy 0, policy_version 64460 (0.0009) -[2023-10-12 05:55:44,341][78091] Updated weights for policy 0, policy_version 64470 (0.0009) -[2023-10-12 05:55:44,709][78091] Updated weights for policy 0, policy_version 64480 (0.0009) -[2023-10-12 05:55:45,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 131727360. Throughput: 0: 1592.0, 1: 1590.9. Samples: 32933044. Policy #0 lag: (min: 25.0, avg: 35.5, max: 57.0) -[2023-10-12 05:55:45,202][77203] Avg episode reward: [(0, '55.680'), (1, '46.890')] -[2023-10-12 05:55:47,452][78123] Updated weights for policy 1, policy_version 64170 (0.0009) -[2023-10-12 05:55:47,820][78123] Updated weights for policy 1, policy_version 64180 (0.0009) -[2023-10-12 05:55:48,182][78123] Updated weights for policy 1, policy_version 64190 (0.0009) -[2023-10-12 05:55:49,193][78091] Updated weights for policy 0, policy_version 64490 (0.0007) -[2023-10-12 05:55:49,566][78091] Updated weights for policy 0, policy_version 64500 (0.0010) -[2023-10-12 05:55:49,943][78091] Updated weights for policy 0, policy_version 64510 (0.0010) -[2023-10-12 05:55:50,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 131792896. Throughput: 0: 1610.1, 1: 1574.3. Samples: 32952058. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-12 05:55:50,202][77203] Avg episode reward: [(0, '51.840'), (1, '50.110')] -[2023-10-12 05:55:52,534][78123] Updated weights for policy 1, policy_version 64200 (0.0009) -[2023-10-12 05:55:52,904][78123] Updated weights for policy 1, policy_version 64210 (0.0009) -[2023-10-12 05:55:53,275][78123] Updated weights for policy 1, policy_version 64220 (0.0008) -[2023-10-12 05:55:54,420][78091] Updated weights for policy 0, policy_version 64520 (0.0011) -[2023-10-12 05:55:54,791][78091] Updated weights for policy 0, policy_version 64530 (0.0010) -[2023-10-12 05:55:55,164][78091] Updated weights for policy 0, policy_version 64540 (0.0009) -[2023-10-12 05:55:55,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 131825664. Throughput: 0: 1594.0, 1: 1574.4. Samples: 32970720. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-12 05:55:55,201][77203] Avg episode reward: [(0, '56.830'), (1, '48.770')] -[2023-10-12 05:55:57,448][78123] Updated weights for policy 1, policy_version 64230 (0.0007) -[2023-10-12 05:55:57,818][78123] Updated weights for policy 1, policy_version 64240 (0.0007) -[2023-10-12 05:55:58,185][78123] Updated weights for policy 1, policy_version 64250 (0.0007) -[2023-10-12 05:55:59,318][78091] Updated weights for policy 0, policy_version 64550 (0.0008) -[2023-10-12 05:55:59,697][78091] Updated weights for policy 0, policy_version 64560 (0.0010) -[2023-10-12 05:56:00,069][78091] Updated weights for policy 0, policy_version 64570 (0.0008) -[2023-10-12 05:56:00,201][77203] Fps is (10 sec: 9830.6, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 131891200. Throughput: 0: 1584.3, 1: 1591.2. Samples: 32980720. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-12 05:56:00,201][77203] Avg episode reward: [(0, '57.690'), (1, '38.990')] -[2023-10-12 05:56:02,443][78123] Updated weights for policy 1, policy_version 64260 (0.0008) -[2023-10-12 05:56:02,816][78123] Updated weights for policy 1, policy_version 64270 (0.0007) -[2023-10-12 05:56:03,183][78123] Updated weights for policy 1, policy_version 64280 (0.0009) -[2023-10-12 05:56:04,394][78091] Updated weights for policy 0, policy_version 64580 (0.0009) -[2023-10-12 05:56:04,774][78091] Updated weights for policy 0, policy_version 64590 (0.0007) -[2023-10-12 05:56:05,131][78091] Updated weights for policy 0, policy_version 64600 (0.0008) -[2023-10-12 05:56:05,201][77203] Fps is (10 sec: 13106.8, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 131956736. Throughput: 0: 1605.4, 1: 1574.3. Samples: 32999658. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-12 05:56:05,202][77203] Avg episode reward: [(0, '55.210'), (1, '42.390')] -[2023-10-12 05:56:07,685][78123] Updated weights for policy 1, policy_version 64290 (0.0010) -[2023-10-12 05:56:08,064][78123] Updated weights for policy 1, policy_version 64300 (0.0010) -[2023-10-12 05:56:08,430][78123] Updated weights for policy 1, policy_version 64310 (0.0008) -[2023-10-12 05:56:08,792][78123] Updated weights for policy 1, policy_version 64320 (0.0010) -[2023-10-12 05:56:09,321][78091] Updated weights for policy 0, policy_version 64610 (0.0010) -[2023-10-12 05:56:09,702][78091] Updated weights for policy 0, policy_version 64620 (0.0009) -[2023-10-12 05:56:10,079][78091] Updated weights for policy 0, policy_version 64630 (0.0010) -[2023-10-12 05:56:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.2, 300 sec: 12774.0). Total num frames: 132022272. Throughput: 0: 1603.9, 1: 1574.0. Samples: 33018772. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-12 05:56:10,201][77203] Avg episode reward: [(0, '57.770'), (1, '46.750')] -[2023-10-12 05:56:10,442][78091] Updated weights for policy 0, policy_version 64640 (0.0007) -[2023-10-12 05:56:13,298][78123] Updated weights for policy 1, policy_version 64330 (0.0011) -[2023-10-12 05:56:13,676][78123] Updated weights for policy 1, policy_version 64340 (0.0010) -[2023-10-12 05:56:14,041][78123] Updated weights for policy 1, policy_version 64350 (0.0008) -[2023-10-12 05:56:14,698][78091] Updated weights for policy 0, policy_version 64650 (0.0009) -[2023-10-12 05:56:15,079][78091] Updated weights for policy 0, policy_version 64660 (0.0009) -[2023-10-12 05:56:15,201][77203] Fps is (10 sec: 13107.6, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 132087808. Throughput: 0: 1592.3, 1: 1603.5. Samples: 33029148. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-12 05:56:15,201][77203] Avg episode reward: [(0, '56.400'), (1, '51.900')] -[2023-10-12 05:56:15,447][78091] Updated weights for policy 0, policy_version 64670 (0.0011) -[2023-10-12 05:56:18,295][78123] Updated weights for policy 1, policy_version 64360 (0.0009) -[2023-10-12 05:56:18,660][78123] Updated weights for policy 1, policy_version 64370 (0.0008) -[2023-10-12 05:56:19,015][78123] Updated weights for policy 1, policy_version 64380 (0.0010) -[2023-10-12 05:56:19,804][78091] Updated weights for policy 0, policy_version 64680 (0.0007) -[2023-10-12 05:56:20,176][78091] Updated weights for policy 0, policy_version 64690 (0.0010) -[2023-10-12 05:56:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 132153344. Throughput: 0: 1597.8, 1: 1587.7. Samples: 33047912. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-12 05:56:20,201][77203] Avg episode reward: [(0, '57.370'), (1, '43.950')] -[2023-10-12 05:56:20,549][78091] Updated weights for policy 0, policy_version 64700 (0.0010) -[2023-10-12 05:56:23,354][78123] Updated weights for policy 1, policy_version 64390 (0.0008) -[2023-10-12 05:56:23,728][78123] Updated weights for policy 1, policy_version 64400 (0.0008) -[2023-10-12 05:56:24,092][78123] Updated weights for policy 1, policy_version 64410 (0.0009) -[2023-10-12 05:56:24,791][78091] Updated weights for policy 0, policy_version 64710 (0.0009) -[2023-10-12 05:56:25,163][78091] Updated weights for policy 0, policy_version 64720 (0.0010) -[2023-10-12 05:56:25,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 132218880. Throughput: 0: 1615.3, 1: 1581.6. Samples: 33066924. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-12 05:56:25,202][77203] Avg episode reward: [(0, '57.340'), (1, '47.400')] -[2023-10-12 05:56:25,526][78091] Updated weights for policy 0, policy_version 64730 (0.0010) -[2023-10-12 05:56:28,481][78123] Updated weights for policy 1, policy_version 64420 (0.0008) -[2023-10-12 05:56:28,850][78123] Updated weights for policy 1, policy_version 64430 (0.0009) -[2023-10-12 05:56:29,203][78123] Updated weights for policy 1, policy_version 64440 (0.0008) -[2023-10-12 05:56:29,959][78091] Updated weights for policy 0, policy_version 64740 (0.0010) -[2023-10-12 05:56:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 132284416. Throughput: 0: 1592.6, 1: 1600.7. Samples: 33076740. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-12 05:56:30,201][77203] Avg episode reward: [(0, '53.590'), (1, '48.470')] -[2023-10-12 05:56:30,316][78091] Updated weights for policy 0, policy_version 64750 (0.0010) -[2023-10-12 05:56:30,685][78091] Updated weights for policy 0, policy_version 64760 (0.0011) -[2023-10-12 05:56:33,588][78123] Updated weights for policy 1, policy_version 64450 (0.0008) -[2023-10-12 05:56:33,958][78123] Updated weights for policy 1, policy_version 64460 (0.0009) -[2023-10-12 05:56:34,323][78123] Updated weights for policy 1, policy_version 64470 (0.0009) -[2023-10-12 05:56:34,689][78123] Updated weights for policy 1, policy_version 64480 (0.0009) -[2023-10-12 05:56:34,872][78091] Updated weights for policy 0, policy_version 64770 (0.0009) -[2023-10-12 05:56:35,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 132349952. Throughput: 0: 1599.4, 1: 1602.4. Samples: 33096142. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-10-12 05:56:35,202][77203] Avg episode reward: [(0, '51.330'), (1, '51.650')] -[2023-10-12 05:56:35,237][78091] Updated weights for policy 0, policy_version 64780 (0.0008) -[2023-10-12 05:56:35,606][78091] Updated weights for policy 0, policy_version 64790 (0.0008) -[2023-10-12 05:56:35,976][78091] Updated weights for policy 0, policy_version 64800 (0.0009) -[2023-10-12 05:56:38,985][78123] Updated weights for policy 1, policy_version 64490 (0.0007) -[2023-10-12 05:56:39,361][78123] Updated weights for policy 1, policy_version 64500 (0.0007) -[2023-10-12 05:56:39,733][78123] Updated weights for policy 1, policy_version 64510 (0.0008) -[2023-10-12 05:56:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 132415488. Throughput: 0: 1618.1, 1: 1585.0. Samples: 33114862. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-10-12 05:56:40,201][77203] Avg episode reward: [(0, '53.780'), (1, '50.220')] -[2023-10-12 05:56:40,378][78091] Updated weights for policy 0, policy_version 64810 (0.0008) -[2023-10-12 05:56:40,747][78091] Updated weights for policy 0, policy_version 64820 (0.0009) -[2023-10-12 05:56:41,121][78091] Updated weights for policy 0, policy_version 64830 (0.0009) -[2023-10-12 05:56:44,003][78123] Updated weights for policy 1, policy_version 64520 (0.0008) -[2023-10-12 05:56:44,371][78123] Updated weights for policy 1, policy_version 64530 (0.0010) -[2023-10-12 05:56:44,747][78123] Updated weights for policy 1, policy_version 64540 (0.0007) -[2023-10-12 05:56:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 132481024. Throughput: 0: 1598.2, 1: 1591.9. Samples: 33124274. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-10-12 05:56:45,202][77203] Avg episode reward: [(0, '53.080'), (1, '48.620')] -[2023-10-12 05:56:45,467][78091] Updated weights for policy 0, policy_version 64840 (0.0009) -[2023-10-12 05:56:45,841][78091] Updated weights for policy 0, policy_version 64850 (0.0010) -[2023-10-12 05:56:46,207][78091] Updated weights for policy 0, policy_version 64860 (0.0009) -[2023-10-12 05:56:49,237][78123] Updated weights for policy 1, policy_version 64550 (0.0008) -[2023-10-12 05:56:49,610][78123] Updated weights for policy 1, policy_version 64560 (0.0008) -[2023-10-12 05:56:49,978][78123] Updated weights for policy 1, policy_version 64570 (0.0009) -[2023-10-12 05:56:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 132546560. Throughput: 0: 1594.0, 1: 1604.4. Samples: 33143586. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-10-12 05:56:50,201][77203] Avg episode reward: [(0, '51.790'), (1, '45.090')] -[2023-10-12 05:56:50,550][78091] Updated weights for policy 0, policy_version 64870 (0.0007) -[2023-10-12 05:56:50,916][78091] Updated weights for policy 0, policy_version 64880 (0.0008) -[2023-10-12 05:56:51,282][78091] Updated weights for policy 0, policy_version 64890 (0.0008) -[2023-10-12 05:56:54,420][78123] Updated weights for policy 1, policy_version 64580 (0.0009) -[2023-10-12 05:56:54,791][78123] Updated weights for policy 1, policy_version 64590 (0.0008) -[2023-10-12 05:56:55,156][78123] Updated weights for policy 1, policy_version 64600 (0.0010) -[2023-10-12 05:56:55,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 132579328. Throughput: 0: 1602.6, 1: 1592.6. Samples: 33162556. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-10-12 05:56:55,202][77203] Avg episode reward: [(0, '50.450'), (1, '48.350')] -[2023-10-12 05:56:55,656][78091] Updated weights for policy 0, policy_version 64900 (0.0007) -[2023-10-12 05:56:56,028][78091] Updated weights for policy 0, policy_version 64910 (0.0008) -[2023-10-12 05:56:56,395][78091] Updated weights for policy 0, policy_version 64920 (0.0007) -[2023-10-12 05:56:59,421][78123] Updated weights for policy 1, policy_version 64610 (0.0008) -[2023-10-12 05:56:59,797][78123] Updated weights for policy 1, policy_version 64620 (0.0007) -[2023-10-12 05:57:00,170][78123] Updated weights for policy 1, policy_version 64630 (0.0007) -[2023-10-12 05:57:00,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 132644864. Throughput: 0: 1589.5, 1: 1574.9. Samples: 33171546. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-10-12 05:57:00,201][77203] Avg episode reward: [(0, '51.900'), (1, '47.090')] -[2023-10-12 05:57:00,536][78123] Updated weights for policy 1, policy_version 64640 (0.0007) -[2023-10-12 05:57:00,701][78091] Updated weights for policy 0, policy_version 64930 (0.0009) -[2023-10-12 05:57:01,067][78091] Updated weights for policy 0, policy_version 64940 (0.0007) -[2023-10-12 05:57:01,445][78091] Updated weights for policy 0, policy_version 64950 (0.0010) -[2023-10-12 05:57:01,820][78091] Updated weights for policy 0, policy_version 64960 (0.0007) -[2023-10-12 05:57:04,909][78123] Updated weights for policy 1, policy_version 64650 (0.0007) -[2023-10-12 05:57:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 132710400. Throughput: 0: 1588.4, 1: 1587.8. Samples: 33190842. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-10-12 05:57:05,201][77203] Avg episode reward: [(0, '57.710'), (1, '46.150')] -[2023-10-12 05:57:05,281][78123] Updated weights for policy 1, policy_version 64660 (0.0008) -[2023-10-12 05:57:05,649][78123] Updated weights for policy 1, policy_version 64670 (0.0007) -[2023-10-12 05:57:06,166][78091] Updated weights for policy 0, policy_version 64970 (0.0008) -[2023-10-12 05:57:06,542][78091] Updated weights for policy 0, policy_version 64980 (0.0007) -[2023-10-12 05:57:06,922][78091] Updated weights for policy 0, policy_version 64990 (0.0007) -[2023-10-12 05:57:09,954][78123] Updated weights for policy 1, policy_version 64680 (0.0009) -[2023-10-12 05:57:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 132775936. Throughput: 0: 1588.2, 1: 1596.1. Samples: 33210218. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-10-12 05:57:10,201][77203] Avg episode reward: [(0, '56.680'), (1, '47.130')] -[2023-10-12 05:57:10,210][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000064992_66551808.pth... -[2023-10-12 05:57:10,243][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000063520_65044480.pth -[2023-10-12 05:57:10,323][78123] Updated weights for policy 1, policy_version 64690 (0.0009) -[2023-10-12 05:57:10,690][78123] Updated weights for policy 1, policy_version 64700 (0.0008) -[2023-10-12 05:57:10,834][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000064704_66256896.pth... -[2023-10-12 05:57:10,864][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000063200_64716800.pth -[2023-10-12 05:57:11,244][78091] Updated weights for policy 0, policy_version 65000 (0.0009) -[2023-10-12 05:57:11,615][78091] Updated weights for policy 0, policy_version 65010 (0.0007) -[2023-10-12 05:57:11,998][78091] Updated weights for policy 0, policy_version 65020 (0.0008) -[2023-10-12 05:57:14,933][78123] Updated weights for policy 1, policy_version 64710 (0.0007) -[2023-10-12 05:57:15,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 132841472. Throughput: 0: 1586.7, 1: 1573.5. Samples: 33218946. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:57:15,201][77203] Avg episode reward: [(0, '57.320'), (1, '47.650')] -[2023-10-12 05:57:15,308][78123] Updated weights for policy 1, policy_version 64720 (0.0007) -[2023-10-12 05:57:15,668][78123] Updated weights for policy 1, policy_version 64730 (0.0009) -[2023-10-12 05:57:16,179][78091] Updated weights for policy 0, policy_version 65030 (0.0007) -[2023-10-12 05:57:16,544][78091] Updated weights for policy 0, policy_version 65040 (0.0008) -[2023-10-12 05:57:16,907][78091] Updated weights for policy 0, policy_version 65050 (0.0007) -[2023-10-12 05:57:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 132907008. Throughput: 0: 1588.3, 1: 1575.3. Samples: 33238504. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:57:20,201][77203] Avg episode reward: [(0, '51.660'), (1, '51.670')] -[2023-10-12 05:57:20,273][78123] Updated weights for policy 1, policy_version 64740 (0.0008) -[2023-10-12 05:57:20,643][78123] Updated weights for policy 1, policy_version 64750 (0.0007) -[2023-10-12 05:57:21,006][78123] Updated weights for policy 1, policy_version 64760 (0.0008) -[2023-10-12 05:57:21,171][78091] Updated weights for policy 0, policy_version 65060 (0.0009) -[2023-10-12 05:57:21,533][78091] Updated weights for policy 0, policy_version 65070 (0.0008) -[2023-10-12 05:57:21,911][78091] Updated weights for policy 0, policy_version 65080 (0.0007) -[2023-10-12 05:57:25,201][77203] Fps is (10 sec: 13106.8, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 132972544. Throughput: 0: 1588.9, 1: 1588.4. Samples: 33257842. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:57:25,202][77203] Avg episode reward: [(0, '63.070'), (1, '44.030')] -[2023-10-12 05:57:25,537][78123] Updated weights for policy 1, policy_version 64770 (0.0009) -[2023-10-12 05:57:25,910][78123] Updated weights for policy 1, policy_version 64780 (0.0009) -[2023-10-12 05:57:26,177][78091] Updated weights for policy 0, policy_version 65090 (0.0007) -[2023-10-12 05:57:26,273][78123] Updated weights for policy 1, policy_version 64790 (0.0007) -[2023-10-12 05:57:26,558][78091] Updated weights for policy 0, policy_version 65100 (0.0008) -[2023-10-12 05:57:26,630][78123] Updated weights for policy 1, policy_version 64800 (0.0009) -[2023-10-12 05:57:26,922][78091] Updated weights for policy 0, policy_version 65110 (0.0009) -[2023-10-12 05:57:27,299][78091] Updated weights for policy 0, policy_version 65120 (0.0007) -[2023-10-12 05:57:30,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 133038080. Throughput: 0: 1588.3, 1: 1565.2. Samples: 33266182. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:57:30,202][77203] Avg episode reward: [(0, '55.060'), (1, '45.160')] -[2023-10-12 05:57:31,149][78123] Updated weights for policy 1, policy_version 64810 (0.0008) -[2023-10-12 05:57:31,512][78123] Updated weights for policy 1, policy_version 64820 (0.0008) -[2023-10-12 05:57:31,741][78091] Updated weights for policy 0, policy_version 65130 (0.0007) -[2023-10-12 05:57:31,875][78123] Updated weights for policy 1, policy_version 64830 (0.0007) -[2023-10-12 05:57:32,117][78091] Updated weights for policy 0, policy_version 65140 (0.0007) -[2023-10-12 05:57:32,491][78091] Updated weights for policy 0, policy_version 65150 (0.0009) -[2023-10-12 05:57:35,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 133103616. Throughput: 0: 1588.1, 1: 1574.0. Samples: 33285882. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:57:35,202][77203] Avg episode reward: [(0, '54.070'), (1, '48.730')] -[2023-10-12 05:57:36,145][78123] Updated weights for policy 1, policy_version 64840 (0.0008) -[2023-10-12 05:57:36,514][78123] Updated weights for policy 1, policy_version 64850 (0.0007) -[2023-10-12 05:57:36,669][78091] Updated weights for policy 0, policy_version 65160 (0.0008) -[2023-10-12 05:57:36,876][78123] Updated weights for policy 1, policy_version 64860 (0.0007) -[2023-10-12 05:57:37,042][78091] Updated weights for policy 0, policy_version 65170 (0.0007) -[2023-10-12 05:57:37,410][78091] Updated weights for policy 0, policy_version 65180 (0.0007) -[2023-10-12 05:57:40,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 133169152. Throughput: 0: 1589.3, 1: 1583.1. Samples: 33305314. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:57:40,201][77203] Avg episode reward: [(0, '50.400'), (1, '56.100')] -[2023-10-12 05:57:41,273][78123] Updated weights for policy 1, policy_version 64870 (0.0007) -[2023-10-12 05:57:41,628][78091] Updated weights for policy 0, policy_version 65190 (0.0010) -[2023-10-12 05:57:41,637][78123] Updated weights for policy 1, policy_version 64880 (0.0007) -[2023-10-12 05:57:42,000][78091] Updated weights for policy 0, policy_version 65200 (0.0009) -[2023-10-12 05:57:42,002][78123] Updated weights for policy 1, policy_version 64890 (0.0007) -[2023-10-12 05:57:42,363][78091] Updated weights for policy 0, policy_version 65210 (0.0009) -[2023-10-12 05:57:45,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 133234688. Throughput: 0: 1590.4, 1: 1571.8. Samples: 33313844. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:57:45,201][77203] Avg episode reward: [(0, '50.300'), (1, '45.570')] -[2023-10-12 05:57:46,326][78123] Updated weights for policy 1, policy_version 64900 (0.0008) -[2023-10-12 05:57:46,583][78091] Updated weights for policy 0, policy_version 65220 (0.0009) -[2023-10-12 05:57:46,696][78123] Updated weights for policy 1, policy_version 64910 (0.0011) -[2023-10-12 05:57:46,947][78091] Updated weights for policy 0, policy_version 65230 (0.0009) -[2023-10-12 05:57:47,060][78123] Updated weights for policy 1, policy_version 64920 (0.0009) -[2023-10-12 05:57:47,320][78091] Updated weights for policy 0, policy_version 65240 (0.0008) -[2023-10-12 05:57:50,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 133300224. Throughput: 0: 1592.8, 1: 1573.8. Samples: 33333338. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:57:50,201][77203] Avg episode reward: [(0, '52.720'), (1, '41.720')] -[2023-10-12 05:57:51,135][78123] Updated weights for policy 1, policy_version 64930 (0.0008) -[2023-10-12 05:57:51,526][78123] Updated weights for policy 1, policy_version 64940 (0.0009) -[2023-10-12 05:57:51,892][78123] Updated weights for policy 1, policy_version 64950 (0.0009) -[2023-10-12 05:57:51,920][78091] Updated weights for policy 0, policy_version 65250 (0.0008) -[2023-10-12 05:57:52,251][78123] Updated weights for policy 1, policy_version 64960 (0.0009) -[2023-10-12 05:57:52,291][78091] Updated weights for policy 0, policy_version 65260 (0.0007) -[2023-10-12 05:57:52,672][78091] Updated weights for policy 0, policy_version 65270 (0.0007) -[2023-10-12 05:57:53,038][78091] Updated weights for policy 0, policy_version 65280 (0.0007) -[2023-10-12 05:57:55,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 133365760. Throughput: 0: 1595.1, 1: 1577.4. Samples: 33352980. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:57:55,202][77203] Avg episode reward: [(0, '56.260'), (1, '49.310')] -[2023-10-12 05:57:56,574][78123] Updated weights for policy 1, policy_version 64970 (0.0007) -[2023-10-12 05:57:56,943][78123] Updated weights for policy 1, policy_version 64980 (0.0010) -[2023-10-12 05:57:57,297][78091] Updated weights for policy 0, policy_version 65290 (0.0007) -[2023-10-12 05:57:57,307][78123] Updated weights for policy 1, policy_version 64990 (0.0009) -[2023-10-12 05:57:57,659][78091] Updated weights for policy 0, policy_version 65300 (0.0007) -[2023-10-12 05:57:58,031][78091] Updated weights for policy 0, policy_version 65310 (0.0007) -[2023-10-12 05:58:00,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 133431296. Throughput: 0: 1603.4, 1: 1573.6. Samples: 33361910. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-12 05:58:00,202][77203] Avg episode reward: [(0, '54.710'), (1, '48.720')] -[2023-10-12 05:58:01,617][78123] Updated weights for policy 1, policy_version 65000 (0.0007) -[2023-10-12 05:58:01,989][78123] Updated weights for policy 1, policy_version 65010 (0.0007) -[2023-10-12 05:58:02,347][78123] Updated weights for policy 1, policy_version 65020 (0.0008) -[2023-10-12 05:58:02,403][78091] Updated weights for policy 0, policy_version 65320 (0.0009) -[2023-10-12 05:58:02,771][78091] Updated weights for policy 0, policy_version 65330 (0.0010) -[2023-10-12 05:58:03,153][78091] Updated weights for policy 0, policy_version 65340 (0.0007) -[2023-10-12 05:58:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 133496832. Throughput: 0: 1587.2, 1: 1582.0. Samples: 33381120. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-12 05:58:05,202][77203] Avg episode reward: [(0, '54.680'), (1, '58.140')] -[2023-10-12 05:58:06,537][78123] Updated weights for policy 1, policy_version 65030 (0.0009) -[2023-10-12 05:58:06,911][78123] Updated weights for policy 1, policy_version 65040 (0.0009) -[2023-10-12 05:58:07,281][78123] Updated weights for policy 1, policy_version 65050 (0.0008) -[2023-10-12 05:58:07,553][78091] Updated weights for policy 0, policy_version 65350 (0.0007) -[2023-10-12 05:58:07,932][78091] Updated weights for policy 0, policy_version 65360 (0.0009) -[2023-10-12 05:58:08,299][78091] Updated weights for policy 0, policy_version 65370 (0.0008) -[2023-10-12 05:58:10,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 133562368. Throughput: 0: 1590.5, 1: 1588.1. Samples: 33400876. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-12 05:58:10,201][77203] Avg episode reward: [(0, '59.790'), (1, '45.770')] -[2023-10-12 05:58:11,549][78123] Updated weights for policy 1, policy_version 65060 (0.0007) -[2023-10-12 05:58:11,918][78123] Updated weights for policy 1, policy_version 65070 (0.0007) -[2023-10-12 05:58:12,283][78123] Updated weights for policy 1, policy_version 65080 (0.0008) -[2023-10-12 05:58:12,596][78091] Updated weights for policy 0, policy_version 65380 (0.0007) -[2023-10-12 05:58:12,985][78091] Updated weights for policy 0, policy_version 65390 (0.0009) -[2023-10-12 05:58:13,371][78091] Updated weights for policy 0, policy_version 65400 (0.0008) -[2023-10-12 05:58:15,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 133627904. Throughput: 0: 1611.8, 1: 1591.7. Samples: 33410338. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-12 05:58:15,202][77203] Avg episode reward: [(0, '54.250'), (1, '50.250')] -[2023-10-12 05:58:16,590][78123] Updated weights for policy 1, policy_version 65090 (0.0009) -[2023-10-12 05:58:16,957][78123] Updated weights for policy 1, policy_version 65100 (0.0008) -[2023-10-12 05:58:17,323][78123] Updated weights for policy 1, policy_version 65110 (0.0008) -[2023-10-12 05:58:17,642][78091] Updated weights for policy 0, policy_version 65410 (0.0008) -[2023-10-12 05:58:17,691][78123] Updated weights for policy 1, policy_version 65120 (0.0008) -[2023-10-12 05:58:18,016][78091] Updated weights for policy 0, policy_version 65420 (0.0008) -[2023-10-12 05:58:18,385][78091] Updated weights for policy 0, policy_version 65430 (0.0008) -[2023-10-12 05:58:18,761][78091] Updated weights for policy 0, policy_version 65440 (0.0010) -[2023-10-12 05:58:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 133693440. Throughput: 0: 1592.3, 1: 1589.2. Samples: 33429048. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-12 05:58:20,201][77203] Avg episode reward: [(0, '56.500'), (1, '51.770')] -[2023-10-12 05:58:22,201][78123] Updated weights for policy 1, policy_version 65130 (0.0009) -[2023-10-12 05:58:22,560][78123] Updated weights for policy 1, policy_version 65140 (0.0011) -[2023-10-12 05:58:22,921][78123] Updated weights for policy 1, policy_version 65150 (0.0008) -[2023-10-12 05:58:23,181][78091] Updated weights for policy 0, policy_version 65450 (0.0010) -[2023-10-12 05:58:23,541][78091] Updated weights for policy 0, policy_version 65460 (0.0007) -[2023-10-12 05:58:23,916][78091] Updated weights for policy 0, policy_version 65470 (0.0008) -[2023-10-12 05:58:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 133758976. Throughput: 0: 1587.2, 1: 1593.0. Samples: 33448420. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-12 05:58:25,201][77203] Avg episode reward: [(0, '56.130'), (1, '47.120')] -[2023-10-12 05:58:27,065][78123] Updated weights for policy 1, policy_version 65160 (0.0010) -[2023-10-12 05:58:27,435][78123] Updated weights for policy 1, policy_version 65170 (0.0008) -[2023-10-12 05:58:27,789][78123] Updated weights for policy 1, policy_version 65180 (0.0008) -[2023-10-12 05:58:28,322][78091] Updated weights for policy 0, policy_version 65480 (0.0009) -[2023-10-12 05:58:28,696][78091] Updated weights for policy 0, policy_version 65490 (0.0009) -[2023-10-12 05:58:29,063][78091] Updated weights for policy 0, policy_version 65500 (0.0009) -[2023-10-12 05:58:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 133824512. Throughput: 0: 1613.7, 1: 1601.6. Samples: 33458530. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-12 05:58:30,201][77203] Avg episode reward: [(0, '56.000'), (1, '45.460')] -[2023-10-12 05:58:32,127][78123] Updated weights for policy 1, policy_version 65190 (0.0009) -[2023-10-12 05:58:32,492][78123] Updated weights for policy 1, policy_version 65200 (0.0007) -[2023-10-12 05:58:32,852][78123] Updated weights for policy 1, policy_version 65210 (0.0009) -[2023-10-12 05:58:33,445][78091] Updated weights for policy 0, policy_version 65510 (0.0010) -[2023-10-12 05:58:33,811][78091] Updated weights for policy 0, policy_version 65520 (0.0007) -[2023-10-12 05:58:34,187][78091] Updated weights for policy 0, policy_version 65530 (0.0008) -[2023-10-12 05:58:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 133890048. Throughput: 0: 1600.1, 1: 1597.8. Samples: 33477246. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-12 05:58:35,202][77203] Avg episode reward: [(0, '56.460'), (1, '47.980')] -[2023-10-12 05:58:37,330][78123] Updated weights for policy 1, policy_version 65220 (0.0011) -[2023-10-12 05:58:37,714][78123] Updated weights for policy 1, policy_version 65230 (0.0008) -[2023-10-12 05:58:38,082][78123] Updated weights for policy 1, policy_version 65240 (0.0007) -[2023-10-12 05:58:38,289][78091] Updated weights for policy 0, policy_version 65540 (0.0008) -[2023-10-12 05:58:38,661][78091] Updated weights for policy 0, policy_version 65550 (0.0009) -[2023-10-12 05:58:39,024][78091] Updated weights for policy 0, policy_version 65560 (0.0010) -[2023-10-12 05:58:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 133955584. Throughput: 0: 1590.5, 1: 1591.8. Samples: 33496182. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:58:40,201][77203] Avg episode reward: [(0, '62.580'), (1, '43.380')] -[2023-10-12 05:58:42,368][78123] Updated weights for policy 1, policy_version 65250 (0.0007) -[2023-10-12 05:58:42,722][78123] Updated weights for policy 1, policy_version 65260 (0.0010) -[2023-10-12 05:58:43,087][78123] Updated weights for policy 1, policy_version 65270 (0.0010) -[2023-10-12 05:58:43,322][78091] Updated weights for policy 0, policy_version 65570 (0.0009) -[2023-10-12 05:58:43,452][78123] Updated weights for policy 1, policy_version 65280 (0.0009) -[2023-10-12 05:58:43,691][78091] Updated weights for policy 0, policy_version 65580 (0.0008) -[2023-10-12 05:58:44,058][78091] Updated weights for policy 0, policy_version 65590 (0.0010) -[2023-10-12 05:58:44,434][78091] Updated weights for policy 0, policy_version 65600 (0.0008) -[2023-10-12 05:58:45,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 134021120. Throughput: 0: 1610.5, 1: 1611.2. Samples: 33506888. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:58:45,202][77203] Avg episode reward: [(0, '60.620'), (1, '48.210')] -[2023-10-12 05:58:47,923][78123] Updated weights for policy 1, policy_version 65290 (0.0008) -[2023-10-12 05:58:48,293][78123] Updated weights for policy 1, policy_version 65300 (0.0008) -[2023-10-12 05:58:48,663][78123] Updated weights for policy 1, policy_version 65310 (0.0007) -[2023-10-12 05:58:48,874][78091] Updated weights for policy 0, policy_version 65610 (0.0008) -[2023-10-12 05:58:49,253][78091] Updated weights for policy 0, policy_version 65620 (0.0010) -[2023-10-12 05:58:49,615][78091] Updated weights for policy 0, policy_version 65630 (0.0010) -[2023-10-12 05:58:50,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 134086656. Throughput: 0: 1611.2, 1: 1590.0. Samples: 33525176. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:58:50,202][77203] Avg episode reward: [(0, '58.520'), (1, '43.680')] -[2023-10-12 05:58:52,937][78123] Updated weights for policy 1, policy_version 65320 (0.0010) -[2023-10-12 05:58:53,292][78123] Updated weights for policy 1, policy_version 65330 (0.0007) -[2023-10-12 05:58:53,660][78123] Updated weights for policy 1, policy_version 65340 (0.0007) -[2023-10-12 05:58:53,819][78091] Updated weights for policy 0, policy_version 65640 (0.0008) -[2023-10-12 05:58:54,179][78091] Updated weights for policy 0, policy_version 65650 (0.0008) -[2023-10-12 05:58:54,562][78091] Updated weights for policy 0, policy_version 65660 (0.0007) -[2023-10-12 05:58:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 134152192. Throughput: 0: 1591.4, 1: 1586.0. Samples: 33543860. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:58:55,202][77203] Avg episode reward: [(0, '54.540'), (1, '49.060')] -[2023-10-12 05:58:58,021][78123] Updated weights for policy 1, policy_version 65350 (0.0008) -[2023-10-12 05:58:58,382][78123] Updated weights for policy 1, policy_version 65360 (0.0008) -[2023-10-12 05:58:58,757][78123] Updated weights for policy 1, policy_version 65370 (0.0007) -[2023-10-12 05:58:58,857][78091] Updated weights for policy 0, policy_version 65670 (0.0010) -[2023-10-12 05:58:59,229][78091] Updated weights for policy 0, policy_version 65680 (0.0009) -[2023-10-12 05:58:59,604][78091] Updated weights for policy 0, policy_version 65690 (0.0009) -[2023-10-12 05:59:00,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 134217728. Throughput: 0: 1598.8, 1: 1608.9. Samples: 33554688. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:59:00,202][77203] Avg episode reward: [(0, '58.830'), (1, '47.680')] -[2023-10-12 05:59:03,258][78123] Updated weights for policy 1, policy_version 65380 (0.0009) -[2023-10-12 05:59:03,615][78123] Updated weights for policy 1, policy_version 65390 (0.0010) -[2023-10-12 05:59:03,827][78091] Updated weights for policy 0, policy_version 65700 (0.0009) -[2023-10-12 05:59:03,982][78123] Updated weights for policy 1, policy_version 65400 (0.0007) -[2023-10-12 05:59:04,194][78091] Updated weights for policy 0, policy_version 65710 (0.0009) -[2023-10-12 05:59:04,560][78091] Updated weights for policy 0, policy_version 65720 (0.0008) -[2023-10-12 05:59:05,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 134283264. Throughput: 0: 1612.3, 1: 1590.7. Samples: 33573180. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:59:05,202][77203] Avg episode reward: [(0, '58.850'), (1, '48.890')] -[2023-10-12 05:59:08,254][78123] Updated weights for policy 1, policy_version 65410 (0.0008) -[2023-10-12 05:59:08,621][78123] Updated weights for policy 1, policy_version 65420 (0.0008) -[2023-10-12 05:59:08,917][78091] Updated weights for policy 0, policy_version 65730 (0.0009) -[2023-10-12 05:59:08,993][78123] Updated weights for policy 1, policy_version 65430 (0.0008) -[2023-10-12 05:59:09,281][78091] Updated weights for policy 0, policy_version 65740 (0.0009) -[2023-10-12 05:59:09,349][78123] Updated weights for policy 1, policy_version 65440 (0.0009) -[2023-10-12 05:59:09,661][78091] Updated weights for policy 0, policy_version 65750 (0.0008) -[2023-10-12 05:59:10,027][78091] Updated weights for policy 0, policy_version 65760 (0.0009) -[2023-10-12 05:59:10,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 134348800. Throughput: 0: 1596.6, 1: 1579.1. Samples: 33591326. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:59:10,201][77203] Avg episode reward: [(0, '54.040'), (1, '48.850')] -[2023-10-12 05:59:10,209][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000065440_67010560.pth... -[2023-10-12 05:59:10,209][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000065760_67338240.pth... -[2023-10-12 05:59:10,238][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000063936_65470464.pth -[2023-10-12 05:59:10,246][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000064256_65798144.pth -[2023-10-12 05:59:13,700][78123] Updated weights for policy 1, policy_version 65450 (0.0007) -[2023-10-12 05:59:14,067][78123] Updated weights for policy 1, policy_version 65460 (0.0009) -[2023-10-12 05:59:14,387][78091] Updated weights for policy 0, policy_version 65770 (0.0007) -[2023-10-12 05:59:14,433][78123] Updated weights for policy 1, policy_version 65470 (0.0008) -[2023-10-12 05:59:14,744][78091] Updated weights for policy 0, policy_version 65780 (0.0011) -[2023-10-12 05:59:15,114][78091] Updated weights for policy 0, policy_version 65790 (0.0009) -[2023-10-12 05:59:15,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 134414336. Throughput: 0: 1589.4, 1: 1598.0. Samples: 33601964. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:59:15,201][77203] Avg episode reward: [(0, '55.570'), (1, '57.520')] -[2023-10-12 05:59:18,850][78123] Updated weights for policy 1, policy_version 65480 (0.0008) -[2023-10-12 05:59:19,215][78123] Updated weights for policy 1, policy_version 65490 (0.0008) -[2023-10-12 05:59:19,414][78091] Updated weights for policy 0, policy_version 65800 (0.0009) -[2023-10-12 05:59:19,581][78123] Updated weights for policy 1, policy_version 65500 (0.0008) -[2023-10-12 05:59:19,782][78091] Updated weights for policy 0, policy_version 65810 (0.0009) -[2023-10-12 05:59:20,151][78091] Updated weights for policy 0, policy_version 65820 (0.0009) -[2023-10-12 05:59:20,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 134447104. Throughput: 0: 1601.6, 1: 1597.2. Samples: 33621194. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:59:20,201][77203] Avg episode reward: [(0, '55.570'), (1, '49.910')] -[2023-10-12 05:59:23,963][78123] Updated weights for policy 1, policy_version 65510 (0.0008) -[2023-10-12 05:59:24,345][78123] Updated weights for policy 1, policy_version 65520 (0.0010) -[2023-10-12 05:59:24,557][78091] Updated weights for policy 0, policy_version 65830 (0.0007) -[2023-10-12 05:59:24,708][78123] Updated weights for policy 1, policy_version 65530 (0.0009) -[2023-10-12 05:59:24,922][78091] Updated weights for policy 0, policy_version 65840 (0.0009) -[2023-10-12 05:59:25,201][77203] Fps is (10 sec: 9830.2, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 134512640. Throughput: 0: 1597.0, 1: 1582.5. Samples: 33639258. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 05:59:25,202][77203] Avg episode reward: [(0, '58.350'), (1, '41.600')] -[2023-10-12 05:59:25,300][78091] Updated weights for policy 0, policy_version 65850 (0.0010) -[2023-10-12 05:59:29,080][78123] Updated weights for policy 1, policy_version 65540 (0.0008) -[2023-10-12 05:59:29,452][78123] Updated weights for policy 1, policy_version 65550 (0.0009) -[2023-10-12 05:59:29,667][78091] Updated weights for policy 0, policy_version 65860 (0.0009) -[2023-10-12 05:59:29,817][78123] Updated weights for policy 1, policy_version 65560 (0.0009) -[2023-10-12 05:59:30,037][78091] Updated weights for policy 0, policy_version 65870 (0.0007) -[2023-10-12 05:59:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 134578176. Throughput: 0: 1581.3, 1: 1583.5. Samples: 33649306. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 05:59:30,201][77203] Avg episode reward: [(0, '60.260'), (1, '41.600')] -[2023-10-12 05:59:30,401][78091] Updated weights for policy 0, policy_version 65880 (0.0009) -[2023-10-12 05:59:34,129][78123] Updated weights for policy 1, policy_version 65570 (0.0010) -[2023-10-12 05:59:34,510][78123] Updated weights for policy 1, policy_version 65580 (0.0011) -[2023-10-12 05:59:34,725][78091] Updated weights for policy 0, policy_version 65890 (0.0009) -[2023-10-12 05:59:34,864][78123] Updated weights for policy 1, policy_version 65590 (0.0009) -[2023-10-12 05:59:35,088][78091] Updated weights for policy 0, policy_version 65900 (0.0009) -[2023-10-12 05:59:35,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 134610944. Throughput: 0: 1586.5, 1: 1601.6. Samples: 33668642. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 05:59:35,202][77203] Avg episode reward: [(0, '60.260'), (1, '52.500')] -[2023-10-12 05:59:35,236][78123] Updated weights for policy 1, policy_version 65600 (0.0008) -[2023-10-12 05:59:35,477][78091] Updated weights for policy 0, policy_version 65910 (0.0009) -[2023-10-12 05:59:35,844][78091] Updated weights for policy 0, policy_version 65920 (0.0008) -[2023-10-12 05:59:39,582][78123] Updated weights for policy 1, policy_version 65610 (0.0009) -[2023-10-12 05:59:39,946][78123] Updated weights for policy 1, policy_version 65620 (0.0009) -[2023-10-12 05:59:40,127][78091] Updated weights for policy 0, policy_version 65930 (0.0007) -[2023-10-12 05:59:40,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 134676480. Throughput: 0: 1603.9, 1: 1590.6. Samples: 33687610. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 05:59:40,201][77203] Avg episode reward: [(0, '56.080'), (1, '52.640')] -[2023-10-12 05:59:40,310][78123] Updated weights for policy 1, policy_version 65630 (0.0010) -[2023-10-12 05:59:40,495][78091] Updated weights for policy 0, policy_version 65940 (0.0010) -[2023-10-12 05:59:40,874][78091] Updated weights for policy 0, policy_version 65950 (0.0008) -[2023-10-12 05:59:44,785][78123] Updated weights for policy 1, policy_version 65640 (0.0007) -[2023-10-12 05:59:45,153][78123] Updated weights for policy 1, policy_version 65650 (0.0008) -[2023-10-12 05:59:45,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 134742016. Throughput: 0: 1576.9, 1: 1580.2. Samples: 33696760. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 05:59:45,201][77203] Avg episode reward: [(0, '58.420'), (1, '55.100')] -[2023-10-12 05:59:45,422][78091] Updated weights for policy 0, policy_version 65960 (0.0009) -[2023-10-12 05:59:45,532][78123] Updated weights for policy 1, policy_version 65660 (0.0010) -[2023-10-12 05:59:45,794][78091] Updated weights for policy 0, policy_version 65970 (0.0009) -[2023-10-12 05:59:46,172][78091] Updated weights for policy 0, policy_version 65980 (0.0009) -[2023-10-12 05:59:49,893][78123] Updated weights for policy 1, policy_version 65670 (0.0010) -[2023-10-12 05:59:50,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 134807552. Throughput: 0: 1578.5, 1: 1592.5. Samples: 33715874. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 05:59:50,202][77203] Avg episode reward: [(0, '59.720'), (1, '45.780')] -[2023-10-12 05:59:50,269][78123] Updated weights for policy 1, policy_version 65680 (0.0010) -[2023-10-12 05:59:50,580][78091] Updated weights for policy 0, policy_version 65990 (0.0009) -[2023-10-12 05:59:50,638][78123] Updated weights for policy 1, policy_version 65690 (0.0008) -[2023-10-12 05:59:50,955][78091] Updated weights for policy 0, policy_version 66000 (0.0009) -[2023-10-12 05:59:51,324][78091] Updated weights for policy 0, policy_version 66010 (0.0008) -[2023-10-12 05:59:55,080][78123] Updated weights for policy 1, policy_version 65700 (0.0007) -[2023-10-12 05:59:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 134873088. Throughput: 0: 1599.4, 1: 1601.7. Samples: 33735378. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 05:59:55,201][77203] Avg episode reward: [(0, '54.520'), (1, '48.930')] -[2023-10-12 05:59:55,448][78123] Updated weights for policy 1, policy_version 65710 (0.0007) -[2023-10-12 05:59:55,702][78091] Updated weights for policy 0, policy_version 66020 (0.0008) -[2023-10-12 05:59:55,809][78123] Updated weights for policy 1, policy_version 65720 (0.0008) -[2023-10-12 05:59:56,075][78091] Updated weights for policy 0, policy_version 66030 (0.0009) -[2023-10-12 05:59:56,452][78091] Updated weights for policy 0, policy_version 66040 (0.0007) -[2023-10-12 06:00:00,085][78123] Updated weights for policy 1, policy_version 65730 (0.0008) -[2023-10-12 06:00:00,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 134938624. Throughput: 0: 1581.2, 1: 1575.9. Samples: 33744036. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 06:00:00,201][77203] Avg episode reward: [(0, '54.150'), (1, '46.480')] -[2023-10-12 06:00:00,464][78123] Updated weights for policy 1, policy_version 65740 (0.0010) -[2023-10-12 06:00:00,665][78091] Updated weights for policy 0, policy_version 66050 (0.0009) -[2023-10-12 06:00:00,826][78123] Updated weights for policy 1, policy_version 65750 (0.0010) -[2023-10-12 06:00:01,029][78091] Updated weights for policy 0, policy_version 66060 (0.0007) -[2023-10-12 06:00:01,197][78123] Updated weights for policy 1, policy_version 65760 (0.0007) -[2023-10-12 06:00:01,403][78091] Updated weights for policy 0, policy_version 66070 (0.0007) -[2023-10-12 06:00:01,767][78091] Updated weights for policy 0, policy_version 66080 (0.0007) -[2023-10-12 06:00:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 135004160. Throughput: 0: 1586.1, 1: 1579.0. Samples: 33763622. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 06:00:05,201][77203] Avg episode reward: [(0, '60.690'), (1, '48.760')] -[2023-10-12 06:00:05,638][78123] Updated weights for policy 1, policy_version 65770 (0.0009) -[2023-10-12 06:00:06,002][78123] Updated weights for policy 1, policy_version 65780 (0.0007) -[2023-10-12 06:00:06,069][78091] Updated weights for policy 0, policy_version 66090 (0.0007) -[2023-10-12 06:00:06,374][78123] Updated weights for policy 1, policy_version 65790 (0.0008) -[2023-10-12 06:00:06,448][78091] Updated weights for policy 0, policy_version 66100 (0.0009) -[2023-10-12 06:00:06,824][78091] Updated weights for policy 0, policy_version 66110 (0.0007) -[2023-10-12 06:00:10,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 135069696. Throughput: 0: 1601.5, 1: 1595.7. Samples: 33783132. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-12 06:00:10,202][77203] Avg episode reward: [(0, '60.710'), (1, '43.600')] -[2023-10-12 06:00:10,827][78123] Updated weights for policy 1, policy_version 65800 (0.0010) -[2023-10-12 06:00:11,163][78091] Updated weights for policy 0, policy_version 66120 (0.0007) -[2023-10-12 06:00:11,198][78123] Updated weights for policy 1, policy_version 65810 (0.0009) -[2023-10-12 06:00:11,522][78091] Updated weights for policy 0, policy_version 66130 (0.0008) -[2023-10-12 06:00:11,557][78123] Updated weights for policy 1, policy_version 65820 (0.0007) -[2023-10-12 06:00:11,902][78091] Updated weights for policy 0, policy_version 66140 (0.0007) -[2023-10-12 06:00:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 135135232. Throughput: 0: 1589.7, 1: 1574.9. Samples: 33791712. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:00:15,202][77203] Avg episode reward: [(0, '55.740'), (1, '44.370')] -[2023-10-12 06:00:15,973][78123] Updated weights for policy 1, policy_version 65830 (0.0008) -[2023-10-12 06:00:16,214][78091] Updated weights for policy 0, policy_version 66150 (0.0008) -[2023-10-12 06:00:16,339][78123] Updated weights for policy 1, policy_version 65840 (0.0009) -[2023-10-12 06:00:16,576][78091] Updated weights for policy 0, policy_version 66160 (0.0007) -[2023-10-12 06:00:16,702][78123] Updated weights for policy 1, policy_version 65850 (0.0007) -[2023-10-12 06:00:16,944][78091] Updated weights for policy 0, policy_version 66170 (0.0009) -[2023-10-12 06:00:20,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 135200768. Throughput: 0: 1588.1, 1: 1577.6. Samples: 33811102. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:00:20,202][77203] Avg episode reward: [(0, '56.550'), (1, '53.510')] -[2023-10-12 06:00:20,930][78123] Updated weights for policy 1, policy_version 65860 (0.0008) -[2023-10-12 06:00:21,250][78091] Updated weights for policy 0, policy_version 66180 (0.0009) -[2023-10-12 06:00:21,294][78123] Updated weights for policy 1, policy_version 65870 (0.0009) -[2023-10-12 06:00:21,622][78091] Updated weights for policy 0, policy_version 66190 (0.0010) -[2023-10-12 06:00:21,660][78123] Updated weights for policy 1, policy_version 65880 (0.0008) -[2023-10-12 06:00:21,996][78091] Updated weights for policy 0, policy_version 66200 (0.0009) -[2023-10-12 06:00:25,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 135266304. Throughput: 0: 1589.6, 1: 1587.4. Samples: 33830576. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:00:25,201][77203] Avg episode reward: [(0, '56.550'), (1, '48.220')] -[2023-10-12 06:00:25,999][78123] Updated weights for policy 1, policy_version 65890 (0.0009) -[2023-10-12 06:00:26,194][78091] Updated weights for policy 0, policy_version 66210 (0.0009) -[2023-10-12 06:00:26,366][78123] Updated weights for policy 1, policy_version 65900 (0.0007) -[2023-10-12 06:00:26,569][78091] Updated weights for policy 0, policy_version 66220 (0.0009) -[2023-10-12 06:00:26,725][78123] Updated weights for policy 1, policy_version 65910 (0.0008) -[2023-10-12 06:00:26,935][78091] Updated weights for policy 0, policy_version 66230 (0.0009) -[2023-10-12 06:00:27,097][78123] Updated weights for policy 1, policy_version 65920 (0.0008) -[2023-10-12 06:00:27,300][78091] Updated weights for policy 0, policy_version 66240 (0.0009) -[2023-10-12 06:00:30,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 135331840. Throughput: 0: 1591.9, 1: 1573.5. Samples: 33839202. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:00:30,201][77203] Avg episode reward: [(0, '57.080'), (1, '49.280')] -[2023-10-12 06:00:31,467][78123] Updated weights for policy 1, policy_version 65930 (0.0008) -[2023-10-12 06:00:31,771][78091] Updated weights for policy 0, policy_version 66250 (0.0007) -[2023-10-12 06:00:31,847][78123] Updated weights for policy 1, policy_version 65940 (0.0008) -[2023-10-12 06:00:32,135][78091] Updated weights for policy 0, policy_version 66260 (0.0007) -[2023-10-12 06:00:32,201][78123] Updated weights for policy 1, policy_version 65950 (0.0007) -[2023-10-12 06:00:32,514][78091] Updated weights for policy 0, policy_version 66270 (0.0008) -[2023-10-12 06:00:35,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 135397376. Throughput: 0: 1600.1, 1: 1573.6. Samples: 33858692. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:00:35,202][77203] Avg episode reward: [(0, '48.360'), (1, '51.090')] -[2023-10-12 06:00:36,500][78123] Updated weights for policy 1, policy_version 65960 (0.0007) -[2023-10-12 06:00:36,603][78091] Updated weights for policy 0, policy_version 66280 (0.0007) -[2023-10-12 06:00:36,865][78123] Updated weights for policy 1, policy_version 65970 (0.0010) -[2023-10-12 06:00:36,964][78091] Updated weights for policy 0, policy_version 66290 (0.0009) -[2023-10-12 06:00:37,230][78123] Updated weights for policy 1, policy_version 65980 (0.0008) -[2023-10-12 06:00:37,340][78091] Updated weights for policy 0, policy_version 66300 (0.0010) -[2023-10-12 06:00:40,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 135462912. Throughput: 0: 1599.2, 1: 1572.8. Samples: 33878116. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:00:40,201][77203] Avg episode reward: [(0, '53.050'), (1, '50.780')] -[2023-10-12 06:00:41,584][78123] Updated weights for policy 1, policy_version 65990 (0.0008) -[2023-10-12 06:00:41,729][78091] Updated weights for policy 0, policy_version 66310 (0.0010) -[2023-10-12 06:00:41,950][78123] Updated weights for policy 1, policy_version 66000 (0.0009) -[2023-10-12 06:00:42,097][78091] Updated weights for policy 0, policy_version 66320 (0.0009) -[2023-10-12 06:00:42,310][78123] Updated weights for policy 1, policy_version 66010 (0.0007) -[2023-10-12 06:00:42,471][78091] Updated weights for policy 0, policy_version 66330 (0.0008) -[2023-10-12 06:00:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 135528448. Throughput: 0: 1596.3, 1: 1573.6. Samples: 33886684. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:00:45,202][77203] Avg episode reward: [(0, '51.740'), (1, '53.370')] -[2023-10-12 06:00:46,594][78123] Updated weights for policy 1, policy_version 66020 (0.0008) -[2023-10-12 06:00:46,783][78091] Updated weights for policy 0, policy_version 66340 (0.0007) -[2023-10-12 06:00:46,953][78123] Updated weights for policy 1, policy_version 66030 (0.0008) -[2023-10-12 06:00:47,150][78091] Updated weights for policy 0, policy_version 66350 (0.0008) -[2023-10-12 06:00:47,321][78123] Updated weights for policy 1, policy_version 66040 (0.0009) -[2023-10-12 06:00:47,526][78091] Updated weights for policy 0, policy_version 66360 (0.0008) -[2023-10-12 06:00:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 135593984. Throughput: 0: 1591.9, 1: 1578.9. Samples: 33906306. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:00:50,201][77203] Avg episode reward: [(0, '55.550'), (1, '53.360')] -[2023-10-12 06:00:51,706][78091] Updated weights for policy 0, policy_version 66370 (0.0008) -[2023-10-12 06:00:51,809][78123] Updated weights for policy 1, policy_version 66050 (0.0010) -[2023-10-12 06:00:52,068][78091] Updated weights for policy 0, policy_version 66380 (0.0009) -[2023-10-12 06:00:52,171][78123] Updated weights for policy 1, policy_version 66060 (0.0008) -[2023-10-12 06:00:52,433][78091] Updated weights for policy 0, policy_version 66390 (0.0008) -[2023-10-12 06:00:52,545][78123] Updated weights for policy 1, policy_version 66070 (0.0008) -[2023-10-12 06:00:52,804][78091] Updated weights for policy 0, policy_version 66400 (0.0010) -[2023-10-12 06:00:52,907][78123] Updated weights for policy 1, policy_version 66080 (0.0007) -[2023-10-12 06:00:55,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 135659520. Throughput: 0: 1591.7, 1: 1577.5. Samples: 33925748. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:00:55,202][77203] Avg episode reward: [(0, '54.580'), (1, '42.280')] -[2023-10-12 06:00:57,113][78091] Updated weights for policy 0, policy_version 66410 (0.0010) -[2023-10-12 06:00:57,370][78123] Updated weights for policy 1, policy_version 66090 (0.0008) -[2023-10-12 06:00:57,482][78091] Updated weights for policy 0, policy_version 66420 (0.0010) -[2023-10-12 06:00:57,739][78123] Updated weights for policy 1, policy_version 66100 (0.0007) -[2023-10-12 06:00:57,857][78091] Updated weights for policy 0, policy_version 66430 (0.0008) -[2023-10-12 06:00:58,106][78123] Updated weights for policy 1, policy_version 66110 (0.0009) -[2023-10-12 06:01:00,201][77203] Fps is (10 sec: 13106.6, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 135725056. Throughput: 0: 1597.1, 1: 1582.5. Samples: 33934796. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 06:01:00,202][77203] Avg episode reward: [(0, '57.620'), (1, '46.960')] -[2023-10-12 06:01:02,124][78091] Updated weights for policy 0, policy_version 66440 (0.0007) -[2023-10-12 06:01:02,406][78123] Updated weights for policy 1, policy_version 66120 (0.0009) -[2023-10-12 06:01:02,496][78091] Updated weights for policy 0, policy_version 66450 (0.0008) -[2023-10-12 06:01:02,768][78123] Updated weights for policy 1, policy_version 66130 (0.0008) -[2023-10-12 06:01:02,866][78091] Updated weights for policy 0, policy_version 66460 (0.0009) -[2023-10-12 06:01:03,127][78123] Updated weights for policy 1, policy_version 66140 (0.0009) -[2023-10-12 06:01:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 135790592. Throughput: 0: 1596.4, 1: 1568.4. Samples: 33953520. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 06:01:05,202][77203] Avg episode reward: [(0, '55.630'), (1, '42.470')] -[2023-10-12 06:01:07,244][78091] Updated weights for policy 0, policy_version 66470 (0.0007) -[2023-10-12 06:01:07,580][78123] Updated weights for policy 1, policy_version 66150 (0.0010) -[2023-10-12 06:01:07,618][78091] Updated weights for policy 0, policy_version 66480 (0.0008) -[2023-10-12 06:01:07,954][78123] Updated weights for policy 1, policy_version 66160 (0.0007) -[2023-10-12 06:01:07,987][78091] Updated weights for policy 0, policy_version 66490 (0.0009) -[2023-10-12 06:01:08,323][78123] Updated weights for policy 1, policy_version 66170 (0.0008) -[2023-10-12 06:01:10,201][77203] Fps is (10 sec: 13107.8, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 135856128. Throughput: 0: 1599.8, 1: 1568.0. Samples: 33973126. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 06:01:10,201][77203] Avg episode reward: [(0, '56.630'), (1, '50.500')] -[2023-10-12 06:01:10,209][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000066176_67764224.pth... -[2023-10-12 06:01:10,209][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000066496_68091904.pth... -[2023-10-12 06:01:10,239][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000064704_66256896.pth -[2023-10-12 06:01:10,247][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000064992_66551808.pth -[2023-10-12 06:01:12,272][78091] Updated weights for policy 0, policy_version 66500 (0.0007) -[2023-10-12 06:01:12,514][78123] Updated weights for policy 1, policy_version 66180 (0.0009) -[2023-10-12 06:01:12,642][78091] Updated weights for policy 0, policy_version 66510 (0.0009) -[2023-10-12 06:01:12,887][78123] Updated weights for policy 1, policy_version 66190 (0.0010) -[2023-10-12 06:01:13,005][78091] Updated weights for policy 0, policy_version 66520 (0.0007) -[2023-10-12 06:01:13,248][78123] Updated weights for policy 1, policy_version 66200 (0.0009) -[2023-10-12 06:01:15,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 135921664. Throughput: 0: 1609.5, 1: 1586.7. Samples: 33983030. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 06:01:15,201][77203] Avg episode reward: [(0, '63.630'), (1, '50.970')] -[2023-10-12 06:01:17,276][78091] Updated weights for policy 0, policy_version 66530 (0.0007) -[2023-10-12 06:01:17,635][78091] Updated weights for policy 0, policy_version 66540 (0.0008) -[2023-10-12 06:01:17,655][78123] Updated weights for policy 1, policy_version 66210 (0.0007) -[2023-10-12 06:01:18,009][78091] Updated weights for policy 0, policy_version 66550 (0.0008) -[2023-10-12 06:01:18,017][78123] Updated weights for policy 1, policy_version 66220 (0.0010) -[2023-10-12 06:01:18,379][78091] Updated weights for policy 0, policy_version 66560 (0.0007) -[2023-10-12 06:01:18,385][78123] Updated weights for policy 1, policy_version 66230 (0.0007) -[2023-10-12 06:01:18,752][78123] Updated weights for policy 1, policy_version 66240 (0.0008) -[2023-10-12 06:01:20,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 135987200. Throughput: 0: 1595.0, 1: 1576.5. Samples: 34001408. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 06:01:20,202][77203] Avg episode reward: [(0, '58.920'), (1, '52.920')] -[2023-10-12 06:01:22,994][78091] Updated weights for policy 0, policy_version 66570 (0.0007) -[2023-10-12 06:01:23,078][78123] Updated weights for policy 1, policy_version 66250 (0.0008) -[2023-10-12 06:01:23,367][78091] Updated weights for policy 0, policy_version 66580 (0.0007) -[2023-10-12 06:01:23,443][78123] Updated weights for policy 1, policy_version 66260 (0.0009) -[2023-10-12 06:01:23,733][78091] Updated weights for policy 0, policy_version 66590 (0.0007) -[2023-10-12 06:01:23,812][78123] Updated weights for policy 1, policy_version 66270 (0.0008) -[2023-10-12 06:01:25,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 136052736. Throughput: 0: 1589.0, 1: 1573.5. Samples: 34020426. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 06:01:25,202][77203] Avg episode reward: [(0, '51.690'), (1, '50.380')] -[2023-10-12 06:01:28,004][78091] Updated weights for policy 0, policy_version 66600 (0.0009) -[2023-10-12 06:01:28,229][78123] Updated weights for policy 1, policy_version 66280 (0.0008) -[2023-10-12 06:01:28,377][78091] Updated weights for policy 0, policy_version 66610 (0.0008) -[2023-10-12 06:01:28,593][78123] Updated weights for policy 1, policy_version 66290 (0.0008) -[2023-10-12 06:01:28,744][78091] Updated weights for policy 0, policy_version 66620 (0.0007) -[2023-10-12 06:01:28,951][78123] Updated weights for policy 1, policy_version 66300 (0.0008) -[2023-10-12 06:01:30,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 136118272. Throughput: 0: 1615.7, 1: 1594.9. Samples: 34031160. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 06:01:30,201][77203] Avg episode reward: [(0, '65.630'), (1, '53.310')] -[2023-10-12 06:01:30,202][77792] Saving new best policy, reward=65.630! -[2023-10-12 06:01:33,000][78091] Updated weights for policy 0, policy_version 66630 (0.0007) -[2023-10-12 06:01:33,285][78123] Updated weights for policy 1, policy_version 66310 (0.0010) -[2023-10-12 06:01:33,366][78091] Updated weights for policy 0, policy_version 66640 (0.0008) -[2023-10-12 06:01:33,650][78123] Updated weights for policy 1, policy_version 66320 (0.0008) -[2023-10-12 06:01:33,742][78091] Updated weights for policy 0, policy_version 66650 (0.0007) -[2023-10-12 06:01:34,015][78123] Updated weights for policy 1, policy_version 66330 (0.0008) -[2023-10-12 06:01:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 136183808. Throughput: 0: 1598.8, 1: 1579.1. Samples: 34049312. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 06:01:35,202][77203] Avg episode reward: [(0, '53.740'), (1, '54.590')] -[2023-10-12 06:01:38,065][78091] Updated weights for policy 0, policy_version 66660 (0.0009) -[2023-10-12 06:01:38,424][78123] Updated weights for policy 1, policy_version 66340 (0.0010) -[2023-10-12 06:01:38,447][78091] Updated weights for policy 0, policy_version 66670 (0.0008) -[2023-10-12 06:01:38,794][78123] Updated weights for policy 1, policy_version 66350 (0.0009) -[2023-10-12 06:01:38,814][78091] Updated weights for policy 0, policy_version 66680 (0.0007) -[2023-10-12 06:01:39,162][78123] Updated weights for policy 1, policy_version 66360 (0.0007) -[2023-10-12 06:01:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 136249344. Throughput: 0: 1592.4, 1: 1575.8. Samples: 34068320. Policy #0 lag: (min: 22.0, avg: 25.1, max: 54.0) -[2023-10-12 06:01:40,201][77203] Avg episode reward: [(0, '56.070'), (1, '44.800')] -[2023-10-12 06:01:43,221][78091] Updated weights for policy 0, policy_version 66690 (0.0008) -[2023-10-12 06:01:43,483][78123] Updated weights for policy 1, policy_version 66370 (0.0009) -[2023-10-12 06:01:43,590][78091] Updated weights for policy 0, policy_version 66700 (0.0008) -[2023-10-12 06:01:43,874][78123] Updated weights for policy 1, policy_version 66380 (0.0008) -[2023-10-12 06:01:43,952][78091] Updated weights for policy 0, policy_version 66710 (0.0008) -[2023-10-12 06:01:44,245][78123] Updated weights for policy 1, policy_version 66390 (0.0008) -[2023-10-12 06:01:44,326][78091] Updated weights for policy 0, policy_version 66720 (0.0009) -[2023-10-12 06:01:44,615][78123] Updated weights for policy 1, policy_version 66400 (0.0009) -[2023-10-12 06:01:45,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 136314880. Throughput: 0: 1612.0, 1: 1600.6. Samples: 34079362. Policy #0 lag: (min: 22.0, avg: 25.1, max: 54.0) -[2023-10-12 06:01:45,201][77203] Avg episode reward: [(0, '59.050'), (1, '47.410')] -[2023-10-12 06:01:48,653][78091] Updated weights for policy 0, policy_version 66730 (0.0008) -[2023-10-12 06:01:49,013][78123] Updated weights for policy 1, policy_version 66410 (0.0008) -[2023-10-12 06:01:49,021][78091] Updated weights for policy 0, policy_version 66740 (0.0010) -[2023-10-12 06:01:49,378][78123] Updated weights for policy 1, policy_version 66420 (0.0008) -[2023-10-12 06:01:49,386][78091] Updated weights for policy 0, policy_version 66750 (0.0009) -[2023-10-12 06:01:49,748][78123] Updated weights for policy 1, policy_version 66430 (0.0007) -[2023-10-12 06:01:50,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 136380416. Throughput: 0: 1603.6, 1: 1606.7. Samples: 34097980. Policy #0 lag: (min: 22.0, avg: 25.1, max: 54.0) -[2023-10-12 06:01:50,202][77203] Avg episode reward: [(0, '53.770'), (1, '48.290')] -[2023-10-12 06:01:53,555][78091] Updated weights for policy 0, policy_version 66760 (0.0009) -[2023-10-12 06:01:53,924][78091] Updated weights for policy 0, policy_version 66770 (0.0008) -[2023-10-12 06:01:54,129][78123] Updated weights for policy 1, policy_version 66440 (0.0008) -[2023-10-12 06:01:54,289][78091] Updated weights for policy 0, policy_version 66780 (0.0010) -[2023-10-12 06:01:54,497][78123] Updated weights for policy 1, policy_version 66450 (0.0008) -[2023-10-12 06:01:54,869][78123] Updated weights for policy 1, policy_version 66460 (0.0009) -[2023-10-12 06:01:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 136445952. Throughput: 0: 1579.5, 1: 1592.0. Samples: 34115846. Policy #0 lag: (min: 22.0, avg: 25.1, max: 54.0) -[2023-10-12 06:01:55,202][77203] Avg episode reward: [(0, '62.930'), (1, '48.150')] -[2023-10-12 06:01:58,688][78091] Updated weights for policy 0, policy_version 66790 (0.0011) -[2023-10-12 06:01:59,060][78091] Updated weights for policy 0, policy_version 66800 (0.0009) -[2023-10-12 06:01:59,273][78123] Updated weights for policy 1, policy_version 66470 (0.0008) -[2023-10-12 06:01:59,428][78091] Updated weights for policy 0, policy_version 66810 (0.0010) -[2023-10-12 06:01:59,639][78123] Updated weights for policy 1, policy_version 66480 (0.0007) -[2023-10-12 06:02:00,005][78123] Updated weights for policy 1, policy_version 66490 (0.0010) -[2023-10-12 06:02:00,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.2, 300 sec: 12774.0). Total num frames: 136478720. Throughput: 0: 1596.8, 1: 1588.6. Samples: 34126376. Policy #0 lag: (min: 22.0, avg: 25.1, max: 54.0) -[2023-10-12 06:02:00,201][77203] Avg episode reward: [(0, '47.530'), (1, '48.760')] -[2023-10-12 06:02:03,932][78091] Updated weights for policy 0, policy_version 66820 (0.0009) -[2023-10-12 06:02:04,288][78123] Updated weights for policy 1, policy_version 66500 (0.0010) -[2023-10-12 06:02:04,301][78091] Updated weights for policy 0, policy_version 66830 (0.0007) -[2023-10-12 06:02:04,656][78123] Updated weights for policy 1, policy_version 66510 (0.0008) -[2023-10-12 06:02:04,666][78091] Updated weights for policy 0, policy_version 66840 (0.0008) -[2023-10-12 06:02:05,028][78123] Updated weights for policy 1, policy_version 66520 (0.0009) -[2023-10-12 06:02:05,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 136544256. Throughput: 0: 1605.6, 1: 1603.3. Samples: 34145808. Policy #0 lag: (min: 22.0, avg: 25.1, max: 54.0) -[2023-10-12 06:02:05,202][77203] Avg episode reward: [(0, '47.490'), (1, '45.940')] -[2023-10-12 06:02:08,910][78091] Updated weights for policy 0, policy_version 66850 (0.0009) -[2023-10-12 06:02:09,303][78091] Updated weights for policy 0, policy_version 66860 (0.0009) -[2023-10-12 06:02:09,548][78123] Updated weights for policy 1, policy_version 66530 (0.0009) -[2023-10-12 06:02:09,672][78091] Updated weights for policy 0, policy_version 66870 (0.0008) -[2023-10-12 06:02:09,911][78123] Updated weights for policy 1, policy_version 66540 (0.0008) -[2023-10-12 06:02:10,042][78091] Updated weights for policy 0, policy_version 66880 (0.0009) -[2023-10-12 06:02:10,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 136609792. Throughput: 0: 1594.0, 1: 1604.1. Samples: 34164340. Policy #0 lag: (min: 22.0, avg: 25.1, max: 54.0) -[2023-10-12 06:02:10,202][77203] Avg episode reward: [(0, '61.900'), (1, '45.670')] -[2023-10-12 06:02:10,281][78123] Updated weights for policy 1, policy_version 66550 (0.0008) -[2023-10-12 06:02:10,643][78123] Updated weights for policy 1, policy_version 66560 (0.0008) -[2023-10-12 06:02:14,236][78091] Updated weights for policy 0, policy_version 66890 (0.0008) -[2023-10-12 06:02:14,616][78091] Updated weights for policy 0, policy_version 66900 (0.0007) -[2023-10-12 06:02:14,920][78123] Updated weights for policy 1, policy_version 66570 (0.0010) -[2023-10-12 06:02:14,979][78091] Updated weights for policy 0, policy_version 66910 (0.0008) -[2023-10-12 06:02:15,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 136675328. Throughput: 0: 1588.9, 1: 1588.7. Samples: 34174152. Policy #0 lag: (min: 22.0, avg: 25.1, max: 54.0) -[2023-10-12 06:02:15,201][77203] Avg episode reward: [(0, '57.430'), (1, '44.650')] -[2023-10-12 06:02:15,283][78123] Updated weights for policy 1, policy_version 66580 (0.0010) -[2023-10-12 06:02:15,657][78123] Updated weights for policy 1, policy_version 66590 (0.0009) -[2023-10-12 06:02:19,341][78091] Updated weights for policy 0, policy_version 66920 (0.0007) -[2023-10-12 06:02:19,705][78091] Updated weights for policy 0, policy_version 66930 (0.0007) -[2023-10-12 06:02:20,081][78091] Updated weights for policy 0, policy_version 66940 (0.0008) -[2023-10-12 06:02:20,164][78123] Updated weights for policy 1, policy_version 66600 (0.0007) -[2023-10-12 06:02:20,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 136708096. Throughput: 0: 1604.0, 1: 1599.2. Samples: 34193454. Policy #0 lag: (min: 22.0, avg: 25.1, max: 54.0) -[2023-10-12 06:02:20,201][77203] Avg episode reward: [(0, '55.550'), (1, '51.470')] -[2023-10-12 06:02:20,528][78123] Updated weights for policy 1, policy_version 66610 (0.0007) -[2023-10-12 06:02:20,896][78123] Updated weights for policy 1, policy_version 66620 (0.0007) -[2023-10-12 06:02:24,272][78091] Updated weights for policy 0, policy_version 66950 (0.0007) -[2023-10-12 06:02:24,641][78091] Updated weights for policy 0, policy_version 66960 (0.0009) -[2023-10-12 06:02:25,006][78123] Updated weights for policy 1, policy_version 66630 (0.0009) -[2023-10-12 06:02:25,017][78091] Updated weights for policy 0, policy_version 66970 (0.0007) -[2023-10-12 06:02:25,201][77203] Fps is (10 sec: 9830.2, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 136773632. Throughput: 0: 1591.6, 1: 1605.3. Samples: 34212182. Policy #0 lag: (min: 22.0, avg: 25.1, max: 54.0) -[2023-10-12 06:02:25,202][77203] Avg episode reward: [(0, '50.670'), (1, '47.090')] -[2023-10-12 06:02:25,376][78123] Updated weights for policy 1, policy_version 66640 (0.0010) -[2023-10-12 06:02:25,737][78123] Updated weights for policy 1, policy_version 66650 (0.0011) -[2023-10-12 06:02:29,446][78091] Updated weights for policy 0, policy_version 66980 (0.0007) -[2023-10-12 06:02:29,828][78091] Updated weights for policy 0, policy_version 66990 (0.0009) -[2023-10-12 06:02:30,103][78123] Updated weights for policy 1, policy_version 66660 (0.0010) -[2023-10-12 06:02:30,199][78091] Updated weights for policy 0, policy_version 67000 (0.0009) -[2023-10-12 06:02:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 136839168. Throughput: 0: 1581.1, 1: 1579.3. Samples: 34221578. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:02:30,201][77203] Avg episode reward: [(0, '55.430'), (1, '49.030')] -[2023-10-12 06:02:30,497][78123] Updated weights for policy 1, policy_version 66670 (0.0008) -[2023-10-12 06:02:30,861][78123] Updated weights for policy 1, policy_version 66680 (0.0007) -[2023-10-12 06:02:34,608][78091] Updated weights for policy 0, policy_version 67010 (0.0010) -[2023-10-12 06:02:34,980][78091] Updated weights for policy 0, policy_version 67020 (0.0007) -[2023-10-12 06:02:35,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 136904704. Throughput: 0: 1591.0, 1: 1581.2. Samples: 34240726. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:02:35,202][77203] Avg episode reward: [(0, '58.020'), (1, '46.590')] -[2023-10-12 06:02:35,323][78123] Updated weights for policy 1, policy_version 66690 (0.0008) -[2023-10-12 06:02:35,347][78091] Updated weights for policy 0, policy_version 67030 (0.0009) -[2023-10-12 06:02:35,685][78123] Updated weights for policy 1, policy_version 66700 (0.0007) -[2023-10-12 06:02:35,722][78091] Updated weights for policy 0, policy_version 67040 (0.0011) -[2023-10-12 06:02:36,048][78123] Updated weights for policy 1, policy_version 66710 (0.0009) -[2023-10-12 06:02:36,412][78123] Updated weights for policy 1, policy_version 66720 (0.0008) -[2023-10-12 06:02:40,071][78091] Updated weights for policy 0, policy_version 67050 (0.0011) -[2023-10-12 06:02:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 136970240. Throughput: 0: 1605.6, 1: 1593.2. Samples: 34259790. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:02:40,201][77203] Avg episode reward: [(0, '48.530'), (1, '49.780')] -[2023-10-12 06:02:40,445][78091] Updated weights for policy 0, policy_version 67060 (0.0010) -[2023-10-12 06:02:40,810][78091] Updated weights for policy 0, policy_version 67070 (0.0007) -[2023-10-12 06:02:40,828][78123] Updated weights for policy 1, policy_version 66730 (0.0008) -[2023-10-12 06:02:41,191][78123] Updated weights for policy 1, policy_version 66740 (0.0009) -[2023-10-12 06:02:41,553][78123] Updated weights for policy 1, policy_version 66750 (0.0007) -[2023-10-12 06:02:45,175][78091] Updated weights for policy 0, policy_version 67080 (0.0009) -[2023-10-12 06:02:45,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 137035776. Throughput: 0: 1579.1, 1: 1577.3. Samples: 34268414. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:02:45,201][77203] Avg episode reward: [(0, '47.340'), (1, '50.210')] -[2023-10-12 06:02:45,539][78091] Updated weights for policy 0, policy_version 67090 (0.0010) -[2023-10-12 06:02:45,826][78123] Updated weights for policy 1, policy_version 66760 (0.0007) -[2023-10-12 06:02:45,912][78091] Updated weights for policy 0, policy_version 67100 (0.0009) -[2023-10-12 06:02:46,191][78123] Updated weights for policy 1, policy_version 66770 (0.0009) -[2023-10-12 06:02:46,561][78123] Updated weights for policy 1, policy_version 66780 (0.0009) -[2023-10-12 06:02:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 137101312. Throughput: 0: 1584.0, 1: 1576.1. Samples: 34288012. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:02:50,201][77203] Avg episode reward: [(0, '50.190'), (1, '53.390')] -[2023-10-12 06:02:50,307][78091] Updated weights for policy 0, policy_version 67110 (0.0010) -[2023-10-12 06:02:50,672][78091] Updated weights for policy 0, policy_version 67120 (0.0009) -[2023-10-12 06:02:51,001][78123] Updated weights for policy 1, policy_version 66790 (0.0008) -[2023-10-12 06:02:51,047][78091] Updated weights for policy 0, policy_version 67130 (0.0007) -[2023-10-12 06:02:51,375][78123] Updated weights for policy 1, policy_version 66800 (0.0008) -[2023-10-12 06:02:51,741][78123] Updated weights for policy 1, policy_version 66810 (0.0008) -[2023-10-12 06:02:55,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 137166848. Throughput: 0: 1600.6, 1: 1579.0. Samples: 34307422. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:02:55,202][77203] Avg episode reward: [(0, '58.260'), (1, '46.910')] -[2023-10-12 06:02:55,416][78091] Updated weights for policy 0, policy_version 67140 (0.0007) -[2023-10-12 06:02:55,815][78091] Updated weights for policy 0, policy_version 67150 (0.0008) -[2023-10-12 06:02:56,118][78123] Updated weights for policy 1, policy_version 66820 (0.0009) -[2023-10-12 06:02:56,192][78091] Updated weights for policy 0, policy_version 67160 (0.0009) -[2023-10-12 06:02:56,484][78123] Updated weights for policy 1, policy_version 66830 (0.0009) -[2023-10-12 06:02:56,854][78123] Updated weights for policy 1, policy_version 66840 (0.0010) -[2023-10-12 06:03:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 137232384. Throughput: 0: 1578.3, 1: 1571.3. Samples: 34315886. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:03:00,201][77203] Avg episode reward: [(0, '71.210'), (1, '47.550')] -[2023-10-12 06:03:00,350][78091] Updated weights for policy 0, policy_version 67170 (0.0008) -[2023-10-12 06:03:00,720][78091] Updated weights for policy 0, policy_version 67180 (0.0008) -[2023-10-12 06:03:01,098][78091] Updated weights for policy 0, policy_version 67190 (0.0008) -[2023-10-12 06:03:01,232][78123] Updated weights for policy 1, policy_version 66850 (0.0009) -[2023-10-12 06:03:01,460][77792] Saving new best policy, reward=71.210! -[2023-10-12 06:03:01,461][78091] Updated weights for policy 0, policy_version 67200 (0.0007) -[2023-10-12 06:03:01,600][78123] Updated weights for policy 1, policy_version 66860 (0.0008) -[2023-10-12 06:03:01,962][78123] Updated weights for policy 1, policy_version 66870 (0.0008) -[2023-10-12 06:03:02,336][78123] Updated weights for policy 1, policy_version 66880 (0.0008) -[2023-10-12 06:03:05,201][77203] Fps is (10 sec: 13107.6, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 137297920. Throughput: 0: 1579.9, 1: 1573.7. Samples: 34335364. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:03:05,201][77203] Avg episode reward: [(0, '61.620'), (1, '49.380')] -[2023-10-12 06:03:05,851][78091] Updated weights for policy 0, policy_version 67210 (0.0009) -[2023-10-12 06:03:06,219][78091] Updated weights for policy 0, policy_version 67220 (0.0007) -[2023-10-12 06:03:06,586][78091] Updated weights for policy 0, policy_version 67230 (0.0009) -[2023-10-12 06:03:06,633][78123] Updated weights for policy 1, policy_version 66890 (0.0009) -[2023-10-12 06:03:07,002][78123] Updated weights for policy 1, policy_version 66900 (0.0010) -[2023-10-12 06:03:07,365][78123] Updated weights for policy 1, policy_version 66910 (0.0010) -[2023-10-12 06:03:10,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 137363456. Throughput: 0: 1594.4, 1: 1578.4. Samples: 34354962. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:03:10,202][77203] Avg episode reward: [(0, '53.030'), (1, '49.780')] -[2023-10-12 06:03:10,210][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000067232_68845568.pth... -[2023-10-12 06:03:10,210][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000066912_68517888.pth... -[2023-10-12 06:03:10,240][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000065760_67338240.pth -[2023-10-12 06:03:10,242][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000065440_67010560.pth -[2023-10-12 06:03:10,245][77792] Saving a milestone ./train_atari/atari_hero_APPO/checkpoint_p0/milestones/checkpoint_000067232_68845568.pth -[2023-10-12 06:03:10,246][77950] Saving a milestone ./train_atari/atari_hero_APPO/checkpoint_p1/milestones/checkpoint_000066912_68517888.pth -[2023-10-12 06:03:10,938][78091] Updated weights for policy 0, policy_version 67240 (0.0007) -[2023-10-12 06:03:11,312][78091] Updated weights for policy 0, policy_version 67250 (0.0007) -[2023-10-12 06:03:11,604][78123] Updated weights for policy 1, policy_version 66920 (0.0008) -[2023-10-12 06:03:11,682][78091] Updated weights for policy 0, policy_version 67260 (0.0007) -[2023-10-12 06:03:11,980][78123] Updated weights for policy 1, policy_version 66930 (0.0011) -[2023-10-12 06:03:12,347][78123] Updated weights for policy 1, policy_version 66940 (0.0009) -[2023-10-12 06:03:15,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 137428992. Throughput: 0: 1580.3, 1: 1574.6. Samples: 34363550. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-12 06:03:15,202][77203] Avg episode reward: [(0, '55.920'), (1, '50.060')] -[2023-10-12 06:03:15,983][78091] Updated weights for policy 0, policy_version 67270 (0.0009) -[2023-10-12 06:03:16,354][78091] Updated weights for policy 0, policy_version 67280 (0.0007) -[2023-10-12 06:03:16,714][78091] Updated weights for policy 0, policy_version 67290 (0.0009) -[2023-10-12 06:03:16,726][78123] Updated weights for policy 1, policy_version 66950 (0.0008) -[2023-10-12 06:03:17,083][78123] Updated weights for policy 1, policy_version 66960 (0.0009) -[2023-10-12 06:03:17,451][78123] Updated weights for policy 1, policy_version 66970 (0.0008) -[2023-10-12 06:03:20,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 137494528. Throughput: 0: 1584.3, 1: 1583.0. Samples: 34383254. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-12 06:03:20,202][77203] Avg episode reward: [(0, '68.180'), (1, '46.580')] -[2023-10-12 06:03:21,199][78091] Updated weights for policy 0, policy_version 67300 (0.0008) -[2023-10-12 06:03:21,565][78091] Updated weights for policy 0, policy_version 67310 (0.0008) -[2023-10-12 06:03:21,806][78123] Updated weights for policy 1, policy_version 66980 (0.0008) -[2023-10-12 06:03:21,935][78091] Updated weights for policy 0, policy_version 67320 (0.0007) -[2023-10-12 06:03:22,198][78123] Updated weights for policy 1, policy_version 66990 (0.0007) -[2023-10-12 06:03:22,554][78123] Updated weights for policy 1, policy_version 67000 (0.0009) -[2023-10-12 06:03:25,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 137560064. Throughput: 0: 1587.6, 1: 1584.2. Samples: 34402522. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-12 06:03:25,202][77203] Avg episode reward: [(0, '57.290'), (1, '44.700')] -[2023-10-12 06:03:26,308][78091] Updated weights for policy 0, policy_version 67330 (0.0007) -[2023-10-12 06:03:26,671][78091] Updated weights for policy 0, policy_version 67340 (0.0009) -[2023-10-12 06:03:26,933][78123] Updated weights for policy 1, policy_version 67010 (0.0010) -[2023-10-12 06:03:27,041][78091] Updated weights for policy 0, policy_version 67350 (0.0009) -[2023-10-12 06:03:27,305][78123] Updated weights for policy 1, policy_version 67020 (0.0010) -[2023-10-12 06:03:27,405][78091] Updated weights for policy 0, policy_version 67360 (0.0010) -[2023-10-12 06:03:27,679][78123] Updated weights for policy 1, policy_version 67030 (0.0008) -[2023-10-12 06:03:28,039][78123] Updated weights for policy 1, policy_version 67040 (0.0008) -[2023-10-12 06:03:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 137625600. Throughput: 0: 1585.8, 1: 1590.7. Samples: 34411356. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-12 06:03:30,201][77203] Avg episode reward: [(0, '54.140'), (1, '46.450')] -[2023-10-12 06:03:31,529][78091] Updated weights for policy 0, policy_version 67370 (0.0007) -[2023-10-12 06:03:31,907][78091] Updated weights for policy 0, policy_version 67380 (0.0008) -[2023-10-12 06:03:32,271][78091] Updated weights for policy 0, policy_version 67390 (0.0009) -[2023-10-12 06:03:32,282][78123] Updated weights for policy 1, policy_version 67050 (0.0009) -[2023-10-12 06:03:32,650][78123] Updated weights for policy 1, policy_version 67060 (0.0009) -[2023-10-12 06:03:33,018][78123] Updated weights for policy 1, policy_version 67070 (0.0010) -[2023-10-12 06:03:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 137691136. Throughput: 0: 1584.7, 1: 1582.4. Samples: 34430532. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-12 06:03:35,202][77203] Avg episode reward: [(0, '47.810'), (1, '52.810')] -[2023-10-12 06:03:36,486][78091] Updated weights for policy 0, policy_version 67400 (0.0008) -[2023-10-12 06:03:36,850][78091] Updated weights for policy 0, policy_version 67410 (0.0007) -[2023-10-12 06:03:37,224][78091] Updated weights for policy 0, policy_version 67420 (0.0008) -[2023-10-12 06:03:37,317][78123] Updated weights for policy 1, policy_version 67080 (0.0009) -[2023-10-12 06:03:37,680][78123] Updated weights for policy 1, policy_version 67090 (0.0011) -[2023-10-12 06:03:38,045][78123] Updated weights for policy 1, policy_version 67100 (0.0010) -[2023-10-12 06:03:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 137756672. Throughput: 0: 1587.9, 1: 1584.2. Samples: 34450168. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-12 06:03:40,201][77203] Avg episode reward: [(0, '53.150'), (1, '47.610')] -[2023-10-12 06:03:41,650][78091] Updated weights for policy 0, policy_version 67430 (0.0008) -[2023-10-12 06:03:42,030][78091] Updated weights for policy 0, policy_version 67440 (0.0009) -[2023-10-12 06:03:42,406][78091] Updated weights for policy 0, policy_version 67450 (0.0008) -[2023-10-12 06:03:42,549][78123] Updated weights for policy 1, policy_version 67110 (0.0010) -[2023-10-12 06:03:42,911][78123] Updated weights for policy 1, policy_version 67120 (0.0009) -[2023-10-12 06:03:43,277][78123] Updated weights for policy 1, policy_version 67130 (0.0007) -[2023-10-12 06:03:45,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 137822208. Throughput: 0: 1587.9, 1: 1597.6. Samples: 34459232. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-12 06:03:45,202][77203] Avg episode reward: [(0, '64.760'), (1, '52.600')] -[2023-10-12 06:03:46,757][78091] Updated weights for policy 0, policy_version 67460 (0.0009) -[2023-10-12 06:03:47,121][78091] Updated weights for policy 0, policy_version 67470 (0.0007) -[2023-10-12 06:03:47,495][78091] Updated weights for policy 0, policy_version 67480 (0.0007) -[2023-10-12 06:03:47,623][78123] Updated weights for policy 1, policy_version 67140 (0.0007) -[2023-10-12 06:03:47,990][78123] Updated weights for policy 1, policy_version 67150 (0.0007) -[2023-10-12 06:03:48,354][78123] Updated weights for policy 1, policy_version 67160 (0.0008) -[2023-10-12 06:03:50,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 137887744. Throughput: 0: 1586.7, 1: 1581.3. Samples: 34477924. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-12 06:03:50,202][77203] Avg episode reward: [(0, '53.020'), (1, '50.800')] -[2023-10-12 06:03:51,848][78091] Updated weights for policy 0, policy_version 67490 (0.0009) -[2023-10-12 06:03:52,220][78091] Updated weights for policy 0, policy_version 67500 (0.0010) -[2023-10-12 06:03:52,593][78091] Updated weights for policy 0, policy_version 67510 (0.0008) -[2023-10-12 06:03:52,726][78123] Updated weights for policy 1, policy_version 67170 (0.0007) -[2023-10-12 06:03:52,957][78091] Updated weights for policy 0, policy_version 67520 (0.0008) -[2023-10-12 06:03:53,088][78123] Updated weights for policy 1, policy_version 67180 (0.0009) -[2023-10-12 06:03:53,458][78123] Updated weights for policy 1, policy_version 67190 (0.0007) -[2023-10-12 06:03:53,827][78123] Updated weights for policy 1, policy_version 67200 (0.0009) -[2023-10-12 06:03:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 137953280. Throughput: 0: 1590.1, 1: 1574.0. Samples: 34497348. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-12 06:03:55,201][77203] Avg episode reward: [(0, '44.510'), (1, '52.730')] -[2023-10-12 06:03:57,390][78091] Updated weights for policy 0, policy_version 67530 (0.0007) -[2023-10-12 06:03:57,763][78091] Updated weights for policy 0, policy_version 67540 (0.0008) -[2023-10-12 06:03:58,110][78123] Updated weights for policy 1, policy_version 67210 (0.0008) -[2023-10-12 06:03:58,137][78091] Updated weights for policy 0, policy_version 67550 (0.0007) -[2023-10-12 06:03:58,467][78123] Updated weights for policy 1, policy_version 67220 (0.0008) -[2023-10-12 06:03:58,842][78123] Updated weights for policy 1, policy_version 67230 (0.0009) -[2023-10-12 06:04:00,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 138018816. Throughput: 0: 1603.3, 1: 1603.8. Samples: 34507872. Policy #0 lag: (min: 28.0, avg: 28.0, max: 33.0) -[2023-10-12 06:04:00,201][77203] Avg episode reward: [(0, '46.770'), (1, '50.760')] -[2023-10-12 06:04:02,345][78091] Updated weights for policy 0, policy_version 67560 (0.0010) -[2023-10-12 06:04:02,713][78091] Updated weights for policy 0, policy_version 67570 (0.0008) -[2023-10-12 06:04:03,084][78091] Updated weights for policy 0, policy_version 67580 (0.0009) -[2023-10-12 06:04:03,090][78123] Updated weights for policy 1, policy_version 67240 (0.0010) -[2023-10-12 06:04:03,455][78123] Updated weights for policy 1, policy_version 67250 (0.0009) -[2023-10-12 06:04:03,825][78123] Updated weights for policy 1, policy_version 67260 (0.0008) -[2023-10-12 06:04:05,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 138084352. Throughput: 0: 1593.1, 1: 1585.7. Samples: 34526300. Policy #0 lag: (min: 28.0, avg: 28.0, max: 33.0) -[2023-10-12 06:04:05,202][77203] Avg episode reward: [(0, '57.850'), (1, '48.820')] -[2023-10-12 06:04:07,313][78091] Updated weights for policy 0, policy_version 67590 (0.0007) -[2023-10-12 06:04:07,687][78091] Updated weights for policy 0, policy_version 67600 (0.0011) -[2023-10-12 06:04:08,062][78091] Updated weights for policy 0, policy_version 67610 (0.0009) -[2023-10-12 06:04:08,102][78123] Updated weights for policy 1, policy_version 67270 (0.0007) -[2023-10-12 06:04:08,490][78123] Updated weights for policy 1, policy_version 67280 (0.0008) -[2023-10-12 06:04:08,861][78123] Updated weights for policy 1, policy_version 67290 (0.0008) -[2023-10-12 06:04:10,201][77203] Fps is (10 sec: 13106.5, 60 sec: 13107.1, 300 sec: 12662.9). Total num frames: 138149888. Throughput: 0: 1592.8, 1: 1583.5. Samples: 34545458. Policy #0 lag: (min: 28.0, avg: 28.0, max: 33.0) -[2023-10-12 06:04:10,203][77203] Avg episode reward: [(0, '54.000'), (1, '48.900')] -[2023-10-12 06:04:12,482][78091] Updated weights for policy 0, policy_version 67620 (0.0009) -[2023-10-12 06:04:12,855][78091] Updated weights for policy 0, policy_version 67630 (0.0010) -[2023-10-12 06:04:13,229][78091] Updated weights for policy 0, policy_version 67640 (0.0007) -[2023-10-12 06:04:13,277][78123] Updated weights for policy 1, policy_version 67300 (0.0008) -[2023-10-12 06:04:13,635][78123] Updated weights for policy 1, policy_version 67310 (0.0009) -[2023-10-12 06:04:14,002][78123] Updated weights for policy 1, policy_version 67320 (0.0009) -[2023-10-12 06:04:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 138215424. Throughput: 0: 1610.2, 1: 1603.6. Samples: 34555978. Policy #0 lag: (min: 28.0, avg: 28.0, max: 33.0) -[2023-10-12 06:04:15,202][77203] Avg episode reward: [(0, '49.810'), (1, '49.930')] -[2023-10-12 06:04:17,583][78091] Updated weights for policy 0, policy_version 67650 (0.0008) -[2023-10-12 06:04:17,957][78091] Updated weights for policy 0, policy_version 67660 (0.0010) -[2023-10-12 06:04:18,316][78123] Updated weights for policy 1, policy_version 67330 (0.0010) -[2023-10-12 06:04:18,326][78091] Updated weights for policy 0, policy_version 67670 (0.0009) -[2023-10-12 06:04:18,679][78123] Updated weights for policy 1, policy_version 67340 (0.0008) -[2023-10-12 06:04:18,703][78091] Updated weights for policy 0, policy_version 67680 (0.0008) -[2023-10-12 06:04:19,043][78123] Updated weights for policy 1, policy_version 67350 (0.0010) -[2023-10-12 06:04:19,410][78123] Updated weights for policy 1, policy_version 67360 (0.0010) -[2023-10-12 06:04:20,201][77203] Fps is (10 sec: 13107.9, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 138280960. Throughput: 0: 1594.0, 1: 1603.7. Samples: 34574426. Policy #0 lag: (min: 28.0, avg: 28.0, max: 33.0) -[2023-10-12 06:04:20,201][77203] Avg episode reward: [(0, '50.260'), (1, '49.150')] -[2023-10-12 06:04:22,894][78091] Updated weights for policy 0, policy_version 67690 (0.0007) -[2023-10-12 06:04:23,258][78091] Updated weights for policy 0, policy_version 67700 (0.0007) -[2023-10-12 06:04:23,632][78091] Updated weights for policy 0, policy_version 67710 (0.0007) -[2023-10-12 06:04:23,890][78123] Updated weights for policy 1, policy_version 67370 (0.0008) -[2023-10-12 06:04:24,257][78123] Updated weights for policy 1, policy_version 67380 (0.0009) -[2023-10-12 06:04:24,621][78123] Updated weights for policy 1, policy_version 67390 (0.0010) -[2023-10-12 06:04:25,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 138346496. Throughput: 0: 1596.8, 1: 1586.6. Samples: 34593422. Policy #0 lag: (min: 28.0, avg: 28.0, max: 33.0) -[2023-10-12 06:04:25,201][77203] Avg episode reward: [(0, '53.770'), (1, '49.310')] -[2023-10-12 06:04:28,050][78091] Updated weights for policy 0, policy_version 67720 (0.0008) -[2023-10-12 06:04:28,415][78091] Updated weights for policy 0, policy_version 67730 (0.0008) -[2023-10-12 06:04:28,779][78091] Updated weights for policy 0, policy_version 67740 (0.0009) -[2023-10-12 06:04:28,987][78123] Updated weights for policy 1, policy_version 67400 (0.0008) -[2023-10-12 06:04:29,352][78123] Updated weights for policy 1, policy_version 67410 (0.0009) -[2023-10-12 06:04:29,724][78123] Updated weights for policy 1, policy_version 67420 (0.0010) -[2023-10-12 06:04:30,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 138412032. Throughput: 0: 1621.5, 1: 1596.0. Samples: 34604018. Policy #0 lag: (min: 28.0, avg: 28.0, max: 33.0) -[2023-10-12 06:04:30,202][77203] Avg episode reward: [(0, '51.500'), (1, '45.290')] -[2023-10-12 06:04:33,034][78091] Updated weights for policy 0, policy_version 67750 (0.0009) -[2023-10-12 06:04:33,406][78091] Updated weights for policy 0, policy_version 67760 (0.0008) -[2023-10-12 06:04:33,793][78091] Updated weights for policy 0, policy_version 67770 (0.0008) -[2023-10-12 06:04:33,894][78123] Updated weights for policy 1, policy_version 67430 (0.0009) -[2023-10-12 06:04:34,269][78123] Updated weights for policy 1, policy_version 67440 (0.0007) -[2023-10-12 06:04:34,639][78123] Updated weights for policy 1, policy_version 67450 (0.0008) -[2023-10-12 06:04:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 138477568. Throughput: 0: 1603.4, 1: 1612.8. Samples: 34622654. Policy #0 lag: (min: 28.0, avg: 28.0, max: 33.0) -[2023-10-12 06:04:35,201][77203] Avg episode reward: [(0, '52.770'), (1, '54.710')] -[2023-10-12 06:04:38,080][78091] Updated weights for policy 0, policy_version 67780 (0.0010) -[2023-10-12 06:04:38,441][78091] Updated weights for policy 0, policy_version 67790 (0.0009) -[2023-10-12 06:04:38,812][78091] Updated weights for policy 0, policy_version 67800 (0.0008) -[2023-10-12 06:04:39,045][78123] Updated weights for policy 1, policy_version 67460 (0.0009) -[2023-10-12 06:04:39,403][78123] Updated weights for policy 1, policy_version 67470 (0.0009) -[2023-10-12 06:04:39,784][78123] Updated weights for policy 1, policy_version 67480 (0.0009) -[2023-10-12 06:04:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 138543104. Throughput: 0: 1595.0, 1: 1598.6. Samples: 34641062. Policy #0 lag: (min: 28.0, avg: 28.0, max: 33.0) -[2023-10-12 06:04:40,202][77203] Avg episode reward: [(0, '46.590'), (1, '51.470')] -[2023-10-12 06:04:43,193][78091] Updated weights for policy 0, policy_version 67810 (0.0009) -[2023-10-12 06:04:43,573][78091] Updated weights for policy 0, policy_version 67820 (0.0010) -[2023-10-12 06:04:43,944][78091] Updated weights for policy 0, policy_version 67830 (0.0009) -[2023-10-12 06:04:44,094][78123] Updated weights for policy 1, policy_version 67490 (0.0008) -[2023-10-12 06:04:44,305][78091] Updated weights for policy 0, policy_version 67840 (0.0007) -[2023-10-12 06:04:44,457][78123] Updated weights for policy 1, policy_version 67500 (0.0010) -[2023-10-12 06:04:44,830][78123] Updated weights for policy 1, policy_version 67510 (0.0007) -[2023-10-12 06:04:45,194][78123] Updated weights for policy 1, policy_version 67520 (0.0007) -[2023-10-12 06:04:45,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 138608640. Throughput: 0: 1609.5, 1: 1585.0. Samples: 34651624. Policy #0 lag: (min: 12.0, avg: 13.4, max: 37.0) -[2023-10-12 06:04:45,201][77203] Avg episode reward: [(0, '48.540'), (1, '45.740')] -[2023-10-12 06:04:48,682][78091] Updated weights for policy 0, policy_version 67850 (0.0007) -[2023-10-12 06:04:49,046][78091] Updated weights for policy 0, policy_version 67860 (0.0007) -[2023-10-12 06:04:49,424][78091] Updated weights for policy 0, policy_version 67870 (0.0008) -[2023-10-12 06:04:49,527][78123] Updated weights for policy 1, policy_version 67530 (0.0007) -[2023-10-12 06:04:49,894][78123] Updated weights for policy 1, policy_version 67540 (0.0009) -[2023-10-12 06:04:50,201][77203] Fps is (10 sec: 9830.6, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 138641408. Throughput: 0: 1602.5, 1: 1599.7. Samples: 34670400. Policy #0 lag: (min: 12.0, avg: 13.4, max: 37.0) -[2023-10-12 06:04:50,201][77203] Avg episode reward: [(0, '60.090'), (1, '46.920')] -[2023-10-12 06:04:50,264][78123] Updated weights for policy 1, policy_version 67550 (0.0009) -[2023-10-12 06:04:53,554][78091] Updated weights for policy 0, policy_version 67880 (0.0008) -[2023-10-12 06:04:53,935][78091] Updated weights for policy 0, policy_version 67890 (0.0008) -[2023-10-12 06:04:54,305][78091] Updated weights for policy 0, policy_version 67900 (0.0008) -[2023-10-12 06:04:54,617][78123] Updated weights for policy 1, policy_version 67560 (0.0007) -[2023-10-12 06:04:54,990][78123] Updated weights for policy 1, policy_version 67570 (0.0008) -[2023-10-12 06:04:55,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 138706944. Throughput: 0: 1593.8, 1: 1596.2. Samples: 34689010. Policy #0 lag: (min: 12.0, avg: 13.4, max: 37.0) -[2023-10-12 06:04:55,201][77203] Avg episode reward: [(0, '65.290'), (1, '46.110')] -[2023-10-12 06:04:55,356][78123] Updated weights for policy 1, policy_version 67580 (0.0008) -[2023-10-12 06:04:58,632][78091] Updated weights for policy 0, policy_version 67910 (0.0008) -[2023-10-12 06:04:58,995][78091] Updated weights for policy 0, policy_version 67920 (0.0011) -[2023-10-12 06:04:59,360][78091] Updated weights for policy 0, policy_version 67930 (0.0008) -[2023-10-12 06:04:59,633][78123] Updated weights for policy 1, policy_version 67590 (0.0009) -[2023-10-12 06:04:59,998][78123] Updated weights for policy 1, policy_version 67600 (0.0008) -[2023-10-12 06:05:00,201][77203] Fps is (10 sec: 13106.8, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 138772480. Throughput: 0: 1603.0, 1: 1578.1. Samples: 34699126. Policy #0 lag: (min: 12.0, avg: 13.4, max: 37.0) -[2023-10-12 06:05:00,202][77203] Avg episode reward: [(0, '54.290'), (1, '48.300')] -[2023-10-12 06:05:00,371][78123] Updated weights for policy 1, policy_version 67610 (0.0008) -[2023-10-12 06:05:03,632][78091] Updated weights for policy 0, policy_version 67940 (0.0007) -[2023-10-12 06:05:04,000][78091] Updated weights for policy 0, policy_version 67950 (0.0007) -[2023-10-12 06:05:04,379][78091] Updated weights for policy 0, policy_version 67960 (0.0008) -[2023-10-12 06:05:04,655][78123] Updated weights for policy 1, policy_version 67620 (0.0008) -[2023-10-12 06:05:05,030][78123] Updated weights for policy 1, policy_version 67630 (0.0007) -[2023-10-12 06:05:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 138838016. Throughput: 0: 1611.3, 1: 1588.3. Samples: 34718408. Policy #0 lag: (min: 12.0, avg: 13.4, max: 37.0) -[2023-10-12 06:05:05,201][77203] Avg episode reward: [(0, '56.810'), (1, '53.000')] -[2023-10-12 06:05:05,398][78123] Updated weights for policy 1, policy_version 67640 (0.0007) -[2023-10-12 06:05:08,636][78091] Updated weights for policy 0, policy_version 67970 (0.0008) -[2023-10-12 06:05:09,008][78091] Updated weights for policy 0, policy_version 67980 (0.0009) -[2023-10-12 06:05:09,387][78091] Updated weights for policy 0, policy_version 67990 (0.0007) -[2023-10-12 06:05:09,745][78091] Updated weights for policy 0, policy_version 68000 (0.0007) -[2023-10-12 06:05:09,788][78123] Updated weights for policy 1, policy_version 67650 (0.0008) -[2023-10-12 06:05:10,151][78123] Updated weights for policy 1, policy_version 67660 (0.0010) -[2023-10-12 06:05:10,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.2, 300 sec: 12774.0). Total num frames: 138903552. Throughput: 0: 1589.2, 1: 1606.3. Samples: 34737220. Policy #0 lag: (min: 12.0, avg: 13.4, max: 37.0) -[2023-10-12 06:05:10,201][77203] Avg episode reward: [(0, '62.590'), (1, '49.560')] -[2023-10-12 06:05:10,210][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000068000_69632000.pth... -[2023-10-12 06:05:10,239][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000066496_68091904.pth -[2023-10-12 06:05:10,517][78123] Updated weights for policy 1, policy_version 67670 (0.0011) -[2023-10-12 06:05:10,882][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000067680_69304320.pth... -[2023-10-12 06:05:10,887][78123] Updated weights for policy 1, policy_version 67680 (0.0008) -[2023-10-12 06:05:10,921][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000066176_67764224.pth -[2023-10-12 06:05:14,132][78091] Updated weights for policy 0, policy_version 68010 (0.0009) -[2023-10-12 06:05:14,502][78091] Updated weights for policy 0, policy_version 68020 (0.0009) -[2023-10-12 06:05:14,876][78091] Updated weights for policy 0, policy_version 68030 (0.0008) -[2023-10-12 06:05:15,201][77203] Fps is (10 sec: 13106.7, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 138969088. Throughput: 0: 1596.1, 1: 1585.3. Samples: 34747182. Policy #0 lag: (min: 12.0, avg: 13.4, max: 37.0) -[2023-10-12 06:05:15,202][77203] Avg episode reward: [(0, '51.900'), (1, '49.990')] -[2023-10-12 06:05:15,264][78123] Updated weights for policy 1, policy_version 67690 (0.0010) -[2023-10-12 06:05:15,631][78123] Updated weights for policy 1, policy_version 67700 (0.0009) -[2023-10-12 06:05:15,991][78123] Updated weights for policy 1, policy_version 67710 (0.0008) -[2023-10-12 06:05:19,233][78091] Updated weights for policy 0, policy_version 68040 (0.0008) -[2023-10-12 06:05:19,612][78091] Updated weights for policy 0, policy_version 68050 (0.0009) -[2023-10-12 06:05:19,979][78091] Updated weights for policy 0, policy_version 68060 (0.0008) -[2023-10-12 06:05:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 139034624. Throughput: 0: 1614.2, 1: 1590.3. Samples: 34766858. Policy #0 lag: (min: 12.0, avg: 13.4, max: 37.0) -[2023-10-12 06:05:20,201][77203] Avg episode reward: [(0, '46.340'), (1, '50.290')] -[2023-10-12 06:05:20,357][78123] Updated weights for policy 1, policy_version 67720 (0.0010) -[2023-10-12 06:05:20,726][78123] Updated weights for policy 1, policy_version 67730 (0.0009) -[2023-10-12 06:05:21,091][78123] Updated weights for policy 1, policy_version 67740 (0.0009) -[2023-10-12 06:05:24,236][78091] Updated weights for policy 0, policy_version 68070 (0.0010) -[2023-10-12 06:05:24,616][78091] Updated weights for policy 0, policy_version 68080 (0.0008) -[2023-10-12 06:05:24,989][78091] Updated weights for policy 0, policy_version 68090 (0.0007) -[2023-10-12 06:05:25,201][77203] Fps is (10 sec: 9830.7, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 139067392. Throughput: 0: 1606.5, 1: 1605.0. Samples: 34785582. Policy #0 lag: (min: 12.0, avg: 13.4, max: 37.0) -[2023-10-12 06:05:25,201][77203] Avg episode reward: [(0, '50.050'), (1, '53.110')] -[2023-10-12 06:05:25,389][78123] Updated weights for policy 1, policy_version 67750 (0.0009) -[2023-10-12 06:05:25,766][78123] Updated weights for policy 1, policy_version 67760 (0.0007) -[2023-10-12 06:05:26,134][78123] Updated weights for policy 1, policy_version 67770 (0.0008) -[2023-10-12 06:05:29,129][78091] Updated weights for policy 0, policy_version 68100 (0.0008) -[2023-10-12 06:05:29,504][78091] Updated weights for policy 0, policy_version 68110 (0.0008) -[2023-10-12 06:05:29,875][78091] Updated weights for policy 0, policy_version 68120 (0.0007) -[2023-10-12 06:05:30,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 139165696. Throughput: 0: 1596.7, 1: 1591.8. Samples: 34795108. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-12 06:05:30,202][77203] Avg episode reward: [(0, '62.080'), (1, '55.100')] -[2023-10-12 06:05:30,277][78123] Updated weights for policy 1, policy_version 67780 (0.0009) -[2023-10-12 06:05:30,640][78123] Updated weights for policy 1, policy_version 67790 (0.0010) -[2023-10-12 06:05:31,005][78123] Updated weights for policy 1, policy_version 67800 (0.0007) -[2023-10-12 06:05:34,137][78091] Updated weights for policy 0, policy_version 68130 (0.0008) -[2023-10-12 06:05:34,505][78091] Updated weights for policy 0, policy_version 68140 (0.0009) -[2023-10-12 06:05:34,871][78091] Updated weights for policy 0, policy_version 68150 (0.0007) -[2023-10-12 06:05:35,128][78123] Updated weights for policy 1, policy_version 67810 (0.0008) -[2023-10-12 06:05:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 139198464. Throughput: 0: 1613.2, 1: 1599.9. Samples: 34814988. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-12 06:05:35,202][77203] Avg episode reward: [(0, '54.710'), (1, '47.180')] -[2023-10-12 06:05:35,240][78091] Updated weights for policy 0, policy_version 68160 (0.0008) -[2023-10-12 06:05:35,500][78123] Updated weights for policy 1, policy_version 67820 (0.0009) -[2023-10-12 06:05:35,870][78123] Updated weights for policy 1, policy_version 67830 (0.0009) -[2023-10-12 06:05:36,233][78123] Updated weights for policy 1, policy_version 67840 (0.0009) -[2023-10-12 06:05:39,788][78091] Updated weights for policy 0, policy_version 68170 (0.0007) -[2023-10-12 06:05:40,166][78091] Updated weights for policy 0, policy_version 68180 (0.0007) -[2023-10-12 06:05:40,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 139264000. Throughput: 0: 1610.0, 1: 1606.3. Samples: 34833744. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-12 06:05:40,201][77203] Avg episode reward: [(0, '55.840'), (1, '50.150')] -[2023-10-12 06:05:40,532][78091] Updated weights for policy 0, policy_version 68190 (0.0008) -[2023-10-12 06:05:40,654][78123] Updated weights for policy 1, policy_version 67850 (0.0009) -[2023-10-12 06:05:41,024][78123] Updated weights for policy 1, policy_version 67860 (0.0010) -[2023-10-12 06:05:41,388][78123] Updated weights for policy 1, policy_version 67870 (0.0010) -[2023-10-12 06:05:44,858][78091] Updated weights for policy 0, policy_version 68200 (0.0008) -[2023-10-12 06:05:45,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 139329536. Throughput: 0: 1590.4, 1: 1596.3. Samples: 34842526. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-12 06:05:45,201][77203] Avg episode reward: [(0, '53.760'), (1, '49.750')] -[2023-10-12 06:05:45,228][78091] Updated weights for policy 0, policy_version 68210 (0.0008) -[2023-10-12 06:05:45,591][78091] Updated weights for policy 0, policy_version 68220 (0.0008) -[2023-10-12 06:05:45,750][78123] Updated weights for policy 1, policy_version 67880 (0.0007) -[2023-10-12 06:05:46,117][78123] Updated weights for policy 1, policy_version 67890 (0.0011) -[2023-10-12 06:05:46,470][78123] Updated weights for policy 1, policy_version 67900 (0.0009) -[2023-10-12 06:05:49,939][78091] Updated weights for policy 0, policy_version 68230 (0.0009) -[2023-10-12 06:05:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 139395072. Throughput: 0: 1600.2, 1: 1592.4. Samples: 34862074. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-12 06:05:50,202][77203] Avg episode reward: [(0, '59.880'), (1, '47.470')] -[2023-10-12 06:05:50,319][78091] Updated weights for policy 0, policy_version 68240 (0.0010) -[2023-10-12 06:05:50,697][78091] Updated weights for policy 0, policy_version 68250 (0.0007) -[2023-10-12 06:05:50,977][78123] Updated weights for policy 1, policy_version 67910 (0.0010) -[2023-10-12 06:05:51,351][78123] Updated weights for policy 1, policy_version 67920 (0.0008) -[2023-10-12 06:05:51,723][78123] Updated weights for policy 1, policy_version 67930 (0.0009) -[2023-10-12 06:05:54,994][78091] Updated weights for policy 0, policy_version 68260 (0.0007) -[2023-10-12 06:05:55,201][77203] Fps is (10 sec: 13106.8, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 139460608. Throughput: 0: 1610.2, 1: 1590.4. Samples: 34881250. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-12 06:05:55,202][77203] Avg episode reward: [(0, '58.870'), (1, '46.520')] -[2023-10-12 06:05:55,372][78091] Updated weights for policy 0, policy_version 68270 (0.0007) -[2023-10-12 06:05:55,742][78091] Updated weights for policy 0, policy_version 68280 (0.0007) -[2023-10-12 06:05:56,021][78123] Updated weights for policy 1, policy_version 67940 (0.0008) -[2023-10-12 06:05:56,398][78123] Updated weights for policy 1, policy_version 67950 (0.0009) -[2023-10-12 06:05:56,762][78123] Updated weights for policy 1, policy_version 67960 (0.0007) -[2023-10-12 06:06:00,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 139526144. Throughput: 0: 1580.1, 1: 1591.7. Samples: 34889910. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-12 06:06:00,201][77203] Avg episode reward: [(0, '57.470'), (1, '50.350')] -[2023-10-12 06:06:00,230][78091] Updated weights for policy 0, policy_version 68290 (0.0008) -[2023-10-12 06:06:00,641][78091] Updated weights for policy 0, policy_version 68300 (0.0011) -[2023-10-12 06:06:01,020][78091] Updated weights for policy 0, policy_version 68310 (0.0009) -[2023-10-12 06:06:01,071][78123] Updated weights for policy 1, policy_version 67970 (0.0007) -[2023-10-12 06:06:01,383][78091] Updated weights for policy 0, policy_version 68320 (0.0009) -[2023-10-12 06:06:01,435][78123] Updated weights for policy 1, policy_version 67980 (0.0007) -[2023-10-12 06:06:01,791][78123] Updated weights for policy 1, policy_version 67990 (0.0007) -[2023-10-12 06:06:02,150][78123] Updated weights for policy 1, policy_version 68000 (0.0007) -[2023-10-12 06:06:05,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 139591680. Throughput: 0: 1579.6, 1: 1590.3. Samples: 34909504. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-12 06:06:05,202][77203] Avg episode reward: [(0, '54.250'), (1, '50.870')] -[2023-10-12 06:06:05,489][78091] Updated weights for policy 0, policy_version 68330 (0.0008) -[2023-10-12 06:06:05,853][78091] Updated weights for policy 0, policy_version 68340 (0.0007) -[2023-10-12 06:06:06,222][78091] Updated weights for policy 0, policy_version 68350 (0.0007) -[2023-10-12 06:06:06,464][78123] Updated weights for policy 1, policy_version 68010 (0.0008) -[2023-10-12 06:06:06,821][78123] Updated weights for policy 1, policy_version 68020 (0.0011) -[2023-10-12 06:06:07,189][78123] Updated weights for policy 1, policy_version 68030 (0.0008) -[2023-10-12 06:06:10,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 139657216. Throughput: 0: 1595.1, 1: 1593.0. Samples: 34929048. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-12 06:06:10,202][77203] Avg episode reward: [(0, '57.200'), (1, '48.830')] -[2023-10-12 06:06:10,548][78091] Updated weights for policy 0, policy_version 68360 (0.0008) -[2023-10-12 06:06:10,920][78091] Updated weights for policy 0, policy_version 68370 (0.0009) -[2023-10-12 06:06:11,298][78091] Updated weights for policy 0, policy_version 68380 (0.0007) -[2023-10-12 06:06:11,479][78123] Updated weights for policy 1, policy_version 68040 (0.0009) -[2023-10-12 06:06:11,864][78123] Updated weights for policy 1, policy_version 68050 (0.0009) -[2023-10-12 06:06:12,235][78123] Updated weights for policy 1, policy_version 68060 (0.0010) -[2023-10-12 06:06:15,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 139722752. Throughput: 0: 1577.3, 1: 1590.4. Samples: 34937654. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-12 06:06:15,201][77203] Avg episode reward: [(0, '55.790'), (1, '45.090')] -[2023-10-12 06:06:15,624][78091] Updated weights for policy 0, policy_version 68390 (0.0008) -[2023-10-12 06:06:15,986][78091] Updated weights for policy 0, policy_version 68400 (0.0007) -[2023-10-12 06:06:16,353][78091] Updated weights for policy 0, policy_version 68410 (0.0008) -[2023-10-12 06:06:16,643][78123] Updated weights for policy 1, policy_version 68070 (0.0009) -[2023-10-12 06:06:17,015][78123] Updated weights for policy 1, policy_version 68080 (0.0010) -[2023-10-12 06:06:17,387][78123] Updated weights for policy 1, policy_version 68090 (0.0009) -[2023-10-12 06:06:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 139788288. Throughput: 0: 1580.8, 1: 1581.9. Samples: 34957312. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:06:20,201][77203] Avg episode reward: [(0, '55.380'), (1, '49.380')] -[2023-10-12 06:06:20,596][78091] Updated weights for policy 0, policy_version 68420 (0.0009) -[2023-10-12 06:06:20,970][78091] Updated weights for policy 0, policy_version 68430 (0.0008) -[2023-10-12 06:06:21,338][78091] Updated weights for policy 0, policy_version 68440 (0.0007) -[2023-10-12 06:06:21,737][78123] Updated weights for policy 1, policy_version 68100 (0.0008) -[2023-10-12 06:06:22,104][78123] Updated weights for policy 1, policy_version 68110 (0.0008) -[2023-10-12 06:06:22,466][78123] Updated weights for policy 1, policy_version 68120 (0.0009) -[2023-10-12 06:06:25,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 139853824. Throughput: 0: 1594.9, 1: 1584.7. Samples: 34976826. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:06:25,202][77203] Avg episode reward: [(0, '53.690'), (1, '50.790')] -[2023-10-12 06:06:25,703][78091] Updated weights for policy 0, policy_version 68450 (0.0007) -[2023-10-12 06:06:26,076][78091] Updated weights for policy 0, policy_version 68460 (0.0007) -[2023-10-12 06:06:26,437][78091] Updated weights for policy 0, policy_version 68470 (0.0008) -[2023-10-12 06:06:26,772][78123] Updated weights for policy 1, policy_version 68130 (0.0008) -[2023-10-12 06:06:26,812][78091] Updated weights for policy 0, policy_version 68480 (0.0008) -[2023-10-12 06:06:27,162][78123] Updated weights for policy 1, policy_version 68140 (0.0007) -[2023-10-12 06:06:27,520][78123] Updated weights for policy 1, policy_version 68150 (0.0008) -[2023-10-12 06:06:27,883][78123] Updated weights for policy 1, policy_version 68160 (0.0008) -[2023-10-12 06:06:30,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 139919360. Throughput: 0: 1589.3, 1: 1588.7. Samples: 34985536. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:06:30,201][77203] Avg episode reward: [(0, '53.190'), (1, '46.250')] -[2023-10-12 06:06:31,163][78091] Updated weights for policy 0, policy_version 68490 (0.0009) -[2023-10-12 06:06:31,533][78091] Updated weights for policy 0, policy_version 68500 (0.0008) -[2023-10-12 06:06:31,903][78091] Updated weights for policy 0, policy_version 68510 (0.0007) -[2023-10-12 06:06:32,204][78123] Updated weights for policy 1, policy_version 68170 (0.0008) -[2023-10-12 06:06:32,574][78123] Updated weights for policy 1, policy_version 68180 (0.0009) -[2023-10-12 06:06:32,935][78123] Updated weights for policy 1, policy_version 68190 (0.0009) -[2023-10-12 06:06:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 139984896. Throughput: 0: 1586.0, 1: 1587.5. Samples: 35004880. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:06:35,202][77203] Avg episode reward: [(0, '55.880'), (1, '49.440')] -[2023-10-12 06:06:36,186][78091] Updated weights for policy 0, policy_version 68520 (0.0008) -[2023-10-12 06:06:36,551][78091] Updated weights for policy 0, policy_version 68530 (0.0008) -[2023-10-12 06:06:36,920][78091] Updated weights for policy 0, policy_version 68540 (0.0009) -[2023-10-12 06:06:37,328][78123] Updated weights for policy 1, policy_version 68200 (0.0008) -[2023-10-12 06:06:37,695][78123] Updated weights for policy 1, policy_version 68210 (0.0009) -[2023-10-12 06:06:38,059][78123] Updated weights for policy 1, policy_version 68220 (0.0008) -[2023-10-12 06:06:40,201][77203] Fps is (10 sec: 13106.7, 60 sec: 13107.1, 300 sec: 12662.9). Total num frames: 140050432. Throughput: 0: 1593.4, 1: 1588.7. Samples: 35024446. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:06:40,202][77203] Avg episode reward: [(0, '55.310'), (1, '51.610')] -[2023-10-12 06:06:41,289][78091] Updated weights for policy 0, policy_version 68550 (0.0010) -[2023-10-12 06:06:41,654][78091] Updated weights for policy 0, policy_version 68560 (0.0011) -[2023-10-12 06:06:42,033][78091] Updated weights for policy 0, policy_version 68570 (0.0009) -[2023-10-12 06:06:42,344][78123] Updated weights for policy 1, policy_version 68230 (0.0008) -[2023-10-12 06:06:42,700][78123] Updated weights for policy 1, policy_version 68240 (0.0009) -[2023-10-12 06:06:43,074][78123] Updated weights for policy 1, policy_version 68250 (0.0007) -[2023-10-12 06:06:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 140115968. Throughput: 0: 1591.6, 1: 1602.7. Samples: 35033656. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:06:45,202][77203] Avg episode reward: [(0, '59.130'), (1, '55.570')] -[2023-10-12 06:06:46,445][78091] Updated weights for policy 0, policy_version 68580 (0.0008) -[2023-10-12 06:06:46,814][78091] Updated weights for policy 0, policy_version 68590 (0.0007) -[2023-10-12 06:06:47,184][78091] Updated weights for policy 0, policy_version 68600 (0.0009) -[2023-10-12 06:06:47,501][78123] Updated weights for policy 1, policy_version 68260 (0.0007) -[2023-10-12 06:06:47,865][78123] Updated weights for policy 1, policy_version 68270 (0.0008) -[2023-10-12 06:06:48,230][78123] Updated weights for policy 1, policy_version 68280 (0.0007) -[2023-10-12 06:06:50,201][77203] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 140181504. Throughput: 0: 1594.0, 1: 1589.3. Samples: 35052754. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:06:50,201][77203] Avg episode reward: [(0, '53.000'), (1, '53.030')] -[2023-10-12 06:06:51,484][78091] Updated weights for policy 0, policy_version 68610 (0.0007) -[2023-10-12 06:06:51,875][78091] Updated weights for policy 0, policy_version 68620 (0.0010) -[2023-10-12 06:06:52,242][78091] Updated weights for policy 0, policy_version 68630 (0.0009) -[2023-10-12 06:06:52,472][78123] Updated weights for policy 1, policy_version 68290 (0.0007) -[2023-10-12 06:06:52,617][78091] Updated weights for policy 0, policy_version 68640 (0.0008) -[2023-10-12 06:06:52,845][78123] Updated weights for policy 1, policy_version 68300 (0.0009) -[2023-10-12 06:06:53,211][78123] Updated weights for policy 1, policy_version 68310 (0.0008) -[2023-10-12 06:06:53,581][78123] Updated weights for policy 1, policy_version 68320 (0.0010) -[2023-10-12 06:06:55,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 12774.0). Total num frames: 140247040. Throughput: 0: 1591.0, 1: 1591.4. Samples: 35072258. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:06:55,201][77203] Avg episode reward: [(0, '53.430'), (1, '51.720')] -[2023-10-12 06:06:56,740][78091] Updated weights for policy 0, policy_version 68650 (0.0008) -[2023-10-12 06:06:57,114][78091] Updated weights for policy 0, policy_version 68660 (0.0008) -[2023-10-12 06:06:57,489][78091] Updated weights for policy 0, policy_version 68670 (0.0009) -[2023-10-12 06:06:57,958][78123] Updated weights for policy 1, policy_version 68330 (0.0007) -[2023-10-12 06:06:58,317][78123] Updated weights for policy 1, policy_version 68340 (0.0010) -[2023-10-12 06:06:58,697][78123] Updated weights for policy 1, policy_version 68350 (0.0008) -[2023-10-12 06:07:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 140312576. Throughput: 0: 1589.1, 1: 1617.6. Samples: 35081954. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:07:00,201][77203] Avg episode reward: [(0, '64.060'), (1, '50.240')] -[2023-10-12 06:07:01,784][78091] Updated weights for policy 0, policy_version 68680 (0.0010) -[2023-10-12 06:07:02,162][78091] Updated weights for policy 0, policy_version 68690 (0.0008) -[2023-10-12 06:07:02,536][78091] Updated weights for policy 0, policy_version 68700 (0.0009) -[2023-10-12 06:07:03,204][78123] Updated weights for policy 1, policy_version 68360 (0.0008) -[2023-10-12 06:07:03,565][78123] Updated weights for policy 1, policy_version 68370 (0.0007) -[2023-10-12 06:07:03,931][78123] Updated weights for policy 1, policy_version 68380 (0.0008) -[2023-10-12 06:07:05,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 140378112. Throughput: 0: 1589.2, 1: 1601.7. Samples: 35100902. Policy #0 lag: (min: 8.0, avg: 31.8, max: 40.0) -[2023-10-12 06:07:05,202][77203] Avg episode reward: [(0, '58.250'), (1, '48.990')] -[2023-10-12 06:07:06,829][78091] Updated weights for policy 0, policy_version 68710 (0.0008) -[2023-10-12 06:07:07,205][78091] Updated weights for policy 0, policy_version 68720 (0.0008) -[2023-10-12 06:07:07,571][78091] Updated weights for policy 0, policy_version 68730 (0.0010) -[2023-10-12 06:07:08,212][78123] Updated weights for policy 1, policy_version 68390 (0.0009) -[2023-10-12 06:07:08,587][78123] Updated weights for policy 1, policy_version 68400 (0.0009) -[2023-10-12 06:07:08,952][78123] Updated weights for policy 1, policy_version 68410 (0.0007) -[2023-10-12 06:07:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 140443648. Throughput: 0: 1586.7, 1: 1591.4. Samples: 35119840. Policy #0 lag: (min: 8.0, avg: 31.8, max: 40.0) -[2023-10-12 06:07:10,202][77203] Avg episode reward: [(0, '52.050'), (1, '51.950')] -[2023-10-12 06:07:10,210][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000068416_70057984.pth... -[2023-10-12 06:07:10,210][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000068736_70385664.pth... -[2023-10-12 06:07:10,249][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000066912_68517888.pth -[2023-10-12 06:07:10,250][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000067232_68845568.pth -[2023-10-12 06:07:12,047][78091] Updated weights for policy 0, policy_version 68740 (0.0009) -[2023-10-12 06:07:12,406][78091] Updated weights for policy 0, policy_version 68750 (0.0009) -[2023-10-12 06:07:12,780][78091] Updated weights for policy 0, policy_version 68760 (0.0008) -[2023-10-12 06:07:13,400][78123] Updated weights for policy 1, policy_version 68420 (0.0009) -[2023-10-12 06:07:13,771][78123] Updated weights for policy 1, policy_version 68430 (0.0008) -[2023-10-12 06:07:14,132][78123] Updated weights for policy 1, policy_version 68440 (0.0008) -[2023-10-12 06:07:15,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 140509184. Throughput: 0: 1594.3, 1: 1612.0. Samples: 35129818. Policy #0 lag: (min: 8.0, avg: 31.8, max: 40.0) -[2023-10-12 06:07:15,201][77203] Avg episode reward: [(0, '57.690'), (1, '48.660')] -[2023-10-12 06:07:17,164][78091] Updated weights for policy 0, policy_version 68770 (0.0007) -[2023-10-12 06:07:17,527][78091] Updated weights for policy 0, policy_version 68780 (0.0009) -[2023-10-12 06:07:17,898][78091] Updated weights for policy 0, policy_version 68790 (0.0008) -[2023-10-12 06:07:18,266][78091] Updated weights for policy 0, policy_version 68800 (0.0008) -[2023-10-12 06:07:18,612][78123] Updated weights for policy 1, policy_version 68450 (0.0008) -[2023-10-12 06:07:18,985][78123] Updated weights for policy 1, policy_version 68460 (0.0007) -[2023-10-12 06:07:19,347][78123] Updated weights for policy 1, policy_version 68470 (0.0007) -[2023-10-12 06:07:19,717][78123] Updated weights for policy 1, policy_version 68480 (0.0008) -[2023-10-12 06:07:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 140574720. Throughput: 0: 1587.9, 1: 1609.3. Samples: 35148756. Policy #0 lag: (min: 8.0, avg: 31.8, max: 40.0) -[2023-10-12 06:07:20,201][77203] Avg episode reward: [(0, '54.840'), (1, '46.930')] -[2023-10-12 06:07:22,375][78091] Updated weights for policy 0, policy_version 68810 (0.0007) -[2023-10-12 06:07:22,749][78091] Updated weights for policy 0, policy_version 68820 (0.0007) -[2023-10-12 06:07:23,127][78091] Updated weights for policy 0, policy_version 68830 (0.0007) -[2023-10-12 06:07:23,824][78123] Updated weights for policy 1, policy_version 68490 (0.0010) -[2023-10-12 06:07:24,182][78123] Updated weights for policy 1, policy_version 68500 (0.0011) -[2023-10-12 06:07:24,549][78123] Updated weights for policy 1, policy_version 68510 (0.0007) -[2023-10-12 06:07:25,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 140640256. Throughput: 0: 1589.2, 1: 1589.6. Samples: 35167490. Policy #0 lag: (min: 8.0, avg: 31.8, max: 40.0) -[2023-10-12 06:07:25,202][77203] Avg episode reward: [(0, '62.900'), (1, '48.080')] -[2023-10-12 06:07:27,481][78091] Updated weights for policy 0, policy_version 68840 (0.0008) -[2023-10-12 06:07:27,851][78091] Updated weights for policy 0, policy_version 68850 (0.0009) -[2023-10-12 06:07:28,230][78091] Updated weights for policy 0, policy_version 68860 (0.0010) -[2023-10-12 06:07:28,754][78123] Updated weights for policy 1, policy_version 68520 (0.0009) -[2023-10-12 06:07:29,123][78123] Updated weights for policy 1, policy_version 68530 (0.0011) -[2023-10-12 06:07:29,493][78123] Updated weights for policy 1, policy_version 68540 (0.0010) -[2023-10-12 06:07:30,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 140705792. Throughput: 0: 1607.4, 1: 1597.7. Samples: 35177886. Policy #0 lag: (min: 8.0, avg: 31.8, max: 40.0) -[2023-10-12 06:07:30,201][77203] Avg episode reward: [(0, '52.810'), (1, '49.990')] -[2023-10-12 06:07:32,531][78091] Updated weights for policy 0, policy_version 68870 (0.0009) -[2023-10-12 06:07:32,900][78091] Updated weights for policy 0, policy_version 68880 (0.0009) -[2023-10-12 06:07:33,272][78091] Updated weights for policy 0, policy_version 68890 (0.0008) -[2023-10-12 06:07:33,636][78123] Updated weights for policy 1, policy_version 68550 (0.0009) -[2023-10-12 06:07:33,993][78123] Updated weights for policy 1, policy_version 68560 (0.0008) -[2023-10-12 06:07:34,359][78123] Updated weights for policy 1, policy_version 68570 (0.0009) -[2023-10-12 06:07:35,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 140771328. Throughput: 0: 1589.3, 1: 1604.8. Samples: 35196492. Policy #0 lag: (min: 8.0, avg: 31.8, max: 40.0) -[2023-10-12 06:07:35,202][77203] Avg episode reward: [(0, '52.180'), (1, '49.950')] -[2023-10-12 06:07:37,726][78091] Updated weights for policy 0, policy_version 68900 (0.0008) -[2023-10-12 06:07:38,113][78091] Updated weights for policy 0, policy_version 68910 (0.0008) -[2023-10-12 06:07:38,488][78091] Updated weights for policy 0, policy_version 68920 (0.0007) -[2023-10-12 06:07:38,803][78123] Updated weights for policy 1, policy_version 68580 (0.0009) -[2023-10-12 06:07:39,178][78123] Updated weights for policy 1, policy_version 68590 (0.0008) -[2023-10-12 06:07:39,547][78123] Updated weights for policy 1, policy_version 68600 (0.0008) -[2023-10-12 06:07:40,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.3, 300 sec: 12885.0). Total num frames: 140836864. Throughput: 0: 1589.8, 1: 1589.1. Samples: 35215308. Policy #0 lag: (min: 8.0, avg: 31.8, max: 40.0) -[2023-10-12 06:07:40,202][77203] Avg episode reward: [(0, '56.680'), (1, '44.470')] -[2023-10-12 06:07:42,529][78091] Updated weights for policy 0, policy_version 68930 (0.0009) -[2023-10-12 06:07:42,909][78091] Updated weights for policy 0, policy_version 68940 (0.0007) -[2023-10-12 06:07:43,282][78091] Updated weights for policy 0, policy_version 68950 (0.0008) -[2023-10-12 06:07:43,652][78091] Updated weights for policy 0, policy_version 68960 (0.0009) -[2023-10-12 06:07:44,051][78123] Updated weights for policy 1, policy_version 68610 (0.0008) -[2023-10-12 06:07:44,416][78123] Updated weights for policy 1, policy_version 68620 (0.0007) -[2023-10-12 06:07:44,778][78123] Updated weights for policy 1, policy_version 68630 (0.0008) -[2023-10-12 06:07:45,155][78123] Updated weights for policy 1, policy_version 68640 (0.0008) -[2023-10-12 06:07:45,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 140902400. Throughput: 0: 1615.9, 1: 1581.9. Samples: 35225856. Policy #0 lag: (min: 8.0, avg: 31.8, max: 40.0) -[2023-10-12 06:07:45,201][77203] Avg episode reward: [(0, '55.380'), (1, '46.730')] -[2023-10-12 06:07:48,022][78091] Updated weights for policy 0, policy_version 68970 (0.0010) -[2023-10-12 06:07:48,394][78091] Updated weights for policy 0, policy_version 68980 (0.0007) -[2023-10-12 06:07:48,778][78091] Updated weights for policy 0, policy_version 68990 (0.0008) -[2023-10-12 06:07:49,503][78123] Updated weights for policy 1, policy_version 68650 (0.0010) -[2023-10-12 06:07:49,875][78123] Updated weights for policy 1, policy_version 68660 (0.0008) -[2023-10-12 06:07:50,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 140935168. Throughput: 0: 1596.0, 1: 1595.2. Samples: 35244506. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:07:50,202][77203] Avg episode reward: [(0, '50.590'), (1, '44.480')] -[2023-10-12 06:07:50,237][78123] Updated weights for policy 1, policy_version 68670 (0.0007) -[2023-10-12 06:07:53,206][78091] Updated weights for policy 0, policy_version 69000 (0.0007) -[2023-10-12 06:07:53,590][78091] Updated weights for policy 0, policy_version 69010 (0.0008) -[2023-10-12 06:07:53,963][78091] Updated weights for policy 0, policy_version 69020 (0.0008) -[2023-10-12 06:07:54,538][78123] Updated weights for policy 1, policy_version 68680 (0.0007) -[2023-10-12 06:07:54,908][78123] Updated weights for policy 1, policy_version 68690 (0.0007) -[2023-10-12 06:07:55,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 141000704. Throughput: 0: 1595.2, 1: 1596.8. Samples: 35263480. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:07:55,201][77203] Avg episode reward: [(0, '48.200'), (1, '53.770')] -[2023-10-12 06:07:55,269][78123] Updated weights for policy 1, policy_version 68700 (0.0008) -[2023-10-12 06:07:58,060][78091] Updated weights for policy 0, policy_version 69030 (0.0007) -[2023-10-12 06:07:58,429][78091] Updated weights for policy 0, policy_version 69040 (0.0007) -[2023-10-12 06:07:58,810][78091] Updated weights for policy 0, policy_version 69050 (0.0007) -[2023-10-12 06:07:59,485][78123] Updated weights for policy 1, policy_version 68710 (0.0011) -[2023-10-12 06:07:59,865][78123] Updated weights for policy 1, policy_version 68720 (0.0008) -[2023-10-12 06:08:00,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 141066240. Throughput: 0: 1616.8, 1: 1584.8. Samples: 35273894. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:08:00,201][77203] Avg episode reward: [(0, '54.920'), (1, '46.110')] -[2023-10-12 06:08:00,231][78123] Updated weights for policy 1, policy_version 68730 (0.0007) -[2023-10-12 06:08:03,115][78091] Updated weights for policy 0, policy_version 69060 (0.0009) -[2023-10-12 06:08:03,488][78091] Updated weights for policy 0, policy_version 69070 (0.0009) -[2023-10-12 06:08:03,862][78091] Updated weights for policy 0, policy_version 69080 (0.0009) -[2023-10-12 06:08:04,608][78123] Updated weights for policy 1, policy_version 68740 (0.0009) -[2023-10-12 06:08:04,975][78123] Updated weights for policy 1, policy_version 68750 (0.0009) -[2023-10-12 06:08:05,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 141131776. Throughput: 0: 1603.8, 1: 1592.8. Samples: 35292604. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:08:05,202][77203] Avg episode reward: [(0, '52.050'), (1, '46.500')] -[2023-10-12 06:08:05,346][78123] Updated weights for policy 1, policy_version 68760 (0.0007) -[2023-10-12 06:08:07,961][78091] Updated weights for policy 0, policy_version 69090 (0.0009) -[2023-10-12 06:08:08,327][78091] Updated weights for policy 0, policy_version 69100 (0.0008) -[2023-10-12 06:08:08,705][78091] Updated weights for policy 0, policy_version 69110 (0.0008) -[2023-10-12 06:08:09,071][78091] Updated weights for policy 0, policy_version 69120 (0.0010) -[2023-10-12 06:08:09,673][78123] Updated weights for policy 1, policy_version 68770 (0.0008) -[2023-10-12 06:08:10,030][78123] Updated weights for policy 1, policy_version 68780 (0.0009) -[2023-10-12 06:08:10,201][77203] Fps is (10 sec: 13106.7, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 141197312. Throughput: 0: 1593.6, 1: 1611.4. Samples: 35311716. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:08:10,202][77203] Avg episode reward: [(0, '54.790'), (1, '48.570')] -[2023-10-12 06:08:10,407][78123] Updated weights for policy 1, policy_version 68790 (0.0008) -[2023-10-12 06:08:10,771][78123] Updated weights for policy 1, policy_version 68800 (0.0010) -[2023-10-12 06:08:13,465][78091] Updated weights for policy 0, policy_version 69130 (0.0007) -[2023-10-12 06:08:13,829][78091] Updated weights for policy 0, policy_version 69140 (0.0008) -[2023-10-12 06:08:14,210][78091] Updated weights for policy 0, policy_version 69150 (0.0008) -[2023-10-12 06:08:15,114][78123] Updated weights for policy 1, policy_version 68810 (0.0007) -[2023-10-12 06:08:15,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 141262848. Throughput: 0: 1605.5, 1: 1587.8. Samples: 35321584. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:08:15,201][77203] Avg episode reward: [(0, '51.490'), (1, '53.310')] -[2023-10-12 06:08:15,469][78123] Updated weights for policy 1, policy_version 68820 (0.0010) -[2023-10-12 06:08:15,833][78123] Updated weights for policy 1, policy_version 68830 (0.0010) -[2023-10-12 06:08:18,545][78091] Updated weights for policy 0, policy_version 69160 (0.0009) -[2023-10-12 06:08:18,922][78091] Updated weights for policy 0, policy_version 69170 (0.0010) -[2023-10-12 06:08:19,280][78091] Updated weights for policy 0, policy_version 69180 (0.0010) -[2023-10-12 06:08:20,132][78123] Updated weights for policy 1, policy_version 68840 (0.0007) -[2023-10-12 06:08:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 141328384. Throughput: 0: 1612.5, 1: 1592.4. Samples: 35340714. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:08:20,202][77203] Avg episode reward: [(0, '57.650'), (1, '50.430')] -[2023-10-12 06:08:20,494][78123] Updated weights for policy 1, policy_version 68850 (0.0007) -[2023-10-12 06:08:20,849][78123] Updated weights for policy 1, policy_version 68860 (0.0007) -[2023-10-12 06:08:23,756][78091] Updated weights for policy 0, policy_version 69190 (0.0008) -[2023-10-12 06:08:24,126][78091] Updated weights for policy 0, policy_version 69200 (0.0007) -[2023-10-12 06:08:24,494][78091] Updated weights for policy 0, policy_version 69210 (0.0007) -[2023-10-12 06:08:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 141393920. Throughput: 0: 1601.6, 1: 1604.1. Samples: 35359566. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:08:25,201][77203] Avg episode reward: [(0, '53.890'), (1, '41.760')] -[2023-10-12 06:08:25,353][78123] Updated weights for policy 1, policy_version 68870 (0.0007) -[2023-10-12 06:08:25,722][78123] Updated weights for policy 1, policy_version 68880 (0.0007) -[2023-10-12 06:08:26,080][78123] Updated weights for policy 1, policy_version 68890 (0.0008) -[2023-10-12 06:08:28,631][78091] Updated weights for policy 0, policy_version 69220 (0.0008) -[2023-10-12 06:08:28,999][78091] Updated weights for policy 0, policy_version 69230 (0.0009) -[2023-10-12 06:08:29,368][78091] Updated weights for policy 0, policy_version 69240 (0.0011) -[2023-10-12 06:08:30,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 141459456. Throughput: 0: 1606.0, 1: 1583.1. Samples: 35369366. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:08:30,202][77203] Avg episode reward: [(0, '58.340'), (1, '48.280')] -[2023-10-12 06:08:30,234][78123] Updated weights for policy 1, policy_version 68900 (0.0010) -[2023-10-12 06:08:30,594][78123] Updated weights for policy 1, policy_version 68910 (0.0010) -[2023-10-12 06:08:30,965][78123] Updated weights for policy 1, policy_version 68920 (0.0008) -[2023-10-12 06:08:33,454][78091] Updated weights for policy 0, policy_version 69250 (0.0008) -[2023-10-12 06:08:33,819][78091] Updated weights for policy 0, policy_version 69260 (0.0007) -[2023-10-12 06:08:34,192][78091] Updated weights for policy 0, policy_version 69270 (0.0007) -[2023-10-12 06:08:34,557][78091] Updated weights for policy 0, policy_version 69280 (0.0007) -[2023-10-12 06:08:35,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 141524992. Throughput: 0: 1619.6, 1: 1585.3. Samples: 35388728. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:08:35,202][77203] Avg episode reward: [(0, '53.380'), (1, '51.640')] -[2023-10-12 06:08:35,391][78123] Updated weights for policy 1, policy_version 68930 (0.0008) -[2023-10-12 06:08:35,756][78123] Updated weights for policy 1, policy_version 68940 (0.0010) -[2023-10-12 06:08:36,124][78123] Updated weights for policy 1, policy_version 68950 (0.0009) -[2023-10-12 06:08:36,494][78123] Updated weights for policy 1, policy_version 68960 (0.0010) -[2023-10-12 06:08:38,835][78091] Updated weights for policy 0, policy_version 69290 (0.0009) -[2023-10-12 06:08:39,206][78091] Updated weights for policy 0, policy_version 69300 (0.0007) -[2023-10-12 06:08:39,571][78091] Updated weights for policy 0, policy_version 69310 (0.0007) -[2023-10-12 06:08:40,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 141590528. Throughput: 0: 1606.2, 1: 1592.3. Samples: 35407412. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:08:40,201][77203] Avg episode reward: [(0, '57.100'), (1, '53.940')] -[2023-10-12 06:08:41,049][78123] Updated weights for policy 1, policy_version 68970 (0.0010) -[2023-10-12 06:08:41,416][78123] Updated weights for policy 1, policy_version 68980 (0.0008) -[2023-10-12 06:08:41,787][78123] Updated weights for policy 1, policy_version 68990 (0.0007) -[2023-10-12 06:08:44,000][78091] Updated weights for policy 0, policy_version 69320 (0.0009) -[2023-10-12 06:08:44,376][78091] Updated weights for policy 0, policy_version 69330 (0.0007) -[2023-10-12 06:08:44,753][78091] Updated weights for policy 0, policy_version 69340 (0.0007) -[2023-10-12 06:08:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 141656064. Throughput: 0: 1602.8, 1: 1583.5. Samples: 35417278. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:08:45,202][77203] Avg episode reward: [(0, '54.570'), (1, '49.190')] -[2023-10-12 06:08:45,950][78123] Updated weights for policy 1, policy_version 69000 (0.0008) -[2023-10-12 06:08:46,313][78123] Updated weights for policy 1, policy_version 69010 (0.0008) -[2023-10-12 06:08:46,687][78123] Updated weights for policy 1, policy_version 69020 (0.0009) -[2023-10-12 06:08:49,058][78091] Updated weights for policy 0, policy_version 69350 (0.0007) -[2023-10-12 06:08:49,428][78091] Updated weights for policy 0, policy_version 69360 (0.0007) -[2023-10-12 06:08:49,794][78091] Updated weights for policy 0, policy_version 69370 (0.0007) -[2023-10-12 06:08:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 141721600. Throughput: 0: 1624.4, 1: 1578.5. Samples: 35436734. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:08:50,201][77203] Avg episode reward: [(0, '56.440'), (1, '48.710')] -[2023-10-12 06:08:51,044][78123] Updated weights for policy 1, policy_version 69030 (0.0009) -[2023-10-12 06:08:51,414][78123] Updated weights for policy 1, policy_version 69040 (0.0007) -[2023-10-12 06:08:51,776][78123] Updated weights for policy 1, policy_version 69050 (0.0007) -[2023-10-12 06:08:54,262][78091] Updated weights for policy 0, policy_version 69380 (0.0007) -[2023-10-12 06:08:54,639][78091] Updated weights for policy 0, policy_version 69390 (0.0007) -[2023-10-12 06:08:55,006][78091] Updated weights for policy 0, policy_version 69400 (0.0008) -[2023-10-12 06:08:55,201][77203] Fps is (10 sec: 9830.6, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 141754368. Throughput: 0: 1616.4, 1: 1578.4. Samples: 35455480. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:08:55,201][77203] Avg episode reward: [(0, '48.600'), (1, '52.900')] -[2023-10-12 06:08:56,173][78123] Updated weights for policy 1, policy_version 69060 (0.0009) -[2023-10-12 06:08:56,547][78123] Updated weights for policy 1, policy_version 69070 (0.0007) -[2023-10-12 06:08:56,913][78123] Updated weights for policy 1, policy_version 69080 (0.0009) -[2023-10-12 06:08:59,504][78091] Updated weights for policy 0, policy_version 69410 (0.0009) -[2023-10-12 06:08:59,865][78091] Updated weights for policy 0, policy_version 69420 (0.0008) -[2023-10-12 06:09:00,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 141819904. Throughput: 0: 1602.2, 1: 1578.4. Samples: 35464710. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:09:00,201][77203] Avg episode reward: [(0, '54.690'), (1, '58.680')] -[2023-10-12 06:09:00,202][77950] Saving new best policy, reward=58.680! -[2023-10-12 06:09:00,240][78091] Updated weights for policy 0, policy_version 69430 (0.0009) -[2023-10-12 06:09:00,611][78091] Updated weights for policy 0, policy_version 69440 (0.0007) -[2023-10-12 06:09:01,190][78123] Updated weights for policy 1, policy_version 69090 (0.0010) -[2023-10-12 06:09:01,567][78123] Updated weights for policy 1, policy_version 69100 (0.0007) -[2023-10-12 06:09:01,937][78123] Updated weights for policy 1, policy_version 69110 (0.0007) -[2023-10-12 06:09:02,308][78123] Updated weights for policy 1, policy_version 69120 (0.0008) -[2023-10-12 06:09:04,764][78091] Updated weights for policy 0, policy_version 69450 (0.0011) -[2023-10-12 06:09:05,136][78091] Updated weights for policy 0, policy_version 69460 (0.0008) -[2023-10-12 06:09:05,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 141885440. Throughput: 0: 1614.8, 1: 1578.4. Samples: 35484410. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:09:05,202][77203] Avg episode reward: [(0, '54.530'), (1, '47.250')] -[2023-10-12 06:09:05,503][78091] Updated weights for policy 0, policy_version 69470 (0.0008) -[2023-10-12 06:09:06,425][78123] Updated weights for policy 1, policy_version 69130 (0.0008) -[2023-10-12 06:09:06,786][78123] Updated weights for policy 1, policy_version 69140 (0.0007) -[2023-10-12 06:09:07,146][78123] Updated weights for policy 1, policy_version 69150 (0.0009) -[2023-10-12 06:09:09,660][78091] Updated weights for policy 0, policy_version 69480 (0.0009) -[2023-10-12 06:09:10,036][78091] Updated weights for policy 0, policy_version 69490 (0.0009) -[2023-10-12 06:09:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 141950976. Throughput: 0: 1620.8, 1: 1582.7. Samples: 35503724. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:09:10,202][77203] Avg episode reward: [(0, '56.920'), (1, '47.300')] -[2023-10-12 06:09:10,208][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000069152_70811648.pth... -[2023-10-12 06:09:10,245][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000067680_69304320.pth -[2023-10-12 06:09:10,405][78091] Updated weights for policy 0, policy_version 69500 (0.0009) -[2023-10-12 06:09:10,553][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000069504_71172096.pth... -[2023-10-12 06:09:10,582][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000068000_69632000.pth -[2023-10-12 06:09:11,654][78123] Updated weights for policy 1, policy_version 69160 (0.0009) -[2023-10-12 06:09:12,016][78123] Updated weights for policy 1, policy_version 69170 (0.0009) -[2023-10-12 06:09:12,386][78123] Updated weights for policy 1, policy_version 69180 (0.0009) -[2023-10-12 06:09:14,716][78091] Updated weights for policy 0, policy_version 69510 (0.0008) -[2023-10-12 06:09:15,084][78091] Updated weights for policy 0, policy_version 69520 (0.0009) -[2023-10-12 06:09:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 142016512. Throughput: 0: 1601.3, 1: 1581.4. Samples: 35512588. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:09:15,202][77203] Avg episode reward: [(0, '63.020'), (1, '47.680')] -[2023-10-12 06:09:15,463][78091] Updated weights for policy 0, policy_version 69530 (0.0009) -[2023-10-12 06:09:16,845][78123] Updated weights for policy 1, policy_version 69190 (0.0007) -[2023-10-12 06:09:17,204][78123] Updated weights for policy 1, policy_version 69200 (0.0009) -[2023-10-12 06:09:17,578][78123] Updated weights for policy 1, policy_version 69210 (0.0007) -[2023-10-12 06:09:19,657][78091] Updated weights for policy 0, policy_version 69540 (0.0009) -[2023-10-12 06:09:20,023][78091] Updated weights for policy 0, policy_version 69550 (0.0009) -[2023-10-12 06:09:20,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 142082048. Throughput: 0: 1606.3, 1: 1584.3. Samples: 35532306. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:09:20,201][77203] Avg episode reward: [(0, '56.320'), (1, '55.650')] -[2023-10-12 06:09:20,387][78091] Updated weights for policy 0, policy_version 69560 (0.0008) -[2023-10-12 06:09:21,747][78123] Updated weights for policy 1, policy_version 69220 (0.0009) -[2023-10-12 06:09:22,114][78123] Updated weights for policy 1, policy_version 69230 (0.0008) -[2023-10-12 06:09:22,489][78123] Updated weights for policy 1, policy_version 69240 (0.0007) -[2023-10-12 06:09:24,689][78091] Updated weights for policy 0, policy_version 69570 (0.0008) -[2023-10-12 06:09:25,062][78091] Updated weights for policy 0, policy_version 69580 (0.0008) -[2023-10-12 06:09:25,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 142147584. Throughput: 0: 1618.3, 1: 1588.3. Samples: 35551712. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-12 06:09:25,202][77203] Avg episode reward: [(0, '57.810'), (1, '49.290')] -[2023-10-12 06:09:25,422][78091] Updated weights for policy 0, policy_version 69590 (0.0008) -[2023-10-12 06:09:25,794][78091] Updated weights for policy 0, policy_version 69600 (0.0007) -[2023-10-12 06:09:26,905][78123] Updated weights for policy 1, policy_version 69250 (0.0009) -[2023-10-12 06:09:27,269][78123] Updated weights for policy 1, policy_version 69260 (0.0007) -[2023-10-12 06:09:27,636][78123] Updated weights for policy 1, policy_version 69270 (0.0008) -[2023-10-12 06:09:28,010][78123] Updated weights for policy 1, policy_version 69280 (0.0007) -[2023-10-12 06:09:30,132][78091] Updated weights for policy 0, policy_version 69610 (0.0009) -[2023-10-12 06:09:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 142213120. Throughput: 0: 1596.3, 1: 1594.0. Samples: 35560842. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-12 06:09:30,201][77203] Avg episode reward: [(0, '54.910'), (1, '49.250')] -[2023-10-12 06:09:30,508][78091] Updated weights for policy 0, policy_version 69620 (0.0009) -[2023-10-12 06:09:30,874][78091] Updated weights for policy 0, policy_version 69630 (0.0009) -[2023-10-12 06:09:32,481][78123] Updated weights for policy 1, policy_version 69290 (0.0008) -[2023-10-12 06:09:32,842][78123] Updated weights for policy 1, policy_version 69300 (0.0007) -[2023-10-12 06:09:33,204][78123] Updated weights for policy 1, policy_version 69310 (0.0007) -[2023-10-12 06:09:35,194][78091] Updated weights for policy 0, policy_version 69640 (0.0009) -[2023-10-12 06:09:35,201][77203] Fps is (10 sec: 13107.6, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 142278656. Throughput: 0: 1597.1, 1: 1589.4. Samples: 35580124. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-12 06:09:35,202][77203] Avg episode reward: [(0, '56.450'), (1, '47.740')] -[2023-10-12 06:09:35,559][78091] Updated weights for policy 0, policy_version 69650 (0.0008) -[2023-10-12 06:09:35,926][78091] Updated weights for policy 0, policy_version 69660 (0.0009) -[2023-10-12 06:09:37,490][78123] Updated weights for policy 1, policy_version 69320 (0.0008) -[2023-10-12 06:09:37,851][78123] Updated weights for policy 1, policy_version 69330 (0.0009) -[2023-10-12 06:09:38,217][78123] Updated weights for policy 1, policy_version 69340 (0.0009) -[2023-10-12 06:09:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 142344192. Throughput: 0: 1610.4, 1: 1593.3. Samples: 35599648. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-12 06:09:40,201][77203] Avg episode reward: [(0, '53.590'), (1, '54.240')] -[2023-10-12 06:09:40,356][78091] Updated weights for policy 0, policy_version 69670 (0.0010) -[2023-10-12 06:09:40,729][78091] Updated weights for policy 0, policy_version 69680 (0.0008) -[2023-10-12 06:09:41,095][78091] Updated weights for policy 0, policy_version 69690 (0.0010) -[2023-10-12 06:09:42,475][78123] Updated weights for policy 1, policy_version 69350 (0.0008) -[2023-10-12 06:09:42,850][78123] Updated weights for policy 1, policy_version 69360 (0.0007) -[2023-10-12 06:09:43,222][78123] Updated weights for policy 1, policy_version 69370 (0.0007) -[2023-10-12 06:09:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 142409728. Throughput: 0: 1597.6, 1: 1609.8. Samples: 35609040. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-12 06:09:45,201][77203] Avg episode reward: [(0, '56.450'), (1, '49.850')] -[2023-10-12 06:09:45,374][78091] Updated weights for policy 0, policy_version 69700 (0.0010) -[2023-10-12 06:09:45,730][78091] Updated weights for policy 0, policy_version 69710 (0.0009) -[2023-10-12 06:09:46,097][78091] Updated weights for policy 0, policy_version 69720 (0.0008) -[2023-10-12 06:09:47,411][78123] Updated weights for policy 1, policy_version 69380 (0.0010) -[2023-10-12 06:09:47,785][78123] Updated weights for policy 1, policy_version 69390 (0.0009) -[2023-10-12 06:09:48,151][78123] Updated weights for policy 1, policy_version 69400 (0.0008) -[2023-10-12 06:09:50,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 142475264. Throughput: 0: 1594.7, 1: 1597.1. Samples: 35628042. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-12 06:09:50,202][77203] Avg episode reward: [(0, '57.040'), (1, '50.400')] -[2023-10-12 06:09:50,362][78091] Updated weights for policy 0, policy_version 69730 (0.0008) -[2023-10-12 06:09:50,730][78091] Updated weights for policy 0, policy_version 69740 (0.0008) -[2023-10-12 06:09:51,106][78091] Updated weights for policy 0, policy_version 69750 (0.0008) -[2023-10-12 06:09:51,477][78091] Updated weights for policy 0, policy_version 69760 (0.0009) -[2023-10-12 06:09:52,429][78123] Updated weights for policy 1, policy_version 69410 (0.0009) -[2023-10-12 06:09:52,801][78123] Updated weights for policy 1, policy_version 69420 (0.0008) -[2023-10-12 06:09:53,174][78123] Updated weights for policy 1, policy_version 69430 (0.0009) -[2023-10-12 06:09:53,533][78123] Updated weights for policy 1, policy_version 69440 (0.0009) -[2023-10-12 06:09:55,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 142540800. Throughput: 0: 1606.2, 1: 1594.2. Samples: 35647744. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-12 06:09:55,202][77203] Avg episode reward: [(0, '58.890'), (1, '50.140')] -[2023-10-12 06:09:55,806][78091] Updated weights for policy 0, policy_version 69770 (0.0007) -[2023-10-12 06:09:56,173][78091] Updated weights for policy 0, policy_version 69780 (0.0008) -[2023-10-12 06:09:56,538][78091] Updated weights for policy 0, policy_version 69790 (0.0007) -[2023-10-12 06:09:57,873][78123] Updated weights for policy 1, policy_version 69450 (0.0007) -[2023-10-12 06:09:58,251][78123] Updated weights for policy 1, policy_version 69460 (0.0008) -[2023-10-12 06:09:58,617][78123] Updated weights for policy 1, policy_version 69470 (0.0009) -[2023-10-12 06:10:00,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 142606336. Throughput: 0: 1594.6, 1: 1616.9. Samples: 35657108. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-12 06:10:00,202][77203] Avg episode reward: [(0, '55.950'), (1, '46.770')] -[2023-10-12 06:10:00,843][78091] Updated weights for policy 0, policy_version 69800 (0.0010) -[2023-10-12 06:10:01,213][78091] Updated weights for policy 0, policy_version 69810 (0.0010) -[2023-10-12 06:10:01,570][78091] Updated weights for policy 0, policy_version 69820 (0.0010) -[2023-10-12 06:10:03,096][78123] Updated weights for policy 1, policy_version 69480 (0.0009) -[2023-10-12 06:10:03,471][78123] Updated weights for policy 1, policy_version 69490 (0.0009) -[2023-10-12 06:10:03,841][78123] Updated weights for policy 1, policy_version 69500 (0.0009) -[2023-10-12 06:10:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 142671872. Throughput: 0: 1588.7, 1: 1600.2. Samples: 35675808. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-12 06:10:05,202][77203] Avg episode reward: [(0, '57.290'), (1, '54.100')] -[2023-10-12 06:10:05,922][78091] Updated weights for policy 0, policy_version 69830 (0.0009) -[2023-10-12 06:10:06,295][78091] Updated weights for policy 0, policy_version 69840 (0.0009) -[2023-10-12 06:10:06,677][78091] Updated weights for policy 0, policy_version 69850 (0.0009) -[2023-10-12 06:10:08,098][78123] Updated weights for policy 1, policy_version 69510 (0.0008) -[2023-10-12 06:10:08,460][78123] Updated weights for policy 1, policy_version 69520 (0.0007) -[2023-10-12 06:10:08,832][78123] Updated weights for policy 1, policy_version 69530 (0.0007) -[2023-10-12 06:10:10,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 142737408. Throughput: 0: 1595.1, 1: 1591.5. Samples: 35695106. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:10:10,202][77203] Avg episode reward: [(0, '53.940'), (1, '48.400')] -[2023-10-12 06:10:10,880][78091] Updated weights for policy 0, policy_version 69860 (0.0008) -[2023-10-12 06:10:11,249][78091] Updated weights for policy 0, policy_version 69870 (0.0008) -[2023-10-12 06:10:11,629][78091] Updated weights for policy 0, policy_version 69880 (0.0009) -[2023-10-12 06:10:12,881][78123] Updated weights for policy 1, policy_version 69540 (0.0009) -[2023-10-12 06:10:13,237][78123] Updated weights for policy 1, policy_version 69550 (0.0007) -[2023-10-12 06:10:13,607][78123] Updated weights for policy 1, policy_version 69560 (0.0007) -[2023-10-12 06:10:15,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 142802944. Throughput: 0: 1592.2, 1: 1611.3. Samples: 35705002. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:10:15,201][77203] Avg episode reward: [(0, '55.380'), (1, '52.810')] -[2023-10-12 06:10:15,939][78091] Updated weights for policy 0, policy_version 69890 (0.0008) -[2023-10-12 06:10:16,312][78091] Updated weights for policy 0, policy_version 69900 (0.0009) -[2023-10-12 06:10:16,688][78091] Updated weights for policy 0, policy_version 69910 (0.0009) -[2023-10-12 06:10:17,060][78091] Updated weights for policy 0, policy_version 69920 (0.0007) -[2023-10-12 06:10:18,090][78123] Updated weights for policy 1, policy_version 69570 (0.0008) -[2023-10-12 06:10:18,486][78123] Updated weights for policy 1, policy_version 69580 (0.0008) -[2023-10-12 06:10:18,849][78123] Updated weights for policy 1, policy_version 69590 (0.0008) -[2023-10-12 06:10:19,218][78123] Updated weights for policy 1, policy_version 69600 (0.0009) -[2023-10-12 06:10:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 142868480. Throughput: 0: 1590.7, 1: 1604.2. Samples: 35723894. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:10:20,201][77203] Avg episode reward: [(0, '54.500'), (1, '48.790')] -[2023-10-12 06:10:21,347][78091] Updated weights for policy 0, policy_version 69930 (0.0009) -[2023-10-12 06:10:21,720][78091] Updated weights for policy 0, policy_version 69940 (0.0009) -[2023-10-12 06:10:22,092][78091] Updated weights for policy 0, policy_version 69950 (0.0009) -[2023-10-12 06:10:23,456][78123] Updated weights for policy 1, policy_version 69610 (0.0008) -[2023-10-12 06:10:23,823][78123] Updated weights for policy 1, policy_version 69620 (0.0008) -[2023-10-12 06:10:24,188][78123] Updated weights for policy 1, policy_version 69630 (0.0009) -[2023-10-12 06:10:25,201][77203] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 142934016. Throughput: 0: 1596.6, 1: 1597.4. Samples: 35743376. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:10:25,202][77203] Avg episode reward: [(0, '58.890'), (1, '46.770')] -[2023-10-12 06:10:26,471][78091] Updated weights for policy 0, policy_version 69960 (0.0009) -[2023-10-12 06:10:26,841][78091] Updated weights for policy 0, policy_version 69970 (0.0011) -[2023-10-12 06:10:27,215][78091] Updated weights for policy 0, policy_version 69980 (0.0009) -[2023-10-12 06:10:28,391][78123] Updated weights for policy 1, policy_version 69640 (0.0008) -[2023-10-12 06:10:28,763][78123] Updated weights for policy 1, policy_version 69650 (0.0008) -[2023-10-12 06:10:29,123][78123] Updated weights for policy 1, policy_version 69660 (0.0009) -[2023-10-12 06:10:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 142999552. Throughput: 0: 1594.8, 1: 1607.9. Samples: 35753162. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:10:30,202][77203] Avg episode reward: [(0, '54.660'), (1, '54.240')] -[2023-10-12 06:10:31,572][78091] Updated weights for policy 0, policy_version 69990 (0.0008) -[2023-10-12 06:10:31,949][78091] Updated weights for policy 0, policy_version 70000 (0.0007) -[2023-10-12 06:10:32,314][78091] Updated weights for policy 0, policy_version 70010 (0.0008) -[2023-10-12 06:10:33,353][78123] Updated weights for policy 1, policy_version 69670 (0.0008) -[2023-10-12 06:10:33,723][78123] Updated weights for policy 1, policy_version 69680 (0.0010) -[2023-10-12 06:10:34,094][78123] Updated weights for policy 1, policy_version 69690 (0.0009) -[2023-10-12 06:10:35,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 143065088. Throughput: 0: 1597.4, 1: 1613.2. Samples: 35772518. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:10:35,201][77203] Avg episode reward: [(0, '62.400'), (1, '56.900')] -[2023-10-12 06:10:36,473][78091] Updated weights for policy 0, policy_version 70020 (0.0007) -[2023-10-12 06:10:36,838][78091] Updated weights for policy 0, policy_version 70030 (0.0007) -[2023-10-12 06:10:37,212][78091] Updated weights for policy 0, policy_version 70040 (0.0007) -[2023-10-12 06:10:38,511][78123] Updated weights for policy 1, policy_version 69700 (0.0010) -[2023-10-12 06:10:38,876][78123] Updated weights for policy 1, policy_version 69710 (0.0008) -[2023-10-12 06:10:39,244][78123] Updated weights for policy 1, policy_version 69720 (0.0008) -[2023-10-12 06:10:40,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 143130624. Throughput: 0: 1594.2, 1: 1598.9. Samples: 35791432. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:10:40,201][77203] Avg episode reward: [(0, '54.240'), (1, '51.780')] -[2023-10-12 06:10:41,507][78091] Updated weights for policy 0, policy_version 70050 (0.0007) -[2023-10-12 06:10:41,900][78091] Updated weights for policy 0, policy_version 70060 (0.0009) -[2023-10-12 06:10:42,275][78091] Updated weights for policy 0, policy_version 70070 (0.0008) -[2023-10-12 06:10:42,634][78091] Updated weights for policy 0, policy_version 70080 (0.0008) -[2023-10-12 06:10:43,436][78123] Updated weights for policy 1, policy_version 69730 (0.0007) -[2023-10-12 06:10:43,806][78123] Updated weights for policy 1, policy_version 69740 (0.0008) -[2023-10-12 06:10:44,169][78123] Updated weights for policy 1, policy_version 69750 (0.0010) -[2023-10-12 06:10:44,541][78123] Updated weights for policy 1, policy_version 69760 (0.0008) -[2023-10-12 06:10:45,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 143196160. Throughput: 0: 1594.1, 1: 1607.2. Samples: 35801168. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:10:45,202][77203] Avg episode reward: [(0, '56.590'), (1, '49.420')] -[2023-10-12 06:10:46,823][78091] Updated weights for policy 0, policy_version 70090 (0.0008) -[2023-10-12 06:10:47,188][78091] Updated weights for policy 0, policy_version 70100 (0.0009) -[2023-10-12 06:10:47,573][78091] Updated weights for policy 0, policy_version 70110 (0.0011) -[2023-10-12 06:10:48,977][78123] Updated weights for policy 1, policy_version 69770 (0.0007) -[2023-10-12 06:10:49,336][78123] Updated weights for policy 1, policy_version 69780 (0.0008) -[2023-10-12 06:10:49,712][78123] Updated weights for policy 1, policy_version 69790 (0.0010) -[2023-10-12 06:10:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 143261696. Throughput: 0: 1596.3, 1: 1616.9. Samples: 35820404. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:10:50,201][77203] Avg episode reward: [(0, '59.950'), (1, '48.100')] -[2023-10-12 06:10:51,820][78091] Updated weights for policy 0, policy_version 70120 (0.0010) -[2023-10-12 06:10:52,185][78091] Updated weights for policy 0, policy_version 70130 (0.0007) -[2023-10-12 06:10:52,557][78091] Updated weights for policy 0, policy_version 70140 (0.0008) -[2023-10-12 06:10:53,917][78123] Updated weights for policy 1, policy_version 69800 (0.0009) -[2023-10-12 06:10:54,286][78123] Updated weights for policy 1, policy_version 69810 (0.0010) -[2023-10-12 06:10:54,644][78123] Updated weights for policy 1, policy_version 69820 (0.0009) -[2023-10-12 06:10:55,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 143327232. Throughput: 0: 1597.4, 1: 1607.0. Samples: 35839304. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-12 06:10:55,202][77203] Avg episode reward: [(0, '59.440'), (1, '62.590')] -[2023-10-12 06:10:55,214][77950] Saving new best policy, reward=62.590! -[2023-10-12 06:10:56,872][78091] Updated weights for policy 0, policy_version 70150 (0.0009) -[2023-10-12 06:10:57,235][78091] Updated weights for policy 0, policy_version 70160 (0.0009) -[2023-10-12 06:10:57,606][78091] Updated weights for policy 0, policy_version 70170 (0.0009) -[2023-10-12 06:10:59,174][78123] Updated weights for policy 1, policy_version 69830 (0.0007) -[2023-10-12 06:10:59,540][78123] Updated weights for policy 1, policy_version 69840 (0.0010) -[2023-10-12 06:10:59,907][78123] Updated weights for policy 1, policy_version 69850 (0.0011) -[2023-10-12 06:11:00,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 12885.1). Total num frames: 143392768. Throughput: 0: 1599.6, 1: 1601.9. Samples: 35849070. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-12 06:11:00,201][77203] Avg episode reward: [(0, '57.020'), (1, '54.040')] -[2023-10-12 06:11:01,783][78091] Updated weights for policy 0, policy_version 70180 (0.0008) -[2023-10-12 06:11:02,140][78091] Updated weights for policy 0, policy_version 70190 (0.0008) -[2023-10-12 06:11:02,505][78091] Updated weights for policy 0, policy_version 70200 (0.0010) -[2023-10-12 06:11:04,239][78123] Updated weights for policy 1, policy_version 69860 (0.0010) -[2023-10-12 06:11:04,611][78123] Updated weights for policy 1, policy_version 69870 (0.0010) -[2023-10-12 06:11:04,976][78123] Updated weights for policy 1, policy_version 69880 (0.0009) -[2023-10-12 06:11:05,201][77203] Fps is (10 sec: 9830.7, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 143425536. Throughput: 0: 1599.2, 1: 1614.5. Samples: 35868510. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-12 06:11:05,201][77203] Avg episode reward: [(0, '53.610'), (1, '47.140')] -[2023-10-12 06:11:06,754][78091] Updated weights for policy 0, policy_version 70210 (0.0008) -[2023-10-12 06:11:07,126][78091] Updated weights for policy 0, policy_version 70220 (0.0007) -[2023-10-12 06:11:07,506][78091] Updated weights for policy 0, policy_version 70230 (0.0007) -[2023-10-12 06:11:07,880][78091] Updated weights for policy 0, policy_version 70240 (0.0008) -[2023-10-12 06:11:09,358][78123] Updated weights for policy 1, policy_version 69890 (0.0009) -[2023-10-12 06:11:09,726][78123] Updated weights for policy 1, policy_version 69900 (0.0007) -[2023-10-12 06:11:10,095][78123] Updated weights for policy 1, policy_version 69910 (0.0007) -[2023-10-12 06:11:10,201][77203] Fps is (10 sec: 9830.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 143491072. Throughput: 0: 1596.8, 1: 1606.0. Samples: 35887500. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-12 06:11:10,202][77203] Avg episode reward: [(0, '59.490'), (1, '46.710')] -[2023-10-12 06:11:10,210][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000070240_71925760.pth... -[2023-10-12 06:11:10,250][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000068736_70385664.pth -[2023-10-12 06:11:10,464][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000069920_71598080.pth... -[2023-10-12 06:11:10,468][78123] Updated weights for policy 1, policy_version 69920 (0.0008) -[2023-10-12 06:11:10,503][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000068416_70057984.pth -[2023-10-12 06:11:12,290][78091] Updated weights for policy 0, policy_version 70250 (0.0009) -[2023-10-12 06:11:12,672][78091] Updated weights for policy 0, policy_version 70260 (0.0007) -[2023-10-12 06:11:13,047][78091] Updated weights for policy 0, policy_version 70270 (0.0007) -[2023-10-12 06:11:14,744][78123] Updated weights for policy 1, policy_version 69930 (0.0007) -[2023-10-12 06:11:15,113][78123] Updated weights for policy 1, policy_version 69940 (0.0007) -[2023-10-12 06:11:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 143556608. Throughput: 0: 1604.9, 1: 1585.5. Samples: 35896730. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-12 06:11:15,202][77203] Avg episode reward: [(0, '58.440'), (1, '49.090')] -[2023-10-12 06:11:15,476][78123] Updated weights for policy 1, policy_version 69950 (0.0007) -[2023-10-12 06:11:17,363][78091] Updated weights for policy 0, policy_version 70280 (0.0009) -[2023-10-12 06:11:17,736][78091] Updated weights for policy 0, policy_version 70290 (0.0009) -[2023-10-12 06:11:18,102][78091] Updated weights for policy 0, policy_version 70300 (0.0008) -[2023-10-12 06:11:19,913][78123] Updated weights for policy 1, policy_version 69960 (0.0010) -[2023-10-12 06:11:20,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 143622144. Throughput: 0: 1595.2, 1: 1591.5. Samples: 35915920. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-12 06:11:20,201][77203] Avg episode reward: [(0, '59.560'), (1, '61.460')] -[2023-10-12 06:11:20,274][78123] Updated weights for policy 1, policy_version 69970 (0.0011) -[2023-10-12 06:11:20,645][78123] Updated weights for policy 1, policy_version 69980 (0.0008) -[2023-10-12 06:11:22,390][78091] Updated weights for policy 0, policy_version 70310 (0.0008) -[2023-10-12 06:11:22,766][78091] Updated weights for policy 0, policy_version 70320 (0.0009) -[2023-10-12 06:11:23,134][78091] Updated weights for policy 0, policy_version 70330 (0.0009) -[2023-10-12 06:11:24,903][78123] Updated weights for policy 1, policy_version 69990 (0.0007) -[2023-10-12 06:11:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 143687680. Throughput: 0: 1596.8, 1: 1605.2. Samples: 35935526. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-12 06:11:25,202][77203] Avg episode reward: [(0, '58.600'), (1, '44.280')] -[2023-10-12 06:11:25,271][78123] Updated weights for policy 1, policy_version 70000 (0.0009) -[2023-10-12 06:11:25,629][78123] Updated weights for policy 1, policy_version 70010 (0.0010) -[2023-10-12 06:11:27,526][78091] Updated weights for policy 0, policy_version 70340 (0.0009) -[2023-10-12 06:11:27,917][78091] Updated weights for policy 0, policy_version 70350 (0.0007) -[2023-10-12 06:11:28,294][78091] Updated weights for policy 0, policy_version 70360 (0.0011) -[2023-10-12 06:11:30,079][78123] Updated weights for policy 1, policy_version 70020 (0.0008) -[2023-10-12 06:11:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 143753216. Throughput: 0: 1614.6, 1: 1578.5. Samples: 35944856. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-12 06:11:30,201][77203] Avg episode reward: [(0, '60.900'), (1, '44.970')] -[2023-10-12 06:11:30,441][78123] Updated weights for policy 1, policy_version 70030 (0.0008) -[2023-10-12 06:11:30,809][78123] Updated weights for policy 1, policy_version 70040 (0.0007) -[2023-10-12 06:11:32,478][78091] Updated weights for policy 0, policy_version 70370 (0.0009) -[2023-10-12 06:11:32,861][78091] Updated weights for policy 0, policy_version 70380 (0.0008) -[2023-10-12 06:11:33,233][78091] Updated weights for policy 0, policy_version 70390 (0.0007) -[2023-10-12 06:11:33,600][78091] Updated weights for policy 0, policy_version 70400 (0.0008) -[2023-10-12 06:11:35,110][78123] Updated weights for policy 1, policy_version 70050 (0.0009) -[2023-10-12 06:11:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 143818752. Throughput: 0: 1598.6, 1: 1581.2. Samples: 35963494. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-12 06:11:35,201][77203] Avg episode reward: [(0, '52.130'), (1, '49.830')] -[2023-10-12 06:11:35,484][78123] Updated weights for policy 1, policy_version 70060 (0.0009) -[2023-10-12 06:11:35,859][78123] Updated weights for policy 1, policy_version 70070 (0.0010) -[2023-10-12 06:11:36,226][78123] Updated weights for policy 1, policy_version 70080 (0.0007) -[2023-10-12 06:11:37,949][78091] Updated weights for policy 0, policy_version 70410 (0.0009) -[2023-10-12 06:11:38,319][78091] Updated weights for policy 0, policy_version 70420 (0.0009) -[2023-10-12 06:11:38,694][78091] Updated weights for policy 0, policy_version 70430 (0.0008) -[2023-10-12 06:11:40,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 143884288. Throughput: 0: 1593.8, 1: 1596.7. Samples: 35982876. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 06:11:40,202][77203] Avg episode reward: [(0, '65.040'), (1, '58.450')] -[2023-10-12 06:11:40,538][78123] Updated weights for policy 1, policy_version 70090 (0.0010) -[2023-10-12 06:11:40,893][78123] Updated weights for policy 1, policy_version 70100 (0.0009) -[2023-10-12 06:11:41,252][78123] Updated weights for policy 1, policy_version 70110 (0.0010) -[2023-10-12 06:11:42,994][78091] Updated weights for policy 0, policy_version 70440 (0.0010) -[2023-10-12 06:11:43,364][78091] Updated weights for policy 0, policy_version 70450 (0.0011) -[2023-10-12 06:11:43,745][78091] Updated weights for policy 0, policy_version 70460 (0.0008) -[2023-10-12 06:11:45,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 143949824. Throughput: 0: 1615.2, 1: 1572.9. Samples: 35992534. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 06:11:45,202][77203] Avg episode reward: [(0, '51.570'), (1, '58.410')] -[2023-10-12 06:11:45,702][78123] Updated weights for policy 1, policy_version 70120 (0.0007) -[2023-10-12 06:11:46,064][78123] Updated weights for policy 1, policy_version 70130 (0.0008) -[2023-10-12 06:11:46,439][78123] Updated weights for policy 1, policy_version 70140 (0.0010) -[2023-10-12 06:11:48,208][78091] Updated weights for policy 0, policy_version 70470 (0.0009) -[2023-10-12 06:11:48,588][78091] Updated weights for policy 0, policy_version 70480 (0.0008) -[2023-10-12 06:11:48,955][78091] Updated weights for policy 0, policy_version 70490 (0.0007) -[2023-10-12 06:11:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 144015360. Throughput: 0: 1599.7, 1: 1575.0. Samples: 36011370. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 06:11:50,201][77203] Avg episode reward: [(0, '52.970'), (1, '43.370')] -[2023-10-12 06:11:50,827][78123] Updated weights for policy 1, policy_version 70150 (0.0007) -[2023-10-12 06:11:51,204][78123] Updated weights for policy 1, policy_version 70160 (0.0007) -[2023-10-12 06:11:51,574][78123] Updated weights for policy 1, policy_version 70170 (0.0008) -[2023-10-12 06:11:53,247][78091] Updated weights for policy 0, policy_version 70500 (0.0008) -[2023-10-12 06:11:53,610][78091] Updated weights for policy 0, policy_version 70510 (0.0011) -[2023-10-12 06:11:53,988][78091] Updated weights for policy 0, policy_version 70520 (0.0010) -[2023-10-12 06:11:55,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 144080896. Throughput: 0: 1587.3, 1: 1589.4. Samples: 36030454. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 06:11:55,202][77203] Avg episode reward: [(0, '52.560'), (1, '47.760')] -[2023-10-12 06:11:55,745][78123] Updated weights for policy 1, policy_version 70180 (0.0007) -[2023-10-12 06:11:56,107][78123] Updated weights for policy 1, policy_version 70190 (0.0008) -[2023-10-12 06:11:56,469][78123] Updated weights for policy 1, policy_version 70200 (0.0007) -[2023-10-12 06:11:58,309][78091] Updated weights for policy 0, policy_version 70530 (0.0009) -[2023-10-12 06:11:58,682][78091] Updated weights for policy 0, policy_version 70540 (0.0008) -[2023-10-12 06:11:59,051][78091] Updated weights for policy 0, policy_version 70550 (0.0009) -[2023-10-12 06:11:59,421][78091] Updated weights for policy 0, policy_version 70560 (0.0008) -[2023-10-12 06:12:00,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 144146432. Throughput: 0: 1607.8, 1: 1582.7. Samples: 36040304. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 06:12:00,201][77203] Avg episode reward: [(0, '55.400'), (1, '47.980')] -[2023-10-12 06:12:00,878][78123] Updated weights for policy 1, policy_version 70210 (0.0007) -[2023-10-12 06:12:01,240][78123] Updated weights for policy 1, policy_version 70220 (0.0007) -[2023-10-12 06:12:01,607][78123] Updated weights for policy 1, policy_version 70230 (0.0010) -[2023-10-12 06:12:01,978][78123] Updated weights for policy 1, policy_version 70240 (0.0008) -[2023-10-12 06:12:03,807][78091] Updated weights for policy 0, policy_version 70570 (0.0007) -[2023-10-12 06:12:04,185][78091] Updated weights for policy 0, policy_version 70580 (0.0010) -[2023-10-12 06:12:04,561][78091] Updated weights for policy 0, policy_version 70590 (0.0007) -[2023-10-12 06:12:05,201][77203] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 144211968. Throughput: 0: 1607.8, 1: 1581.3. Samples: 36059430. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 06:12:05,201][77203] Avg episode reward: [(0, '57.360'), (1, '60.040')] -[2023-10-12 06:12:06,233][78123] Updated weights for policy 1, policy_version 70250 (0.0009) -[2023-10-12 06:12:06,601][78123] Updated weights for policy 1, policy_version 70260 (0.0009) -[2023-10-12 06:12:06,978][78123] Updated weights for policy 1, policy_version 70270 (0.0008) -[2023-10-12 06:12:08,839][78091] Updated weights for policy 0, policy_version 70600 (0.0010) -[2023-10-12 06:12:09,215][78091] Updated weights for policy 0, policy_version 70610 (0.0008) -[2023-10-12 06:12:09,586][78091] Updated weights for policy 0, policy_version 70620 (0.0008) -[2023-10-12 06:12:10,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 144277504. Throughput: 0: 1587.8, 1: 1587.1. Samples: 36078398. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 06:12:10,201][77203] Avg episode reward: [(0, '59.070'), (1, '52.290')] -[2023-10-12 06:12:11,235][78123] Updated weights for policy 1, policy_version 70280 (0.0008) -[2023-10-12 06:12:11,603][78123] Updated weights for policy 1, policy_version 70290 (0.0007) -[2023-10-12 06:12:11,966][78123] Updated weights for policy 1, policy_version 70300 (0.0007) -[2023-10-12 06:12:14,022][78091] Updated weights for policy 0, policy_version 70630 (0.0010) -[2023-10-12 06:12:14,415][78091] Updated weights for policy 0, policy_version 70640 (0.0009) -[2023-10-12 06:12:14,790][78091] Updated weights for policy 0, policy_version 70650 (0.0008) -[2023-10-12 06:12:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 144343040. Throughput: 0: 1601.8, 1: 1587.4. Samples: 36088370. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 06:12:15,201][77203] Avg episode reward: [(0, '60.580'), (1, '44.510')] -[2023-10-12 06:12:16,332][78123] Updated weights for policy 1, policy_version 70310 (0.0008) -[2023-10-12 06:12:16,705][78123] Updated weights for policy 1, policy_version 70320 (0.0007) -[2023-10-12 06:12:17,073][78123] Updated weights for policy 1, policy_version 70330 (0.0009) -[2023-10-12 06:12:19,122][78091] Updated weights for policy 0, policy_version 70660 (0.0009) -[2023-10-12 06:12:19,489][78091] Updated weights for policy 0, policy_version 70670 (0.0009) -[2023-10-12 06:12:19,863][78091] Updated weights for policy 0, policy_version 70680 (0.0008) -[2023-10-12 06:12:20,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 144408576. Throughput: 0: 1616.6, 1: 1586.8. Samples: 36107644. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 06:12:20,201][77203] Avg episode reward: [(0, '56.800'), (1, '49.510')] -[2023-10-12 06:12:21,228][78123] Updated weights for policy 1, policy_version 70340 (0.0007) -[2023-10-12 06:12:21,587][78123] Updated weights for policy 1, policy_version 70350 (0.0011) -[2023-10-12 06:12:21,953][78123] Updated weights for policy 1, policy_version 70360 (0.0009) -[2023-10-12 06:12:23,989][78091] Updated weights for policy 0, policy_version 70690 (0.0008) -[2023-10-12 06:12:24,351][78091] Updated weights for policy 0, policy_version 70700 (0.0009) -[2023-10-12 06:12:24,719][78091] Updated weights for policy 0, policy_version 70710 (0.0007) -[2023-10-12 06:12:25,093][78091] Updated weights for policy 0, policy_version 70720 (0.0008) -[2023-10-12 06:12:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 144474112. Throughput: 0: 1598.5, 1: 1591.8. Samples: 36126440. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-12 06:12:25,201][77203] Avg episode reward: [(0, '54.360'), (1, '56.570')] -[2023-10-12 06:12:26,325][78123] Updated weights for policy 1, policy_version 70370 (0.0009) -[2023-10-12 06:12:26,687][78123] Updated weights for policy 1, policy_version 70380 (0.0007) -[2023-10-12 06:12:27,055][78123] Updated weights for policy 1, policy_version 70390 (0.0007) -[2023-10-12 06:12:27,435][78123] Updated weights for policy 1, policy_version 70400 (0.0010) -[2023-10-12 06:12:29,226][78091] Updated weights for policy 0, policy_version 70730 (0.0008) -[2023-10-12 06:12:29,609][78091] Updated weights for policy 0, policy_version 70740 (0.0009) -[2023-10-12 06:12:29,979][78091] Updated weights for policy 0, policy_version 70750 (0.0009) -[2023-10-12 06:12:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 144539648. Throughput: 0: 1594.0, 1: 1595.2. Samples: 36136050. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-12 06:12:30,201][77203] Avg episode reward: [(0, '64.960'), (1, '52.780')] -[2023-10-12 06:12:31,773][78123] Updated weights for policy 1, policy_version 70410 (0.0010) -[2023-10-12 06:12:32,149][78123] Updated weights for policy 1, policy_version 70420 (0.0008) -[2023-10-12 06:12:32,514][78123] Updated weights for policy 1, policy_version 70430 (0.0007) -[2023-10-12 06:12:34,151][78091] Updated weights for policy 0, policy_version 70760 (0.0010) -[2023-10-12 06:12:34,514][78091] Updated weights for policy 0, policy_version 70770 (0.0010) -[2023-10-12 06:12:34,882][78091] Updated weights for policy 0, policy_version 70780 (0.0010) -[2023-10-12 06:12:35,201][77203] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 144605184. Throughput: 0: 1612.4, 1: 1597.1. Samples: 36155802. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-12 06:12:35,202][77203] Avg episode reward: [(0, '65.930'), (1, '45.800')] -[2023-10-12 06:12:36,807][78123] Updated weights for policy 1, policy_version 70440 (0.0009) -[2023-10-12 06:12:37,173][78123] Updated weights for policy 1, policy_version 70450 (0.0010) -[2023-10-12 06:12:37,542][78123] Updated weights for policy 1, policy_version 70460 (0.0011) -[2023-10-12 06:12:39,390][78091] Updated weights for policy 0, policy_version 70790 (0.0010) -[2023-10-12 06:12:39,755][78091] Updated weights for policy 0, policy_version 70800 (0.0008) -[2023-10-12 06:12:40,126][78091] Updated weights for policy 0, policy_version 70810 (0.0008) -[2023-10-12 06:12:40,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 144637952. Throughput: 0: 1605.6, 1: 1600.1. Samples: 36174712. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-12 06:12:40,202][77203] Avg episode reward: [(0, '56.540'), (1, '45.810')] -[2023-10-12 06:12:42,071][78123] Updated weights for policy 1, policy_version 70470 (0.0007) -[2023-10-12 06:12:42,449][78123] Updated weights for policy 1, policy_version 70480 (0.0008) -[2023-10-12 06:12:42,821][78123] Updated weights for policy 1, policy_version 70490 (0.0008) -[2023-10-12 06:12:44,350][78091] Updated weights for policy 0, policy_version 70820 (0.0010) -[2023-10-12 06:12:44,726][78091] Updated weights for policy 0, policy_version 70830 (0.0009) -[2023-10-12 06:12:45,089][78091] Updated weights for policy 0, policy_version 70840 (0.0009) -[2023-10-12 06:12:45,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 144703488. Throughput: 0: 1596.6, 1: 1606.5. Samples: 36184444. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-12 06:12:45,202][77203] Avg episode reward: [(0, '51.870'), (1, '46.820')] -[2023-10-12 06:12:47,020][78123] Updated weights for policy 1, policy_version 70500 (0.0008) -[2023-10-12 06:12:47,391][78123] Updated weights for policy 1, policy_version 70510 (0.0008) -[2023-10-12 06:12:47,747][78123] Updated weights for policy 1, policy_version 70520 (0.0007) -[2023-10-12 06:12:49,323][78091] Updated weights for policy 0, policy_version 70850 (0.0009) -[2023-10-12 06:12:49,692][78091] Updated weights for policy 0, policy_version 70860 (0.0008) -[2023-10-12 06:12:50,065][78091] Updated weights for policy 0, policy_version 70870 (0.0009) -[2023-10-12 06:12:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 144769024. Throughput: 0: 1607.3, 1: 1600.4. Samples: 36203778. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-12 06:12:50,202][77203] Avg episode reward: [(0, '57.560'), (1, '55.190')] -[2023-10-12 06:12:50,433][78091] Updated weights for policy 0, policy_version 70880 (0.0009) -[2023-10-12 06:12:51,974][78123] Updated weights for policy 1, policy_version 70530 (0.0007) -[2023-10-12 06:12:52,346][78123] Updated weights for policy 1, policy_version 70540 (0.0009) -[2023-10-12 06:12:52,703][78123] Updated weights for policy 1, policy_version 70550 (0.0010) -[2023-10-12 06:12:53,075][78123] Updated weights for policy 1, policy_version 70560 (0.0010) -[2023-10-12 06:12:54,687][78091] Updated weights for policy 0, policy_version 70890 (0.0009) -[2023-10-12 06:12:55,057][78091] Updated weights for policy 0, policy_version 70900 (0.0008) -[2023-10-12 06:12:55,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 144834560. Throughput: 0: 1615.9, 1: 1602.5. Samples: 36223226. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-12 06:12:55,202][77203] Avg episode reward: [(0, '57.150'), (1, '49.240')] -[2023-10-12 06:12:55,436][78091] Updated weights for policy 0, policy_version 70910 (0.0007) -[2023-10-12 06:12:57,246][78123] Updated weights for policy 1, policy_version 70570 (0.0008) -[2023-10-12 06:12:57,614][78123] Updated weights for policy 1, policy_version 70580 (0.0009) -[2023-10-12 06:12:57,981][78123] Updated weights for policy 1, policy_version 70590 (0.0007) -[2023-10-12 06:12:59,920][78091] Updated weights for policy 0, policy_version 70920 (0.0010) -[2023-10-12 06:13:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 144900096. Throughput: 0: 1595.6, 1: 1610.7. Samples: 36232652. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-12 06:13:00,202][77203] Avg episode reward: [(0, '47.670'), (1, '51.130')] -[2023-10-12 06:13:00,293][78091] Updated weights for policy 0, policy_version 70930 (0.0009) -[2023-10-12 06:13:00,666][78091] Updated weights for policy 0, policy_version 70940 (0.0008) -[2023-10-12 06:13:02,188][78123] Updated weights for policy 1, policy_version 70600 (0.0007) -[2023-10-12 06:13:02,562][78123] Updated weights for policy 1, policy_version 70610 (0.0009) -[2023-10-12 06:13:02,925][78123] Updated weights for policy 1, policy_version 70620 (0.0009) -[2023-10-12 06:13:05,074][78091] Updated weights for policy 0, policy_version 70950 (0.0008) -[2023-10-12 06:13:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 144965632. Throughput: 0: 1594.9, 1: 1605.0. Samples: 36251640. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-12 06:13:05,202][77203] Avg episode reward: [(0, '49.980'), (1, '46.430')] -[2023-10-12 06:13:05,462][78091] Updated weights for policy 0, policy_version 70960 (0.0007) -[2023-10-12 06:13:05,834][78091] Updated weights for policy 0, policy_version 70970 (0.0008) -[2023-10-12 06:13:07,357][78123] Updated weights for policy 1, policy_version 70630 (0.0009) -[2023-10-12 06:13:07,722][78123] Updated weights for policy 1, policy_version 70640 (0.0009) -[2023-10-12 06:13:08,094][78123] Updated weights for policy 1, policy_version 70650 (0.0007) -[2023-10-12 06:13:10,201][77203] Fps is (10 sec: 13106.8, 60 sec: 12561.0, 300 sec: 12773.9). Total num frames: 145031168. Throughput: 0: 1611.3, 1: 1604.2. Samples: 36271138. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-12 06:13:10,202][77203] Avg episode reward: [(0, '56.150'), (1, '45.030')] -[2023-10-12 06:13:10,211][78091] Updated weights for policy 0, policy_version 70980 (0.0007) -[2023-10-12 06:13:10,212][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000070656_72351744.pth... -[2023-10-12 06:13:10,251][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000069152_70811648.pth -[2023-10-12 06:13:10,583][78091] Updated weights for policy 0, policy_version 70990 (0.0008) -[2023-10-12 06:13:10,948][78091] Updated weights for policy 0, policy_version 71000 (0.0008) -[2023-10-12 06:13:11,241][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000071008_72712192.pth... -[2023-10-12 06:13:11,280][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000069504_71172096.pth -[2023-10-12 06:13:12,211][78123] Updated weights for policy 1, policy_version 70660 (0.0009) -[2023-10-12 06:13:12,583][78123] Updated weights for policy 1, policy_version 70670 (0.0008) -[2023-10-12 06:13:12,947][78123] Updated weights for policy 1, policy_version 70680 (0.0007) -[2023-10-12 06:13:15,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 145096704. Throughput: 0: 1591.2, 1: 1617.6. Samples: 36280446. Policy #0 lag: (min: 30.0, avg: 44.9, max: 62.0) -[2023-10-12 06:13:15,202][77203] Avg episode reward: [(0, '55.680'), (1, '49.230')] -[2023-10-12 06:13:15,263][78091] Updated weights for policy 0, policy_version 71010 (0.0008) -[2023-10-12 06:13:15,633][78091] Updated weights for policy 0, policy_version 71020 (0.0007) -[2023-10-12 06:13:16,012][78091] Updated weights for policy 0, policy_version 71030 (0.0008) -[2023-10-12 06:13:16,385][78091] Updated weights for policy 0, policy_version 71040 (0.0007) -[2023-10-12 06:13:17,529][78123] Updated weights for policy 1, policy_version 70690 (0.0008) -[2023-10-12 06:13:17,899][78123] Updated weights for policy 1, policy_version 70700 (0.0007) -[2023-10-12 06:13:18,269][78123] Updated weights for policy 1, policy_version 70710 (0.0010) -[2023-10-12 06:13:18,638][78123] Updated weights for policy 1, policy_version 70720 (0.0008) -[2023-10-12 06:13:20,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 145162240. Throughput: 0: 1589.9, 1: 1598.0. Samples: 36299260. Policy #0 lag: (min: 30.0, avg: 44.9, max: 62.0) -[2023-10-12 06:13:20,202][77203] Avg episode reward: [(0, '61.440'), (1, '58.370')] -[2023-10-12 06:13:20,830][78091] Updated weights for policy 0, policy_version 71050 (0.0010) -[2023-10-12 06:13:21,194][78091] Updated weights for policy 0, policy_version 71060 (0.0010) -[2023-10-12 06:13:21,567][78091] Updated weights for policy 0, policy_version 71070 (0.0010) -[2023-10-12 06:13:22,989][78123] Updated weights for policy 1, policy_version 70730 (0.0007) -[2023-10-12 06:13:23,359][78123] Updated weights for policy 1, policy_version 70740 (0.0007) -[2023-10-12 06:13:23,732][78123] Updated weights for policy 1, policy_version 70750 (0.0008) -[2023-10-12 06:13:25,201][77203] Fps is (10 sec: 13107.6, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 145227776. Throughput: 0: 1607.1, 1: 1592.0. Samples: 36318670. Policy #0 lag: (min: 30.0, avg: 44.9, max: 62.0) -[2023-10-12 06:13:25,201][77203] Avg episode reward: [(0, '58.040'), (1, '45.980')] -[2023-10-12 06:13:25,765][78091] Updated weights for policy 0, policy_version 71080 (0.0010) -[2023-10-12 06:13:26,144][78091] Updated weights for policy 0, policy_version 71090 (0.0007) -[2023-10-12 06:13:26,519][78091] Updated weights for policy 0, policy_version 71100 (0.0007) -[2023-10-12 06:13:28,072][78123] Updated weights for policy 1, policy_version 70760 (0.0008) -[2023-10-12 06:13:28,441][78123] Updated weights for policy 1, policy_version 70770 (0.0009) -[2023-10-12 06:13:28,806][78123] Updated weights for policy 1, policy_version 70780 (0.0010) -[2023-10-12 06:13:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 145293312. Throughput: 0: 1590.6, 1: 1612.1. Samples: 36328566. Policy #0 lag: (min: 30.0, avg: 44.9, max: 62.0) -[2023-10-12 06:13:30,202][77203] Avg episode reward: [(0, '58.050'), (1, '47.180')] -[2023-10-12 06:13:30,755][78091] Updated weights for policy 0, policy_version 71110 (0.0008) -[2023-10-12 06:13:31,127][78091] Updated weights for policy 0, policy_version 71120 (0.0009) -[2023-10-12 06:13:31,501][78091] Updated weights for policy 0, policy_version 71130 (0.0008) -[2023-10-12 06:13:33,200][78123] Updated weights for policy 1, policy_version 70790 (0.0008) -[2023-10-12 06:13:33,576][78123] Updated weights for policy 1, policy_version 70800 (0.0007) -[2023-10-12 06:13:33,950][78123] Updated weights for policy 1, policy_version 70810 (0.0007) -[2023-10-12 06:13:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 145358848. Throughput: 0: 1589.0, 1: 1596.8. Samples: 36347138. Policy #0 lag: (min: 30.0, avg: 44.9, max: 62.0) -[2023-10-12 06:13:35,201][77203] Avg episode reward: [(0, '58.620'), (1, '51.680')] -[2023-10-12 06:13:35,659][78091] Updated weights for policy 0, policy_version 71140 (0.0009) -[2023-10-12 06:13:36,031][78091] Updated weights for policy 0, policy_version 71150 (0.0009) -[2023-10-12 06:13:36,396][78091] Updated weights for policy 0, policy_version 71160 (0.0010) -[2023-10-12 06:13:38,414][78123] Updated weights for policy 1, policy_version 70820 (0.0008) -[2023-10-12 06:13:38,777][78123] Updated weights for policy 1, policy_version 70830 (0.0007) -[2023-10-12 06:13:39,149][78123] Updated weights for policy 1, policy_version 70840 (0.0009) -[2023-10-12 06:13:40,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 145424384. Throughput: 0: 1598.7, 1: 1579.4. Samples: 36366242. Policy #0 lag: (min: 30.0, avg: 44.9, max: 62.0) -[2023-10-12 06:13:40,203][77203] Avg episode reward: [(0, '55.700'), (1, '49.070')] -[2023-10-12 06:13:40,718][78091] Updated weights for policy 0, policy_version 71170 (0.0009) -[2023-10-12 06:13:41,090][78091] Updated weights for policy 0, policy_version 71180 (0.0007) -[2023-10-12 06:13:41,470][78091] Updated weights for policy 0, policy_version 71190 (0.0007) -[2023-10-12 06:13:41,837][78091] Updated weights for policy 0, policy_version 71200 (0.0007) -[2023-10-12 06:13:43,230][78123] Updated weights for policy 1, policy_version 70850 (0.0009) -[2023-10-12 06:13:43,597][78123] Updated weights for policy 1, policy_version 70860 (0.0009) -[2023-10-12 06:13:43,961][78123] Updated weights for policy 1, policy_version 70870 (0.0009) -[2023-10-12 06:13:44,324][78123] Updated weights for policy 1, policy_version 70880 (0.0007) -[2023-10-12 06:13:45,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 145489920. Throughput: 0: 1588.4, 1: 1599.8. Samples: 36376122. Policy #0 lag: (min: 30.0, avg: 44.9, max: 62.0) -[2023-10-12 06:13:45,202][77203] Avg episode reward: [(0, '57.530'), (1, '56.490')] -[2023-10-12 06:13:46,135][78091] Updated weights for policy 0, policy_version 71210 (0.0008) -[2023-10-12 06:13:46,506][78091] Updated weights for policy 0, policy_version 71220 (0.0008) -[2023-10-12 06:13:46,884][78091] Updated weights for policy 0, policy_version 71230 (0.0009) -[2023-10-12 06:13:48,790][78123] Updated weights for policy 1, policy_version 70890 (0.0008) -[2023-10-12 06:13:49,161][78123] Updated weights for policy 1, policy_version 70900 (0.0009) -[2023-10-12 06:13:49,537][78123] Updated weights for policy 1, policy_version 70910 (0.0009) -[2023-10-12 06:13:50,201][77203] Fps is (10 sec: 13107.8, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 145555456. Throughput: 0: 1595.0, 1: 1599.5. Samples: 36395390. Policy #0 lag: (min: 30.0, avg: 44.9, max: 62.0) -[2023-10-12 06:13:50,201][77203] Avg episode reward: [(0, '49.840'), (1, '46.940')] -[2023-10-12 06:13:51,055][78091] Updated weights for policy 0, policy_version 71240 (0.0007) -[2023-10-12 06:13:51,430][78091] Updated weights for policy 0, policy_version 71250 (0.0008) -[2023-10-12 06:13:51,804][78091] Updated weights for policy 0, policy_version 71260 (0.0010) -[2023-10-12 06:13:53,991][78123] Updated weights for policy 1, policy_version 70920 (0.0008) -[2023-10-12 06:13:54,361][78123] Updated weights for policy 1, policy_version 70930 (0.0007) -[2023-10-12 06:13:54,717][78123] Updated weights for policy 1, policy_version 70940 (0.0007) -[2023-10-12 06:13:55,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 145620992. Throughput: 0: 1599.1, 1: 1581.4. Samples: 36414260. Policy #0 lag: (min: 30.0, avg: 44.9, max: 62.0) -[2023-10-12 06:13:55,202][77203] Avg episode reward: [(0, '56.590'), (1, '56.790')] -[2023-10-12 06:13:56,215][78091] Updated weights for policy 0, policy_version 71270 (0.0010) -[2023-10-12 06:13:56,589][78091] Updated weights for policy 0, policy_version 71280 (0.0011) -[2023-10-12 06:13:56,964][78091] Updated weights for policy 0, policy_version 71290 (0.0009) -[2023-10-12 06:13:59,160][78123] Updated weights for policy 1, policy_version 70950 (0.0009) -[2023-10-12 06:13:59,515][78123] Updated weights for policy 1, policy_version 70960 (0.0010) -[2023-10-12 06:13:59,881][78123] Updated weights for policy 1, policy_version 70970 (0.0008) -[2023-10-12 06:14:00,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 145686528. Throughput: 0: 1597.7, 1: 1588.4. Samples: 36423820. Policy #0 lag: (min: 16.0, avg: 33.6, max: 48.0) -[2023-10-12 06:14:00,201][77203] Avg episode reward: [(0, '62.070'), (1, '50.400')] -[2023-10-12 06:14:01,149][78091] Updated weights for policy 0, policy_version 71300 (0.0007) -[2023-10-12 06:14:01,526][78091] Updated weights for policy 0, policy_version 71310 (0.0011) -[2023-10-12 06:14:01,889][78091] Updated weights for policy 0, policy_version 71320 (0.0010) -[2023-10-12 06:14:04,128][78123] Updated weights for policy 1, policy_version 70980 (0.0008) -[2023-10-12 06:14:04,500][78123] Updated weights for policy 1, policy_version 70990 (0.0009) -[2023-10-12 06:14:04,862][78123] Updated weights for policy 1, policy_version 71000 (0.0007) -[2023-10-12 06:14:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 145752064. Throughput: 0: 1597.6, 1: 1605.0. Samples: 36443378. Policy #0 lag: (min: 16.0, avg: 33.6, max: 48.0) -[2023-10-12 06:14:05,202][77203] Avg episode reward: [(0, '62.990'), (1, '49.150')] -[2023-10-12 06:14:06,253][78091] Updated weights for policy 0, policy_version 71330 (0.0009) -[2023-10-12 06:14:06,624][78091] Updated weights for policy 0, policy_version 71340 (0.0009) -[2023-10-12 06:14:06,994][78091] Updated weights for policy 0, policy_version 71350 (0.0009) -[2023-10-12 06:14:07,358][78091] Updated weights for policy 0, policy_version 71360 (0.0007) -[2023-10-12 06:14:09,349][78123] Updated weights for policy 1, policy_version 71010 (0.0008) -[2023-10-12 06:14:09,772][78123] Updated weights for policy 1, policy_version 71020 (0.0009) -[2023-10-12 06:14:10,134][78123] Updated weights for policy 1, policy_version 71030 (0.0008) -[2023-10-12 06:14:10,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 145784832. Throughput: 0: 1602.7, 1: 1590.8. Samples: 36462378. Policy #0 lag: (min: 16.0, avg: 33.6, max: 48.0) -[2023-10-12 06:14:10,201][77203] Avg episode reward: [(0, '58.000'), (1, '53.110')] -[2023-10-12 06:14:10,500][78123] Updated weights for policy 1, policy_version 71040 (0.0010) -[2023-10-12 06:14:11,683][78091] Updated weights for policy 0, policy_version 71370 (0.0010) -[2023-10-12 06:14:12,058][78091] Updated weights for policy 0, policy_version 71380 (0.0009) -[2023-10-12 06:14:12,426][78091] Updated weights for policy 0, policy_version 71390 (0.0008) -[2023-10-12 06:14:14,932][78123] Updated weights for policy 1, policy_version 71050 (0.0010) -[2023-10-12 06:14:15,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 145850368. Throughput: 0: 1603.6, 1: 1569.3. Samples: 36471346. Policy #0 lag: (min: 16.0, avg: 33.6, max: 48.0) -[2023-10-12 06:14:15,201][77203] Avg episode reward: [(0, '53.620'), (1, '53.410')] -[2023-10-12 06:14:15,303][78123] Updated weights for policy 1, policy_version 71060 (0.0007) -[2023-10-12 06:14:15,668][78123] Updated weights for policy 1, policy_version 71070 (0.0007) -[2023-10-12 06:14:16,766][78091] Updated weights for policy 0, policy_version 71400 (0.0009) -[2023-10-12 06:14:17,133][78091] Updated weights for policy 0, policy_version 71410 (0.0008) -[2023-10-12 06:14:17,505][78091] Updated weights for policy 0, policy_version 71420 (0.0008) -[2023-10-12 06:14:19,997][78123] Updated weights for policy 1, policy_version 71080 (0.0007) -[2023-10-12 06:14:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 145915904. Throughput: 0: 1603.7, 1: 1592.8. Samples: 36490980. Policy #0 lag: (min: 16.0, avg: 33.6, max: 48.0) -[2023-10-12 06:14:20,201][77203] Avg episode reward: [(0, '60.690'), (1, '51.460')] -[2023-10-12 06:14:20,366][78123] Updated weights for policy 1, policy_version 71090 (0.0007) -[2023-10-12 06:14:20,742][78123] Updated weights for policy 1, policy_version 71100 (0.0008) -[2023-10-12 06:14:21,799][78091] Updated weights for policy 0, policy_version 71430 (0.0008) -[2023-10-12 06:14:22,159][78091] Updated weights for policy 0, policy_version 71440 (0.0008) -[2023-10-12 06:14:22,526][78091] Updated weights for policy 0, policy_version 71450 (0.0011) -[2023-10-12 06:14:24,990][78123] Updated weights for policy 1, policy_version 71110 (0.0008) -[2023-10-12 06:14:25,201][77203] Fps is (10 sec: 13106.8, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 145981440. Throughput: 0: 1604.2, 1: 1603.4. Samples: 36510586. Policy #0 lag: (min: 16.0, avg: 33.6, max: 48.0) -[2023-10-12 06:14:25,202][77203] Avg episode reward: [(0, '55.250'), (1, '43.470')] -[2023-10-12 06:14:25,355][78123] Updated weights for policy 1, policy_version 71120 (0.0010) -[2023-10-12 06:14:25,725][78123] Updated weights for policy 1, policy_version 71130 (0.0010) -[2023-10-12 06:14:26,568][78091] Updated weights for policy 0, policy_version 71460 (0.0010) -[2023-10-12 06:14:26,940][78091] Updated weights for policy 0, policy_version 71470 (0.0007) -[2023-10-12 06:14:27,312][78091] Updated weights for policy 0, policy_version 71480 (0.0007) -[2023-10-12 06:14:30,128][78123] Updated weights for policy 1, policy_version 71140 (0.0009) -[2023-10-12 06:14:30,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 146046976. Throughput: 0: 1607.9, 1: 1573.8. Samples: 36519298. Policy #0 lag: (min: 16.0, avg: 33.6, max: 48.0) -[2023-10-12 06:14:30,201][77203] Avg episode reward: [(0, '50.730'), (1, '48.250')] -[2023-10-12 06:14:30,493][78123] Updated weights for policy 1, policy_version 71150 (0.0008) -[2023-10-12 06:14:30,852][78123] Updated weights for policy 1, policy_version 71160 (0.0008) -[2023-10-12 06:14:31,687][78091] Updated weights for policy 0, policy_version 71490 (0.0008) -[2023-10-12 06:14:32,082][78091] Updated weights for policy 0, policy_version 71500 (0.0007) -[2023-10-12 06:14:32,448][78091] Updated weights for policy 0, policy_version 71510 (0.0009) -[2023-10-12 06:14:32,822][78091] Updated weights for policy 0, policy_version 71520 (0.0011) -[2023-10-12 06:14:35,148][78123] Updated weights for policy 1, policy_version 71170 (0.0008) -[2023-10-12 06:14:35,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 146112512. Throughput: 0: 1603.7, 1: 1582.3. Samples: 36538760. Policy #0 lag: (min: 16.0, avg: 33.6, max: 48.0) -[2023-10-12 06:14:35,201][77203] Avg episode reward: [(0, '59.010'), (1, '52.360')] -[2023-10-12 06:14:35,509][78123] Updated weights for policy 1, policy_version 71180 (0.0010) -[2023-10-12 06:14:35,880][78123] Updated weights for policy 1, policy_version 71190 (0.0007) -[2023-10-12 06:14:36,247][78123] Updated weights for policy 1, policy_version 71200 (0.0008) -[2023-10-12 06:14:37,239][78091] Updated weights for policy 0, policy_version 71530 (0.0009) -[2023-10-12 06:14:37,614][78091] Updated weights for policy 0, policy_version 71540 (0.0010) -[2023-10-12 06:14:37,990][78091] Updated weights for policy 0, policy_version 71550 (0.0010) -[2023-10-12 06:14:40,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 146178048. Throughput: 0: 1600.0, 1: 1596.0. Samples: 36558082. Policy #0 lag: (min: 16.0, avg: 33.6, max: 48.0) -[2023-10-12 06:14:40,202][77203] Avg episode reward: [(0, '53.640'), (1, '50.660')] -[2023-10-12 06:14:40,668][78123] Updated weights for policy 1, policy_version 71210 (0.0010) -[2023-10-12 06:14:41,037][78123] Updated weights for policy 1, policy_version 71220 (0.0008) -[2023-10-12 06:14:41,409][78123] Updated weights for policy 1, policy_version 71230 (0.0007) -[2023-10-12 06:14:42,314][78091] Updated weights for policy 0, policy_version 71560 (0.0010) -[2023-10-12 06:14:42,687][78091] Updated weights for policy 0, policy_version 71570 (0.0007) -[2023-10-12 06:14:43,064][78091] Updated weights for policy 0, policy_version 71580 (0.0007) -[2023-10-12 06:14:45,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 146243584. Throughput: 0: 1612.7, 1: 1574.2. Samples: 36567232. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-12 06:14:45,202][77203] Avg episode reward: [(0, '62.490'), (1, '40.140')] -[2023-10-12 06:14:45,800][78123] Updated weights for policy 1, policy_version 71240 (0.0008) -[2023-10-12 06:14:46,173][78123] Updated weights for policy 1, policy_version 71250 (0.0008) -[2023-10-12 06:14:46,542][78123] Updated weights for policy 1, policy_version 71260 (0.0008) -[2023-10-12 06:14:47,327][78091] Updated weights for policy 0, policy_version 71590 (0.0008) -[2023-10-12 06:14:47,688][78091] Updated weights for policy 0, policy_version 71600 (0.0010) -[2023-10-12 06:14:48,058][78091] Updated weights for policy 0, policy_version 71610 (0.0011) -[2023-10-12 06:14:50,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 146309120. Throughput: 0: 1598.2, 1: 1575.2. Samples: 36586182. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-12 06:14:50,202][77203] Avg episode reward: [(0, '59.250'), (1, '49.130')] -[2023-10-12 06:14:50,798][78123] Updated weights for policy 1, policy_version 71270 (0.0008) -[2023-10-12 06:14:51,158][78123] Updated weights for policy 1, policy_version 71280 (0.0009) -[2023-10-12 06:14:51,538][78123] Updated weights for policy 1, policy_version 71290 (0.0009) -[2023-10-12 06:14:52,415][78091] Updated weights for policy 0, policy_version 71620 (0.0008) -[2023-10-12 06:14:52,779][78091] Updated weights for policy 0, policy_version 71630 (0.0007) -[2023-10-12 06:14:53,157][78091] Updated weights for policy 0, policy_version 71640 (0.0007) -[2023-10-12 06:14:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 146374656. Throughput: 0: 1590.9, 1: 1589.4. Samples: 36605492. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-12 06:14:55,202][77203] Avg episode reward: [(0, '61.910'), (1, '53.490')] -[2023-10-12 06:14:55,821][78123] Updated weights for policy 1, policy_version 71300 (0.0009) -[2023-10-12 06:14:56,215][78123] Updated weights for policy 1, policy_version 71310 (0.0009) -[2023-10-12 06:14:56,583][78123] Updated weights for policy 1, policy_version 71320 (0.0009) -[2023-10-12 06:14:57,420][78091] Updated weights for policy 0, policy_version 71650 (0.0010) -[2023-10-12 06:14:57,786][78091] Updated weights for policy 0, policy_version 71660 (0.0009) -[2023-10-12 06:14:58,159][78091] Updated weights for policy 0, policy_version 71670 (0.0007) -[2023-10-12 06:14:58,527][78091] Updated weights for policy 0, policy_version 71680 (0.0009) -[2023-10-12 06:15:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 146440192. Throughput: 0: 1610.1, 1: 1579.2. Samples: 36614868. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-12 06:15:00,202][77203] Avg episode reward: [(0, '49.960'), (1, '54.440')] -[2023-10-12 06:15:00,935][78123] Updated weights for policy 1, policy_version 71330 (0.0010) -[2023-10-12 06:15:01,304][78123] Updated weights for policy 1, policy_version 71340 (0.0011) -[2023-10-12 06:15:01,676][78123] Updated weights for policy 1, policy_version 71350 (0.0009) -[2023-10-12 06:15:02,049][78123] Updated weights for policy 1, policy_version 71360 (0.0011) -[2023-10-12 06:15:02,801][78091] Updated weights for policy 0, policy_version 71690 (0.0008) -[2023-10-12 06:15:03,169][78091] Updated weights for policy 0, policy_version 71700 (0.0007) -[2023-10-12 06:15:03,539][78091] Updated weights for policy 0, policy_version 71710 (0.0009) -[2023-10-12 06:15:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 146505728. Throughput: 0: 1593.5, 1: 1582.0. Samples: 36633874. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-12 06:15:05,202][77203] Avg episode reward: [(0, '52.860'), (1, '49.730')] -[2023-10-12 06:15:06,391][78123] Updated weights for policy 1, policy_version 71370 (0.0008) -[2023-10-12 06:15:06,749][78123] Updated weights for policy 1, policy_version 71380 (0.0011) -[2023-10-12 06:15:07,120][78123] Updated weights for policy 1, policy_version 71390 (0.0009) -[2023-10-12 06:15:07,828][78091] Updated weights for policy 0, policy_version 71720 (0.0007) -[2023-10-12 06:15:08,197][78091] Updated weights for policy 0, policy_version 71730 (0.0007) -[2023-10-12 06:15:08,571][78091] Updated weights for policy 0, policy_version 71740 (0.0008) -[2023-10-12 06:15:10,201][77203] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 146571264. Throughput: 0: 1593.3, 1: 1582.7. Samples: 36653508. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-12 06:15:10,202][77203] Avg episode reward: [(0, '51.060'), (1, '42.950')] -[2023-10-12 06:15:10,213][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000071744_73465856.pth... -[2023-10-12 06:15:10,213][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000071392_73105408.pth... -[2023-10-12 06:15:10,244][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000069920_71598080.pth -[2023-10-12 06:15:10,251][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000070240_71925760.pth -[2023-10-12 06:15:11,568][78123] Updated weights for policy 1, policy_version 71400 (0.0007) -[2023-10-12 06:15:11,938][78123] Updated weights for policy 1, policy_version 71410 (0.0007) -[2023-10-12 06:15:12,299][78123] Updated weights for policy 1, policy_version 71420 (0.0008) -[2023-10-12 06:15:12,943][78091] Updated weights for policy 0, policy_version 71750 (0.0009) -[2023-10-12 06:15:13,308][78091] Updated weights for policy 0, policy_version 71760 (0.0008) -[2023-10-12 06:15:13,668][78091] Updated weights for policy 0, policy_version 71770 (0.0010) -[2023-10-12 06:15:15,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 146636800. Throughput: 0: 1614.6, 1: 1580.0. Samples: 36663056. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-12 06:15:15,202][77203] Avg episode reward: [(0, '59.210'), (1, '52.370')] -[2023-10-12 06:15:16,657][78123] Updated weights for policy 1, policy_version 71430 (0.0010) -[2023-10-12 06:15:17,023][78123] Updated weights for policy 1, policy_version 71440 (0.0008) -[2023-10-12 06:15:17,402][78123] Updated weights for policy 1, policy_version 71450 (0.0009) -[2023-10-12 06:15:17,958][78091] Updated weights for policy 0, policy_version 71780 (0.0008) -[2023-10-12 06:15:18,352][78091] Updated weights for policy 0, policy_version 71790 (0.0007) -[2023-10-12 06:15:18,727][78091] Updated weights for policy 0, policy_version 71800 (0.0007) -[2023-10-12 06:15:20,201][77203] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 146702336. Throughput: 0: 1596.6, 1: 1580.4. Samples: 36681724. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-12 06:15:20,202][77203] Avg episode reward: [(0, '50.310'), (1, '49.410')] -[2023-10-12 06:15:21,866][78123] Updated weights for policy 1, policy_version 71460 (0.0008) -[2023-10-12 06:15:22,241][78123] Updated weights for policy 1, policy_version 71470 (0.0008) -[2023-10-12 06:15:22,609][78123] Updated weights for policy 1, policy_version 71480 (0.0009) -[2023-10-12 06:15:22,911][78091] Updated weights for policy 0, policy_version 71810 (0.0008) -[2023-10-12 06:15:23,279][78091] Updated weights for policy 0, policy_version 71820 (0.0007) -[2023-10-12 06:15:23,657][78091] Updated weights for policy 0, policy_version 71830 (0.0008) -[2023-10-12 06:15:24,022][78091] Updated weights for policy 0, policy_version 71840 (0.0008) -[2023-10-12 06:15:25,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.3, 300 sec: 12774.0). Total num frames: 146767872. Throughput: 0: 1600.1, 1: 1577.7. Samples: 36701084. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-12 06:15:25,201][77203] Avg episode reward: [(0, '53.240'), (1, '50.000')] -[2023-10-12 06:15:26,807][78123] Updated weights for policy 1, policy_version 71490 (0.0007) -[2023-10-12 06:15:27,172][78123] Updated weights for policy 1, policy_version 71500 (0.0011) -[2023-10-12 06:15:27,540][78123] Updated weights for policy 1, policy_version 71510 (0.0008) -[2023-10-12 06:15:27,901][78123] Updated weights for policy 1, policy_version 71520 (0.0008) -[2023-10-12 06:15:28,413][78091] Updated weights for policy 0, policy_version 71850 (0.0007) -[2023-10-12 06:15:28,771][78091] Updated weights for policy 0, policy_version 71860 (0.0008) -[2023-10-12 06:15:29,143][78091] Updated weights for policy 0, policy_version 71870 (0.0009) -[2023-10-12 06:15:30,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 146833408. Throughput: 0: 1617.8, 1: 1585.2. Samples: 36711364. Policy #0 lag: (min: 26.0, avg: 34.0, max: 58.0) -[2023-10-12 06:15:30,202][77203] Avg episode reward: [(0, '62.820'), (1, '46.100')] -[2023-10-12 06:15:32,120][78123] Updated weights for policy 1, policy_version 71530 (0.0008) -[2023-10-12 06:15:32,484][78123] Updated weights for policy 1, policy_version 71540 (0.0007) -[2023-10-12 06:15:32,843][78123] Updated weights for policy 1, policy_version 71550 (0.0008) -[2023-10-12 06:15:33,274][78091] Updated weights for policy 0, policy_version 71880 (0.0008) -[2023-10-12 06:15:33,646][78091] Updated weights for policy 0, policy_version 71890 (0.0007) -[2023-10-12 06:15:34,015][78091] Updated weights for policy 0, policy_version 71900 (0.0008) -[2023-10-12 06:15:35,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 146898944. Throughput: 0: 1613.4, 1: 1581.1. Samples: 36729932. Policy #0 lag: (min: 26.0, avg: 34.0, max: 58.0) -[2023-10-12 06:15:35,202][77203] Avg episode reward: [(0, '56.540'), (1, '48.330')] -[2023-10-12 06:15:37,184][78123] Updated weights for policy 1, policy_version 71560 (0.0008) -[2023-10-12 06:15:37,544][78123] Updated weights for policy 1, policy_version 71570 (0.0008) -[2023-10-12 06:15:37,903][78123] Updated weights for policy 1, policy_version 71580 (0.0009) -[2023-10-12 06:15:38,292][78091] Updated weights for policy 0, policy_version 71910 (0.0009) -[2023-10-12 06:15:38,658][78091] Updated weights for policy 0, policy_version 71920 (0.0008) -[2023-10-12 06:15:39,029][78091] Updated weights for policy 0, policy_version 71930 (0.0009) -[2023-10-12 06:15:40,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 146964480. Throughput: 0: 1607.1, 1: 1585.7. Samples: 36749166. Policy #0 lag: (min: 26.0, avg: 34.0, max: 58.0) -[2023-10-12 06:15:40,201][77203] Avg episode reward: [(0, '62.330'), (1, '52.320')] -[2023-10-12 06:15:42,322][78123] Updated weights for policy 1, policy_version 71590 (0.0007) -[2023-10-12 06:15:42,681][78123] Updated weights for policy 1, policy_version 71600 (0.0009) -[2023-10-12 06:15:43,051][78123] Updated weights for policy 1, policy_version 71610 (0.0010) -[2023-10-12 06:15:43,191][78091] Updated weights for policy 0, policy_version 71940 (0.0009) -[2023-10-12 06:15:43,552][78091] Updated weights for policy 0, policy_version 71950 (0.0010) -[2023-10-12 06:15:43,919][78091] Updated weights for policy 0, policy_version 71960 (0.0008) -[2023-10-12 06:15:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 147030016. Throughput: 0: 1613.2, 1: 1598.7. Samples: 36759406. Policy #0 lag: (min: 26.0, avg: 34.0, max: 58.0) -[2023-10-12 06:15:45,202][77203] Avg episode reward: [(0, '54.200'), (1, '56.340')] -[2023-10-12 06:15:47,260][78123] Updated weights for policy 1, policy_version 71620 (0.0008) -[2023-10-12 06:15:47,625][78123] Updated weights for policy 1, policy_version 71630 (0.0011) -[2023-10-12 06:15:47,990][78123] Updated weights for policy 1, policy_version 71640 (0.0008) -[2023-10-12 06:15:48,314][78091] Updated weights for policy 0, policy_version 71970 (0.0008) -[2023-10-12 06:15:48,686][78091] Updated weights for policy 0, policy_version 71980 (0.0009) -[2023-10-12 06:15:49,046][78091] Updated weights for policy 0, policy_version 71990 (0.0010) -[2023-10-12 06:15:49,416][78091] Updated weights for policy 0, policy_version 72000 (0.0009) -[2023-10-12 06:15:50,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 147095552. Throughput: 0: 1623.6, 1: 1582.1. Samples: 36778132. Policy #0 lag: (min: 26.0, avg: 34.0, max: 58.0) -[2023-10-12 06:15:50,202][77203] Avg episode reward: [(0, '60.120'), (1, '50.050')] -[2023-10-12 06:15:52,366][78123] Updated weights for policy 1, policy_version 71650 (0.0009) -[2023-10-12 06:15:52,737][78123] Updated weights for policy 1, policy_version 71660 (0.0007) -[2023-10-12 06:15:53,099][78123] Updated weights for policy 1, policy_version 71670 (0.0009) -[2023-10-12 06:15:53,469][78123] Updated weights for policy 1, policy_version 71680 (0.0008) -[2023-10-12 06:15:53,798][78091] Updated weights for policy 0, policy_version 72010 (0.0008) -[2023-10-12 06:15:54,182][78091] Updated weights for policy 0, policy_version 72020 (0.0008) -[2023-10-12 06:15:54,547][78091] Updated weights for policy 0, policy_version 72030 (0.0008) -[2023-10-12 06:15:55,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.3, 300 sec: 12774.0). Total num frames: 147161088. Throughput: 0: 1606.9, 1: 1579.6. Samples: 36796898. Policy #0 lag: (min: 26.0, avg: 34.0, max: 58.0) -[2023-10-12 06:15:55,201][77203] Avg episode reward: [(0, '55.230'), (1, '46.130')] -[2023-10-12 06:15:57,842][78123] Updated weights for policy 1, policy_version 71690 (0.0008) -[2023-10-12 06:15:58,217][78123] Updated weights for policy 1, policy_version 71700 (0.0009) -[2023-10-12 06:15:58,583][78123] Updated weights for policy 1, policy_version 71710 (0.0008) -[2023-10-12 06:15:58,882][78091] Updated weights for policy 0, policy_version 72040 (0.0009) -[2023-10-12 06:15:59,251][78091] Updated weights for policy 0, policy_version 72050 (0.0010) -[2023-10-12 06:15:59,617][78091] Updated weights for policy 0, policy_version 72060 (0.0009) -[2023-10-12 06:16:00,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 147226624. Throughput: 0: 1607.6, 1: 1603.5. Samples: 36807556. Policy #0 lag: (min: 26.0, avg: 34.0, max: 58.0) -[2023-10-12 06:16:00,201][77203] Avg episode reward: [(0, '55.230'), (1, '44.290')] -[2023-10-12 06:16:02,798][78123] Updated weights for policy 1, policy_version 71720 (0.0007) -[2023-10-12 06:16:03,160][78123] Updated weights for policy 1, policy_version 71730 (0.0008) -[2023-10-12 06:16:03,527][78123] Updated weights for policy 1, policy_version 71740 (0.0010) -[2023-10-12 06:16:03,888][78091] Updated weights for policy 0, policy_version 72070 (0.0007) -[2023-10-12 06:16:04,261][78091] Updated weights for policy 0, policy_version 72080 (0.0009) -[2023-10-12 06:16:04,629][78091] Updated weights for policy 0, policy_version 72090 (0.0009) -[2023-10-12 06:16:05,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 147292160. Throughput: 0: 1625.5, 1: 1586.1. Samples: 36826248. Policy #0 lag: (min: 26.0, avg: 34.0, max: 58.0) -[2023-10-12 06:16:05,202][77203] Avg episode reward: [(0, '58.580'), (1, '46.130')] -[2023-10-12 06:16:07,736][78123] Updated weights for policy 1, policy_version 71750 (0.0007) -[2023-10-12 06:16:08,104][78123] Updated weights for policy 1, policy_version 71760 (0.0008) -[2023-10-12 06:16:08,485][78123] Updated weights for policy 1, policy_version 71770 (0.0008) -[2023-10-12 06:16:08,963][78091] Updated weights for policy 0, policy_version 72100 (0.0010) -[2023-10-12 06:16:09,330][78091] Updated weights for policy 0, policy_version 72110 (0.0008) -[2023-10-12 06:16:09,703][78091] Updated weights for policy 0, policy_version 72120 (0.0008) -[2023-10-12 06:16:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 12885.0). Total num frames: 147357696. Throughput: 0: 1604.0, 1: 1592.3. Samples: 36844916. Policy #0 lag: (min: 26.0, avg: 34.0, max: 58.0) -[2023-10-12 06:16:10,201][77203] Avg episode reward: [(0, '55.620'), (1, '48.250')] -[2023-10-12 06:16:12,861][78123] Updated weights for policy 1, policy_version 71780 (0.0009) -[2023-10-12 06:16:13,227][78123] Updated weights for policy 1, policy_version 71790 (0.0010) -[2023-10-12 06:16:13,597][78123] Updated weights for policy 1, policy_version 71800 (0.0010) -[2023-10-12 06:16:14,106][78091] Updated weights for policy 0, policy_version 72130 (0.0011) -[2023-10-12 06:16:14,482][78091] Updated weights for policy 0, policy_version 72140 (0.0009) -[2023-10-12 06:16:14,849][78091] Updated weights for policy 0, policy_version 72150 (0.0009) -[2023-10-12 06:16:15,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 147390464. Throughput: 0: 1592.8, 1: 1607.2. Samples: 36855366. Policy #0 lag: (min: 26.0, avg: 34.0, max: 58.0) -[2023-10-12 06:16:15,201][77203] Avg episode reward: [(0, '55.710'), (1, '42.510')] -[2023-10-12 06:16:15,219][78091] Updated weights for policy 0, policy_version 72160 (0.0009) -[2023-10-12 06:16:17,941][78123] Updated weights for policy 1, policy_version 71810 (0.0009) -[2023-10-12 06:16:18,308][78123] Updated weights for policy 1, policy_version 71820 (0.0009) -[2023-10-12 06:16:18,672][78123] Updated weights for policy 1, policy_version 71830 (0.0009) -[2023-10-12 06:16:19,037][78123] Updated weights for policy 1, policy_version 71840 (0.0010) -[2023-10-12 06:16:19,551][78091] Updated weights for policy 0, policy_version 72170 (0.0009) -[2023-10-12 06:16:19,914][78091] Updated weights for policy 0, policy_version 72180 (0.0010) -[2023-10-12 06:16:20,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 147456000. Throughput: 0: 1609.4, 1: 1594.9. Samples: 36874124. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-10-12 06:16:20,201][77203] Avg episode reward: [(0, '55.590'), (1, '49.190')] -[2023-10-12 06:16:20,295][78091] Updated weights for policy 0, policy_version 72190 (0.0008) -[2023-10-12 06:16:23,498][78123] Updated weights for policy 1, policy_version 71850 (0.0008) -[2023-10-12 06:16:23,874][78123] Updated weights for policy 1, policy_version 71860 (0.0008) -[2023-10-12 06:16:24,244][78123] Updated weights for policy 1, policy_version 71870 (0.0009) -[2023-10-12 06:16:24,571][78091] Updated weights for policy 0, policy_version 72200 (0.0008) -[2023-10-12 06:16:24,943][78091] Updated weights for policy 0, policy_version 72210 (0.0007) -[2023-10-12 06:16:25,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 147521536. Throughput: 0: 1611.5, 1: 1587.4. Samples: 36893120. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-10-12 06:16:25,202][77203] Avg episode reward: [(0, '61.300'), (1, '43.870')] -[2023-10-12 06:16:25,307][78091] Updated weights for policy 0, policy_version 72220 (0.0009) -[2023-10-12 06:16:28,642][78123] Updated weights for policy 1, policy_version 71880 (0.0009) -[2023-10-12 06:16:29,011][78123] Updated weights for policy 1, policy_version 71890 (0.0009) -[2023-10-12 06:16:29,377][78123] Updated weights for policy 1, policy_version 71900 (0.0007) -[2023-10-12 06:16:29,735][78091] Updated weights for policy 0, policy_version 72230 (0.0007) -[2023-10-12 06:16:30,106][78091] Updated weights for policy 0, policy_version 72240 (0.0008) -[2023-10-12 06:16:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 147587072. Throughput: 0: 1592.7, 1: 1604.4. Samples: 36903274. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-10-12 06:16:30,201][77203] Avg episode reward: [(0, '58.130'), (1, '50.880')] -[2023-10-12 06:16:30,479][78091] Updated weights for policy 0, policy_version 72250 (0.0009) -[2023-10-12 06:16:33,666][78123] Updated weights for policy 1, policy_version 71910 (0.0007) -[2023-10-12 06:16:34,046][78123] Updated weights for policy 1, policy_version 71920 (0.0008) -[2023-10-12 06:16:34,412][78123] Updated weights for policy 1, policy_version 71930 (0.0008) -[2023-10-12 06:16:34,608][78091] Updated weights for policy 0, policy_version 72260 (0.0008) -[2023-10-12 06:16:34,980][78091] Updated weights for policy 0, policy_version 72270 (0.0010) -[2023-10-12 06:16:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 147652608. Throughput: 0: 1600.1, 1: 1611.0. Samples: 36922632. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-10-12 06:16:35,202][77203] Avg episode reward: [(0, '61.080'), (1, '53.440')] -[2023-10-12 06:16:35,351][78091] Updated weights for policy 0, policy_version 72280 (0.0009) -[2023-10-12 06:16:38,668][78123] Updated weights for policy 1, policy_version 71940 (0.0007) -[2023-10-12 06:16:39,035][78123] Updated weights for policy 1, policy_version 71950 (0.0009) -[2023-10-12 06:16:39,393][78123] Updated weights for policy 1, policy_version 71960 (0.0008) -[2023-10-12 06:16:39,577][78091] Updated weights for policy 0, policy_version 72290 (0.0010) -[2023-10-12 06:16:39,955][78091] Updated weights for policy 0, policy_version 72300 (0.0010) -[2023-10-12 06:16:40,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 147718144. Throughput: 0: 1611.3, 1: 1593.6. Samples: 36941118. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-10-12 06:16:40,201][77203] Avg episode reward: [(0, '54.240'), (1, '46.120')] -[2023-10-12 06:16:40,332][78091] Updated weights for policy 0, policy_version 72310 (0.0009) -[2023-10-12 06:16:40,698][78091] Updated weights for policy 0, policy_version 72320 (0.0009) -[2023-10-12 06:16:43,827][78123] Updated weights for policy 1, policy_version 71970 (0.0008) -[2023-10-12 06:16:44,194][78123] Updated weights for policy 1, policy_version 71980 (0.0010) -[2023-10-12 06:16:44,563][78123] Updated weights for policy 1, policy_version 71990 (0.0009) -[2023-10-12 06:16:44,931][78123] Updated weights for policy 1, policy_version 72000 (0.0009) -[2023-10-12 06:16:44,980][78091] Updated weights for policy 0, policy_version 72330 (0.0008) -[2023-10-12 06:16:45,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 147783680. Throughput: 0: 1590.4, 1: 1598.6. Samples: 36951062. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-10-12 06:16:45,201][77203] Avg episode reward: [(0, '59.400'), (1, '50.810')] -[2023-10-12 06:16:45,348][78091] Updated weights for policy 0, policy_version 72340 (0.0010) -[2023-10-12 06:16:45,722][78091] Updated weights for policy 0, policy_version 72350 (0.0009) -[2023-10-12 06:16:49,298][78123] Updated weights for policy 1, policy_version 72010 (0.0008) -[2023-10-12 06:16:49,662][78123] Updated weights for policy 1, policy_version 72020 (0.0009) -[2023-10-12 06:16:50,028][78123] Updated weights for policy 1, policy_version 72030 (0.0008) -[2023-10-12 06:16:50,099][78091] Updated weights for policy 0, policy_version 72360 (0.0007) -[2023-10-12 06:16:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 147849216. Throughput: 0: 1588.4, 1: 1614.9. Samples: 36970394. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-10-12 06:16:50,201][77203] Avg episode reward: [(0, '63.850'), (1, '45.610')] -[2023-10-12 06:16:50,470][78091] Updated weights for policy 0, policy_version 72370 (0.0007) -[2023-10-12 06:16:50,844][78091] Updated weights for policy 0, policy_version 72380 (0.0009) -[2023-10-12 06:16:54,469][78123] Updated weights for policy 1, policy_version 72040 (0.0008) -[2023-10-12 06:16:54,836][78123] Updated weights for policy 1, policy_version 72050 (0.0008) -[2023-10-12 06:16:55,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 147881984. Throughput: 0: 1607.2, 1: 1602.0. Samples: 36989330. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-10-12 06:16:55,201][77203] Avg episode reward: [(0, '58.050'), (1, '52.570')] -[2023-10-12 06:16:55,204][78123] Updated weights for policy 1, policy_version 72060 (0.0008) -[2023-10-12 06:16:55,280][78091] Updated weights for policy 0, policy_version 72390 (0.0007) -[2023-10-12 06:16:55,655][78091] Updated weights for policy 0, policy_version 72400 (0.0007) -[2023-10-12 06:16:56,031][78091] Updated weights for policy 0, policy_version 72410 (0.0008) -[2023-10-12 06:16:59,417][78123] Updated weights for policy 1, policy_version 72070 (0.0009) -[2023-10-12 06:16:59,785][78123] Updated weights for policy 1, policy_version 72080 (0.0008) -[2023-10-12 06:17:00,144][78123] Updated weights for policy 1, policy_version 72090 (0.0008) -[2023-10-12 06:17:00,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 147947520. Throughput: 0: 1590.8, 1: 1592.0. Samples: 36998590. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-10-12 06:17:00,201][77203] Avg episode reward: [(0, '58.020'), (1, '47.760')] -[2023-10-12 06:17:00,285][78091] Updated weights for policy 0, policy_version 72420 (0.0007) -[2023-10-12 06:17:00,657][78091] Updated weights for policy 0, policy_version 72430 (0.0008) -[2023-10-12 06:17:01,027][78091] Updated weights for policy 0, policy_version 72440 (0.0009) -[2023-10-12 06:17:04,282][78123] Updated weights for policy 1, policy_version 72100 (0.0010) -[2023-10-12 06:17:04,650][78123] Updated weights for policy 1, policy_version 72110 (0.0009) -[2023-10-12 06:17:05,023][78123] Updated weights for policy 1, policy_version 72120 (0.0007) -[2023-10-12 06:17:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 148013056. Throughput: 0: 1591.1, 1: 1610.1. Samples: 37018178. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-12 06:17:05,201][77203] Avg episode reward: [(0, '52.320'), (1, '50.480')] -[2023-10-12 06:17:05,331][78091] Updated weights for policy 0, policy_version 72450 (0.0011) -[2023-10-12 06:17:05,705][78091] Updated weights for policy 0, policy_version 72460 (0.0008) -[2023-10-12 06:17:06,074][78091] Updated weights for policy 0, policy_version 72470 (0.0007) -[2023-10-12 06:17:06,437][78091] Updated weights for policy 0, policy_version 72480 (0.0010) -[2023-10-12 06:17:09,280][78123] Updated weights for policy 1, policy_version 72130 (0.0007) -[2023-10-12 06:17:09,639][78123] Updated weights for policy 1, policy_version 72140 (0.0010) -[2023-10-12 06:17:10,008][78123] Updated weights for policy 1, policy_version 72150 (0.0010) -[2023-10-12 06:17:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 148078592. Throughput: 0: 1598.5, 1: 1606.0. Samples: 37037326. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-12 06:17:10,202][77203] Avg episode reward: [(0, '60.930'), (1, '52.760')] -[2023-10-12 06:17:10,211][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000072480_74219520.pth... -[2023-10-12 06:17:10,240][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000071008_72712192.pth -[2023-10-12 06:17:10,369][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000072160_73891840.pth... -[2023-10-12 06:17:10,371][78123] Updated weights for policy 1, policy_version 72160 (0.0010) -[2023-10-12 06:17:10,398][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000070656_72351744.pth -[2023-10-12 06:17:10,863][78091] Updated weights for policy 0, policy_version 72490 (0.0008) -[2023-10-12 06:17:11,242][78091] Updated weights for policy 0, policy_version 72500 (0.0007) -[2023-10-12 06:17:11,605][78091] Updated weights for policy 0, policy_version 72510 (0.0009) -[2023-10-12 06:17:14,874][78123] Updated weights for policy 1, policy_version 72170 (0.0010) -[2023-10-12 06:17:15,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 148144128. Throughput: 0: 1589.5, 1: 1591.4. Samples: 37046414. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-12 06:17:15,202][77203] Avg episode reward: [(0, '56.750'), (1, '46.120')] -[2023-10-12 06:17:15,248][78123] Updated weights for policy 1, policy_version 72180 (0.0008) -[2023-10-12 06:17:15,611][78123] Updated weights for policy 1, policy_version 72190 (0.0008) -[2023-10-12 06:17:15,896][78091] Updated weights for policy 0, policy_version 72520 (0.0007) -[2023-10-12 06:17:16,266][78091] Updated weights for policy 0, policy_version 72530 (0.0008) -[2023-10-12 06:17:16,637][78091] Updated weights for policy 0, policy_version 72540 (0.0011) -[2023-10-12 06:17:19,793][78123] Updated weights for policy 1, policy_version 72200 (0.0009) -[2023-10-12 06:17:20,157][78123] Updated weights for policy 1, policy_version 72210 (0.0010) -[2023-10-12 06:17:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 148209664. Throughput: 0: 1585.9, 1: 1598.6. Samples: 37065934. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-12 06:17:20,201][77203] Avg episode reward: [(0, '58.970'), (1, '54.400')] -[2023-10-12 06:17:20,527][78123] Updated weights for policy 1, policy_version 72220 (0.0011) -[2023-10-12 06:17:20,924][78091] Updated weights for policy 0, policy_version 72550 (0.0008) -[2023-10-12 06:17:21,286][78091] Updated weights for policy 0, policy_version 72560 (0.0009) -[2023-10-12 06:17:21,656][78091] Updated weights for policy 0, policy_version 72570 (0.0008) -[2023-10-12 06:17:24,984][78123] Updated weights for policy 1, policy_version 72230 (0.0009) -[2023-10-12 06:17:25,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 148275200. Throughput: 0: 1588.6, 1: 1615.8. Samples: 37085316. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-12 06:17:25,202][77203] Avg episode reward: [(0, '51.480'), (1, '42.410')] -[2023-10-12 06:17:25,343][78123] Updated weights for policy 1, policy_version 72240 (0.0007) -[2023-10-12 06:17:25,709][78123] Updated weights for policy 1, policy_version 72250 (0.0008) -[2023-10-12 06:17:26,115][78091] Updated weights for policy 0, policy_version 72580 (0.0008) -[2023-10-12 06:17:26,476][78091] Updated weights for policy 0, policy_version 72590 (0.0009) -[2023-10-12 06:17:26,846][78091] Updated weights for policy 0, policy_version 72600 (0.0011) -[2023-10-12 06:17:29,893][78123] Updated weights for policy 1, policy_version 72260 (0.0007) -[2023-10-12 06:17:30,201][77203] Fps is (10 sec: 13106.4, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 148340736. Throughput: 0: 1584.2, 1: 1590.9. Samples: 37093942. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-12 06:17:30,203][77203] Avg episode reward: [(0, '57.360'), (1, '49.570')] -[2023-10-12 06:17:30,257][78123] Updated weights for policy 1, policy_version 72270 (0.0010) -[2023-10-12 06:17:30,622][78123] Updated weights for policy 1, policy_version 72280 (0.0010) -[2023-10-12 06:17:31,143][78091] Updated weights for policy 0, policy_version 72610 (0.0008) -[2023-10-12 06:17:31,503][78091] Updated weights for policy 0, policy_version 72620 (0.0008) -[2023-10-12 06:17:31,866][78091] Updated weights for policy 0, policy_version 72630 (0.0010) -[2023-10-12 06:17:32,239][78091] Updated weights for policy 0, policy_version 72640 (0.0008) -[2023-10-12 06:17:35,030][78123] Updated weights for policy 1, policy_version 72290 (0.0010) -[2023-10-12 06:17:35,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 148406272. Throughput: 0: 1590.8, 1: 1587.9. Samples: 37113434. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-12 06:17:35,202][77203] Avg episode reward: [(0, '62.010'), (1, '50.190')] -[2023-10-12 06:17:35,388][78123] Updated weights for policy 1, policy_version 72300 (0.0009) -[2023-10-12 06:17:35,760][78123] Updated weights for policy 1, policy_version 72310 (0.0008) -[2023-10-12 06:17:36,122][78123] Updated weights for policy 1, policy_version 72320 (0.0009) -[2023-10-12 06:17:36,578][78091] Updated weights for policy 0, policy_version 72650 (0.0009) -[2023-10-12 06:17:36,949][78091] Updated weights for policy 0, policy_version 72660 (0.0008) -[2023-10-12 06:17:37,321][78091] Updated weights for policy 0, policy_version 72670 (0.0008) -[2023-10-12 06:17:40,201][77203] Fps is (10 sec: 13107.9, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 148471808. Throughput: 0: 1588.5, 1: 1603.6. Samples: 37132978. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-12 06:17:40,201][77203] Avg episode reward: [(0, '61.040'), (1, '49.900')] -[2023-10-12 06:17:40,317][78123] Updated weights for policy 1, policy_version 72330 (0.0009) -[2023-10-12 06:17:40,680][78123] Updated weights for policy 1, policy_version 72340 (0.0009) -[2023-10-12 06:17:41,049][78123] Updated weights for policy 1, policy_version 72350 (0.0009) -[2023-10-12 06:17:41,649][78091] Updated weights for policy 0, policy_version 72680 (0.0007) -[2023-10-12 06:17:42,021][78091] Updated weights for policy 0, policy_version 72690 (0.0007) -[2023-10-12 06:17:42,382][78091] Updated weights for policy 0, policy_version 72700 (0.0007) -[2023-10-12 06:17:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 148537344. Throughput: 0: 1588.9, 1: 1590.0. Samples: 37141640. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-12 06:17:45,202][77203] Avg episode reward: [(0, '59.630'), (1, '48.220')] -[2023-10-12 06:17:45,543][78123] Updated weights for policy 1, policy_version 72360 (0.0008) -[2023-10-12 06:17:45,913][78123] Updated weights for policy 1, policy_version 72370 (0.0010) -[2023-10-12 06:17:46,275][78123] Updated weights for policy 1, policy_version 72380 (0.0007) -[2023-10-12 06:17:46,590][78091] Updated weights for policy 0, policy_version 72710 (0.0010) -[2023-10-12 06:17:46,952][78091] Updated weights for policy 0, policy_version 72720 (0.0010) -[2023-10-12 06:17:47,327][78091] Updated weights for policy 0, policy_version 72730 (0.0007) -[2023-10-12 06:17:50,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 148602880. Throughput: 0: 1591.5, 1: 1587.0. Samples: 37161208. Policy #0 lag: (min: 19.0, avg: 20.2, max: 43.0) -[2023-10-12 06:17:50,202][77203] Avg episode reward: [(0, '60.440'), (1, '47.370')] -[2023-10-12 06:17:50,545][78123] Updated weights for policy 1, policy_version 72390 (0.0009) -[2023-10-12 06:17:50,914][78123] Updated weights for policy 1, policy_version 72400 (0.0010) -[2023-10-12 06:17:51,282][78123] Updated weights for policy 1, policy_version 72410 (0.0009) -[2023-10-12 06:17:51,666][78091] Updated weights for policy 0, policy_version 72740 (0.0008) -[2023-10-12 06:17:52,043][78091] Updated weights for policy 0, policy_version 72750 (0.0011) -[2023-10-12 06:17:52,409][78091] Updated weights for policy 0, policy_version 72760 (0.0008) -[2023-10-12 06:17:55,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 148668416. Throughput: 0: 1594.0, 1: 1594.0. Samples: 37180786. Policy #0 lag: (min: 19.0, avg: 20.2, max: 43.0) -[2023-10-12 06:17:55,201][77203] Avg episode reward: [(0, '54.610'), (1, '52.410')] -[2023-10-12 06:17:55,730][78123] Updated weights for policy 1, policy_version 72420 (0.0007) -[2023-10-12 06:17:56,096][78123] Updated weights for policy 1, policy_version 72430 (0.0007) -[2023-10-12 06:17:56,465][78123] Updated weights for policy 1, policy_version 72440 (0.0008) -[2023-10-12 06:17:56,519][78091] Updated weights for policy 0, policy_version 72770 (0.0011) -[2023-10-12 06:17:56,890][78091] Updated weights for policy 0, policy_version 72780 (0.0009) -[2023-10-12 06:17:57,259][78091] Updated weights for policy 0, policy_version 72790 (0.0008) -[2023-10-12 06:17:57,626][78091] Updated weights for policy 0, policy_version 72800 (0.0009) -[2023-10-12 06:18:00,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 148733952. Throughput: 0: 1594.3, 1: 1585.2. Samples: 37189490. Policy #0 lag: (min: 19.0, avg: 20.2, max: 43.0) -[2023-10-12 06:18:00,202][77203] Avg episode reward: [(0, '57.870'), (1, '47.960')] -[2023-10-12 06:18:01,032][78123] Updated weights for policy 1, policy_version 72450 (0.0009) -[2023-10-12 06:18:01,450][78123] Updated weights for policy 1, policy_version 72460 (0.0010) -[2023-10-12 06:18:01,819][78123] Updated weights for policy 1, policy_version 72470 (0.0009) -[2023-10-12 06:18:01,961][78091] Updated weights for policy 0, policy_version 72810 (0.0009) -[2023-10-12 06:18:02,179][78123] Updated weights for policy 1, policy_version 72480 (0.0009) -[2023-10-12 06:18:02,329][78091] Updated weights for policy 0, policy_version 72820 (0.0009) -[2023-10-12 06:18:02,692][78091] Updated weights for policy 0, policy_version 72830 (0.0009) -[2023-10-12 06:18:05,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 148799488. Throughput: 0: 1598.4, 1: 1579.4. Samples: 37208934. Policy #0 lag: (min: 19.0, avg: 20.2, max: 43.0) -[2023-10-12 06:18:05,202][77203] Avg episode reward: [(0, '54.180'), (1, '51.430')] -[2023-10-12 06:18:06,428][78123] Updated weights for policy 1, policy_version 72490 (0.0008) -[2023-10-12 06:18:06,796][78123] Updated weights for policy 1, policy_version 72500 (0.0008) -[2023-10-12 06:18:07,028][78091] Updated weights for policy 0, policy_version 72840 (0.0009) -[2023-10-12 06:18:07,168][78123] Updated weights for policy 1, policy_version 72510 (0.0009) -[2023-10-12 06:18:07,391][78091] Updated weights for policy 0, policy_version 72850 (0.0009) -[2023-10-12 06:18:07,779][78091] Updated weights for policy 0, policy_version 72860 (0.0007) -[2023-10-12 06:18:10,201][77203] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 148865024. Throughput: 0: 1601.1, 1: 1580.1. Samples: 37228468. Policy #0 lag: (min: 19.0, avg: 20.2, max: 43.0) -[2023-10-12 06:18:10,201][77203] Avg episode reward: [(0, '54.570'), (1, '44.360')] -[2023-10-12 06:18:11,379][78123] Updated weights for policy 1, policy_version 72520 (0.0009) -[2023-10-12 06:18:11,755][78123] Updated weights for policy 1, policy_version 72530 (0.0009) -[2023-10-12 06:18:12,055][78091] Updated weights for policy 0, policy_version 72870 (0.0008) -[2023-10-12 06:18:12,122][78123] Updated weights for policy 1, policy_version 72540 (0.0007) -[2023-10-12 06:18:12,430][78091] Updated weights for policy 0, policy_version 72880 (0.0009) -[2023-10-12 06:18:12,796][78091] Updated weights for policy 0, policy_version 72890 (0.0009) -[2023-10-12 06:18:15,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 148930560. Throughput: 0: 1606.3, 1: 1577.2. Samples: 37237198. Policy #0 lag: (min: 19.0, avg: 20.2, max: 43.0) -[2023-10-12 06:18:15,201][77203] Avg episode reward: [(0, '57.500'), (1, '50.510')] -[2023-10-12 06:18:16,525][78123] Updated weights for policy 1, policy_version 72550 (0.0009) -[2023-10-12 06:18:16,884][78123] Updated weights for policy 1, policy_version 72560 (0.0009) -[2023-10-12 06:18:17,017][78091] Updated weights for policy 0, policy_version 72900 (0.0010) -[2023-10-12 06:18:17,253][78123] Updated weights for policy 1, policy_version 72570 (0.0008) -[2023-10-12 06:18:17,386][78091] Updated weights for policy 0, policy_version 72910 (0.0007) -[2023-10-12 06:18:17,763][78091] Updated weights for policy 0, policy_version 72920 (0.0008) -[2023-10-12 06:18:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 148996096. Throughput: 0: 1595.7, 1: 1581.4. Samples: 37256404. Policy #0 lag: (min: 19.0, avg: 20.2, max: 43.0) -[2023-10-12 06:18:20,201][77203] Avg episode reward: [(0, '56.720'), (1, '59.380')] -[2023-10-12 06:18:21,653][78123] Updated weights for policy 1, policy_version 72580 (0.0009) -[2023-10-12 06:18:22,016][78123] Updated weights for policy 1, policy_version 72590 (0.0009) -[2023-10-12 06:18:22,182][78091] Updated weights for policy 0, policy_version 72930 (0.0008) -[2023-10-12 06:18:22,391][78123] Updated weights for policy 1, policy_version 72600 (0.0009) -[2023-10-12 06:18:22,576][78091] Updated weights for policy 0, policy_version 72940 (0.0010) -[2023-10-12 06:18:22,944][78091] Updated weights for policy 0, policy_version 72950 (0.0008) -[2023-10-12 06:18:23,315][78091] Updated weights for policy 0, policy_version 72960 (0.0007) -[2023-10-12 06:18:25,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 149061632. Throughput: 0: 1598.2, 1: 1579.8. Samples: 37275988. Policy #0 lag: (min: 19.0, avg: 20.2, max: 43.0) -[2023-10-12 06:18:25,202][77203] Avg episode reward: [(0, '64.700'), (1, '49.730')] -[2023-10-12 06:18:26,714][78123] Updated weights for policy 1, policy_version 72610 (0.0009) -[2023-10-12 06:18:27,077][78123] Updated weights for policy 1, policy_version 72620 (0.0009) -[2023-10-12 06:18:27,449][78123] Updated weights for policy 1, policy_version 72630 (0.0010) -[2023-10-12 06:18:27,630][78091] Updated weights for policy 0, policy_version 72970 (0.0010) -[2023-10-12 06:18:27,813][78123] Updated weights for policy 1, policy_version 72640 (0.0007) -[2023-10-12 06:18:28,000][78091] Updated weights for policy 0, policy_version 72980 (0.0009) -[2023-10-12 06:18:28,381][78091] Updated weights for policy 0, policy_version 72990 (0.0007) -[2023-10-12 06:18:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 12774.0). Total num frames: 149127168. Throughput: 0: 1610.4, 1: 1585.7. Samples: 37285462. Policy #0 lag: (min: 19.0, avg: 20.2, max: 43.0) -[2023-10-12 06:18:30,201][77203] Avg episode reward: [(0, '56.630'), (1, '44.070')] -[2023-10-12 06:18:32,188][78123] Updated weights for policy 1, policy_version 72650 (0.0008) -[2023-10-12 06:18:32,456][78091] Updated weights for policy 0, policy_version 73000 (0.0009) -[2023-10-12 06:18:32,551][78123] Updated weights for policy 1, policy_version 72660 (0.0008) -[2023-10-12 06:18:32,835][78091] Updated weights for policy 0, policy_version 73010 (0.0008) -[2023-10-12 06:18:32,918][78123] Updated weights for policy 1, policy_version 72670 (0.0008) -[2023-10-12 06:18:33,212][78091] Updated weights for policy 0, policy_version 73020 (0.0009) -[2023-10-12 06:18:35,201][77203] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 149192704. Throughput: 0: 1593.1, 1: 1585.6. Samples: 37304250. Policy #0 lag: (min: 25.0, avg: 26.6, max: 45.0) -[2023-10-12 06:18:35,201][77203] Avg episode reward: [(0, '55.750'), (1, '48.440')] -[2023-10-12 06:18:37,327][78123] Updated weights for policy 1, policy_version 72680 (0.0009) -[2023-10-12 06:18:37,655][78091] Updated weights for policy 0, policy_version 73030 (0.0008) -[2023-10-12 06:18:37,691][78123] Updated weights for policy 1, policy_version 72690 (0.0007) -[2023-10-12 06:18:38,026][78091] Updated weights for policy 0, policy_version 73040 (0.0008) -[2023-10-12 06:18:38,053][78123] Updated weights for policy 1, policy_version 72700 (0.0007) -[2023-10-12 06:18:38,394][78091] Updated weights for policy 0, policy_version 73050 (0.0007) -[2023-10-12 06:18:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 149258240. Throughput: 0: 1587.2, 1: 1582.5. Samples: 37323424. Policy #0 lag: (min: 25.0, avg: 26.6, max: 45.0) -[2023-10-12 06:18:40,201][77203] Avg episode reward: [(0, '58.250'), (1, '53.550')] -[2023-10-12 06:18:42,289][78123] Updated weights for policy 1, policy_version 72710 (0.0008) -[2023-10-12 06:18:42,644][78123] Updated weights for policy 1, policy_version 72720 (0.0009) -[2023-10-12 06:18:42,806][78091] Updated weights for policy 0, policy_version 73060 (0.0009) -[2023-10-12 06:18:43,014][78123] Updated weights for policy 1, policy_version 72730 (0.0009) -[2023-10-12 06:18:43,174][78091] Updated weights for policy 0, policy_version 73070 (0.0009) -[2023-10-12 06:18:43,541][78091] Updated weights for policy 0, policy_version 73080 (0.0009) -[2023-10-12 06:18:45,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 149323776. Throughput: 0: 1608.7, 1: 1591.5. Samples: 37333498. Policy #0 lag: (min: 25.0, avg: 26.6, max: 45.0) -[2023-10-12 06:18:45,202][77203] Avg episode reward: [(0, '56.740'), (1, '54.010')] -[2023-10-12 06:18:47,294][78123] Updated weights for policy 1, policy_version 72740 (0.0009) -[2023-10-12 06:18:47,671][78123] Updated weights for policy 1, policy_version 72750 (0.0009) -[2023-10-12 06:18:47,897][78091] Updated weights for policy 0, policy_version 73090 (0.0008) -[2023-10-12 06:18:48,029][78123] Updated weights for policy 1, policy_version 72760 (0.0008) -[2023-10-12 06:18:48,260][78091] Updated weights for policy 0, policy_version 73100 (0.0008) -[2023-10-12 06:18:48,638][78091] Updated weights for policy 0, policy_version 73110 (0.0010) -[2023-10-12 06:18:49,007][78091] Updated weights for policy 0, policy_version 73120 (0.0010) -[2023-10-12 06:18:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 12774.0). Total num frames: 149389312. Throughput: 0: 1587.7, 1: 1585.8. Samples: 37351742. Policy #0 lag: (min: 25.0, avg: 26.6, max: 45.0) -[2023-10-12 06:18:50,201][77203] Avg episode reward: [(0, '59.410'), (1, '44.820')] -[2023-10-12 06:18:52,260][78123] Updated weights for policy 1, policy_version 72770 (0.0009) -[2023-10-12 06:18:52,673][78123] Updated weights for policy 1, policy_version 72780 (0.0009) -[2023-10-12 06:18:53,041][78123] Updated weights for policy 1, policy_version 72790 (0.0010) -[2023-10-12 06:18:53,394][78123] Updated weights for policy 1, policy_version 72800 (0.0009) -[2023-10-12 06:18:53,400][78091] Updated weights for policy 0, policy_version 73130 (0.0007) -[2023-10-12 06:18:53,767][78091] Updated weights for policy 0, policy_version 73140 (0.0009) -[2023-10-12 06:18:54,145][78091] Updated weights for policy 0, policy_version 73150 (0.0008) -[2023-10-12 06:18:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 149454848. Throughput: 0: 1576.2, 1: 1589.7. Samples: 37370932. Policy #0 lag: (min: 25.0, avg: 26.6, max: 45.0) -[2023-10-12 06:18:55,202][77203] Avg episode reward: [(0, '50.920'), (1, '44.980')] -[2023-10-12 06:18:57,553][78123] Updated weights for policy 1, policy_version 72810 (0.0007) -[2023-10-12 06:18:57,906][78123] Updated weights for policy 1, policy_version 72820 (0.0008) -[2023-10-12 06:18:58,279][78123] Updated weights for policy 1, policy_version 72830 (0.0009) -[2023-10-12 06:18:58,565][78091] Updated weights for policy 0, policy_version 73160 (0.0007) -[2023-10-12 06:18:58,944][78091] Updated weights for policy 0, policy_version 73170 (0.0008) -[2023-10-12 06:18:59,313][78091] Updated weights for policy 0, policy_version 73180 (0.0010) -[2023-10-12 06:19:00,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.3, 300 sec: 12774.0). Total num frames: 149520384. Throughput: 0: 1596.1, 1: 1606.9. Samples: 37381332. Policy #0 lag: (min: 25.0, avg: 26.6, max: 45.0) -[2023-10-12 06:19:00,201][77203] Avg episode reward: [(0, '57.110'), (1, '49.440')] -[2023-10-12 06:19:02,631][78123] Updated weights for policy 1, policy_version 72840 (0.0008) -[2023-10-12 06:19:03,013][78123] Updated weights for policy 1, policy_version 72850 (0.0008) -[2023-10-12 06:19:03,382][78123] Updated weights for policy 1, policy_version 72860 (0.0007) -[2023-10-12 06:19:03,620][78091] Updated weights for policy 0, policy_version 73190 (0.0010) -[2023-10-12 06:19:03,994][78091] Updated weights for policy 0, policy_version 73200 (0.0009) -[2023-10-12 06:19:04,354][78091] Updated weights for policy 0, policy_version 73210 (0.0008) -[2023-10-12 06:19:05,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 149585920. Throughput: 0: 1598.6, 1: 1593.9. Samples: 37400066. Policy #0 lag: (min: 25.0, avg: 26.6, max: 45.0) -[2023-10-12 06:19:05,202][77203] Avg episode reward: [(0, '60.850'), (1, '53.220')] -[2023-10-12 06:19:07,741][78123] Updated weights for policy 1, policy_version 72870 (0.0008) -[2023-10-12 06:19:08,103][78123] Updated weights for policy 1, policy_version 72880 (0.0009) -[2023-10-12 06:19:08,459][78123] Updated weights for policy 1, policy_version 72890 (0.0010) -[2023-10-12 06:19:08,912][78091] Updated weights for policy 0, policy_version 73220 (0.0010) -[2023-10-12 06:19:09,318][78091] Updated weights for policy 0, policy_version 73230 (0.0009) -[2023-10-12 06:19:09,691][78091] Updated weights for policy 0, policy_version 73240 (0.0010) -[2023-10-12 06:19:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 149651456. Throughput: 0: 1582.9, 1: 1591.3. Samples: 37418830. Policy #0 lag: (min: 25.0, avg: 26.6, max: 45.0) -[2023-10-12 06:19:10,202][77203] Avg episode reward: [(0, '59.620'), (1, '49.930')] -[2023-10-12 06:19:10,211][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000073248_75005952.pth... -[2023-10-12 06:19:10,211][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000072896_74645504.pth... -[2023-10-12 06:19:10,241][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000071744_73465856.pth -[2023-10-12 06:19:10,246][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000071392_73105408.pth -[2023-10-12 06:19:12,735][78123] Updated weights for policy 1, policy_version 72900 (0.0010) -[2023-10-12 06:19:13,103][78123] Updated weights for policy 1, policy_version 72910 (0.0011) -[2023-10-12 06:19:13,479][78123] Updated weights for policy 1, policy_version 72920 (0.0009) -[2023-10-12 06:19:13,783][78091] Updated weights for policy 0, policy_version 73250 (0.0009) -[2023-10-12 06:19:14,144][78091] Updated weights for policy 0, policy_version 73260 (0.0010) -[2023-10-12 06:19:14,523][78091] Updated weights for policy 0, policy_version 73270 (0.0010) -[2023-10-12 06:19:14,897][78091] Updated weights for policy 0, policy_version 73280 (0.0007) -[2023-10-12 06:19:15,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 149716992. Throughput: 0: 1589.3, 1: 1609.5. Samples: 37429408. Policy #0 lag: (min: 25.0, avg: 26.6, max: 45.0) -[2023-10-12 06:19:15,201][77203] Avg episode reward: [(0, '55.940'), (1, '42.190')] -[2023-10-12 06:19:17,852][78123] Updated weights for policy 1, policy_version 72930 (0.0009) -[2023-10-12 06:19:18,217][78123] Updated weights for policy 1, policy_version 72940 (0.0009) -[2023-10-12 06:19:18,592][78123] Updated weights for policy 1, policy_version 72950 (0.0011) -[2023-10-12 06:19:18,953][78123] Updated weights for policy 1, policy_version 72960 (0.0010) -[2023-10-12 06:19:19,328][78091] Updated weights for policy 0, policy_version 73290 (0.0008) -[2023-10-12 06:19:19,693][78091] Updated weights for policy 0, policy_version 73300 (0.0008) -[2023-10-12 06:19:20,062][78091] Updated weights for policy 0, policy_version 73310 (0.0007) -[2023-10-12 06:19:20,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 149782528. Throughput: 0: 1603.9, 1: 1592.3. Samples: 37448076. Policy #0 lag: (min: 31.0, avg: 32.3, max: 56.0) -[2023-10-12 06:19:20,201][77203] Avg episode reward: [(0, '53.560'), (1, '48.280')] -[2023-10-12 06:19:23,470][78123] Updated weights for policy 1, policy_version 72970 (0.0007) -[2023-10-12 06:19:23,823][78123] Updated weights for policy 1, policy_version 72980 (0.0009) -[2023-10-12 06:19:24,175][78091] Updated weights for policy 0, policy_version 73320 (0.0008) -[2023-10-12 06:19:24,196][78123] Updated weights for policy 1, policy_version 72990 (0.0009) -[2023-10-12 06:19:24,540][78091] Updated weights for policy 0, policy_version 73330 (0.0009) -[2023-10-12 06:19:24,908][78091] Updated weights for policy 0, policy_version 73340 (0.0009) -[2023-10-12 06:19:25,201][77203] Fps is (10 sec: 13106.7, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 149848064. Throughput: 0: 1589.4, 1: 1595.6. Samples: 37466752. Policy #0 lag: (min: 31.0, avg: 32.3, max: 56.0) -[2023-10-12 06:19:25,203][77203] Avg episode reward: [(0, '60.710'), (1, '46.480')] -[2023-10-12 06:19:28,437][78123] Updated weights for policy 1, policy_version 73000 (0.0007) -[2023-10-12 06:19:28,812][78123] Updated weights for policy 1, policy_version 73010 (0.0010) -[2023-10-12 06:19:29,180][78123] Updated weights for policy 1, policy_version 73020 (0.0009) -[2023-10-12 06:19:29,369][78091] Updated weights for policy 0, policy_version 73350 (0.0008) -[2023-10-12 06:19:29,732][78091] Updated weights for policy 0, policy_version 73360 (0.0008) -[2023-10-12 06:19:30,108][78091] Updated weights for policy 0, policy_version 73370 (0.0008) -[2023-10-12 06:19:30,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 149880832. Throughput: 0: 1586.4, 1: 1611.2. Samples: 37477386. Policy #0 lag: (min: 31.0, avg: 32.3, max: 56.0) -[2023-10-12 06:19:30,202][77203] Avg episode reward: [(0, '63.180'), (1, '53.200')] -[2023-10-12 06:19:33,414][78123] Updated weights for policy 1, policy_version 73030 (0.0007) -[2023-10-12 06:19:33,777][78123] Updated weights for policy 1, policy_version 73040 (0.0009) -[2023-10-12 06:19:34,144][78123] Updated weights for policy 1, policy_version 73050 (0.0010) -[2023-10-12 06:19:34,584][78091] Updated weights for policy 0, policy_version 73380 (0.0010) -[2023-10-12 06:19:34,951][78091] Updated weights for policy 0, policy_version 73390 (0.0009) -[2023-10-12 06:19:35,201][77203] Fps is (10 sec: 9830.8, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 149946368. Throughput: 0: 1604.8, 1: 1610.6. Samples: 37496434. Policy #0 lag: (min: 31.0, avg: 32.3, max: 56.0) -[2023-10-12 06:19:35,201][77203] Avg episode reward: [(0, '61.340'), (1, '44.960')] -[2023-10-12 06:19:35,329][78091] Updated weights for policy 0, policy_version 73400 (0.0009) -[2023-10-12 06:19:38,627][78123] Updated weights for policy 1, policy_version 73060 (0.0009) -[2023-10-12 06:19:39,009][78123] Updated weights for policy 1, policy_version 73070 (0.0007) -[2023-10-12 06:19:39,379][78123] Updated weights for policy 1, policy_version 73080 (0.0008) -[2023-10-12 06:19:39,407][78091] Updated weights for policy 0, policy_version 73410 (0.0009) -[2023-10-12 06:19:39,774][78091] Updated weights for policy 0, policy_version 73420 (0.0010) -[2023-10-12 06:19:40,150][78091] Updated weights for policy 0, policy_version 73430 (0.0008) -[2023-10-12 06:19:40,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 150011904. Throughput: 0: 1609.8, 1: 1593.0. Samples: 37515058. Policy #0 lag: (min: 31.0, avg: 32.3, max: 56.0) -[2023-10-12 06:19:40,202][77203] Avg episode reward: [(0, '57.660'), (1, '47.580')] -[2023-10-12 06:19:40,521][78091] Updated weights for policy 0, policy_version 73440 (0.0008) -[2023-10-12 06:19:43,578][78123] Updated weights for policy 1, policy_version 73090 (0.0007) -[2023-10-12 06:19:43,946][78123] Updated weights for policy 1, policy_version 73100 (0.0010) -[2023-10-12 06:19:44,305][78123] Updated weights for policy 1, policy_version 73110 (0.0009) -[2023-10-12 06:19:44,671][78123] Updated weights for policy 1, policy_version 73120 (0.0008) -[2023-10-12 06:19:44,701][78091] Updated weights for policy 0, policy_version 73450 (0.0009) -[2023-10-12 06:19:45,069][78091] Updated weights for policy 0, policy_version 73460 (0.0009) -[2023-10-12 06:19:45,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 150077440. Throughput: 0: 1595.9, 1: 1604.3. Samples: 37525340. Policy #0 lag: (min: 31.0, avg: 32.3, max: 56.0) -[2023-10-12 06:19:45,201][77203] Avg episode reward: [(0, '55.410'), (1, '48.690')] -[2023-10-12 06:19:45,444][78091] Updated weights for policy 0, policy_version 73470 (0.0008) -[2023-10-12 06:19:49,061][78123] Updated weights for policy 1, policy_version 73130 (0.0008) -[2023-10-12 06:19:49,426][78123] Updated weights for policy 1, policy_version 73140 (0.0007) -[2023-10-12 06:19:49,792][78123] Updated weights for policy 1, policy_version 73150 (0.0008) -[2023-10-12 06:19:49,903][78091] Updated weights for policy 0, policy_version 73480 (0.0009) -[2023-10-12 06:19:50,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 150142976. Throughput: 0: 1601.5, 1: 1617.4. Samples: 37544916. Policy #0 lag: (min: 31.0, avg: 32.3, max: 56.0) -[2023-10-12 06:19:50,201][77203] Avg episode reward: [(0, '60.220'), (1, '44.430')] -[2023-10-12 06:19:50,275][78091] Updated weights for policy 0, policy_version 73490 (0.0009) -[2023-10-12 06:19:50,651][78091] Updated weights for policy 0, policy_version 73500 (0.0009) -[2023-10-12 06:19:53,900][78123] Updated weights for policy 1, policy_version 73160 (0.0008) -[2023-10-12 06:19:54,270][78123] Updated weights for policy 1, policy_version 73170 (0.0008) -[2023-10-12 06:19:54,646][78123] Updated weights for policy 1, policy_version 73180 (0.0009) -[2023-10-12 06:19:54,883][78091] Updated weights for policy 0, policy_version 73510 (0.0009) -[2023-10-12 06:19:55,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 150208512. Throughput: 0: 1612.9, 1: 1600.9. Samples: 37563452. Policy #0 lag: (min: 31.0, avg: 32.3, max: 56.0) -[2023-10-12 06:19:55,202][77203] Avg episode reward: [(0, '59.400'), (1, '54.940')] -[2023-10-12 06:19:55,267][78091] Updated weights for policy 0, policy_version 73520 (0.0010) -[2023-10-12 06:19:55,648][78091] Updated weights for policy 0, policy_version 73530 (0.0009) -[2023-10-12 06:19:58,954][78123] Updated weights for policy 1, policy_version 73190 (0.0009) -[2023-10-12 06:19:59,323][78123] Updated weights for policy 1, policy_version 73200 (0.0010) -[2023-10-12 06:19:59,694][78123] Updated weights for policy 1, policy_version 73210 (0.0010) -[2023-10-12 06:20:00,016][78091] Updated weights for policy 0, policy_version 73540 (0.0007) -[2023-10-12 06:20:00,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 150274048. Throughput: 0: 1596.5, 1: 1599.9. Samples: 37573246. Policy #0 lag: (min: 31.0, avg: 32.3, max: 56.0) -[2023-10-12 06:20:00,202][77203] Avg episode reward: [(0, '49.200'), (1, '55.320')] -[2023-10-12 06:20:00,386][78091] Updated weights for policy 0, policy_version 73550 (0.0008) -[2023-10-12 06:20:00,760][78091] Updated weights for policy 0, policy_version 73560 (0.0007) -[2023-10-12 06:20:03,965][78123] Updated weights for policy 1, policy_version 73220 (0.0008) -[2023-10-12 06:20:04,338][78123] Updated weights for policy 1, policy_version 73230 (0.0008) -[2023-10-12 06:20:04,716][78123] Updated weights for policy 1, policy_version 73240 (0.0009) -[2023-10-12 06:20:05,109][78091] Updated weights for policy 0, policy_version 73570 (0.0007) -[2023-10-12 06:20:05,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 150339584. Throughput: 0: 1596.9, 1: 1620.6. Samples: 37592864. Policy #0 lag: (min: 31.0, avg: 32.3, max: 56.0) -[2023-10-12 06:20:05,201][77203] Avg episode reward: [(0, '54.370'), (1, '47.770')] -[2023-10-12 06:20:05,471][78091] Updated weights for policy 0, policy_version 73580 (0.0007) -[2023-10-12 06:20:05,843][78091] Updated weights for policy 0, policy_version 73590 (0.0009) -[2023-10-12 06:20:06,211][78091] Updated weights for policy 0, policy_version 73600 (0.0007) -[2023-10-12 06:20:09,050][78123] Updated weights for policy 1, policy_version 73250 (0.0008) -[2023-10-12 06:20:09,419][78123] Updated weights for policy 1, policy_version 73260 (0.0009) -[2023-10-12 06:20:09,793][78123] Updated weights for policy 1, policy_version 73270 (0.0009) -[2023-10-12 06:20:10,154][78123] Updated weights for policy 1, policy_version 73280 (0.0009) -[2023-10-12 06:20:10,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 150405120. Throughput: 0: 1614.5, 1: 1603.8. Samples: 37611576. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-10-12 06:20:10,202][77203] Avg episode reward: [(0, '59.700'), (1, '47.970')] -[2023-10-12 06:20:10,416][78091] Updated weights for policy 0, policy_version 73610 (0.0008) -[2023-10-12 06:20:10,781][78091] Updated weights for policy 0, policy_version 73620 (0.0007) -[2023-10-12 06:20:11,156][78091] Updated weights for policy 0, policy_version 73630 (0.0007) -[2023-10-12 06:20:14,330][78123] Updated weights for policy 1, policy_version 73290 (0.0007) -[2023-10-12 06:20:14,697][78123] Updated weights for policy 1, policy_version 73300 (0.0010) -[2023-10-12 06:20:15,058][78123] Updated weights for policy 1, policy_version 73310 (0.0010) -[2023-10-12 06:20:15,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 150470656. Throughput: 0: 1595.5, 1: 1596.8. Samples: 37621040. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-10-12 06:20:15,202][77203] Avg episode reward: [(0, '57.220'), (1, '46.460')] -[2023-10-12 06:20:15,584][78091] Updated weights for policy 0, policy_version 73640 (0.0009) -[2023-10-12 06:20:15,951][78091] Updated weights for policy 0, policy_version 73650 (0.0011) -[2023-10-12 06:20:16,327][78091] Updated weights for policy 0, policy_version 73660 (0.0008) -[2023-10-12 06:20:19,456][78123] Updated weights for policy 1, policy_version 73320 (0.0008) -[2023-10-12 06:20:19,821][78123] Updated weights for policy 1, policy_version 73330 (0.0007) -[2023-10-12 06:20:20,197][78123] Updated weights for policy 1, policy_version 73340 (0.0008) -[2023-10-12 06:20:20,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 150503424. Throughput: 0: 1592.1, 1: 1606.8. Samples: 37640388. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-10-12 06:20:20,202][77203] Avg episode reward: [(0, '49.530'), (1, '53.480')] -[2023-10-12 06:20:20,715][78091] Updated weights for policy 0, policy_version 73670 (0.0009) -[2023-10-12 06:20:21,079][78091] Updated weights for policy 0, policy_version 73680 (0.0010) -[2023-10-12 06:20:21,448][78091] Updated weights for policy 0, policy_version 73690 (0.0010) -[2023-10-12 06:20:24,574][78123] Updated weights for policy 1, policy_version 73350 (0.0009) -[2023-10-12 06:20:24,945][78123] Updated weights for policy 1, policy_version 73360 (0.0010) -[2023-10-12 06:20:25,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 150568960. Throughput: 0: 1600.0, 1: 1614.5. Samples: 37659706. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-10-12 06:20:25,201][77203] Avg episode reward: [(0, '51.560'), (1, '54.660')] -[2023-10-12 06:20:25,316][78123] Updated weights for policy 1, policy_version 73370 (0.0010) -[2023-10-12 06:20:25,788][78091] Updated weights for policy 0, policy_version 73700 (0.0009) -[2023-10-12 06:20:26,169][78091] Updated weights for policy 0, policy_version 73710 (0.0007) -[2023-10-12 06:20:26,536][78091] Updated weights for policy 0, policy_version 73720 (0.0010) -[2023-10-12 06:20:29,633][78123] Updated weights for policy 1, policy_version 73380 (0.0009) -[2023-10-12 06:20:29,986][78123] Updated weights for policy 1, policy_version 73390 (0.0008) -[2023-10-12 06:20:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 150634496. Throughput: 0: 1590.4, 1: 1595.8. Samples: 37668718. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-10-12 06:20:30,202][77203] Avg episode reward: [(0, '57.460'), (1, '45.410')] -[2023-10-12 06:20:30,353][78123] Updated weights for policy 1, policy_version 73400 (0.0007) -[2023-10-12 06:20:30,485][78091] Updated weights for policy 0, policy_version 73730 (0.0009) -[2023-10-12 06:20:30,854][78091] Updated weights for policy 0, policy_version 73740 (0.0008) -[2023-10-12 06:20:31,231][78091] Updated weights for policy 0, policy_version 73750 (0.0008) -[2023-10-12 06:20:31,606][78091] Updated weights for policy 0, policy_version 73760 (0.0007) -[2023-10-12 06:20:34,780][78123] Updated weights for policy 1, policy_version 73410 (0.0007) -[2023-10-12 06:20:35,143][78123] Updated weights for policy 1, policy_version 73420 (0.0008) -[2023-10-12 06:20:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 150700032. Throughput: 0: 1594.7, 1: 1593.2. Samples: 37688372. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-10-12 06:20:35,201][77203] Avg episode reward: [(0, '54.000'), (1, '46.470')] -[2023-10-12 06:20:35,517][78123] Updated weights for policy 1, policy_version 73430 (0.0008) -[2023-10-12 06:20:35,885][78123] Updated weights for policy 1, policy_version 73440 (0.0007) -[2023-10-12 06:20:35,942][78091] Updated weights for policy 0, policy_version 73770 (0.0009) -[2023-10-12 06:20:36,317][78091] Updated weights for policy 0, policy_version 73780 (0.0009) -[2023-10-12 06:20:36,687][78091] Updated weights for policy 0, policy_version 73790 (0.0010) -[2023-10-12 06:20:40,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 150765568. Throughput: 0: 1599.7, 1: 1600.9. Samples: 37707478. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-10-12 06:20:40,201][77203] Avg episode reward: [(0, '54.410'), (1, '48.800')] -[2023-10-12 06:20:40,371][78123] Updated weights for policy 1, policy_version 73450 (0.0009) -[2023-10-12 06:20:40,739][78123] Updated weights for policy 1, policy_version 73460 (0.0009) -[2023-10-12 06:20:41,054][78091] Updated weights for policy 0, policy_version 73800 (0.0007) -[2023-10-12 06:20:41,115][78123] Updated weights for policy 1, policy_version 73470 (0.0008) -[2023-10-12 06:20:41,423][78091] Updated weights for policy 0, policy_version 73810 (0.0009) -[2023-10-12 06:20:41,797][78091] Updated weights for policy 0, policy_version 73820 (0.0007) -[2023-10-12 06:20:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 150831104. Throughput: 0: 1595.4, 1: 1582.2. Samples: 37716238. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-10-12 06:20:45,201][77203] Avg episode reward: [(0, '58.680'), (1, '50.900')] -[2023-10-12 06:20:45,444][78123] Updated weights for policy 1, policy_version 73480 (0.0007) -[2023-10-12 06:20:45,808][78123] Updated weights for policy 1, policy_version 73490 (0.0007) -[2023-10-12 06:20:46,140][78091] Updated weights for policy 0, policy_version 73830 (0.0008) -[2023-10-12 06:20:46,185][78123] Updated weights for policy 1, policy_version 73500 (0.0007) -[2023-10-12 06:20:46,516][78091] Updated weights for policy 0, policy_version 73840 (0.0008) -[2023-10-12 06:20:46,882][78091] Updated weights for policy 0, policy_version 73850 (0.0008) -[2023-10-12 06:20:50,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 150896640. Throughput: 0: 1592.1, 1: 1579.2. Samples: 37735572. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-10-12 06:20:50,201][77203] Avg episode reward: [(0, '51.770'), (1, '49.990')] -[2023-10-12 06:20:50,354][78123] Updated weights for policy 1, policy_version 73510 (0.0008) -[2023-10-12 06:20:50,711][78123] Updated weights for policy 1, policy_version 73520 (0.0008) -[2023-10-12 06:20:51,084][78123] Updated weights for policy 1, policy_version 73530 (0.0010) -[2023-10-12 06:20:51,342][78091] Updated weights for policy 0, policy_version 73860 (0.0008) -[2023-10-12 06:20:51,707][78091] Updated weights for policy 0, policy_version 73870 (0.0007) -[2023-10-12 06:20:52,080][78091] Updated weights for policy 0, policy_version 73880 (0.0007) -[2023-10-12 06:20:55,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 150962176. Throughput: 0: 1590.1, 1: 1599.7. Samples: 37755118. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-12 06:20:55,202][77203] Avg episode reward: [(0, '60.540'), (1, '47.900')] -[2023-10-12 06:20:55,334][78123] Updated weights for policy 1, policy_version 73540 (0.0008) -[2023-10-12 06:20:55,708][78123] Updated weights for policy 1, policy_version 73550 (0.0008) -[2023-10-12 06:20:56,080][78123] Updated weights for policy 1, policy_version 73560 (0.0010) -[2023-10-12 06:20:56,473][78091] Updated weights for policy 0, policy_version 73890 (0.0008) -[2023-10-12 06:20:56,841][78091] Updated weights for policy 0, policy_version 73900 (0.0010) -[2023-10-12 06:20:57,215][78091] Updated weights for policy 0, policy_version 73910 (0.0008) -[2023-10-12 06:20:57,592][78091] Updated weights for policy 0, policy_version 73920 (0.0007) -[2023-10-12 06:21:00,201][77203] Fps is (10 sec: 13106.8, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 151027712. Throughput: 0: 1589.3, 1: 1579.8. Samples: 37763650. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-12 06:21:00,202][77203] Avg episode reward: [(0, '57.590'), (1, '44.880')] -[2023-10-12 06:21:00,485][78123] Updated weights for policy 1, policy_version 73570 (0.0008) -[2023-10-12 06:21:00,842][78123] Updated weights for policy 1, policy_version 73580 (0.0007) -[2023-10-12 06:21:01,208][78123] Updated weights for policy 1, policy_version 73590 (0.0009) -[2023-10-12 06:21:01,580][78123] Updated weights for policy 1, policy_version 73600 (0.0010) -[2023-10-12 06:21:01,649][78091] Updated weights for policy 0, policy_version 73930 (0.0008) -[2023-10-12 06:21:02,026][78091] Updated weights for policy 0, policy_version 73940 (0.0007) -[2023-10-12 06:21:02,390][78091] Updated weights for policy 0, policy_version 73950 (0.0007) -[2023-10-12 06:21:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 151093248. Throughput: 0: 1607.0, 1: 1582.3. Samples: 37783906. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-12 06:21:05,202][77203] Avg episode reward: [(0, '62.840'), (1, '54.380')] -[2023-10-12 06:21:05,945][78123] Updated weights for policy 1, policy_version 73610 (0.0008) -[2023-10-12 06:21:06,320][78123] Updated weights for policy 1, policy_version 73620 (0.0007) -[2023-10-12 06:21:06,502][78091] Updated weights for policy 0, policy_version 73960 (0.0007) -[2023-10-12 06:21:06,682][78123] Updated weights for policy 1, policy_version 73630 (0.0008) -[2023-10-12 06:21:06,873][78091] Updated weights for policy 0, policy_version 73970 (0.0010) -[2023-10-12 06:21:07,245][78091] Updated weights for policy 0, policy_version 73980 (0.0010) -[2023-10-12 06:21:10,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 151158784. Throughput: 0: 1613.2, 1: 1590.9. Samples: 37803888. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-12 06:21:10,201][77203] Avg episode reward: [(0, '55.160'), (1, '51.600')] -[2023-10-12 06:21:10,209][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000073632_75399168.pth... -[2023-10-12 06:21:10,209][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000073984_75759616.pth... -[2023-10-12 06:21:10,240][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000072160_73891840.pth -[2023-10-12 06:21:10,240][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000072480_74219520.pth -[2023-10-12 06:21:11,165][78123] Updated weights for policy 1, policy_version 73640 (0.0009) -[2023-10-12 06:21:11,280][78091] Updated weights for policy 0, policy_version 73990 (0.0009) -[2023-10-12 06:21:11,536][78123] Updated weights for policy 1, policy_version 73650 (0.0007) -[2023-10-12 06:21:11,650][78091] Updated weights for policy 0, policy_version 74000 (0.0009) -[2023-10-12 06:21:11,905][78123] Updated weights for policy 1, policy_version 73660 (0.0007) -[2023-10-12 06:21:12,019][78091] Updated weights for policy 0, policy_version 74010 (0.0008) -[2023-10-12 06:21:15,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 151224320. Throughput: 0: 1612.7, 1: 1580.2. Samples: 37812400. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-12 06:21:15,202][77203] Avg episode reward: [(0, '62.860'), (1, '46.700')] -[2023-10-12 06:21:16,223][78123] Updated weights for policy 1, policy_version 73670 (0.0008) -[2023-10-12 06:21:16,387][78091] Updated weights for policy 0, policy_version 74020 (0.0008) -[2023-10-12 06:21:16,581][78123] Updated weights for policy 1, policy_version 73680 (0.0009) -[2023-10-12 06:21:16,755][78091] Updated weights for policy 0, policy_version 74030 (0.0010) -[2023-10-12 06:21:16,950][78123] Updated weights for policy 1, policy_version 73690 (0.0008) -[2023-10-12 06:21:17,124][78091] Updated weights for policy 0, policy_version 74040 (0.0007) -[2023-10-12 06:21:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 151289856. Throughput: 0: 1609.6, 1: 1582.9. Samples: 37832036. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-12 06:21:20,201][77203] Avg episode reward: [(0, '50.370'), (1, '45.400')] -[2023-10-12 06:21:21,329][78123] Updated weights for policy 1, policy_version 73700 (0.0009) -[2023-10-12 06:21:21,494][78091] Updated weights for policy 0, policy_version 74050 (0.0008) -[2023-10-12 06:21:21,699][78123] Updated weights for policy 1, policy_version 73710 (0.0010) -[2023-10-12 06:21:21,862][78091] Updated weights for policy 0, policy_version 74060 (0.0007) -[2023-10-12 06:21:22,063][78123] Updated weights for policy 1, policy_version 73720 (0.0008) -[2023-10-12 06:21:22,232][78091] Updated weights for policy 0, policy_version 74070 (0.0009) -[2023-10-12 06:21:22,595][78091] Updated weights for policy 0, policy_version 74080 (0.0010) -[2023-10-12 06:21:25,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 151355392. Throughput: 0: 1607.8, 1: 1589.7. Samples: 37851364. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-12 06:21:25,202][77203] Avg episode reward: [(0, '55.480'), (1, '44.340')] -[2023-10-12 06:21:26,427][78123] Updated weights for policy 1, policy_version 73730 (0.0008) -[2023-10-12 06:21:26,781][78123] Updated weights for policy 1, policy_version 73740 (0.0010) -[2023-10-12 06:21:26,926][78091] Updated weights for policy 0, policy_version 74090 (0.0010) -[2023-10-12 06:21:27,148][78123] Updated weights for policy 1, policy_version 73750 (0.0008) -[2023-10-12 06:21:27,301][78091] Updated weights for policy 0, policy_version 74100 (0.0009) -[2023-10-12 06:21:27,516][78123] Updated weights for policy 1, policy_version 73760 (0.0007) -[2023-10-12 06:21:27,661][78091] Updated weights for policy 0, policy_version 74110 (0.0008) -[2023-10-12 06:21:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 151420928. Throughput: 0: 1606.1, 1: 1586.6. Samples: 37859910. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-12 06:21:30,202][77203] Avg episode reward: [(0, '60.790'), (1, '58.490')] -[2023-10-12 06:21:31,594][78123] Updated weights for policy 1, policy_version 73770 (0.0007) -[2023-10-12 06:21:31,957][78123] Updated weights for policy 1, policy_version 73780 (0.0007) -[2023-10-12 06:21:32,083][78091] Updated weights for policy 0, policy_version 74120 (0.0007) -[2023-10-12 06:21:32,315][78123] Updated weights for policy 1, policy_version 73790 (0.0008) -[2023-10-12 06:21:32,444][78091] Updated weights for policy 0, policy_version 74130 (0.0008) -[2023-10-12 06:21:32,823][78091] Updated weights for policy 0, policy_version 74140 (0.0009) -[2023-10-12 06:21:35,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 151486464. Throughput: 0: 1605.1, 1: 1594.7. Samples: 37879566. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-12 06:21:35,202][77203] Avg episode reward: [(0, '60.870'), (1, '48.450')] -[2023-10-12 06:21:36,679][78123] Updated weights for policy 1, policy_version 73800 (0.0008) -[2023-10-12 06:21:37,044][78123] Updated weights for policy 1, policy_version 73810 (0.0007) -[2023-10-12 06:21:37,171][78091] Updated weights for policy 0, policy_version 74150 (0.0010) -[2023-10-12 06:21:37,410][78123] Updated weights for policy 1, policy_version 73820 (0.0007) -[2023-10-12 06:21:37,533][78091] Updated weights for policy 0, policy_version 74160 (0.0009) -[2023-10-12 06:21:37,906][78091] Updated weights for policy 0, policy_version 74170 (0.0011) -[2023-10-12 06:21:40,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 151552000. Throughput: 0: 1605.7, 1: 1593.2. Samples: 37899068. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-12 06:21:40,201][77203] Avg episode reward: [(0, '63.280'), (1, '46.890')] -[2023-10-12 06:21:41,742][78123] Updated weights for policy 1, policy_version 73830 (0.0008) -[2023-10-12 06:21:42,109][78123] Updated weights for policy 1, policy_version 73840 (0.0010) -[2023-10-12 06:21:42,145][78091] Updated weights for policy 0, policy_version 74180 (0.0009) -[2023-10-12 06:21:42,470][78123] Updated weights for policy 1, policy_version 73850 (0.0008) -[2023-10-12 06:21:42,513][78091] Updated weights for policy 0, policy_version 74190 (0.0007) -[2023-10-12 06:21:42,886][78091] Updated weights for policy 0, policy_version 74200 (0.0008) -[2023-10-12 06:21:45,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 151617536. Throughput: 0: 1619.2, 1: 1594.9. Samples: 37908284. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-10-12 06:21:45,201][77203] Avg episode reward: [(0, '49.780'), (1, '48.910')] -[2023-10-12 06:21:46,879][78123] Updated weights for policy 1, policy_version 73860 (0.0008) -[2023-10-12 06:21:47,245][78123] Updated weights for policy 1, policy_version 73870 (0.0008) -[2023-10-12 06:21:47,266][78091] Updated weights for policy 0, policy_version 74210 (0.0009) -[2023-10-12 06:21:47,615][78123] Updated weights for policy 1, policy_version 73880 (0.0010) -[2023-10-12 06:21:47,638][78091] Updated weights for policy 0, policy_version 74220 (0.0008) -[2023-10-12 06:21:48,006][78091] Updated weights for policy 0, policy_version 74230 (0.0011) -[2023-10-12 06:21:48,383][78091] Updated weights for policy 0, policy_version 74240 (0.0009) -[2023-10-12 06:21:50,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 151683072. Throughput: 0: 1591.9, 1: 1590.2. Samples: 37927098. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-10-12 06:21:50,201][77203] Avg episode reward: [(0, '55.640'), (1, '48.700')] -[2023-10-12 06:21:51,876][78123] Updated weights for policy 1, policy_version 73890 (0.0010) -[2023-10-12 06:21:52,243][78123] Updated weights for policy 1, policy_version 73900 (0.0009) -[2023-10-12 06:21:52,611][78123] Updated weights for policy 1, policy_version 73910 (0.0009) -[2023-10-12 06:21:52,742][78091] Updated weights for policy 0, policy_version 74250 (0.0009) -[2023-10-12 06:21:52,971][78123] Updated weights for policy 1, policy_version 73920 (0.0009) -[2023-10-12 06:21:53,104][78091] Updated weights for policy 0, policy_version 74260 (0.0010) -[2023-10-12 06:21:53,474][78091] Updated weights for policy 0, policy_version 74270 (0.0008) -[2023-10-12 06:21:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 12885.0). Total num frames: 151748608. Throughput: 0: 1579.3, 1: 1586.8. Samples: 37946364. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-10-12 06:21:55,201][77203] Avg episode reward: [(0, '52.270'), (1, '48.770')] -[2023-10-12 06:21:57,438][78123] Updated weights for policy 1, policy_version 73930 (0.0009) -[2023-10-12 06:21:57,808][78123] Updated weights for policy 1, policy_version 73940 (0.0010) -[2023-10-12 06:21:57,858][78091] Updated weights for policy 0, policy_version 74280 (0.0009) -[2023-10-12 06:21:58,166][78123] Updated weights for policy 1, policy_version 73950 (0.0008) -[2023-10-12 06:21:58,226][78091] Updated weights for policy 0, policy_version 74290 (0.0009) -[2023-10-12 06:21:58,588][78091] Updated weights for policy 0, policy_version 74300 (0.0007) -[2023-10-12 06:22:00,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 12885.0). Total num frames: 151814144. Throughput: 0: 1600.8, 1: 1599.2. Samples: 37956402. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-10-12 06:22:00,201][77203] Avg episode reward: [(0, '55.630'), (1, '42.190')] -[2023-10-12 06:22:02,408][78123] Updated weights for policy 1, policy_version 73960 (0.0008) -[2023-10-12 06:22:02,773][78123] Updated weights for policy 1, policy_version 73970 (0.0007) -[2023-10-12 06:22:02,924][78091] Updated weights for policy 0, policy_version 74310 (0.0009) -[2023-10-12 06:22:03,150][78123] Updated weights for policy 1, policy_version 73980 (0.0007) -[2023-10-12 06:22:03,293][78091] Updated weights for policy 0, policy_version 74320 (0.0009) -[2023-10-12 06:22:03,662][78091] Updated weights for policy 0, policy_version 74330 (0.0008) -[2023-10-12 06:22:05,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 151879680. Throughput: 0: 1581.2, 1: 1587.1. Samples: 37974608. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-10-12 06:22:05,202][77203] Avg episode reward: [(0, '55.500'), (1, '45.500')] -[2023-10-12 06:22:07,521][78123] Updated weights for policy 1, policy_version 73990 (0.0008) -[2023-10-12 06:22:07,896][78123] Updated weights for policy 1, policy_version 74000 (0.0008) -[2023-10-12 06:22:08,017][78091] Updated weights for policy 0, policy_version 74340 (0.0009) -[2023-10-12 06:22:08,254][78123] Updated weights for policy 1, policy_version 74010 (0.0008) -[2023-10-12 06:22:08,387][78091] Updated weights for policy 0, policy_version 74350 (0.0008) -[2023-10-12 06:22:08,761][78091] Updated weights for policy 0, policy_version 74360 (0.0008) -[2023-10-12 06:22:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 151945216. Throughput: 0: 1578.9, 1: 1591.9. Samples: 37994048. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-10-12 06:22:10,201][77203] Avg episode reward: [(0, '52.550'), (1, '49.810')] -[2023-10-12 06:22:12,699][78123] Updated weights for policy 1, policy_version 74020 (0.0009) -[2023-10-12 06:22:13,072][78123] Updated weights for policy 1, policy_version 74030 (0.0009) -[2023-10-12 06:22:13,134][78091] Updated weights for policy 0, policy_version 74370 (0.0009) -[2023-10-12 06:22:13,444][78123] Updated weights for policy 1, policy_version 74040 (0.0009) -[2023-10-12 06:22:13,533][78091] Updated weights for policy 0, policy_version 74380 (0.0009) -[2023-10-12 06:22:13,906][78091] Updated weights for policy 0, policy_version 74390 (0.0009) -[2023-10-12 06:22:14,272][78091] Updated weights for policy 0, policy_version 74400 (0.0008) -[2023-10-12 06:22:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 152010752. Throughput: 0: 1607.0, 1: 1609.1. Samples: 38004636. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-10-12 06:22:15,202][77203] Avg episode reward: [(0, '56.990'), (1, '46.590')] -[2023-10-12 06:22:17,649][78123] Updated weights for policy 1, policy_version 74050 (0.0009) -[2023-10-12 06:22:18,020][78123] Updated weights for policy 1, policy_version 74060 (0.0007) -[2023-10-12 06:22:18,385][78123] Updated weights for policy 1, policy_version 74070 (0.0007) -[2023-10-12 06:22:18,448][78091] Updated weights for policy 0, policy_version 74410 (0.0007) -[2023-10-12 06:22:18,757][78123] Updated weights for policy 1, policy_version 74080 (0.0008) -[2023-10-12 06:22:18,816][78091] Updated weights for policy 0, policy_version 74420 (0.0007) -[2023-10-12 06:22:19,200][78091] Updated weights for policy 0, policy_version 74430 (0.0010) -[2023-10-12 06:22:20,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 152076288. Throughput: 0: 1594.8, 1: 1585.1. Samples: 38022658. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-10-12 06:22:20,202][77203] Avg episode reward: [(0, '53.090'), (1, '51.290')] -[2023-10-12 06:22:23,205][78123] Updated weights for policy 1, policy_version 74090 (0.0008) -[2023-10-12 06:22:23,441][78091] Updated weights for policy 0, policy_version 74440 (0.0009) -[2023-10-12 06:22:23,563][78123] Updated weights for policy 1, policy_version 74100 (0.0007) -[2023-10-12 06:22:23,812][78091] Updated weights for policy 0, policy_version 74450 (0.0007) -[2023-10-12 06:22:23,929][78123] Updated weights for policy 1, policy_version 74110 (0.0009) -[2023-10-12 06:22:24,170][78091] Updated weights for policy 0, policy_version 74460 (0.0007) -[2023-10-12 06:22:25,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 152141824. Throughput: 0: 1584.4, 1: 1579.3. Samples: 38041438. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-10-12 06:22:25,202][77203] Avg episode reward: [(0, '64.210'), (1, '46.980')] -[2023-10-12 06:22:28,290][78123] Updated weights for policy 1, policy_version 74120 (0.0009) -[2023-10-12 06:22:28,313][78091] Updated weights for policy 0, policy_version 74470 (0.0009) -[2023-10-12 06:22:28,650][78123] Updated weights for policy 1, policy_version 74130 (0.0008) -[2023-10-12 06:22:28,680][78091] Updated weights for policy 0, policy_version 74480 (0.0008) -[2023-10-12 06:22:29,017][78123] Updated weights for policy 1, policy_version 74140 (0.0008) -[2023-10-12 06:22:29,045][78091] Updated weights for policy 0, policy_version 74490 (0.0009) -[2023-10-12 06:22:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 152207360. Throughput: 0: 1600.1, 1: 1604.5. Samples: 38052492. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-10-12 06:22:30,202][77203] Avg episode reward: [(0, '56.440'), (1, '48.570')] -[2023-10-12 06:22:33,233][78091] Updated weights for policy 0, policy_version 74500 (0.0009) -[2023-10-12 06:22:33,359][78123] Updated weights for policy 1, policy_version 74150 (0.0008) -[2023-10-12 06:22:33,614][78091] Updated weights for policy 0, policy_version 74510 (0.0010) -[2023-10-12 06:22:33,734][78123] Updated weights for policy 1, policy_version 74160 (0.0009) -[2023-10-12 06:22:33,979][78091] Updated weights for policy 0, policy_version 74520 (0.0009) -[2023-10-12 06:22:34,106][78123] Updated weights for policy 1, policy_version 74170 (0.0010) -[2023-10-12 06:22:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 152272896. Throughput: 0: 1604.8, 1: 1595.9. Samples: 38071130. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-12 06:22:35,202][77203] Avg episode reward: [(0, '57.830'), (1, '49.800')] -[2023-10-12 06:22:38,285][78123] Updated weights for policy 1, policy_version 74180 (0.0009) -[2023-10-12 06:22:38,322][78091] Updated weights for policy 0, policy_version 74530 (0.0008) -[2023-10-12 06:22:38,648][78123] Updated weights for policy 1, policy_version 74190 (0.0009) -[2023-10-12 06:22:38,692][78091] Updated weights for policy 0, policy_version 74540 (0.0009) -[2023-10-12 06:22:39,013][78123] Updated weights for policy 1, policy_version 74200 (0.0009) -[2023-10-12 06:22:39,055][78091] Updated weights for policy 0, policy_version 74550 (0.0011) -[2023-10-12 06:22:39,421][78091] Updated weights for policy 0, policy_version 74560 (0.0010) -[2023-10-12 06:22:40,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 152338432. Throughput: 0: 1596.6, 1: 1589.6. Samples: 38089744. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-12 06:22:40,201][77203] Avg episode reward: [(0, '60.820'), (1, '47.920')] -[2023-10-12 06:22:43,404][78123] Updated weights for policy 1, policy_version 74210 (0.0009) -[2023-10-12 06:22:43,769][78091] Updated weights for policy 0, policy_version 74570 (0.0008) -[2023-10-12 06:22:43,826][78123] Updated weights for policy 1, policy_version 74220 (0.0008) -[2023-10-12 06:22:44,132][78091] Updated weights for policy 0, policy_version 74580 (0.0008) -[2023-10-12 06:22:44,186][78123] Updated weights for policy 1, policy_version 74230 (0.0008) -[2023-10-12 06:22:44,509][78091] Updated weights for policy 0, policy_version 74590 (0.0007) -[2023-10-12 06:22:44,547][78123] Updated weights for policy 1, policy_version 74240 (0.0009) -[2023-10-12 06:22:45,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 152403968. Throughput: 0: 1598.6, 1: 1605.2. Samples: 38100574. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-12 06:22:45,202][77203] Avg episode reward: [(0, '59.810'), (1, '52.950')] -[2023-10-12 06:22:48,909][78091] Updated weights for policy 0, policy_version 74600 (0.0008) -[2023-10-12 06:22:48,976][78123] Updated weights for policy 1, policy_version 74250 (0.0009) -[2023-10-12 06:22:49,273][78091] Updated weights for policy 0, policy_version 74610 (0.0009) -[2023-10-12 06:22:49,345][78123] Updated weights for policy 1, policy_version 74260 (0.0009) -[2023-10-12 06:22:49,647][78091] Updated weights for policy 0, policy_version 74620 (0.0008) -[2023-10-12 06:22:49,704][78123] Updated weights for policy 1, policy_version 74270 (0.0008) -[2023-10-12 06:22:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 152469504. Throughput: 0: 1613.4, 1: 1605.4. Samples: 38119452. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-12 06:22:50,201][77203] Avg episode reward: [(0, '48.870'), (1, '51.560')] -[2023-10-12 06:22:53,950][78091] Updated weights for policy 0, policy_version 74630 (0.0010) -[2023-10-12 06:22:54,062][78123] Updated weights for policy 1, policy_version 74280 (0.0009) -[2023-10-12 06:22:54,318][78091] Updated weights for policy 0, policy_version 74640 (0.0009) -[2023-10-12 06:22:54,426][78123] Updated weights for policy 1, policy_version 74290 (0.0007) -[2023-10-12 06:22:54,689][78091] Updated weights for policy 0, policy_version 74650 (0.0007) -[2023-10-12 06:22:54,786][78123] Updated weights for policy 1, policy_version 74300 (0.0009) -[2023-10-12 06:22:55,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.1, 300 sec: 12885.0). Total num frames: 152535040. Throughput: 0: 1601.0, 1: 1582.7. Samples: 38137318. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-12 06:22:55,202][77203] Avg episode reward: [(0, '49.880'), (1, '52.270')] -[2023-10-12 06:22:59,066][78091] Updated weights for policy 0, policy_version 74660 (0.0008) -[2023-10-12 06:22:59,103][78123] Updated weights for policy 1, policy_version 74310 (0.0008) -[2023-10-12 06:22:59,464][78123] Updated weights for policy 1, policy_version 74320 (0.0007) -[2023-10-12 06:22:59,466][78091] Updated weights for policy 0, policy_version 74670 (0.0008) -[2023-10-12 06:22:59,823][78123] Updated weights for policy 1, policy_version 74330 (0.0007) -[2023-10-12 06:22:59,840][78091] Updated weights for policy 0, policy_version 74680 (0.0009) -[2023-10-12 06:23:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 152600576. Throughput: 0: 1597.2, 1: 1587.4. Samples: 38147942. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-12 06:23:00,201][77203] Avg episode reward: [(0, '61.420'), (1, '51.670')] -[2023-10-12 06:23:03,985][78123] Updated weights for policy 1, policy_version 74340 (0.0008) -[2023-10-12 06:23:04,286][78091] Updated weights for policy 0, policy_version 74690 (0.0009) -[2023-10-12 06:23:04,354][78123] Updated weights for policy 1, policy_version 74350 (0.0008) -[2023-10-12 06:23:04,659][78091] Updated weights for policy 0, policy_version 74700 (0.0010) -[2023-10-12 06:23:04,724][78123] Updated weights for policy 1, policy_version 74360 (0.0009) -[2023-10-12 06:23:05,039][78091] Updated weights for policy 0, policy_version 74710 (0.0009) -[2023-10-12 06:23:05,201][77203] Fps is (10 sec: 9830.6, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 152633344. Throughput: 0: 1605.2, 1: 1608.8. Samples: 38167286. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-12 06:23:05,202][77203] Avg episode reward: [(0, '63.450'), (1, '56.520')] -[2023-10-12 06:23:05,404][78091] Updated weights for policy 0, policy_version 74720 (0.0007) -[2023-10-12 06:23:08,976][78123] Updated weights for policy 1, policy_version 74370 (0.0007) -[2023-10-12 06:23:09,352][78123] Updated weights for policy 1, policy_version 74380 (0.0008) -[2023-10-12 06:23:09,647][78091] Updated weights for policy 0, policy_version 74730 (0.0007) -[2023-10-12 06:23:09,719][78123] Updated weights for policy 1, policy_version 74390 (0.0009) -[2023-10-12 06:23:10,019][78091] Updated weights for policy 0, policy_version 74740 (0.0007) -[2023-10-12 06:23:10,073][78123] Updated weights for policy 1, policy_version 74400 (0.0007) -[2023-10-12 06:23:10,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 152698880. Throughput: 0: 1608.5, 1: 1598.1. Samples: 38185736. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-12 06:23:10,201][77203] Avg episode reward: [(0, '61.130'), (1, '50.870')] -[2023-10-12 06:23:10,208][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000074400_76185600.pth... -[2023-10-12 06:23:10,243][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000072896_74645504.pth -[2023-10-12 06:23:10,247][77950] Saving a milestone ./train_atari/atari_hero_APPO/checkpoint_p1/milestones/checkpoint_000074400_76185600.pth -[2023-10-12 06:23:10,395][78091] Updated weights for policy 0, policy_version 74750 (0.0007) -[2023-10-12 06:23:10,458][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000074752_76546048.pth... -[2023-10-12 06:23:10,487][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000073248_75005952.pth -[2023-10-12 06:23:10,491][77792] Saving a milestone ./train_atari/atari_hero_APPO/checkpoint_p0/milestones/checkpoint_000074752_76546048.pth -[2023-10-12 06:23:14,378][78123] Updated weights for policy 1, policy_version 74410 (0.0012) -[2023-10-12 06:23:14,750][78123] Updated weights for policy 1, policy_version 74420 (0.0009) -[2023-10-12 06:23:14,760][78091] Updated weights for policy 0, policy_version 74760 (0.0009) -[2023-10-12 06:23:15,116][78123] Updated weights for policy 1, policy_version 74430 (0.0008) -[2023-10-12 06:23:15,126][78091] Updated weights for policy 0, policy_version 74770 (0.0007) -[2023-10-12 06:23:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 152764416. Throughput: 0: 1589.2, 1: 1587.8. Samples: 38195458. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-12 06:23:15,202][77203] Avg episode reward: [(0, '54.820'), (1, '44.650')] -[2023-10-12 06:23:15,499][78091] Updated weights for policy 0, policy_version 74780 (0.0007) -[2023-10-12 06:23:19,487][78123] Updated weights for policy 1, policy_version 74440 (0.0009) -[2023-10-12 06:23:19,857][78123] Updated weights for policy 1, policy_version 74450 (0.0008) -[2023-10-12 06:23:19,871][78091] Updated weights for policy 0, policy_version 74790 (0.0008) -[2023-10-12 06:23:20,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 152797184. Throughput: 0: 1598.5, 1: 1597.5. Samples: 38214950. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-12 06:23:20,201][77203] Avg episode reward: [(0, '57.320'), (1, '45.490')] -[2023-10-12 06:23:20,220][78123] Updated weights for policy 1, policy_version 74460 (0.0008) -[2023-10-12 06:23:20,248][78091] Updated weights for policy 0, policy_version 74800 (0.0009) -[2023-10-12 06:23:20,602][78091] Updated weights for policy 0, policy_version 74810 (0.0009) -[2023-10-12 06:23:24,642][78123] Updated weights for policy 1, policy_version 74470 (0.0009) -[2023-10-12 06:23:24,964][78091] Updated weights for policy 0, policy_version 74820 (0.0010) -[2023-10-12 06:23:25,002][78123] Updated weights for policy 1, policy_version 74480 (0.0009) -[2023-10-12 06:23:25,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 152862720. Throughput: 0: 1609.7, 1: 1602.2. Samples: 38234280. Policy #0 lag: (min: 18.0, avg: 18.2, max: 29.0) -[2023-10-12 06:23:25,202][77203] Avg episode reward: [(0, '55.850'), (1, '47.950')] -[2023-10-12 06:23:25,335][78091] Updated weights for policy 0, policy_version 74830 (0.0008) -[2023-10-12 06:23:25,369][78123] Updated weights for policy 1, policy_version 74490 (0.0010) -[2023-10-12 06:23:25,700][78091] Updated weights for policy 0, policy_version 74840 (0.0010) -[2023-10-12 06:23:29,781][78123] Updated weights for policy 1, policy_version 74500 (0.0009) -[2023-10-12 06:23:30,028][78091] Updated weights for policy 0, policy_version 74850 (0.0007) -[2023-10-12 06:23:30,155][78123] Updated weights for policy 1, policy_version 74510 (0.0009) -[2023-10-12 06:23:30,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 152928256. Throughput: 0: 1585.7, 1: 1582.6. Samples: 38243148. Policy #0 lag: (min: 18.0, avg: 18.2, max: 29.0) -[2023-10-12 06:23:30,201][77203] Avg episode reward: [(0, '66.500'), (1, '56.310')] -[2023-10-12 06:23:30,394][78091] Updated weights for policy 0, policy_version 74860 (0.0007) -[2023-10-12 06:23:30,521][78123] Updated weights for policy 1, policy_version 74520 (0.0007) -[2023-10-12 06:23:30,759][78091] Updated weights for policy 0, policy_version 74870 (0.0007) -[2023-10-12 06:23:31,132][78091] Updated weights for policy 0, policy_version 74880 (0.0008) -[2023-10-12 06:23:34,948][78123] Updated weights for policy 1, policy_version 74530 (0.0008) -[2023-10-12 06:23:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 152993792. Throughput: 0: 1583.4, 1: 1594.2. Samples: 38262442. Policy #0 lag: (min: 18.0, avg: 18.2, max: 29.0) -[2023-10-12 06:23:35,202][77203] Avg episode reward: [(0, '56.290'), (1, '51.680')] -[2023-10-12 06:23:35,313][78123] Updated weights for policy 1, policy_version 74540 (0.0007) -[2023-10-12 06:23:35,459][78091] Updated weights for policy 0, policy_version 74890 (0.0008) -[2023-10-12 06:23:35,682][78123] Updated weights for policy 1, policy_version 74550 (0.0009) -[2023-10-12 06:23:35,839][78091] Updated weights for policy 0, policy_version 74900 (0.0008) -[2023-10-12 06:23:36,049][78123] Updated weights for policy 1, policy_version 74560 (0.0007) -[2023-10-12 06:23:36,201][78091] Updated weights for policy 0, policy_version 74910 (0.0009) -[2023-10-12 06:23:40,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 153059328. Throughput: 0: 1602.4, 1: 1609.6. Samples: 38281858. Policy #0 lag: (min: 18.0, avg: 18.2, max: 29.0) -[2023-10-12 06:23:40,202][77203] Avg episode reward: [(0, '55.260'), (1, '49.090')] -[2023-10-12 06:23:40,428][78123] Updated weights for policy 1, policy_version 74570 (0.0008) -[2023-10-12 06:23:40,505][78091] Updated weights for policy 0, policy_version 74920 (0.0008) -[2023-10-12 06:23:40,798][78123] Updated weights for policy 1, policy_version 74580 (0.0008) -[2023-10-12 06:23:40,883][78091] Updated weights for policy 0, policy_version 74930 (0.0008) -[2023-10-12 06:23:41,174][78123] Updated weights for policy 1, policy_version 74590 (0.0008) -[2023-10-12 06:23:41,242][78091] Updated weights for policy 0, policy_version 74940 (0.0008) -[2023-10-12 06:23:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 153124864. Throughput: 0: 1581.1, 1: 1587.7. Samples: 38290540. Policy #0 lag: (min: 18.0, avg: 18.2, max: 29.0) -[2023-10-12 06:23:45,202][77203] Avg episode reward: [(0, '55.870'), (1, '46.700')] -[2023-10-12 06:23:45,512][78123] Updated weights for policy 1, policy_version 74600 (0.0008) -[2023-10-12 06:23:45,632][78091] Updated weights for policy 0, policy_version 74950 (0.0008) -[2023-10-12 06:23:45,864][78123] Updated weights for policy 1, policy_version 74610 (0.0010) -[2023-10-12 06:23:46,012][78091] Updated weights for policy 0, policy_version 74960 (0.0007) -[2023-10-12 06:23:46,228][78123] Updated weights for policy 1, policy_version 74620 (0.0008) -[2023-10-12 06:23:46,375][78091] Updated weights for policy 0, policy_version 74970 (0.0008) -[2023-10-12 06:23:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 153190400. Throughput: 0: 1590.4, 1: 1583.4. Samples: 38310106. Policy #0 lag: (min: 18.0, avg: 18.2, max: 29.0) -[2023-10-12 06:23:50,202][77203] Avg episode reward: [(0, '63.950'), (1, '48.260')] -[2023-10-12 06:23:50,552][78123] Updated weights for policy 1, policy_version 74630 (0.0009) -[2023-10-12 06:23:50,633][78091] Updated weights for policy 0, policy_version 74980 (0.0008) -[2023-10-12 06:23:50,922][78123] Updated weights for policy 1, policy_version 74640 (0.0009) -[2023-10-12 06:23:51,010][78091] Updated weights for policy 0, policy_version 74990 (0.0009) -[2023-10-12 06:23:51,293][78123] Updated weights for policy 1, policy_version 74650 (0.0009) -[2023-10-12 06:23:51,374][78091] Updated weights for policy 0, policy_version 75000 (0.0008) -[2023-10-12 06:23:55,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 153255936. Throughput: 0: 1600.3, 1: 1596.5. Samples: 38329594. Policy #0 lag: (min: 18.0, avg: 18.2, max: 29.0) -[2023-10-12 06:23:55,202][77203] Avg episode reward: [(0, '63.900'), (1, '57.830')] -[2023-10-12 06:23:55,531][78123] Updated weights for policy 1, policy_version 74660 (0.0009) -[2023-10-12 06:23:55,670][78091] Updated weights for policy 0, policy_version 75010 (0.0009) -[2023-10-12 06:23:55,903][78123] Updated weights for policy 1, policy_version 74670 (0.0009) -[2023-10-12 06:23:56,044][78091] Updated weights for policy 0, policy_version 75020 (0.0007) -[2023-10-12 06:23:56,257][78123] Updated weights for policy 1, policy_version 74680 (0.0009) -[2023-10-12 06:23:56,418][78091] Updated weights for policy 0, policy_version 75030 (0.0007) -[2023-10-12 06:23:56,793][78091] Updated weights for policy 0, policy_version 75040 (0.0009) -[2023-10-12 06:24:00,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 153321472. Throughput: 0: 1591.7, 1: 1578.7. Samples: 38338126. Policy #0 lag: (min: 18.0, avg: 18.2, max: 29.0) -[2023-10-12 06:24:00,202][77203] Avg episode reward: [(0, '58.960'), (1, '46.660')] -[2023-10-12 06:24:00,763][78123] Updated weights for policy 1, policy_version 74690 (0.0007) -[2023-10-12 06:24:00,924][78091] Updated weights for policy 0, policy_version 75050 (0.0009) -[2023-10-12 06:24:01,130][78123] Updated weights for policy 1, policy_version 74700 (0.0008) -[2023-10-12 06:24:01,296][78091] Updated weights for policy 0, policy_version 75060 (0.0009) -[2023-10-12 06:24:01,495][78123] Updated weights for policy 1, policy_version 74710 (0.0008) -[2023-10-12 06:24:01,665][78091] Updated weights for policy 0, policy_version 75070 (0.0008) -[2023-10-12 06:24:01,855][78123] Updated weights for policy 1, policy_version 74720 (0.0007) -[2023-10-12 06:24:05,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 153387008. Throughput: 0: 1591.1, 1: 1577.1. Samples: 38357520. Policy #0 lag: (min: 18.0, avg: 18.2, max: 29.0) -[2023-10-12 06:24:05,202][77203] Avg episode reward: [(0, '57.580'), (1, '41.220')] -[2023-10-12 06:24:06,020][78091] Updated weights for policy 0, policy_version 75080 (0.0008) -[2023-10-12 06:24:06,309][78123] Updated weights for policy 1, policy_version 74730 (0.0009) -[2023-10-12 06:24:06,395][78091] Updated weights for policy 0, policy_version 75090 (0.0009) -[2023-10-12 06:24:06,678][78123] Updated weights for policy 1, policy_version 74740 (0.0010) -[2023-10-12 06:24:06,763][78091] Updated weights for policy 0, policy_version 75100 (0.0008) -[2023-10-12 06:24:07,052][78123] Updated weights for policy 1, policy_version 74750 (0.0009) -[2023-10-12 06:24:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 153452544. Throughput: 0: 1591.1, 1: 1581.4. Samples: 38377042. Policy #0 lag: (min: 18.0, avg: 18.2, max: 29.0) -[2023-10-12 06:24:10,201][77203] Avg episode reward: [(0, '55.520'), (1, '45.030')] -[2023-10-12 06:24:11,060][78091] Updated weights for policy 0, policy_version 75110 (0.0010) -[2023-10-12 06:24:11,348][78123] Updated weights for policy 1, policy_version 74760 (0.0009) -[2023-10-12 06:24:11,422][78091] Updated weights for policy 0, policy_version 75120 (0.0007) -[2023-10-12 06:24:11,720][78123] Updated weights for policy 1, policy_version 74770 (0.0008) -[2023-10-12 06:24:11,784][78091] Updated weights for policy 0, policy_version 75130 (0.0007) -[2023-10-12 06:24:12,081][78123] Updated weights for policy 1, policy_version 74780 (0.0008) -[2023-10-12 06:24:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 153518080. Throughput: 0: 1592.3, 1: 1576.0. Samples: 38385722. Policy #0 lag: (min: 2.0, avg: 5.5, max: 34.0) -[2023-10-12 06:24:15,202][77203] Avg episode reward: [(0, '56.710'), (1, '47.050')] -[2023-10-12 06:24:16,122][78091] Updated weights for policy 0, policy_version 75140 (0.0008) -[2023-10-12 06:24:16,451][78123] Updated weights for policy 1, policy_version 74790 (0.0009) -[2023-10-12 06:24:16,495][78091] Updated weights for policy 0, policy_version 75150 (0.0008) -[2023-10-12 06:24:16,819][78123] Updated weights for policy 1, policy_version 74800 (0.0007) -[2023-10-12 06:24:16,873][78091] Updated weights for policy 0, policy_version 75160 (0.0008) -[2023-10-12 06:24:17,177][78123] Updated weights for policy 1, policy_version 74810 (0.0008) -[2023-10-12 06:24:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 153583616. Throughput: 0: 1593.7, 1: 1575.4. Samples: 38405050. Policy #0 lag: (min: 2.0, avg: 5.5, max: 34.0) -[2023-10-12 06:24:20,201][77203] Avg episode reward: [(0, '49.700'), (1, '53.240')] -[2023-10-12 06:24:21,273][78091] Updated weights for policy 0, policy_version 75170 (0.0008) -[2023-10-12 06:24:21,649][78091] Updated weights for policy 0, policy_version 75180 (0.0009) -[2023-10-12 06:24:21,665][78123] Updated weights for policy 1, policy_version 74820 (0.0009) -[2023-10-12 06:24:22,022][78091] Updated weights for policy 0, policy_version 75190 (0.0009) -[2023-10-12 06:24:22,053][78123] Updated weights for policy 1, policy_version 74830 (0.0008) -[2023-10-12 06:24:22,400][78091] Updated weights for policy 0, policy_version 75200 (0.0009) -[2023-10-12 06:24:22,410][78123] Updated weights for policy 1, policy_version 74840 (0.0009) -[2023-10-12 06:24:25,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 153649152. Throughput: 0: 1596.1, 1: 1575.1. Samples: 38424562. Policy #0 lag: (min: 2.0, avg: 5.5, max: 34.0) -[2023-10-12 06:24:25,202][77203] Avg episode reward: [(0, '53.950'), (1, '56.970')] -[2023-10-12 06:24:26,591][78091] Updated weights for policy 0, policy_version 75210 (0.0007) -[2023-10-12 06:24:26,610][78123] Updated weights for policy 1, policy_version 74850 (0.0010) -[2023-10-12 06:24:26,968][78091] Updated weights for policy 0, policy_version 75220 (0.0008) -[2023-10-12 06:24:26,972][78123] Updated weights for policy 1, policy_version 74860 (0.0007) -[2023-10-12 06:24:27,328][78091] Updated weights for policy 0, policy_version 75230 (0.0008) -[2023-10-12 06:24:27,333][78123] Updated weights for policy 1, policy_version 74870 (0.0008) -[2023-10-12 06:24:27,700][78123] Updated weights for policy 1, policy_version 74880 (0.0008) -[2023-10-12 06:24:30,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 153714688. Throughput: 0: 1596.9, 1: 1577.3. Samples: 38433378. Policy #0 lag: (min: 2.0, avg: 5.5, max: 34.0) -[2023-10-12 06:24:30,201][77203] Avg episode reward: [(0, '59.700'), (1, '46.890')] -[2023-10-12 06:24:31,679][78091] Updated weights for policy 0, policy_version 75240 (0.0010) -[2023-10-12 06:24:32,048][78091] Updated weights for policy 0, policy_version 75250 (0.0009) -[2023-10-12 06:24:32,110][78123] Updated weights for policy 1, policy_version 74890 (0.0008) -[2023-10-12 06:24:32,424][78091] Updated weights for policy 0, policy_version 75260 (0.0009) -[2023-10-12 06:24:32,478][78123] Updated weights for policy 1, policy_version 74900 (0.0008) -[2023-10-12 06:24:32,845][78123] Updated weights for policy 1, policy_version 74910 (0.0009) -[2023-10-12 06:24:35,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 153780224. Throughput: 0: 1598.4, 1: 1577.2. Samples: 38453010. Policy #0 lag: (min: 2.0, avg: 5.5, max: 34.0) -[2023-10-12 06:24:35,202][77203] Avg episode reward: [(0, '49.610'), (1, '51.260')] -[2023-10-12 06:24:36,709][78091] Updated weights for policy 0, policy_version 75270 (0.0009) -[2023-10-12 06:24:36,910][78123] Updated weights for policy 1, policy_version 74920 (0.0007) -[2023-10-12 06:24:37,082][78091] Updated weights for policy 0, policy_version 75280 (0.0008) -[2023-10-12 06:24:37,277][78123] Updated weights for policy 1, policy_version 74930 (0.0008) -[2023-10-12 06:24:37,451][78091] Updated weights for policy 0, policy_version 75290 (0.0009) -[2023-10-12 06:24:37,649][78123] Updated weights for policy 1, policy_version 74940 (0.0008) -[2023-10-12 06:24:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 153845760. Throughput: 0: 1597.3, 1: 1582.2. Samples: 38472670. Policy #0 lag: (min: 2.0, avg: 5.5, max: 34.0) -[2023-10-12 06:24:40,202][77203] Avg episode reward: [(0, '60.450'), (1, '48.130')] -[2023-10-12 06:24:41,741][78091] Updated weights for policy 0, policy_version 75300 (0.0010) -[2023-10-12 06:24:42,041][78123] Updated weights for policy 1, policy_version 74950 (0.0008) -[2023-10-12 06:24:42,108][78091] Updated weights for policy 0, policy_version 75310 (0.0008) -[2023-10-12 06:24:42,408][78123] Updated weights for policy 1, policy_version 74960 (0.0007) -[2023-10-12 06:24:42,485][78091] Updated weights for policy 0, policy_version 75320 (0.0009) -[2023-10-12 06:24:42,784][78123] Updated weights for policy 1, policy_version 74970 (0.0007) -[2023-10-12 06:24:45,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 153911296. Throughput: 0: 1597.9, 1: 1588.2. Samples: 38481500. Policy #0 lag: (min: 2.0, avg: 5.5, max: 34.0) -[2023-10-12 06:24:45,202][77203] Avg episode reward: [(0, '59.490'), (1, '48.400')] -[2023-10-12 06:24:46,830][78091] Updated weights for policy 0, policy_version 75330 (0.0008) -[2023-10-12 06:24:47,187][78091] Updated weights for policy 0, policy_version 75340 (0.0008) -[2023-10-12 06:24:47,198][78123] Updated weights for policy 1, policy_version 74980 (0.0007) -[2023-10-12 06:24:47,554][78091] Updated weights for policy 0, policy_version 75350 (0.0007) -[2023-10-12 06:24:47,565][78123] Updated weights for policy 1, policy_version 74990 (0.0008) -[2023-10-12 06:24:47,930][78123] Updated weights for policy 1, policy_version 75000 (0.0008) -[2023-10-12 06:24:47,930][78091] Updated weights for policy 0, policy_version 75360 (0.0008) -[2023-10-12 06:24:50,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 153976832. Throughput: 0: 1592.0, 1: 1583.4. Samples: 38500414. Policy #0 lag: (min: 2.0, avg: 5.5, max: 34.0) -[2023-10-12 06:24:50,202][77203] Avg episode reward: [(0, '56.080'), (1, '51.340')] -[2023-10-12 06:24:52,214][78123] Updated weights for policy 1, policy_version 75010 (0.0009) -[2023-10-12 06:24:52,331][78091] Updated weights for policy 0, policy_version 75370 (0.0007) -[2023-10-12 06:24:52,575][78123] Updated weights for policy 1, policy_version 75020 (0.0008) -[2023-10-12 06:24:52,698][78091] Updated weights for policy 0, policy_version 75380 (0.0008) -[2023-10-12 06:24:52,943][78123] Updated weights for policy 1, policy_version 75030 (0.0007) -[2023-10-12 06:24:53,066][78091] Updated weights for policy 0, policy_version 75390 (0.0007) -[2023-10-12 06:24:53,300][78123] Updated weights for policy 1, policy_version 75040 (0.0007) -[2023-10-12 06:24:55,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 154042368. Throughput: 0: 1594.0, 1: 1581.0. Samples: 38519918. Policy #0 lag: (min: 2.0, avg: 5.5, max: 34.0) -[2023-10-12 06:24:55,202][77203] Avg episode reward: [(0, '57.110'), (1, '47.360')] -[2023-10-12 06:24:57,311][78091] Updated weights for policy 0, policy_version 75400 (0.0009) -[2023-10-12 06:24:57,678][78091] Updated weights for policy 0, policy_version 75410 (0.0007) -[2023-10-12 06:24:57,735][78123] Updated weights for policy 1, policy_version 75050 (0.0008) -[2023-10-12 06:24:58,045][78091] Updated weights for policy 0, policy_version 75420 (0.0007) -[2023-10-12 06:24:58,108][78123] Updated weights for policy 1, policy_version 75060 (0.0009) -[2023-10-12 06:24:58,474][78123] Updated weights for policy 1, policy_version 75070 (0.0009) -[2023-10-12 06:25:00,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 154107904. Throughput: 0: 1607.0, 1: 1598.9. Samples: 38529984. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:25:00,201][77203] Avg episode reward: [(0, '54.450'), (1, '48.730')] -[2023-10-12 06:25:02,260][78091] Updated weights for policy 0, policy_version 75430 (0.0008) -[2023-10-12 06:25:02,624][78091] Updated weights for policy 0, policy_version 75440 (0.0011) -[2023-10-12 06:25:02,827][78123] Updated weights for policy 1, policy_version 75080 (0.0009) -[2023-10-12 06:25:02,996][78091] Updated weights for policy 0, policy_version 75450 (0.0010) -[2023-10-12 06:25:03,204][78123] Updated weights for policy 1, policy_version 75090 (0.0007) -[2023-10-12 06:25:03,560][78123] Updated weights for policy 1, policy_version 75100 (0.0010) -[2023-10-12 06:25:05,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 154173440. Throughput: 0: 1603.0, 1: 1577.6. Samples: 38548176. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:25:05,201][77203] Avg episode reward: [(0, '57.730'), (1, '49.040')] -[2023-10-12 06:25:07,376][78091] Updated weights for policy 0, policy_version 75460 (0.0009) -[2023-10-12 06:25:07,732][78091] Updated weights for policy 0, policy_version 75470 (0.0008) -[2023-10-12 06:25:08,093][78123] Updated weights for policy 1, policy_version 75110 (0.0008) -[2023-10-12 06:25:08,107][78091] Updated weights for policy 0, policy_version 75480 (0.0009) -[2023-10-12 06:25:08,469][78123] Updated weights for policy 1, policy_version 75120 (0.0009) -[2023-10-12 06:25:08,845][78123] Updated weights for policy 1, policy_version 75130 (0.0009) -[2023-10-12 06:25:10,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 154238976. Throughput: 0: 1597.6, 1: 1576.4. Samples: 38567392. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:25:10,202][77203] Avg episode reward: [(0, '52.010'), (1, '51.060')] -[2023-10-12 06:25:10,210][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000075136_76939264.pth... -[2023-10-12 06:25:10,211][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000075488_77299712.pth... -[2023-10-12 06:25:10,241][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000073632_75399168.pth -[2023-10-12 06:25:10,256][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000073984_75759616.pth -[2023-10-12 06:25:12,530][78091] Updated weights for policy 0, policy_version 75490 (0.0009) -[2023-10-12 06:25:12,897][78091] Updated weights for policy 0, policy_version 75500 (0.0009) -[2023-10-12 06:25:13,174][78123] Updated weights for policy 1, policy_version 75140 (0.0009) -[2023-10-12 06:25:13,269][78091] Updated weights for policy 0, policy_version 75510 (0.0009) -[2023-10-12 06:25:13,551][78123] Updated weights for policy 1, policy_version 75150 (0.0007) -[2023-10-12 06:25:13,637][78091] Updated weights for policy 0, policy_version 75520 (0.0010) -[2023-10-12 06:25:13,919][78123] Updated weights for policy 1, policy_version 75160 (0.0007) -[2023-10-12 06:25:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 154304512. Throughput: 0: 1613.2, 1: 1598.7. Samples: 38577912. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:25:15,202][77203] Avg episode reward: [(0, '57.810'), (1, '52.100')] -[2023-10-12 06:25:17,870][78091] Updated weights for policy 0, policy_version 75530 (0.0007) -[2023-10-12 06:25:18,235][78123] Updated weights for policy 1, policy_version 75170 (0.0007) -[2023-10-12 06:25:18,245][78091] Updated weights for policy 0, policy_version 75540 (0.0008) -[2023-10-12 06:25:18,597][78123] Updated weights for policy 1, policy_version 75180 (0.0008) -[2023-10-12 06:25:18,613][78091] Updated weights for policy 0, policy_version 75550 (0.0007) -[2023-10-12 06:25:18,957][78123] Updated weights for policy 1, policy_version 75190 (0.0009) -[2023-10-12 06:25:19,326][78123] Updated weights for policy 1, policy_version 75200 (0.0009) -[2023-10-12 06:25:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 154370048. Throughput: 0: 1595.9, 1: 1584.2. Samples: 38596112. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:25:20,201][77203] Avg episode reward: [(0, '56.230'), (1, '55.390')] -[2023-10-12 06:25:22,982][78091] Updated weights for policy 0, policy_version 75560 (0.0009) -[2023-10-12 06:25:23,349][78091] Updated weights for policy 0, policy_version 75570 (0.0007) -[2023-10-12 06:25:23,720][78091] Updated weights for policy 0, policy_version 75580 (0.0007) -[2023-10-12 06:25:24,022][78123] Updated weights for policy 1, policy_version 75210 (0.0010) -[2023-10-12 06:25:24,387][78123] Updated weights for policy 1, policy_version 75220 (0.0009) -[2023-10-12 06:25:24,751][78123] Updated weights for policy 1, policy_version 75230 (0.0008) -[2023-10-12 06:25:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 154435584. Throughput: 0: 1596.9, 1: 1567.8. Samples: 38615080. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:25:25,202][77203] Avg episode reward: [(0, '57.450'), (1, '49.450')] -[2023-10-12 06:25:28,081][78091] Updated weights for policy 0, policy_version 75590 (0.0010) -[2023-10-12 06:25:28,443][78091] Updated weights for policy 0, policy_version 75600 (0.0009) -[2023-10-12 06:25:28,831][78091] Updated weights for policy 0, policy_version 75610 (0.0009) -[2023-10-12 06:25:29,159][78123] Updated weights for policy 1, policy_version 75240 (0.0009) -[2023-10-12 06:25:29,527][78123] Updated weights for policy 1, policy_version 75250 (0.0008) -[2023-10-12 06:25:29,900][78123] Updated weights for policy 1, policy_version 75260 (0.0008) -[2023-10-12 06:25:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 154501120. Throughput: 0: 1622.5, 1: 1584.9. Samples: 38625832. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:25:30,201][77203] Avg episode reward: [(0, '54.050'), (1, '45.630')] -[2023-10-12 06:25:33,138][78091] Updated weights for policy 0, policy_version 75620 (0.0008) -[2023-10-12 06:25:33,511][78091] Updated weights for policy 0, policy_version 75630 (0.0009) -[2023-10-12 06:25:33,886][78091] Updated weights for policy 0, policy_version 75640 (0.0007) -[2023-10-12 06:25:34,148][78123] Updated weights for policy 1, policy_version 75270 (0.0010) -[2023-10-12 06:25:34,516][78123] Updated weights for policy 1, policy_version 75280 (0.0007) -[2023-10-12 06:25:34,885][78123] Updated weights for policy 1, policy_version 75290 (0.0008) -[2023-10-12 06:25:35,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 154566656. Throughput: 0: 1611.6, 1: 1597.1. Samples: 38644802. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:25:35,202][77203] Avg episode reward: [(0, '55.360'), (1, '55.820')] -[2023-10-12 06:25:38,188][78091] Updated weights for policy 0, policy_version 75650 (0.0009) -[2023-10-12 06:25:38,557][78091] Updated weights for policy 0, policy_version 75660 (0.0008) -[2023-10-12 06:25:38,934][78091] Updated weights for policy 0, policy_version 75670 (0.0011) -[2023-10-12 06:25:39,186][78123] Updated weights for policy 1, policy_version 75300 (0.0009) -[2023-10-12 06:25:39,296][78091] Updated weights for policy 0, policy_version 75680 (0.0009) -[2023-10-12 06:25:39,553][78123] Updated weights for policy 1, policy_version 75310 (0.0010) -[2023-10-12 06:25:39,921][78123] Updated weights for policy 1, policy_version 75320 (0.0007) -[2023-10-12 06:25:40,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 154599424. Throughput: 0: 1598.4, 1: 1585.0. Samples: 38663172. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:25:40,201][77203] Avg episode reward: [(0, '55.600'), (1, '52.530')] -[2023-10-12 06:25:43,627][78091] Updated weights for policy 0, policy_version 75690 (0.0007) -[2023-10-12 06:25:44,005][78091] Updated weights for policy 0, policy_version 75700 (0.0008) -[2023-10-12 06:25:44,175][78123] Updated weights for policy 1, policy_version 75330 (0.0008) -[2023-10-12 06:25:44,371][78091] Updated weights for policy 0, policy_version 75710 (0.0009) -[2023-10-12 06:25:44,535][78123] Updated weights for policy 1, policy_version 75340 (0.0007) -[2023-10-12 06:25:44,908][78123] Updated weights for policy 1, policy_version 75350 (0.0010) -[2023-10-12 06:25:45,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 154664960. Throughput: 0: 1611.0, 1: 1577.9. Samples: 38673484. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:25:45,201][77203] Avg episode reward: [(0, '47.060'), (1, '49.300')] -[2023-10-12 06:25:45,277][78123] Updated weights for policy 1, policy_version 75360 (0.0007) -[2023-10-12 06:25:48,377][78091] Updated weights for policy 0, policy_version 75720 (0.0008) -[2023-10-12 06:25:48,735][78091] Updated weights for policy 0, policy_version 75730 (0.0009) -[2023-10-12 06:25:49,108][78091] Updated weights for policy 0, policy_version 75740 (0.0009) -[2023-10-12 06:25:49,660][78123] Updated weights for policy 1, policy_version 75370 (0.0009) -[2023-10-12 06:25:50,028][78123] Updated weights for policy 1, policy_version 75380 (0.0011) -[2023-10-12 06:25:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 154730496. Throughput: 0: 1605.4, 1: 1603.2. Samples: 38692564. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:25:50,201][77203] Avg episode reward: [(0, '56.240'), (1, '50.100')] -[2023-10-12 06:25:50,393][78123] Updated weights for policy 1, policy_version 75390 (0.0009) -[2023-10-12 06:25:53,485][78091] Updated weights for policy 0, policy_version 75750 (0.0007) -[2023-10-12 06:25:53,858][78091] Updated weights for policy 0, policy_version 75760 (0.0007) -[2023-10-12 06:25:54,230][78091] Updated weights for policy 0, policy_version 75770 (0.0010) -[2023-10-12 06:25:54,831][78123] Updated weights for policy 1, policy_version 75400 (0.0008) -[2023-10-12 06:25:55,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 154796032. Throughput: 0: 1595.5, 1: 1600.5. Samples: 38711212. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:25:55,202][77203] Avg episode reward: [(0, '58.810'), (1, '49.950')] -[2023-10-12 06:25:55,210][78123] Updated weights for policy 1, policy_version 75410 (0.0007) -[2023-10-12 06:25:55,580][78123] Updated weights for policy 1, policy_version 75420 (0.0008) -[2023-10-12 06:25:58,434][78091] Updated weights for policy 0, policy_version 75780 (0.0007) -[2023-10-12 06:25:58,814][78091] Updated weights for policy 0, policy_version 75790 (0.0009) -[2023-10-12 06:25:59,181][78091] Updated weights for policy 0, policy_version 75800 (0.0008) -[2023-10-12 06:25:59,970][78123] Updated weights for policy 1, policy_version 75430 (0.0007) -[2023-10-12 06:26:00,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 154861568. Throughput: 0: 1610.5, 1: 1581.6. Samples: 38721556. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:26:00,201][77203] Avg episode reward: [(0, '56.590'), (1, '55.890')] -[2023-10-12 06:26:00,346][78123] Updated weights for policy 1, policy_version 75440 (0.0009) -[2023-10-12 06:26:00,704][78123] Updated weights for policy 1, policy_version 75450 (0.0010) -[2023-10-12 06:26:03,522][78091] Updated weights for policy 0, policy_version 75810 (0.0007) -[2023-10-12 06:26:03,928][78091] Updated weights for policy 0, policy_version 75820 (0.0007) -[2023-10-12 06:26:04,296][78091] Updated weights for policy 0, policy_version 75830 (0.0009) -[2023-10-12 06:26:04,664][78091] Updated weights for policy 0, policy_version 75840 (0.0009) -[2023-10-12 06:26:04,871][78123] Updated weights for policy 1, policy_version 75460 (0.0008) -[2023-10-12 06:26:05,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 154927104. Throughput: 0: 1614.8, 1: 1599.4. Samples: 38740752. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:26:05,201][77203] Avg episode reward: [(0, '53.840'), (1, '51.270')] -[2023-10-12 06:26:05,229][78123] Updated weights for policy 1, policy_version 75470 (0.0010) -[2023-10-12 06:26:05,604][78123] Updated weights for policy 1, policy_version 75480 (0.0010) -[2023-10-12 06:26:09,072][78091] Updated weights for policy 0, policy_version 75850 (0.0009) -[2023-10-12 06:26:09,438][78091] Updated weights for policy 0, policy_version 75860 (0.0010) -[2023-10-12 06:26:09,806][78091] Updated weights for policy 0, policy_version 75870 (0.0008) -[2023-10-12 06:26:09,840][78123] Updated weights for policy 1, policy_version 75490 (0.0009) -[2023-10-12 06:26:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 154992640. Throughput: 0: 1593.8, 1: 1613.7. Samples: 38759418. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:26:10,201][77203] Avg episode reward: [(0, '55.350'), (1, '44.730')] -[2023-10-12 06:26:10,210][78123] Updated weights for policy 1, policy_version 75500 (0.0009) -[2023-10-12 06:26:10,570][78123] Updated weights for policy 1, policy_version 75510 (0.0010) -[2023-10-12 06:26:10,936][78123] Updated weights for policy 1, policy_version 75520 (0.0008) -[2023-10-12 06:26:14,057][78091] Updated weights for policy 0, policy_version 75880 (0.0009) -[2023-10-12 06:26:14,432][78091] Updated weights for policy 0, policy_version 75890 (0.0008) -[2023-10-12 06:26:14,804][78091] Updated weights for policy 0, policy_version 75900 (0.0008) -[2023-10-12 06:26:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 155058176. Throughput: 0: 1595.2, 1: 1591.5. Samples: 38769232. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:26:15,201][77203] Avg episode reward: [(0, '63.600'), (1, '49.300')] -[2023-10-12 06:26:15,242][78123] Updated weights for policy 1, policy_version 75530 (0.0008) -[2023-10-12 06:26:15,600][78123] Updated weights for policy 1, policy_version 75540 (0.0008) -[2023-10-12 06:26:15,981][78123] Updated weights for policy 1, policy_version 75550 (0.0010) -[2023-10-12 06:26:19,155][78091] Updated weights for policy 0, policy_version 75910 (0.0008) -[2023-10-12 06:26:19,520][78091] Updated weights for policy 0, policy_version 75920 (0.0009) -[2023-10-12 06:26:19,897][78091] Updated weights for policy 0, policy_version 75930 (0.0010) -[2023-10-12 06:26:20,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 155123712. Throughput: 0: 1609.4, 1: 1588.5. Samples: 38788708. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:26:20,201][77203] Avg episode reward: [(0, '56.380'), (1, '51.410')] -[2023-10-12 06:26:20,295][78123] Updated weights for policy 1, policy_version 75560 (0.0009) -[2023-10-12 06:26:20,658][78123] Updated weights for policy 1, policy_version 75570 (0.0009) -[2023-10-12 06:26:21,026][78123] Updated weights for policy 1, policy_version 75580 (0.0007) -[2023-10-12 06:26:24,197][78091] Updated weights for policy 0, policy_version 75940 (0.0008) -[2023-10-12 06:26:24,571][78091] Updated weights for policy 0, policy_version 75950 (0.0008) -[2023-10-12 06:26:24,936][78091] Updated weights for policy 0, policy_version 75960 (0.0007) -[2023-10-12 06:26:25,201][77203] Fps is (10 sec: 9830.1, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 155156480. Throughput: 0: 1606.1, 1: 1603.6. Samples: 38807610. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:26:25,202][77203] Avg episode reward: [(0, '55.360'), (1, '48.380')] -[2023-10-12 06:26:25,331][78123] Updated weights for policy 1, policy_version 75590 (0.0010) -[2023-10-12 06:26:25,696][78123] Updated weights for policy 1, policy_version 75600 (0.0008) -[2023-10-12 06:26:26,065][78123] Updated weights for policy 1, policy_version 75610 (0.0009) -[2023-10-12 06:26:29,256][78091] Updated weights for policy 0, policy_version 75970 (0.0008) -[2023-10-12 06:26:29,629][78091] Updated weights for policy 0, policy_version 75980 (0.0007) -[2023-10-12 06:26:29,993][78091] Updated weights for policy 0, policy_version 75990 (0.0010) -[2023-10-12 06:26:30,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 155222016. Throughput: 0: 1595.6, 1: 1590.8. Samples: 38816872. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:26:30,202][77203] Avg episode reward: [(0, '52.470'), (1, '45.250')] -[2023-10-12 06:26:30,364][78091] Updated weights for policy 0, policy_version 76000 (0.0009) -[2023-10-12 06:26:30,419][78123] Updated weights for policy 1, policy_version 75620 (0.0008) -[2023-10-12 06:26:30,789][78123] Updated weights for policy 1, policy_version 75630 (0.0009) -[2023-10-12 06:26:31,155][78123] Updated weights for policy 1, policy_version 75640 (0.0008) -[2023-10-12 06:26:34,605][78091] Updated weights for policy 0, policy_version 76010 (0.0008) -[2023-10-12 06:26:34,973][78091] Updated weights for policy 0, policy_version 76020 (0.0008) -[2023-10-12 06:26:35,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 155287552. Throughput: 0: 1611.5, 1: 1587.0. Samples: 38836496. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:26:35,205][77203] Avg episode reward: [(0, '60.610'), (1, '49.400')] -[2023-10-12 06:26:35,350][78091] Updated weights for policy 0, policy_version 76030 (0.0008) -[2023-10-12 06:26:35,538][78123] Updated weights for policy 1, policy_version 75650 (0.0009) -[2023-10-12 06:26:35,909][78123] Updated weights for policy 1, policy_version 75660 (0.0008) -[2023-10-12 06:26:36,267][78123] Updated weights for policy 1, policy_version 75670 (0.0008) -[2023-10-12 06:26:36,634][78123] Updated weights for policy 1, policy_version 75680 (0.0010) -[2023-10-12 06:26:39,785][78091] Updated weights for policy 0, policy_version 76040 (0.0010) -[2023-10-12 06:26:40,154][78091] Updated weights for policy 0, policy_version 76050 (0.0009) -[2023-10-12 06:26:40,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 155353088. Throughput: 0: 1611.3, 1: 1593.3. Samples: 38855418. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:26:40,201][77203] Avg episode reward: [(0, '56.160'), (1, '50.500')] -[2023-10-12 06:26:40,524][78091] Updated weights for policy 0, policy_version 76060 (0.0010) -[2023-10-12 06:26:41,046][78123] Updated weights for policy 1, policy_version 75690 (0.0008) -[2023-10-12 06:26:41,418][78123] Updated weights for policy 1, policy_version 75700 (0.0010) -[2023-10-12 06:26:41,786][78123] Updated weights for policy 1, policy_version 75710 (0.0010) -[2023-10-12 06:26:44,646][78091] Updated weights for policy 0, policy_version 76070 (0.0008) -[2023-10-12 06:26:45,018][78091] Updated weights for policy 0, policy_version 76080 (0.0007) -[2023-10-12 06:26:45,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 155418624. Throughput: 0: 1583.6, 1: 1583.5. Samples: 38864076. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:26:45,201][77203] Avg episode reward: [(0, '58.630'), (1, '53.500')] -[2023-10-12 06:26:45,390][78091] Updated weights for policy 0, policy_version 76090 (0.0008) -[2023-10-12 06:26:46,298][78123] Updated weights for policy 1, policy_version 75720 (0.0008) -[2023-10-12 06:26:46,670][78123] Updated weights for policy 1, policy_version 75730 (0.0008) -[2023-10-12 06:26:47,034][78123] Updated weights for policy 1, policy_version 75740 (0.0008) -[2023-10-12 06:26:49,670][78091] Updated weights for policy 0, policy_version 76100 (0.0009) -[2023-10-12 06:26:50,048][78091] Updated weights for policy 0, policy_version 76110 (0.0009) -[2023-10-12 06:26:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 155484160. Throughput: 0: 1595.0, 1: 1577.9. Samples: 38883532. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:26:50,201][77203] Avg episode reward: [(0, '56.340'), (1, '53.510')] -[2023-10-12 06:26:50,422][78091] Updated weights for policy 0, policy_version 76120 (0.0008) -[2023-10-12 06:26:51,312][78123] Updated weights for policy 1, policy_version 75750 (0.0008) -[2023-10-12 06:26:51,676][78123] Updated weights for policy 1, policy_version 75760 (0.0007) -[2023-10-12 06:26:52,053][78123] Updated weights for policy 1, policy_version 75770 (0.0007) -[2023-10-12 06:26:54,861][78091] Updated weights for policy 0, policy_version 76130 (0.0007) -[2023-10-12 06:26:55,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 155549696. Throughput: 0: 1611.5, 1: 1579.8. Samples: 38903028. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:26:55,202][77203] Avg episode reward: [(0, '57.710'), (1, '50.860')] -[2023-10-12 06:26:55,228][78091] Updated weights for policy 0, policy_version 76140 (0.0009) -[2023-10-12 06:26:55,600][78091] Updated weights for policy 0, policy_version 76150 (0.0009) -[2023-10-12 06:26:55,966][78091] Updated weights for policy 0, policy_version 76160 (0.0009) -[2023-10-12 06:26:56,245][78123] Updated weights for policy 1, policy_version 75780 (0.0010) -[2023-10-12 06:26:56,600][78123] Updated weights for policy 1, policy_version 75790 (0.0007) -[2023-10-12 06:26:56,963][78123] Updated weights for policy 1, policy_version 75800 (0.0008) -[2023-10-12 06:27:00,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 155615232. Throughput: 0: 1585.9, 1: 1580.3. Samples: 38911710. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:27:00,202][77203] Avg episode reward: [(0, '63.560'), (1, '51.360')] -[2023-10-12 06:27:00,370][78091] Updated weights for policy 0, policy_version 76170 (0.0010) -[2023-10-12 06:27:00,743][78091] Updated weights for policy 0, policy_version 76180 (0.0008) -[2023-10-12 06:27:01,110][78091] Updated weights for policy 0, policy_version 76190 (0.0009) -[2023-10-12 06:27:01,270][78123] Updated weights for policy 1, policy_version 75810 (0.0009) -[2023-10-12 06:27:01,648][78123] Updated weights for policy 1, policy_version 75820 (0.0007) -[2023-10-12 06:27:02,019][78123] Updated weights for policy 1, policy_version 75830 (0.0007) -[2023-10-12 06:27:02,386][78123] Updated weights for policy 1, policy_version 75840 (0.0010) -[2023-10-12 06:27:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 155680768. Throughput: 0: 1593.7, 1: 1582.5. Samples: 38931638. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:27:05,202][77203] Avg episode reward: [(0, '48.690'), (1, '50.050')] -[2023-10-12 06:27:05,304][78091] Updated weights for policy 0, policy_version 76200 (0.0010) -[2023-10-12 06:27:05,668][78091] Updated weights for policy 0, policy_version 76210 (0.0011) -[2023-10-12 06:27:06,042][78091] Updated weights for policy 0, policy_version 76220 (0.0009) -[2023-10-12 06:27:06,823][78123] Updated weights for policy 1, policy_version 75850 (0.0009) -[2023-10-12 06:27:07,194][78123] Updated weights for policy 1, policy_version 75860 (0.0010) -[2023-10-12 06:27:07,562][78123] Updated weights for policy 1, policy_version 75870 (0.0011) -[2023-10-12 06:27:10,201][77203] Fps is (10 sec: 13106.8, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 155746304. Throughput: 0: 1609.6, 1: 1583.1. Samples: 38951282. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:27:10,202][77203] Avg episode reward: [(0, '56.450'), (1, '47.220')] -[2023-10-12 06:27:10,209][78091] Updated weights for policy 0, policy_version 76230 (0.0009) -[2023-10-12 06:27:10,212][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000075872_77692928.pth... -[2023-10-12 06:27:10,250][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000074400_76185600.pth -[2023-10-12 06:27:10,578][78091] Updated weights for policy 0, policy_version 76240 (0.0010) -[2023-10-12 06:27:10,953][78091] Updated weights for policy 0, policy_version 76250 (0.0008) -[2023-10-12 06:27:11,171][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000076256_78086144.pth... -[2023-10-12 06:27:11,199][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000074752_76546048.pth -[2023-10-12 06:27:11,881][78123] Updated weights for policy 1, policy_version 75880 (0.0010) -[2023-10-12 06:27:12,244][78123] Updated weights for policy 1, policy_version 75890 (0.0008) -[2023-10-12 06:27:12,606][78123] Updated weights for policy 1, policy_version 75900 (0.0009) -[2023-10-12 06:27:15,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 155811840. Throughput: 0: 1594.1, 1: 1588.0. Samples: 38960064. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:27:15,202][77203] Avg episode reward: [(0, '56.960'), (1, '49.380')] -[2023-10-12 06:27:15,290][78091] Updated weights for policy 0, policy_version 76260 (0.0007) -[2023-10-12 06:27:15,655][78091] Updated weights for policy 0, policy_version 76270 (0.0008) -[2023-10-12 06:27:16,025][78091] Updated weights for policy 0, policy_version 76280 (0.0009) -[2023-10-12 06:27:16,695][78123] Updated weights for policy 1, policy_version 75910 (0.0008) -[2023-10-12 06:27:17,054][78123] Updated weights for policy 1, policy_version 75920 (0.0007) -[2023-10-12 06:27:17,430][78123] Updated weights for policy 1, policy_version 75930 (0.0008) -[2023-10-12 06:27:20,201][77203] Fps is (10 sec: 13107.7, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 155877376. Throughput: 0: 1593.0, 1: 1588.0. Samples: 38979642. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:27:20,201][77203] Avg episode reward: [(0, '61.340'), (1, '44.980')] -[2023-10-12 06:27:20,432][78091] Updated weights for policy 0, policy_version 76290 (0.0008) -[2023-10-12 06:27:20,800][78091] Updated weights for policy 0, policy_version 76300 (0.0007) -[2023-10-12 06:27:21,168][78091] Updated weights for policy 0, policy_version 76310 (0.0008) -[2023-10-12 06:27:21,540][78091] Updated weights for policy 0, policy_version 76320 (0.0009) -[2023-10-12 06:27:21,734][78123] Updated weights for policy 1, policy_version 75940 (0.0009) -[2023-10-12 06:27:22,101][78123] Updated weights for policy 1, policy_version 75950 (0.0009) -[2023-10-12 06:27:22,470][78123] Updated weights for policy 1, policy_version 75960 (0.0008) -[2023-10-12 06:27:25,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 155942912. Throughput: 0: 1608.3, 1: 1594.5. Samples: 38999542. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:27:25,202][77203] Avg episode reward: [(0, '59.220'), (1, '53.190')] -[2023-10-12 06:27:25,656][78091] Updated weights for policy 0, policy_version 76330 (0.0009) -[2023-10-12 06:27:26,012][78091] Updated weights for policy 0, policy_version 76340 (0.0009) -[2023-10-12 06:27:26,379][78091] Updated weights for policy 0, policy_version 76350 (0.0011) -[2023-10-12 06:27:26,751][78123] Updated weights for policy 1, policy_version 75970 (0.0008) -[2023-10-12 06:27:27,148][78123] Updated weights for policy 1, policy_version 75980 (0.0008) -[2023-10-12 06:27:27,517][78123] Updated weights for policy 1, policy_version 75990 (0.0007) -[2023-10-12 06:27:27,878][78123] Updated weights for policy 1, policy_version 76000 (0.0007) -[2023-10-12 06:27:30,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 156008448. Throughput: 0: 1601.2, 1: 1602.8. Samples: 39008258. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:27:30,202][77203] Avg episode reward: [(0, '57.810'), (1, '50.090')] -[2023-10-12 06:27:30,775][78091] Updated weights for policy 0, policy_version 76360 (0.0007) -[2023-10-12 06:27:31,150][78091] Updated weights for policy 0, policy_version 76370 (0.0007) -[2023-10-12 06:27:31,519][78091] Updated weights for policy 0, policy_version 76380 (0.0009) -[2023-10-12 06:27:32,018][78123] Updated weights for policy 1, policy_version 76010 (0.0008) -[2023-10-12 06:27:32,381][78123] Updated weights for policy 1, policy_version 76020 (0.0008) -[2023-10-12 06:27:32,752][78123] Updated weights for policy 1, policy_version 76030 (0.0009) -[2023-10-12 06:27:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 156073984. Throughput: 0: 1599.6, 1: 1599.5. Samples: 39027490. Policy #0 lag: (min: 31.0, avg: 31.1, max: 38.0) -[2023-10-12 06:27:35,202][77203] Avg episode reward: [(0, '57.800'), (1, '45.590')] -[2023-10-12 06:27:35,890][78091] Updated weights for policy 0, policy_version 76390 (0.0008) -[2023-10-12 06:27:36,271][78091] Updated weights for policy 0, policy_version 76400 (0.0009) -[2023-10-12 06:27:36,637][78091] Updated weights for policy 0, policy_version 76410 (0.0010) -[2023-10-12 06:27:37,198][78123] Updated weights for policy 1, policy_version 76040 (0.0008) -[2023-10-12 06:27:37,572][78123] Updated weights for policy 1, policy_version 76050 (0.0008) -[2023-10-12 06:27:37,943][78123] Updated weights for policy 1, policy_version 76060 (0.0007) -[2023-10-12 06:27:40,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 156139520. Throughput: 0: 1597.8, 1: 1598.5. Samples: 39046862. Policy #0 lag: (min: 31.0, avg: 31.1, max: 38.0) -[2023-10-12 06:27:40,201][77203] Avg episode reward: [(0, '65.200'), (1, '50.030')] -[2023-10-12 06:27:40,979][78091] Updated weights for policy 0, policy_version 76420 (0.0010) -[2023-10-12 06:27:41,350][78091] Updated weights for policy 0, policy_version 76430 (0.0007) -[2023-10-12 06:27:41,723][78091] Updated weights for policy 0, policy_version 76440 (0.0007) -[2023-10-12 06:27:42,206][78123] Updated weights for policy 1, policy_version 76070 (0.0008) -[2023-10-12 06:27:42,569][78123] Updated weights for policy 1, policy_version 76080 (0.0008) -[2023-10-12 06:27:42,942][78123] Updated weights for policy 1, policy_version 76090 (0.0008) -[2023-10-12 06:27:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 156205056. Throughput: 0: 1596.0, 1: 1610.4. Samples: 39056000. Policy #0 lag: (min: 31.0, avg: 31.1, max: 38.0) -[2023-10-12 06:27:45,202][77203] Avg episode reward: [(0, '63.210'), (1, '49.960')] -[2023-10-12 06:27:46,009][78091] Updated weights for policy 0, policy_version 76450 (0.0007) -[2023-10-12 06:27:46,377][78091] Updated weights for policy 0, policy_version 76460 (0.0008) -[2023-10-12 06:27:46,747][78091] Updated weights for policy 0, policy_version 76470 (0.0007) -[2023-10-12 06:27:47,116][78091] Updated weights for policy 0, policy_version 76480 (0.0008) -[2023-10-12 06:27:47,209][78123] Updated weights for policy 1, policy_version 76100 (0.0011) -[2023-10-12 06:27:47,582][78123] Updated weights for policy 1, policy_version 76110 (0.0010) -[2023-10-12 06:27:47,954][78123] Updated weights for policy 1, policy_version 76120 (0.0009) -[2023-10-12 06:27:50,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 156270592. Throughput: 0: 1589.0, 1: 1598.8. Samples: 39075090. Policy #0 lag: (min: 31.0, avg: 31.1, max: 38.0) -[2023-10-12 06:27:50,202][77203] Avg episode reward: [(0, '54.460'), (1, '50.450')] -[2023-10-12 06:27:51,492][78091] Updated weights for policy 0, policy_version 76490 (0.0007) -[2023-10-12 06:27:51,853][78091] Updated weights for policy 0, policy_version 76500 (0.0009) -[2023-10-12 06:27:52,229][78091] Updated weights for policy 0, policy_version 76510 (0.0007) -[2023-10-12 06:27:52,300][78123] Updated weights for policy 1, policy_version 76130 (0.0009) -[2023-10-12 06:27:52,664][78123] Updated weights for policy 1, policy_version 76140 (0.0008) -[2023-10-12 06:27:53,026][78123] Updated weights for policy 1, policy_version 76150 (0.0008) -[2023-10-12 06:27:53,403][78123] Updated weights for policy 1, policy_version 76160 (0.0008) -[2023-10-12 06:27:55,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 156336128. Throughput: 0: 1592.6, 1: 1594.7. Samples: 39094712. Policy #0 lag: (min: 31.0, avg: 31.1, max: 38.0) -[2023-10-12 06:27:55,202][77203] Avg episode reward: [(0, '54.420'), (1, '49.130')] -[2023-10-12 06:27:56,439][78091] Updated weights for policy 0, policy_version 76520 (0.0009) -[2023-10-12 06:27:56,814][78091] Updated weights for policy 0, policy_version 76530 (0.0008) -[2023-10-12 06:27:57,185][78091] Updated weights for policy 0, policy_version 76540 (0.0007) -[2023-10-12 06:27:57,816][78123] Updated weights for policy 1, policy_version 76170 (0.0007) -[2023-10-12 06:27:58,187][78123] Updated weights for policy 1, policy_version 76180 (0.0007) -[2023-10-12 06:27:58,546][78123] Updated weights for policy 1, policy_version 76190 (0.0009) -[2023-10-12 06:28:00,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 156401664. Throughput: 0: 1594.4, 1: 1608.3. Samples: 39104186. Policy #0 lag: (min: 31.0, avg: 31.1, max: 38.0) -[2023-10-12 06:28:00,202][77203] Avg episode reward: [(0, '56.780'), (1, '50.270')] -[2023-10-12 06:28:01,395][78091] Updated weights for policy 0, policy_version 76550 (0.0007) -[2023-10-12 06:28:01,777][78091] Updated weights for policy 0, policy_version 76560 (0.0008) -[2023-10-12 06:28:02,152][78091] Updated weights for policy 0, policy_version 76570 (0.0007) -[2023-10-12 06:28:02,923][78123] Updated weights for policy 1, policy_version 76200 (0.0009) -[2023-10-12 06:28:03,294][78123] Updated weights for policy 1, policy_version 76210 (0.0011) -[2023-10-12 06:28:03,658][78123] Updated weights for policy 1, policy_version 76220 (0.0009) -[2023-10-12 06:28:05,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 156467200. Throughput: 0: 1598.1, 1: 1594.7. Samples: 39123320. Policy #0 lag: (min: 31.0, avg: 31.1, max: 38.0) -[2023-10-12 06:28:05,202][77203] Avg episode reward: [(0, '57.280'), (1, '50.330')] -[2023-10-12 06:28:06,416][78091] Updated weights for policy 0, policy_version 76580 (0.0008) -[2023-10-12 06:28:06,790][78091] Updated weights for policy 0, policy_version 76590 (0.0008) -[2023-10-12 06:28:07,159][78091] Updated weights for policy 0, policy_version 76600 (0.0009) -[2023-10-12 06:28:08,090][78123] Updated weights for policy 1, policy_version 76230 (0.0009) -[2023-10-12 06:28:08,456][78123] Updated weights for policy 1, policy_version 76240 (0.0009) -[2023-10-12 06:28:08,825][78123] Updated weights for policy 1, policy_version 76250 (0.0008) -[2023-10-12 06:28:10,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 12774.0). Total num frames: 156532736. Throughput: 0: 1596.3, 1: 1587.9. Samples: 39142828. Policy #0 lag: (min: 31.0, avg: 31.1, max: 38.0) -[2023-10-12 06:28:10,201][77203] Avg episode reward: [(0, '52.780'), (1, '50.560')] -[2023-10-12 06:28:11,399][78091] Updated weights for policy 0, policy_version 76610 (0.0008) -[2023-10-12 06:28:11,777][78091] Updated weights for policy 0, policy_version 76620 (0.0009) -[2023-10-12 06:28:12,147][78091] Updated weights for policy 0, policy_version 76630 (0.0009) -[2023-10-12 06:28:12,515][78091] Updated weights for policy 0, policy_version 76640 (0.0008) -[2023-10-12 06:28:13,284][78123] Updated weights for policy 1, policy_version 76260 (0.0009) -[2023-10-12 06:28:13,684][78123] Updated weights for policy 1, policy_version 76270 (0.0008) -[2023-10-12 06:28:14,041][78123] Updated weights for policy 1, policy_version 76280 (0.0010) -[2023-10-12 06:28:15,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 156598272. Throughput: 0: 1597.4, 1: 1608.6. Samples: 39152528. Policy #0 lag: (min: 31.0, avg: 31.1, max: 38.0) -[2023-10-12 06:28:15,202][77203] Avg episode reward: [(0, '55.680'), (1, '55.200')] -[2023-10-12 06:28:16,875][78091] Updated weights for policy 0, policy_version 76650 (0.0010) -[2023-10-12 06:28:17,245][78091] Updated weights for policy 0, policy_version 76660 (0.0010) -[2023-10-12 06:28:17,628][78091] Updated weights for policy 0, policy_version 76670 (0.0010) -[2023-10-12 06:28:18,449][78123] Updated weights for policy 1, policy_version 76290 (0.0007) -[2023-10-12 06:28:18,821][78123] Updated weights for policy 1, policy_version 76300 (0.0009) -[2023-10-12 06:28:19,189][78123] Updated weights for policy 1, policy_version 76310 (0.0009) -[2023-10-12 06:28:19,551][78123] Updated weights for policy 1, policy_version 76320 (0.0010) -[2023-10-12 06:28:20,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 156663808. Throughput: 0: 1601.3, 1: 1600.9. Samples: 39171590. Policy #0 lag: (min: 31.0, avg: 31.1, max: 38.0) -[2023-10-12 06:28:20,202][77203] Avg episode reward: [(0, '54.380'), (1, '54.780')] -[2023-10-12 06:28:22,015][78091] Updated weights for policy 0, policy_version 76680 (0.0008) -[2023-10-12 06:28:22,394][78091] Updated weights for policy 0, policy_version 76690 (0.0009) -[2023-10-12 06:28:22,764][78091] Updated weights for policy 0, policy_version 76700 (0.0010) -[2023-10-12 06:28:23,791][78123] Updated weights for policy 1, policy_version 76330 (0.0009) -[2023-10-12 06:28:24,159][78123] Updated weights for policy 1, policy_version 76340 (0.0009) -[2023-10-12 06:28:24,522][78123] Updated weights for policy 1, policy_version 76350 (0.0009) -[2023-10-12 06:28:25,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 12885.0). Total num frames: 156729344. Throughput: 0: 1604.0, 1: 1583.3. Samples: 39190290. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:28:25,201][77203] Avg episode reward: [(0, '60.080'), (1, '49.870')] -[2023-10-12 06:28:26,988][78091] Updated weights for policy 0, policy_version 76710 (0.0009) -[2023-10-12 06:28:27,351][78091] Updated weights for policy 0, policy_version 76720 (0.0008) -[2023-10-12 06:28:27,722][78091] Updated weights for policy 0, policy_version 76730 (0.0009) -[2023-10-12 06:28:28,740][78123] Updated weights for policy 1, policy_version 76360 (0.0010) -[2023-10-12 06:28:29,107][78123] Updated weights for policy 1, policy_version 76370 (0.0007) -[2023-10-12 06:28:29,485][78123] Updated weights for policy 1, policy_version 76380 (0.0010) -[2023-10-12 06:28:30,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 156794880. Throughput: 0: 1608.1, 1: 1599.2. Samples: 39200328. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:28:30,201][77203] Avg episode reward: [(0, '60.710'), (1, '55.560')] -[2023-10-12 06:28:31,964][78091] Updated weights for policy 0, policy_version 76740 (0.0010) -[2023-10-12 06:28:32,342][78091] Updated weights for policy 0, policy_version 76750 (0.0008) -[2023-10-12 06:28:32,706][78091] Updated weights for policy 0, policy_version 76760 (0.0008) -[2023-10-12 06:28:33,784][78123] Updated weights for policy 1, policy_version 76390 (0.0009) -[2023-10-12 06:28:34,162][78123] Updated weights for policy 1, policy_version 76400 (0.0009) -[2023-10-12 06:28:34,539][78123] Updated weights for policy 1, policy_version 76410 (0.0008) -[2023-10-12 06:28:35,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 156860416. Throughput: 0: 1603.0, 1: 1605.9. Samples: 39219490. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:28:35,202][77203] Avg episode reward: [(0, '59.870'), (1, '51.940')] -[2023-10-12 06:28:37,064][78091] Updated weights for policy 0, policy_version 76770 (0.0010) -[2023-10-12 06:28:37,433][78091] Updated weights for policy 0, policy_version 76780 (0.0009) -[2023-10-12 06:28:37,799][78091] Updated weights for policy 0, policy_version 76790 (0.0009) -[2023-10-12 06:28:38,169][78091] Updated weights for policy 0, policy_version 76800 (0.0009) -[2023-10-12 06:28:38,906][78123] Updated weights for policy 1, policy_version 76420 (0.0009) -[2023-10-12 06:28:39,278][78123] Updated weights for policy 1, policy_version 76430 (0.0008) -[2023-10-12 06:28:39,637][78123] Updated weights for policy 1, policy_version 76440 (0.0007) -[2023-10-12 06:28:40,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 156925952. Throughput: 0: 1594.3, 1: 1595.6. Samples: 39238258. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:28:40,201][77203] Avg episode reward: [(0, '48.830'), (1, '53.840')] -[2023-10-12 06:28:42,586][78091] Updated weights for policy 0, policy_version 76810 (0.0007) -[2023-10-12 06:28:42,969][78091] Updated weights for policy 0, policy_version 76820 (0.0007) -[2023-10-12 06:28:43,343][78091] Updated weights for policy 0, policy_version 76830 (0.0007) -[2023-10-12 06:28:44,053][78123] Updated weights for policy 1, policy_version 76450 (0.0008) -[2023-10-12 06:28:44,413][78123] Updated weights for policy 1, policy_version 76460 (0.0010) -[2023-10-12 06:28:44,777][78123] Updated weights for policy 1, policy_version 76470 (0.0010) -[2023-10-12 06:28:45,151][78123] Updated weights for policy 1, policy_version 76480 (0.0009) -[2023-10-12 06:28:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 156991488. Throughput: 0: 1609.4, 1: 1596.8. Samples: 39248464. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:28:45,202][77203] Avg episode reward: [(0, '51.680'), (1, '58.180')] -[2023-10-12 06:28:47,576][78091] Updated weights for policy 0, policy_version 76840 (0.0009) -[2023-10-12 06:28:47,949][78091] Updated weights for policy 0, policy_version 76850 (0.0008) -[2023-10-12 06:28:48,319][78091] Updated weights for policy 0, policy_version 76860 (0.0008) -[2023-10-12 06:28:49,353][78123] Updated weights for policy 1, policy_version 76490 (0.0009) -[2023-10-12 06:28:49,726][78123] Updated weights for policy 1, policy_version 76500 (0.0009) -[2023-10-12 06:28:50,094][78123] Updated weights for policy 1, policy_version 76510 (0.0009) -[2023-10-12 06:28:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 157057024. Throughput: 0: 1593.6, 1: 1607.4. Samples: 39267364. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:28:50,201][77203] Avg episode reward: [(0, '54.600'), (1, '52.580')] -[2023-10-12 06:28:52,662][78091] Updated weights for policy 0, policy_version 76870 (0.0007) -[2023-10-12 06:28:53,036][78091] Updated weights for policy 0, policy_version 76880 (0.0009) -[2023-10-12 06:28:53,404][78091] Updated weights for policy 0, policy_version 76890 (0.0008) -[2023-10-12 06:28:54,455][78123] Updated weights for policy 1, policy_version 76520 (0.0008) -[2023-10-12 06:28:54,827][78123] Updated weights for policy 1, policy_version 76530 (0.0008) -[2023-10-12 06:28:55,201][78123] Updated weights for policy 1, policy_version 76540 (0.0009) -[2023-10-12 06:28:55,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 157089792. Throughput: 0: 1595.1, 1: 1595.4. Samples: 39286398. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:28:55,202][77203] Avg episode reward: [(0, '52.320'), (1, '48.350')] -[2023-10-12 06:28:57,571][78091] Updated weights for policy 0, policy_version 76900 (0.0010) -[2023-10-12 06:28:57,947][78091] Updated weights for policy 0, policy_version 76910 (0.0008) -[2023-10-12 06:28:58,316][78091] Updated weights for policy 0, policy_version 76920 (0.0008) -[2023-10-12 06:28:59,547][78123] Updated weights for policy 1, policy_version 76550 (0.0011) -[2023-10-12 06:28:59,919][78123] Updated weights for policy 1, policy_version 76560 (0.0009) -[2023-10-12 06:29:00,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 157155328. Throughput: 0: 1614.4, 1: 1585.2. Samples: 39296508. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:29:00,201][77203] Avg episode reward: [(0, '58.020'), (1, '49.010')] -[2023-10-12 06:29:00,293][78123] Updated weights for policy 1, policy_version 76570 (0.0008) -[2023-10-12 06:29:02,639][78091] Updated weights for policy 0, policy_version 76930 (0.0009) -[2023-10-12 06:29:03,008][78091] Updated weights for policy 0, policy_version 76940 (0.0011) -[2023-10-12 06:29:03,377][78091] Updated weights for policy 0, policy_version 76950 (0.0008) -[2023-10-12 06:29:03,745][78091] Updated weights for policy 0, policy_version 76960 (0.0008) -[2023-10-12 06:29:04,453][78123] Updated weights for policy 1, policy_version 76580 (0.0008) -[2023-10-12 06:29:04,816][78123] Updated weights for policy 1, policy_version 76590 (0.0010) -[2023-10-12 06:29:05,178][78123] Updated weights for policy 1, policy_version 76600 (0.0010) -[2023-10-12 06:29:05,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 157220864. Throughput: 0: 1592.0, 1: 1599.0. Samples: 39315184. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:29:05,202][77203] Avg episode reward: [(0, '55.880'), (1, '50.820')] -[2023-10-12 06:29:08,081][78091] Updated weights for policy 0, policy_version 76970 (0.0009) -[2023-10-12 06:29:08,437][78091] Updated weights for policy 0, policy_version 76980 (0.0010) -[2023-10-12 06:29:08,815][78091] Updated weights for policy 0, policy_version 76990 (0.0009) -[2023-10-12 06:29:09,618][78123] Updated weights for policy 1, policy_version 76610 (0.0009) -[2023-10-12 06:29:09,987][78123] Updated weights for policy 1, policy_version 76620 (0.0009) -[2023-10-12 06:29:10,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 157286400. Throughput: 0: 1594.1, 1: 1607.1. Samples: 39334348. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:29:10,202][77203] Avg episode reward: [(0, '61.660'), (1, '49.740')] -[2023-10-12 06:29:10,210][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000076992_78839808.pth... -[2023-10-12 06:29:10,245][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000075488_77299712.pth -[2023-10-12 06:29:10,349][78123] Updated weights for policy 1, policy_version 76630 (0.0009) -[2023-10-12 06:29:10,726][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000076640_78479360.pth... -[2023-10-12 06:29:10,731][78123] Updated weights for policy 1, policy_version 76640 (0.0009) -[2023-10-12 06:29:10,763][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000075136_76939264.pth -[2023-10-12 06:29:13,099][78091] Updated weights for policy 0, policy_version 77000 (0.0007) -[2023-10-12 06:29:13,477][78091] Updated weights for policy 0, policy_version 77010 (0.0009) -[2023-10-12 06:29:13,857][78091] Updated weights for policy 0, policy_version 77020 (0.0009) -[2023-10-12 06:29:15,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 157351936. Throughput: 0: 1617.2, 1: 1586.2. Samples: 39344484. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) -[2023-10-12 06:29:15,202][77203] Avg episode reward: [(0, '61.720'), (1, '46.240')] -[2023-10-12 06:29:15,304][78123] Updated weights for policy 1, policy_version 76650 (0.0008) -[2023-10-12 06:29:15,677][78123] Updated weights for policy 1, policy_version 76660 (0.0008) -[2023-10-12 06:29:16,034][78123] Updated weights for policy 1, policy_version 76670 (0.0008) -[2023-10-12 06:29:18,160][78091] Updated weights for policy 0, policy_version 77030 (0.0008) -[2023-10-12 06:29:18,536][78091] Updated weights for policy 0, policy_version 77040 (0.0007) -[2023-10-12 06:29:18,919][78091] Updated weights for policy 0, policy_version 77050 (0.0007) -[2023-10-12 06:29:20,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 157417472. Throughput: 0: 1603.6, 1: 1589.4. Samples: 39363176. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) -[2023-10-12 06:29:20,201][77203] Avg episode reward: [(0, '60.810'), (1, '51.600')] -[2023-10-12 06:29:20,384][78123] Updated weights for policy 1, policy_version 76680 (0.0008) -[2023-10-12 06:29:20,761][78123] Updated weights for policy 1, policy_version 76690 (0.0007) -[2023-10-12 06:29:21,130][78123] Updated weights for policy 1, policy_version 76700 (0.0007) -[2023-10-12 06:29:23,330][78091] Updated weights for policy 0, policy_version 77060 (0.0009) -[2023-10-12 06:29:23,701][78091] Updated weights for policy 0, policy_version 77070 (0.0008) -[2023-10-12 06:29:24,074][78091] Updated weights for policy 0, policy_version 77080 (0.0008) -[2023-10-12 06:29:25,122][78123] Updated weights for policy 1, policy_version 76710 (0.0009) -[2023-10-12 06:29:25,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 157483008. Throughput: 0: 1600.8, 1: 1603.8. Samples: 39382464. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) -[2023-10-12 06:29:25,202][77203] Avg episode reward: [(0, '60.930'), (1, '47.930')] -[2023-10-12 06:29:25,492][78123] Updated weights for policy 1, policy_version 76720 (0.0010) -[2023-10-12 06:29:25,863][78123] Updated weights for policy 1, policy_version 76730 (0.0010) -[2023-10-12 06:29:28,209][78091] Updated weights for policy 0, policy_version 77090 (0.0008) -[2023-10-12 06:29:28,594][78091] Updated weights for policy 0, policy_version 77100 (0.0007) -[2023-10-12 06:29:28,967][78091] Updated weights for policy 0, policy_version 77110 (0.0007) -[2023-10-12 06:29:29,331][78091] Updated weights for policy 0, policy_version 77120 (0.0009) -[2023-10-12 06:29:30,068][78123] Updated weights for policy 1, policy_version 76740 (0.0009) -[2023-10-12 06:29:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 157548544. Throughput: 0: 1611.5, 1: 1585.5. Samples: 39392328. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) -[2023-10-12 06:29:30,201][77203] Avg episode reward: [(0, '52.450'), (1, '51.390')] -[2023-10-12 06:29:30,436][78123] Updated weights for policy 1, policy_version 76750 (0.0009) -[2023-10-12 06:29:30,810][78123] Updated weights for policy 1, policy_version 76760 (0.0007) -[2023-10-12 06:29:33,651][78091] Updated weights for policy 0, policy_version 77130 (0.0007) -[2023-10-12 06:29:34,015][78091] Updated weights for policy 0, policy_version 77140 (0.0009) -[2023-10-12 06:29:34,385][78091] Updated weights for policy 0, policy_version 77150 (0.0010) -[2023-10-12 06:29:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 157614080. Throughput: 0: 1613.4, 1: 1591.2. Samples: 39411572. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) -[2023-10-12 06:29:35,202][77203] Avg episode reward: [(0, '56.250'), (1, '44.730')] -[2023-10-12 06:29:35,214][78123] Updated weights for policy 1, policy_version 76770 (0.0008) -[2023-10-12 06:29:35,587][78123] Updated weights for policy 1, policy_version 76780 (0.0009) -[2023-10-12 06:29:35,954][78123] Updated weights for policy 1, policy_version 76790 (0.0009) -[2023-10-12 06:29:36,315][78123] Updated weights for policy 1, policy_version 76800 (0.0009) -[2023-10-12 06:29:38,439][78091] Updated weights for policy 0, policy_version 77160 (0.0010) -[2023-10-12 06:29:38,817][78091] Updated weights for policy 0, policy_version 77170 (0.0008) -[2023-10-12 06:29:39,178][78091] Updated weights for policy 0, policy_version 77180 (0.0011) -[2023-10-12 06:29:40,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 157679616. Throughput: 0: 1601.2, 1: 1603.2. Samples: 39430592. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) -[2023-10-12 06:29:40,201][77203] Avg episode reward: [(0, '59.990'), (1, '43.090')] -[2023-10-12 06:29:40,770][78123] Updated weights for policy 1, policy_version 76810 (0.0009) -[2023-10-12 06:29:41,137][78123] Updated weights for policy 1, policy_version 76820 (0.0008) -[2023-10-12 06:29:41,506][78123] Updated weights for policy 1, policy_version 76830 (0.0007) -[2023-10-12 06:29:43,471][78091] Updated weights for policy 0, policy_version 77190 (0.0009) -[2023-10-12 06:29:43,839][78091] Updated weights for policy 0, policy_version 77200 (0.0008) -[2023-10-12 06:29:44,207][78091] Updated weights for policy 0, policy_version 77210 (0.0009) -[2023-10-12 06:29:45,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 157745152. Throughput: 0: 1611.3, 1: 1585.3. Samples: 39440354. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) -[2023-10-12 06:29:45,202][77203] Avg episode reward: [(0, '54.260'), (1, '43.180')] -[2023-10-12 06:29:46,027][78123] Updated weights for policy 1, policy_version 76840 (0.0010) -[2023-10-12 06:29:46,399][78123] Updated weights for policy 1, policy_version 76850 (0.0008) -[2023-10-12 06:29:46,766][78123] Updated weights for policy 1, policy_version 76860 (0.0008) -[2023-10-12 06:29:48,537][78091] Updated weights for policy 0, policy_version 77220 (0.0007) -[2023-10-12 06:29:48,907][78091] Updated weights for policy 0, policy_version 77230 (0.0008) -[2023-10-12 06:29:49,284][78091] Updated weights for policy 0, policy_version 77240 (0.0009) -[2023-10-12 06:29:50,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 157810688. Throughput: 0: 1623.9, 1: 1578.9. Samples: 39459312. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) -[2023-10-12 06:29:50,201][77203] Avg episode reward: [(0, '54.170'), (1, '52.140')] -[2023-10-12 06:29:51,200][78123] Updated weights for policy 1, policy_version 76870 (0.0009) -[2023-10-12 06:29:51,571][78123] Updated weights for policy 1, policy_version 76880 (0.0009) -[2023-10-12 06:29:51,950][78123] Updated weights for policy 1, policy_version 76890 (0.0008) -[2023-10-12 06:29:53,624][78091] Updated weights for policy 0, policy_version 77250 (0.0007) -[2023-10-12 06:29:54,014][78091] Updated weights for policy 0, policy_version 77260 (0.0008) -[2023-10-12 06:29:54,382][78091] Updated weights for policy 0, policy_version 77270 (0.0008) -[2023-10-12 06:29:54,755][78091] Updated weights for policy 0, policy_version 77280 (0.0007) -[2023-10-12 06:29:55,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 157876224. Throughput: 0: 1608.0, 1: 1587.6. Samples: 39478146. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) -[2023-10-12 06:29:55,202][77203] Avg episode reward: [(0, '57.940'), (1, '50.530')] -[2023-10-12 06:29:56,191][78123] Updated weights for policy 1, policy_version 76900 (0.0007) -[2023-10-12 06:29:56,552][78123] Updated weights for policy 1, policy_version 76910 (0.0008) -[2023-10-12 06:29:56,906][78123] Updated weights for policy 1, policy_version 76920 (0.0009) -[2023-10-12 06:29:58,999][78091] Updated weights for policy 0, policy_version 77290 (0.0009) -[2023-10-12 06:29:59,366][78091] Updated weights for policy 0, policy_version 77300 (0.0009) -[2023-10-12 06:29:59,733][78091] Updated weights for policy 0, policy_version 77310 (0.0009) -[2023-10-12 06:30:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 157941760. Throughput: 0: 1607.3, 1: 1580.9. Samples: 39487952. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) -[2023-10-12 06:30:00,202][77203] Avg episode reward: [(0, '55.090'), (1, '52.250')] -[2023-10-12 06:30:01,361][78123] Updated weights for policy 1, policy_version 76930 (0.0009) -[2023-10-12 06:30:01,730][78123] Updated weights for policy 1, policy_version 76940 (0.0009) -[2023-10-12 06:30:02,104][78123] Updated weights for policy 1, policy_version 76950 (0.0009) -[2023-10-12 06:30:02,472][78123] Updated weights for policy 1, policy_version 76960 (0.0010) -[2023-10-12 06:30:03,978][78091] Updated weights for policy 0, policy_version 77320 (0.0011) -[2023-10-12 06:30:04,359][78091] Updated weights for policy 0, policy_version 77330 (0.0008) -[2023-10-12 06:30:04,742][78091] Updated weights for policy 0, policy_version 77340 (0.0008) -[2023-10-12 06:30:05,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 158007296. Throughput: 0: 1629.8, 1: 1577.2. Samples: 39507494. Policy #0 lag: (min: 8.0, avg: 33.0, max: 40.0) -[2023-10-12 06:30:05,202][77203] Avg episode reward: [(0, '57.550'), (1, '46.520')] -[2023-10-12 06:30:06,609][78123] Updated weights for policy 1, policy_version 76970 (0.0008) -[2023-10-12 06:30:06,977][78123] Updated weights for policy 1, policy_version 76980 (0.0008) -[2023-10-12 06:30:07,344][78123] Updated weights for policy 1, policy_version 76990 (0.0008) -[2023-10-12 06:30:09,215][78091] Updated weights for policy 0, policy_version 77350 (0.0008) -[2023-10-12 06:30:09,590][78091] Updated weights for policy 0, policy_version 77360 (0.0008) -[2023-10-12 06:30:09,957][78091] Updated weights for policy 0, policy_version 77370 (0.0008) -[2023-10-12 06:30:10,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 158072832. Throughput: 0: 1622.0, 1: 1577.4. Samples: 39526438. Policy #0 lag: (min: 8.0, avg: 33.0, max: 40.0) -[2023-10-12 06:30:10,201][77203] Avg episode reward: [(0, '59.460'), (1, '46.460')] -[2023-10-12 06:30:11,809][78123] Updated weights for policy 1, policy_version 77000 (0.0007) -[2023-10-12 06:30:12,178][78123] Updated weights for policy 1, policy_version 77010 (0.0010) -[2023-10-12 06:30:12,548][78123] Updated weights for policy 1, policy_version 77020 (0.0011) -[2023-10-12 06:30:13,965][78091] Updated weights for policy 0, policy_version 77380 (0.0009) -[2023-10-12 06:30:14,335][78091] Updated weights for policy 0, policy_version 77390 (0.0008) -[2023-10-12 06:30:14,701][78091] Updated weights for policy 0, policy_version 77400 (0.0009) -[2023-10-12 06:30:15,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 158138368. Throughput: 0: 1612.8, 1: 1576.4. Samples: 39535844. Policy #0 lag: (min: 8.0, avg: 33.0, max: 40.0) -[2023-10-12 06:30:15,201][77203] Avg episode reward: [(0, '54.030'), (1, '55.230')] -[2023-10-12 06:30:16,749][78123] Updated weights for policy 1, policy_version 77030 (0.0010) -[2023-10-12 06:30:17,125][78123] Updated weights for policy 1, policy_version 77040 (0.0009) -[2023-10-12 06:30:17,490][78123] Updated weights for policy 1, policy_version 77050 (0.0010) -[2023-10-12 06:30:18,954][78091] Updated weights for policy 0, policy_version 77410 (0.0008) -[2023-10-12 06:30:19,328][78091] Updated weights for policy 0, policy_version 77420 (0.0008) -[2023-10-12 06:30:19,697][78091] Updated weights for policy 0, policy_version 77430 (0.0010) -[2023-10-12 06:30:20,071][78091] Updated weights for policy 0, policy_version 77440 (0.0008) -[2023-10-12 06:30:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 158203904. Throughput: 0: 1621.7, 1: 1581.2. Samples: 39555704. Policy #0 lag: (min: 8.0, avg: 33.0, max: 40.0) -[2023-10-12 06:30:20,201][77203] Avg episode reward: [(0, '57.910'), (1, '46.080')] -[2023-10-12 06:30:21,777][78123] Updated weights for policy 1, policy_version 77060 (0.0010) -[2023-10-12 06:30:22,152][78123] Updated weights for policy 1, policy_version 77070 (0.0008) -[2023-10-12 06:30:22,521][78123] Updated weights for policy 1, policy_version 77080 (0.0009) -[2023-10-12 06:30:24,475][78091] Updated weights for policy 0, policy_version 77450 (0.0008) -[2023-10-12 06:30:24,860][78091] Updated weights for policy 0, policy_version 77460 (0.0009) -[2023-10-12 06:30:25,201][77203] Fps is (10 sec: 9830.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 158236672. Throughput: 0: 1612.8, 1: 1584.6. Samples: 39574478. Policy #0 lag: (min: 8.0, avg: 33.0, max: 40.0) -[2023-10-12 06:30:25,202][77203] Avg episode reward: [(0, '61.330'), (1, '46.740')] -[2023-10-12 06:30:25,235][78091] Updated weights for policy 0, policy_version 77470 (0.0009) -[2023-10-12 06:30:26,652][78123] Updated weights for policy 1, policy_version 77090 (0.0009) -[2023-10-12 06:30:27,011][78123] Updated weights for policy 1, policy_version 77100 (0.0007) -[2023-10-12 06:30:27,376][78123] Updated weights for policy 1, policy_version 77110 (0.0010) -[2023-10-12 06:30:27,743][78123] Updated weights for policy 1, policy_version 77120 (0.0010) -[2023-10-12 06:30:29,601][78091] Updated weights for policy 0, policy_version 77480 (0.0009) -[2023-10-12 06:30:29,977][78091] Updated weights for policy 0, policy_version 77490 (0.0008) -[2023-10-12 06:30:30,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 158302208. Throughput: 0: 1597.6, 1: 1590.9. Samples: 39583834. Policy #0 lag: (min: 8.0, avg: 33.0, max: 40.0) -[2023-10-12 06:30:30,201][77203] Avg episode reward: [(0, '62.810'), (1, '50.210')] -[2023-10-12 06:30:30,343][78091] Updated weights for policy 0, policy_version 77500 (0.0008) -[2023-10-12 06:30:32,201][78123] Updated weights for policy 1, policy_version 77130 (0.0009) -[2023-10-12 06:30:32,571][78123] Updated weights for policy 1, policy_version 77140 (0.0008) -[2023-10-12 06:30:32,936][78123] Updated weights for policy 1, policy_version 77150 (0.0007) -[2023-10-12 06:30:34,601][78091] Updated weights for policy 0, policy_version 77510 (0.0009) -[2023-10-12 06:30:34,970][78091] Updated weights for policy 0, policy_version 77520 (0.0007) -[2023-10-12 06:30:35,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 158367744. Throughput: 0: 1606.8, 1: 1590.3. Samples: 39603178. Policy #0 lag: (min: 8.0, avg: 33.0, max: 40.0) -[2023-10-12 06:30:35,201][77203] Avg episode reward: [(0, '63.230'), (1, '49.460')] -[2023-10-12 06:30:35,345][78091] Updated weights for policy 0, policy_version 77530 (0.0008) -[2023-10-12 06:30:37,140][78123] Updated weights for policy 1, policy_version 77160 (0.0008) -[2023-10-12 06:30:37,504][78123] Updated weights for policy 1, policy_version 77170 (0.0008) -[2023-10-12 06:30:37,870][78123] Updated weights for policy 1, policy_version 77180 (0.0009) -[2023-10-12 06:30:39,677][78091] Updated weights for policy 0, policy_version 77540 (0.0009) -[2023-10-12 06:30:40,065][78091] Updated weights for policy 0, policy_version 77550 (0.0010) -[2023-10-12 06:30:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 158433280. Throughput: 0: 1615.9, 1: 1590.1. Samples: 39622418. Policy #0 lag: (min: 8.0, avg: 33.0, max: 40.0) -[2023-10-12 06:30:40,201][77203] Avg episode reward: [(0, '57.650'), (1, '57.600')] -[2023-10-12 06:30:40,438][78091] Updated weights for policy 0, policy_version 77560 (0.0009) -[2023-10-12 06:30:42,315][78123] Updated weights for policy 1, policy_version 77190 (0.0009) -[2023-10-12 06:30:42,688][78123] Updated weights for policy 1, policy_version 77200 (0.0007) -[2023-10-12 06:30:43,063][78123] Updated weights for policy 1, policy_version 77210 (0.0007) -[2023-10-12 06:30:44,766][78091] Updated weights for policy 0, policy_version 77570 (0.0010) -[2023-10-12 06:30:45,143][78091] Updated weights for policy 0, policy_version 77580 (0.0009) -[2023-10-12 06:30:45,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 158498816. Throughput: 0: 1594.6, 1: 1599.5. Samples: 39631688. Policy #0 lag: (min: 8.0, avg: 33.0, max: 40.0) -[2023-10-12 06:30:45,201][77203] Avg episode reward: [(0, '55.560'), (1, '55.660')] -[2023-10-12 06:30:45,504][78091] Updated weights for policy 0, policy_version 77590 (0.0008) -[2023-10-12 06:30:45,884][78091] Updated weights for policy 0, policy_version 77600 (0.0009) -[2023-10-12 06:30:47,413][78123] Updated weights for policy 1, policy_version 77220 (0.0008) -[2023-10-12 06:30:47,790][78123] Updated weights for policy 1, policy_version 77230 (0.0008) -[2023-10-12 06:30:48,155][78123] Updated weights for policy 1, policy_version 77240 (0.0009) -[2023-10-12 06:30:50,121][78091] Updated weights for policy 0, policy_version 77610 (0.0008) -[2023-10-12 06:30:50,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 158564352. Throughput: 0: 1592.2, 1: 1590.2. Samples: 39650702. Policy #0 lag: (min: 8.0, avg: 33.0, max: 40.0) -[2023-10-12 06:30:50,201][77203] Avg episode reward: [(0, '58.000'), (1, '48.130')] -[2023-10-12 06:30:50,495][78091] Updated weights for policy 0, policy_version 77620 (0.0009) -[2023-10-12 06:30:50,877][78091] Updated weights for policy 0, policy_version 77630 (0.0009) -[2023-10-12 06:30:52,506][78123] Updated weights for policy 1, policy_version 77250 (0.0007) -[2023-10-12 06:30:52,873][78123] Updated weights for policy 1, policy_version 77260 (0.0007) -[2023-10-12 06:30:53,248][78123] Updated weights for policy 1, policy_version 77270 (0.0007) -[2023-10-12 06:30:53,607][78123] Updated weights for policy 1, policy_version 77280 (0.0008) -[2023-10-12 06:30:55,103][78091] Updated weights for policy 0, policy_version 77640 (0.0008) -[2023-10-12 06:30:55,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 158629888. Throughput: 0: 1610.4, 1: 1594.7. Samples: 39670668. Policy #0 lag: (min: 8.0, avg: 33.0, max: 40.0) -[2023-10-12 06:30:55,201][77203] Avg episode reward: [(0, '56.060'), (1, '51.650')] -[2023-10-12 06:30:55,467][78091] Updated weights for policy 0, policy_version 77650 (0.0007) -[2023-10-12 06:30:55,840][78091] Updated weights for policy 0, policy_version 77660 (0.0009) -[2023-10-12 06:30:57,770][78123] Updated weights for policy 1, policy_version 77290 (0.0008) -[2023-10-12 06:30:58,136][78123] Updated weights for policy 1, policy_version 77300 (0.0007) -[2023-10-12 06:30:58,502][78123] Updated weights for policy 1, policy_version 77310 (0.0007) -[2023-10-12 06:31:00,103][78091] Updated weights for policy 0, policy_version 77670 (0.0007) -[2023-10-12 06:31:00,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 158695424. Throughput: 0: 1591.6, 1: 1615.2. Samples: 39680148. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-12 06:31:00,201][77203] Avg episode reward: [(0, '52.140'), (1, '49.680')] -[2023-10-12 06:31:00,466][78091] Updated weights for policy 0, policy_version 77680 (0.0009) -[2023-10-12 06:31:00,847][78091] Updated weights for policy 0, policy_version 77690 (0.0007) -[2023-10-12 06:31:02,880][78123] Updated weights for policy 1, policy_version 77320 (0.0010) -[2023-10-12 06:31:03,249][78123] Updated weights for policy 1, policy_version 77330 (0.0008) -[2023-10-12 06:31:03,621][78123] Updated weights for policy 1, policy_version 77340 (0.0008) -[2023-10-12 06:31:05,144][78091] Updated weights for policy 0, policy_version 77700 (0.0009) -[2023-10-12 06:31:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 158760960. Throughput: 0: 1594.4, 1: 1593.9. Samples: 39699178. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-12 06:31:05,201][77203] Avg episode reward: [(0, '54.490'), (1, '51.090')] -[2023-10-12 06:31:05,517][78091] Updated weights for policy 0, policy_version 77710 (0.0007) -[2023-10-12 06:31:05,897][78091] Updated weights for policy 0, policy_version 77720 (0.0008) -[2023-10-12 06:31:08,017][78123] Updated weights for policy 1, policy_version 77350 (0.0008) -[2023-10-12 06:31:08,382][78123] Updated weights for policy 1, policy_version 77360 (0.0007) -[2023-10-12 06:31:08,745][78123] Updated weights for policy 1, policy_version 77370 (0.0009) -[2023-10-12 06:31:10,087][78091] Updated weights for policy 0, policy_version 77730 (0.0008) -[2023-10-12 06:31:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 158826496. Throughput: 0: 1610.7, 1: 1594.3. Samples: 39718702. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-12 06:31:10,201][77203] Avg episode reward: [(0, '52.490'), (1, '52.010')] -[2023-10-12 06:31:10,208][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000077376_79233024.pth... -[2023-10-12 06:31:10,247][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000075872_77692928.pth -[2023-10-12 06:31:10,467][78091] Updated weights for policy 0, policy_version 77740 (0.0009) -[2023-10-12 06:31:10,832][78091] Updated weights for policy 0, policy_version 77750 (0.0009) -[2023-10-12 06:31:11,205][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000077760_79626240.pth... -[2023-10-12 06:31:11,210][78091] Updated weights for policy 0, policy_version 77760 (0.0010) -[2023-10-12 06:31:11,243][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000076256_78086144.pth -[2023-10-12 06:31:13,008][78123] Updated weights for policy 1, policy_version 77380 (0.0008) -[2023-10-12 06:31:13,386][78123] Updated weights for policy 1, policy_version 77390 (0.0008) -[2023-10-12 06:31:13,753][78123] Updated weights for policy 1, policy_version 77400 (0.0008) -[2023-10-12 06:31:15,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 158892032. Throughput: 0: 1600.0, 1: 1616.7. Samples: 39728588. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-12 06:31:15,202][77203] Avg episode reward: [(0, '59.130'), (1, '47.410')] -[2023-10-12 06:31:15,483][78091] Updated weights for policy 0, policy_version 77770 (0.0009) -[2023-10-12 06:31:15,853][78091] Updated weights for policy 0, policy_version 77780 (0.0009) -[2023-10-12 06:31:16,232][78091] Updated weights for policy 0, policy_version 77790 (0.0008) -[2023-10-12 06:31:18,001][78123] Updated weights for policy 1, policy_version 77410 (0.0008) -[2023-10-12 06:31:18,422][78123] Updated weights for policy 1, policy_version 77420 (0.0007) -[2023-10-12 06:31:18,794][78123] Updated weights for policy 1, policy_version 77430 (0.0007) -[2023-10-12 06:31:19,166][78123] Updated weights for policy 1, policy_version 77440 (0.0007) -[2023-10-12 06:31:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12885.1). Total num frames: 158957568. Throughput: 0: 1594.1, 1: 1606.7. Samples: 39747212. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-12 06:31:20,201][77203] Avg episode reward: [(0, '54.200'), (1, '48.960')] -[2023-10-12 06:31:20,632][78091] Updated weights for policy 0, policy_version 77800 (0.0008) -[2023-10-12 06:31:21,013][78091] Updated weights for policy 0, policy_version 77810 (0.0009) -[2023-10-12 06:31:21,386][78091] Updated weights for policy 0, policy_version 77820 (0.0008) -[2023-10-12 06:31:23,324][78123] Updated weights for policy 1, policy_version 77450 (0.0008) -[2023-10-12 06:31:23,694][78123] Updated weights for policy 1, policy_version 77460 (0.0008) -[2023-10-12 06:31:24,071][78123] Updated weights for policy 1, policy_version 77470 (0.0008) -[2023-10-12 06:31:25,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.3, 300 sec: 12885.1). Total num frames: 159023104. Throughput: 0: 1603.6, 1: 1597.7. Samples: 39766474. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-12 06:31:25,201][77203] Avg episode reward: [(0, '53.700'), (1, '48.910')] -[2023-10-12 06:31:25,648][78091] Updated weights for policy 0, policy_version 77830 (0.0009) -[2023-10-12 06:31:26,028][78091] Updated weights for policy 0, policy_version 77840 (0.0007) -[2023-10-12 06:31:26,391][78091] Updated weights for policy 0, policy_version 77850 (0.0007) -[2023-10-12 06:31:28,434][78123] Updated weights for policy 1, policy_version 77480 (0.0010) -[2023-10-12 06:31:28,799][78123] Updated weights for policy 1, policy_version 77490 (0.0009) -[2023-10-12 06:31:29,174][78123] Updated weights for policy 1, policy_version 77500 (0.0008) -[2023-10-12 06:31:30,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 159088640. Throughput: 0: 1596.2, 1: 1616.6. Samples: 39776264. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-12 06:31:30,202][77203] Avg episode reward: [(0, '56.050'), (1, '52.130')] -[2023-10-12 06:31:30,607][78091] Updated weights for policy 0, policy_version 77860 (0.0009) -[2023-10-12 06:31:30,978][78091] Updated weights for policy 0, policy_version 77870 (0.0010) -[2023-10-12 06:31:31,349][78091] Updated weights for policy 0, policy_version 77880 (0.0008) -[2023-10-12 06:31:33,526][78123] Updated weights for policy 1, policy_version 77510 (0.0008) -[2023-10-12 06:31:33,886][78123] Updated weights for policy 1, policy_version 77520 (0.0008) -[2023-10-12 06:31:34,255][78123] Updated weights for policy 1, policy_version 77530 (0.0007) -[2023-10-12 06:31:35,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 159154176. Throughput: 0: 1601.2, 1: 1619.0. Samples: 39795610. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-12 06:31:35,202][77203] Avg episode reward: [(0, '53.730'), (1, '54.400')] -[2023-10-12 06:31:35,543][78091] Updated weights for policy 0, policy_version 77890 (0.0007) -[2023-10-12 06:31:35,915][78091] Updated weights for policy 0, policy_version 77900 (0.0008) -[2023-10-12 06:31:36,271][78091] Updated weights for policy 0, policy_version 77910 (0.0009) -[2023-10-12 06:31:36,637][78091] Updated weights for policy 0, policy_version 77920 (0.0009) -[2023-10-12 06:31:38,501][78123] Updated weights for policy 1, policy_version 77540 (0.0008) -[2023-10-12 06:31:38,875][78123] Updated weights for policy 1, policy_version 77550 (0.0009) -[2023-10-12 06:31:39,246][78123] Updated weights for policy 1, policy_version 77560 (0.0008) -[2023-10-12 06:31:40,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 159219712. Throughput: 0: 1602.8, 1: 1594.6. Samples: 39814552. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-12 06:31:40,201][77203] Avg episode reward: [(0, '55.000'), (1, '45.930')] -[2023-10-12 06:31:40,958][78091] Updated weights for policy 0, policy_version 77930 (0.0010) -[2023-10-12 06:31:41,325][78091] Updated weights for policy 0, policy_version 77940 (0.0009) -[2023-10-12 06:31:41,694][78091] Updated weights for policy 0, policy_version 77950 (0.0009) -[2023-10-12 06:31:43,707][78123] Updated weights for policy 1, policy_version 77570 (0.0008) -[2023-10-12 06:31:44,078][78123] Updated weights for policy 1, policy_version 77580 (0.0010) -[2023-10-12 06:31:44,439][78123] Updated weights for policy 1, policy_version 77590 (0.0010) -[2023-10-12 06:31:44,800][78123] Updated weights for policy 1, policy_version 77600 (0.0008) -[2023-10-12 06:31:45,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 159285248. Throughput: 0: 1602.2, 1: 1598.4. Samples: 39824172. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-12 06:31:45,202][77203] Avg episode reward: [(0, '49.280'), (1, '46.670')] -[2023-10-12 06:31:45,960][78091] Updated weights for policy 0, policy_version 77960 (0.0009) -[2023-10-12 06:31:46,322][78091] Updated weights for policy 0, policy_version 77970 (0.0010) -[2023-10-12 06:31:46,699][78091] Updated weights for policy 0, policy_version 77980 (0.0010) -[2023-10-12 06:31:49,041][78123] Updated weights for policy 1, policy_version 77610 (0.0007) -[2023-10-12 06:31:49,399][78123] Updated weights for policy 1, policy_version 77620 (0.0008) -[2023-10-12 06:31:49,768][78123] Updated weights for policy 1, policy_version 77630 (0.0008) -[2023-10-12 06:31:50,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 159350784. Throughput: 0: 1602.9, 1: 1614.6. Samples: 39843966. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-12 06:31:50,201][77203] Avg episode reward: [(0, '50.270'), (1, '46.360')] -[2023-10-12 06:31:51,088][78091] Updated weights for policy 0, policy_version 77990 (0.0007) -[2023-10-12 06:31:51,456][78091] Updated weights for policy 0, policy_version 78000 (0.0008) -[2023-10-12 06:31:51,822][78091] Updated weights for policy 0, policy_version 78010 (0.0009) -[2023-10-12 06:31:54,045][78123] Updated weights for policy 1, policy_version 77640 (0.0008) -[2023-10-12 06:31:54,422][78123] Updated weights for policy 1, policy_version 77650 (0.0010) -[2023-10-12 06:31:54,796][78123] Updated weights for policy 1, policy_version 77660 (0.0008) -[2023-10-12 06:31:55,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 159416320. Throughput: 0: 1603.9, 1: 1602.6. Samples: 39862994. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-12 06:31:55,202][77203] Avg episode reward: [(0, '47.410'), (1, '51.370')] -[2023-10-12 06:31:56,002][78091] Updated weights for policy 0, policy_version 78020 (0.0008) -[2023-10-12 06:31:56,372][78091] Updated weights for policy 0, policy_version 78030 (0.0011) -[2023-10-12 06:31:56,743][78091] Updated weights for policy 0, policy_version 78040 (0.0008) -[2023-10-12 06:31:59,043][78123] Updated weights for policy 1, policy_version 77670 (0.0008) -[2023-10-12 06:31:59,406][78123] Updated weights for policy 1, policy_version 77680 (0.0008) -[2023-10-12 06:31:59,775][78123] Updated weights for policy 1, policy_version 77690 (0.0008) -[2023-10-12 06:32:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 159481856. Throughput: 0: 1604.4, 1: 1599.2. Samples: 39872752. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-12 06:32:00,201][77203] Avg episode reward: [(0, '58.510'), (1, '53.020')] -[2023-10-12 06:32:00,923][78091] Updated weights for policy 0, policy_version 78050 (0.0007) -[2023-10-12 06:32:01,304][78091] Updated weights for policy 0, policy_version 78060 (0.0008) -[2023-10-12 06:32:01,678][78091] Updated weights for policy 0, policy_version 78070 (0.0007) -[2023-10-12 06:32:02,039][78091] Updated weights for policy 0, policy_version 78080 (0.0007) -[2023-10-12 06:32:04,216][78123] Updated weights for policy 1, policy_version 77700 (0.0010) -[2023-10-12 06:32:04,581][78123] Updated weights for policy 1, policy_version 77710 (0.0009) -[2023-10-12 06:32:04,944][78123] Updated weights for policy 1, policy_version 77720 (0.0007) -[2023-10-12 06:32:05,201][77203] Fps is (10 sec: 9830.6, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 159514624. Throughput: 0: 1611.4, 1: 1616.8. Samples: 39892480. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-12 06:32:05,202][77203] Avg episode reward: [(0, '54.100'), (1, '56.850')] -[2023-10-12 06:32:06,238][78091] Updated weights for policy 0, policy_version 78090 (0.0008) -[2023-10-12 06:32:06,609][78091] Updated weights for policy 0, policy_version 78100 (0.0009) -[2023-10-12 06:32:06,980][78091] Updated weights for policy 0, policy_version 78110 (0.0008) -[2023-10-12 06:32:09,214][78123] Updated weights for policy 1, policy_version 77730 (0.0008) -[2023-10-12 06:32:09,573][78123] Updated weights for policy 1, policy_version 77740 (0.0009) -[2023-10-12 06:32:09,946][78123] Updated weights for policy 1, policy_version 77750 (0.0007) -[2023-10-12 06:32:10,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 159580160. Throughput: 0: 1611.2, 1: 1611.9. Samples: 39911514. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-12 06:32:10,201][77203] Avg episode reward: [(0, '53.990'), (1, '56.630')] -[2023-10-12 06:32:10,304][78123] Updated weights for policy 1, policy_version 77760 (0.0009) -[2023-10-12 06:32:11,384][78091] Updated weights for policy 0, policy_version 78120 (0.0009) -[2023-10-12 06:32:11,760][78091] Updated weights for policy 0, policy_version 78130 (0.0010) -[2023-10-12 06:32:12,142][78091] Updated weights for policy 0, policy_version 78140 (0.0012) -[2023-10-12 06:32:14,756][78123] Updated weights for policy 1, policy_version 77770 (0.0009) -[2023-10-12 06:32:15,122][78123] Updated weights for policy 1, policy_version 77780 (0.0008) -[2023-10-12 06:32:15,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 159645696. Throughput: 0: 1612.0, 1: 1595.6. Samples: 39920606. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-12 06:32:15,202][77203] Avg episode reward: [(0, '63.220'), (1, '51.170')] -[2023-10-12 06:32:15,494][78123] Updated weights for policy 1, policy_version 77790 (0.0007) -[2023-10-12 06:32:16,559][78091] Updated weights for policy 0, policy_version 78150 (0.0009) -[2023-10-12 06:32:16,930][78091] Updated weights for policy 0, policy_version 78160 (0.0008) -[2023-10-12 06:32:17,305][78091] Updated weights for policy 0, policy_version 78170 (0.0009) -[2023-10-12 06:32:19,754][78123] Updated weights for policy 1, policy_version 77800 (0.0007) -[2023-10-12 06:32:20,121][78123] Updated weights for policy 1, policy_version 77810 (0.0007) -[2023-10-12 06:32:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 159711232. Throughput: 0: 1608.2, 1: 1605.7. Samples: 39940236. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-12 06:32:20,201][77203] Avg episode reward: [(0, '60.870'), (1, '50.410')] -[2023-10-12 06:32:20,490][78123] Updated weights for policy 1, policy_version 77820 (0.0010) -[2023-10-12 06:32:21,533][78091] Updated weights for policy 0, policy_version 78180 (0.0008) -[2023-10-12 06:32:21,911][78091] Updated weights for policy 0, policy_version 78190 (0.0008) -[2023-10-12 06:32:22,276][78091] Updated weights for policy 0, policy_version 78200 (0.0009) -[2023-10-12 06:32:24,801][78123] Updated weights for policy 1, policy_version 77830 (0.0008) -[2023-10-12 06:32:25,170][78123] Updated weights for policy 1, policy_version 77840 (0.0007) -[2023-10-12 06:32:25,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 159776768. Throughput: 0: 1603.5, 1: 1620.5. Samples: 39959634. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-12 06:32:25,202][77203] Avg episode reward: [(0, '63.680'), (1, '50.610')] -[2023-10-12 06:32:25,528][78123] Updated weights for policy 1, policy_version 77850 (0.0007) -[2023-10-12 06:32:26,666][78091] Updated weights for policy 0, policy_version 78210 (0.0009) -[2023-10-12 06:32:27,028][78091] Updated weights for policy 0, policy_version 78220 (0.0007) -[2023-10-12 06:32:27,400][78091] Updated weights for policy 0, policy_version 78230 (0.0010) -[2023-10-12 06:32:27,763][78091] Updated weights for policy 0, policy_version 78240 (0.0008) -[2023-10-12 06:32:29,809][78123] Updated weights for policy 1, policy_version 77860 (0.0007) -[2023-10-12 06:32:30,170][78123] Updated weights for policy 1, policy_version 77870 (0.0008) -[2023-10-12 06:32:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 159842304. Throughput: 0: 1603.2, 1: 1601.2. Samples: 39968368. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-12 06:32:30,201][77203] Avg episode reward: [(0, '53.040'), (1, '46.220')] -[2023-10-12 06:32:30,534][78123] Updated weights for policy 1, policy_version 77880 (0.0010) -[2023-10-12 06:32:32,202][78091] Updated weights for policy 0, policy_version 78250 (0.0009) -[2023-10-12 06:32:32,575][78091] Updated weights for policy 0, policy_version 78260 (0.0008) -[2023-10-12 06:32:32,948][78091] Updated weights for policy 0, policy_version 78270 (0.0008) -[2023-10-12 06:32:34,996][78123] Updated weights for policy 1, policy_version 77890 (0.0009) -[2023-10-12 06:32:35,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 159907840. Throughput: 0: 1597.6, 1: 1599.7. Samples: 39987844. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-12 06:32:35,201][77203] Avg episode reward: [(0, '55.910'), (1, '48.770')] -[2023-10-12 06:32:35,365][78123] Updated weights for policy 1, policy_version 77900 (0.0008) -[2023-10-12 06:32:35,718][78123] Updated weights for policy 1, policy_version 77910 (0.0011) -[2023-10-12 06:32:36,091][78123] Updated weights for policy 1, policy_version 77920 (0.0009) -[2023-10-12 06:32:37,326][78091] Updated weights for policy 0, policy_version 78280 (0.0008) -[2023-10-12 06:32:37,687][78091] Updated weights for policy 0, policy_version 78290 (0.0010) -[2023-10-12 06:32:38,059][78091] Updated weights for policy 0, policy_version 78300 (0.0008) -[2023-10-12 06:32:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 159973376. Throughput: 0: 1597.4, 1: 1607.7. Samples: 40007222. Policy #0 lag: (min: 5.0, avg: 12.4, max: 37.0) -[2023-10-12 06:32:40,201][77203] Avg episode reward: [(0, '60.720'), (1, '46.500')] -[2023-10-12 06:32:40,505][78123] Updated weights for policy 1, policy_version 77930 (0.0010) -[2023-10-12 06:32:40,868][78123] Updated weights for policy 1, policy_version 77940 (0.0010) -[2023-10-12 06:32:41,235][78123] Updated weights for policy 1, policy_version 77950 (0.0010) -[2023-10-12 06:32:42,291][78091] Updated weights for policy 0, policy_version 78310 (0.0009) -[2023-10-12 06:32:42,666][78091] Updated weights for policy 0, policy_version 78320 (0.0010) -[2023-10-12 06:32:43,046][78091] Updated weights for policy 0, policy_version 78330 (0.0008) -[2023-10-12 06:32:45,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 160038912. Throughput: 0: 1604.4, 1: 1585.0. Samples: 40016278. Policy #0 lag: (min: 5.0, avg: 12.4, max: 37.0) -[2023-10-12 06:32:45,202][77203] Avg episode reward: [(0, '55.890'), (1, '39.990')] -[2023-10-12 06:32:45,536][78123] Updated weights for policy 1, policy_version 77960 (0.0009) -[2023-10-12 06:32:45,899][78123] Updated weights for policy 1, policy_version 77970 (0.0009) -[2023-10-12 06:32:46,269][78123] Updated weights for policy 1, policy_version 77980 (0.0010) -[2023-10-12 06:32:47,262][78091] Updated weights for policy 0, policy_version 78340 (0.0008) -[2023-10-12 06:32:47,631][78091] Updated weights for policy 0, policy_version 78350 (0.0008) -[2023-10-12 06:32:47,996][78091] Updated weights for policy 0, policy_version 78360 (0.0008) -[2023-10-12 06:32:50,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 160104448. Throughput: 0: 1589.5, 1: 1580.7. Samples: 40035142. Policy #0 lag: (min: 5.0, avg: 12.4, max: 37.0) -[2023-10-12 06:32:50,202][77203] Avg episode reward: [(0, '60.680'), (1, '49.820')] -[2023-10-12 06:32:50,807][78123] Updated weights for policy 1, policy_version 77990 (0.0010) -[2023-10-12 06:32:51,196][78123] Updated weights for policy 1, policy_version 78000 (0.0010) -[2023-10-12 06:32:51,560][78123] Updated weights for policy 1, policy_version 78010 (0.0007) -[2023-10-12 06:32:52,473][78091] Updated weights for policy 0, policy_version 78370 (0.0007) -[2023-10-12 06:32:52,832][78091] Updated weights for policy 0, policy_version 78380 (0.0007) -[2023-10-12 06:32:53,202][78091] Updated weights for policy 0, policy_version 78390 (0.0007) -[2023-10-12 06:32:53,570][78091] Updated weights for policy 0, policy_version 78400 (0.0008) -[2023-10-12 06:32:55,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 160169984. Throughput: 0: 1584.2, 1: 1586.5. Samples: 40054196. Policy #0 lag: (min: 5.0, avg: 12.4, max: 37.0) -[2023-10-12 06:32:55,201][77203] Avg episode reward: [(0, '56.820'), (1, '53.910')] -[2023-10-12 06:32:56,054][78123] Updated weights for policy 1, policy_version 78020 (0.0008) -[2023-10-12 06:32:56,437][78123] Updated weights for policy 1, policy_version 78030 (0.0009) -[2023-10-12 06:32:56,801][78123] Updated weights for policy 1, policy_version 78040 (0.0010) -[2023-10-12 06:32:58,050][78091] Updated weights for policy 0, policy_version 78410 (0.0009) -[2023-10-12 06:32:58,430][78091] Updated weights for policy 0, policy_version 78420 (0.0008) -[2023-10-12 06:32:58,788][78091] Updated weights for policy 0, policy_version 78430 (0.0008) -[2023-10-12 06:33:00,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 160235520. Throughput: 0: 1606.3, 1: 1571.6. Samples: 40063608. Policy #0 lag: (min: 5.0, avg: 12.4, max: 37.0) -[2023-10-12 06:33:00,202][77203] Avg episode reward: [(0, '58.390'), (1, '54.080')] -[2023-10-12 06:33:01,198][78123] Updated weights for policy 1, policy_version 78050 (0.0009) -[2023-10-12 06:33:01,557][78123] Updated weights for policy 1, policy_version 78060 (0.0007) -[2023-10-12 06:33:01,929][78123] Updated weights for policy 1, policy_version 78070 (0.0007) -[2023-10-12 06:33:02,303][78123] Updated weights for policy 1, policy_version 78080 (0.0007) -[2023-10-12 06:33:03,107][78091] Updated weights for policy 0, policy_version 78440 (0.0007) -[2023-10-12 06:33:03,477][78091] Updated weights for policy 0, policy_version 78450 (0.0008) -[2023-10-12 06:33:03,842][78091] Updated weights for policy 0, policy_version 78460 (0.0008) -[2023-10-12 06:33:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 160301056. Throughput: 0: 1584.5, 1: 1568.8. Samples: 40082136. Policy #0 lag: (min: 5.0, avg: 12.4, max: 37.0) -[2023-10-12 06:33:05,201][77203] Avg episode reward: [(0, '58.960'), (1, '46.600')] -[2023-10-12 06:33:06,581][78123] Updated weights for policy 1, policy_version 78090 (0.0007) -[2023-10-12 06:33:06,946][78123] Updated weights for policy 1, policy_version 78100 (0.0010) -[2023-10-12 06:33:07,317][78123] Updated weights for policy 1, policy_version 78110 (0.0009) -[2023-10-12 06:33:08,131][78091] Updated weights for policy 0, policy_version 78470 (0.0008) -[2023-10-12 06:33:08,500][78091] Updated weights for policy 0, policy_version 78480 (0.0007) -[2023-10-12 06:33:08,874][78091] Updated weights for policy 0, policy_version 78490 (0.0007) -[2023-10-12 06:33:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 160366592. Throughput: 0: 1580.0, 1: 1572.2. Samples: 40101484. Policy #0 lag: (min: 5.0, avg: 12.4, max: 37.0) -[2023-10-12 06:33:10,201][77203] Avg episode reward: [(0, '59.800'), (1, '48.840')] -[2023-10-12 06:33:10,209][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000078112_79986688.pth... -[2023-10-12 06:33:10,209][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000078496_80379904.pth... -[2023-10-12 06:33:10,252][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000076640_78479360.pth -[2023-10-12 06:33:10,253][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000076992_78839808.pth -[2023-10-12 06:33:11,552][78123] Updated weights for policy 1, policy_version 78120 (0.0009) -[2023-10-12 06:33:11,924][78123] Updated weights for policy 1, policy_version 78130 (0.0009) -[2023-10-12 06:33:12,300][78123] Updated weights for policy 1, policy_version 78140 (0.0008) -[2023-10-12 06:33:13,119][78091] Updated weights for policy 0, policy_version 78500 (0.0009) -[2023-10-12 06:33:13,482][78091] Updated weights for policy 0, policy_version 78510 (0.0008) -[2023-10-12 06:33:13,849][78091] Updated weights for policy 0, policy_version 78520 (0.0008) -[2023-10-12 06:33:15,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 160432128. Throughput: 0: 1609.0, 1: 1565.1. Samples: 40111204. Policy #0 lag: (min: 5.0, avg: 12.4, max: 37.0) -[2023-10-12 06:33:15,202][77203] Avg episode reward: [(0, '61.610'), (1, '46.620')] -[2023-10-12 06:33:16,770][78123] Updated weights for policy 1, policy_version 78150 (0.0010) -[2023-10-12 06:33:17,126][78123] Updated weights for policy 1, policy_version 78160 (0.0007) -[2023-10-12 06:33:17,500][78123] Updated weights for policy 1, policy_version 78170 (0.0009) -[2023-10-12 06:33:18,361][78091] Updated weights for policy 0, policy_version 78530 (0.0010) -[2023-10-12 06:33:18,723][78091] Updated weights for policy 0, policy_version 78540 (0.0009) -[2023-10-12 06:33:19,095][78091] Updated weights for policy 0, policy_version 78550 (0.0008) -[2023-10-12 06:33:19,463][78091] Updated weights for policy 0, policy_version 78560 (0.0009) -[2023-10-12 06:33:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 160497664. Throughput: 0: 1598.0, 1: 1565.2. Samples: 40130190. Policy #0 lag: (min: 5.0, avg: 12.4, max: 37.0) -[2023-10-12 06:33:20,201][77203] Avg episode reward: [(0, '60.270'), (1, '45.330')] -[2023-10-12 06:33:21,818][78123] Updated weights for policy 1, policy_version 78180 (0.0007) -[2023-10-12 06:33:22,187][78123] Updated weights for policy 1, policy_version 78190 (0.0008) -[2023-10-12 06:33:22,549][78123] Updated weights for policy 1, policy_version 78200 (0.0011) -[2023-10-12 06:33:23,711][78091] Updated weights for policy 0, policy_version 78570 (0.0007) -[2023-10-12 06:33:24,082][78091] Updated weights for policy 0, policy_version 78580 (0.0008) -[2023-10-12 06:33:24,443][78091] Updated weights for policy 0, policy_version 78590 (0.0007) -[2023-10-12 06:33:25,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.3, 300 sec: 12774.0). Total num frames: 160563200. Throughput: 0: 1584.4, 1: 1566.7. Samples: 40149018. Policy #0 lag: (min: 5.0, avg: 12.4, max: 37.0) -[2023-10-12 06:33:25,201][77203] Avg episode reward: [(0, '56.360'), (1, '49.750')] -[2023-10-12 06:33:26,908][78123] Updated weights for policy 1, policy_version 78210 (0.0007) -[2023-10-12 06:33:27,278][78123] Updated weights for policy 1, policy_version 78220 (0.0007) -[2023-10-12 06:33:27,636][78123] Updated weights for policy 1, policy_version 78230 (0.0009) -[2023-10-12 06:33:28,000][78123] Updated weights for policy 1, policy_version 78240 (0.0009) -[2023-10-12 06:33:28,628][78091] Updated weights for policy 0, policy_version 78600 (0.0009) -[2023-10-12 06:33:29,002][78091] Updated weights for policy 0, policy_version 78610 (0.0008) -[2023-10-12 06:33:29,367][78091] Updated weights for policy 0, policy_version 78620 (0.0008) -[2023-10-12 06:33:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 160628736. Throughput: 0: 1602.3, 1: 1575.0. Samples: 40159256. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:33:30,202][77203] Avg episode reward: [(0, '57.500'), (1, '47.710')] -[2023-10-12 06:33:32,074][78123] Updated weights for policy 1, policy_version 78250 (0.0007) -[2023-10-12 06:33:32,441][78123] Updated weights for policy 1, policy_version 78260 (0.0007) -[2023-10-12 06:33:32,804][78123] Updated weights for policy 1, policy_version 78270 (0.0008) -[2023-10-12 06:33:33,652][78091] Updated weights for policy 0, policy_version 78630 (0.0010) -[2023-10-12 06:33:34,025][78091] Updated weights for policy 0, policy_version 78640 (0.0008) -[2023-10-12 06:33:34,394][78091] Updated weights for policy 0, policy_version 78650 (0.0007) -[2023-10-12 06:33:35,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 160694272. Throughput: 0: 1609.4, 1: 1578.6. Samples: 40178600. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:33:35,201][77203] Avg episode reward: [(0, '55.610'), (1, '46.860')] -[2023-10-12 06:33:37,245][78123] Updated weights for policy 1, policy_version 78280 (0.0008) -[2023-10-12 06:33:37,621][78123] Updated weights for policy 1, policy_version 78290 (0.0008) -[2023-10-12 06:33:37,985][78123] Updated weights for policy 1, policy_version 78300 (0.0007) -[2023-10-12 06:33:38,642][78091] Updated weights for policy 0, policy_version 78660 (0.0007) -[2023-10-12 06:33:39,007][78091] Updated weights for policy 0, policy_version 78670 (0.0007) -[2023-10-12 06:33:39,373][78091] Updated weights for policy 0, policy_version 78680 (0.0010) -[2023-10-12 06:33:40,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 160759808. Throughput: 0: 1594.5, 1: 1583.0. Samples: 40197186. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:33:40,201][77203] Avg episode reward: [(0, '51.250'), (1, '47.480')] -[2023-10-12 06:33:42,314][78123] Updated weights for policy 1, policy_version 78310 (0.0008) -[2023-10-12 06:33:42,688][78123] Updated weights for policy 1, policy_version 78320 (0.0009) -[2023-10-12 06:33:43,048][78123] Updated weights for policy 1, policy_version 78330 (0.0008) -[2023-10-12 06:33:43,755][78091] Updated weights for policy 0, policy_version 78690 (0.0009) -[2023-10-12 06:33:44,144][78091] Updated weights for policy 0, policy_version 78700 (0.0010) -[2023-10-12 06:33:44,524][78091] Updated weights for policy 0, policy_version 78710 (0.0011) -[2023-10-12 06:33:44,884][78091] Updated weights for policy 0, policy_version 78720 (0.0011) -[2023-10-12 06:33:45,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 160825344. Throughput: 0: 1597.6, 1: 1599.0. Samples: 40207458. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:33:45,202][77203] Avg episode reward: [(0, '55.080'), (1, '50.360')] -[2023-10-12 06:33:47,518][78123] Updated weights for policy 1, policy_version 78340 (0.0008) -[2023-10-12 06:33:47,881][78123] Updated weights for policy 1, policy_version 78350 (0.0007) -[2023-10-12 06:33:48,251][78123] Updated weights for policy 1, policy_version 78360 (0.0009) -[2023-10-12 06:33:49,187][78091] Updated weights for policy 0, policy_version 78730 (0.0009) -[2023-10-12 06:33:49,554][78091] Updated weights for policy 0, policy_version 78740 (0.0008) -[2023-10-12 06:33:49,923][78091] Updated weights for policy 0, policy_version 78750 (0.0007) -[2023-10-12 06:33:50,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 160890880. Throughput: 0: 1615.5, 1: 1587.4. Samples: 40226264. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:33:50,201][77203] Avg episode reward: [(0, '55.030'), (1, '48.450')] -[2023-10-12 06:33:52,619][78123] Updated weights for policy 1, policy_version 78370 (0.0010) -[2023-10-12 06:33:52,984][78123] Updated weights for policy 1, policy_version 78380 (0.0007) -[2023-10-12 06:33:53,349][78123] Updated weights for policy 1, policy_version 78390 (0.0009) -[2023-10-12 06:33:53,710][78123] Updated weights for policy 1, policy_version 78400 (0.0010) -[2023-10-12 06:33:54,375][78091] Updated weights for policy 0, policy_version 78760 (0.0008) -[2023-10-12 06:33:54,754][78091] Updated weights for policy 0, policy_version 78770 (0.0007) -[2023-10-12 06:33:55,112][78091] Updated weights for policy 0, policy_version 78780 (0.0008) -[2023-10-12 06:33:55,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 160923648. Throughput: 0: 1603.4, 1: 1588.2. Samples: 40245108. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:33:55,202][77203] Avg episode reward: [(0, '58.520'), (1, '55.510')] -[2023-10-12 06:33:58,082][78123] Updated weights for policy 1, policy_version 78410 (0.0010) -[2023-10-12 06:33:58,457][78123] Updated weights for policy 1, policy_version 78420 (0.0008) -[2023-10-12 06:33:58,823][78123] Updated weights for policy 1, policy_version 78430 (0.0008) -[2023-10-12 06:33:59,321][78091] Updated weights for policy 0, policy_version 78790 (0.0007) -[2023-10-12 06:33:59,702][78091] Updated weights for policy 0, policy_version 78800 (0.0008) -[2023-10-12 06:34:00,075][78091] Updated weights for policy 0, policy_version 78810 (0.0009) -[2023-10-12 06:34:00,201][77203] Fps is (10 sec: 9830.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 160989184. Throughput: 0: 1588.8, 1: 1618.5. Samples: 40255530. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:34:00,202][77203] Avg episode reward: [(0, '58.090'), (1, '53.900')] -[2023-10-12 06:34:03,105][78123] Updated weights for policy 1, policy_version 78440 (0.0008) -[2023-10-12 06:34:03,474][78123] Updated weights for policy 1, policy_version 78450 (0.0010) -[2023-10-12 06:34:03,850][78123] Updated weights for policy 1, policy_version 78460 (0.0011) -[2023-10-12 06:34:04,242][78091] Updated weights for policy 0, policy_version 78820 (0.0009) -[2023-10-12 06:34:04,626][78091] Updated weights for policy 0, policy_version 78830 (0.0009) -[2023-10-12 06:34:04,998][78091] Updated weights for policy 0, policy_version 78840 (0.0007) -[2023-10-12 06:34:05,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 161054720. Throughput: 0: 1607.0, 1: 1598.6. Samples: 40274442. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:34:05,201][77203] Avg episode reward: [(0, '60.110'), (1, '49.510')] -[2023-10-12 06:34:08,235][78123] Updated weights for policy 1, policy_version 78470 (0.0010) -[2023-10-12 06:34:08,602][78123] Updated weights for policy 1, policy_version 78480 (0.0008) -[2023-10-12 06:34:08,975][78123] Updated weights for policy 1, policy_version 78490 (0.0007) -[2023-10-12 06:34:09,208][78091] Updated weights for policy 0, policy_version 78850 (0.0007) -[2023-10-12 06:34:09,571][78091] Updated weights for policy 0, policy_version 78860 (0.0009) -[2023-10-12 06:34:09,945][78091] Updated weights for policy 0, policy_version 78870 (0.0009) -[2023-10-12 06:34:10,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 161120256. Throughput: 0: 1608.8, 1: 1591.5. Samples: 40293032. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:34:10,202][77203] Avg episode reward: [(0, '56.320'), (1, '56.850')] -[2023-10-12 06:34:10,315][78091] Updated weights for policy 0, policy_version 78880 (0.0008) -[2023-10-12 06:34:13,181][78123] Updated weights for policy 1, policy_version 78500 (0.0008) -[2023-10-12 06:34:13,552][78123] Updated weights for policy 1, policy_version 78510 (0.0007) -[2023-10-12 06:34:13,923][78123] Updated weights for policy 1, policy_version 78520 (0.0008) -[2023-10-12 06:34:14,690][78091] Updated weights for policy 0, policy_version 78890 (0.0009) -[2023-10-12 06:34:15,059][78091] Updated weights for policy 0, policy_version 78900 (0.0008) -[2023-10-12 06:34:15,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 161185792. Throughput: 0: 1591.3, 1: 1611.1. Samples: 40303364. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:34:15,202][77203] Avg episode reward: [(0, '57.480'), (1, '51.820')] -[2023-10-12 06:34:15,433][78091] Updated weights for policy 0, policy_version 78910 (0.0008) -[2023-10-12 06:34:18,372][78123] Updated weights for policy 1, policy_version 78530 (0.0008) -[2023-10-12 06:34:18,741][78123] Updated weights for policy 1, policy_version 78540 (0.0008) -[2023-10-12 06:34:19,121][78123] Updated weights for policy 1, policy_version 78550 (0.0010) -[2023-10-12 06:34:19,486][78123] Updated weights for policy 1, policy_version 78560 (0.0009) -[2023-10-12 06:34:19,864][78091] Updated weights for policy 0, policy_version 78920 (0.0008) -[2023-10-12 06:34:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 161251328. Throughput: 0: 1593.8, 1: 1597.2. Samples: 40322192. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:34:20,202][77203] Avg episode reward: [(0, '54.010'), (1, '51.220')] -[2023-10-12 06:34:20,232][78091] Updated weights for policy 0, policy_version 78930 (0.0008) -[2023-10-12 06:34:20,614][78091] Updated weights for policy 0, policy_version 78940 (0.0008) -[2023-10-12 06:34:23,738][78123] Updated weights for policy 1, policy_version 78570 (0.0009) -[2023-10-12 06:34:24,097][78123] Updated weights for policy 1, policy_version 78580 (0.0009) -[2023-10-12 06:34:24,466][78123] Updated weights for policy 1, policy_version 78590 (0.0010) -[2023-10-12 06:34:25,098][78091] Updated weights for policy 0, policy_version 78950 (0.0009) -[2023-10-12 06:34:25,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 161316864. Throughput: 0: 1609.9, 1: 1585.2. Samples: 40340964. Policy #0 lag: (min: 1.0, avg: 4.4, max: 33.0) -[2023-10-12 06:34:25,201][77203] Avg episode reward: [(0, '61.520'), (1, '51.410')] -[2023-10-12 06:34:25,468][78091] Updated weights for policy 0, policy_version 78960 (0.0010) -[2023-10-12 06:34:25,836][78091] Updated weights for policy 0, policy_version 78970 (0.0008) -[2023-10-12 06:34:28,633][78123] Updated weights for policy 1, policy_version 78600 (0.0009) -[2023-10-12 06:34:28,990][78123] Updated weights for policy 1, policy_version 78610 (0.0009) -[2023-10-12 06:34:29,366][78123] Updated weights for policy 1, policy_version 78620 (0.0010) -[2023-10-12 06:34:30,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 161382400. Throughput: 0: 1582.9, 1: 1601.2. Samples: 40350742. Policy #0 lag: (min: 1.0, avg: 4.4, max: 33.0) -[2023-10-12 06:34:30,202][77203] Avg episode reward: [(0, '56.530'), (1, '52.730')] -[2023-10-12 06:34:30,217][78091] Updated weights for policy 0, policy_version 78980 (0.0008) -[2023-10-12 06:34:30,607][78091] Updated weights for policy 0, policy_version 78990 (0.0009) -[2023-10-12 06:34:30,984][78091] Updated weights for policy 0, policy_version 79000 (0.0010) -[2023-10-12 06:34:33,816][78123] Updated weights for policy 1, policy_version 78630 (0.0009) -[2023-10-12 06:34:34,187][78123] Updated weights for policy 1, policy_version 78640 (0.0009) -[2023-10-12 06:34:34,550][78123] Updated weights for policy 1, policy_version 78650 (0.0010) -[2023-10-12 06:34:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 161447936. Throughput: 0: 1584.2, 1: 1606.9. Samples: 40369866. Policy #0 lag: (min: 1.0, avg: 4.4, max: 33.0) -[2023-10-12 06:34:35,201][77203] Avg episode reward: [(0, '59.680'), (1, '47.800')] -[2023-10-12 06:34:35,324][78091] Updated weights for policy 0, policy_version 79010 (0.0008) -[2023-10-12 06:34:35,698][78091] Updated weights for policy 0, policy_version 79020 (0.0010) -[2023-10-12 06:34:36,069][78091] Updated weights for policy 0, policy_version 79030 (0.0010) -[2023-10-12 06:34:36,446][78091] Updated weights for policy 0, policy_version 79040 (0.0008) -[2023-10-12 06:34:38,734][78123] Updated weights for policy 1, policy_version 78660 (0.0009) -[2023-10-12 06:34:39,100][78123] Updated weights for policy 1, policy_version 78670 (0.0011) -[2023-10-12 06:34:39,469][78123] Updated weights for policy 1, policy_version 78680 (0.0010) -[2023-10-12 06:34:40,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 161513472. Throughput: 0: 1604.7, 1: 1585.9. Samples: 40388690. Policy #0 lag: (min: 1.0, avg: 4.4, max: 33.0) -[2023-10-12 06:34:40,202][77203] Avg episode reward: [(0, '56.510'), (1, '47.590')] -[2023-10-12 06:34:40,739][78091] Updated weights for policy 0, policy_version 79050 (0.0010) -[2023-10-12 06:34:41,096][78091] Updated weights for policy 0, policy_version 79060 (0.0010) -[2023-10-12 06:34:41,469][78091] Updated weights for policy 0, policy_version 79070 (0.0008) -[2023-10-12 06:34:43,868][78123] Updated weights for policy 1, policy_version 78690 (0.0010) -[2023-10-12 06:34:44,232][78123] Updated weights for policy 1, policy_version 78700 (0.0008) -[2023-10-12 06:34:44,609][78123] Updated weights for policy 1, policy_version 78710 (0.0009) -[2023-10-12 06:34:44,970][78123] Updated weights for policy 1, policy_version 78720 (0.0009) -[2023-10-12 06:34:45,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 161579008. Throughput: 0: 1591.3, 1: 1583.0. Samples: 40398376. Policy #0 lag: (min: 1.0, avg: 4.4, max: 33.0) -[2023-10-12 06:34:45,202][77203] Avg episode reward: [(0, '54.050'), (1, '51.920')] -[2023-10-12 06:34:45,632][78091] Updated weights for policy 0, policy_version 79080 (0.0007) -[2023-10-12 06:34:46,001][78091] Updated weights for policy 0, policy_version 79090 (0.0007) -[2023-10-12 06:34:46,379][78091] Updated weights for policy 0, policy_version 79100 (0.0007) -[2023-10-12 06:34:49,291][78123] Updated weights for policy 1, policy_version 78730 (0.0008) -[2023-10-12 06:34:49,672][78123] Updated weights for policy 1, policy_version 78740 (0.0009) -[2023-10-12 06:34:50,039][78123] Updated weights for policy 1, policy_version 78750 (0.0009) -[2023-10-12 06:34:50,201][77203] Fps is (10 sec: 13107.7, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 161644544. Throughput: 0: 1587.3, 1: 1603.2. Samples: 40418014. Policy #0 lag: (min: 1.0, avg: 4.4, max: 33.0) -[2023-10-12 06:34:50,201][77203] Avg episode reward: [(0, '54.000'), (1, '49.540')] -[2023-10-12 06:34:50,670][78091] Updated weights for policy 0, policy_version 79110 (0.0009) -[2023-10-12 06:34:51,033][78091] Updated weights for policy 0, policy_version 79120 (0.0007) -[2023-10-12 06:34:51,404][78091] Updated weights for policy 0, policy_version 79130 (0.0008) -[2023-10-12 06:34:54,411][78123] Updated weights for policy 1, policy_version 78760 (0.0010) -[2023-10-12 06:34:54,778][78123] Updated weights for policy 1, policy_version 78770 (0.0008) -[2023-10-12 06:34:55,133][78123] Updated weights for policy 1, policy_version 78780 (0.0009) -[2023-10-12 06:34:55,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 161677312. Throughput: 0: 1601.5, 1: 1596.2. Samples: 40436928. Policy #0 lag: (min: 1.0, avg: 4.4, max: 33.0) -[2023-10-12 06:34:55,202][77203] Avg episode reward: [(0, '62.860'), (1, '55.050')] -[2023-10-12 06:34:55,663][78091] Updated weights for policy 0, policy_version 79140 (0.0008) -[2023-10-12 06:34:56,029][78091] Updated weights for policy 0, policy_version 79150 (0.0008) -[2023-10-12 06:34:56,401][78091] Updated weights for policy 0, policy_version 79160 (0.0007) -[2023-10-12 06:34:59,342][78123] Updated weights for policy 1, policy_version 78790 (0.0009) -[2023-10-12 06:34:59,712][78123] Updated weights for policy 1, policy_version 78800 (0.0010) -[2023-10-12 06:35:00,081][78123] Updated weights for policy 1, policy_version 78810 (0.0008) -[2023-10-12 06:35:00,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 161742848. Throughput: 0: 1591.0, 1: 1582.8. Samples: 40446184. Policy #0 lag: (min: 1.0, avg: 4.4, max: 33.0) -[2023-10-12 06:35:00,201][77203] Avg episode reward: [(0, '53.800'), (1, '54.700')] -[2023-10-12 06:35:00,751][78091] Updated weights for policy 0, policy_version 79170 (0.0009) -[2023-10-12 06:35:01,119][78091] Updated weights for policy 0, policy_version 79180 (0.0008) -[2023-10-12 06:35:01,486][78091] Updated weights for policy 0, policy_version 79190 (0.0009) -[2023-10-12 06:35:01,862][78091] Updated weights for policy 0, policy_version 79200 (0.0009) -[2023-10-12 06:35:04,426][78123] Updated weights for policy 1, policy_version 78820 (0.0008) -[2023-10-12 06:35:04,786][78123] Updated weights for policy 1, policy_version 78830 (0.0010) -[2023-10-12 06:35:05,158][78123] Updated weights for policy 1, policy_version 78840 (0.0009) -[2023-10-12 06:35:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 161808384. Throughput: 0: 1590.6, 1: 1597.4. Samples: 40465652. Policy #0 lag: (min: 1.0, avg: 4.4, max: 33.0) -[2023-10-12 06:35:05,201][77203] Avg episode reward: [(0, '55.540'), (1, '56.270')] -[2023-10-12 06:35:06,118][78091] Updated weights for policy 0, policy_version 79210 (0.0009) -[2023-10-12 06:35:06,489][78091] Updated weights for policy 0, policy_version 79220 (0.0010) -[2023-10-12 06:35:06,869][78091] Updated weights for policy 0, policy_version 79230 (0.0011) -[2023-10-12 06:35:09,459][78123] Updated weights for policy 1, policy_version 78850 (0.0010) -[2023-10-12 06:35:09,856][78123] Updated weights for policy 1, policy_version 78860 (0.0007) -[2023-10-12 06:35:10,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 161873920. Throughput: 0: 1595.7, 1: 1603.9. Samples: 40484946. Policy #0 lag: (min: 1.0, avg: 4.4, max: 33.0) -[2023-10-12 06:35:10,202][77203] Avg episode reward: [(0, '55.560'), (1, '51.220')] -[2023-10-12 06:35:10,210][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000079232_81133568.pth... -[2023-10-12 06:35:10,223][78123] Updated weights for policy 1, policy_version 78870 (0.0007) -[2023-10-12 06:35:10,250][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000077760_79626240.pth -[2023-10-12 06:35:10,585][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000078880_80773120.pth... -[2023-10-12 06:35:10,586][78123] Updated weights for policy 1, policy_version 78880 (0.0009) -[2023-10-12 06:35:10,626][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000077376_79233024.pth -[2023-10-12 06:35:11,182][78091] Updated weights for policy 0, policy_version 79240 (0.0009) -[2023-10-12 06:35:11,555][78091] Updated weights for policy 0, policy_version 79250 (0.0008) -[2023-10-12 06:35:11,935][78091] Updated weights for policy 0, policy_version 79260 (0.0007) -[2023-10-12 06:35:14,881][78123] Updated weights for policy 1, policy_version 78890 (0.0007) -[2023-10-12 06:35:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 161939456. Throughput: 0: 1595.2, 1: 1583.5. Samples: 40493782. Policy #0 lag: (min: 15.0, avg: 18.2, max: 47.0) -[2023-10-12 06:35:15,201][77203] Avg episode reward: [(0, '59.350'), (1, '51.550')] -[2023-10-12 06:35:15,244][78123] Updated weights for policy 1, policy_version 78900 (0.0007) -[2023-10-12 06:35:15,608][78123] Updated weights for policy 1, policy_version 78910 (0.0007) -[2023-10-12 06:35:16,334][78091] Updated weights for policy 0, policy_version 79270 (0.0009) -[2023-10-12 06:35:16,713][78091] Updated weights for policy 0, policy_version 79280 (0.0007) -[2023-10-12 06:35:17,095][78091] Updated weights for policy 0, policy_version 79290 (0.0008) -[2023-10-12 06:35:19,903][78123] Updated weights for policy 1, policy_version 78920 (0.0008) -[2023-10-12 06:35:20,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 162004992. Throughput: 0: 1594.7, 1: 1595.0. Samples: 40513402. Policy #0 lag: (min: 15.0, avg: 18.2, max: 47.0) -[2023-10-12 06:35:20,202][77203] Avg episode reward: [(0, '54.750'), (1, '50.240')] -[2023-10-12 06:35:20,269][78123] Updated weights for policy 1, policy_version 78930 (0.0008) -[2023-10-12 06:35:20,637][78123] Updated weights for policy 1, policy_version 78940 (0.0008) -[2023-10-12 06:35:21,402][78091] Updated weights for policy 0, policy_version 79300 (0.0007) -[2023-10-12 06:35:21,764][78091] Updated weights for policy 0, policy_version 79310 (0.0008) -[2023-10-12 06:35:22,140][78091] Updated weights for policy 0, policy_version 79320 (0.0007) -[2023-10-12 06:35:25,076][78123] Updated weights for policy 1, policy_version 78950 (0.0007) -[2023-10-12 06:35:25,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 162070528. Throughput: 0: 1588.9, 1: 1612.5. Samples: 40532754. Policy #0 lag: (min: 15.0, avg: 18.2, max: 47.0) -[2023-10-12 06:35:25,202][77203] Avg episode reward: [(0, '51.590'), (1, '48.730')] -[2023-10-12 06:35:25,445][78123] Updated weights for policy 1, policy_version 78960 (0.0009) -[2023-10-12 06:35:25,818][78123] Updated weights for policy 1, policy_version 78970 (0.0009) -[2023-10-12 06:35:26,451][78091] Updated weights for policy 0, policy_version 79330 (0.0008) -[2023-10-12 06:35:26,809][78091] Updated weights for policy 0, policy_version 79340 (0.0010) -[2023-10-12 06:35:27,181][78091] Updated weights for policy 0, policy_version 79350 (0.0007) -[2023-10-12 06:35:27,551][78091] Updated weights for policy 0, policy_version 79360 (0.0009) -[2023-10-12 06:35:30,095][78123] Updated weights for policy 1, policy_version 78980 (0.0008) -[2023-10-12 06:35:30,201][77203] Fps is (10 sec: 13107.7, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 162136064. Throughput: 0: 1590.0, 1: 1589.4. Samples: 40541446. Policy #0 lag: (min: 15.0, avg: 18.2, max: 47.0) -[2023-10-12 06:35:30,201][77203] Avg episode reward: [(0, '57.960'), (1, '50.690')] -[2023-10-12 06:35:30,461][78123] Updated weights for policy 1, policy_version 78990 (0.0007) -[2023-10-12 06:35:30,829][78123] Updated weights for policy 1, policy_version 79000 (0.0008) -[2023-10-12 06:35:31,871][78091] Updated weights for policy 0, policy_version 79370 (0.0009) -[2023-10-12 06:35:32,238][78091] Updated weights for policy 0, policy_version 79380 (0.0009) -[2023-10-12 06:35:32,615][78091] Updated weights for policy 0, policy_version 79390 (0.0007) -[2023-10-12 06:35:35,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 162201600. Throughput: 0: 1588.6, 1: 1584.5. Samples: 40560806. Policy #0 lag: (min: 15.0, avg: 18.2, max: 47.0) -[2023-10-12 06:35:35,202][77203] Avg episode reward: [(0, '58.030'), (1, '46.720')] -[2023-10-12 06:35:35,210][78123] Updated weights for policy 1, policy_version 79010 (0.0009) -[2023-10-12 06:35:35,579][78123] Updated weights for policy 1, policy_version 79020 (0.0007) -[2023-10-12 06:35:35,951][78123] Updated weights for policy 1, policy_version 79030 (0.0008) -[2023-10-12 06:35:36,314][78123] Updated weights for policy 1, policy_version 79040 (0.0010) -[2023-10-12 06:35:36,762][78091] Updated weights for policy 0, policy_version 79400 (0.0010) -[2023-10-12 06:35:37,132][78091] Updated weights for policy 0, policy_version 79410 (0.0008) -[2023-10-12 06:35:37,509][78091] Updated weights for policy 0, policy_version 79420 (0.0010) -[2023-10-12 06:35:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 162267136. Throughput: 0: 1592.8, 1: 1595.9. Samples: 40580418. Policy #0 lag: (min: 15.0, avg: 18.2, max: 47.0) -[2023-10-12 06:35:40,202][77203] Avg episode reward: [(0, '58.470'), (1, '49.180')] -[2023-10-12 06:35:40,761][78123] Updated weights for policy 1, policy_version 79050 (0.0008) -[2023-10-12 06:35:41,121][78123] Updated weights for policy 1, policy_version 79060 (0.0007) -[2023-10-12 06:35:41,489][78123] Updated weights for policy 1, policy_version 79070 (0.0008) -[2023-10-12 06:35:41,837][78091] Updated weights for policy 0, policy_version 79430 (0.0010) -[2023-10-12 06:35:42,193][78091] Updated weights for policy 0, policy_version 79440 (0.0011) -[2023-10-12 06:35:42,570][78091] Updated weights for policy 0, policy_version 79450 (0.0011) -[2023-10-12 06:35:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 162332672. Throughput: 0: 1594.8, 1: 1583.2. Samples: 40589190. Policy #0 lag: (min: 15.0, avg: 18.2, max: 47.0) -[2023-10-12 06:35:45,202][77203] Avg episode reward: [(0, '46.800'), (1, '52.240')] -[2023-10-12 06:35:45,933][78123] Updated weights for policy 1, policy_version 79080 (0.0007) -[2023-10-12 06:35:46,304][78123] Updated weights for policy 1, policy_version 79090 (0.0010) -[2023-10-12 06:35:46,662][78123] Updated weights for policy 1, policy_version 79100 (0.0010) -[2023-10-12 06:35:46,879][78091] Updated weights for policy 0, policy_version 79460 (0.0010) -[2023-10-12 06:35:47,252][78091] Updated weights for policy 0, policy_version 79470 (0.0008) -[2023-10-12 06:35:47,621][78091] Updated weights for policy 0, policy_version 79480 (0.0009) -[2023-10-12 06:35:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 162398208. Throughput: 0: 1596.6, 1: 1577.5. Samples: 40608484. Policy #0 lag: (min: 15.0, avg: 18.2, max: 47.0) -[2023-10-12 06:35:50,202][77203] Avg episode reward: [(0, '57.260'), (1, '56.200')] -[2023-10-12 06:35:51,063][78123] Updated weights for policy 1, policy_version 79110 (0.0007) -[2023-10-12 06:35:51,423][78123] Updated weights for policy 1, policy_version 79120 (0.0008) -[2023-10-12 06:35:51,790][78123] Updated weights for policy 1, policy_version 79130 (0.0009) -[2023-10-12 06:35:52,038][78091] Updated weights for policy 0, policy_version 79490 (0.0008) -[2023-10-12 06:35:52,404][78091] Updated weights for policy 0, policy_version 79500 (0.0011) -[2023-10-12 06:35:52,774][78091] Updated weights for policy 0, policy_version 79510 (0.0009) -[2023-10-12 06:35:53,146][78091] Updated weights for policy 0, policy_version 79520 (0.0009) -[2023-10-12 06:35:55,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 162463744. Throughput: 0: 1589.3, 1: 1587.4. Samples: 40627898. Policy #0 lag: (min: 15.0, avg: 18.2, max: 47.0) -[2023-10-12 06:35:55,202][77203] Avg episode reward: [(0, '57.840'), (1, '57.150')] -[2023-10-12 06:35:56,221][78123] Updated weights for policy 1, policy_version 79140 (0.0009) -[2023-10-12 06:35:56,598][78123] Updated weights for policy 1, policy_version 79150 (0.0010) -[2023-10-12 06:35:56,974][78123] Updated weights for policy 1, policy_version 79160 (0.0011) -[2023-10-12 06:35:57,543][78091] Updated weights for policy 0, policy_version 79530 (0.0008) -[2023-10-12 06:35:57,913][78091] Updated weights for policy 0, policy_version 79540 (0.0010) -[2023-10-12 06:35:58,282][78091] Updated weights for policy 0, policy_version 79550 (0.0010) -[2023-10-12 06:36:00,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 162529280. Throughput: 0: 1602.5, 1: 1572.3. Samples: 40636648. Policy #0 lag: (min: 15.0, avg: 18.2, max: 47.0) -[2023-10-12 06:36:00,201][77203] Avg episode reward: [(0, '57.270'), (1, '49.520')] -[2023-10-12 06:36:01,390][78123] Updated weights for policy 1, policy_version 79170 (0.0009) -[2023-10-12 06:36:01,753][78123] Updated weights for policy 1, policy_version 79180 (0.0008) -[2023-10-12 06:36:02,127][78123] Updated weights for policy 1, policy_version 79190 (0.0007) -[2023-10-12 06:36:02,496][78123] Updated weights for policy 1, policy_version 79200 (0.0007) -[2023-10-12 06:36:02,664][78091] Updated weights for policy 0, policy_version 79560 (0.0008) -[2023-10-12 06:36:03,030][78091] Updated weights for policy 0, policy_version 79570 (0.0007) -[2023-10-12 06:36:03,400][78091] Updated weights for policy 0, policy_version 79580 (0.0007) -[2023-10-12 06:36:05,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 162594816. Throughput: 0: 1593.6, 1: 1570.0. Samples: 40655760. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 06:36:05,201][77203] Avg episode reward: [(0, '57.050'), (1, '51.790')] -[2023-10-12 06:36:06,880][78123] Updated weights for policy 1, policy_version 79210 (0.0008) -[2023-10-12 06:36:07,249][78123] Updated weights for policy 1, policy_version 79220 (0.0009) -[2023-10-12 06:36:07,517][78091] Updated weights for policy 0, policy_version 79590 (0.0007) -[2023-10-12 06:36:07,616][78123] Updated weights for policy 1, policy_version 79230 (0.0010) -[2023-10-12 06:36:07,883][78091] Updated weights for policy 0, policy_version 79600 (0.0008) -[2023-10-12 06:36:08,251][78091] Updated weights for policy 0, policy_version 79610 (0.0009) -[2023-10-12 06:36:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 162660352. Throughput: 0: 1599.5, 1: 1568.4. Samples: 40675310. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 06:36:10,201][77203] Avg episode reward: [(0, '58.220'), (1, '53.840')] -[2023-10-12 06:36:12,130][78123] Updated weights for policy 1, policy_version 79240 (0.0008) -[2023-10-12 06:36:12,497][78123] Updated weights for policy 1, policy_version 79250 (0.0010) -[2023-10-12 06:36:12,645][78091] Updated weights for policy 0, policy_version 79620 (0.0008) -[2023-10-12 06:36:12,874][78123] Updated weights for policy 1, policy_version 79260 (0.0010) -[2023-10-12 06:36:13,021][78091] Updated weights for policy 0, policy_version 79630 (0.0007) -[2023-10-12 06:36:13,401][78091] Updated weights for policy 0, policy_version 79640 (0.0009) -[2023-10-12 06:36:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 162725888. Throughput: 0: 1617.6, 1: 1572.6. Samples: 40685002. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 06:36:15,202][77203] Avg episode reward: [(0, '60.210'), (1, '53.480')] -[2023-10-12 06:36:17,238][78123] Updated weights for policy 1, policy_version 79270 (0.0010) -[2023-10-12 06:36:17,607][78123] Updated weights for policy 1, policy_version 79280 (0.0008) -[2023-10-12 06:36:17,664][78091] Updated weights for policy 0, policy_version 79650 (0.0010) -[2023-10-12 06:36:17,974][78123] Updated weights for policy 1, policy_version 79290 (0.0009) -[2023-10-12 06:36:18,038][78091] Updated weights for policy 0, policy_version 79660 (0.0008) -[2023-10-12 06:36:18,398][78091] Updated weights for policy 0, policy_version 79670 (0.0009) -[2023-10-12 06:36:18,773][78091] Updated weights for policy 0, policy_version 79680 (0.0009) -[2023-10-12 06:36:20,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 162791424. Throughput: 0: 1601.6, 1: 1567.7. Samples: 40703424. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 06:36:20,202][77203] Avg episode reward: [(0, '55.420'), (1, '55.330')] -[2023-10-12 06:36:22,277][78123] Updated weights for policy 1, policy_version 79300 (0.0008) -[2023-10-12 06:36:22,646][78123] Updated weights for policy 1, policy_version 79310 (0.0009) -[2023-10-12 06:36:23,009][78123] Updated weights for policy 1, policy_version 79320 (0.0008) -[2023-10-12 06:36:23,192][78091] Updated weights for policy 0, policy_version 79690 (0.0009) -[2023-10-12 06:36:23,566][78091] Updated weights for policy 0, policy_version 79700 (0.0007) -[2023-10-12 06:36:23,930][78091] Updated weights for policy 0, policy_version 79710 (0.0008) -[2023-10-12 06:36:25,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 162856960. Throughput: 0: 1592.6, 1: 1571.2. Samples: 40722792. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 06:36:25,201][77203] Avg episode reward: [(0, '55.560'), (1, '60.390')] -[2023-10-12 06:36:27,331][78123] Updated weights for policy 1, policy_version 79330 (0.0009) -[2023-10-12 06:36:27,707][78123] Updated weights for policy 1, policy_version 79340 (0.0008) -[2023-10-12 06:36:28,068][78123] Updated weights for policy 1, policy_version 79350 (0.0007) -[2023-10-12 06:36:28,124][78091] Updated weights for policy 0, policy_version 79720 (0.0007) -[2023-10-12 06:36:28,445][78123] Updated weights for policy 1, policy_version 79360 (0.0007) -[2023-10-12 06:36:28,491][78091] Updated weights for policy 0, policy_version 79730 (0.0007) -[2023-10-12 06:36:28,865][78091] Updated weights for policy 0, policy_version 79740 (0.0009) -[2023-10-12 06:36:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 162922496. Throughput: 0: 1619.6, 1: 1586.8. Samples: 40733478. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 06:36:30,202][77203] Avg episode reward: [(0, '48.970'), (1, '53.580')] -[2023-10-12 06:36:32,650][78123] Updated weights for policy 1, policy_version 79370 (0.0009) -[2023-10-12 06:36:33,014][78123] Updated weights for policy 1, policy_version 79380 (0.0009) -[2023-10-12 06:36:33,211][78091] Updated weights for policy 0, policy_version 79750 (0.0009) -[2023-10-12 06:36:33,386][78123] Updated weights for policy 1, policy_version 79390 (0.0009) -[2023-10-12 06:36:33,582][78091] Updated weights for policy 0, policy_version 79760 (0.0009) -[2023-10-12 06:36:33,950][78091] Updated weights for policy 0, policy_version 79770 (0.0010) -[2023-10-12 06:36:35,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 162988032. Throughput: 0: 1605.2, 1: 1573.3. Samples: 40751516. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 06:36:35,202][77203] Avg episode reward: [(0, '49.290'), (1, '52.170')] -[2023-10-12 06:36:37,722][78123] Updated weights for policy 1, policy_version 79400 (0.0008) -[2023-10-12 06:36:38,095][78123] Updated weights for policy 1, policy_version 79410 (0.0008) -[2023-10-12 06:36:38,153][78091] Updated weights for policy 0, policy_version 79780 (0.0009) -[2023-10-12 06:36:38,457][78123] Updated weights for policy 1, policy_version 79420 (0.0007) -[2023-10-12 06:36:38,533][78091] Updated weights for policy 0, policy_version 79790 (0.0008) -[2023-10-12 06:36:38,908][78091] Updated weights for policy 0, policy_version 79800 (0.0009) -[2023-10-12 06:36:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 163053568. Throughput: 0: 1603.1, 1: 1572.7. Samples: 40770806. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 06:36:40,202][77203] Avg episode reward: [(0, '50.670'), (1, '51.310')] -[2023-10-12 06:36:42,659][78123] Updated weights for policy 1, policy_version 79430 (0.0010) -[2023-10-12 06:36:43,035][78123] Updated weights for policy 1, policy_version 79440 (0.0009) -[2023-10-12 06:36:43,243][78091] Updated weights for policy 0, policy_version 79810 (0.0009) -[2023-10-12 06:36:43,405][78123] Updated weights for policy 1, policy_version 79450 (0.0010) -[2023-10-12 06:36:43,620][78091] Updated weights for policy 0, policy_version 79820 (0.0007) -[2023-10-12 06:36:43,997][78091] Updated weights for policy 0, policy_version 79830 (0.0009) -[2023-10-12 06:36:44,363][78091] Updated weights for policy 0, policy_version 79840 (0.0009) -[2023-10-12 06:36:45,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 163119104. Throughput: 0: 1621.1, 1: 1598.8. Samples: 40781542. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 06:36:45,202][77203] Avg episode reward: [(0, '56.810'), (1, '49.380')] -[2023-10-12 06:36:47,764][78123] Updated weights for policy 1, policy_version 79460 (0.0007) -[2023-10-12 06:36:48,126][78123] Updated weights for policy 1, policy_version 79470 (0.0009) -[2023-10-12 06:36:48,493][78123] Updated weights for policy 1, policy_version 79480 (0.0008) -[2023-10-12 06:36:48,721][78091] Updated weights for policy 0, policy_version 79850 (0.0008) -[2023-10-12 06:36:49,084][78091] Updated weights for policy 0, policy_version 79860 (0.0007) -[2023-10-12 06:36:49,459][78091] Updated weights for policy 0, policy_version 79870 (0.0009) -[2023-10-12 06:36:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 163184640. Throughput: 0: 1617.1, 1: 1580.2. Samples: 40799638. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 06:36:50,202][77203] Avg episode reward: [(0, '52.250'), (1, '57.650')] -[2023-10-12 06:36:52,884][78123] Updated weights for policy 1, policy_version 79490 (0.0009) -[2023-10-12 06:36:53,252][78123] Updated weights for policy 1, policy_version 79500 (0.0009) -[2023-10-12 06:36:53,602][78123] Updated weights for policy 1, policy_version 79510 (0.0009) -[2023-10-12 06:36:53,742][78091] Updated weights for policy 0, policy_version 79880 (0.0008) -[2023-10-12 06:36:53,966][78123] Updated weights for policy 1, policy_version 79520 (0.0008) -[2023-10-12 06:36:54,114][78091] Updated weights for policy 0, policy_version 79890 (0.0009) -[2023-10-12 06:36:54,484][78091] Updated weights for policy 0, policy_version 79900 (0.0011) -[2023-10-12 06:36:55,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 163250176. Throughput: 0: 1597.2, 1: 1577.6. Samples: 40818174. Policy #0 lag: (min: 18.0, avg: 20.1, max: 41.0) -[2023-10-12 06:36:55,202][77203] Avg episode reward: [(0, '52.870'), (1, '48.060')] -[2023-10-12 06:36:58,587][78123] Updated weights for policy 1, policy_version 79530 (0.0007) -[2023-10-12 06:36:58,731][78091] Updated weights for policy 0, policy_version 79910 (0.0008) -[2023-10-12 06:36:58,952][78123] Updated weights for policy 1, policy_version 79540 (0.0009) -[2023-10-12 06:36:59,099][78091] Updated weights for policy 0, policy_version 79920 (0.0007) -[2023-10-12 06:36:59,325][78123] Updated weights for policy 1, policy_version 79550 (0.0007) -[2023-10-12 06:36:59,475][78091] Updated weights for policy 0, policy_version 79930 (0.0007) -[2023-10-12 06:37:00,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 163315712. Throughput: 0: 1604.0, 1: 1595.4. Samples: 40828972. Policy #0 lag: (min: 18.0, avg: 20.1, max: 41.0) -[2023-10-12 06:37:00,201][77203] Avg episode reward: [(0, '56.470'), (1, '44.250')] -[2023-10-12 06:37:03,524][78123] Updated weights for policy 1, policy_version 79560 (0.0008) -[2023-10-12 06:37:03,536][78091] Updated weights for policy 0, policy_version 79940 (0.0008) -[2023-10-12 06:37:03,888][78123] Updated weights for policy 1, policy_version 79570 (0.0007) -[2023-10-12 06:37:03,907][78091] Updated weights for policy 0, policy_version 79950 (0.0009) -[2023-10-12 06:37:04,256][78123] Updated weights for policy 1, policy_version 79580 (0.0008) -[2023-10-12 06:37:04,275][78091] Updated weights for policy 0, policy_version 79960 (0.0008) -[2023-10-12 06:37:05,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.1, 300 sec: 12885.0). Total num frames: 163381248. Throughput: 0: 1613.2, 1: 1596.8. Samples: 40847878. Policy #0 lag: (min: 18.0, avg: 20.1, max: 41.0) -[2023-10-12 06:37:05,202][77203] Avg episode reward: [(0, '59.350'), (1, '46.020')] -[2023-10-12 06:37:08,567][78123] Updated weights for policy 1, policy_version 79590 (0.0007) -[2023-10-12 06:37:08,615][78091] Updated weights for policy 0, policy_version 79970 (0.0007) -[2023-10-12 06:37:08,930][78123] Updated weights for policy 1, policy_version 79600 (0.0008) -[2023-10-12 06:37:08,978][78091] Updated weights for policy 0, policy_version 79980 (0.0009) -[2023-10-12 06:37:09,290][78123] Updated weights for policy 1, policy_version 79610 (0.0009) -[2023-10-12 06:37:09,345][78091] Updated weights for policy 0, policy_version 79990 (0.0011) -[2023-10-12 06:37:09,711][78091] Updated weights for policy 0, policy_version 80000 (0.0011) -[2023-10-12 06:37:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 163446784. Throughput: 0: 1596.8, 1: 1587.6. Samples: 40866086. Policy #0 lag: (min: 18.0, avg: 20.1, max: 41.0) -[2023-10-12 06:37:10,201][77203] Avg episode reward: [(0, '54.570'), (1, '54.970')] -[2023-10-12 06:37:10,212][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000080000_81920000.pth... -[2023-10-12 06:37:10,212][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000079616_81526784.pth... -[2023-10-12 06:37:10,241][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000078496_80379904.pth -[2023-10-12 06:37:10,247][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000078112_79986688.pth -[2023-10-12 06:37:13,536][78123] Updated weights for policy 1, policy_version 79620 (0.0008) -[2023-10-12 06:37:13,905][78123] Updated weights for policy 1, policy_version 79630 (0.0007) -[2023-10-12 06:37:14,046][78091] Updated weights for policy 0, policy_version 80010 (0.0008) -[2023-10-12 06:37:14,261][78123] Updated weights for policy 1, policy_version 79640 (0.0008) -[2023-10-12 06:37:14,422][78091] Updated weights for policy 0, policy_version 80020 (0.0008) -[2023-10-12 06:37:14,781][78091] Updated weights for policy 0, policy_version 80030 (0.0007) -[2023-10-12 06:37:15,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 163512320. Throughput: 0: 1592.7, 1: 1592.5. Samples: 40876812. Policy #0 lag: (min: 18.0, avg: 20.1, max: 41.0) -[2023-10-12 06:37:15,202][77203] Avg episode reward: [(0, '53.320'), (1, '48.620')] -[2023-10-12 06:37:18,800][78123] Updated weights for policy 1, policy_version 79650 (0.0009) -[2023-10-12 06:37:19,174][78123] Updated weights for policy 1, policy_version 79660 (0.0008) -[2023-10-12 06:37:19,188][78091] Updated weights for policy 0, policy_version 80040 (0.0008) -[2023-10-12 06:37:19,538][78123] Updated weights for policy 1, policy_version 79670 (0.0008) -[2023-10-12 06:37:19,547][78091] Updated weights for policy 0, policy_version 80050 (0.0007) -[2023-10-12 06:37:19,905][78123] Updated weights for policy 1, policy_version 79680 (0.0009) -[2023-10-12 06:37:19,916][78091] Updated weights for policy 0, policy_version 80060 (0.0008) -[2023-10-12 06:37:20,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 163577856. Throughput: 0: 1605.7, 1: 1609.6. Samples: 40896204. Policy #0 lag: (min: 18.0, avg: 20.1, max: 41.0) -[2023-10-12 06:37:20,202][77203] Avg episode reward: [(0, '55.910'), (1, '45.260')] -[2023-10-12 06:37:24,319][78123] Updated weights for policy 1, policy_version 79690 (0.0008) -[2023-10-12 06:37:24,320][78091] Updated weights for policy 0, policy_version 80070 (0.0007) -[2023-10-12 06:37:24,686][78123] Updated weights for policy 1, policy_version 79700 (0.0007) -[2023-10-12 06:37:24,690][78091] Updated weights for policy 0, policy_version 80080 (0.0009) -[2023-10-12 06:37:25,052][78123] Updated weights for policy 1, policy_version 79710 (0.0009) -[2023-10-12 06:37:25,061][78091] Updated weights for policy 0, policy_version 80090 (0.0008) -[2023-10-12 06:37:25,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 163610624. Throughput: 0: 1596.8, 1: 1588.9. Samples: 40914160. Policy #0 lag: (min: 18.0, avg: 20.1, max: 41.0) -[2023-10-12 06:37:25,202][77203] Avg episode reward: [(0, '54.080'), (1, '49.180')] -[2023-10-12 06:37:29,409][78091] Updated weights for policy 0, policy_version 80100 (0.0010) -[2023-10-12 06:37:29,551][78123] Updated weights for policy 1, policy_version 79720 (0.0008) -[2023-10-12 06:37:29,784][78091] Updated weights for policy 0, policy_version 80110 (0.0007) -[2023-10-12 06:37:29,928][78123] Updated weights for policy 1, policy_version 79730 (0.0008) -[2023-10-12 06:37:30,162][78091] Updated weights for policy 0, policy_version 80120 (0.0008) -[2023-10-12 06:37:30,201][77203] Fps is (10 sec: 6553.7, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 163643392. Throughput: 0: 1581.7, 1: 1586.5. Samples: 40924110. Policy #0 lag: (min: 18.0, avg: 20.1, max: 41.0) -[2023-10-12 06:37:30,201][77203] Avg episode reward: [(0, '49.690'), (1, '60.670')] -[2023-10-12 06:37:30,288][78123] Updated weights for policy 1, policy_version 79740 (0.0007) -[2023-10-12 06:37:34,487][78091] Updated weights for policy 0, policy_version 80130 (0.0008) -[2023-10-12 06:37:34,700][78123] Updated weights for policy 1, policy_version 79750 (0.0007) -[2023-10-12 06:37:34,878][78091] Updated weights for policy 0, policy_version 80140 (0.0007) -[2023-10-12 06:37:35,067][78123] Updated weights for policy 1, policy_version 79760 (0.0008) -[2023-10-12 06:37:35,201][77203] Fps is (10 sec: 9830.7, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 163708928. Throughput: 0: 1600.5, 1: 1600.2. Samples: 40943668. Policy #0 lag: (min: 18.0, avg: 20.1, max: 41.0) -[2023-10-12 06:37:35,201][77203] Avg episode reward: [(0, '50.690'), (1, '63.630')] -[2023-10-12 06:37:35,252][78091] Updated weights for policy 0, policy_version 80150 (0.0009) -[2023-10-12 06:37:35,426][78123] Updated weights for policy 1, policy_version 79770 (0.0008) -[2023-10-12 06:37:35,612][78091] Updated weights for policy 0, policy_version 80160 (0.0009) -[2023-10-12 06:37:35,642][77950] Saving new best policy, reward=63.630! -[2023-10-12 06:37:39,749][78123] Updated weights for policy 1, policy_version 79780 (0.0008) -[2023-10-12 06:37:39,984][78091] Updated weights for policy 0, policy_version 80170 (0.0009) -[2023-10-12 06:37:40,111][78123] Updated weights for policy 1, policy_version 79790 (0.0008) -[2023-10-12 06:37:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 163774464. Throughput: 0: 1604.8, 1: 1603.1. Samples: 40962530. Policy #0 lag: (min: 18.0, avg: 20.1, max: 41.0) -[2023-10-12 06:37:40,202][77203] Avg episode reward: [(0, '54.120'), (1, '51.950')] -[2023-10-12 06:37:40,353][78091] Updated weights for policy 0, policy_version 80180 (0.0008) -[2023-10-12 06:37:40,480][78123] Updated weights for policy 1, policy_version 79800 (0.0011) -[2023-10-12 06:37:40,724][78091] Updated weights for policy 0, policy_version 80190 (0.0007) -[2023-10-12 06:37:44,574][78123] Updated weights for policy 1, policy_version 79810 (0.0007) -[2023-10-12 06:37:44,943][78123] Updated weights for policy 1, policy_version 79820 (0.0009) -[2023-10-12 06:37:45,152][78091] Updated weights for policy 0, policy_version 80200 (0.0010) -[2023-10-12 06:37:45,201][77203] Fps is (10 sec: 13106.8, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 163840000. Throughput: 0: 1584.3, 1: 1584.2. Samples: 40971558. Policy #0 lag: (min: 18.0, avg: 20.1, max: 41.0) -[2023-10-12 06:37:45,202][77203] Avg episode reward: [(0, '56.110'), (1, '46.610')] -[2023-10-12 06:37:45,302][78123] Updated weights for policy 1, policy_version 79830 (0.0009) -[2023-10-12 06:37:45,522][78091] Updated weights for policy 0, policy_version 80210 (0.0009) -[2023-10-12 06:37:45,671][78123] Updated weights for policy 1, policy_version 79840 (0.0009) -[2023-10-12 06:37:45,908][78091] Updated weights for policy 0, policy_version 80220 (0.0008) -[2023-10-12 06:37:50,079][78123] Updated weights for policy 1, policy_version 79850 (0.0009) -[2023-10-12 06:37:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 163905536. Throughput: 0: 1587.7, 1: 1587.9. Samples: 40990778. Policy #0 lag: (min: 21.0, avg: 28.7, max: 53.0) -[2023-10-12 06:37:50,201][77203] Avg episode reward: [(0, '58.400'), (1, '45.050')] -[2023-10-12 06:37:50,245][78091] Updated weights for policy 0, policy_version 80230 (0.0008) -[2023-10-12 06:37:50,439][78123] Updated weights for policy 1, policy_version 79860 (0.0009) -[2023-10-12 06:37:50,624][78091] Updated weights for policy 0, policy_version 80240 (0.0008) -[2023-10-12 06:37:50,805][78123] Updated weights for policy 1, policy_version 79870 (0.0009) -[2023-10-12 06:37:50,994][78091] Updated weights for policy 0, policy_version 80250 (0.0009) -[2023-10-12 06:37:55,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 163971072. Throughput: 0: 1606.1, 1: 1595.6. Samples: 41010164. Policy #0 lag: (min: 21.0, avg: 28.7, max: 53.0) -[2023-10-12 06:37:55,202][77203] Avg episode reward: [(0, '58.500'), (1, '54.540')] -[2023-10-12 06:37:55,300][78091] Updated weights for policy 0, policy_version 80260 (0.0012) -[2023-10-12 06:37:55,300][78123] Updated weights for policy 1, policy_version 79880 (0.0008) -[2023-10-12 06:37:55,664][78123] Updated weights for policy 1, policy_version 79890 (0.0010) -[2023-10-12 06:37:55,665][78091] Updated weights for policy 0, policy_version 80270 (0.0009) -[2023-10-12 06:37:56,030][78123] Updated weights for policy 1, policy_version 79900 (0.0008) -[2023-10-12 06:37:56,041][78091] Updated weights for policy 0, policy_version 80280 (0.0008) -[2023-10-12 06:38:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 164036608. Throughput: 0: 1581.7, 1: 1570.6. Samples: 41018664. Policy #0 lag: (min: 21.0, avg: 28.7, max: 53.0) -[2023-10-12 06:38:00,202][77203] Avg episode reward: [(0, '55.390'), (1, '51.490')] -[2023-10-12 06:38:00,386][78091] Updated weights for policy 0, policy_version 80290 (0.0009) -[2023-10-12 06:38:00,511][78123] Updated weights for policy 1, policy_version 79910 (0.0008) -[2023-10-12 06:38:00,761][78091] Updated weights for policy 0, policy_version 80300 (0.0009) -[2023-10-12 06:38:00,872][78123] Updated weights for policy 1, policy_version 79920 (0.0008) -[2023-10-12 06:38:01,142][78091] Updated weights for policy 0, policy_version 80310 (0.0010) -[2023-10-12 06:38:01,232][78123] Updated weights for policy 1, policy_version 79930 (0.0008) -[2023-10-12 06:38:01,506][78091] Updated weights for policy 0, policy_version 80320 (0.0007) -[2023-10-12 06:38:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 164102144. Throughput: 0: 1582.1, 1: 1573.0. Samples: 41038184. Policy #0 lag: (min: 21.0, avg: 28.7, max: 53.0) -[2023-10-12 06:38:05,201][77203] Avg episode reward: [(0, '55.960'), (1, '45.920')] -[2023-10-12 06:38:05,407][78123] Updated weights for policy 1, policy_version 79940 (0.0007) -[2023-10-12 06:38:05,771][78091] Updated weights for policy 0, policy_version 80330 (0.0009) -[2023-10-12 06:38:05,779][78123] Updated weights for policy 1, policy_version 79950 (0.0008) -[2023-10-12 06:38:06,143][78091] Updated weights for policy 0, policy_version 80340 (0.0008) -[2023-10-12 06:38:06,145][78123] Updated weights for policy 1, policy_version 79960 (0.0009) -[2023-10-12 06:38:06,517][78091] Updated weights for policy 0, policy_version 80350 (0.0007) -[2023-10-12 06:38:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 164167680. Throughput: 0: 1600.1, 1: 1596.0. Samples: 41057984. Policy #0 lag: (min: 21.0, avg: 28.7, max: 53.0) -[2023-10-12 06:38:10,202][77203] Avg episode reward: [(0, '53.360'), (1, '40.130')] -[2023-10-12 06:38:10,489][78123] Updated weights for policy 1, policy_version 79970 (0.0009) -[2023-10-12 06:38:10,753][78091] Updated weights for policy 0, policy_version 80360 (0.0007) -[2023-10-12 06:38:10,851][78123] Updated weights for policy 1, policy_version 79980 (0.0007) -[2023-10-12 06:38:11,121][78091] Updated weights for policy 0, policy_version 80370 (0.0009) -[2023-10-12 06:38:11,213][78123] Updated weights for policy 1, policy_version 79990 (0.0007) -[2023-10-12 06:38:11,495][78091] Updated weights for policy 0, policy_version 80380 (0.0008) -[2023-10-12 06:38:11,573][78123] Updated weights for policy 1, policy_version 80000 (0.0010) -[2023-10-12 06:38:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 164233216. Throughput: 0: 1587.6, 1: 1578.7. Samples: 41066594. Policy #0 lag: (min: 21.0, avg: 28.7, max: 53.0) -[2023-10-12 06:38:15,202][77203] Avg episode reward: [(0, '61.650'), (1, '45.260')] -[2023-10-12 06:38:15,763][78091] Updated weights for policy 0, policy_version 80390 (0.0010) -[2023-10-12 06:38:16,107][78123] Updated weights for policy 1, policy_version 80010 (0.0007) -[2023-10-12 06:38:16,131][78091] Updated weights for policy 0, policy_version 80400 (0.0008) -[2023-10-12 06:38:16,466][78123] Updated weights for policy 1, policy_version 80020 (0.0009) -[2023-10-12 06:38:16,498][78091] Updated weights for policy 0, policy_version 80410 (0.0008) -[2023-10-12 06:38:16,836][78123] Updated weights for policy 1, policy_version 80030 (0.0008) -[2023-10-12 06:38:20,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 164298752. Throughput: 0: 1584.8, 1: 1579.1. Samples: 41086044. Policy #0 lag: (min: 21.0, avg: 28.7, max: 53.0) -[2023-10-12 06:38:20,201][77203] Avg episode reward: [(0, '58.750'), (1, '42.200')] -[2023-10-12 06:38:20,831][78091] Updated weights for policy 0, policy_version 80420 (0.0007) -[2023-10-12 06:38:21,093][78123] Updated weights for policy 1, policy_version 80040 (0.0007) -[2023-10-12 06:38:21,217][78091] Updated weights for policy 0, policy_version 80430 (0.0007) -[2023-10-12 06:38:21,453][78123] Updated weights for policy 1, policy_version 80050 (0.0008) -[2023-10-12 06:38:21,581][78091] Updated weights for policy 0, policy_version 80440 (0.0010) -[2023-10-12 06:38:21,820][78123] Updated weights for policy 1, policy_version 80060 (0.0009) -[2023-10-12 06:38:25,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 164364288. Throughput: 0: 1594.9, 1: 1583.2. Samples: 41105544. Policy #0 lag: (min: 21.0, avg: 28.7, max: 53.0) -[2023-10-12 06:38:25,202][77203] Avg episode reward: [(0, '60.530'), (1, '53.670')] -[2023-10-12 06:38:26,031][78091] Updated weights for policy 0, policy_version 80450 (0.0008) -[2023-10-12 06:38:26,128][78123] Updated weights for policy 1, policy_version 80070 (0.0008) -[2023-10-12 06:38:26,409][78091] Updated weights for policy 0, policy_version 80460 (0.0009) -[2023-10-12 06:38:26,499][78123] Updated weights for policy 1, policy_version 80080 (0.0009) -[2023-10-12 06:38:26,778][78091] Updated weights for policy 0, policy_version 80470 (0.0008) -[2023-10-12 06:38:26,860][78123] Updated weights for policy 1, policy_version 80090 (0.0008) -[2023-10-12 06:38:27,141][78091] Updated weights for policy 0, policy_version 80480 (0.0007) -[2023-10-12 06:38:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 164429824. Throughput: 0: 1589.7, 1: 1578.9. Samples: 41114146. Policy #0 lag: (min: 21.0, avg: 28.7, max: 53.0) -[2023-10-12 06:38:30,202][77203] Avg episode reward: [(0, '57.450'), (1, '58.930')] -[2023-10-12 06:38:31,055][78123] Updated weights for policy 1, policy_version 80100 (0.0008) -[2023-10-12 06:38:31,422][78123] Updated weights for policy 1, policy_version 80110 (0.0009) -[2023-10-12 06:38:31,477][78091] Updated weights for policy 0, policy_version 80490 (0.0008) -[2023-10-12 06:38:31,797][78123] Updated weights for policy 1, policy_version 80120 (0.0007) -[2023-10-12 06:38:31,839][78091] Updated weights for policy 0, policy_version 80500 (0.0010) -[2023-10-12 06:38:32,217][78091] Updated weights for policy 0, policy_version 80510 (0.0008) -[2023-10-12 06:38:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 164495360. Throughput: 0: 1594.5, 1: 1581.3. Samples: 41133690. Policy #0 lag: (min: 21.0, avg: 28.7, max: 53.0) -[2023-10-12 06:38:35,202][77203] Avg episode reward: [(0, '58.250'), (1, '58.880')] -[2023-10-12 06:38:36,214][78123] Updated weights for policy 1, policy_version 80130 (0.0009) -[2023-10-12 06:38:36,426][78091] Updated weights for policy 0, policy_version 80520 (0.0008) -[2023-10-12 06:38:36,567][78123] Updated weights for policy 1, policy_version 80140 (0.0009) -[2023-10-12 06:38:36,792][78091] Updated weights for policy 0, policy_version 80530 (0.0008) -[2023-10-12 06:38:36,934][78123] Updated weights for policy 1, policy_version 80150 (0.0008) -[2023-10-12 06:38:37,169][78091] Updated weights for policy 0, policy_version 80540 (0.0008) -[2023-10-12 06:38:37,297][78123] Updated weights for policy 1, policy_version 80160 (0.0008) -[2023-10-12 06:38:40,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 164560896. Throughput: 0: 1593.2, 1: 1580.3. Samples: 41152970. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:38:40,201][77203] Avg episode reward: [(0, '56.290'), (1, '53.380')] -[2023-10-12 06:38:41,579][78091] Updated weights for policy 0, policy_version 80550 (0.0008) -[2023-10-12 06:38:41,786][78123] Updated weights for policy 1, policy_version 80170 (0.0009) -[2023-10-12 06:38:41,951][78091] Updated weights for policy 0, policy_version 80560 (0.0008) -[2023-10-12 06:38:42,154][78123] Updated weights for policy 1, policy_version 80180 (0.0008) -[2023-10-12 06:38:42,317][78091] Updated weights for policy 0, policy_version 80570 (0.0009) -[2023-10-12 06:38:42,522][78123] Updated weights for policy 1, policy_version 80190 (0.0007) -[2023-10-12 06:38:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 164626432. Throughput: 0: 1591.9, 1: 1584.0. Samples: 41161580. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:38:45,202][77203] Avg episode reward: [(0, '51.790'), (1, '47.480')] -[2023-10-12 06:38:46,696][78091] Updated weights for policy 0, policy_version 80580 (0.0009) -[2023-10-12 06:38:46,758][78123] Updated weights for policy 1, policy_version 80200 (0.0009) -[2023-10-12 06:38:47,071][78091] Updated weights for policy 0, policy_version 80590 (0.0007) -[2023-10-12 06:38:47,121][78123] Updated weights for policy 1, policy_version 80210 (0.0011) -[2023-10-12 06:38:47,441][78091] Updated weights for policy 0, policy_version 80600 (0.0007) -[2023-10-12 06:38:47,477][78123] Updated weights for policy 1, policy_version 80220 (0.0008) -[2023-10-12 06:38:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 164691968. Throughput: 0: 1591.1, 1: 1585.8. Samples: 41181144. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:38:50,201][77203] Avg episode reward: [(0, '52.340'), (1, '49.340')] -[2023-10-12 06:38:51,792][78091] Updated weights for policy 0, policy_version 80610 (0.0010) -[2023-10-12 06:38:51,830][78123] Updated weights for policy 1, policy_version 80230 (0.0009) -[2023-10-12 06:38:52,160][78091] Updated weights for policy 0, policy_version 80620 (0.0008) -[2023-10-12 06:38:52,196][78123] Updated weights for policy 1, policy_version 80240 (0.0008) -[2023-10-12 06:38:52,525][78091] Updated weights for policy 0, policy_version 80630 (0.0008) -[2023-10-12 06:38:52,558][78123] Updated weights for policy 1, policy_version 80250 (0.0010) -[2023-10-12 06:38:52,903][78091] Updated weights for policy 0, policy_version 80640 (0.0008) -[2023-10-12 06:38:55,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 164757504. Throughput: 0: 1583.4, 1: 1580.4. Samples: 41200354. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:38:55,202][77203] Avg episode reward: [(0, '50.310'), (1, '55.510')] -[2023-10-12 06:38:56,844][78123] Updated weights for policy 1, policy_version 80260 (0.0007) -[2023-10-12 06:38:57,206][78123] Updated weights for policy 1, policy_version 80270 (0.0007) -[2023-10-12 06:38:57,216][78091] Updated weights for policy 0, policy_version 80650 (0.0007) -[2023-10-12 06:38:57,570][78123] Updated weights for policy 1, policy_version 80280 (0.0008) -[2023-10-12 06:38:57,592][78091] Updated weights for policy 0, policy_version 80660 (0.0007) -[2023-10-12 06:38:57,965][78091] Updated weights for policy 0, policy_version 80670 (0.0007) -[2023-10-12 06:39:00,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 164823040. Throughput: 0: 1589.8, 1: 1585.7. Samples: 41209492. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:39:00,202][77203] Avg episode reward: [(0, '53.150'), (1, '48.360')] -[2023-10-12 06:39:01,984][78123] Updated weights for policy 1, policy_version 80290 (0.0008) -[2023-10-12 06:39:02,279][78091] Updated weights for policy 0, policy_version 80680 (0.0009) -[2023-10-12 06:39:02,382][78123] Updated weights for policy 1, policy_version 80300 (0.0007) -[2023-10-12 06:39:02,643][78091] Updated weights for policy 0, policy_version 80690 (0.0009) -[2023-10-12 06:39:02,737][78123] Updated weights for policy 1, policy_version 80310 (0.0008) -[2023-10-12 06:39:03,013][78091] Updated weights for policy 0, policy_version 80700 (0.0007) -[2023-10-12 06:39:03,100][78123] Updated weights for policy 1, policy_version 80320 (0.0008) -[2023-10-12 06:39:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 164888576. Throughput: 0: 1583.8, 1: 1582.5. Samples: 41228528. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:39:05,202][77203] Avg episode reward: [(0, '60.810'), (1, '44.090')] -[2023-10-12 06:39:07,423][78123] Updated weights for policy 1, policy_version 80330 (0.0007) -[2023-10-12 06:39:07,518][78091] Updated weights for policy 0, policy_version 80710 (0.0007) -[2023-10-12 06:39:07,777][78123] Updated weights for policy 1, policy_version 80340 (0.0007) -[2023-10-12 06:39:07,906][78091] Updated weights for policy 0, policy_version 80720 (0.0008) -[2023-10-12 06:39:08,145][78123] Updated weights for policy 1, policy_version 80350 (0.0008) -[2023-10-12 06:39:08,284][78091] Updated weights for policy 0, policy_version 80730 (0.0007) -[2023-10-12 06:39:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 164954112. Throughput: 0: 1580.8, 1: 1582.0. Samples: 41247872. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:39:10,202][77203] Avg episode reward: [(0, '61.360'), (1, '37.930')] -[2023-10-12 06:39:10,213][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000080352_82280448.pth... -[2023-10-12 06:39:10,214][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000080736_82673664.pth... -[2023-10-12 06:39:10,250][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000079232_81133568.pth -[2023-10-12 06:39:10,254][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000078880_80773120.pth -[2023-10-12 06:39:12,429][78123] Updated weights for policy 1, policy_version 80360 (0.0010) -[2023-10-12 06:39:12,441][78091] Updated weights for policy 0, policy_version 80740 (0.0008) -[2023-10-12 06:39:12,799][78123] Updated weights for policy 1, policy_version 80370 (0.0009) -[2023-10-12 06:39:12,807][78091] Updated weights for policy 0, policy_version 80750 (0.0009) -[2023-10-12 06:39:13,161][78123] Updated weights for policy 1, policy_version 80380 (0.0008) -[2023-10-12 06:39:13,173][78091] Updated weights for policy 0, policy_version 80760 (0.0008) -[2023-10-12 06:39:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 165019648. Throughput: 0: 1595.8, 1: 1598.3. Samples: 41257878. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:39:15,202][77203] Avg episode reward: [(0, '56.790'), (1, '40.870')] -[2023-10-12 06:39:17,354][78091] Updated weights for policy 0, policy_version 80770 (0.0008) -[2023-10-12 06:39:17,616][78123] Updated weights for policy 1, policy_version 80390 (0.0010) -[2023-10-12 06:39:17,734][78091] Updated weights for policy 0, policy_version 80780 (0.0008) -[2023-10-12 06:39:17,979][78123] Updated weights for policy 1, policy_version 80400 (0.0008) -[2023-10-12 06:39:18,093][78091] Updated weights for policy 0, policy_version 80790 (0.0007) -[2023-10-12 06:39:18,358][78123] Updated weights for policy 1, policy_version 80410 (0.0008) -[2023-10-12 06:39:18,459][78091] Updated weights for policy 0, policy_version 80800 (0.0009) -[2023-10-12 06:39:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 165085184. Throughput: 0: 1580.9, 1: 1582.1. Samples: 41276028. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:39:20,202][77203] Avg episode reward: [(0, '53.420'), (1, '52.020')] -[2023-10-12 06:39:22,645][78123] Updated weights for policy 1, policy_version 80420 (0.0007) -[2023-10-12 06:39:22,758][78091] Updated weights for policy 0, policy_version 80810 (0.0007) -[2023-10-12 06:39:23,013][78123] Updated weights for policy 1, policy_version 80430 (0.0008) -[2023-10-12 06:39:23,123][78091] Updated weights for policy 0, policy_version 80820 (0.0008) -[2023-10-12 06:39:23,373][78123] Updated weights for policy 1, policy_version 80440 (0.0008) -[2023-10-12 06:39:23,500][78091] Updated weights for policy 0, policy_version 80830 (0.0007) -[2023-10-12 06:39:25,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.3, 300 sec: 12774.0). Total num frames: 165150720. Throughput: 0: 1581.2, 1: 1584.7. Samples: 41295436. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:39:25,201][77203] Avg episode reward: [(0, '52.970'), (1, '62.340')] -[2023-10-12 06:39:27,825][78123] Updated weights for policy 1, policy_version 80450 (0.0008) -[2023-10-12 06:39:27,937][78091] Updated weights for policy 0, policy_version 80840 (0.0008) -[2023-10-12 06:39:28,183][78123] Updated weights for policy 1, policy_version 80460 (0.0008) -[2023-10-12 06:39:28,300][78091] Updated weights for policy 0, policy_version 80850 (0.0010) -[2023-10-12 06:39:28,553][78123] Updated weights for policy 1, policy_version 80470 (0.0008) -[2023-10-12 06:39:28,677][78091] Updated weights for policy 0, policy_version 80860 (0.0010) -[2023-10-12 06:39:28,921][78123] Updated weights for policy 1, policy_version 80480 (0.0009) -[2023-10-12 06:39:30,201][77203] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 165216256. Throughput: 0: 1602.6, 1: 1607.7. Samples: 41306044. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-12 06:39:30,201][77203] Avg episode reward: [(0, '57.780'), (1, '44.720')] -[2023-10-12 06:39:33,093][78091] Updated weights for policy 0, policy_version 80870 (0.0008) -[2023-10-12 06:39:33,235][78123] Updated weights for policy 1, policy_version 80490 (0.0008) -[2023-10-12 06:39:33,459][78091] Updated weights for policy 0, policy_version 80880 (0.0008) -[2023-10-12 06:39:33,607][78123] Updated weights for policy 1, policy_version 80500 (0.0009) -[2023-10-12 06:39:33,841][78091] Updated weights for policy 0, policy_version 80890 (0.0009) -[2023-10-12 06:39:33,970][78123] Updated weights for policy 1, policy_version 80510 (0.0009) -[2023-10-12 06:39:35,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 165281792. Throughput: 0: 1588.9, 1: 1587.2. Samples: 41324070. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-12 06:39:35,202][77203] Avg episode reward: [(0, '55.480'), (1, '46.600')] -[2023-10-12 06:39:38,001][78091] Updated weights for policy 0, policy_version 80900 (0.0007) -[2023-10-12 06:39:38,181][78123] Updated weights for policy 1, policy_version 80520 (0.0009) -[2023-10-12 06:39:38,380][78091] Updated weights for policy 0, policy_version 80910 (0.0008) -[2023-10-12 06:39:38,540][78123] Updated weights for policy 1, policy_version 80530 (0.0008) -[2023-10-12 06:39:38,754][78091] Updated weights for policy 0, policy_version 80920 (0.0008) -[2023-10-12 06:39:38,906][78123] Updated weights for policy 1, policy_version 80540 (0.0008) -[2023-10-12 06:39:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 165347328. Throughput: 0: 1588.9, 1: 1583.3. Samples: 41343102. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-12 06:39:40,201][77203] Avg episode reward: [(0, '55.720'), (1, '48.590')] -[2023-10-12 06:39:43,105][78091] Updated weights for policy 0, policy_version 80930 (0.0008) -[2023-10-12 06:39:43,353][78123] Updated weights for policy 1, policy_version 80550 (0.0007) -[2023-10-12 06:39:43,479][78091] Updated weights for policy 0, policy_version 80940 (0.0010) -[2023-10-12 06:39:43,721][78123] Updated weights for policy 1, policy_version 80560 (0.0007) -[2023-10-12 06:39:43,850][78091] Updated weights for policy 0, policy_version 80950 (0.0008) -[2023-10-12 06:39:44,078][78123] Updated weights for policy 1, policy_version 80570 (0.0010) -[2023-10-12 06:39:44,222][78091] Updated weights for policy 0, policy_version 80960 (0.0008) -[2023-10-12 06:39:45,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 165412864. Throughput: 0: 1608.1, 1: 1602.3. Samples: 41353962. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-12 06:39:45,202][77203] Avg episode reward: [(0, '60.420'), (1, '52.310')] -[2023-10-12 06:39:48,572][78091] Updated weights for policy 0, policy_version 80970 (0.0007) -[2023-10-12 06:39:48,648][78123] Updated weights for policy 1, policy_version 80580 (0.0010) -[2023-10-12 06:39:48,941][78091] Updated weights for policy 0, policy_version 80980 (0.0009) -[2023-10-12 06:39:49,041][78123] Updated weights for policy 1, policy_version 80590 (0.0008) -[2023-10-12 06:39:49,308][78091] Updated weights for policy 0, policy_version 80990 (0.0009) -[2023-10-12 06:39:49,404][78123] Updated weights for policy 1, policy_version 80600 (0.0010) -[2023-10-12 06:39:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 165478400. Throughput: 0: 1599.8, 1: 1596.9. Samples: 41372378. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-12 06:39:50,201][77203] Avg episode reward: [(0, '61.920'), (1, '59.560')] -[2023-10-12 06:39:53,634][78091] Updated weights for policy 0, policy_version 81000 (0.0010) -[2023-10-12 06:39:53,650][78123] Updated weights for policy 1, policy_version 80610 (0.0007) -[2023-10-12 06:39:54,012][78091] Updated weights for policy 0, policy_version 81010 (0.0008) -[2023-10-12 06:39:54,017][78123] Updated weights for policy 1, policy_version 80620 (0.0009) -[2023-10-12 06:39:54,373][78123] Updated weights for policy 1, policy_version 80630 (0.0009) -[2023-10-12 06:39:54,379][78091] Updated weights for policy 0, policy_version 81020 (0.0008) -[2023-10-12 06:39:54,741][78123] Updated weights for policy 1, policy_version 80640 (0.0010) -[2023-10-12 06:39:55,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 165543936. Throughput: 0: 1591.9, 1: 1578.0. Samples: 41390518. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-12 06:39:55,201][77203] Avg episode reward: [(0, '61.950'), (1, '45.310')] -[2023-10-12 06:39:58,679][78091] Updated weights for policy 0, policy_version 81030 (0.0008) -[2023-10-12 06:39:59,046][78091] Updated weights for policy 0, policy_version 81040 (0.0008) -[2023-10-12 06:39:59,183][78123] Updated weights for policy 1, policy_version 80650 (0.0008) -[2023-10-12 06:39:59,418][78091] Updated weights for policy 0, policy_version 81050 (0.0009) -[2023-10-12 06:39:59,556][78123] Updated weights for policy 1, policy_version 80660 (0.0007) -[2023-10-12 06:39:59,920][78123] Updated weights for policy 1, policy_version 80670 (0.0008) -[2023-10-12 06:40:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 12885.0). Total num frames: 165609472. Throughput: 0: 1602.6, 1: 1584.9. Samples: 41401316. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-12 06:40:00,201][77203] Avg episode reward: [(0, '50.690'), (1, '43.720')] -[2023-10-12 06:40:03,555][78091] Updated weights for policy 0, policy_version 81060 (0.0009) -[2023-10-12 06:40:03,919][78091] Updated weights for policy 0, policy_version 81070 (0.0010) -[2023-10-12 06:40:04,289][78091] Updated weights for policy 0, policy_version 81080 (0.0008) -[2023-10-12 06:40:04,355][78123] Updated weights for policy 1, policy_version 80680 (0.0007) -[2023-10-12 06:40:04,730][78123] Updated weights for policy 1, policy_version 80690 (0.0007) -[2023-10-12 06:40:05,111][78123] Updated weights for policy 1, policy_version 80700 (0.0009) -[2023-10-12 06:40:05,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 165642240. Throughput: 0: 1607.2, 1: 1603.9. Samples: 41420530. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-12 06:40:05,202][77203] Avg episode reward: [(0, '51.140'), (1, '48.600')] -[2023-10-12 06:40:08,619][78091] Updated weights for policy 0, policy_version 81090 (0.0009) -[2023-10-12 06:40:08,992][78091] Updated weights for policy 0, policy_version 81100 (0.0007) -[2023-10-12 06:40:09,356][78091] Updated weights for policy 0, policy_version 81110 (0.0007) -[2023-10-12 06:40:09,393][78123] Updated weights for policy 1, policy_version 80710 (0.0009) -[2023-10-12 06:40:09,729][78091] Updated weights for policy 0, policy_version 81120 (0.0008) -[2023-10-12 06:40:09,755][78123] Updated weights for policy 1, policy_version 80720 (0.0008) -[2023-10-12 06:40:10,116][78123] Updated weights for policy 1, policy_version 80730 (0.0007) -[2023-10-12 06:40:10,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 165707776. Throughput: 0: 1596.1, 1: 1593.1. Samples: 41438952. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-12 06:40:10,201][77203] Avg episode reward: [(0, '51.160'), (1, '44.000')] -[2023-10-12 06:40:14,041][78091] Updated weights for policy 0, policy_version 81130 (0.0008) -[2023-10-12 06:40:14,417][78091] Updated weights for policy 0, policy_version 81140 (0.0008) -[2023-10-12 06:40:14,437][78123] Updated weights for policy 1, policy_version 80740 (0.0007) -[2023-10-12 06:40:14,788][78091] Updated weights for policy 0, policy_version 81150 (0.0007) -[2023-10-12 06:40:14,800][78123] Updated weights for policy 1, policy_version 80750 (0.0007) -[2023-10-12 06:40:15,169][78123] Updated weights for policy 1, policy_version 80760 (0.0007) -[2023-10-12 06:40:15,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 165773312. Throughput: 0: 1601.7, 1: 1581.6. Samples: 41449294. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-12 06:40:15,202][77203] Avg episode reward: [(0, '53.620'), (1, '45.700')] -[2023-10-12 06:40:19,183][78091] Updated weights for policy 0, policy_version 81160 (0.0008) -[2023-10-12 06:40:19,546][78091] Updated weights for policy 0, policy_version 81170 (0.0007) -[2023-10-12 06:40:19,561][78123] Updated weights for policy 1, policy_version 80770 (0.0008) -[2023-10-12 06:40:19,926][78123] Updated weights for policy 1, policy_version 80780 (0.0009) -[2023-10-12 06:40:19,928][78091] Updated weights for policy 0, policy_version 81180 (0.0008) -[2023-10-12 06:40:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 165838848. Throughput: 0: 1613.3, 1: 1601.0. Samples: 41468712. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:40:20,201][77203] Avg episode reward: [(0, '49.550'), (1, '51.210')] -[2023-10-12 06:40:20,289][78123] Updated weights for policy 1, policy_version 80790 (0.0009) -[2023-10-12 06:40:20,663][78123] Updated weights for policy 1, policy_version 80800 (0.0010) -[2023-10-12 06:40:24,240][78091] Updated weights for policy 0, policy_version 81190 (0.0009) -[2023-10-12 06:40:24,612][78091] Updated weights for policy 0, policy_version 81200 (0.0010) -[2023-10-12 06:40:24,977][78091] Updated weights for policy 0, policy_version 81210 (0.0009) -[2023-10-12 06:40:25,081][78123] Updated weights for policy 1, policy_version 80810 (0.0009) -[2023-10-12 06:40:25,201][77203] Fps is (10 sec: 13107.6, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 165904384. Throughput: 0: 1601.9, 1: 1604.0. Samples: 41487368. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:40:25,201][77203] Avg episode reward: [(0, '54.270'), (1, '47.460')] -[2023-10-12 06:40:25,464][78123] Updated weights for policy 1, policy_version 80820 (0.0010) -[2023-10-12 06:40:25,840][78123] Updated weights for policy 1, policy_version 80830 (0.0009) -[2023-10-12 06:40:29,281][78091] Updated weights for policy 0, policy_version 81220 (0.0009) -[2023-10-12 06:40:29,654][78091] Updated weights for policy 0, policy_version 81230 (0.0008) -[2023-10-12 06:40:30,019][78091] Updated weights for policy 0, policy_version 81240 (0.0008) -[2023-10-12 06:40:30,110][78123] Updated weights for policy 1, policy_version 80840 (0.0009) -[2023-10-12 06:40:30,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 165937152. Throughput: 0: 1593.9, 1: 1577.2. Samples: 41496660. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:40:30,201][77203] Avg episode reward: [(0, '57.290'), (1, '44.010')] -[2023-10-12 06:40:30,478][78123] Updated weights for policy 1, policy_version 80850 (0.0010) -[2023-10-12 06:40:30,835][78123] Updated weights for policy 1, policy_version 80860 (0.0007) -[2023-10-12 06:40:34,454][78091] Updated weights for policy 0, policy_version 81250 (0.0009) -[2023-10-12 06:40:34,826][78091] Updated weights for policy 0, policy_version 81260 (0.0009) -[2023-10-12 06:40:35,136][78123] Updated weights for policy 1, policy_version 80870 (0.0007) -[2023-10-12 06:40:35,188][78091] Updated weights for policy 0, policy_version 81270 (0.0008) -[2023-10-12 06:40:35,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 166002688. Throughput: 0: 1604.6, 1: 1590.1. Samples: 41516140. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:40:35,201][77203] Avg episode reward: [(0, '59.670'), (1, '44.610')] -[2023-10-12 06:40:35,516][78123] Updated weights for policy 1, policy_version 80880 (0.0009) -[2023-10-12 06:40:35,555][78091] Updated weights for policy 0, policy_version 81280 (0.0007) -[2023-10-12 06:40:35,889][78123] Updated weights for policy 1, policy_version 80890 (0.0007) -[2023-10-12 06:40:39,928][78091] Updated weights for policy 0, policy_version 81290 (0.0010) -[2023-10-12 06:40:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 166068224. Throughput: 0: 1609.7, 1: 1606.4. Samples: 41535246. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:40:40,202][77203] Avg episode reward: [(0, '52.040'), (1, '46.930')] -[2023-10-12 06:40:40,235][78123] Updated weights for policy 1, policy_version 80900 (0.0008) -[2023-10-12 06:40:40,299][78091] Updated weights for policy 0, policy_version 81300 (0.0008) -[2023-10-12 06:40:40,594][78123] Updated weights for policy 1, policy_version 80910 (0.0007) -[2023-10-12 06:40:40,658][78091] Updated weights for policy 0, policy_version 81310 (0.0007) -[2023-10-12 06:40:40,964][78123] Updated weights for policy 1, policy_version 80920 (0.0007) -[2023-10-12 06:40:45,055][78091] Updated weights for policy 0, policy_version 81320 (0.0009) -[2023-10-12 06:40:45,126][78123] Updated weights for policy 1, policy_version 80930 (0.0008) -[2023-10-12 06:40:45,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 166133760. Throughput: 0: 1586.8, 1: 1584.4. Samples: 41544022. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:40:45,202][77203] Avg episode reward: [(0, '54.000'), (1, '50.830')] -[2023-10-12 06:40:45,424][78091] Updated weights for policy 0, policy_version 81330 (0.0008) -[2023-10-12 06:40:45,493][78123] Updated weights for policy 1, policy_version 80940 (0.0008) -[2023-10-12 06:40:45,804][78091] Updated weights for policy 0, policy_version 81340 (0.0009) -[2023-10-12 06:40:45,855][78123] Updated weights for policy 1, policy_version 80950 (0.0010) -[2023-10-12 06:40:46,228][78123] Updated weights for policy 1, policy_version 80960 (0.0009) -[2023-10-12 06:40:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 166199296. Throughput: 0: 1591.0, 1: 1581.1. Samples: 41563274. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:40:50,201][77203] Avg episode reward: [(0, '54.990'), (1, '57.650')] -[2023-10-12 06:40:50,229][78091] Updated weights for policy 0, policy_version 81350 (0.0009) -[2023-10-12 06:40:50,591][78123] Updated weights for policy 1, policy_version 80970 (0.0007) -[2023-10-12 06:40:50,598][78091] Updated weights for policy 0, policy_version 81360 (0.0010) -[2023-10-12 06:40:50,956][78123] Updated weights for policy 1, policy_version 80980 (0.0007) -[2023-10-12 06:40:50,969][78091] Updated weights for policy 0, policy_version 81370 (0.0009) -[2023-10-12 06:40:51,316][78123] Updated weights for policy 1, policy_version 80990 (0.0008) -[2023-10-12 06:40:55,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 166264832. Throughput: 0: 1604.5, 1: 1592.7. Samples: 41582828. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:40:55,201][77203] Avg episode reward: [(0, '57.400'), (1, '50.040')] -[2023-10-12 06:40:55,265][78091] Updated weights for policy 0, policy_version 81380 (0.0009) -[2023-10-12 06:40:55,631][78091] Updated weights for policy 0, policy_version 81390 (0.0008) -[2023-10-12 06:40:55,835][78123] Updated weights for policy 1, policy_version 81000 (0.0008) -[2023-10-12 06:40:55,991][78091] Updated weights for policy 0, policy_version 81400 (0.0007) -[2023-10-12 06:40:56,202][78123] Updated weights for policy 1, policy_version 81010 (0.0009) -[2023-10-12 06:40:56,571][78123] Updated weights for policy 1, policy_version 81020 (0.0007) -[2023-10-12 06:41:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 166330368. Throughput: 0: 1575.4, 1: 1579.5. Samples: 41591264. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:41:00,201][77203] Avg episode reward: [(0, '57.370'), (1, '43.570')] -[2023-10-12 06:41:00,265][78091] Updated weights for policy 0, policy_version 81410 (0.0008) -[2023-10-12 06:41:00,639][78091] Updated weights for policy 0, policy_version 81420 (0.0010) -[2023-10-12 06:41:00,883][78123] Updated weights for policy 1, policy_version 81030 (0.0008) -[2023-10-12 06:41:01,004][78091] Updated weights for policy 0, policy_version 81430 (0.0009) -[2023-10-12 06:41:01,240][78123] Updated weights for policy 1, policy_version 81040 (0.0007) -[2023-10-12 06:41:01,373][78091] Updated weights for policy 0, policy_version 81440 (0.0007) -[2023-10-12 06:41:01,604][78123] Updated weights for policy 1, policy_version 81050 (0.0009) -[2023-10-12 06:41:05,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 166395904. Throughput: 0: 1575.6, 1: 1581.5. Samples: 41610782. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:41:05,202][77203] Avg episode reward: [(0, '51.920'), (1, '41.230')] -[2023-10-12 06:41:05,862][78091] Updated weights for policy 0, policy_version 81450 (0.0009) -[2023-10-12 06:41:05,863][78123] Updated weights for policy 1, policy_version 81060 (0.0007) -[2023-10-12 06:41:06,227][78091] Updated weights for policy 0, policy_version 81460 (0.0007) -[2023-10-12 06:41:06,229][78123] Updated weights for policy 1, policy_version 81070 (0.0008) -[2023-10-12 06:41:06,594][78123] Updated weights for policy 1, policy_version 81080 (0.0008) -[2023-10-12 06:41:06,596][78091] Updated weights for policy 0, policy_version 81470 (0.0007) -[2023-10-12 06:41:10,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 166461440. Throughput: 0: 1591.3, 1: 1582.5. Samples: 41630190. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:41:10,202][77203] Avg episode reward: [(0, '54.800'), (1, '50.830')] -[2023-10-12 06:41:10,213][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000081088_83034112.pth... -[2023-10-12 06:41:10,213][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000081472_83427328.pth... -[2023-10-12 06:41:10,249][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000080000_81920000.pth -[2023-10-12 06:41:10,258][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000079616_81526784.pth -[2023-10-12 06:41:10,870][78091] Updated weights for policy 0, policy_version 81480 (0.0007) -[2023-10-12 06:41:11,174][78123] Updated weights for policy 1, policy_version 81090 (0.0009) -[2023-10-12 06:41:11,245][78091] Updated weights for policy 0, policy_version 81490 (0.0008) -[2023-10-12 06:41:11,538][78123] Updated weights for policy 1, policy_version 81100 (0.0008) -[2023-10-12 06:41:11,612][78091] Updated weights for policy 0, policy_version 81500 (0.0008) -[2023-10-12 06:41:11,899][78123] Updated weights for policy 1, policy_version 81110 (0.0009) -[2023-10-12 06:41:12,255][78123] Updated weights for policy 1, policy_version 81120 (0.0008) -[2023-10-12 06:41:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 166526976. Throughput: 0: 1575.0, 1: 1583.3. Samples: 41638784. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:41:15,202][77203] Avg episode reward: [(0, '57.660'), (1, '63.040')] -[2023-10-12 06:41:15,796][78091] Updated weights for policy 0, policy_version 81510 (0.0008) -[2023-10-12 06:41:16,175][78091] Updated weights for policy 0, policy_version 81520 (0.0009) -[2023-10-12 06:41:16,482][78123] Updated weights for policy 1, policy_version 81130 (0.0009) -[2023-10-12 06:41:16,537][78091] Updated weights for policy 0, policy_version 81530 (0.0008) -[2023-10-12 06:41:16,838][78123] Updated weights for policy 1, policy_version 81140 (0.0007) -[2023-10-12 06:41:17,219][78123] Updated weights for policy 1, policy_version 81150 (0.0007) -[2023-10-12 06:41:20,201][77203] Fps is (10 sec: 13107.6, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 166592512. Throughput: 0: 1577.5, 1: 1583.6. Samples: 41658390. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:41:20,201][77203] Avg episode reward: [(0, '62.380'), (1, '47.010')] -[2023-10-12 06:41:20,951][78091] Updated weights for policy 0, policy_version 81540 (0.0007) -[2023-10-12 06:41:21,325][78091] Updated weights for policy 0, policy_version 81550 (0.0007) -[2023-10-12 06:41:21,631][78123] Updated weights for policy 1, policy_version 81160 (0.0009) -[2023-10-12 06:41:21,708][78091] Updated weights for policy 0, policy_version 81560 (0.0008) -[2023-10-12 06:41:21,993][78123] Updated weights for policy 1, policy_version 81170 (0.0007) -[2023-10-12 06:41:22,362][78123] Updated weights for policy 1, policy_version 81180 (0.0008) -[2023-10-12 06:41:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 166658048. Throughput: 0: 1581.9, 1: 1583.2. Samples: 41677674. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:41:25,202][77203] Avg episode reward: [(0, '59.980'), (1, '40.340')] -[2023-10-12 06:41:26,142][78091] Updated weights for policy 0, policy_version 81570 (0.0008) -[2023-10-12 06:41:26,548][78091] Updated weights for policy 0, policy_version 81580 (0.0010) -[2023-10-12 06:41:26,583][78123] Updated weights for policy 1, policy_version 81190 (0.0010) -[2023-10-12 06:41:26,908][78091] Updated weights for policy 0, policy_version 81590 (0.0010) -[2023-10-12 06:41:26,952][78123] Updated weights for policy 1, policy_version 81200 (0.0009) -[2023-10-12 06:41:27,275][78091] Updated weights for policy 0, policy_version 81600 (0.0010) -[2023-10-12 06:41:27,311][78123] Updated weights for policy 1, policy_version 81210 (0.0009) -[2023-10-12 06:41:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 166723584. Throughput: 0: 1578.1, 1: 1580.9. Samples: 41686176. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:41:30,201][77203] Avg episode reward: [(0, '54.760'), (1, '42.930')] -[2023-10-12 06:41:31,559][78091] Updated weights for policy 0, policy_version 81610 (0.0009) -[2023-10-12 06:41:31,579][78123] Updated weights for policy 1, policy_version 81220 (0.0008) -[2023-10-12 06:41:31,941][78091] Updated weights for policy 0, policy_version 81620 (0.0008) -[2023-10-12 06:41:31,943][78123] Updated weights for policy 1, policy_version 81230 (0.0008) -[2023-10-12 06:41:32,305][78123] Updated weights for policy 1, policy_version 81240 (0.0008) -[2023-10-12 06:41:32,315][78091] Updated weights for policy 0, policy_version 81630 (0.0008) -[2023-10-12 06:41:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 166789120. Throughput: 0: 1583.4, 1: 1578.4. Samples: 41705558. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:41:35,202][77203] Avg episode reward: [(0, '59.260'), (1, '44.930')] -[2023-10-12 06:41:36,760][78091] Updated weights for policy 0, policy_version 81640 (0.0009) -[2023-10-12 06:41:36,761][78123] Updated weights for policy 1, policy_version 81250 (0.0009) -[2023-10-12 06:41:37,123][78091] Updated weights for policy 0, policy_version 81650 (0.0008) -[2023-10-12 06:41:37,129][78123] Updated weights for policy 1, policy_version 81260 (0.0008) -[2023-10-12 06:41:37,487][78123] Updated weights for policy 1, policy_version 81270 (0.0008) -[2023-10-12 06:41:37,504][78091] Updated weights for policy 0, policy_version 81660 (0.0009) -[2023-10-12 06:41:37,851][78123] Updated weights for policy 1, policy_version 81280 (0.0008) -[2023-10-12 06:41:40,201][77203] Fps is (10 sec: 13106.7, 60 sec: 13107.1, 300 sec: 12662.9). Total num frames: 166854656. Throughput: 0: 1581.0, 1: 1578.0. Samples: 41724986. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:41:40,202][77203] Avg episode reward: [(0, '64.490'), (1, '50.960')] -[2023-10-12 06:41:41,787][78091] Updated weights for policy 0, policy_version 81670 (0.0008) -[2023-10-12 06:41:42,157][78091] Updated weights for policy 0, policy_version 81680 (0.0008) -[2023-10-12 06:41:42,277][78123] Updated weights for policy 1, policy_version 81290 (0.0009) -[2023-10-12 06:41:42,524][78091] Updated weights for policy 0, policy_version 81690 (0.0008) -[2023-10-12 06:41:42,649][78123] Updated weights for policy 1, policy_version 81300 (0.0008) -[2023-10-12 06:41:43,011][78123] Updated weights for policy 1, policy_version 81310 (0.0009) -[2023-10-12 06:41:45,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.3, 300 sec: 12662.9). Total num frames: 166920192. Throughput: 0: 1584.7, 1: 1586.4. Samples: 41733964. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:41:45,201][77203] Avg episode reward: [(0, '59.300'), (1, '51.030')] -[2023-10-12 06:41:46,726][78091] Updated weights for policy 0, policy_version 81700 (0.0008) -[2023-10-12 06:41:47,096][78091] Updated weights for policy 0, policy_version 81710 (0.0007) -[2023-10-12 06:41:47,474][78091] Updated weights for policy 0, policy_version 81720 (0.0009) -[2023-10-12 06:41:47,537][78123] Updated weights for policy 1, policy_version 81320 (0.0008) -[2023-10-12 06:41:47,891][78123] Updated weights for policy 1, policy_version 81330 (0.0009) -[2023-10-12 06:41:48,270][78123] Updated weights for policy 1, policy_version 81340 (0.0009) -[2023-10-12 06:41:50,201][77203] Fps is (10 sec: 13107.7, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 166985728. Throughput: 0: 1592.6, 1: 1569.8. Samples: 41753090. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:41:50,202][77203] Avg episode reward: [(0, '54.130'), (1, '46.180')] -[2023-10-12 06:41:51,735][78091] Updated weights for policy 0, policy_version 81730 (0.0008) -[2023-10-12 06:41:52,110][78091] Updated weights for policy 0, policy_version 81740 (0.0009) -[2023-10-12 06:41:52,475][78091] Updated weights for policy 0, policy_version 81750 (0.0009) -[2023-10-12 06:41:52,655][78123] Updated weights for policy 1, policy_version 81350 (0.0008) -[2023-10-12 06:41:52,845][78091] Updated weights for policy 0, policy_version 81760 (0.0009) -[2023-10-12 06:41:53,031][78123] Updated weights for policy 1, policy_version 81360 (0.0007) -[2023-10-12 06:41:53,391][78123] Updated weights for policy 1, policy_version 81370 (0.0008) -[2023-10-12 06:41:55,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 167051264. Throughput: 0: 1595.6, 1: 1575.2. Samples: 41772876. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:41:55,202][77203] Avg episode reward: [(0, '56.200'), (1, '52.530')] -[2023-10-12 06:41:56,989][78091] Updated weights for policy 0, policy_version 81770 (0.0011) -[2023-10-12 06:41:57,361][78091] Updated weights for policy 0, policy_version 81780 (0.0011) -[2023-10-12 06:41:57,654][78123] Updated weights for policy 1, policy_version 81380 (0.0008) -[2023-10-12 06:41:57,718][78091] Updated weights for policy 0, policy_version 81790 (0.0008) -[2023-10-12 06:41:58,029][78123] Updated weights for policy 1, policy_version 81390 (0.0007) -[2023-10-12 06:41:58,395][78123] Updated weights for policy 1, policy_version 81400 (0.0009) -[2023-10-12 06:42:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 167116800. Throughput: 0: 1596.9, 1: 1600.2. Samples: 41782654. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:42:00,202][77203] Avg episode reward: [(0, '56.740'), (1, '50.120')] -[2023-10-12 06:42:01,978][78091] Updated weights for policy 0, policy_version 81800 (0.0009) -[2023-10-12 06:42:02,353][78091] Updated weights for policy 0, policy_version 81810 (0.0009) -[2023-10-12 06:42:02,721][78091] Updated weights for policy 0, policy_version 81820 (0.0009) -[2023-10-12 06:42:02,937][78123] Updated weights for policy 1, policy_version 81410 (0.0010) -[2023-10-12 06:42:03,297][78123] Updated weights for policy 1, policy_version 81420 (0.0010) -[2023-10-12 06:42:03,665][78123] Updated weights for policy 1, policy_version 81430 (0.0007) -[2023-10-12 06:42:04,033][78123] Updated weights for policy 1, policy_version 81440 (0.0008) -[2023-10-12 06:42:05,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 167182336. Throughput: 0: 1599.9, 1: 1581.1. Samples: 41801534. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:42:05,202][77203] Avg episode reward: [(0, '60.020'), (1, '46.610')] -[2023-10-12 06:42:06,844][78091] Updated weights for policy 0, policy_version 81830 (0.0009) -[2023-10-12 06:42:07,204][78091] Updated weights for policy 0, policy_version 81840 (0.0010) -[2023-10-12 06:42:07,576][78091] Updated weights for policy 0, policy_version 81850 (0.0009) -[2023-10-12 06:42:08,349][78123] Updated weights for policy 1, policy_version 81450 (0.0007) -[2023-10-12 06:42:08,715][78123] Updated weights for policy 1, policy_version 81460 (0.0007) -[2023-10-12 06:42:09,083][78123] Updated weights for policy 1, policy_version 81470 (0.0007) -[2023-10-12 06:42:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 12662.9). Total num frames: 167247872. Throughput: 0: 1606.3, 1: 1573.6. Samples: 41820768. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:42:10,201][77203] Avg episode reward: [(0, '52.450'), (1, '46.930')] -[2023-10-12 06:42:11,837][78091] Updated weights for policy 0, policy_version 81860 (0.0008) -[2023-10-12 06:42:12,227][78091] Updated weights for policy 0, policy_version 81870 (0.0007) -[2023-10-12 06:42:12,599][78091] Updated weights for policy 0, policy_version 81880 (0.0007) -[2023-10-12 06:42:13,385][78123] Updated weights for policy 1, policy_version 81480 (0.0009) -[2023-10-12 06:42:13,759][78123] Updated weights for policy 1, policy_version 81490 (0.0008) -[2023-10-12 06:42:14,128][78123] Updated weights for policy 1, policy_version 81500 (0.0010) -[2023-10-12 06:42:15,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 167313408. Throughput: 0: 1610.0, 1: 1601.0. Samples: 41830670. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:42:15,201][77203] Avg episode reward: [(0, '49.750'), (1, '52.230')] -[2023-10-12 06:42:16,925][78091] Updated weights for policy 0, policy_version 81890 (0.0007) -[2023-10-12 06:42:17,291][78091] Updated weights for policy 0, policy_version 81900 (0.0007) -[2023-10-12 06:42:17,660][78091] Updated weights for policy 0, policy_version 81910 (0.0009) -[2023-10-12 06:42:18,033][78091] Updated weights for policy 0, policy_version 81920 (0.0007) -[2023-10-12 06:42:18,274][78123] Updated weights for policy 1, policy_version 81510 (0.0008) -[2023-10-12 06:42:18,646][78123] Updated weights for policy 1, policy_version 81520 (0.0010) -[2023-10-12 06:42:19,013][78123] Updated weights for policy 1, policy_version 81530 (0.0009) -[2023-10-12 06:42:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 167378944. Throughput: 0: 1607.1, 1: 1597.3. Samples: 41849756. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:42:20,201][77203] Avg episode reward: [(0, '55.540'), (1, '47.280')] -[2023-10-12 06:42:22,448][78091] Updated weights for policy 0, policy_version 81930 (0.0009) -[2023-10-12 06:42:22,822][78091] Updated weights for policy 0, policy_version 81940 (0.0007) -[2023-10-12 06:42:23,194][78091] Updated weights for policy 0, policy_version 81950 (0.0007) -[2023-10-12 06:42:23,257][78123] Updated weights for policy 1, policy_version 81540 (0.0007) -[2023-10-12 06:42:23,619][78123] Updated weights for policy 1, policy_version 81550 (0.0009) -[2023-10-12 06:42:23,986][78123] Updated weights for policy 1, policy_version 81560 (0.0008) -[2023-10-12 06:42:25,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 167444480. Throughput: 0: 1607.3, 1: 1586.4. Samples: 41868702. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:42:25,202][77203] Avg episode reward: [(0, '46.470'), (1, '39.520')] -[2023-10-12 06:42:27,452][78091] Updated weights for policy 0, policy_version 81960 (0.0008) -[2023-10-12 06:42:27,824][78091] Updated weights for policy 0, policy_version 81970 (0.0007) -[2023-10-12 06:42:28,204][78091] Updated weights for policy 0, policy_version 81980 (0.0007) -[2023-10-12 06:42:28,234][78123] Updated weights for policy 1, policy_version 81570 (0.0009) -[2023-10-12 06:42:28,598][78123] Updated weights for policy 1, policy_version 81580 (0.0009) -[2023-10-12 06:42:28,965][78123] Updated weights for policy 1, policy_version 81590 (0.0008) -[2023-10-12 06:42:29,326][78123] Updated weights for policy 1, policy_version 81600 (0.0008) -[2023-10-12 06:42:30,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 167510016. Throughput: 0: 1620.9, 1: 1605.3. Samples: 41879144. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:42:30,201][77203] Avg episode reward: [(0, '55.880'), (1, '42.100')] -[2023-10-12 06:42:32,509][78091] Updated weights for policy 0, policy_version 81990 (0.0009) -[2023-10-12 06:42:32,883][78091] Updated weights for policy 0, policy_version 82000 (0.0008) -[2023-10-12 06:42:33,245][78091] Updated weights for policy 0, policy_version 82010 (0.0010) -[2023-10-12 06:42:33,984][78123] Updated weights for policy 1, policy_version 81610 (0.0009) -[2023-10-12 06:42:34,354][78123] Updated weights for policy 1, policy_version 81620 (0.0008) -[2023-10-12 06:42:34,726][78123] Updated weights for policy 1, policy_version 81630 (0.0008) -[2023-10-12 06:42:35,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 167575552. Throughput: 0: 1605.3, 1: 1611.8. Samples: 41897860. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:42:35,202][77203] Avg episode reward: [(0, '54.160'), (1, '46.620')] -[2023-10-12 06:42:37,672][78091] Updated weights for policy 0, policy_version 82020 (0.0008) -[2023-10-12 06:42:38,040][78091] Updated weights for policy 0, policy_version 82030 (0.0009) -[2023-10-12 06:42:38,414][78091] Updated weights for policy 0, policy_version 82040 (0.0010) -[2023-10-12 06:42:39,118][78123] Updated weights for policy 1, policy_version 81640 (0.0010) -[2023-10-12 06:42:39,483][78123] Updated weights for policy 1, policy_version 81650 (0.0008) -[2023-10-12 06:42:39,841][78123] Updated weights for policy 1, policy_version 81660 (0.0007) -[2023-10-12 06:42:40,201][77203] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 167641088. Throughput: 0: 1601.9, 1: 1590.4. Samples: 41916530. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:42:40,202][77203] Avg episode reward: [(0, '55.960'), (1, '52.560')] -[2023-10-12 06:42:42,416][78091] Updated weights for policy 0, policy_version 82050 (0.0010) -[2023-10-12 06:42:42,781][78091] Updated weights for policy 0, policy_version 82060 (0.0008) -[2023-10-12 06:42:43,158][78091] Updated weights for policy 0, policy_version 82070 (0.0008) -[2023-10-12 06:42:43,531][78091] Updated weights for policy 0, policy_version 82080 (0.0009) -[2023-10-12 06:42:44,357][78123] Updated weights for policy 1, policy_version 81670 (0.0009) -[2023-10-12 06:42:44,731][78123] Updated weights for policy 1, policy_version 81680 (0.0007) -[2023-10-12 06:42:45,103][78123] Updated weights for policy 1, policy_version 81690 (0.0008) -[2023-10-12 06:42:45,201][77203] Fps is (10 sec: 9830.6, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 167673856. Throughput: 0: 1620.5, 1: 1584.0. Samples: 41926856. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:42:45,201][77203] Avg episode reward: [(0, '54.050'), (1, '57.470')] -[2023-10-12 06:42:47,886][78091] Updated weights for policy 0, policy_version 82090 (0.0009) -[2023-10-12 06:42:48,263][78091] Updated weights for policy 0, policy_version 82100 (0.0009) -[2023-10-12 06:42:48,627][78091] Updated weights for policy 0, policy_version 82110 (0.0011) -[2023-10-12 06:42:49,049][78123] Updated weights for policy 1, policy_version 81700 (0.0007) -[2023-10-12 06:42:49,428][78123] Updated weights for policy 1, policy_version 81710 (0.0009) -[2023-10-12 06:42:49,786][78123] Updated weights for policy 1, policy_version 81720 (0.0009) -[2023-10-12 06:42:50,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 167772160. Throughput: 0: 1599.0, 1: 1602.4. Samples: 41945598. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:42:50,201][77203] Avg episode reward: [(0, '56.790'), (1, '56.980')] -[2023-10-12 06:42:52,917][78091] Updated weights for policy 0, policy_version 82120 (0.0007) -[2023-10-12 06:42:53,283][78091] Updated weights for policy 0, policy_version 82130 (0.0009) -[2023-10-12 06:42:53,663][78091] Updated weights for policy 0, policy_version 82140 (0.0007) -[2023-10-12 06:42:54,255][78123] Updated weights for policy 1, policy_version 81730 (0.0008) -[2023-10-12 06:42:54,658][78123] Updated weights for policy 1, policy_version 81740 (0.0009) -[2023-10-12 06:42:55,013][78123] Updated weights for policy 1, policy_version 81750 (0.0008) -[2023-10-12 06:42:55,201][77203] Fps is (10 sec: 13106.8, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 167804928. Throughput: 0: 1595.7, 1: 1601.7. Samples: 41964652. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-12 06:42:55,202][77203] Avg episode reward: [(0, '54.910'), (1, '55.230')] -[2023-10-12 06:42:55,376][78123] Updated weights for policy 1, policy_version 81760 (0.0008) -[2023-10-12 06:42:58,083][78091] Updated weights for policy 0, policy_version 82150 (0.0009) -[2023-10-12 06:42:58,460][78091] Updated weights for policy 0, policy_version 82160 (0.0011) -[2023-10-12 06:42:58,832][78091] Updated weights for policy 0, policy_version 82170 (0.0008) -[2023-10-12 06:42:59,669][78123] Updated weights for policy 1, policy_version 81770 (0.0008) -[2023-10-12 06:43:00,027][78123] Updated weights for policy 1, policy_version 81780 (0.0009) -[2023-10-12 06:43:00,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 167870464. Throughput: 0: 1619.2, 1: 1586.2. Samples: 41974914. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-12 06:43:00,201][77203] Avg episode reward: [(0, '57.750'), (1, '57.320')] -[2023-10-12 06:43:00,389][78123] Updated weights for policy 1, policy_version 81790 (0.0008) -[2023-10-12 06:43:03,109][78091] Updated weights for policy 0, policy_version 82180 (0.0008) -[2023-10-12 06:43:03,475][78091] Updated weights for policy 0, policy_version 82190 (0.0010) -[2023-10-12 06:43:03,848][78091] Updated weights for policy 0, policy_version 82200 (0.0008) -[2023-10-12 06:43:04,647][78123] Updated weights for policy 1, policy_version 81800 (0.0007) -[2023-10-12 06:43:05,020][78123] Updated weights for policy 1, policy_version 81810 (0.0009) -[2023-10-12 06:43:05,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 167936000. Throughput: 0: 1605.9, 1: 1595.6. Samples: 41993826. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-12 06:43:05,201][77203] Avg episode reward: [(0, '54.450'), (1, '54.900')] -[2023-10-12 06:43:05,379][78123] Updated weights for policy 1, policy_version 81820 (0.0010) -[2023-10-12 06:43:08,056][78091] Updated weights for policy 0, policy_version 82210 (0.0007) -[2023-10-12 06:43:08,419][78091] Updated weights for policy 0, policy_version 82220 (0.0010) -[2023-10-12 06:43:08,799][78091] Updated weights for policy 0, policy_version 82230 (0.0010) -[2023-10-12 06:43:09,166][78091] Updated weights for policy 0, policy_version 82240 (0.0009) -[2023-10-12 06:43:09,542][78123] Updated weights for policy 1, policy_version 81830 (0.0008) -[2023-10-12 06:43:09,907][78123] Updated weights for policy 1, policy_version 81840 (0.0010) -[2023-10-12 06:43:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 168001536. Throughput: 0: 1601.9, 1: 1597.8. Samples: 42012688. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-12 06:43:10,201][77203] Avg episode reward: [(0, '60.220'), (1, '50.590')] -[2023-10-12 06:43:10,207][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000082240_84213760.pth... -[2023-10-12 06:43:10,236][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000080736_82673664.pth -[2023-10-12 06:43:10,240][77792] Saving a milestone ./train_atari/atari_hero_APPO/checkpoint_p0/milestones/checkpoint_000082240_84213760.pth -[2023-10-12 06:43:10,280][78123] Updated weights for policy 1, policy_version 81850 (0.0011) -[2023-10-12 06:43:10,501][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000081856_83820544.pth... -[2023-10-12 06:43:10,529][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000080352_82280448.pth -[2023-10-12 06:43:10,533][77950] Saving a milestone ./train_atari/atari_hero_APPO/checkpoint_p1/milestones/checkpoint_000081856_83820544.pth -[2023-10-12 06:43:13,474][78091] Updated weights for policy 0, policy_version 82250 (0.0009) -[2023-10-12 06:43:13,853][78091] Updated weights for policy 0, policy_version 82260 (0.0008) -[2023-10-12 06:43:14,217][78091] Updated weights for policy 0, policy_version 82270 (0.0009) -[2023-10-12 06:43:14,625][78123] Updated weights for policy 1, policy_version 81860 (0.0009) -[2023-10-12 06:43:14,993][78123] Updated weights for policy 1, policy_version 81870 (0.0009) -[2023-10-12 06:43:15,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 168067072. Throughput: 0: 1612.1, 1: 1577.0. Samples: 42022654. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-12 06:43:15,201][77203] Avg episode reward: [(0, '65.290'), (1, '52.790')] -[2023-10-12 06:43:15,359][78123] Updated weights for policy 1, policy_version 81880 (0.0011) -[2023-10-12 06:43:18,454][78091] Updated weights for policy 0, policy_version 82280 (0.0007) -[2023-10-12 06:43:18,819][78091] Updated weights for policy 0, policy_version 82290 (0.0008) -[2023-10-12 06:43:19,195][78091] Updated weights for policy 0, policy_version 82300 (0.0007) -[2023-10-12 06:43:19,758][78123] Updated weights for policy 1, policy_version 81890 (0.0009) -[2023-10-12 06:43:20,134][78123] Updated weights for policy 1, policy_version 81900 (0.0009) -[2023-10-12 06:43:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 168132608. Throughput: 0: 1611.9, 1: 1582.5. Samples: 42041604. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-12 06:43:20,201][77203] Avg episode reward: [(0, '54.560'), (1, '47.960')] -[2023-10-12 06:43:20,492][78123] Updated weights for policy 1, policy_version 81910 (0.0008) -[2023-10-12 06:43:20,856][78123] Updated weights for policy 1, policy_version 81920 (0.0009) -[2023-10-12 06:43:23,479][78091] Updated weights for policy 0, policy_version 82310 (0.0009) -[2023-10-12 06:43:23,856][78091] Updated weights for policy 0, policy_version 82320 (0.0010) -[2023-10-12 06:43:24,225][78091] Updated weights for policy 0, policy_version 82330 (0.0010) -[2023-10-12 06:43:25,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 168198144. Throughput: 0: 1600.9, 1: 1607.2. Samples: 42060894. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-12 06:43:25,202][77203] Avg episode reward: [(0, '57.810'), (1, '47.540')] -[2023-10-12 06:43:25,273][78123] Updated weights for policy 1, policy_version 81930 (0.0007) -[2023-10-12 06:43:25,631][78123] Updated weights for policy 1, policy_version 81940 (0.0007) -[2023-10-12 06:43:26,010][78123] Updated weights for policy 1, policy_version 81950 (0.0009) -[2023-10-12 06:43:28,559][78091] Updated weights for policy 0, policy_version 82340 (0.0009) -[2023-10-12 06:43:28,931][78091] Updated weights for policy 0, policy_version 82350 (0.0009) -[2023-10-12 06:43:29,297][78091] Updated weights for policy 0, policy_version 82360 (0.0010) -[2023-10-12 06:43:30,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 168263680. Throughput: 0: 1603.7, 1: 1590.7. Samples: 42070602. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-12 06:43:30,201][77203] Avg episode reward: [(0, '55.180'), (1, '44.800')] -[2023-10-12 06:43:30,296][78123] Updated weights for policy 1, policy_version 81960 (0.0010) -[2023-10-12 06:43:30,657][78123] Updated weights for policy 1, policy_version 81970 (0.0007) -[2023-10-12 06:43:31,023][78123] Updated weights for policy 1, policy_version 81980 (0.0009) -[2023-10-12 06:43:33,651][78091] Updated weights for policy 0, policy_version 82370 (0.0007) -[2023-10-12 06:43:34,020][78091] Updated weights for policy 0, policy_version 82380 (0.0007) -[2023-10-12 06:43:34,390][78091] Updated weights for policy 0, policy_version 82390 (0.0007) -[2023-10-12 06:43:34,769][78091] Updated weights for policy 0, policy_version 82400 (0.0008) -[2023-10-12 06:43:35,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 168329216. Throughput: 0: 1620.5, 1: 1593.1. Samples: 42090212. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-12 06:43:35,202][77203] Avg episode reward: [(0, '58.090'), (1, '46.200')] -[2023-10-12 06:43:35,432][78123] Updated weights for policy 1, policy_version 81990 (0.0010) -[2023-10-12 06:43:35,791][78123] Updated weights for policy 1, policy_version 82000 (0.0010) -[2023-10-12 06:43:36,155][78123] Updated weights for policy 1, policy_version 82010 (0.0011) -[2023-10-12 06:43:38,884][78091] Updated weights for policy 0, policy_version 82410 (0.0009) -[2023-10-12 06:43:39,259][78091] Updated weights for policy 0, policy_version 82420 (0.0008) -[2023-10-12 06:43:39,631][78091] Updated weights for policy 0, policy_version 82430 (0.0008) -[2023-10-12 06:43:40,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 168394752. Throughput: 0: 1602.9, 1: 1601.3. Samples: 42108840. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-12 06:43:40,202][77203] Avg episode reward: [(0, '55.590'), (1, '49.770')] -[2023-10-12 06:43:40,547][78123] Updated weights for policy 1, policy_version 82020 (0.0009) -[2023-10-12 06:43:40,939][78123] Updated weights for policy 1, policy_version 82030 (0.0009) -[2023-10-12 06:43:41,309][78123] Updated weights for policy 1, policy_version 82040 (0.0008) -[2023-10-12 06:43:43,944][78091] Updated weights for policy 0, policy_version 82440 (0.0009) -[2023-10-12 06:43:44,313][78091] Updated weights for policy 0, policy_version 82450 (0.0007) -[2023-10-12 06:43:44,690][78091] Updated weights for policy 0, policy_version 82460 (0.0008) -[2023-10-12 06:43:45,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 168460288. Throughput: 0: 1602.6, 1: 1587.9. Samples: 42118486. Policy #0 lag: (min: 11.0, avg: 17.0, max: 43.0) -[2023-10-12 06:43:45,202][77203] Avg episode reward: [(0, '47.030'), (1, '49.580')] -[2023-10-12 06:43:45,683][78123] Updated weights for policy 1, policy_version 82050 (0.0009) -[2023-10-12 06:43:46,044][78123] Updated weights for policy 1, policy_version 82060 (0.0009) -[2023-10-12 06:43:46,416][78123] Updated weights for policy 1, policy_version 82070 (0.0009) -[2023-10-12 06:43:46,784][78123] Updated weights for policy 1, policy_version 82080 (0.0011) -[2023-10-12 06:43:49,113][78091] Updated weights for policy 0, policy_version 82470 (0.0010) -[2023-10-12 06:43:49,489][78091] Updated weights for policy 0, policy_version 82480 (0.0009) -[2023-10-12 06:43:49,850][78091] Updated weights for policy 0, policy_version 82490 (0.0008) -[2023-10-12 06:43:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 168525824. Throughput: 0: 1618.1, 1: 1583.9. Samples: 42137918. Policy #0 lag: (min: 11.0, avg: 17.0, max: 43.0) -[2023-10-12 06:43:50,201][77203] Avg episode reward: [(0, '51.660'), (1, '52.240')] -[2023-10-12 06:43:51,286][78123] Updated weights for policy 1, policy_version 82090 (0.0008) -[2023-10-12 06:43:51,649][78123] Updated weights for policy 1, policy_version 82100 (0.0008) -[2023-10-12 06:43:52,020][78123] Updated weights for policy 1, policy_version 82110 (0.0008) -[2023-10-12 06:43:54,083][78091] Updated weights for policy 0, policy_version 82500 (0.0008) -[2023-10-12 06:43:54,454][78091] Updated weights for policy 0, policy_version 82510 (0.0009) -[2023-10-12 06:43:54,829][78091] Updated weights for policy 0, policy_version 82520 (0.0007) -[2023-10-12 06:43:55,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 168591360. Throughput: 0: 1606.3, 1: 1591.7. Samples: 42156598. Policy #0 lag: (min: 11.0, avg: 17.0, max: 43.0) -[2023-10-12 06:43:55,202][77203] Avg episode reward: [(0, '51.250'), (1, '46.550')] -[2023-10-12 06:43:56,217][78123] Updated weights for policy 1, policy_version 82120 (0.0009) -[2023-10-12 06:43:56,583][78123] Updated weights for policy 1, policy_version 82130 (0.0007) -[2023-10-12 06:43:56,949][78123] Updated weights for policy 1, policy_version 82140 (0.0008) -[2023-10-12 06:43:59,125][78091] Updated weights for policy 0, policy_version 82530 (0.0009) -[2023-10-12 06:43:59,499][78091] Updated weights for policy 0, policy_version 82540 (0.0010) -[2023-10-12 06:43:59,869][78091] Updated weights for policy 0, policy_version 82550 (0.0010) -[2023-10-12 06:44:00,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 168624128. Throughput: 0: 1600.7, 1: 1586.6. Samples: 42166082. Policy #0 lag: (min: 11.0, avg: 17.0, max: 43.0) -[2023-10-12 06:44:00,202][77203] Avg episode reward: [(0, '64.390'), (1, '46.300')] -[2023-10-12 06:44:00,247][78091] Updated weights for policy 0, policy_version 82560 (0.0008) -[2023-10-12 06:44:01,195][78123] Updated weights for policy 1, policy_version 82150 (0.0008) -[2023-10-12 06:44:01,568][78123] Updated weights for policy 1, policy_version 82160 (0.0008) -[2023-10-12 06:44:01,942][78123] Updated weights for policy 1, policy_version 82170 (0.0009) -[2023-10-12 06:44:04,442][78091] Updated weights for policy 0, policy_version 82570 (0.0007) -[2023-10-12 06:44:04,813][78091] Updated weights for policy 0, policy_version 82580 (0.0008) -[2023-10-12 06:44:05,190][78091] Updated weights for policy 0, policy_version 82590 (0.0008) -[2023-10-12 06:44:05,201][77203] Fps is (10 sec: 9830.6, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 168689664. Throughput: 0: 1618.2, 1: 1587.3. Samples: 42185852. Policy #0 lag: (min: 11.0, avg: 17.0, max: 43.0) -[2023-10-12 06:44:05,201][77203] Avg episode reward: [(0, '54.060'), (1, '51.520')] -[2023-10-12 06:44:06,340][78123] Updated weights for policy 1, policy_version 82180 (0.0010) -[2023-10-12 06:44:06,694][78123] Updated weights for policy 1, policy_version 82190 (0.0010) -[2023-10-12 06:44:07,068][78123] Updated weights for policy 1, policy_version 82200 (0.0010) -[2023-10-12 06:44:09,390][78091] Updated weights for policy 0, policy_version 82600 (0.0009) -[2023-10-12 06:44:09,757][78091] Updated weights for policy 0, policy_version 82610 (0.0008) -[2023-10-12 06:44:10,128][78091] Updated weights for policy 0, policy_version 82620 (0.0008) -[2023-10-12 06:44:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 168755200. Throughput: 0: 1620.3, 1: 1576.5. Samples: 42204748. Policy #0 lag: (min: 11.0, avg: 17.0, max: 43.0) -[2023-10-12 06:44:10,202][77203] Avg episode reward: [(0, '48.790'), (1, '55.320')] -[2023-10-12 06:44:11,328][78123] Updated weights for policy 1, policy_version 82210 (0.0010) -[2023-10-12 06:44:11,693][78123] Updated weights for policy 1, policy_version 82220 (0.0007) -[2023-10-12 06:44:12,050][78123] Updated weights for policy 1, policy_version 82230 (0.0010) -[2023-10-12 06:44:12,415][78123] Updated weights for policy 1, policy_version 82240 (0.0011) -[2023-10-12 06:44:14,275][78091] Updated weights for policy 0, policy_version 82630 (0.0007) -[2023-10-12 06:44:14,642][78091] Updated weights for policy 0, policy_version 82640 (0.0007) -[2023-10-12 06:44:15,016][78091] Updated weights for policy 0, policy_version 82650 (0.0007) -[2023-10-12 06:44:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 168820736. Throughput: 0: 1612.9, 1: 1577.5. Samples: 42214170. Policy #0 lag: (min: 11.0, avg: 17.0, max: 43.0) -[2023-10-12 06:44:15,201][77203] Avg episode reward: [(0, '55.020'), (1, '51.710')] -[2023-10-12 06:44:16,838][78123] Updated weights for policy 1, policy_version 82250 (0.0010) -[2023-10-12 06:44:17,217][78123] Updated weights for policy 1, policy_version 82260 (0.0011) -[2023-10-12 06:44:17,583][78123] Updated weights for policy 1, policy_version 82270 (0.0008) -[2023-10-12 06:44:19,206][78091] Updated weights for policy 0, policy_version 82660 (0.0008) -[2023-10-12 06:44:19,572][78091] Updated weights for policy 0, policy_version 82670 (0.0007) -[2023-10-12 06:44:19,944][78091] Updated weights for policy 0, policy_version 82680 (0.0007) -[2023-10-12 06:44:20,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 168886272. Throughput: 0: 1622.2, 1: 1574.4. Samples: 42234060. Policy #0 lag: (min: 11.0, avg: 17.0, max: 43.0) -[2023-10-12 06:44:20,201][77203] Avg episode reward: [(0, '59.730'), (1, '51.380')] -[2023-10-12 06:44:21,888][78123] Updated weights for policy 1, policy_version 82280 (0.0008) -[2023-10-12 06:44:22,258][78123] Updated weights for policy 1, policy_version 82290 (0.0007) -[2023-10-12 06:44:22,612][78123] Updated weights for policy 1, policy_version 82300 (0.0009) -[2023-10-12 06:44:24,146][78091] Updated weights for policy 0, policy_version 82690 (0.0008) -[2023-10-12 06:44:24,516][78091] Updated weights for policy 0, policy_version 82700 (0.0007) -[2023-10-12 06:44:24,894][78091] Updated weights for policy 0, policy_version 82710 (0.0007) -[2023-10-12 06:44:25,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 168951808. Throughput: 0: 1624.8, 1: 1580.4. Samples: 42253076. Policy #0 lag: (min: 11.0, avg: 17.0, max: 43.0) -[2023-10-12 06:44:25,202][77203] Avg episode reward: [(0, '57.940'), (1, '54.230')] -[2023-10-12 06:44:25,253][78091] Updated weights for policy 0, policy_version 82720 (0.0010) -[2023-10-12 06:44:26,974][78123] Updated weights for policy 1, policy_version 82310 (0.0009) -[2023-10-12 06:44:27,350][78123] Updated weights for policy 1, policy_version 82320 (0.0008) -[2023-10-12 06:44:27,722][78123] Updated weights for policy 1, policy_version 82330 (0.0008) -[2023-10-12 06:44:29,669][78091] Updated weights for policy 0, policy_version 82730 (0.0007) -[2023-10-12 06:44:30,042][78091] Updated weights for policy 0, policy_version 82740 (0.0008) -[2023-10-12 06:44:30,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 169017344. Throughput: 0: 1614.4, 1: 1588.7. Samples: 42262622. Policy #0 lag: (min: 11.0, avg: 17.0, max: 43.0) -[2023-10-12 06:44:30,202][77203] Avg episode reward: [(0, '62.650'), (1, '54.740')] -[2023-10-12 06:44:30,415][78091] Updated weights for policy 0, policy_version 82750 (0.0009) -[2023-10-12 06:44:31,996][78123] Updated weights for policy 1, policy_version 82340 (0.0007) -[2023-10-12 06:44:32,359][78123] Updated weights for policy 1, policy_version 82350 (0.0007) -[2023-10-12 06:44:32,729][78123] Updated weights for policy 1, policy_version 82360 (0.0008) -[2023-10-12 06:44:34,663][78091] Updated weights for policy 0, policy_version 82760 (0.0008) -[2023-10-12 06:44:35,037][78091] Updated weights for policy 0, policy_version 82770 (0.0007) -[2023-10-12 06:44:35,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 169082880. Throughput: 0: 1616.3, 1: 1587.8. Samples: 42282102. Policy #0 lag: (min: 11.0, avg: 17.0, max: 43.0) -[2023-10-12 06:44:35,202][77203] Avg episode reward: [(0, '58.790'), (1, '57.600')] -[2023-10-12 06:44:35,408][78091] Updated weights for policy 0, policy_version 82780 (0.0007) -[2023-10-12 06:44:37,121][78123] Updated weights for policy 1, policy_version 82370 (0.0009) -[2023-10-12 06:44:37,493][78123] Updated weights for policy 1, policy_version 82380 (0.0007) -[2023-10-12 06:44:37,865][78123] Updated weights for policy 1, policy_version 82390 (0.0010) -[2023-10-12 06:44:38,237][78123] Updated weights for policy 1, policy_version 82400 (0.0009) -[2023-10-12 06:44:39,922][78091] Updated weights for policy 0, policy_version 82790 (0.0007) -[2023-10-12 06:44:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 169148416. Throughput: 0: 1628.0, 1: 1588.4. Samples: 42301336. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:44:40,201][77203] Avg episode reward: [(0, '56.630'), (1, '46.690')] -[2023-10-12 06:44:40,284][78091] Updated weights for policy 0, policy_version 82800 (0.0010) -[2023-10-12 06:44:40,651][78091] Updated weights for policy 0, policy_version 82810 (0.0007) -[2023-10-12 06:44:42,556][78123] Updated weights for policy 1, policy_version 82410 (0.0008) -[2023-10-12 06:44:42,930][78123] Updated weights for policy 1, policy_version 82420 (0.0007) -[2023-10-12 06:44:43,295][78123] Updated weights for policy 1, policy_version 82430 (0.0007) -[2023-10-12 06:44:45,010][78091] Updated weights for policy 0, policy_version 82820 (0.0009) -[2023-10-12 06:44:45,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 169213952. Throughput: 0: 1612.6, 1: 1603.7. Samples: 42310816. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:44:45,202][77203] Avg episode reward: [(0, '64.000'), (1, '44.720')] -[2023-10-12 06:44:45,381][78091] Updated weights for policy 0, policy_version 82830 (0.0009) -[2023-10-12 06:44:45,761][78091] Updated weights for policy 0, policy_version 82840 (0.0009) -[2023-10-12 06:44:47,623][78123] Updated weights for policy 1, policy_version 82440 (0.0009) -[2023-10-12 06:44:47,991][78123] Updated weights for policy 1, policy_version 82450 (0.0011) -[2023-10-12 06:44:48,365][78123] Updated weights for policy 1, policy_version 82460 (0.0010) -[2023-10-12 06:44:49,916][78091] Updated weights for policy 0, policy_version 82850 (0.0008) -[2023-10-12 06:44:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 169279488. Throughput: 0: 1607.7, 1: 1588.1. Samples: 42329664. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:44:50,201][77203] Avg episode reward: [(0, '51.470'), (1, '47.410')] -[2023-10-12 06:44:50,281][78091] Updated weights for policy 0, policy_version 82860 (0.0008) -[2023-10-12 06:44:50,655][78091] Updated weights for policy 0, policy_version 82870 (0.0010) -[2023-10-12 06:44:51,027][78091] Updated weights for policy 0, policy_version 82880 (0.0009) -[2023-10-12 06:44:52,536][78123] Updated weights for policy 1, policy_version 82470 (0.0010) -[2023-10-12 06:44:52,908][78123] Updated weights for policy 1, policy_version 82480 (0.0008) -[2023-10-12 06:44:53,276][78123] Updated weights for policy 1, policy_version 82490 (0.0007) -[2023-10-12 06:44:55,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 169345024. Throughput: 0: 1617.9, 1: 1598.8. Samples: 42349502. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:44:55,202][77203] Avg episode reward: [(0, '50.980'), (1, '52.000')] -[2023-10-12 06:44:55,321][78091] Updated weights for policy 0, policy_version 82890 (0.0009) -[2023-10-12 06:44:55,681][78091] Updated weights for policy 0, policy_version 82900 (0.0009) -[2023-10-12 06:44:56,056][78091] Updated weights for policy 0, policy_version 82910 (0.0011) -[2023-10-12 06:44:57,379][78123] Updated weights for policy 1, policy_version 82500 (0.0008) -[2023-10-12 06:44:57,740][78123] Updated weights for policy 1, policy_version 82510 (0.0010) -[2023-10-12 06:44:58,112][78123] Updated weights for policy 1, policy_version 82520 (0.0009) -[2023-10-12 06:45:00,201][77203] Fps is (10 sec: 13106.7, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 169410560. Throughput: 0: 1599.5, 1: 1615.8. Samples: 42358856. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:45:00,202][77203] Avg episode reward: [(0, '51.410'), (1, '51.790')] -[2023-10-12 06:45:00,324][78091] Updated weights for policy 0, policy_version 82920 (0.0008) -[2023-10-12 06:45:00,698][78091] Updated weights for policy 0, policy_version 82930 (0.0007) -[2023-10-12 06:45:01,056][78091] Updated weights for policy 0, policy_version 82940 (0.0009) -[2023-10-12 06:45:02,479][78123] Updated weights for policy 1, policy_version 82530 (0.0008) -[2023-10-12 06:45:02,854][78123] Updated weights for policy 1, policy_version 82540 (0.0010) -[2023-10-12 06:45:03,213][78123] Updated weights for policy 1, policy_version 82550 (0.0007) -[2023-10-12 06:45:03,578][78123] Updated weights for policy 1, policy_version 82560 (0.0007) -[2023-10-12 06:45:05,173][78091] Updated weights for policy 0, policy_version 82950 (0.0007) -[2023-10-12 06:45:05,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 169476096. Throughput: 0: 1596.5, 1: 1600.3. Samples: 42377914. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:45:05,202][77203] Avg episode reward: [(0, '47.550'), (1, '51.790')] -[2023-10-12 06:45:05,529][78091] Updated weights for policy 0, policy_version 82960 (0.0007) -[2023-10-12 06:45:05,908][78091] Updated weights for policy 0, policy_version 82970 (0.0007) -[2023-10-12 06:45:07,995][78123] Updated weights for policy 1, policy_version 82570 (0.0007) -[2023-10-12 06:45:08,367][78123] Updated weights for policy 1, policy_version 82580 (0.0008) -[2023-10-12 06:45:08,741][78123] Updated weights for policy 1, policy_version 82590 (0.0008) -[2023-10-12 06:45:10,201][77203] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 169541632. Throughput: 0: 1610.6, 1: 1594.6. Samples: 42397312. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:45:10,201][77203] Avg episode reward: [(0, '55.480'), (1, '51.160')] -[2023-10-12 06:45:10,208][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000082592_84574208.pth... -[2023-10-12 06:45:10,243][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000081088_83034112.pth -[2023-10-12 06:45:10,351][78091] Updated weights for policy 0, policy_version 82980 (0.0009) -[2023-10-12 06:45:10,722][78091] Updated weights for policy 0, policy_version 82990 (0.0008) -[2023-10-12 06:45:11,091][78091] Updated weights for policy 0, policy_version 83000 (0.0008) -[2023-10-12 06:45:11,385][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000083008_85000192.pth... -[2023-10-12 06:45:11,415][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000081472_83427328.pth -[2023-10-12 06:45:13,281][78123] Updated weights for policy 1, policy_version 82600 (0.0008) -[2023-10-12 06:45:13,655][78123] Updated weights for policy 1, policy_version 82610 (0.0012) -[2023-10-12 06:45:14,024][78123] Updated weights for policy 1, policy_version 82620 (0.0011) -[2023-10-12 06:45:15,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 169607168. Throughput: 0: 1594.9, 1: 1612.8. Samples: 42406968. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:45:15,201][77203] Avg episode reward: [(0, '51.030'), (1, '50.310')] -[2023-10-12 06:45:15,428][78091] Updated weights for policy 0, policy_version 83010 (0.0007) -[2023-10-12 06:45:15,812][78091] Updated weights for policy 0, policy_version 83020 (0.0007) -[2023-10-12 06:45:16,189][78091] Updated weights for policy 0, policy_version 83030 (0.0008) -[2023-10-12 06:45:16,562][78091] Updated weights for policy 0, policy_version 83040 (0.0008) -[2023-10-12 06:45:18,374][78123] Updated weights for policy 1, policy_version 82630 (0.0008) -[2023-10-12 06:45:18,736][78123] Updated weights for policy 1, policy_version 82640 (0.0007) -[2023-10-12 06:45:19,117][78123] Updated weights for policy 1, policy_version 82650 (0.0011) -[2023-10-12 06:45:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 169672704. Throughput: 0: 1594.8, 1: 1596.9. Samples: 42425726. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:45:20,201][77203] Avg episode reward: [(0, '57.760'), (1, '54.980')] -[2023-10-12 06:45:20,806][78091] Updated weights for policy 0, policy_version 83050 (0.0009) -[2023-10-12 06:45:21,171][78091] Updated weights for policy 0, policy_version 83060 (0.0009) -[2023-10-12 06:45:21,547][78091] Updated weights for policy 0, policy_version 83070 (0.0009) -[2023-10-12 06:45:23,489][78123] Updated weights for policy 1, policy_version 82660 (0.0009) -[2023-10-12 06:45:23,857][78123] Updated weights for policy 1, policy_version 82670 (0.0010) -[2023-10-12 06:45:24,228][78123] Updated weights for policy 1, policy_version 82680 (0.0011) -[2023-10-12 06:45:25,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 169738240. Throughput: 0: 1598.7, 1: 1582.4. Samples: 42444486. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:45:25,202][77203] Avg episode reward: [(0, '51.040'), (1, '55.010')] -[2023-10-12 06:45:25,774][78091] Updated weights for policy 0, policy_version 83080 (0.0008) -[2023-10-12 06:45:26,142][78091] Updated weights for policy 0, policy_version 83090 (0.0008) -[2023-10-12 06:45:26,511][78091] Updated weights for policy 0, policy_version 83100 (0.0008) -[2023-10-12 06:45:28,489][78123] Updated weights for policy 1, policy_version 82690 (0.0008) -[2023-10-12 06:45:28,850][78123] Updated weights for policy 1, policy_version 82700 (0.0009) -[2023-10-12 06:45:29,222][78123] Updated weights for policy 1, policy_version 82710 (0.0009) -[2023-10-12 06:45:29,586][78123] Updated weights for policy 1, policy_version 82720 (0.0007) -[2023-10-12 06:45:30,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 169803776. Throughput: 0: 1595.5, 1: 1595.8. Samples: 42454422. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:45:30,202][77203] Avg episode reward: [(0, '56.320'), (1, '58.100')] -[2023-10-12 06:45:30,860][78091] Updated weights for policy 0, policy_version 83110 (0.0008) -[2023-10-12 06:45:31,237][78091] Updated weights for policy 0, policy_version 83120 (0.0008) -[2023-10-12 06:45:31,606][78091] Updated weights for policy 0, policy_version 83130 (0.0009) -[2023-10-12 06:45:33,901][78123] Updated weights for policy 1, policy_version 82730 (0.0011) -[2023-10-12 06:45:34,276][78123] Updated weights for policy 1, policy_version 82740 (0.0010) -[2023-10-12 06:45:34,635][78123] Updated weights for policy 1, policy_version 82750 (0.0008) -[2023-10-12 06:45:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 169869312. Throughput: 0: 1596.9, 1: 1606.2. Samples: 42473802. Policy #0 lag: (min: 12.0, avg: 16.5, max: 44.0) -[2023-10-12 06:45:35,202][77203] Avg episode reward: [(0, '61.590'), (1, '52.070')] -[2023-10-12 06:45:35,737][78091] Updated weights for policy 0, policy_version 83140 (0.0009) -[2023-10-12 06:45:36,116][78091] Updated weights for policy 0, policy_version 83150 (0.0007) -[2023-10-12 06:45:36,494][78091] Updated weights for policy 0, policy_version 83160 (0.0007) -[2023-10-12 06:45:39,130][78123] Updated weights for policy 1, policy_version 82760 (0.0009) -[2023-10-12 06:45:39,483][78123] Updated weights for policy 1, policy_version 82770 (0.0009) -[2023-10-12 06:45:39,851][78123] Updated weights for policy 1, policy_version 82780 (0.0007) -[2023-10-12 06:45:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 169934848. Throughput: 0: 1594.8, 1: 1581.9. Samples: 42492452. Policy #0 lag: (min: 12.0, avg: 16.5, max: 44.0) -[2023-10-12 06:45:40,202][77203] Avg episode reward: [(0, '56.800'), (1, '46.880')] -[2023-10-12 06:45:40,882][78091] Updated weights for policy 0, policy_version 83170 (0.0010) -[2023-10-12 06:45:41,256][78091] Updated weights for policy 0, policy_version 83180 (0.0008) -[2023-10-12 06:45:41,635][78091] Updated weights for policy 0, policy_version 83190 (0.0009) -[2023-10-12 06:45:41,999][78091] Updated weights for policy 0, policy_version 83200 (0.0007) -[2023-10-12 06:45:44,175][78123] Updated weights for policy 1, policy_version 82790 (0.0007) -[2023-10-12 06:45:44,547][78123] Updated weights for policy 1, policy_version 82800 (0.0009) -[2023-10-12 06:45:44,916][78123] Updated weights for policy 1, policy_version 82810 (0.0009) -[2023-10-12 06:45:45,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.1, 300 sec: 12885.0). Total num frames: 170000384. Throughput: 0: 1596.3, 1: 1581.6. Samples: 42501862. Policy #0 lag: (min: 12.0, avg: 16.5, max: 44.0) -[2023-10-12 06:45:45,202][77203] Avg episode reward: [(0, '52.430'), (1, '44.060')] -[2023-10-12 06:45:46,416][78091] Updated weights for policy 0, policy_version 83210 (0.0008) -[2023-10-12 06:45:46,782][78091] Updated weights for policy 0, policy_version 83220 (0.0009) -[2023-10-12 06:45:47,143][78091] Updated weights for policy 0, policy_version 83230 (0.0007) -[2023-10-12 06:45:49,294][78123] Updated weights for policy 1, policy_version 82820 (0.0009) -[2023-10-12 06:45:49,665][78123] Updated weights for policy 1, policy_version 82830 (0.0008) -[2023-10-12 06:45:50,037][78123] Updated weights for policy 1, policy_version 82840 (0.0008) -[2023-10-12 06:45:50,201][77203] Fps is (10 sec: 9830.6, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 170033152. Throughput: 0: 1588.3, 1: 1594.6. Samples: 42521144. Policy #0 lag: (min: 12.0, avg: 16.5, max: 44.0) -[2023-10-12 06:45:50,201][77203] Avg episode reward: [(0, '54.890'), (1, '48.450')] -[2023-10-12 06:45:51,415][78091] Updated weights for policy 0, policy_version 83240 (0.0008) -[2023-10-12 06:45:51,788][78091] Updated weights for policy 0, policy_version 83250 (0.0007) -[2023-10-12 06:45:52,156][78091] Updated weights for policy 0, policy_version 83260 (0.0009) -[2023-10-12 06:45:54,319][78123] Updated weights for policy 1, policy_version 82850 (0.0008) -[2023-10-12 06:45:54,687][78123] Updated weights for policy 1, policy_version 82860 (0.0008) -[2023-10-12 06:45:55,044][78123] Updated weights for policy 1, policy_version 82870 (0.0008) -[2023-10-12 06:45:55,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 170098688. Throughput: 0: 1590.4, 1: 1588.2. Samples: 42540350. Policy #0 lag: (min: 12.0, avg: 16.5, max: 44.0) -[2023-10-12 06:45:55,202][77203] Avg episode reward: [(0, '54.440'), (1, '50.860')] -[2023-10-12 06:45:55,424][78123] Updated weights for policy 1, policy_version 82880 (0.0008) -[2023-10-12 06:45:56,415][78091] Updated weights for policy 0, policy_version 83270 (0.0008) -[2023-10-12 06:45:56,792][78091] Updated weights for policy 0, policy_version 83280 (0.0010) -[2023-10-12 06:45:57,163][78091] Updated weights for policy 0, policy_version 83290 (0.0010) -[2023-10-12 06:45:59,878][78123] Updated weights for policy 1, policy_version 82890 (0.0009) -[2023-10-12 06:46:00,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 170164224. Throughput: 0: 1590.4, 1: 1578.5. Samples: 42549570. Policy #0 lag: (min: 12.0, avg: 16.5, max: 44.0) -[2023-10-12 06:46:00,201][77203] Avg episode reward: [(0, '55.160'), (1, '51.910')] -[2023-10-12 06:46:00,246][78123] Updated weights for policy 1, policy_version 82900 (0.0008) -[2023-10-12 06:46:00,603][78123] Updated weights for policy 1, policy_version 82910 (0.0008) -[2023-10-12 06:46:01,632][78091] Updated weights for policy 0, policy_version 83300 (0.0010) -[2023-10-12 06:46:02,014][78091] Updated weights for policy 0, policy_version 83310 (0.0007) -[2023-10-12 06:46:02,380][78091] Updated weights for policy 0, policy_version 83320 (0.0007) -[2023-10-12 06:46:04,919][78123] Updated weights for policy 1, policy_version 82920 (0.0008) -[2023-10-12 06:46:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 170229760. Throughput: 0: 1585.8, 1: 1593.5. Samples: 42568794. Policy #0 lag: (min: 12.0, avg: 16.5, max: 44.0) -[2023-10-12 06:46:05,202][77203] Avg episode reward: [(0, '57.970'), (1, '46.620')] -[2023-10-12 06:46:05,289][78123] Updated weights for policy 1, policy_version 82930 (0.0007) -[2023-10-12 06:46:05,649][78123] Updated weights for policy 1, policy_version 82940 (0.0007) -[2023-10-12 06:46:06,765][78091] Updated weights for policy 0, policy_version 83330 (0.0009) -[2023-10-12 06:46:07,138][78091] Updated weights for policy 0, policy_version 83340 (0.0007) -[2023-10-12 06:46:07,516][78091] Updated weights for policy 0, policy_version 83350 (0.0009) -[2023-10-12 06:46:07,894][78091] Updated weights for policy 0, policy_version 83360 (0.0009) -[2023-10-12 06:46:10,141][78123] Updated weights for policy 1, policy_version 82950 (0.0009) -[2023-10-12 06:46:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 170295296. Throughput: 0: 1588.2, 1: 1604.4. Samples: 42588154. Policy #0 lag: (min: 12.0, avg: 16.5, max: 44.0) -[2023-10-12 06:46:10,201][77203] Avg episode reward: [(0, '46.870'), (1, '49.440')] -[2023-10-12 06:46:10,508][78123] Updated weights for policy 1, policy_version 82960 (0.0009) -[2023-10-12 06:46:10,887][78123] Updated weights for policy 1, policy_version 82970 (0.0008) -[2023-10-12 06:46:12,136][78091] Updated weights for policy 0, policy_version 83370 (0.0008) -[2023-10-12 06:46:12,507][78091] Updated weights for policy 0, policy_version 83380 (0.0010) -[2023-10-12 06:46:12,872][78091] Updated weights for policy 0, policy_version 83390 (0.0009) -[2023-10-12 06:46:15,189][78123] Updated weights for policy 1, policy_version 82980 (0.0008) -[2023-10-12 06:46:15,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 170360832. Throughput: 0: 1596.8, 1: 1576.5. Samples: 42597222. Policy #0 lag: (min: 12.0, avg: 16.5, max: 44.0) -[2023-10-12 06:46:15,202][77203] Avg episode reward: [(0, '46.880'), (1, '52.980')] -[2023-10-12 06:46:15,559][78123] Updated weights for policy 1, policy_version 82990 (0.0009) -[2023-10-12 06:46:15,934][78123] Updated weights for policy 1, policy_version 83000 (0.0008) -[2023-10-12 06:46:17,082][78091] Updated weights for policy 0, policy_version 83400 (0.0008) -[2023-10-12 06:46:17,460][78091] Updated weights for policy 0, policy_version 83410 (0.0007) -[2023-10-12 06:46:17,827][78091] Updated weights for policy 0, policy_version 83420 (0.0007) -[2023-10-12 06:46:20,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 170426368. Throughput: 0: 1597.8, 1: 1578.0. Samples: 42616716. Policy #0 lag: (min: 12.0, avg: 16.5, max: 44.0) -[2023-10-12 06:46:20,202][77203] Avg episode reward: [(0, '55.620'), (1, '54.150')] -[2023-10-12 06:46:20,410][78123] Updated weights for policy 1, policy_version 83010 (0.0009) -[2023-10-12 06:46:20,777][78123] Updated weights for policy 1, policy_version 83020 (0.0007) -[2023-10-12 06:46:21,140][78123] Updated weights for policy 1, policy_version 83030 (0.0008) -[2023-10-12 06:46:21,517][78123] Updated weights for policy 1, policy_version 83040 (0.0009) -[2023-10-12 06:46:22,202][78091] Updated weights for policy 0, policy_version 83430 (0.0008) -[2023-10-12 06:46:22,580][78091] Updated weights for policy 0, policy_version 83440 (0.0007) -[2023-10-12 06:46:22,954][78091] Updated weights for policy 0, policy_version 83450 (0.0007) -[2023-10-12 06:46:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 170491904. Throughput: 0: 1594.0, 1: 1596.1. Samples: 42636008. Policy #0 lag: (min: 13.0, avg: 16.4, max: 45.0) -[2023-10-12 06:46:25,202][77203] Avg episode reward: [(0, '61.300'), (1, '54.900')] -[2023-10-12 06:46:25,785][78123] Updated weights for policy 1, policy_version 83050 (0.0009) -[2023-10-12 06:46:26,153][78123] Updated weights for policy 1, policy_version 83060 (0.0008) -[2023-10-12 06:46:26,523][78123] Updated weights for policy 1, policy_version 83070 (0.0007) -[2023-10-12 06:46:27,226][78091] Updated weights for policy 0, policy_version 83460 (0.0009) -[2023-10-12 06:46:27,592][78091] Updated weights for policy 0, policy_version 83470 (0.0008) -[2023-10-12 06:46:27,963][78091] Updated weights for policy 0, policy_version 83480 (0.0007) -[2023-10-12 06:46:30,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 170557440. Throughput: 0: 1610.2, 1: 1577.8. Samples: 42645324. Policy #0 lag: (min: 13.0, avg: 16.4, max: 45.0) -[2023-10-12 06:46:30,202][77203] Avg episode reward: [(0, '57.880'), (1, '48.180')] -[2023-10-12 06:46:30,787][78123] Updated weights for policy 1, policy_version 83080 (0.0009) -[2023-10-12 06:46:31,171][78123] Updated weights for policy 1, policy_version 83090 (0.0010) -[2023-10-12 06:46:31,531][78123] Updated weights for policy 1, policy_version 83100 (0.0009) -[2023-10-12 06:46:32,215][78091] Updated weights for policy 0, policy_version 83490 (0.0008) -[2023-10-12 06:46:32,578][78091] Updated weights for policy 0, policy_version 83500 (0.0011) -[2023-10-12 06:46:32,950][78091] Updated weights for policy 0, policy_version 83510 (0.0008) -[2023-10-12 06:46:33,320][78091] Updated weights for policy 0, policy_version 83520 (0.0008) -[2023-10-12 06:46:35,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 170622976. Throughput: 0: 1604.4, 1: 1581.3. Samples: 42664502. Policy #0 lag: (min: 13.0, avg: 16.4, max: 45.0) -[2023-10-12 06:46:35,201][77203] Avg episode reward: [(0, '57.920'), (1, '48.290')] -[2023-10-12 06:46:35,918][78123] Updated weights for policy 1, policy_version 83110 (0.0008) -[2023-10-12 06:46:36,294][78123] Updated weights for policy 1, policy_version 83120 (0.0007) -[2023-10-12 06:46:36,671][78123] Updated weights for policy 1, policy_version 83130 (0.0007) -[2023-10-12 06:46:37,463][78091] Updated weights for policy 0, policy_version 83530 (0.0008) -[2023-10-12 06:46:37,820][78091] Updated weights for policy 0, policy_version 83540 (0.0008) -[2023-10-12 06:46:38,192][78091] Updated weights for policy 0, policy_version 83550 (0.0007) -[2023-10-12 06:46:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 170688512. Throughput: 0: 1606.3, 1: 1588.0. Samples: 42684092. Policy #0 lag: (min: 13.0, avg: 16.4, max: 45.0) -[2023-10-12 06:46:40,205][77203] Avg episode reward: [(0, '60.420'), (1, '41.430')] -[2023-10-12 06:46:40,963][78123] Updated weights for policy 1, policy_version 83140 (0.0007) -[2023-10-12 06:46:41,328][78123] Updated weights for policy 1, policy_version 83150 (0.0007) -[2023-10-12 06:46:41,691][78123] Updated weights for policy 1, policy_version 83160 (0.0007) -[2023-10-12 06:46:42,486][78091] Updated weights for policy 0, policy_version 83560 (0.0010) -[2023-10-12 06:46:42,862][78091] Updated weights for policy 0, policy_version 83570 (0.0007) -[2023-10-12 06:46:43,232][78091] Updated weights for policy 0, policy_version 83580 (0.0008) -[2023-10-12 06:46:45,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 170754048. Throughput: 0: 1622.0, 1: 1576.9. Samples: 42693524. Policy #0 lag: (min: 13.0, avg: 16.4, max: 45.0) -[2023-10-12 06:46:45,202][77203] Avg episode reward: [(0, '57.580'), (1, '41.290')] -[2023-10-12 06:46:45,814][78123] Updated weights for policy 1, policy_version 83170 (0.0007) -[2023-10-12 06:46:46,194][78123] Updated weights for policy 1, policy_version 83180 (0.0007) -[2023-10-12 06:46:46,554][78123] Updated weights for policy 1, policy_version 83190 (0.0008) -[2023-10-12 06:46:46,920][78123] Updated weights for policy 1, policy_version 83200 (0.0009) -[2023-10-12 06:46:47,566][78091] Updated weights for policy 0, policy_version 83590 (0.0010) -[2023-10-12 06:46:47,934][78091] Updated weights for policy 0, policy_version 83600 (0.0010) -[2023-10-12 06:46:48,309][78091] Updated weights for policy 0, policy_version 83610 (0.0009) -[2023-10-12 06:46:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 170819584. Throughput: 0: 1612.2, 1: 1579.7. Samples: 42712430. Policy #0 lag: (min: 13.0, avg: 16.4, max: 45.0) -[2023-10-12 06:46:50,201][77203] Avg episode reward: [(0, '61.390'), (1, '47.660')] -[2023-10-12 06:46:51,198][78123] Updated weights for policy 1, policy_version 83210 (0.0011) -[2023-10-12 06:46:51,566][78123] Updated weights for policy 1, policy_version 83220 (0.0010) -[2023-10-12 06:46:51,938][78123] Updated weights for policy 1, policy_version 83230 (0.0008) -[2023-10-12 06:46:52,514][78091] Updated weights for policy 0, policy_version 83620 (0.0007) -[2023-10-12 06:46:52,907][78091] Updated weights for policy 0, policy_version 83630 (0.0009) -[2023-10-12 06:46:53,271][78091] Updated weights for policy 0, policy_version 83640 (0.0010) -[2023-10-12 06:46:55,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 170885120. Throughput: 0: 1611.6, 1: 1582.4. Samples: 42731882. Policy #0 lag: (min: 13.0, avg: 16.4, max: 45.0) -[2023-10-12 06:46:55,202][77203] Avg episode reward: [(0, '55.590'), (1, '50.530')] -[2023-10-12 06:46:56,286][78123] Updated weights for policy 1, policy_version 83240 (0.0008) -[2023-10-12 06:46:56,639][78123] Updated weights for policy 1, policy_version 83250 (0.0008) -[2023-10-12 06:46:57,008][78123] Updated weights for policy 1, policy_version 83260 (0.0008) -[2023-10-12 06:46:57,616][78091] Updated weights for policy 0, policy_version 83650 (0.0008) -[2023-10-12 06:46:57,985][78091] Updated weights for policy 0, policy_version 83660 (0.0009) -[2023-10-12 06:46:58,355][78091] Updated weights for policy 0, policy_version 83670 (0.0008) -[2023-10-12 06:46:58,720][78091] Updated weights for policy 0, policy_version 83680 (0.0009) -[2023-10-12 06:47:00,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 170950656. Throughput: 0: 1626.0, 1: 1582.0. Samples: 42741586. Policy #0 lag: (min: 13.0, avg: 16.4, max: 45.0) -[2023-10-12 06:47:00,201][77203] Avg episode reward: [(0, '66.290'), (1, '48.050')] -[2023-10-12 06:47:01,457][78123] Updated weights for policy 1, policy_version 83270 (0.0008) -[2023-10-12 06:47:01,814][78123] Updated weights for policy 1, policy_version 83280 (0.0008) -[2023-10-12 06:47:02,176][78123] Updated weights for policy 1, policy_version 83290 (0.0007) -[2023-10-12 06:47:02,980][78091] Updated weights for policy 0, policy_version 83690 (0.0010) -[2023-10-12 06:47:03,352][78091] Updated weights for policy 0, policy_version 83700 (0.0007) -[2023-10-12 06:47:03,717][78091] Updated weights for policy 0, policy_version 83710 (0.0008) -[2023-10-12 06:47:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 171016192. Throughput: 0: 1606.6, 1: 1591.0. Samples: 42760608. Policy #0 lag: (min: 13.0, avg: 16.4, max: 45.0) -[2023-10-12 06:47:05,201][77203] Avg episode reward: [(0, '52.980'), (1, '48.030')] -[2023-10-12 06:47:06,515][78123] Updated weights for policy 1, policy_version 83300 (0.0008) -[2023-10-12 06:47:06,888][78123] Updated weights for policy 1, policy_version 83310 (0.0009) -[2023-10-12 06:47:07,254][78123] Updated weights for policy 1, policy_version 83320 (0.0008) -[2023-10-12 06:47:07,884][78091] Updated weights for policy 0, policy_version 83720 (0.0010) -[2023-10-12 06:47:08,252][78091] Updated weights for policy 0, policy_version 83730 (0.0011) -[2023-10-12 06:47:08,622][78091] Updated weights for policy 0, policy_version 83740 (0.0010) -[2023-10-12 06:47:10,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 171081728. Throughput: 0: 1609.7, 1: 1593.2. Samples: 42780140. Policy #0 lag: (min: 13.0, avg: 16.4, max: 45.0) -[2023-10-12 06:47:10,202][77203] Avg episode reward: [(0, '58.290'), (1, '48.370')] -[2023-10-12 06:47:10,210][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000083328_85327872.pth... -[2023-10-12 06:47:10,210][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000083744_85753856.pth... -[2023-10-12 06:47:10,252][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000082240_84213760.pth -[2023-10-12 06:47:10,252][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000081856_83820544.pth -[2023-10-12 06:47:11,604][78123] Updated weights for policy 1, policy_version 83330 (0.0007) -[2023-10-12 06:47:11,978][78123] Updated weights for policy 1, policy_version 83340 (0.0010) -[2023-10-12 06:47:12,346][78123] Updated weights for policy 1, policy_version 83350 (0.0010) -[2023-10-12 06:47:12,711][78123] Updated weights for policy 1, policy_version 83360 (0.0008) -[2023-10-12 06:47:12,887][78091] Updated weights for policy 0, policy_version 83750 (0.0010) -[2023-10-12 06:47:13,261][78091] Updated weights for policy 0, policy_version 83760 (0.0009) -[2023-10-12 06:47:13,632][78091] Updated weights for policy 0, policy_version 83770 (0.0010) -[2023-10-12 06:47:15,201][77203] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 171147264. Throughput: 0: 1614.3, 1: 1593.2. Samples: 42789662. Policy #0 lag: (min: 13.0, avg: 16.4, max: 45.0) -[2023-10-12 06:47:15,202][77203] Avg episode reward: [(0, '50.020'), (1, '50.790')] -[2023-10-12 06:47:17,118][78123] Updated weights for policy 1, policy_version 83370 (0.0007) -[2023-10-12 06:47:17,484][78123] Updated weights for policy 1, policy_version 83380 (0.0008) -[2023-10-12 06:47:17,858][78123] Updated weights for policy 1, policy_version 83390 (0.0009) -[2023-10-12 06:47:17,981][78091] Updated weights for policy 0, policy_version 83780 (0.0010) -[2023-10-12 06:47:18,344][78091] Updated weights for policy 0, policy_version 83790 (0.0007) -[2023-10-12 06:47:18,714][78091] Updated weights for policy 0, policy_version 83800 (0.0008) -[2023-10-12 06:47:20,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 171212800. Throughput: 0: 1604.1, 1: 1596.3. Samples: 42808520. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-12 06:47:20,202][77203] Avg episode reward: [(0, '55.790'), (1, '52.880')] -[2023-10-12 06:47:22,002][78123] Updated weights for policy 1, policy_version 83400 (0.0008) -[2023-10-12 06:47:22,379][78123] Updated weights for policy 1, policy_version 83410 (0.0008) -[2023-10-12 06:47:22,746][78123] Updated weights for policy 1, policy_version 83420 (0.0007) -[2023-10-12 06:47:23,173][78091] Updated weights for policy 0, policy_version 83810 (0.0007) -[2023-10-12 06:47:23,539][78091] Updated weights for policy 0, policy_version 83820 (0.0007) -[2023-10-12 06:47:23,910][78091] Updated weights for policy 0, policy_version 83830 (0.0008) -[2023-10-12 06:47:24,277][78091] Updated weights for policy 0, policy_version 83840 (0.0009) -[2023-10-12 06:47:25,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 171278336. Throughput: 0: 1593.4, 1: 1599.8. Samples: 42827786. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-12 06:47:25,201][77203] Avg episode reward: [(0, '56.310'), (1, '52.160')] -[2023-10-12 06:47:27,160][78123] Updated weights for policy 1, policy_version 83430 (0.0010) -[2023-10-12 06:47:27,537][78123] Updated weights for policy 1, policy_version 83440 (0.0009) -[2023-10-12 06:47:27,900][78123] Updated weights for policy 1, policy_version 83450 (0.0009) -[2023-10-12 06:47:28,556][78091] Updated weights for policy 0, policy_version 83850 (0.0010) -[2023-10-12 06:47:28,932][78091] Updated weights for policy 0, policy_version 83860 (0.0009) -[2023-10-12 06:47:29,293][78091] Updated weights for policy 0, policy_version 83870 (0.0010) -[2023-10-12 06:47:30,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 171343872. Throughput: 0: 1608.3, 1: 1604.7. Samples: 42838106. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-12 06:47:30,201][77203] Avg episode reward: [(0, '53.800'), (1, '52.360')] -[2023-10-12 06:47:32,067][78123] Updated weights for policy 1, policy_version 83460 (0.0010) -[2023-10-12 06:47:32,460][78123] Updated weights for policy 1, policy_version 83470 (0.0009) -[2023-10-12 06:47:32,831][78123] Updated weights for policy 1, policy_version 83480 (0.0008) -[2023-10-12 06:47:33,558][78091] Updated weights for policy 0, policy_version 83880 (0.0011) -[2023-10-12 06:47:33,917][78091] Updated weights for policy 0, policy_version 83890 (0.0011) -[2023-10-12 06:47:34,282][78091] Updated weights for policy 0, policy_version 83900 (0.0008) -[2023-10-12 06:47:35,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 171409408. Throughput: 0: 1614.2, 1: 1594.8. Samples: 42856832. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-12 06:47:35,202][77203] Avg episode reward: [(0, '56.610'), (1, '48.400')] -[2023-10-12 06:47:37,269][78123] Updated weights for policy 1, policy_version 83490 (0.0008) -[2023-10-12 06:47:37,630][78123] Updated weights for policy 1, policy_version 83500 (0.0008) -[2023-10-12 06:47:38,001][78123] Updated weights for policy 1, policy_version 83510 (0.0008) -[2023-10-12 06:47:38,361][78123] Updated weights for policy 1, policy_version 83520 (0.0009) -[2023-10-12 06:47:38,677][78091] Updated weights for policy 0, policy_version 83910 (0.0009) -[2023-10-12 06:47:39,060][78091] Updated weights for policy 0, policy_version 83920 (0.0009) -[2023-10-12 06:47:39,430][78091] Updated weights for policy 0, policy_version 83930 (0.0007) -[2023-10-12 06:47:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 171474944. Throughput: 0: 1596.6, 1: 1595.3. Samples: 42875520. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-12 06:47:40,201][77203] Avg episode reward: [(0, '55.130'), (1, '52.640')] -[2023-10-12 06:47:42,779][78123] Updated weights for policy 1, policy_version 83530 (0.0009) -[2023-10-12 06:47:43,140][78123] Updated weights for policy 1, policy_version 83540 (0.0009) -[2023-10-12 06:47:43,513][78123] Updated weights for policy 1, policy_version 83550 (0.0010) -[2023-10-12 06:47:43,650][78091] Updated weights for policy 0, policy_version 83940 (0.0007) -[2023-10-12 06:47:44,018][78091] Updated weights for policy 0, policy_version 83950 (0.0009) -[2023-10-12 06:47:44,387][78091] Updated weights for policy 0, policy_version 83960 (0.0009) -[2023-10-12 06:47:45,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 171540480. Throughput: 0: 1599.3, 1: 1608.7. Samples: 42885946. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-12 06:47:45,202][77203] Avg episode reward: [(0, '62.260'), (1, '54.860')] -[2023-10-12 06:47:47,644][78123] Updated weights for policy 1, policy_version 83560 (0.0010) -[2023-10-12 06:47:48,012][78123] Updated weights for policy 1, policy_version 83570 (0.0009) -[2023-10-12 06:47:48,383][78123] Updated weights for policy 1, policy_version 83580 (0.0011) -[2023-10-12 06:47:48,738][78091] Updated weights for policy 0, policy_version 83970 (0.0009) -[2023-10-12 06:47:49,112][78091] Updated weights for policy 0, policy_version 83980 (0.0008) -[2023-10-12 06:47:49,468][78091] Updated weights for policy 0, policy_version 83990 (0.0010) -[2023-10-12 06:47:49,849][78091] Updated weights for policy 0, policy_version 84000 (0.0009) -[2023-10-12 06:47:50,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 12885.0). Total num frames: 171606016. Throughput: 0: 1615.1, 1: 1582.6. Samples: 42904506. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-12 06:47:50,202][77203] Avg episode reward: [(0, '59.440'), (1, '51.990')] -[2023-10-12 06:47:52,840][78123] Updated weights for policy 1, policy_version 83590 (0.0010) -[2023-10-12 06:47:53,211][78123] Updated weights for policy 1, policy_version 83600 (0.0010) -[2023-10-12 06:47:53,577][78123] Updated weights for policy 1, policy_version 83610 (0.0012) -[2023-10-12 06:47:53,988][78091] Updated weights for policy 0, policy_version 84010 (0.0010) -[2023-10-12 06:47:54,363][78091] Updated weights for policy 0, policy_version 84020 (0.0009) -[2023-10-12 06:47:54,740][78091] Updated weights for policy 0, policy_version 84030 (0.0010) -[2023-10-12 06:47:55,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 171671552. Throughput: 0: 1600.3, 1: 1581.2. Samples: 42923306. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-12 06:47:55,202][77203] Avg episode reward: [(0, '57.060'), (1, '49.760')] -[2023-10-12 06:47:58,045][78123] Updated weights for policy 1, policy_version 83620 (0.0009) -[2023-10-12 06:47:58,417][78123] Updated weights for policy 1, policy_version 83630 (0.0009) -[2023-10-12 06:47:58,779][78123] Updated weights for policy 1, policy_version 83640 (0.0007) -[2023-10-12 06:47:58,833][78091] Updated weights for policy 0, policy_version 84040 (0.0009) -[2023-10-12 06:47:59,200][78091] Updated weights for policy 0, policy_version 84050 (0.0011) -[2023-10-12 06:47:59,569][78091] Updated weights for policy 0, policy_version 84060 (0.0009) -[2023-10-12 06:48:00,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 171737088. Throughput: 0: 1605.3, 1: 1609.4. Samples: 42934322. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-12 06:48:00,201][77203] Avg episode reward: [(0, '56.070'), (1, '49.470')] -[2023-10-12 06:48:03,139][78123] Updated weights for policy 1, policy_version 83650 (0.0008) -[2023-10-12 06:48:03,510][78123] Updated weights for policy 1, policy_version 83660 (0.0008) -[2023-10-12 06:48:03,875][78123] Updated weights for policy 1, policy_version 83670 (0.0008) -[2023-10-12 06:48:03,884][78091] Updated weights for policy 0, policy_version 84070 (0.0008) -[2023-10-12 06:48:04,247][78091] Updated weights for policy 0, policy_version 84080 (0.0008) -[2023-10-12 06:48:04,250][78123] Updated weights for policy 1, policy_version 83680 (0.0009) -[2023-10-12 06:48:04,612][78091] Updated weights for policy 0, policy_version 84090 (0.0010) -[2023-10-12 06:48:05,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 171802624. Throughput: 0: 1623.5, 1: 1591.1. Samples: 42953174. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-12 06:48:05,202][77203] Avg episode reward: [(0, '53.570'), (1, '49.160')] -[2023-10-12 06:48:08,730][78123] Updated weights for policy 1, policy_version 83690 (0.0007) -[2023-10-12 06:48:09,066][78091] Updated weights for policy 0, policy_version 84100 (0.0010) -[2023-10-12 06:48:09,088][78123] Updated weights for policy 1, policy_version 83700 (0.0008) -[2023-10-12 06:48:09,432][78091] Updated weights for policy 0, policy_version 84110 (0.0011) -[2023-10-12 06:48:09,460][78123] Updated weights for policy 1, policy_version 83710 (0.0010) -[2023-10-12 06:48:09,816][78091] Updated weights for policy 0, policy_version 84120 (0.0009) -[2023-10-12 06:48:10,201][77203] Fps is (10 sec: 13106.7, 60 sec: 13107.1, 300 sec: 12885.0). Total num frames: 171868160. Throughput: 0: 1612.7, 1: 1574.3. Samples: 42971198. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:48:10,202][77203] Avg episode reward: [(0, '60.780'), (1, '47.140')] -[2023-10-12 06:48:13,835][78123] Updated weights for policy 1, policy_version 83720 (0.0008) -[2023-10-12 06:48:14,199][78123] Updated weights for policy 1, policy_version 83730 (0.0007) -[2023-10-12 06:48:14,215][78091] Updated weights for policy 0, policy_version 84130 (0.0009) -[2023-10-12 06:48:14,569][78123] Updated weights for policy 1, policy_version 83740 (0.0009) -[2023-10-12 06:48:14,589][78091] Updated weights for policy 0, policy_version 84140 (0.0009) -[2023-10-12 06:48:14,959][78091] Updated weights for policy 0, policy_version 84150 (0.0009) -[2023-10-12 06:48:15,201][77203] Fps is (10 sec: 9830.6, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 171900928. Throughput: 0: 1603.9, 1: 1594.9. Samples: 42982050. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:48:15,201][77203] Avg episode reward: [(0, '55.180'), (1, '47.550')] -[2023-10-12 06:48:15,322][78091] Updated weights for policy 0, policy_version 84160 (0.0011) -[2023-10-12 06:48:18,840][78123] Updated weights for policy 1, policy_version 83750 (0.0008) -[2023-10-12 06:48:19,214][78123] Updated weights for policy 1, policy_version 83760 (0.0009) -[2023-10-12 06:48:19,577][78123] Updated weights for policy 1, policy_version 83770 (0.0007) -[2023-10-12 06:48:19,582][78091] Updated weights for policy 0, policy_version 84170 (0.0007) -[2023-10-12 06:48:19,949][78091] Updated weights for policy 0, policy_version 84180 (0.0009) -[2023-10-12 06:48:20,201][77203] Fps is (10 sec: 9830.8, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 171966464. Throughput: 0: 1608.9, 1: 1601.4. Samples: 43001296. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:48:20,202][77203] Avg episode reward: [(0, '59.920'), (1, '47.910')] -[2023-10-12 06:48:20,316][78091] Updated weights for policy 0, policy_version 84190 (0.0010) -[2023-10-12 06:48:23,739][78123] Updated weights for policy 1, policy_version 83780 (0.0008) -[2023-10-12 06:48:24,102][78123] Updated weights for policy 1, policy_version 83790 (0.0009) -[2023-10-12 06:48:24,468][78123] Updated weights for policy 1, policy_version 83800 (0.0007) -[2023-10-12 06:48:24,636][78091] Updated weights for policy 0, policy_version 84200 (0.0009) -[2023-10-12 06:48:25,009][78091] Updated weights for policy 0, policy_version 84210 (0.0008) -[2023-10-12 06:48:25,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 172032000. Throughput: 0: 1617.9, 1: 1586.3. Samples: 43019708. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:48:25,202][77203] Avg episode reward: [(0, '51.750'), (1, '46.690')] -[2023-10-12 06:48:25,377][78091] Updated weights for policy 0, policy_version 84220 (0.0011) -[2023-10-12 06:48:28,800][78123] Updated weights for policy 1, policy_version 83810 (0.0009) -[2023-10-12 06:48:29,165][78123] Updated weights for policy 1, policy_version 83820 (0.0009) -[2023-10-12 06:48:29,532][78123] Updated weights for policy 1, policy_version 83830 (0.0010) -[2023-10-12 06:48:29,715][78091] Updated weights for policy 0, policy_version 84230 (0.0009) -[2023-10-12 06:48:29,903][78123] Updated weights for policy 1, policy_version 83840 (0.0007) -[2023-10-12 06:48:30,090][78091] Updated weights for policy 0, policy_version 84240 (0.0010) -[2023-10-12 06:48:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 172097536. Throughput: 0: 1601.9, 1: 1593.8. Samples: 43029752. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:48:30,202][77203] Avg episode reward: [(0, '52.730'), (1, '50.470')] -[2023-10-12 06:48:30,457][78091] Updated weights for policy 0, policy_version 84250 (0.0009) -[2023-10-12 06:48:34,096][78123] Updated weights for policy 1, policy_version 83850 (0.0009) -[2023-10-12 06:48:34,460][78123] Updated weights for policy 1, policy_version 83860 (0.0011) -[2023-10-12 06:48:34,708][78091] Updated weights for policy 0, policy_version 84260 (0.0008) -[2023-10-12 06:48:34,831][78123] Updated weights for policy 1, policy_version 83870 (0.0009) -[2023-10-12 06:48:35,086][78091] Updated weights for policy 0, policy_version 84270 (0.0008) -[2023-10-12 06:48:35,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 172163072. Throughput: 0: 1600.5, 1: 1615.8. Samples: 43049236. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:48:35,202][77203] Avg episode reward: [(0, '57.850'), (1, '44.120')] -[2023-10-12 06:48:35,457][78091] Updated weights for policy 0, policy_version 84280 (0.0010) -[2023-10-12 06:48:39,147][78123] Updated weights for policy 1, policy_version 83880 (0.0010) -[2023-10-12 06:48:39,512][78123] Updated weights for policy 1, policy_version 83890 (0.0008) -[2023-10-12 06:48:39,588][78091] Updated weights for policy 0, policy_version 84290 (0.0008) -[2023-10-12 06:48:39,876][78123] Updated weights for policy 1, policy_version 83900 (0.0008) -[2023-10-12 06:48:39,962][78091] Updated weights for policy 0, policy_version 84300 (0.0007) -[2023-10-12 06:48:40,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 172228608. Throughput: 0: 1614.6, 1: 1600.5. Samples: 43067988. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:48:40,202][77203] Avg episode reward: [(0, '49.190'), (1, '48.980')] -[2023-10-12 06:48:40,332][78091] Updated weights for policy 0, policy_version 84310 (0.0009) -[2023-10-12 06:48:40,697][78091] Updated weights for policy 0, policy_version 84320 (0.0010) -[2023-10-12 06:48:44,302][78123] Updated weights for policy 1, policy_version 83910 (0.0008) -[2023-10-12 06:48:44,668][78123] Updated weights for policy 1, policy_version 83920 (0.0008) -[2023-10-12 06:48:45,017][78091] Updated weights for policy 0, policy_version 84330 (0.0007) -[2023-10-12 06:48:45,022][78123] Updated weights for policy 1, policy_version 83930 (0.0009) -[2023-10-12 06:48:45,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 172261376. Throughput: 0: 1595.5, 1: 1588.7. Samples: 43077610. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:48:45,201][77203] Avg episode reward: [(0, '57.220'), (1, '46.460')] -[2023-10-12 06:48:45,387][78091] Updated weights for policy 0, policy_version 84340 (0.0009) -[2023-10-12 06:48:45,754][78091] Updated weights for policy 0, policy_version 84350 (0.0008) -[2023-10-12 06:48:49,420][78123] Updated weights for policy 1, policy_version 83940 (0.0008) -[2023-10-12 06:48:49,792][78123] Updated weights for policy 1, policy_version 83950 (0.0009) -[2023-10-12 06:48:50,034][78091] Updated weights for policy 0, policy_version 84360 (0.0007) -[2023-10-12 06:48:50,153][78123] Updated weights for policy 1, policy_version 83960 (0.0008) -[2023-10-12 06:48:50,201][77203] Fps is (10 sec: 9830.6, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 172326912. Throughput: 0: 1599.4, 1: 1604.1. Samples: 43097332. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:48:50,201][77203] Avg episode reward: [(0, '59.640'), (1, '51.900')] -[2023-10-12 06:48:50,401][78091] Updated weights for policy 0, policy_version 84370 (0.0008) -[2023-10-12 06:48:50,772][78091] Updated weights for policy 0, policy_version 84380 (0.0007) -[2023-10-12 06:48:54,401][78123] Updated weights for policy 1, policy_version 83970 (0.0009) -[2023-10-12 06:48:54,757][78123] Updated weights for policy 1, policy_version 83980 (0.0009) -[2023-10-12 06:48:55,065][78091] Updated weights for policy 0, policy_version 84390 (0.0009) -[2023-10-12 06:48:55,129][78123] Updated weights for policy 1, policy_version 83990 (0.0008) -[2023-10-12 06:48:55,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12014.9, 300 sec: 12774.0). Total num frames: 172392448. Throughput: 0: 1616.5, 1: 1613.1. Samples: 43116530. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:48:55,202][77203] Avg episode reward: [(0, '60.550'), (1, '45.700')] -[2023-10-12 06:48:55,431][78091] Updated weights for policy 0, policy_version 84400 (0.0007) -[2023-10-12 06:48:55,491][78123] Updated weights for policy 1, policy_version 84000 (0.0009) -[2023-10-12 06:48:55,797][78091] Updated weights for policy 0, policy_version 84410 (0.0007) -[2023-10-12 06:48:59,793][78123] Updated weights for policy 1, policy_version 84010 (0.0008) -[2023-10-12 06:49:00,105][78091] Updated weights for policy 0, policy_version 84420 (0.0007) -[2023-10-12 06:49:00,158][78123] Updated weights for policy 1, policy_version 84020 (0.0010) -[2023-10-12 06:49:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 12774.0). Total num frames: 172457984. Throughput: 0: 1595.8, 1: 1595.3. Samples: 43125652. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:49:00,201][77203] Avg episode reward: [(0, '55.890'), (1, '45.080')] -[2023-10-12 06:49:00,467][78091] Updated weights for policy 0, policy_version 84430 (0.0009) -[2023-10-12 06:49:00,521][78123] Updated weights for policy 1, policy_version 84030 (0.0009) -[2023-10-12 06:49:00,849][78091] Updated weights for policy 0, policy_version 84440 (0.0007) -[2023-10-12 06:49:05,099][78123] Updated weights for policy 1, policy_version 84040 (0.0009) -[2023-10-12 06:49:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12015.0, 300 sec: 12774.0). Total num frames: 172523520. Throughput: 0: 1594.7, 1: 1595.9. Samples: 43144874. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:49:05,201][77203] Avg episode reward: [(0, '54.870'), (1, '49.280')] -[2023-10-12 06:49:05,298][78091] Updated weights for policy 0, policy_version 84450 (0.0009) -[2023-10-12 06:49:05,464][78123] Updated weights for policy 1, policy_version 84050 (0.0008) -[2023-10-12 06:49:05,661][78091] Updated weights for policy 0, policy_version 84460 (0.0008) -[2023-10-12 06:49:05,829][78123] Updated weights for policy 1, policy_version 84060 (0.0009) -[2023-10-12 06:49:06,029][78091] Updated weights for policy 0, policy_version 84470 (0.0007) -[2023-10-12 06:49:06,401][78091] Updated weights for policy 0, policy_version 84480 (0.0009) -[2023-10-12 06:49:10,058][78123] Updated weights for policy 1, policy_version 84070 (0.0007) -[2023-10-12 06:49:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12015.0, 300 sec: 12774.0). Total num frames: 172589056. Throughput: 0: 1606.3, 1: 1609.6. Samples: 43164424. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-12 06:49:10,201][77203] Avg episode reward: [(0, '60.660'), (1, '53.800')] -[2023-10-12 06:49:10,209][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000084480_86507520.pth... -[2023-10-12 06:49:10,248][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000083008_85000192.pth -[2023-10-12 06:49:10,424][78123] Updated weights for policy 1, policy_version 84080 (0.0009) -[2023-10-12 06:49:10,757][78091] Updated weights for policy 0, policy_version 84490 (0.0010) -[2023-10-12 06:49:10,793][78123] Updated weights for policy 1, policy_version 84090 (0.0007) -[2023-10-12 06:49:11,006][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000084096_86114304.pth... -[2023-10-12 06:49:11,046][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000082592_84574208.pth -[2023-10-12 06:49:11,132][78091] Updated weights for policy 0, policy_version 84500 (0.0007) -[2023-10-12 06:49:11,501][78091] Updated weights for policy 0, policy_version 84510 (0.0007) -[2023-10-12 06:49:15,082][78123] Updated weights for policy 1, policy_version 84100 (0.0007) -[2023-10-12 06:49:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 172654592. Throughput: 0: 1596.9, 1: 1590.2. Samples: 43173172. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-12 06:49:15,202][77203] Avg episode reward: [(0, '54.920'), (1, '45.760')] -[2023-10-12 06:49:15,452][78123] Updated weights for policy 1, policy_version 84110 (0.0008) -[2023-10-12 06:49:15,737][78091] Updated weights for policy 0, policy_version 84520 (0.0007) -[2023-10-12 06:49:15,828][78123] Updated weights for policy 1, policy_version 84120 (0.0008) -[2023-10-12 06:49:16,105][78091] Updated weights for policy 0, policy_version 84530 (0.0007) -[2023-10-12 06:49:16,476][78091] Updated weights for policy 0, policy_version 84540 (0.0008) -[2023-10-12 06:49:20,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 172720128. Throughput: 0: 1601.2, 1: 1585.5. Samples: 43192636. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-12 06:49:20,202][77203] Avg episode reward: [(0, '65.490'), (1, '51.820')] -[2023-10-12 06:49:20,360][78123] Updated weights for policy 1, policy_version 84130 (0.0008) -[2023-10-12 06:49:20,731][78123] Updated weights for policy 1, policy_version 84140 (0.0008) -[2023-10-12 06:49:20,773][78091] Updated weights for policy 0, policy_version 84550 (0.0007) -[2023-10-12 06:49:21,094][78123] Updated weights for policy 1, policy_version 84150 (0.0008) -[2023-10-12 06:49:21,139][78091] Updated weights for policy 0, policy_version 84560 (0.0007) -[2023-10-12 06:49:21,462][78123] Updated weights for policy 1, policy_version 84160 (0.0008) -[2023-10-12 06:49:21,504][78091] Updated weights for policy 0, policy_version 84570 (0.0008) -[2023-10-12 06:49:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 172785664. Throughput: 0: 1603.4, 1: 1600.2. Samples: 43212150. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-12 06:49:25,202][77203] Avg episode reward: [(0, '56.670'), (1, '49.620')] -[2023-10-12 06:49:25,661][78123] Updated weights for policy 1, policy_version 84170 (0.0010) -[2023-10-12 06:49:25,800][78091] Updated weights for policy 0, policy_version 84580 (0.0010) -[2023-10-12 06:49:26,026][78123] Updated weights for policy 1, policy_version 84180 (0.0010) -[2023-10-12 06:49:26,175][78091] Updated weights for policy 0, policy_version 84590 (0.0008) -[2023-10-12 06:49:26,400][78123] Updated weights for policy 1, policy_version 84190 (0.0009) -[2023-10-12 06:49:26,543][78091] Updated weights for policy 0, policy_version 84600 (0.0008) -[2023-10-12 06:49:30,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 172851200. Throughput: 0: 1596.1, 1: 1580.8. Samples: 43220574. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-12 06:49:30,202][77203] Avg episode reward: [(0, '53.780'), (1, '45.740')] -[2023-10-12 06:49:30,755][78123] Updated weights for policy 1, policy_version 84200 (0.0010) -[2023-10-12 06:49:30,920][78091] Updated weights for policy 0, policy_version 84610 (0.0008) -[2023-10-12 06:49:31,121][78123] Updated weights for policy 1, policy_version 84210 (0.0008) -[2023-10-12 06:49:31,293][78091] Updated weights for policy 0, policy_version 84620 (0.0008) -[2023-10-12 06:49:31,487][78123] Updated weights for policy 1, policy_version 84220 (0.0008) -[2023-10-12 06:49:31,667][78091] Updated weights for policy 0, policy_version 84630 (0.0009) -[2023-10-12 06:49:32,038][78091] Updated weights for policy 0, policy_version 84640 (0.0007) -[2023-10-12 06:49:35,201][77203] Fps is (10 sec: 13106.8, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 172916736. Throughput: 0: 1593.5, 1: 1578.1. Samples: 43240056. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-12 06:49:35,203][77203] Avg episode reward: [(0, '56.670'), (1, '48.490')] -[2023-10-12 06:49:35,912][78123] Updated weights for policy 1, policy_version 84230 (0.0009) -[2023-10-12 06:49:36,170][78091] Updated weights for policy 0, policy_version 84650 (0.0008) -[2023-10-12 06:49:36,278][78123] Updated weights for policy 1, policy_version 84240 (0.0009) -[2023-10-12 06:49:36,553][78091] Updated weights for policy 0, policy_version 84660 (0.0007) -[2023-10-12 06:49:36,646][78123] Updated weights for policy 1, policy_version 84250 (0.0007) -[2023-10-12 06:49:36,932][78091] Updated weights for policy 0, policy_version 84670 (0.0008) -[2023-10-12 06:49:40,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 172982272. Throughput: 0: 1590.8, 1: 1584.8. Samples: 43259432. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-12 06:49:40,201][77203] Avg episode reward: [(0, '54.820'), (1, '51.430')] -[2023-10-12 06:49:40,874][78123] Updated weights for policy 1, policy_version 84260 (0.0010) -[2023-10-12 06:49:41,246][78123] Updated weights for policy 1, policy_version 84270 (0.0009) -[2023-10-12 06:49:41,408][78091] Updated weights for policy 0, policy_version 84680 (0.0010) -[2023-10-12 06:49:41,617][78123] Updated weights for policy 1, policy_version 84280 (0.0009) -[2023-10-12 06:49:41,773][78091] Updated weights for policy 0, policy_version 84690 (0.0009) -[2023-10-12 06:49:42,142][78091] Updated weights for policy 0, policy_version 84700 (0.0011) -[2023-10-12 06:49:45,201][77203] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 173047808. Throughput: 0: 1588.7, 1: 1574.7. Samples: 43268006. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-12 06:49:45,201][77203] Avg episode reward: [(0, '57.710'), (1, '54.070')] -[2023-10-12 06:49:45,990][78123] Updated weights for policy 1, policy_version 84290 (0.0007) -[2023-10-12 06:49:46,355][78123] Updated weights for policy 1, policy_version 84300 (0.0010) -[2023-10-12 06:49:46,622][78091] Updated weights for policy 0, policy_version 84710 (0.0008) -[2023-10-12 06:49:46,719][78123] Updated weights for policy 1, policy_version 84310 (0.0008) -[2023-10-12 06:49:46,981][78091] Updated weights for policy 0, policy_version 84720 (0.0007) -[2023-10-12 06:49:47,082][78123] Updated weights for policy 1, policy_version 84320 (0.0007) -[2023-10-12 06:49:47,349][78091] Updated weights for policy 0, policy_version 84730 (0.0007) -[2023-10-12 06:49:50,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 173113344. Throughput: 0: 1590.2, 1: 1576.2. Samples: 43287362. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-12 06:49:50,202][77203] Avg episode reward: [(0, '52.420'), (1, '51.680')] -[2023-10-12 06:49:51,555][78091] Updated weights for policy 0, policy_version 84740 (0.0009) -[2023-10-12 06:49:51,572][78123] Updated weights for policy 1, policy_version 84330 (0.0009) -[2023-10-12 06:49:51,922][78091] Updated weights for policy 0, policy_version 84750 (0.0010) -[2023-10-12 06:49:51,942][78123] Updated weights for policy 1, policy_version 84340 (0.0010) -[2023-10-12 06:49:52,297][78091] Updated weights for policy 0, policy_version 84760 (0.0008) -[2023-10-12 06:49:52,308][78123] Updated weights for policy 1, policy_version 84350 (0.0010) -[2023-10-12 06:49:55,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 173178880. Throughput: 0: 1588.6, 1: 1577.0. Samples: 43306876. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-12 06:49:55,202][77203] Avg episode reward: [(0, '54.540'), (1, '51.050')] -[2023-10-12 06:49:56,530][78123] Updated weights for policy 1, policy_version 84360 (0.0009) -[2023-10-12 06:49:56,717][78091] Updated weights for policy 0, policy_version 84770 (0.0009) -[2023-10-12 06:49:56,891][78123] Updated weights for policy 1, policy_version 84370 (0.0010) -[2023-10-12 06:49:57,127][78091] Updated weights for policy 0, policy_version 84780 (0.0008) -[2023-10-12 06:49:57,268][78123] Updated weights for policy 1, policy_version 84380 (0.0007) -[2023-10-12 06:49:57,506][78091] Updated weights for policy 0, policy_version 84790 (0.0007) -[2023-10-12 06:49:57,871][78091] Updated weights for policy 0, policy_version 84800 (0.0007) -[2023-10-12 06:50:00,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 173244416. Throughput: 0: 1587.2, 1: 1578.0. Samples: 43315602. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-12 06:50:00,201][77203] Avg episode reward: [(0, '61.780'), (1, '46.520')] -[2023-10-12 06:50:01,598][78123] Updated weights for policy 1, policy_version 84390 (0.0009) -[2023-10-12 06:50:01,968][78123] Updated weights for policy 1, policy_version 84400 (0.0008) -[2023-10-12 06:50:02,113][78091] Updated weights for policy 0, policy_version 84810 (0.0010) -[2023-10-12 06:50:02,334][78123] Updated weights for policy 1, policy_version 84410 (0.0008) -[2023-10-12 06:50:02,480][78091] Updated weights for policy 0, policy_version 84820 (0.0008) -[2023-10-12 06:50:02,847][78091] Updated weights for policy 0, policy_version 84830 (0.0009) -[2023-10-12 06:50:05,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 173309952. Throughput: 0: 1584.5, 1: 1582.5. Samples: 43335146. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:50:05,202][77203] Avg episode reward: [(0, '56.490'), (1, '48.930')] -[2023-10-12 06:50:06,730][78123] Updated weights for policy 1, policy_version 84420 (0.0009) -[2023-10-12 06:50:07,100][78123] Updated weights for policy 1, policy_version 84430 (0.0009) -[2023-10-12 06:50:07,330][78091] Updated weights for policy 0, policy_version 84840 (0.0008) -[2023-10-12 06:50:07,458][78123] Updated weights for policy 1, policy_version 84440 (0.0007) -[2023-10-12 06:50:07,700][78091] Updated weights for policy 0, policy_version 84850 (0.0009) -[2023-10-12 06:50:08,071][78091] Updated weights for policy 0, policy_version 84860 (0.0008) -[2023-10-12 06:50:10,201][77203] Fps is (10 sec: 13106.6, 60 sec: 13107.1, 300 sec: 12773.9). Total num frames: 173375488. Throughput: 0: 1583.5, 1: 1579.5. Samples: 43354486. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:50:10,202][77203] Avg episode reward: [(0, '52.120'), (1, '51.130')] -[2023-10-12 06:50:11,925][78123] Updated weights for policy 1, policy_version 84450 (0.0007) -[2023-10-12 06:50:12,293][78123] Updated weights for policy 1, policy_version 84460 (0.0007) -[2023-10-12 06:50:12,425][78091] Updated weights for policy 0, policy_version 84870 (0.0008) -[2023-10-12 06:50:12,665][78123] Updated weights for policy 1, policy_version 84470 (0.0008) -[2023-10-12 06:50:12,793][78091] Updated weights for policy 0, policy_version 84880 (0.0009) -[2023-10-12 06:50:13,025][78123] Updated weights for policy 1, policy_version 84480 (0.0008) -[2023-10-12 06:50:13,152][78091] Updated weights for policy 0, policy_version 84890 (0.0008) -[2023-10-12 06:50:15,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 173441024. Throughput: 0: 1595.4, 1: 1594.1. Samples: 43364102. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:50:15,201][77203] Avg episode reward: [(0, '53.500'), (1, '56.420')] -[2023-10-12 06:50:17,329][78123] Updated weights for policy 1, policy_version 84490 (0.0008) -[2023-10-12 06:50:17,437][78091] Updated weights for policy 0, policy_version 84900 (0.0008) -[2023-10-12 06:50:17,701][78123] Updated weights for policy 1, policy_version 84500 (0.0008) -[2023-10-12 06:50:17,815][78091] Updated weights for policy 0, policy_version 84910 (0.0008) -[2023-10-12 06:50:18,080][78123] Updated weights for policy 1, policy_version 84510 (0.0009) -[2023-10-12 06:50:18,182][78091] Updated weights for policy 0, policy_version 84920 (0.0010) -[2023-10-12 06:50:20,201][77203] Fps is (10 sec: 13107.8, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 173506560. Throughput: 0: 1581.6, 1: 1585.8. Samples: 43382588. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:50:20,201][77203] Avg episode reward: [(0, '57.840'), (1, '53.980')] -[2023-10-12 06:50:22,367][78123] Updated weights for policy 1, policy_version 84520 (0.0008) -[2023-10-12 06:50:22,455][78091] Updated weights for policy 0, policy_version 84930 (0.0009) -[2023-10-12 06:50:22,728][78123] Updated weights for policy 1, policy_version 84530 (0.0008) -[2023-10-12 06:50:22,833][78091] Updated weights for policy 0, policy_version 84940 (0.0008) -[2023-10-12 06:50:23,094][78123] Updated weights for policy 1, policy_version 84540 (0.0008) -[2023-10-12 06:50:23,203][78091] Updated weights for policy 0, policy_version 84950 (0.0008) -[2023-10-12 06:50:23,570][78091] Updated weights for policy 0, policy_version 84960 (0.0009) -[2023-10-12 06:50:25,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 173572096. Throughput: 0: 1586.0, 1: 1584.1. Samples: 43402088. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:50:25,202][77203] Avg episode reward: [(0, '61.090'), (1, '48.370')] -[2023-10-12 06:50:27,509][78123] Updated weights for policy 1, policy_version 84550 (0.0008) -[2023-10-12 06:50:27,872][78123] Updated weights for policy 1, policy_version 84560 (0.0009) -[2023-10-12 06:50:27,921][78091] Updated weights for policy 0, policy_version 84970 (0.0009) -[2023-10-12 06:50:28,243][78123] Updated weights for policy 1, policy_version 84570 (0.0009) -[2023-10-12 06:50:28,286][78091] Updated weights for policy 0, policy_version 84980 (0.0008) -[2023-10-12 06:50:28,654][78091] Updated weights for policy 0, policy_version 84990 (0.0008) -[2023-10-12 06:50:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 173637632. Throughput: 0: 1604.9, 1: 1600.1. Samples: 43412232. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:50:30,201][77203] Avg episode reward: [(0, '61.550'), (1, '54.180')] -[2023-10-12 06:50:32,611][78123] Updated weights for policy 1, policy_version 84580 (0.0007) -[2023-10-12 06:50:32,973][78123] Updated weights for policy 1, policy_version 84590 (0.0007) -[2023-10-12 06:50:33,098][78091] Updated weights for policy 0, policy_version 85000 (0.0008) -[2023-10-12 06:50:33,332][78123] Updated weights for policy 1, policy_version 84600 (0.0008) -[2023-10-12 06:50:33,454][78091] Updated weights for policy 0, policy_version 85010 (0.0007) -[2023-10-12 06:50:33,831][78091] Updated weights for policy 0, policy_version 85020 (0.0008) -[2023-10-12 06:50:35,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.3, 300 sec: 12774.0). Total num frames: 173703168. Throughput: 0: 1587.9, 1: 1585.6. Samples: 43430168. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:50:35,202][77203] Avg episode reward: [(0, '60.350'), (1, '51.840')] -[2023-10-12 06:50:37,799][78123] Updated weights for policy 1, policy_version 84610 (0.0008) -[2023-10-12 06:50:37,908][78091] Updated weights for policy 0, policy_version 85030 (0.0008) -[2023-10-12 06:50:38,207][78123] Updated weights for policy 1, policy_version 84620 (0.0009) -[2023-10-12 06:50:38,283][78091] Updated weights for policy 0, policy_version 85040 (0.0007) -[2023-10-12 06:50:38,568][78123] Updated weights for policy 1, policy_version 84630 (0.0010) -[2023-10-12 06:50:38,650][78091] Updated weights for policy 0, policy_version 85050 (0.0007) -[2023-10-12 06:50:38,922][78123] Updated weights for policy 1, policy_version 84640 (0.0009) -[2023-10-12 06:50:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 173768704. Throughput: 0: 1581.2, 1: 1581.9. Samples: 43449216. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:50:40,201][77203] Avg episode reward: [(0, '56.640'), (1, '47.720')] -[2023-10-12 06:50:43,093][78091] Updated weights for policy 0, policy_version 85060 (0.0007) -[2023-10-12 06:50:43,409][78123] Updated weights for policy 1, policy_version 84650 (0.0007) -[2023-10-12 06:50:43,467][78091] Updated weights for policy 0, policy_version 85070 (0.0007) -[2023-10-12 06:50:43,771][78123] Updated weights for policy 1, policy_version 84660 (0.0008) -[2023-10-12 06:50:43,839][78091] Updated weights for policy 0, policy_version 85080 (0.0007) -[2023-10-12 06:50:44,134][78123] Updated weights for policy 1, policy_version 84670 (0.0008) -[2023-10-12 06:50:45,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 173834240. Throughput: 0: 1606.5, 1: 1601.0. Samples: 43459942. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:50:45,202][77203] Avg episode reward: [(0, '59.060'), (1, '47.390')] -[2023-10-12 06:50:48,091][78123] Updated weights for policy 1, policy_version 84680 (0.0009) -[2023-10-12 06:50:48,245][78091] Updated weights for policy 0, policy_version 85090 (0.0010) -[2023-10-12 06:50:48,448][78123] Updated weights for policy 1, policy_version 84690 (0.0007) -[2023-10-12 06:50:48,607][78091] Updated weights for policy 0, policy_version 85100 (0.0009) -[2023-10-12 06:50:48,814][78123] Updated weights for policy 1, policy_version 84700 (0.0008) -[2023-10-12 06:50:48,976][78091] Updated weights for policy 0, policy_version 85110 (0.0009) -[2023-10-12 06:50:49,346][78091] Updated weights for policy 0, policy_version 85120 (0.0008) -[2023-10-12 06:50:50,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 173899776. Throughput: 0: 1594.0, 1: 1584.8. Samples: 43478196. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:50:50,202][77203] Avg episode reward: [(0, '60.030'), (1, '50.230')] -[2023-10-12 06:50:53,161][78123] Updated weights for policy 1, policy_version 84710 (0.0007) -[2023-10-12 06:50:53,349][78091] Updated weights for policy 0, policy_version 85130 (0.0008) -[2023-10-12 06:50:53,522][78123] Updated weights for policy 1, policy_version 84720 (0.0008) -[2023-10-12 06:50:53,720][78091] Updated weights for policy 0, policy_version 85140 (0.0007) -[2023-10-12 06:50:53,889][78123] Updated weights for policy 1, policy_version 84730 (0.0007) -[2023-10-12 06:50:54,084][78091] Updated weights for policy 0, policy_version 85150 (0.0007) -[2023-10-12 06:50:55,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 173965312. Throughput: 0: 1588.2, 1: 1583.4. Samples: 43497208. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:50:55,202][77203] Avg episode reward: [(0, '63.400'), (1, '52.740')] -[2023-10-12 06:50:58,323][78091] Updated weights for policy 0, policy_version 85160 (0.0007) -[2023-10-12 06:50:58,334][78123] Updated weights for policy 1, policy_version 84740 (0.0008) -[2023-10-12 06:50:58,694][78123] Updated weights for policy 1, policy_version 84750 (0.0010) -[2023-10-12 06:50:58,699][78091] Updated weights for policy 0, policy_version 85170 (0.0007) -[2023-10-12 06:50:59,066][78123] Updated weights for policy 1, policy_version 84760 (0.0009) -[2023-10-12 06:50:59,070][78091] Updated weights for policy 0, policy_version 85180 (0.0007) -[2023-10-12 06:51:00,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 174030848. Throughput: 0: 1604.3, 1: 1595.6. Samples: 43508094. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-12 06:51:00,201][77203] Avg episode reward: [(0, '60.950'), (1, '51.920')] -[2023-10-12 06:51:03,396][78091] Updated weights for policy 0, policy_version 85190 (0.0009) -[2023-10-12 06:51:03,473][78123] Updated weights for policy 1, policy_version 84770 (0.0008) -[2023-10-12 06:51:03,765][78091] Updated weights for policy 0, policy_version 85200 (0.0009) -[2023-10-12 06:51:03,845][78123] Updated weights for policy 1, policy_version 84780 (0.0007) -[2023-10-12 06:51:04,140][78091] Updated weights for policy 0, policy_version 85210 (0.0009) -[2023-10-12 06:51:04,204][78123] Updated weights for policy 1, policy_version 84790 (0.0008) -[2023-10-12 06:51:04,576][78123] Updated weights for policy 1, policy_version 84800 (0.0008) -[2023-10-12 06:51:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 174096384. Throughput: 0: 1604.4, 1: 1599.6. Samples: 43526770. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-12 06:51:05,202][77203] Avg episode reward: [(0, '54.380'), (1, '45.620')] -[2023-10-12 06:51:08,434][78091] Updated weights for policy 0, policy_version 85220 (0.0007) -[2023-10-12 06:51:08,800][78091] Updated weights for policy 0, policy_version 85230 (0.0008) -[2023-10-12 06:51:08,934][78123] Updated weights for policy 1, policy_version 84810 (0.0007) -[2023-10-12 06:51:09,161][78091] Updated weights for policy 0, policy_version 85240 (0.0008) -[2023-10-12 06:51:09,305][78123] Updated weights for policy 1, policy_version 84820 (0.0008) -[2023-10-12 06:51:09,673][78123] Updated weights for policy 1, policy_version 84830 (0.0008) -[2023-10-12 06:51:10,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 174161920. Throughput: 0: 1591.2, 1: 1586.0. Samples: 43545062. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-12 06:51:10,202][77203] Avg episode reward: [(0, '54.800'), (1, '43.540')] -[2023-10-12 06:51:10,214][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000084832_86867968.pth... -[2023-10-12 06:51:10,214][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000085248_87293952.pth... -[2023-10-12 06:51:10,248][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000083744_85753856.pth -[2023-10-12 06:51:10,249][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000083328_85327872.pth -[2023-10-12 06:51:13,540][78091] Updated weights for policy 0, policy_version 85250 (0.0008) -[2023-10-12 06:51:13,905][78091] Updated weights for policy 0, policy_version 85260 (0.0007) -[2023-10-12 06:51:13,992][78123] Updated weights for policy 1, policy_version 84840 (0.0008) -[2023-10-12 06:51:14,276][78091] Updated weights for policy 0, policy_version 85270 (0.0009) -[2023-10-12 06:51:14,344][78123] Updated weights for policy 1, policy_version 84850 (0.0007) -[2023-10-12 06:51:14,641][78091] Updated weights for policy 0, policy_version 85280 (0.0009) -[2023-10-12 06:51:14,717][78123] Updated weights for policy 1, policy_version 84860 (0.0008) -[2023-10-12 06:51:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 174227456. Throughput: 0: 1598.1, 1: 1591.3. Samples: 43555756. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-12 06:51:15,202][77203] Avg episode reward: [(0, '55.210'), (1, '46.120')] -[2023-10-12 06:51:18,953][78123] Updated weights for policy 1, policy_version 84870 (0.0009) -[2023-10-12 06:51:18,990][78091] Updated weights for policy 0, policy_version 85290 (0.0007) -[2023-10-12 06:51:19,318][78123] Updated weights for policy 1, policy_version 84880 (0.0008) -[2023-10-12 06:51:19,360][78091] Updated weights for policy 0, policy_version 85300 (0.0010) -[2023-10-12 06:51:19,683][78123] Updated weights for policy 1, policy_version 84890 (0.0009) -[2023-10-12 06:51:19,718][78091] Updated weights for policy 0, policy_version 85310 (0.0010) -[2023-10-12 06:51:20,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 174292992. Throughput: 0: 1615.6, 1: 1611.1. Samples: 43575370. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-12 06:51:20,202][77203] Avg episode reward: [(0, '58.150'), (1, '50.240')] -[2023-10-12 06:51:23,998][78091] Updated weights for policy 0, policy_version 85320 (0.0008) -[2023-10-12 06:51:24,066][78123] Updated weights for policy 1, policy_version 84900 (0.0009) -[2023-10-12 06:51:24,371][78091] Updated weights for policy 0, policy_version 85330 (0.0008) -[2023-10-12 06:51:24,436][78123] Updated weights for policy 1, policy_version 84910 (0.0008) -[2023-10-12 06:51:24,749][78091] Updated weights for policy 0, policy_version 85340 (0.0009) -[2023-10-12 06:51:24,798][78123] Updated weights for policy 1, policy_version 84920 (0.0010) -[2023-10-12 06:51:25,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 174358528. Throughput: 0: 1605.9, 1: 1599.0. Samples: 43593434. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-12 06:51:25,202][77203] Avg episode reward: [(0, '52.000'), (1, '52.790')] -[2023-10-12 06:51:29,130][78123] Updated weights for policy 1, policy_version 84930 (0.0007) -[2023-10-12 06:51:29,272][78091] Updated weights for policy 0, policy_version 85350 (0.0008) -[2023-10-12 06:51:29,497][78123] Updated weights for policy 1, policy_version 84940 (0.0010) -[2023-10-12 06:51:29,645][78091] Updated weights for policy 0, policy_version 85360 (0.0009) -[2023-10-12 06:51:29,863][78123] Updated weights for policy 1, policy_version 84950 (0.0009) -[2023-10-12 06:51:30,016][78091] Updated weights for policy 0, policy_version 85370 (0.0009) -[2023-10-12 06:51:30,201][77203] Fps is (10 sec: 6553.6, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 174358528. Throughput: 0: 1604.3, 1: 1592.8. Samples: 43603810. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-12 06:51:30,201][77203] Avg episode reward: [(0, '48.690'), (1, '50.400')] -[2023-10-12 06:51:30,223][78123] Updated weights for policy 1, policy_version 84960 (0.0008) -[2023-10-12 06:51:34,314][78091] Updated weights for policy 0, policy_version 85380 (0.0009) -[2023-10-12 06:51:34,392][78123] Updated weights for policy 1, policy_version 84970 (0.0008) -[2023-10-12 06:51:34,675][78091] Updated weights for policy 0, policy_version 85390 (0.0008) -[2023-10-12 06:51:34,746][78123] Updated weights for policy 1, policy_version 84980 (0.0009) -[2023-10-12 06:51:35,048][78091] Updated weights for policy 0, policy_version 85400 (0.0008) -[2023-10-12 06:51:35,110][78123] Updated weights for policy 1, policy_version 84990 (0.0009) -[2023-10-12 06:51:35,201][77203] Fps is (10 sec: 9830.6, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 174456832. Throughput: 0: 1612.7, 1: 1608.0. Samples: 43623130. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-12 06:51:35,202][77203] Avg episode reward: [(0, '58.170'), (1, '50.160')] -[2023-10-12 06:51:39,262][78091] Updated weights for policy 0, policy_version 85410 (0.0007) -[2023-10-12 06:51:39,432][78123] Updated weights for policy 1, policy_version 85000 (0.0009) -[2023-10-12 06:51:39,627][78091] Updated weights for policy 0, policy_version 85420 (0.0007) -[2023-10-12 06:51:39,798][78123] Updated weights for policy 1, policy_version 85010 (0.0007) -[2023-10-12 06:51:39,994][78091] Updated weights for policy 0, policy_version 85430 (0.0007) -[2023-10-12 06:51:40,160][78123] Updated weights for policy 1, policy_version 85020 (0.0007) -[2023-10-12 06:51:40,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 174489600. Throughput: 0: 1604.9, 1: 1601.6. Samples: 43641500. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-12 06:51:40,201][77203] Avg episode reward: [(0, '53.290'), (1, '47.950')] -[2023-10-12 06:51:40,358][78091] Updated weights for policy 0, policy_version 85440 (0.0009) -[2023-10-12 06:51:44,572][78123] Updated weights for policy 1, policy_version 85030 (0.0008) -[2023-10-12 06:51:44,755][78091] Updated weights for policy 0, policy_version 85450 (0.0009) -[2023-10-12 06:51:44,926][78123] Updated weights for policy 1, policy_version 85040 (0.0008) -[2023-10-12 06:51:45,122][78091] Updated weights for policy 0, policy_version 85460 (0.0008) -[2023-10-12 06:51:45,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 174555136. Throughput: 0: 1592.4, 1: 1587.7. Samples: 43651196. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-12 06:51:45,201][77203] Avg episode reward: [(0, '57.930'), (1, '50.280')] -[2023-10-12 06:51:45,297][78123] Updated weights for policy 1, policy_version 85050 (0.0009) -[2023-10-12 06:51:45,485][78091] Updated weights for policy 0, policy_version 85470 (0.0008) -[2023-10-12 06:51:49,524][78123] Updated weights for policy 1, policy_version 85060 (0.0010) -[2023-10-12 06:51:49,896][78123] Updated weights for policy 1, policy_version 85070 (0.0008) -[2023-10-12 06:51:49,900][78091] Updated weights for policy 0, policy_version 85480 (0.0009) -[2023-10-12 06:51:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 174620672. Throughput: 0: 1601.2, 1: 1595.2. Samples: 43670606. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-12 06:51:50,201][77203] Avg episode reward: [(0, '54.060'), (1, '50.290')] -[2023-10-12 06:51:50,264][78123] Updated weights for policy 1, policy_version 85080 (0.0008) -[2023-10-12 06:51:50,274][78091] Updated weights for policy 0, policy_version 85490 (0.0009) -[2023-10-12 06:51:50,645][78091] Updated weights for policy 0, policy_version 85500 (0.0008) -[2023-10-12 06:51:54,650][78123] Updated weights for policy 1, policy_version 85090 (0.0008) -[2023-10-12 06:51:55,016][78123] Updated weights for policy 1, policy_version 85100 (0.0009) -[2023-10-12 06:51:55,086][78091] Updated weights for policy 0, policy_version 85510 (0.0008) -[2023-10-12 06:51:55,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 174686208. Throughput: 0: 1613.4, 1: 1607.7. Samples: 43690010. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-12 06:51:55,202][77203] Avg episode reward: [(0, '51.210'), (1, '50.140')] -[2023-10-12 06:51:55,383][78123] Updated weights for policy 1, policy_version 85110 (0.0009) -[2023-10-12 06:51:55,464][78091] Updated weights for policy 0, policy_version 85520 (0.0008) -[2023-10-12 06:51:55,748][78123] Updated weights for policy 1, policy_version 85120 (0.0009) -[2023-10-12 06:51:55,842][78091] Updated weights for policy 0, policy_version 85530 (0.0008) -[2023-10-12 06:52:00,130][78091] Updated weights for policy 0, policy_version 85540 (0.0008) -[2023-10-12 06:52:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 174751744. Throughput: 0: 1586.8, 1: 1588.5. Samples: 43698644. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-12 06:52:00,201][77203] Avg episode reward: [(0, '56.580'), (1, '52.950')] -[2023-10-12 06:52:00,295][78123] Updated weights for policy 1, policy_version 85130 (0.0009) -[2023-10-12 06:52:00,494][78091] Updated weights for policy 0, policy_version 85550 (0.0009) -[2023-10-12 06:52:00,656][78123] Updated weights for policy 1, policy_version 85140 (0.0008) -[2023-10-12 06:52:00,869][78091] Updated weights for policy 0, policy_version 85560 (0.0009) -[2023-10-12 06:52:01,021][78123] Updated weights for policy 1, policy_version 85150 (0.0008) -[2023-10-12 06:52:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 174817280. Throughput: 0: 1586.4, 1: 1583.6. Samples: 43718020. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-12 06:52:05,202][77203] Avg episode reward: [(0, '61.010'), (1, '48.070')] -[2023-10-12 06:52:05,231][78091] Updated weights for policy 0, policy_version 85570 (0.0010) -[2023-10-12 06:52:05,460][78123] Updated weights for policy 1, policy_version 85160 (0.0007) -[2023-10-12 06:52:05,598][78091] Updated weights for policy 0, policy_version 85580 (0.0007) -[2023-10-12 06:52:05,829][78123] Updated weights for policy 1, policy_version 85170 (0.0008) -[2023-10-12 06:52:05,959][78091] Updated weights for policy 0, policy_version 85590 (0.0007) -[2023-10-12 06:52:06,195][78123] Updated weights for policy 1, policy_version 85180 (0.0008) -[2023-10-12 06:52:06,338][78091] Updated weights for policy 0, policy_version 85600 (0.0008) -[2023-10-12 06:52:10,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 174882816. Throughput: 0: 1598.6, 1: 1603.5. Samples: 43737528. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-12 06:52:10,202][77203] Avg episode reward: [(0, '59.120'), (1, '53.640')] -[2023-10-12 06:52:10,429][78123] Updated weights for policy 1, policy_version 85190 (0.0008) -[2023-10-12 06:52:10,799][78091] Updated weights for policy 0, policy_version 85610 (0.0007) -[2023-10-12 06:52:10,805][78123] Updated weights for policy 1, policy_version 85200 (0.0009) -[2023-10-12 06:52:11,163][78091] Updated weights for policy 0, policy_version 85620 (0.0009) -[2023-10-12 06:52:11,164][78123] Updated weights for policy 1, policy_version 85210 (0.0009) -[2023-10-12 06:52:11,533][78091] Updated weights for policy 0, policy_version 85630 (0.0010) -[2023-10-12 06:52:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 174948352. Throughput: 0: 1573.1, 1: 1584.4. Samples: 43745896. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-12 06:52:15,202][77203] Avg episode reward: [(0, '58.160'), (1, '46.880')] -[2023-10-12 06:52:15,502][78123] Updated weights for policy 1, policy_version 85220 (0.0008) -[2023-10-12 06:52:15,813][78091] Updated weights for policy 0, policy_version 85640 (0.0007) -[2023-10-12 06:52:15,865][78123] Updated weights for policy 1, policy_version 85230 (0.0008) -[2023-10-12 06:52:16,183][78091] Updated weights for policy 0, policy_version 85650 (0.0007) -[2023-10-12 06:52:16,243][78123] Updated weights for policy 1, policy_version 85240 (0.0009) -[2023-10-12 06:52:16,545][78091] Updated weights for policy 0, policy_version 85660 (0.0008) -[2023-10-12 06:52:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 175013888. Throughput: 0: 1575.3, 1: 1589.3. Samples: 43765540. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-12 06:52:20,202][77203] Avg episode reward: [(0, '58.290'), (1, '46.800')] -[2023-10-12 06:52:20,531][78123] Updated weights for policy 1, policy_version 85250 (0.0010) -[2023-10-12 06:52:20,869][78091] Updated weights for policy 0, policy_version 85670 (0.0008) -[2023-10-12 06:52:20,907][78123] Updated weights for policy 1, policy_version 85260 (0.0009) -[2023-10-12 06:52:21,253][78091] Updated weights for policy 0, policy_version 85680 (0.0008) -[2023-10-12 06:52:21,275][78123] Updated weights for policy 1, policy_version 85270 (0.0010) -[2023-10-12 06:52:21,612][78091] Updated weights for policy 0, policy_version 85690 (0.0008) -[2023-10-12 06:52:21,640][78123] Updated weights for policy 1, policy_version 85280 (0.0007) -[2023-10-12 06:52:25,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 175079424. Throughput: 0: 1589.1, 1: 1597.1. Samples: 43784882. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-12 06:52:25,202][77203] Avg episode reward: [(0, '50.980'), (1, '46.780')] -[2023-10-12 06:52:25,794][78123] Updated weights for policy 1, policy_version 85290 (0.0007) -[2023-10-12 06:52:25,967][78091] Updated weights for policy 0, policy_version 85700 (0.0007) -[2023-10-12 06:52:26,158][78123] Updated weights for policy 1, policy_version 85300 (0.0008) -[2023-10-12 06:52:26,335][78091] Updated weights for policy 0, policy_version 85710 (0.0007) -[2023-10-12 06:52:26,524][78123] Updated weights for policy 1, policy_version 85310 (0.0007) -[2023-10-12 06:52:26,703][78091] Updated weights for policy 0, policy_version 85720 (0.0007) -[2023-10-12 06:52:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 175144960. Throughput: 0: 1575.9, 1: 1587.3. Samples: 43793538. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-12 06:52:30,202][77203] Avg episode reward: [(0, '51.360'), (1, '60.530')] -[2023-10-12 06:52:30,919][78091] Updated weights for policy 0, policy_version 85730 (0.0008) -[2023-10-12 06:52:31,090][78123] Updated weights for policy 1, policy_version 85320 (0.0010) -[2023-10-12 06:52:31,282][78091] Updated weights for policy 0, policy_version 85740 (0.0008) -[2023-10-12 06:52:31,456][78123] Updated weights for policy 1, policy_version 85330 (0.0008) -[2023-10-12 06:52:31,657][78091] Updated weights for policy 0, policy_version 85750 (0.0008) -[2023-10-12 06:52:31,820][78123] Updated weights for policy 1, policy_version 85340 (0.0007) -[2023-10-12 06:52:32,021][78091] Updated weights for policy 0, policy_version 85760 (0.0009) -[2023-10-12 06:52:35,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 175210496. Throughput: 0: 1583.3, 1: 1584.5. Samples: 43813158. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-12 06:52:35,201][77203] Avg episode reward: [(0, '57.150'), (1, '44.440')] -[2023-10-12 06:52:36,224][78123] Updated weights for policy 1, policy_version 85350 (0.0009) -[2023-10-12 06:52:36,272][78091] Updated weights for policy 0, policy_version 85770 (0.0007) -[2023-10-12 06:52:36,597][78123] Updated weights for policy 1, policy_version 85360 (0.0009) -[2023-10-12 06:52:36,642][78091] Updated weights for policy 0, policy_version 85780 (0.0008) -[2023-10-12 06:52:36,967][78123] Updated weights for policy 1, policy_version 85370 (0.0010) -[2023-10-12 06:52:37,018][78091] Updated weights for policy 0, policy_version 85790 (0.0008) -[2023-10-12 06:52:40,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.1, 300 sec: 12662.9). Total num frames: 175276032. Throughput: 0: 1586.7, 1: 1583.3. Samples: 43832662. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-12 06:52:40,202][77203] Avg episode reward: [(0, '56.720'), (1, '48.610')] -[2023-10-12 06:52:41,278][78091] Updated weights for policy 0, policy_version 85800 (0.0007) -[2023-10-12 06:52:41,317][78123] Updated weights for policy 1, policy_version 85380 (0.0009) -[2023-10-12 06:52:41,643][78091] Updated weights for policy 0, policy_version 85810 (0.0008) -[2023-10-12 06:52:41,691][78123] Updated weights for policy 1, policy_version 85390 (0.0008) -[2023-10-12 06:52:42,005][78091] Updated weights for policy 0, policy_version 85820 (0.0008) -[2023-10-12 06:52:42,046][78123] Updated weights for policy 1, policy_version 85400 (0.0008) -[2023-10-12 06:52:45,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 175341568. Throughput: 0: 1586.8, 1: 1582.7. Samples: 43841270. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-12 06:52:45,202][77203] Avg episode reward: [(0, '56.880'), (1, '50.830')] -[2023-10-12 06:52:46,189][78123] Updated weights for policy 1, policy_version 85410 (0.0009) -[2023-10-12 06:52:46,375][78091] Updated weights for policy 0, policy_version 85830 (0.0010) -[2023-10-12 06:52:46,551][78123] Updated weights for policy 1, policy_version 85420 (0.0009) -[2023-10-12 06:52:46,732][78091] Updated weights for policy 0, policy_version 85840 (0.0008) -[2023-10-12 06:52:46,906][78123] Updated weights for policy 1, policy_version 85430 (0.0010) -[2023-10-12 06:52:47,116][78091] Updated weights for policy 0, policy_version 85850 (0.0010) -[2023-10-12 06:52:47,272][78123] Updated weights for policy 1, policy_version 85440 (0.0007) -[2023-10-12 06:52:50,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.1, 300 sec: 12662.9). Total num frames: 175407104. Throughput: 0: 1583.4, 1: 1587.5. Samples: 43860710. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-12 06:52:50,202][77203] Avg episode reward: [(0, '57.340'), (1, '55.530')] -[2023-10-12 06:52:51,586][78123] Updated weights for policy 1, policy_version 85450 (0.0007) -[2023-10-12 06:52:51,601][78091] Updated weights for policy 0, policy_version 85860 (0.0010) -[2023-10-12 06:52:51,957][78123] Updated weights for policy 1, policy_version 85460 (0.0007) -[2023-10-12 06:52:51,966][78091] Updated weights for policy 0, policy_version 85870 (0.0009) -[2023-10-12 06:52:52,311][78123] Updated weights for policy 1, policy_version 85470 (0.0007) -[2023-10-12 06:52:52,343][78091] Updated weights for policy 0, policy_version 85880 (0.0008) -[2023-10-12 06:52:55,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 175472640. Throughput: 0: 1585.2, 1: 1587.7. Samples: 43880310. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-12 06:52:55,201][77203] Avg episode reward: [(0, '51.120'), (1, '54.450')] -[2023-10-12 06:52:56,592][78091] Updated weights for policy 0, policy_version 85890 (0.0009) -[2023-10-12 06:52:56,628][78123] Updated weights for policy 1, policy_version 85480 (0.0007) -[2023-10-12 06:52:56,962][78091] Updated weights for policy 0, policy_version 85900 (0.0008) -[2023-10-12 06:52:57,005][78123] Updated weights for policy 1, policy_version 85490 (0.0009) -[2023-10-12 06:52:57,329][78091] Updated weights for policy 0, policy_version 85910 (0.0008) -[2023-10-12 06:52:57,367][78123] Updated weights for policy 1, policy_version 85500 (0.0007) -[2023-10-12 06:52:57,691][78091] Updated weights for policy 0, policy_version 85920 (0.0009) -[2023-10-12 06:53:00,201][77203] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 175538176. Throughput: 0: 1588.8, 1: 1589.3. Samples: 43888912. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-12 06:53:00,202][77203] Avg episode reward: [(0, '62.090'), (1, '61.610')] -[2023-10-12 06:53:01,637][78123] Updated weights for policy 1, policy_version 85510 (0.0008) -[2023-10-12 06:53:02,005][78123] Updated weights for policy 1, policy_version 85520 (0.0007) -[2023-10-12 06:53:02,052][78091] Updated weights for policy 0, policy_version 85930 (0.0008) -[2023-10-12 06:53:02,368][78123] Updated weights for policy 1, policy_version 85530 (0.0008) -[2023-10-12 06:53:02,415][78091] Updated weights for policy 0, policy_version 85940 (0.0010) -[2023-10-12 06:53:02,780][78091] Updated weights for policy 0, policy_version 85950 (0.0010) -[2023-10-12 06:53:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 175603712. Throughput: 0: 1592.0, 1: 1582.3. Samples: 43908386. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-12 06:53:05,201][77203] Avg episode reward: [(0, '56.870'), (1, '59.400')] -[2023-10-12 06:53:06,858][78123] Updated weights for policy 1, policy_version 85540 (0.0009) -[2023-10-12 06:53:06,967][78091] Updated weights for policy 0, policy_version 85960 (0.0008) -[2023-10-12 06:53:07,213][78123] Updated weights for policy 1, policy_version 85550 (0.0009) -[2023-10-12 06:53:07,326][78091] Updated weights for policy 0, policy_version 85970 (0.0007) -[2023-10-12 06:53:07,585][78123] Updated weights for policy 1, policy_version 85560 (0.0008) -[2023-10-12 06:53:07,699][78091] Updated weights for policy 0, policy_version 85980 (0.0008) -[2023-10-12 06:53:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 175669248. Throughput: 0: 1594.2, 1: 1582.2. Samples: 43927820. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-12 06:53:10,202][77203] Avg episode reward: [(0, '57.270'), (1, '52.250')] -[2023-10-12 06:53:10,210][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000085568_87621632.pth... -[2023-10-12 06:53:10,210][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000085984_88047616.pth... -[2023-10-12 06:53:10,263][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000084096_86114304.pth -[2023-10-12 06:53:10,264][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000084480_86507520.pth -[2023-10-12 06:53:11,985][78123] Updated weights for policy 1, policy_version 85570 (0.0008) -[2023-10-12 06:53:12,161][78091] Updated weights for policy 0, policy_version 85990 (0.0008) -[2023-10-12 06:53:12,355][78123] Updated weights for policy 1, policy_version 85580 (0.0009) -[2023-10-12 06:53:12,523][78091] Updated weights for policy 0, policy_version 86000 (0.0008) -[2023-10-12 06:53:12,715][78123] Updated weights for policy 1, policy_version 85590 (0.0009) -[2023-10-12 06:53:12,892][78091] Updated weights for policy 0, policy_version 86010 (0.0007) -[2023-10-12 06:53:13,080][78123] Updated weights for policy 1, policy_version 85600 (0.0008) -[2023-10-12 06:53:15,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 175734784. Throughput: 0: 1600.3, 1: 1593.1. Samples: 43937240. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-12 06:53:15,201][77203] Avg episode reward: [(0, '52.850'), (1, '46.150')] -[2023-10-12 06:53:17,273][78091] Updated weights for policy 0, policy_version 86020 (0.0010) -[2023-10-12 06:53:17,384][78123] Updated weights for policy 1, policy_version 85610 (0.0008) -[2023-10-12 06:53:17,642][78091] Updated weights for policy 0, policy_version 86030 (0.0009) -[2023-10-12 06:53:17,747][78123] Updated weights for policy 1, policy_version 85620 (0.0008) -[2023-10-12 06:53:18,010][78091] Updated weights for policy 0, policy_version 86040 (0.0008) -[2023-10-12 06:53:18,121][78123] Updated weights for policy 1, policy_version 85630 (0.0008) -[2023-10-12 06:53:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 175800320. Throughput: 0: 1587.2, 1: 1584.9. Samples: 43955904. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-12 06:53:20,201][77203] Avg episode reward: [(0, '56.090'), (1, '48.700')] -[2023-10-12 06:53:22,318][78091] Updated weights for policy 0, policy_version 86050 (0.0008) -[2023-10-12 06:53:22,459][78123] Updated weights for policy 1, policy_version 85640 (0.0008) -[2023-10-12 06:53:22,698][78091] Updated weights for policy 0, policy_version 86060 (0.0009) -[2023-10-12 06:53:22,828][78123] Updated weights for policy 1, policy_version 85650 (0.0008) -[2023-10-12 06:53:23,065][78091] Updated weights for policy 0, policy_version 86070 (0.0008) -[2023-10-12 06:53:23,193][78123] Updated weights for policy 1, policy_version 85660 (0.0007) -[2023-10-12 06:53:23,427][78091] Updated weights for policy 0, policy_version 86080 (0.0009) -[2023-10-12 06:53:25,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 175865856. Throughput: 0: 1583.4, 1: 1589.3. Samples: 43975434. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-12 06:53:25,202][77203] Avg episode reward: [(0, '64.860'), (1, '53.950')] -[2023-10-12 06:53:27,450][78123] Updated weights for policy 1, policy_version 85670 (0.0008) -[2023-10-12 06:53:27,736][78091] Updated weights for policy 0, policy_version 86090 (0.0008) -[2023-10-12 06:53:27,812][78123] Updated weights for policy 1, policy_version 85680 (0.0008) -[2023-10-12 06:53:28,096][78091] Updated weights for policy 0, policy_version 86100 (0.0008) -[2023-10-12 06:53:28,173][78123] Updated weights for policy 1, policy_version 85690 (0.0007) -[2023-10-12 06:53:28,470][78091] Updated weights for policy 0, policy_version 86110 (0.0007) -[2023-10-12 06:53:30,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 175931392. Throughput: 0: 1602.9, 1: 1602.9. Samples: 43985534. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-12 06:53:30,201][77203] Avg episode reward: [(0, '55.190'), (1, '47.070')] -[2023-10-12 06:53:32,588][78123] Updated weights for policy 1, policy_version 85700 (0.0009) -[2023-10-12 06:53:32,949][78091] Updated weights for policy 0, policy_version 86120 (0.0009) -[2023-10-12 06:53:32,966][78123] Updated weights for policy 1, policy_version 85710 (0.0010) -[2023-10-12 06:53:33,324][78091] Updated weights for policy 0, policy_version 86130 (0.0009) -[2023-10-12 06:53:33,327][78123] Updated weights for policy 1, policy_version 85720 (0.0008) -[2023-10-12 06:53:33,694][78091] Updated weights for policy 0, policy_version 86140 (0.0008) -[2023-10-12 06:53:35,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 175996928. Throughput: 0: 1592.8, 1: 1581.8. Samples: 44003566. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-12 06:53:35,202][77203] Avg episode reward: [(0, '52.390'), (1, '49.350')] -[2023-10-12 06:53:37,848][78123] Updated weights for policy 1, policy_version 85730 (0.0009) -[2023-10-12 06:53:37,972][78091] Updated weights for policy 0, policy_version 86150 (0.0007) -[2023-10-12 06:53:38,218][78123] Updated weights for policy 1, policy_version 85740 (0.0009) -[2023-10-12 06:53:38,342][78091] Updated weights for policy 0, policy_version 86160 (0.0008) -[2023-10-12 06:53:38,583][78123] Updated weights for policy 1, policy_version 85750 (0.0008) -[2023-10-12 06:53:38,710][78091] Updated weights for policy 0, policy_version 86170 (0.0009) -[2023-10-12 06:53:38,951][78123] Updated weights for policy 1, policy_version 85760 (0.0009) -[2023-10-12 06:53:40,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 176062464. Throughput: 0: 1591.8, 1: 1577.2. Samples: 44022916. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-12 06:53:40,202][77203] Avg episode reward: [(0, '51.920'), (1, '51.130')] -[2023-10-12 06:53:42,869][78091] Updated weights for policy 0, policy_version 86180 (0.0007) -[2023-10-12 06:53:43,231][78091] Updated weights for policy 0, policy_version 86190 (0.0007) -[2023-10-12 06:53:43,406][78123] Updated weights for policy 1, policy_version 85770 (0.0008) -[2023-10-12 06:53:43,609][78091] Updated weights for policy 0, policy_version 86200 (0.0008) -[2023-10-12 06:53:43,772][78123] Updated weights for policy 1, policy_version 85780 (0.0008) -[2023-10-12 06:53:44,135][78123] Updated weights for policy 1, policy_version 85790 (0.0008) -[2023-10-12 06:53:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 176128000. Throughput: 0: 1613.9, 1: 1603.1. Samples: 44033678. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-12 06:53:45,202][77203] Avg episode reward: [(0, '56.780'), (1, '44.160')] -[2023-10-12 06:53:48,081][78091] Updated weights for policy 0, policy_version 86210 (0.0009) -[2023-10-12 06:53:48,476][78123] Updated weights for policy 1, policy_version 85800 (0.0008) -[2023-10-12 06:53:48,477][78091] Updated weights for policy 0, policy_version 86220 (0.0010) -[2023-10-12 06:53:48,846][78123] Updated weights for policy 1, policy_version 85810 (0.0008) -[2023-10-12 06:53:48,855][78091] Updated weights for policy 0, policy_version 86230 (0.0010) -[2023-10-12 06:53:49,206][78123] Updated weights for policy 1, policy_version 85820 (0.0007) -[2023-10-12 06:53:49,220][78091] Updated weights for policy 0, policy_version 86240 (0.0008) -[2023-10-12 06:53:50,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.3, 300 sec: 12885.0). Total num frames: 176193536. Throughput: 0: 1593.8, 1: 1588.6. Samples: 44051592. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:53:50,201][77203] Avg episode reward: [(0, '56.320'), (1, '46.460')] -[2023-10-12 06:53:53,368][78091] Updated weights for policy 0, policy_version 86250 (0.0007) -[2023-10-12 06:53:53,574][78123] Updated weights for policy 1, policy_version 85830 (0.0008) -[2023-10-12 06:53:53,729][78091] Updated weights for policy 0, policy_version 86260 (0.0007) -[2023-10-12 06:53:53,943][78123] Updated weights for policy 1, policy_version 85840 (0.0008) -[2023-10-12 06:53:54,095][78091] Updated weights for policy 0, policy_version 86270 (0.0008) -[2023-10-12 06:53:54,309][78123] Updated weights for policy 1, policy_version 85850 (0.0008) -[2023-10-12 06:53:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 176259072. Throughput: 0: 1589.8, 1: 1579.4. Samples: 44070432. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:53:55,202][77203] Avg episode reward: [(0, '50.950'), (1, '51.760')] -[2023-10-12 06:53:58,345][78091] Updated weights for policy 0, policy_version 86280 (0.0008) -[2023-10-12 06:53:58,665][78123] Updated weights for policy 1, policy_version 85860 (0.0009) -[2023-10-12 06:53:58,714][78091] Updated weights for policy 0, policy_version 86290 (0.0008) -[2023-10-12 06:53:59,027][78123] Updated weights for policy 1, policy_version 85870 (0.0009) -[2023-10-12 06:53:59,083][78091] Updated weights for policy 0, policy_version 86300 (0.0008) -[2023-10-12 06:53:59,400][78123] Updated weights for policy 1, policy_version 85880 (0.0008) -[2023-10-12 06:54:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 176324608. Throughput: 0: 1607.6, 1: 1592.2. Samples: 44081234. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:54:00,201][77203] Avg episode reward: [(0, '47.770'), (1, '50.060')] -[2023-10-12 06:54:03,582][78091] Updated weights for policy 0, policy_version 86310 (0.0010) -[2023-10-12 06:54:03,809][78123] Updated weights for policy 1, policy_version 85890 (0.0009) -[2023-10-12 06:54:03,951][78091] Updated weights for policy 0, policy_version 86320 (0.0008) -[2023-10-12 06:54:04,171][78123] Updated weights for policy 1, policy_version 85900 (0.0008) -[2023-10-12 06:54:04,318][78091] Updated weights for policy 0, policy_version 86330 (0.0009) -[2023-10-12 06:54:04,535][78123] Updated weights for policy 1, policy_version 85910 (0.0008) -[2023-10-12 06:54:04,895][78123] Updated weights for policy 1, policy_version 85920 (0.0007) -[2023-10-12 06:54:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 176390144. Throughput: 0: 1608.2, 1: 1600.3. Samples: 44100286. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:54:05,202][77203] Avg episode reward: [(0, '58.200'), (1, '49.920')] -[2023-10-12 06:54:08,675][78091] Updated weights for policy 0, policy_version 86340 (0.0007) -[2023-10-12 06:54:09,054][78091] Updated weights for policy 0, policy_version 86350 (0.0007) -[2023-10-12 06:54:09,187][78123] Updated weights for policy 1, policy_version 85930 (0.0007) -[2023-10-12 06:54:09,413][78091] Updated weights for policy 0, policy_version 86360 (0.0009) -[2023-10-12 06:54:09,549][78123] Updated weights for policy 1, policy_version 85940 (0.0007) -[2023-10-12 06:54:09,927][78123] Updated weights for policy 1, policy_version 85950 (0.0008) -[2023-10-12 06:54:10,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 176455680. Throughput: 0: 1588.5, 1: 1584.0. Samples: 44118200. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:54:10,201][77203] Avg episode reward: [(0, '56.370'), (1, '52.300')] -[2023-10-12 06:54:13,775][78091] Updated weights for policy 0, policy_version 86370 (0.0008) -[2023-10-12 06:54:14,145][78091] Updated weights for policy 0, policy_version 86380 (0.0008) -[2023-10-12 06:54:14,241][78123] Updated weights for policy 1, policy_version 85960 (0.0008) -[2023-10-12 06:54:14,513][78091] Updated weights for policy 0, policy_version 86390 (0.0010) -[2023-10-12 06:54:14,594][78123] Updated weights for policy 1, policy_version 85970 (0.0008) -[2023-10-12 06:54:14,884][78091] Updated weights for policy 0, policy_version 86400 (0.0007) -[2023-10-12 06:54:14,960][78123] Updated weights for policy 1, policy_version 85980 (0.0009) -[2023-10-12 06:54:15,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 176521216. Throughput: 0: 1596.4, 1: 1585.1. Samples: 44128700. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:54:15,201][77203] Avg episode reward: [(0, '56.910'), (1, '57.210')] -[2023-10-12 06:54:19,268][78091] Updated weights for policy 0, policy_version 86410 (0.0008) -[2023-10-12 06:54:19,545][78123] Updated weights for policy 1, policy_version 85990 (0.0009) -[2023-10-12 06:54:19,642][78091] Updated weights for policy 0, policy_version 86420 (0.0008) -[2023-10-12 06:54:19,904][78123] Updated weights for policy 1, policy_version 86000 (0.0010) -[2023-10-12 06:54:20,003][78091] Updated weights for policy 0, policy_version 86430 (0.0007) -[2023-10-12 06:54:20,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 176553984. Throughput: 0: 1609.1, 1: 1599.9. Samples: 44147972. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:54:20,202][77203] Avg episode reward: [(0, '57.360'), (1, '61.930')] -[2023-10-12 06:54:20,267][78123] Updated weights for policy 1, policy_version 86010 (0.0009) -[2023-10-12 06:54:24,175][78091] Updated weights for policy 0, policy_version 86440 (0.0009) -[2023-10-12 06:54:24,520][78123] Updated weights for policy 1, policy_version 86020 (0.0008) -[2023-10-12 06:54:24,539][78091] Updated weights for policy 0, policy_version 86450 (0.0008) -[2023-10-12 06:54:24,889][78123] Updated weights for policy 1, policy_version 86030 (0.0009) -[2023-10-12 06:54:24,911][78091] Updated weights for policy 0, policy_version 86460 (0.0008) -[2023-10-12 06:54:25,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 176619520. Throughput: 0: 1592.7, 1: 1596.4. Samples: 44166428. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:54:25,202][77203] Avg episode reward: [(0, '57.840'), (1, '52.840')] -[2023-10-12 06:54:25,261][78123] Updated weights for policy 1, policy_version 86040 (0.0008) -[2023-10-12 06:54:29,388][78091] Updated weights for policy 0, policy_version 86470 (0.0008) -[2023-10-12 06:54:29,485][78123] Updated weights for policy 1, policy_version 86050 (0.0009) -[2023-10-12 06:54:29,755][78091] Updated weights for policy 0, policy_version 86480 (0.0007) -[2023-10-12 06:54:29,861][78123] Updated weights for policy 1, policy_version 86060 (0.0008) -[2023-10-12 06:54:30,118][78091] Updated weights for policy 0, policy_version 86490 (0.0008) -[2023-10-12 06:54:30,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 176652288. Throughput: 0: 1586.1, 1: 1579.1. Samples: 44176110. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:54:30,201][77203] Avg episode reward: [(0, '58.330'), (1, '57.060')] -[2023-10-12 06:54:30,228][78123] Updated weights for policy 1, policy_version 86070 (0.0007) -[2023-10-12 06:54:30,594][78123] Updated weights for policy 1, policy_version 86080 (0.0007) -[2023-10-12 06:54:34,398][78091] Updated weights for policy 0, policy_version 86500 (0.0008) -[2023-10-12 06:54:34,771][78123] Updated weights for policy 1, policy_version 86090 (0.0010) -[2023-10-12 06:54:34,784][78091] Updated weights for policy 0, policy_version 86510 (0.0009) -[2023-10-12 06:54:35,145][78123] Updated weights for policy 1, policy_version 86100 (0.0009) -[2023-10-12 06:54:35,149][78091] Updated weights for policy 0, policy_version 86520 (0.0008) -[2023-10-12 06:54:35,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 176717824. Throughput: 0: 1606.7, 1: 1600.9. Samples: 44195936. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:54:35,201][77203] Avg episode reward: [(0, '52.450'), (1, '57.220')] -[2023-10-12 06:54:35,511][78123] Updated weights for policy 1, policy_version 86110 (0.0007) -[2023-10-12 06:54:39,565][78091] Updated weights for policy 0, policy_version 86530 (0.0008) -[2023-10-12 06:54:39,934][78091] Updated weights for policy 0, policy_version 86540 (0.0009) -[2023-10-12 06:54:39,957][78123] Updated weights for policy 1, policy_version 86120 (0.0007) -[2023-10-12 06:54:40,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 176783360. Throughput: 0: 1601.8, 1: 1607.8. Samples: 44214862. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:54:40,202][77203] Avg episode reward: [(0, '60.090'), (1, '57.750')] -[2023-10-12 06:54:40,306][78091] Updated weights for policy 0, policy_version 86550 (0.0008) -[2023-10-12 06:54:40,312][78123] Updated weights for policy 1, policy_version 86130 (0.0009) -[2023-10-12 06:54:40,682][78091] Updated weights for policy 0, policy_version 86560 (0.0010) -[2023-10-12 06:54:40,686][78123] Updated weights for policy 1, policy_version 86140 (0.0010) -[2023-10-12 06:54:44,996][78091] Updated weights for policy 0, policy_version 86570 (0.0007) -[2023-10-12 06:54:45,117][78123] Updated weights for policy 1, policy_version 86150 (0.0008) -[2023-10-12 06:54:45,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 176848896. Throughput: 0: 1582.8, 1: 1584.6. Samples: 44223770. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:54:45,201][77203] Avg episode reward: [(0, '54.440'), (1, '49.870')] -[2023-10-12 06:54:45,363][78091] Updated weights for policy 0, policy_version 86580 (0.0007) -[2023-10-12 06:54:45,481][78123] Updated weights for policy 1, policy_version 86160 (0.0008) -[2023-10-12 06:54:45,737][78091] Updated weights for policy 0, policy_version 86590 (0.0008) -[2023-10-12 06:54:45,851][78123] Updated weights for policy 1, policy_version 86170 (0.0008) -[2023-10-12 06:54:50,073][78091] Updated weights for policy 0, policy_version 86600 (0.0007) -[2023-10-12 06:54:50,136][78123] Updated weights for policy 1, policy_version 86180 (0.0009) -[2023-10-12 06:54:50,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 176914432. Throughput: 0: 1589.2, 1: 1585.0. Samples: 44243124. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:54:50,201][77203] Avg episode reward: [(0, '62.120'), (1, '51.600')] -[2023-10-12 06:54:50,441][78091] Updated weights for policy 0, policy_version 86610 (0.0008) -[2023-10-12 06:54:50,500][78123] Updated weights for policy 1, policy_version 86190 (0.0009) -[2023-10-12 06:54:50,814][78091] Updated weights for policy 0, policy_version 86620 (0.0007) -[2023-10-12 06:54:50,870][78123] Updated weights for policy 1, policy_version 86200 (0.0008) -[2023-10-12 06:54:55,183][78091] Updated weights for policy 0, policy_version 86630 (0.0009) -[2023-10-12 06:54:55,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 176979968. Throughput: 0: 1608.8, 1: 1600.9. Samples: 44262640. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:54:55,202][77203] Avg episode reward: [(0, '57.160'), (1, '47.650')] -[2023-10-12 06:54:55,239][78123] Updated weights for policy 1, policy_version 86210 (0.0009) -[2023-10-12 06:54:55,552][78091] Updated weights for policy 0, policy_version 86640 (0.0008) -[2023-10-12 06:54:55,600][78123] Updated weights for policy 1, policy_version 86220 (0.0007) -[2023-10-12 06:54:55,917][78091] Updated weights for policy 0, policy_version 86650 (0.0010) -[2023-10-12 06:54:55,966][78123] Updated weights for policy 1, policy_version 86230 (0.0008) -[2023-10-12 06:54:56,336][78123] Updated weights for policy 1, policy_version 86240 (0.0009) -[2023-10-12 06:55:00,123][78091] Updated weights for policy 0, policy_version 86660 (0.0007) -[2023-10-12 06:55:00,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 177045504. Throughput: 0: 1584.7, 1: 1582.9. Samples: 44271242. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:55:00,201][77203] Avg episode reward: [(0, '56.750'), (1, '43.120')] -[2023-10-12 06:55:00,497][78091] Updated weights for policy 0, policy_version 86670 (0.0009) -[2023-10-12 06:55:00,798][78123] Updated weights for policy 1, policy_version 86250 (0.0009) -[2023-10-12 06:55:00,870][78091] Updated weights for policy 0, policy_version 86680 (0.0009) -[2023-10-12 06:55:01,165][78123] Updated weights for policy 1, policy_version 86260 (0.0010) -[2023-10-12 06:55:01,522][78123] Updated weights for policy 1, policy_version 86270 (0.0010) -[2023-10-12 06:55:05,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 177111040. Throughput: 0: 1584.9, 1: 1586.4. Samples: 44290682. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:55:05,202][77203] Avg episode reward: [(0, '60.190'), (1, '47.440')] -[2023-10-12 06:55:05,278][78091] Updated weights for policy 0, policy_version 86690 (0.0009) -[2023-10-12 06:55:05,652][78091] Updated weights for policy 0, policy_version 86700 (0.0008) -[2023-10-12 06:55:05,710][78123] Updated weights for policy 1, policy_version 86280 (0.0009) -[2023-10-12 06:55:06,018][78091] Updated weights for policy 0, policy_version 86710 (0.0007) -[2023-10-12 06:55:06,074][78123] Updated weights for policy 1, policy_version 86290 (0.0008) -[2023-10-12 06:55:06,379][78091] Updated weights for policy 0, policy_version 86720 (0.0007) -[2023-10-12 06:55:06,441][78123] Updated weights for policy 1, policy_version 86300 (0.0009) -[2023-10-12 06:55:10,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 177176576. Throughput: 0: 1602.9, 1: 1591.1. Samples: 44310156. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:55:10,202][77203] Avg episode reward: [(0, '52.090'), (1, '44.850')] -[2023-10-12 06:55:10,208][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000086304_88375296.pth... -[2023-10-12 06:55:10,241][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000084832_86867968.pth -[2023-10-12 06:55:10,583][78091] Updated weights for policy 0, policy_version 86730 (0.0008) -[2023-10-12 06:55:10,791][78123] Updated weights for policy 1, policy_version 86310 (0.0009) -[2023-10-12 06:55:10,942][78091] Updated weights for policy 0, policy_version 86740 (0.0009) -[2023-10-12 06:55:11,152][78123] Updated weights for policy 1, policy_version 86320 (0.0008) -[2023-10-12 06:55:11,313][78091] Updated weights for policy 0, policy_version 86750 (0.0009) -[2023-10-12 06:55:11,385][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000086752_88834048.pth... -[2023-10-12 06:55:11,422][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000085248_87293952.pth -[2023-10-12 06:55:11,521][78123] Updated weights for policy 1, policy_version 86330 (0.0007) -[2023-10-12 06:55:15,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 177242112. Throughput: 0: 1586.0, 1: 1583.4. Samples: 44318734. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:55:15,201][77203] Avg episode reward: [(0, '57.520'), (1, '40.720')] -[2023-10-12 06:55:15,697][78091] Updated weights for policy 0, policy_version 86760 (0.0008) -[2023-10-12 06:55:15,823][78123] Updated weights for policy 1, policy_version 86340 (0.0008) -[2023-10-12 06:55:16,070][78091] Updated weights for policy 0, policy_version 86770 (0.0009) -[2023-10-12 06:55:16,208][78123] Updated weights for policy 1, policy_version 86350 (0.0010) -[2023-10-12 06:55:16,442][78091] Updated weights for policy 0, policy_version 86780 (0.0008) -[2023-10-12 06:55:16,567][78123] Updated weights for policy 1, policy_version 86360 (0.0007) -[2023-10-12 06:55:20,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 177307648. Throughput: 0: 1581.6, 1: 1578.4. Samples: 44338136. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:55:20,201][77203] Avg episode reward: [(0, '56.500'), (1, '45.080')] -[2023-10-12 06:55:20,869][78091] Updated weights for policy 0, policy_version 86790 (0.0008) -[2023-10-12 06:55:20,919][78123] Updated weights for policy 1, policy_version 86370 (0.0009) -[2023-10-12 06:55:21,230][78091] Updated weights for policy 0, policy_version 86800 (0.0007) -[2023-10-12 06:55:21,281][78123] Updated weights for policy 1, policy_version 86380 (0.0008) -[2023-10-12 06:55:21,595][78091] Updated weights for policy 0, policy_version 86810 (0.0007) -[2023-10-12 06:55:21,645][78123] Updated weights for policy 1, policy_version 86390 (0.0007) -[2023-10-12 06:55:22,008][78123] Updated weights for policy 1, policy_version 86400 (0.0007) -[2023-10-12 06:55:25,201][77203] Fps is (10 sec: 13106.8, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 177373184. Throughput: 0: 1584.7, 1: 1583.3. Samples: 44357420. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:55:25,202][77203] Avg episode reward: [(0, '55.680'), (1, '49.310')] -[2023-10-12 06:55:26,032][78091] Updated weights for policy 0, policy_version 86820 (0.0009) -[2023-10-12 06:55:26,397][78091] Updated weights for policy 0, policy_version 86830 (0.0007) -[2023-10-12 06:55:26,436][78123] Updated weights for policy 1, policy_version 86410 (0.0009) -[2023-10-12 06:55:26,773][78091] Updated weights for policy 0, policy_version 86840 (0.0007) -[2023-10-12 06:55:26,801][78123] Updated weights for policy 1, policy_version 86420 (0.0007) -[2023-10-12 06:55:27,162][78123] Updated weights for policy 1, policy_version 86430 (0.0008) -[2023-10-12 06:55:30,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 177438720. Throughput: 0: 1577.3, 1: 1583.2. Samples: 44365996. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:55:30,202][77203] Avg episode reward: [(0, '53.810'), (1, '52.860')] -[2023-10-12 06:55:31,197][78091] Updated weights for policy 0, policy_version 86850 (0.0011) -[2023-10-12 06:55:31,416][78123] Updated weights for policy 1, policy_version 86440 (0.0007) -[2023-10-12 06:55:31,566][78091] Updated weights for policy 0, policy_version 86860 (0.0008) -[2023-10-12 06:55:31,781][78123] Updated weights for policy 1, policy_version 86450 (0.0007) -[2023-10-12 06:55:31,929][78091] Updated weights for policy 0, policy_version 86870 (0.0009) -[2023-10-12 06:55:32,136][78123] Updated weights for policy 1, policy_version 86460 (0.0007) -[2023-10-12 06:55:32,304][78091] Updated weights for policy 0, policy_version 86880 (0.0007) -[2023-10-12 06:55:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 177504256. Throughput: 0: 1577.6, 1: 1589.1. Samples: 44385624. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:55:35,202][77203] Avg episode reward: [(0, '55.230'), (1, '57.180')] -[2023-10-12 06:55:36,345][78123] Updated weights for policy 1, policy_version 86470 (0.0008) -[2023-10-12 06:55:36,665][78091] Updated weights for policy 0, policy_version 86890 (0.0008) -[2023-10-12 06:55:36,701][78123] Updated weights for policy 1, policy_version 86480 (0.0007) -[2023-10-12 06:55:37,034][78091] Updated weights for policy 0, policy_version 86900 (0.0009) -[2023-10-12 06:55:37,071][78123] Updated weights for policy 1, policy_version 86490 (0.0009) -[2023-10-12 06:55:37,410][78091] Updated weights for policy 0, policy_version 86910 (0.0009) -[2023-10-12 06:55:40,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 177569792. Throughput: 0: 1576.7, 1: 1584.0. Samples: 44404872. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:55:40,202][77203] Avg episode reward: [(0, '60.900'), (1, '56.140')] -[2023-10-12 06:55:41,392][78123] Updated weights for policy 1, policy_version 86500 (0.0008) -[2023-10-12 06:55:41,757][78123] Updated weights for policy 1, policy_version 86510 (0.0009) -[2023-10-12 06:55:41,765][78091] Updated weights for policy 0, policy_version 86920 (0.0009) -[2023-10-12 06:55:42,126][78123] Updated weights for policy 1, policy_version 86520 (0.0009) -[2023-10-12 06:55:42,137][78091] Updated weights for policy 0, policy_version 86930 (0.0009) -[2023-10-12 06:55:42,509][78091] Updated weights for policy 0, policy_version 86940 (0.0008) -[2023-10-12 06:55:45,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 177635328. Throughput: 0: 1575.2, 1: 1586.6. Samples: 44413524. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 06:55:45,201][77203] Avg episode reward: [(0, '59.900'), (1, '55.970')] -[2023-10-12 06:55:46,456][78123] Updated weights for policy 1, policy_version 86530 (0.0008) -[2023-10-12 06:55:46,821][78123] Updated weights for policy 1, policy_version 86540 (0.0007) -[2023-10-12 06:55:46,990][78091] Updated weights for policy 0, policy_version 86950 (0.0009) -[2023-10-12 06:55:47,185][78123] Updated weights for policy 1, policy_version 86550 (0.0008) -[2023-10-12 06:55:47,366][78091] Updated weights for policy 0, policy_version 86960 (0.0009) -[2023-10-12 06:55:47,550][78123] Updated weights for policy 1, policy_version 86560 (0.0009) -[2023-10-12 06:55:47,724][78091] Updated weights for policy 0, policy_version 86970 (0.0008) -[2023-10-12 06:55:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 177700864. Throughput: 0: 1569.8, 1: 1591.4. Samples: 44432936. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 06:55:50,202][77203] Avg episode reward: [(0, '56.440'), (1, '55.570')] -[2023-10-12 06:55:52,009][78091] Updated weights for policy 0, policy_version 86980 (0.0008) -[2023-10-12 06:55:52,147][78123] Updated weights for policy 1, policy_version 86570 (0.0009) -[2023-10-12 06:55:52,378][78091] Updated weights for policy 0, policy_version 86990 (0.0008) -[2023-10-12 06:55:52,515][78123] Updated weights for policy 1, policy_version 86580 (0.0009) -[2023-10-12 06:55:52,750][78091] Updated weights for policy 0, policy_version 87000 (0.0009) -[2023-10-12 06:55:52,885][78123] Updated weights for policy 1, policy_version 86590 (0.0009) -[2023-10-12 06:55:55,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 177766400. Throughput: 0: 1573.2, 1: 1589.5. Samples: 44452480. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 06:55:55,202][77203] Avg episode reward: [(0, '56.860'), (1, '58.060')] -[2023-10-12 06:55:56,914][78091] Updated weights for policy 0, policy_version 87010 (0.0009) -[2023-10-12 06:55:57,272][78091] Updated weights for policy 0, policy_version 87020 (0.0010) -[2023-10-12 06:55:57,356][78123] Updated weights for policy 1, policy_version 86600 (0.0008) -[2023-10-12 06:55:57,649][78091] Updated weights for policy 0, policy_version 87030 (0.0009) -[2023-10-12 06:55:57,707][78123] Updated weights for policy 1, policy_version 86610 (0.0008) -[2023-10-12 06:55:58,014][78091] Updated weights for policy 0, policy_version 87040 (0.0007) -[2023-10-12 06:55:58,073][78123] Updated weights for policy 1, policy_version 86620 (0.0009) -[2023-10-12 06:56:00,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 177831936. Throughput: 0: 1581.1, 1: 1600.3. Samples: 44461898. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 06:56:00,201][77203] Avg episode reward: [(0, '57.840'), (1, '56.600')] -[2023-10-12 06:56:02,154][78091] Updated weights for policy 0, policy_version 87050 (0.0009) -[2023-10-12 06:56:02,359][78123] Updated weights for policy 1, policy_version 86630 (0.0009) -[2023-10-12 06:56:02,512][78091] Updated weights for policy 0, policy_version 87060 (0.0008) -[2023-10-12 06:56:02,736][78123] Updated weights for policy 1, policy_version 86640 (0.0008) -[2023-10-12 06:56:02,877][78091] Updated weights for policy 0, policy_version 87070 (0.0008) -[2023-10-12 06:56:03,103][78123] Updated weights for policy 1, policy_version 86650 (0.0009) -[2023-10-12 06:56:05,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 177897472. Throughput: 0: 1585.0, 1: 1588.3. Samples: 44480938. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 06:56:05,202][77203] Avg episode reward: [(0, '58.310'), (1, '57.020')] -[2023-10-12 06:56:07,290][78091] Updated weights for policy 0, policy_version 87080 (0.0009) -[2023-10-12 06:56:07,325][78123] Updated weights for policy 1, policy_version 86660 (0.0010) -[2023-10-12 06:56:07,658][78091] Updated weights for policy 0, policy_version 87090 (0.0008) -[2023-10-12 06:56:07,679][78123] Updated weights for policy 1, policy_version 86670 (0.0009) -[2023-10-12 06:56:08,041][78091] Updated weights for policy 0, policy_version 87100 (0.0008) -[2023-10-12 06:56:08,047][78123] Updated weights for policy 1, policy_version 86680 (0.0009) -[2023-10-12 06:56:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 177963008. Throughput: 0: 1588.4, 1: 1589.5. Samples: 44500424. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 06:56:10,201][77203] Avg episode reward: [(0, '52.520'), (1, '53.570')] -[2023-10-12 06:56:12,193][78091] Updated weights for policy 0, policy_version 87110 (0.0007) -[2023-10-12 06:56:12,521][78123] Updated weights for policy 1, policy_version 86690 (0.0009) -[2023-10-12 06:56:12,564][78091] Updated weights for policy 0, policy_version 87120 (0.0010) -[2023-10-12 06:56:12,871][78123] Updated weights for policy 1, policy_version 86700 (0.0007) -[2023-10-12 06:56:12,924][78091] Updated weights for policy 0, policy_version 87130 (0.0009) -[2023-10-12 06:56:13,231][78123] Updated weights for policy 1, policy_version 86710 (0.0011) -[2023-10-12 06:56:13,595][78123] Updated weights for policy 1, policy_version 86720 (0.0011) -[2023-10-12 06:56:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.1, 300 sec: 12662.9). Total num frames: 178028544. Throughput: 0: 1600.9, 1: 1606.1. Samples: 44510312. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 06:56:15,202][77203] Avg episode reward: [(0, '55.430'), (1, '56.580')] -[2023-10-12 06:56:17,318][78091] Updated weights for policy 0, policy_version 87140 (0.0010) -[2023-10-12 06:56:17,683][78091] Updated weights for policy 0, policy_version 87150 (0.0007) -[2023-10-12 06:56:17,957][78123] Updated weights for policy 1, policy_version 86730 (0.0009) -[2023-10-12 06:56:18,055][78091] Updated weights for policy 0, policy_version 87160 (0.0007) -[2023-10-12 06:56:18,323][78123] Updated weights for policy 1, policy_version 86740 (0.0008) -[2023-10-12 06:56:18,681][78123] Updated weights for policy 1, policy_version 86750 (0.0010) -[2023-10-12 06:56:20,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 178094080. Throughput: 0: 1593.6, 1: 1580.2. Samples: 44528446. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 06:56:20,202][77203] Avg episode reward: [(0, '58.340'), (1, '50.980')] -[2023-10-12 06:56:22,310][78091] Updated weights for policy 0, policy_version 87170 (0.0007) -[2023-10-12 06:56:22,687][78091] Updated weights for policy 0, policy_version 87180 (0.0008) -[2023-10-12 06:56:22,972][78123] Updated weights for policy 1, policy_version 86760 (0.0009) -[2023-10-12 06:56:23,054][78091] Updated weights for policy 0, policy_version 87190 (0.0010) -[2023-10-12 06:56:23,331][78123] Updated weights for policy 1, policy_version 86770 (0.0007) -[2023-10-12 06:56:23,430][78091] Updated weights for policy 0, policy_version 87200 (0.0008) -[2023-10-12 06:56:23,704][78123] Updated weights for policy 1, policy_version 86780 (0.0007) -[2023-10-12 06:56:25,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.3, 300 sec: 12885.0). Total num frames: 178159616. Throughput: 0: 1595.1, 1: 1582.4. Samples: 44547858. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 06:56:25,201][77203] Avg episode reward: [(0, '57.910'), (1, '53.430')] -[2023-10-12 06:56:27,682][78091] Updated weights for policy 0, policy_version 87210 (0.0010) -[2023-10-12 06:56:28,051][78091] Updated weights for policy 0, policy_version 87220 (0.0009) -[2023-10-12 06:56:28,090][78123] Updated weights for policy 1, policy_version 86790 (0.0009) -[2023-10-12 06:56:28,416][78091] Updated weights for policy 0, policy_version 87230 (0.0007) -[2023-10-12 06:56:28,452][78123] Updated weights for policy 1, policy_version 86800 (0.0008) -[2023-10-12 06:56:28,820][78123] Updated weights for policy 1, policy_version 86810 (0.0008) -[2023-10-12 06:56:30,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 178225152. Throughput: 0: 1613.5, 1: 1604.6. Samples: 44558340. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 06:56:30,201][77203] Avg episode reward: [(0, '55.020'), (1, '57.380')] -[2023-10-12 06:56:32,665][78091] Updated weights for policy 0, policy_version 87240 (0.0008) -[2023-10-12 06:56:32,907][78123] Updated weights for policy 1, policy_version 86820 (0.0007) -[2023-10-12 06:56:33,037][78091] Updated weights for policy 0, policy_version 87250 (0.0007) -[2023-10-12 06:56:33,282][78123] Updated weights for policy 1, policy_version 86830 (0.0009) -[2023-10-12 06:56:33,402][78091] Updated weights for policy 0, policy_version 87260 (0.0007) -[2023-10-12 06:56:33,644][78123] Updated weights for policy 1, policy_version 86840 (0.0009) -[2023-10-12 06:56:35,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 178290688. Throughput: 0: 1608.4, 1: 1581.7. Samples: 44576488. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 06:56:35,202][77203] Avg episode reward: [(0, '57.410'), (1, '56.970')] -[2023-10-12 06:56:37,652][78091] Updated weights for policy 0, policy_version 87270 (0.0008) -[2023-10-12 06:56:38,015][78123] Updated weights for policy 1, policy_version 86850 (0.0007) -[2023-10-12 06:56:38,031][78091] Updated weights for policy 0, policy_version 87280 (0.0008) -[2023-10-12 06:56:38,383][78123] Updated weights for policy 1, policy_version 86860 (0.0008) -[2023-10-12 06:56:38,388][78091] Updated weights for policy 0, policy_version 87290 (0.0007) -[2023-10-12 06:56:38,753][78123] Updated weights for policy 1, policy_version 86870 (0.0010) -[2023-10-12 06:56:39,118][78123] Updated weights for policy 1, policy_version 86880 (0.0008) -[2023-10-12 06:56:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 178356224. Throughput: 0: 1607.3, 1: 1576.5. Samples: 44595750. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-12 06:56:40,201][77203] Avg episode reward: [(0, '57.380'), (1, '53.320')] -[2023-10-12 06:56:42,581][78091] Updated weights for policy 0, policy_version 87300 (0.0008) -[2023-10-12 06:56:42,951][78091] Updated weights for policy 0, policy_version 87310 (0.0009) -[2023-10-12 06:56:43,324][78091] Updated weights for policy 0, policy_version 87320 (0.0008) -[2023-10-12 06:56:43,513][78123] Updated weights for policy 1, policy_version 86890 (0.0009) -[2023-10-12 06:56:43,886][78123] Updated weights for policy 1, policy_version 86900 (0.0009) -[2023-10-12 06:56:44,258][78123] Updated weights for policy 1, policy_version 86910 (0.0009) -[2023-10-12 06:56:45,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 178421760. Throughput: 0: 1621.8, 1: 1590.0. Samples: 44606432. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-12 06:56:45,201][77203] Avg episode reward: [(0, '60.550'), (1, '55.190')] -[2023-10-12 06:56:47,705][78091] Updated weights for policy 0, policy_version 87330 (0.0007) -[2023-10-12 06:56:48,078][78091] Updated weights for policy 0, policy_version 87340 (0.0008) -[2023-10-12 06:56:48,450][78091] Updated weights for policy 0, policy_version 87350 (0.0007) -[2023-10-12 06:56:48,759][78123] Updated weights for policy 1, policy_version 86920 (0.0008) -[2023-10-12 06:56:48,825][78091] Updated weights for policy 0, policy_version 87360 (0.0008) -[2023-10-12 06:56:49,134][78123] Updated weights for policy 1, policy_version 86930 (0.0010) -[2023-10-12 06:56:49,492][78123] Updated weights for policy 1, policy_version 86940 (0.0010) -[2023-10-12 06:56:50,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 178487296. Throughput: 0: 1606.4, 1: 1595.2. Samples: 44625010. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-12 06:56:50,202][77203] Avg episode reward: [(0, '57.690'), (1, '55.230')] -[2023-10-12 06:56:53,231][78091] Updated weights for policy 0, policy_version 87370 (0.0008) -[2023-10-12 06:56:53,598][78091] Updated weights for policy 0, policy_version 87380 (0.0007) -[2023-10-12 06:56:53,841][78123] Updated weights for policy 1, policy_version 86950 (0.0009) -[2023-10-12 06:56:53,969][78091] Updated weights for policy 0, policy_version 87390 (0.0007) -[2023-10-12 06:56:54,202][78123] Updated weights for policy 1, policy_version 86960 (0.0009) -[2023-10-12 06:56:54,578][78123] Updated weights for policy 1, policy_version 86970 (0.0008) -[2023-10-12 06:56:55,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 178552832. Throughput: 0: 1604.5, 1: 1576.0. Samples: 44643550. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-12 06:56:55,201][77203] Avg episode reward: [(0, '60.590'), (1, '56.220')] -[2023-10-12 06:56:58,239][78091] Updated weights for policy 0, policy_version 87400 (0.0007) -[2023-10-12 06:56:58,602][78091] Updated weights for policy 0, policy_version 87410 (0.0007) -[2023-10-12 06:56:58,937][78123] Updated weights for policy 1, policy_version 86980 (0.0009) -[2023-10-12 06:56:58,974][78091] Updated weights for policy 0, policy_version 87420 (0.0009) -[2023-10-12 06:56:59,298][78123] Updated weights for policy 1, policy_version 86990 (0.0008) -[2023-10-12 06:56:59,671][78123] Updated weights for policy 1, policy_version 87000 (0.0007) -[2023-10-12 06:57:00,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 178618368. Throughput: 0: 1616.2, 1: 1581.1. Samples: 44654190. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-12 06:57:00,201][77203] Avg episode reward: [(0, '62.100'), (1, '53.320')] -[2023-10-12 06:57:03,365][78091] Updated weights for policy 0, policy_version 87430 (0.0007) -[2023-10-12 06:57:03,731][78091] Updated weights for policy 0, policy_version 87440 (0.0007) -[2023-10-12 06:57:04,094][78091] Updated weights for policy 0, policy_version 87450 (0.0007) -[2023-10-12 06:57:04,112][78123] Updated weights for policy 1, policy_version 87010 (0.0008) -[2023-10-12 06:57:04,479][78123] Updated weights for policy 1, policy_version 87020 (0.0009) -[2023-10-12 06:57:04,835][78123] Updated weights for policy 1, policy_version 87030 (0.0008) -[2023-10-12 06:57:05,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 178683904. Throughput: 0: 1611.1, 1: 1600.4. Samples: 44672964. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-12 06:57:05,202][77203] Avg episode reward: [(0, '62.060'), (1, '45.840')] -[2023-10-12 06:57:05,205][78123] Updated weights for policy 1, policy_version 87040 (0.0008) -[2023-10-12 06:57:08,406][78091] Updated weights for policy 0, policy_version 87460 (0.0008) -[2023-10-12 06:57:08,774][78091] Updated weights for policy 0, policy_version 87470 (0.0010) -[2023-10-12 06:57:09,142][78091] Updated weights for policy 0, policy_version 87480 (0.0008) -[2023-10-12 06:57:09,549][78123] Updated weights for policy 1, policy_version 87050 (0.0010) -[2023-10-12 06:57:09,920][78123] Updated weights for policy 1, policy_version 87060 (0.0011) -[2023-10-12 06:57:10,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 178716672. Throughput: 0: 1599.2, 1: 1591.8. Samples: 44691454. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-12 06:57:10,201][77203] Avg episode reward: [(0, '56.720'), (1, '43.370')] -[2023-10-12 06:57:10,209][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000087488_89587712.pth... -[2023-10-12 06:57:10,241][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000085984_88047616.pth -[2023-10-12 06:57:10,281][78123] Updated weights for policy 1, policy_version 87070 (0.0010) -[2023-10-12 06:57:10,354][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000087072_89161728.pth... -[2023-10-12 06:57:10,394][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000085568_87621632.pth -[2023-10-12 06:57:13,588][78091] Updated weights for policy 0, policy_version 87490 (0.0007) -[2023-10-12 06:57:13,954][78091] Updated weights for policy 0, policy_version 87500 (0.0008) -[2023-10-12 06:57:14,327][78091] Updated weights for policy 0, policy_version 87510 (0.0007) -[2023-10-12 06:57:14,648][78123] Updated weights for policy 1, policy_version 87080 (0.0008) -[2023-10-12 06:57:14,697][78091] Updated weights for policy 0, policy_version 87520 (0.0007) -[2023-10-12 06:57:15,008][78123] Updated weights for policy 1, policy_version 87090 (0.0009) -[2023-10-12 06:57:15,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 178782208. Throughput: 0: 1607.2, 1: 1581.3. Samples: 44701820. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-12 06:57:15,201][77203] Avg episode reward: [(0, '57.800'), (1, '45.150')] -[2023-10-12 06:57:15,379][78123] Updated weights for policy 1, policy_version 87100 (0.0009) -[2023-10-12 06:57:18,831][78091] Updated weights for policy 0, policy_version 87530 (0.0009) -[2023-10-12 06:57:19,212][78091] Updated weights for policy 0, policy_version 87540 (0.0010) -[2023-10-12 06:57:19,577][78091] Updated weights for policy 0, policy_version 87550 (0.0010) -[2023-10-12 06:57:19,764][78123] Updated weights for policy 1, policy_version 87110 (0.0009) -[2023-10-12 06:57:20,137][78123] Updated weights for policy 1, policy_version 87120 (0.0009) -[2023-10-12 06:57:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 178847744. Throughput: 0: 1610.6, 1: 1602.8. Samples: 44721090. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-12 06:57:20,201][77203] Avg episode reward: [(0, '60.770'), (1, '40.550')] -[2023-10-12 06:57:20,501][78123] Updated weights for policy 1, policy_version 87130 (0.0009) -[2023-10-12 06:57:23,951][78091] Updated weights for policy 0, policy_version 87560 (0.0007) -[2023-10-12 06:57:24,316][78091] Updated weights for policy 0, policy_version 87570 (0.0008) -[2023-10-12 06:57:24,687][78091] Updated weights for policy 0, policy_version 87580 (0.0009) -[2023-10-12 06:57:24,865][78123] Updated weights for policy 1, policy_version 87140 (0.0009) -[2023-10-12 06:57:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 178913280. Throughput: 0: 1594.0, 1: 1610.6. Samples: 44739956. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-12 06:57:25,201][77203] Avg episode reward: [(0, '54.980'), (1, '41.980')] -[2023-10-12 06:57:25,236][78123] Updated weights for policy 1, policy_version 87150 (0.0008) -[2023-10-12 06:57:25,616][78123] Updated weights for policy 1, policy_version 87160 (0.0008) -[2023-10-12 06:57:28,851][78091] Updated weights for policy 0, policy_version 87590 (0.0008) -[2023-10-12 06:57:29,231][78091] Updated weights for policy 0, policy_version 87600 (0.0010) -[2023-10-12 06:57:29,602][78091] Updated weights for policy 0, policy_version 87610 (0.0007) -[2023-10-12 06:57:29,921][78123] Updated weights for policy 1, policy_version 87170 (0.0008) -[2023-10-12 06:57:30,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 178978816. Throughput: 0: 1601.2, 1: 1586.0. Samples: 44749858. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-12 06:57:30,202][77203] Avg episode reward: [(0, '56.290'), (1, '53.790')] -[2023-10-12 06:57:30,283][78123] Updated weights for policy 1, policy_version 87180 (0.0008) -[2023-10-12 06:57:30,650][78123] Updated weights for policy 1, policy_version 87190 (0.0008) -[2023-10-12 06:57:31,015][78123] Updated weights for policy 1, policy_version 87200 (0.0007) -[2023-10-12 06:57:33,949][78091] Updated weights for policy 0, policy_version 87620 (0.0007) -[2023-10-12 06:57:34,317][78091] Updated weights for policy 0, policy_version 87630 (0.0008) -[2023-10-12 06:57:34,685][78091] Updated weights for policy 0, policy_version 87640 (0.0010) -[2023-10-12 06:57:35,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 179044352. Throughput: 0: 1616.7, 1: 1593.8. Samples: 44769480. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:57:35,201][77203] Avg episode reward: [(0, '55.850'), (1, '51.520')] -[2023-10-12 06:57:35,351][78123] Updated weights for policy 1, policy_version 87210 (0.0007) -[2023-10-12 06:57:35,719][78123] Updated weights for policy 1, policy_version 87220 (0.0010) -[2023-10-12 06:57:36,081][78123] Updated weights for policy 1, policy_version 87230 (0.0008) -[2023-10-12 06:57:38,943][78091] Updated weights for policy 0, policy_version 87650 (0.0008) -[2023-10-12 06:57:39,336][78091] Updated weights for policy 0, policy_version 87660 (0.0008) -[2023-10-12 06:57:39,705][78091] Updated weights for policy 0, policy_version 87670 (0.0008) -[2023-10-12 06:57:40,078][78091] Updated weights for policy 0, policy_version 87680 (0.0008) -[2023-10-12 06:57:40,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 179109888. Throughput: 0: 1600.6, 1: 1611.6. Samples: 44788100. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:57:40,202][77203] Avg episode reward: [(0, '61.600'), (1, '47.590')] -[2023-10-12 06:57:40,398][78123] Updated weights for policy 1, policy_version 87240 (0.0007) -[2023-10-12 06:57:40,761][78123] Updated weights for policy 1, policy_version 87250 (0.0007) -[2023-10-12 06:57:41,128][78123] Updated weights for policy 1, policy_version 87260 (0.0007) -[2023-10-12 06:57:44,457][78091] Updated weights for policy 0, policy_version 87690 (0.0009) -[2023-10-12 06:57:44,823][78091] Updated weights for policy 0, policy_version 87700 (0.0008) -[2023-10-12 06:57:45,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 179142656. Throughput: 0: 1596.5, 1: 1591.3. Samples: 44797642. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:57:45,202][77203] Avg episode reward: [(0, '57.640'), (1, '49.940')] -[2023-10-12 06:57:45,208][78091] Updated weights for policy 0, policy_version 87710 (0.0007) -[2023-10-12 06:57:45,307][78123] Updated weights for policy 1, policy_version 87270 (0.0008) -[2023-10-12 06:57:45,681][78123] Updated weights for policy 1, policy_version 87280 (0.0008) -[2023-10-12 06:57:46,056][78123] Updated weights for policy 1, policy_version 87290 (0.0007) -[2023-10-12 06:57:49,459][78091] Updated weights for policy 0, policy_version 87720 (0.0010) -[2023-10-12 06:57:49,836][78091] Updated weights for policy 0, policy_version 87730 (0.0011) -[2023-10-12 06:57:50,199][78091] Updated weights for policy 0, policy_version 87740 (0.0010) -[2023-10-12 06:57:50,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 179208192. Throughput: 0: 1612.3, 1: 1590.4. Samples: 44817084. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:57:50,202][77203] Avg episode reward: [(0, '63.340'), (1, '53.720')] -[2023-10-12 06:57:50,417][78123] Updated weights for policy 1, policy_version 87300 (0.0009) -[2023-10-12 06:57:50,782][78123] Updated weights for policy 1, policy_version 87310 (0.0009) -[2023-10-12 06:57:51,146][78123] Updated weights for policy 1, policy_version 87320 (0.0007) -[2023-10-12 06:57:54,577][78091] Updated weights for policy 0, policy_version 87750 (0.0009) -[2023-10-12 06:57:54,945][78091] Updated weights for policy 0, policy_version 87760 (0.0011) -[2023-10-12 06:57:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 179273728. Throughput: 0: 1614.3, 1: 1597.8. Samples: 44835996. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:57:55,202][77203] Avg episode reward: [(0, '57.650'), (1, '59.010')] -[2023-10-12 06:57:55,309][78091] Updated weights for policy 0, policy_version 87770 (0.0010) -[2023-10-12 06:57:55,496][78123] Updated weights for policy 1, policy_version 87330 (0.0008) -[2023-10-12 06:57:55,870][78123] Updated weights for policy 1, policy_version 87340 (0.0009) -[2023-10-12 06:57:56,227][78123] Updated weights for policy 1, policy_version 87350 (0.0009) -[2023-10-12 06:57:56,595][78123] Updated weights for policy 1, policy_version 87360 (0.0009) -[2023-10-12 06:57:59,627][78091] Updated weights for policy 0, policy_version 87780 (0.0008) -[2023-10-12 06:57:59,996][78091] Updated weights for policy 0, policy_version 87790 (0.0007) -[2023-10-12 06:58:00,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 179339264. Throughput: 0: 1599.1, 1: 1586.0. Samples: 44845146. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:58:00,201][77203] Avg episode reward: [(0, '62.960'), (1, '57.010')] -[2023-10-12 06:58:00,366][78091] Updated weights for policy 0, policy_version 87800 (0.0009) -[2023-10-12 06:58:00,815][78123] Updated weights for policy 1, policy_version 87370 (0.0009) -[2023-10-12 06:58:01,181][78123] Updated weights for policy 1, policy_version 87380 (0.0010) -[2023-10-12 06:58:01,544][78123] Updated weights for policy 1, policy_version 87390 (0.0007) -[2023-10-12 06:58:04,712][78091] Updated weights for policy 0, policy_version 87810 (0.0008) -[2023-10-12 06:58:05,082][78091] Updated weights for policy 0, policy_version 87820 (0.0008) -[2023-10-12 06:58:05,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 179404800. Throughput: 0: 1609.0, 1: 1586.1. Samples: 44864872. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:58:05,201][77203] Avg episode reward: [(0, '60.130'), (1, '61.270')] -[2023-10-12 06:58:05,448][78091] Updated weights for policy 0, policy_version 87830 (0.0007) -[2023-10-12 06:58:05,827][78091] Updated weights for policy 0, policy_version 87840 (0.0008) -[2023-10-12 06:58:05,897][78123] Updated weights for policy 1, policy_version 87400 (0.0008) -[2023-10-12 06:58:06,247][78123] Updated weights for policy 1, policy_version 87410 (0.0008) -[2023-10-12 06:58:06,615][78123] Updated weights for policy 1, policy_version 87420 (0.0007) -[2023-10-12 06:58:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 179470336. Throughput: 0: 1616.4, 1: 1589.0. Samples: 44884198. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:58:10,202][77203] Avg episode reward: [(0, '59.300'), (1, '61.440')] -[2023-10-12 06:58:10,264][78091] Updated weights for policy 0, policy_version 87850 (0.0008) -[2023-10-12 06:58:10,642][78091] Updated weights for policy 0, policy_version 87860 (0.0008) -[2023-10-12 06:58:10,949][78123] Updated weights for policy 1, policy_version 87430 (0.0009) -[2023-10-12 06:58:11,014][78091] Updated weights for policy 0, policy_version 87870 (0.0007) -[2023-10-12 06:58:11,324][78123] Updated weights for policy 1, policy_version 87440 (0.0010) -[2023-10-12 06:58:11,695][78123] Updated weights for policy 1, policy_version 87450 (0.0007) -[2023-10-12 06:58:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 179535872. Throughput: 0: 1586.0, 1: 1589.6. Samples: 44892758. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:58:15,201][77203] Avg episode reward: [(0, '57.440'), (1, '49.620')] -[2023-10-12 06:58:15,483][78091] Updated weights for policy 0, policy_version 87880 (0.0011) -[2023-10-12 06:58:15,856][78091] Updated weights for policy 0, policy_version 87890 (0.0010) -[2023-10-12 06:58:16,190][78123] Updated weights for policy 1, policy_version 87460 (0.0007) -[2023-10-12 06:58:16,225][78091] Updated weights for policy 0, policy_version 87900 (0.0008) -[2023-10-12 06:58:16,556][78123] Updated weights for policy 1, policy_version 87470 (0.0009) -[2023-10-12 06:58:16,918][78123] Updated weights for policy 1, policy_version 87480 (0.0010) -[2023-10-12 06:58:20,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 179601408. Throughput: 0: 1583.8, 1: 1586.8. Samples: 44912158. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:58:20,202][77203] Avg episode reward: [(0, '51.770'), (1, '47.320')] -[2023-10-12 06:58:20,578][78091] Updated weights for policy 0, policy_version 87910 (0.0007) -[2023-10-12 06:58:20,953][78091] Updated weights for policy 0, policy_version 87920 (0.0007) -[2023-10-12 06:58:21,191][78123] Updated weights for policy 1, policy_version 87490 (0.0010) -[2023-10-12 06:58:21,330][78091] Updated weights for policy 0, policy_version 87930 (0.0007) -[2023-10-12 06:58:21,583][78123] Updated weights for policy 1, policy_version 87500 (0.0008) -[2023-10-12 06:58:21,949][78123] Updated weights for policy 1, policy_version 87510 (0.0008) -[2023-10-12 06:58:22,312][78123] Updated weights for policy 1, policy_version 87520 (0.0010) -[2023-10-12 06:58:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 179666944. Throughput: 0: 1604.4, 1: 1586.4. Samples: 44931684. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:58:25,201][77203] Avg episode reward: [(0, '56.930'), (1, '49.220')] -[2023-10-12 06:58:25,425][78091] Updated weights for policy 0, policy_version 87940 (0.0008) -[2023-10-12 06:58:25,823][78091] Updated weights for policy 0, policy_version 87950 (0.0008) -[2023-10-12 06:58:26,201][78091] Updated weights for policy 0, policy_version 87960 (0.0008) -[2023-10-12 06:58:26,789][78123] Updated weights for policy 1, policy_version 87530 (0.0010) -[2023-10-12 06:58:27,149][78123] Updated weights for policy 1, policy_version 87540 (0.0010) -[2023-10-12 06:58:27,511][78123] Updated weights for policy 1, policy_version 87550 (0.0010) -[2023-10-12 06:58:30,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 179732480. Throughput: 0: 1584.2, 1: 1583.1. Samples: 44940172. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:58:30,201][77203] Avg episode reward: [(0, '54.060'), (1, '51.190')] -[2023-10-12 06:58:30,565][78091] Updated weights for policy 0, policy_version 87970 (0.0008) -[2023-10-12 06:58:30,945][78091] Updated weights for policy 0, policy_version 87980 (0.0010) -[2023-10-12 06:58:31,322][78091] Updated weights for policy 0, policy_version 87990 (0.0007) -[2023-10-12 06:58:31,680][78091] Updated weights for policy 0, policy_version 88000 (0.0008) -[2023-10-12 06:58:31,831][78123] Updated weights for policy 1, policy_version 87560 (0.0008) -[2023-10-12 06:58:32,204][78123] Updated weights for policy 1, policy_version 87570 (0.0007) -[2023-10-12 06:58:32,573][78123] Updated weights for policy 1, policy_version 87580 (0.0009) -[2023-10-12 06:58:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 179798016. Throughput: 0: 1584.5, 1: 1583.9. Samples: 44959660. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:58:35,201][77203] Avg episode reward: [(0, '59.810'), (1, '50.070')] -[2023-10-12 06:58:35,871][78091] Updated weights for policy 0, policy_version 88010 (0.0010) -[2023-10-12 06:58:36,229][78091] Updated weights for policy 0, policy_version 88020 (0.0010) -[2023-10-12 06:58:36,602][78091] Updated weights for policy 0, policy_version 88030 (0.0010) -[2023-10-12 06:58:36,915][78123] Updated weights for policy 1, policy_version 87590 (0.0009) -[2023-10-12 06:58:37,276][78123] Updated weights for policy 1, policy_version 87600 (0.0009) -[2023-10-12 06:58:37,646][78123] Updated weights for policy 1, policy_version 87610 (0.0011) -[2023-10-12 06:58:40,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 179863552. Throughput: 0: 1593.9, 1: 1584.5. Samples: 44979024. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:58:40,201][77203] Avg episode reward: [(0, '55.430'), (1, '47.850')] -[2023-10-12 06:58:40,897][78091] Updated weights for policy 0, policy_version 88040 (0.0009) -[2023-10-12 06:58:41,265][78091] Updated weights for policy 0, policy_version 88050 (0.0009) -[2023-10-12 06:58:41,643][78091] Updated weights for policy 0, policy_version 88060 (0.0009) -[2023-10-12 06:58:41,917][78123] Updated weights for policy 1, policy_version 87620 (0.0009) -[2023-10-12 06:58:42,287][78123] Updated weights for policy 1, policy_version 87630 (0.0008) -[2023-10-12 06:58:42,652][78123] Updated weights for policy 1, policy_version 87640 (0.0011) -[2023-10-12 06:58:45,201][77203] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 179929088. Throughput: 0: 1584.9, 1: 1590.4. Samples: 44988036. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:58:45,202][77203] Avg episode reward: [(0, '54.990'), (1, '48.040')] -[2023-10-12 06:58:45,856][78091] Updated weights for policy 0, policy_version 88070 (0.0008) -[2023-10-12 06:58:46,220][78091] Updated weights for policy 0, policy_version 88080 (0.0008) -[2023-10-12 06:58:46,597][78091] Updated weights for policy 0, policy_version 88090 (0.0010) -[2023-10-12 06:58:46,905][78123] Updated weights for policy 1, policy_version 87650 (0.0009) -[2023-10-12 06:58:47,283][78123] Updated weights for policy 1, policy_version 87660 (0.0009) -[2023-10-12 06:58:47,638][78123] Updated weights for policy 1, policy_version 87670 (0.0009) -[2023-10-12 06:58:48,011][78123] Updated weights for policy 1, policy_version 87680 (0.0009) -[2023-10-12 06:58:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 179994624. Throughput: 0: 1586.2, 1: 1582.1. Samples: 45007444. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:58:50,201][77203] Avg episode reward: [(0, '57.390'), (1, '48.730')] -[2023-10-12 06:58:50,901][78091] Updated weights for policy 0, policy_version 88100 (0.0008) -[2023-10-12 06:58:51,280][78091] Updated weights for policy 0, policy_version 88110 (0.0011) -[2023-10-12 06:58:51,653][78091] Updated weights for policy 0, policy_version 88120 (0.0010) -[2023-10-12 06:58:52,314][78123] Updated weights for policy 1, policy_version 87690 (0.0009) -[2023-10-12 06:58:52,683][78123] Updated weights for policy 1, policy_version 87700 (0.0009) -[2023-10-12 06:58:53,048][78123] Updated weights for policy 1, policy_version 87710 (0.0010) -[2023-10-12 06:58:55,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 180060160. Throughput: 0: 1591.8, 1: 1578.7. Samples: 45026870. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:58:55,202][77203] Avg episode reward: [(0, '59.820'), (1, '48.640')] -[2023-10-12 06:58:55,933][78091] Updated weights for policy 0, policy_version 88130 (0.0010) -[2023-10-12 06:58:56,312][78091] Updated weights for policy 0, policy_version 88140 (0.0008) -[2023-10-12 06:58:56,680][78091] Updated weights for policy 0, policy_version 88150 (0.0008) -[2023-10-12 06:58:57,044][78091] Updated weights for policy 0, policy_version 88160 (0.0010) -[2023-10-12 06:58:57,396][78123] Updated weights for policy 1, policy_version 87720 (0.0008) -[2023-10-12 06:58:57,773][78123] Updated weights for policy 1, policy_version 87730 (0.0008) -[2023-10-12 06:58:58,144][78123] Updated weights for policy 1, policy_version 87740 (0.0008) -[2023-10-12 06:59:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 180125696. Throughput: 0: 1593.1, 1: 1591.2. Samples: 45036050. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:59:00,201][77203] Avg episode reward: [(0, '54.470'), (1, '48.760')] -[2023-10-12 06:59:01,369][78091] Updated weights for policy 0, policy_version 88170 (0.0007) -[2023-10-12 06:59:01,752][78091] Updated weights for policy 0, policy_version 88180 (0.0007) -[2023-10-12 06:59:02,114][78091] Updated weights for policy 0, policy_version 88190 (0.0007) -[2023-10-12 06:59:02,395][78123] Updated weights for policy 1, policy_version 87750 (0.0009) -[2023-10-12 06:59:02,762][78123] Updated weights for policy 1, policy_version 87760 (0.0010) -[2023-10-12 06:59:03,128][78123] Updated weights for policy 1, policy_version 87770 (0.0010) -[2023-10-12 06:59:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 180191232. Throughput: 0: 1597.4, 1: 1580.2. Samples: 45055152. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:59:05,202][77203] Avg episode reward: [(0, '58.940'), (1, '50.400')] -[2023-10-12 06:59:06,198][78091] Updated weights for policy 0, policy_version 88200 (0.0007) -[2023-10-12 06:59:06,574][78091] Updated weights for policy 0, policy_version 88210 (0.0009) -[2023-10-12 06:59:06,939][78091] Updated weights for policy 0, policy_version 88220 (0.0010) -[2023-10-12 06:59:07,683][78123] Updated weights for policy 1, policy_version 87780 (0.0008) -[2023-10-12 06:59:08,048][78123] Updated weights for policy 1, policy_version 87790 (0.0008) -[2023-10-12 06:59:08,412][78123] Updated weights for policy 1, policy_version 87800 (0.0007) -[2023-10-12 06:59:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 180256768. Throughput: 0: 1600.3, 1: 1579.5. Samples: 45074774. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:59:10,202][77203] Avg episode reward: [(0, '53.110'), (1, '56.900')] -[2023-10-12 06:59:10,212][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000088224_90341376.pth... -[2023-10-12 06:59:10,212][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000087808_89915392.pth... -[2023-10-12 06:59:10,256][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000086752_88834048.pth -[2023-10-12 06:59:10,256][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000086304_88375296.pth -[2023-10-12 06:59:11,313][78091] Updated weights for policy 0, policy_version 88230 (0.0009) -[2023-10-12 06:59:11,695][78091] Updated weights for policy 0, policy_version 88240 (0.0007) -[2023-10-12 06:59:12,068][78091] Updated weights for policy 0, policy_version 88250 (0.0007) -[2023-10-12 06:59:12,677][78123] Updated weights for policy 1, policy_version 87810 (0.0008) -[2023-10-12 06:59:13,047][78123] Updated weights for policy 1, policy_version 87820 (0.0007) -[2023-10-12 06:59:13,425][78123] Updated weights for policy 1, policy_version 87830 (0.0007) -[2023-10-12 06:59:13,793][78123] Updated weights for policy 1, policy_version 87840 (0.0007) -[2023-10-12 06:59:15,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 180322304. Throughput: 0: 1600.3, 1: 1603.1. Samples: 45084322. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:59:15,201][77203] Avg episode reward: [(0, '57.830'), (1, '55.370')] -[2023-10-12 06:59:16,421][78091] Updated weights for policy 0, policy_version 88260 (0.0007) -[2023-10-12 06:59:16,785][78091] Updated weights for policy 0, policy_version 88270 (0.0009) -[2023-10-12 06:59:17,162][78091] Updated weights for policy 0, policy_version 88280 (0.0007) -[2023-10-12 06:59:18,055][78123] Updated weights for policy 1, policy_version 87850 (0.0007) -[2023-10-12 06:59:18,426][78123] Updated weights for policy 1, policy_version 87860 (0.0009) -[2023-10-12 06:59:18,796][78123] Updated weights for policy 1, policy_version 87870 (0.0007) -[2023-10-12 06:59:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 180387840. Throughput: 0: 1600.7, 1: 1586.3. Samples: 45103074. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:59:20,202][77203] Avg episode reward: [(0, '55.390'), (1, '51.050')] -[2023-10-12 06:59:21,417][78091] Updated weights for policy 0, policy_version 88290 (0.0008) -[2023-10-12 06:59:21,786][78091] Updated weights for policy 0, policy_version 88300 (0.0011) -[2023-10-12 06:59:22,149][78091] Updated weights for policy 0, policy_version 88310 (0.0010) -[2023-10-12 06:59:22,527][78091] Updated weights for policy 0, policy_version 88320 (0.0009) -[2023-10-12 06:59:23,204][78123] Updated weights for policy 1, policy_version 87880 (0.0008) -[2023-10-12 06:59:23,561][78123] Updated weights for policy 1, policy_version 87890 (0.0007) -[2023-10-12 06:59:23,929][78123] Updated weights for policy 1, policy_version 87900 (0.0008) -[2023-10-12 06:59:25,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 180453376. Throughput: 0: 1596.7, 1: 1588.6. Samples: 45122360. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 06:59:25,202][77203] Avg episode reward: [(0, '57.780'), (1, '50.610')] -[2023-10-12 06:59:26,992][78091] Updated weights for policy 0, policy_version 88330 (0.0010) -[2023-10-12 06:59:27,367][78091] Updated weights for policy 0, policy_version 88340 (0.0008) -[2023-10-12 06:59:27,735][78091] Updated weights for policy 0, policy_version 88350 (0.0008) -[2023-10-12 06:59:28,187][78123] Updated weights for policy 1, policy_version 87910 (0.0007) -[2023-10-12 06:59:28,555][78123] Updated weights for policy 1, policy_version 87920 (0.0008) -[2023-10-12 06:59:28,921][78123] Updated weights for policy 1, policy_version 87930 (0.0008) -[2023-10-12 06:59:30,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 180518912. Throughput: 0: 1595.3, 1: 1606.6. Samples: 45132118. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 06:59:30,201][77203] Avg episode reward: [(0, '52.520'), (1, '49.050')] -[2023-10-12 06:59:32,053][78091] Updated weights for policy 0, policy_version 88360 (0.0008) -[2023-10-12 06:59:32,418][78091] Updated weights for policy 0, policy_version 88370 (0.0009) -[2023-10-12 06:59:32,785][78091] Updated weights for policy 0, policy_version 88380 (0.0007) -[2023-10-12 06:59:33,305][78123] Updated weights for policy 1, policy_version 87940 (0.0009) -[2023-10-12 06:59:33,667][78123] Updated weights for policy 1, policy_version 87950 (0.0009) -[2023-10-12 06:59:34,038][78123] Updated weights for policy 1, policy_version 87960 (0.0011) -[2023-10-12 06:59:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 180584448. Throughput: 0: 1594.7, 1: 1596.4. Samples: 45151044. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 06:59:35,202][77203] Avg episode reward: [(0, '58.220'), (1, '44.920')] -[2023-10-12 06:59:37,226][78091] Updated weights for policy 0, policy_version 88390 (0.0009) -[2023-10-12 06:59:37,592][78091] Updated weights for policy 0, policy_version 88400 (0.0008) -[2023-10-12 06:59:37,963][78091] Updated weights for policy 0, policy_version 88410 (0.0009) -[2023-10-12 06:59:38,414][78123] Updated weights for policy 1, policy_version 87970 (0.0010) -[2023-10-12 06:59:38,779][78123] Updated weights for policy 1, policy_version 87980 (0.0009) -[2023-10-12 06:59:39,150][78123] Updated weights for policy 1, policy_version 87990 (0.0007) -[2023-10-12 06:59:39,506][78123] Updated weights for policy 1, policy_version 88000 (0.0010) -[2023-10-12 06:59:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 180649984. Throughput: 0: 1594.7, 1: 1579.8. Samples: 45169722. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 06:59:40,201][77203] Avg episode reward: [(0, '61.150'), (1, '45.100')] -[2023-10-12 06:59:42,262][78091] Updated weights for policy 0, policy_version 88420 (0.0009) -[2023-10-12 06:59:42,627][78091] Updated weights for policy 0, policy_version 88430 (0.0009) -[2023-10-12 06:59:42,998][78091] Updated weights for policy 0, policy_version 88440 (0.0009) -[2023-10-12 06:59:44,020][78123] Updated weights for policy 1, policy_version 88010 (0.0010) -[2023-10-12 06:59:44,389][78123] Updated weights for policy 1, policy_version 88020 (0.0011) -[2023-10-12 06:59:44,767][78123] Updated weights for policy 1, policy_version 88030 (0.0010) -[2023-10-12 06:59:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 180715520. Throughput: 0: 1603.1, 1: 1593.2. Samples: 45179886. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 06:59:45,202][77203] Avg episode reward: [(0, '57.320'), (1, '54.540')] -[2023-10-12 06:59:47,438][78091] Updated weights for policy 0, policy_version 88450 (0.0008) -[2023-10-12 06:59:47,805][78091] Updated weights for policy 0, policy_version 88460 (0.0010) -[2023-10-12 06:59:48,173][78091] Updated weights for policy 0, policy_version 88470 (0.0008) -[2023-10-12 06:59:48,541][78091] Updated weights for policy 0, policy_version 88480 (0.0007) -[2023-10-12 06:59:49,134][78123] Updated weights for policy 1, policy_version 88040 (0.0011) -[2023-10-12 06:59:49,503][78123] Updated weights for policy 1, policy_version 88050 (0.0010) -[2023-10-12 06:59:49,869][78123] Updated weights for policy 1, policy_version 88060 (0.0008) -[2023-10-12 06:59:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 180781056. Throughput: 0: 1585.9, 1: 1606.3. Samples: 45198800. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 06:59:50,202][77203] Avg episode reward: [(0, '49.180'), (1, '59.690')] -[2023-10-12 06:59:52,880][78091] Updated weights for policy 0, policy_version 88490 (0.0008) -[2023-10-12 06:59:53,250][78091] Updated weights for policy 0, policy_version 88500 (0.0010) -[2023-10-12 06:59:53,615][78091] Updated weights for policy 0, policy_version 88510 (0.0010) -[2023-10-12 06:59:54,384][78123] Updated weights for policy 1, policy_version 88070 (0.0009) -[2023-10-12 06:59:54,772][78123] Updated weights for policy 1, policy_version 88080 (0.0007) -[2023-10-12 06:59:55,132][78123] Updated weights for policy 1, policy_version 88090 (0.0007) -[2023-10-12 06:59:55,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 180813824. Throughput: 0: 1582.1, 1: 1592.5. Samples: 45217632. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 06:59:55,202][77203] Avg episode reward: [(0, '54.960'), (1, '54.160')] -[2023-10-12 06:59:57,898][78091] Updated weights for policy 0, policy_version 88520 (0.0011) -[2023-10-12 06:59:58,276][78091] Updated weights for policy 0, policy_version 88530 (0.0010) -[2023-10-12 06:59:58,652][78091] Updated weights for policy 0, policy_version 88540 (0.0008) -[2023-10-12 06:59:59,367][78123] Updated weights for policy 1, policy_version 88100 (0.0009) -[2023-10-12 06:59:59,730][78123] Updated weights for policy 1, policy_version 88110 (0.0009) -[2023-10-12 07:00:00,094][78123] Updated weights for policy 1, policy_version 88120 (0.0008) -[2023-10-12 07:00:00,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 180879360. Throughput: 0: 1604.4, 1: 1581.3. Samples: 45227682. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 07:00:00,201][77203] Avg episode reward: [(0, '57.320'), (1, '42.850')] -[2023-10-12 07:00:02,978][78091] Updated weights for policy 0, policy_version 88550 (0.0008) -[2023-10-12 07:00:03,342][78091] Updated weights for policy 0, policy_version 88560 (0.0009) -[2023-10-12 07:00:03,706][78091] Updated weights for policy 0, policy_version 88570 (0.0009) -[2023-10-12 07:00:04,463][78123] Updated weights for policy 1, policy_version 88130 (0.0010) -[2023-10-12 07:00:04,838][78123] Updated weights for policy 1, policy_version 88140 (0.0008) -[2023-10-12 07:00:05,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 180944896. Throughput: 0: 1583.9, 1: 1603.1. Samples: 45246486. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 07:00:05,201][77203] Avg episode reward: [(0, '50.590'), (1, '43.700')] -[2023-10-12 07:00:05,203][78123] Updated weights for policy 1, policy_version 88150 (0.0008) -[2023-10-12 07:00:05,583][78123] Updated weights for policy 1, policy_version 88160 (0.0010) -[2023-10-12 07:00:07,953][78091] Updated weights for policy 0, policy_version 88580 (0.0010) -[2023-10-12 07:00:08,331][78091] Updated weights for policy 0, policy_version 88590 (0.0009) -[2023-10-12 07:00:08,703][78091] Updated weights for policy 0, policy_version 88600 (0.0008) -[2023-10-12 07:00:09,787][78123] Updated weights for policy 1, policy_version 88170 (0.0008) -[2023-10-12 07:00:10,159][78123] Updated weights for policy 1, policy_version 88180 (0.0007) -[2023-10-12 07:00:10,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 181010432. Throughput: 0: 1586.3, 1: 1598.4. Samples: 45265672. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 07:00:10,202][77203] Avg episode reward: [(0, '61.280'), (1, '45.590')] -[2023-10-12 07:00:10,541][78123] Updated weights for policy 1, policy_version 88190 (0.0008) -[2023-10-12 07:00:13,048][78091] Updated weights for policy 0, policy_version 88610 (0.0011) -[2023-10-12 07:00:13,416][78091] Updated weights for policy 0, policy_version 88620 (0.0008) -[2023-10-12 07:00:13,790][78091] Updated weights for policy 0, policy_version 88630 (0.0011) -[2023-10-12 07:00:14,157][78091] Updated weights for policy 0, policy_version 88640 (0.0010) -[2023-10-12 07:00:14,921][78123] Updated weights for policy 1, policy_version 88200 (0.0008) -[2023-10-12 07:00:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 181075968. Throughput: 0: 1611.9, 1: 1580.1. Samples: 45275756. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 07:00:15,201][77203] Avg episode reward: [(0, '55.000'), (1, '52.480')] -[2023-10-12 07:00:15,294][78123] Updated weights for policy 1, policy_version 88210 (0.0007) -[2023-10-12 07:00:15,668][78123] Updated weights for policy 1, policy_version 88220 (0.0008) -[2023-10-12 07:00:18,411][78091] Updated weights for policy 0, policy_version 88650 (0.0008) -[2023-10-12 07:00:18,787][78091] Updated weights for policy 0, policy_version 88660 (0.0008) -[2023-10-12 07:00:19,161][78091] Updated weights for policy 0, policy_version 88670 (0.0010) -[2023-10-12 07:00:19,908][78123] Updated weights for policy 1, policy_version 88230 (0.0008) -[2023-10-12 07:00:20,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 181141504. Throughput: 0: 1594.0, 1: 1591.9. Samples: 45294408. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-12 07:00:20,202][77203] Avg episode reward: [(0, '59.770'), (1, '56.700')] -[2023-10-12 07:00:20,272][78123] Updated weights for policy 1, policy_version 88240 (0.0008) -[2023-10-12 07:00:20,637][78123] Updated weights for policy 1, policy_version 88250 (0.0009) -[2023-10-12 07:00:23,374][78091] Updated weights for policy 0, policy_version 88680 (0.0010) -[2023-10-12 07:00:23,732][78091] Updated weights for policy 0, policy_version 88690 (0.0009) -[2023-10-12 07:00:24,106][78091] Updated weights for policy 0, policy_version 88700 (0.0008) -[2023-10-12 07:00:25,028][78123] Updated weights for policy 1, policy_version 88260 (0.0010) -[2023-10-12 07:00:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 181207040. Throughput: 0: 1586.3, 1: 1610.8. Samples: 45313590. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-12 07:00:25,201][77203] Avg episode reward: [(0, '67.440'), (1, '56.200')] -[2023-10-12 07:00:25,393][78123] Updated weights for policy 1, policy_version 88270 (0.0011) -[2023-10-12 07:00:25,760][78123] Updated weights for policy 1, policy_version 88280 (0.0010) -[2023-10-12 07:00:28,568][78091] Updated weights for policy 0, policy_version 88710 (0.0008) -[2023-10-12 07:00:28,943][78091] Updated weights for policy 0, policy_version 88720 (0.0009) -[2023-10-12 07:00:29,323][78091] Updated weights for policy 0, policy_version 88730 (0.0009) -[2023-10-12 07:00:29,922][78123] Updated weights for policy 1, policy_version 88290 (0.0010) -[2023-10-12 07:00:30,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 181272576. Throughput: 0: 1602.3, 1: 1584.0. Samples: 45323268. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-12 07:00:30,201][77203] Avg episode reward: [(0, '57.400'), (1, '51.170')] -[2023-10-12 07:00:30,293][78123] Updated weights for policy 1, policy_version 88300 (0.0009) -[2023-10-12 07:00:30,646][78123] Updated weights for policy 1, policy_version 88310 (0.0009) -[2023-10-12 07:00:31,018][78123] Updated weights for policy 1, policy_version 88320 (0.0011) -[2023-10-12 07:00:33,669][78091] Updated weights for policy 0, policy_version 88740 (0.0008) -[2023-10-12 07:00:34,047][78091] Updated weights for policy 0, policy_version 88750 (0.0009) -[2023-10-12 07:00:34,416][78091] Updated weights for policy 0, policy_version 88760 (0.0010) -[2023-10-12 07:00:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 181338112. Throughput: 0: 1611.3, 1: 1586.8. Samples: 45342718. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-12 07:00:35,201][77203] Avg episode reward: [(0, '57.400'), (1, '52.500')] -[2023-10-12 07:00:35,322][78123] Updated weights for policy 1, policy_version 88330 (0.0008) -[2023-10-12 07:00:35,674][78123] Updated weights for policy 1, policy_version 88340 (0.0008) -[2023-10-12 07:00:36,042][78123] Updated weights for policy 1, policy_version 88350 (0.0007) -[2023-10-12 07:00:38,660][78091] Updated weights for policy 0, policy_version 88770 (0.0009) -[2023-10-12 07:00:39,034][78091] Updated weights for policy 0, policy_version 88780 (0.0008) -[2023-10-12 07:00:39,393][78091] Updated weights for policy 0, policy_version 88790 (0.0009) -[2023-10-12 07:00:39,760][78091] Updated weights for policy 0, policy_version 88800 (0.0008) -[2023-10-12 07:00:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 181403648. Throughput: 0: 1591.8, 1: 1597.8. Samples: 45361164. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-12 07:00:40,202][77203] Avg episode reward: [(0, '57.380'), (1, '47.550')] -[2023-10-12 07:00:40,675][78123] Updated weights for policy 1, policy_version 88360 (0.0008) -[2023-10-12 07:00:41,048][78123] Updated weights for policy 1, policy_version 88370 (0.0008) -[2023-10-12 07:00:41,419][78123] Updated weights for policy 1, policy_version 88380 (0.0009) -[2023-10-12 07:00:44,202][78091] Updated weights for policy 0, policy_version 88810 (0.0009) -[2023-10-12 07:00:44,581][78091] Updated weights for policy 0, policy_version 88820 (0.0009) -[2023-10-12 07:00:44,950][78091] Updated weights for policy 0, policy_version 88830 (0.0010) -[2023-10-12 07:00:45,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 181469184. Throughput: 0: 1597.6, 1: 1584.7. Samples: 45370886. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-12 07:00:45,202][77203] Avg episode reward: [(0, '60.330'), (1, '50.090')] -[2023-10-12 07:00:45,770][78123] Updated weights for policy 1, policy_version 88390 (0.0007) -[2023-10-12 07:00:46,126][78123] Updated weights for policy 1, policy_version 88400 (0.0009) -[2023-10-12 07:00:46,504][78123] Updated weights for policy 1, policy_version 88410 (0.0009) -[2023-10-12 07:00:48,981][78091] Updated weights for policy 0, policy_version 88840 (0.0009) -[2023-10-12 07:00:49,344][78091] Updated weights for policy 0, policy_version 88850 (0.0009) -[2023-10-12 07:00:49,721][78091] Updated weights for policy 0, policy_version 88860 (0.0008) -[2023-10-12 07:00:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 181534720. Throughput: 0: 1615.9, 1: 1581.8. Samples: 45390380. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-12 07:00:50,201][77203] Avg episode reward: [(0, '53.230'), (1, '51.530')] -[2023-10-12 07:00:50,813][78123] Updated weights for policy 1, policy_version 88420 (0.0008) -[2023-10-12 07:00:51,179][78123] Updated weights for policy 1, policy_version 88430 (0.0008) -[2023-10-12 07:00:51,539][78123] Updated weights for policy 1, policy_version 88440 (0.0007) -[2023-10-12 07:00:54,074][78091] Updated weights for policy 0, policy_version 88870 (0.0007) -[2023-10-12 07:00:54,451][78091] Updated weights for policy 0, policy_version 88880 (0.0008) -[2023-10-12 07:00:54,817][78091] Updated weights for policy 0, policy_version 88890 (0.0008) -[2023-10-12 07:00:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 181600256. Throughput: 0: 1602.2, 1: 1590.8. Samples: 45409358. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-12 07:00:55,201][77203] Avg episode reward: [(0, '56.150'), (1, '54.770')] -[2023-10-12 07:00:55,910][78123] Updated weights for policy 1, policy_version 88450 (0.0007) -[2023-10-12 07:00:56,280][78123] Updated weights for policy 1, policy_version 88460 (0.0008) -[2023-10-12 07:00:56,659][78123] Updated weights for policy 1, policy_version 88470 (0.0009) -[2023-10-12 07:00:57,023][78123] Updated weights for policy 1, policy_version 88480 (0.0008) -[2023-10-12 07:00:58,970][78091] Updated weights for policy 0, policy_version 88900 (0.0009) -[2023-10-12 07:00:59,345][78091] Updated weights for policy 0, policy_version 88910 (0.0008) -[2023-10-12 07:00:59,715][78091] Updated weights for policy 0, policy_version 88920 (0.0009) -[2023-10-12 07:01:00,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 181665792. Throughput: 0: 1598.4, 1: 1583.2. Samples: 45418932. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-12 07:01:00,202][77203] Avg episode reward: [(0, '58.590'), (1, '48.220')] -[2023-10-12 07:01:01,322][78123] Updated weights for policy 1, policy_version 88490 (0.0009) -[2023-10-12 07:01:01,682][78123] Updated weights for policy 1, policy_version 88500 (0.0009) -[2023-10-12 07:01:02,057][78123] Updated weights for policy 1, policy_version 88510 (0.0008) -[2023-10-12 07:01:03,963][78091] Updated weights for policy 0, policy_version 88930 (0.0009) -[2023-10-12 07:01:04,337][78091] Updated weights for policy 0, policy_version 88940 (0.0009) -[2023-10-12 07:01:04,706][78091] Updated weights for policy 0, policy_version 88950 (0.0008) -[2023-10-12 07:01:05,081][78091] Updated weights for policy 0, policy_version 88960 (0.0009) -[2023-10-12 07:01:05,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 181731328. Throughput: 0: 1618.5, 1: 1586.6. Samples: 45438640. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-12 07:01:05,202][77203] Avg episode reward: [(0, '58.070'), (1, '49.780')] -[2023-10-12 07:01:06,305][78123] Updated weights for policy 1, policy_version 88520 (0.0008) -[2023-10-12 07:01:06,670][78123] Updated weights for policy 1, policy_version 88530 (0.0009) -[2023-10-12 07:01:07,044][78123] Updated weights for policy 1, policy_version 88540 (0.0008) -[2023-10-12 07:01:09,423][78091] Updated weights for policy 0, policy_version 88970 (0.0009) -[2023-10-12 07:01:09,800][78091] Updated weights for policy 0, policy_version 88980 (0.0008) -[2023-10-12 07:01:10,168][78091] Updated weights for policy 0, policy_version 88990 (0.0008) -[2023-10-12 07:01:10,201][77203] Fps is (10 sec: 9830.6, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 181764096. Throughput: 0: 1615.4, 1: 1589.7. Samples: 45457818. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-12 07:01:10,201][77203] Avg episode reward: [(0, '56.450'), (1, '52.180')] -[2023-10-12 07:01:10,208][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000088544_90669056.pth... -[2023-10-12 07:01:10,241][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000088992_91127808.pth... -[2023-10-12 07:01:10,242][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000087072_89161728.pth -[2023-10-12 07:01:10,274][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000087488_89587712.pth -[2023-10-12 07:01:11,324][78123] Updated weights for policy 1, policy_version 88550 (0.0010) -[2023-10-12 07:01:11,692][78123] Updated weights for policy 1, policy_version 88560 (0.0009) -[2023-10-12 07:01:12,058][78123] Updated weights for policy 1, policy_version 88570 (0.0010) -[2023-10-12 07:01:14,305][78091] Updated weights for policy 0, policy_version 89000 (0.0007) -[2023-10-12 07:01:14,681][78091] Updated weights for policy 0, policy_version 89010 (0.0009) -[2023-10-12 07:01:15,053][78091] Updated weights for policy 0, policy_version 89020 (0.0008) -[2023-10-12 07:01:15,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 181862400. Throughput: 0: 1611.4, 1: 1586.8. Samples: 45467184. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-12 07:01:15,201][77203] Avg episode reward: [(0, '54.960'), (1, '50.240')] -[2023-10-12 07:01:16,278][78123] Updated weights for policy 1, policy_version 88580 (0.0009) -[2023-10-12 07:01:16,636][78123] Updated weights for policy 1, policy_version 88590 (0.0009) -[2023-10-12 07:01:17,003][78123] Updated weights for policy 1, policy_version 88600 (0.0008) -[2023-10-12 07:01:19,463][78091] Updated weights for policy 0, policy_version 89030 (0.0009) -[2023-10-12 07:01:19,834][78091] Updated weights for policy 0, policy_version 89040 (0.0009) -[2023-10-12 07:01:20,193][78091] Updated weights for policy 0, policy_version 89050 (0.0008) -[2023-10-12 07:01:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 181895168. Throughput: 0: 1616.0, 1: 1589.4. Samples: 45486962. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-12 07:01:20,202][77203] Avg episode reward: [(0, '57.880'), (1, '52.980')] -[2023-10-12 07:01:21,485][78123] Updated weights for policy 1, policy_version 88610 (0.0008) -[2023-10-12 07:01:21,856][78123] Updated weights for policy 1, policy_version 88620 (0.0009) -[2023-10-12 07:01:22,224][78123] Updated weights for policy 1, policy_version 88630 (0.0007) -[2023-10-12 07:01:22,582][78123] Updated weights for policy 1, policy_version 88640 (0.0009) -[2023-10-12 07:01:24,447][78091] Updated weights for policy 0, policy_version 89060 (0.0009) -[2023-10-12 07:01:24,817][78091] Updated weights for policy 0, policy_version 89070 (0.0007) -[2023-10-12 07:01:25,183][78091] Updated weights for policy 0, policy_version 89080 (0.0007) -[2023-10-12 07:01:25,201][77203] Fps is (10 sec: 9830.2, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 181960704. Throughput: 0: 1630.0, 1: 1592.2. Samples: 45506162. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:01:25,202][77203] Avg episode reward: [(0, '56.340'), (1, '52.490')] -[2023-10-12 07:01:27,000][78123] Updated weights for policy 1, policy_version 88650 (0.0010) -[2023-10-12 07:01:27,361][78123] Updated weights for policy 1, policy_version 88660 (0.0007) -[2023-10-12 07:01:27,722][78123] Updated weights for policy 1, policy_version 88670 (0.0010) -[2023-10-12 07:01:29,283][78091] Updated weights for policy 0, policy_version 89090 (0.0009) -[2023-10-12 07:01:29,676][78091] Updated weights for policy 0, policy_version 89100 (0.0008) -[2023-10-12 07:01:30,047][78091] Updated weights for policy 0, policy_version 89110 (0.0008) -[2023-10-12 07:01:30,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 182026240. Throughput: 0: 1614.7, 1: 1594.1. Samples: 45515282. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:01:30,201][77203] Avg episode reward: [(0, '59.090'), (1, '53.950')] -[2023-10-12 07:01:30,416][78091] Updated weights for policy 0, policy_version 89120 (0.0008) -[2023-10-12 07:01:32,133][78123] Updated weights for policy 1, policy_version 88680 (0.0008) -[2023-10-12 07:01:32,501][78123] Updated weights for policy 1, policy_version 88690 (0.0008) -[2023-10-12 07:01:32,865][78123] Updated weights for policy 1, policy_version 88700 (0.0007) -[2023-10-12 07:01:34,683][78091] Updated weights for policy 0, policy_version 89130 (0.0011) -[2023-10-12 07:01:35,057][78091] Updated weights for policy 0, policy_version 89140 (0.0010) -[2023-10-12 07:01:35,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 182091776. Throughput: 0: 1617.0, 1: 1590.9. Samples: 45534736. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:01:35,201][77203] Avg episode reward: [(0, '59.130'), (1, '52.470')] -[2023-10-12 07:01:35,413][78091] Updated weights for policy 0, policy_version 89150 (0.0007) -[2023-10-12 07:01:37,112][78123] Updated weights for policy 1, policy_version 88710 (0.0009) -[2023-10-12 07:01:37,470][78123] Updated weights for policy 1, policy_version 88720 (0.0010) -[2023-10-12 07:01:37,837][78123] Updated weights for policy 1, policy_version 88730 (0.0010) -[2023-10-12 07:01:39,744][78091] Updated weights for policy 0, policy_version 89160 (0.0008) -[2023-10-12 07:01:40,128][78091] Updated weights for policy 0, policy_version 89170 (0.0007) -[2023-10-12 07:01:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 182157312. Throughput: 0: 1624.6, 1: 1587.0. Samples: 45553880. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:01:40,201][77203] Avg episode reward: [(0, '56.130'), (1, '47.970')] -[2023-10-12 07:01:40,497][78091] Updated weights for policy 0, policy_version 89180 (0.0008) -[2023-10-12 07:01:42,131][78123] Updated weights for policy 1, policy_version 88740 (0.0009) -[2023-10-12 07:01:42,493][78123] Updated weights for policy 1, policy_version 88750 (0.0009) -[2023-10-12 07:01:42,870][78123] Updated weights for policy 1, policy_version 88760 (0.0007) -[2023-10-12 07:01:44,714][78091] Updated weights for policy 0, policy_version 89190 (0.0009) -[2023-10-12 07:01:45,080][78091] Updated weights for policy 0, policy_version 89200 (0.0009) -[2023-10-12 07:01:45,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 182222848. Throughput: 0: 1609.2, 1: 1600.6. Samples: 45563370. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:01:45,202][77203] Avg episode reward: [(0, '59.140'), (1, '47.450')] -[2023-10-12 07:01:45,445][78091] Updated weights for policy 0, policy_version 89210 (0.0011) -[2023-10-12 07:01:47,018][78123] Updated weights for policy 1, policy_version 88770 (0.0007) -[2023-10-12 07:01:47,376][78123] Updated weights for policy 1, policy_version 88780 (0.0008) -[2023-10-12 07:01:47,738][78123] Updated weights for policy 1, policy_version 88790 (0.0009) -[2023-10-12 07:01:48,104][78123] Updated weights for policy 1, policy_version 88800 (0.0008) -[2023-10-12 07:01:49,797][78091] Updated weights for policy 0, policy_version 89220 (0.0008) -[2023-10-12 07:01:50,164][78091] Updated weights for policy 0, policy_version 89230 (0.0009) -[2023-10-12 07:01:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 182288384. Throughput: 0: 1604.1, 1: 1593.3. Samples: 45582522. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:01:50,201][77203] Avg episode reward: [(0, '54.810'), (1, '49.400')] -[2023-10-12 07:01:50,538][78091] Updated weights for policy 0, policy_version 89240 (0.0010) -[2023-10-12 07:01:52,375][78123] Updated weights for policy 1, policy_version 88810 (0.0008) -[2023-10-12 07:01:52,744][78123] Updated weights for policy 1, policy_version 88820 (0.0007) -[2023-10-12 07:01:53,115][78123] Updated weights for policy 1, policy_version 88830 (0.0007) -[2023-10-12 07:01:54,749][78091] Updated weights for policy 0, policy_version 89250 (0.0007) -[2023-10-12 07:01:55,127][78091] Updated weights for policy 0, policy_version 89260 (0.0009) -[2023-10-12 07:01:55,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 182353920. Throughput: 0: 1612.1, 1: 1592.2. Samples: 45602014. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:01:55,202][77203] Avg episode reward: [(0, '60.640'), (1, '50.400')] -[2023-10-12 07:01:55,489][78091] Updated weights for policy 0, policy_version 89270 (0.0007) -[2023-10-12 07:01:55,854][78091] Updated weights for policy 0, policy_version 89280 (0.0007) -[2023-10-12 07:01:57,418][78123] Updated weights for policy 1, policy_version 88840 (0.0010) -[2023-10-12 07:01:57,783][78123] Updated weights for policy 1, policy_version 88850 (0.0007) -[2023-10-12 07:01:58,154][78123] Updated weights for policy 1, policy_version 88860 (0.0008) -[2023-10-12 07:02:00,124][78091] Updated weights for policy 0, policy_version 89290 (0.0008) -[2023-10-12 07:02:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 182419456. Throughput: 0: 1597.2, 1: 1610.0. Samples: 45611506. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:02:00,201][77203] Avg episode reward: [(0, '55.000'), (1, '50.410')] -[2023-10-12 07:02:00,496][78091] Updated weights for policy 0, policy_version 89300 (0.0009) -[2023-10-12 07:02:00,870][78091] Updated weights for policy 0, policy_version 89310 (0.0008) -[2023-10-12 07:02:02,455][78123] Updated weights for policy 1, policy_version 88870 (0.0009) -[2023-10-12 07:02:02,824][78123] Updated weights for policy 1, policy_version 88880 (0.0010) -[2023-10-12 07:02:03,200][78123] Updated weights for policy 1, policy_version 88890 (0.0008) -[2023-10-12 07:02:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 182484992. Throughput: 0: 1595.5, 1: 1594.6. Samples: 45630514. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:02:05,201][77203] Avg episode reward: [(0, '57.910'), (1, '48.250')] -[2023-10-12 07:02:05,318][78091] Updated weights for policy 0, policy_version 89320 (0.0007) -[2023-10-12 07:02:05,687][78091] Updated weights for policy 0, policy_version 89330 (0.0007) -[2023-10-12 07:02:06,063][78091] Updated weights for policy 0, policy_version 89340 (0.0008) -[2023-10-12 07:02:07,480][78123] Updated weights for policy 1, policy_version 88900 (0.0009) -[2023-10-12 07:02:07,849][78123] Updated weights for policy 1, policy_version 88910 (0.0007) -[2023-10-12 07:02:08,217][78123] Updated weights for policy 1, policy_version 88920 (0.0007) -[2023-10-12 07:02:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 182550528. Throughput: 0: 1600.5, 1: 1597.2. Samples: 45650056. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:02:10,201][77203] Avg episode reward: [(0, '58.850'), (1, '45.520')] -[2023-10-12 07:02:10,386][78091] Updated weights for policy 0, policy_version 89350 (0.0007) -[2023-10-12 07:02:10,753][78091] Updated weights for policy 0, policy_version 89360 (0.0007) -[2023-10-12 07:02:11,134][78091] Updated weights for policy 0, policy_version 89370 (0.0008) -[2023-10-12 07:02:12,491][78123] Updated weights for policy 1, policy_version 88930 (0.0008) -[2023-10-12 07:02:12,901][78123] Updated weights for policy 1, policy_version 88940 (0.0007) -[2023-10-12 07:02:13,270][78123] Updated weights for policy 1, policy_version 88950 (0.0009) -[2023-10-12 07:02:13,644][78123] Updated weights for policy 1, policy_version 88960 (0.0007) -[2023-10-12 07:02:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 182616064. Throughput: 0: 1589.9, 1: 1617.8. Samples: 45659626. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:02:15,201][77203] Avg episode reward: [(0, '62.650'), (1, '56.720')] -[2023-10-12 07:02:15,647][78091] Updated weights for policy 0, policy_version 89380 (0.0011) -[2023-10-12 07:02:16,019][78091] Updated weights for policy 0, policy_version 89390 (0.0011) -[2023-10-12 07:02:16,395][78091] Updated weights for policy 0, policy_version 89400 (0.0009) -[2023-10-12 07:02:17,886][78123] Updated weights for policy 1, policy_version 88970 (0.0010) -[2023-10-12 07:02:18,264][78123] Updated weights for policy 1, policy_version 88980 (0.0008) -[2023-10-12 07:02:18,636][78123] Updated weights for policy 1, policy_version 88990 (0.0009) -[2023-10-12 07:02:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 182681600. Throughput: 0: 1586.1, 1: 1604.4. Samples: 45678312. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-12 07:02:20,201][77203] Avg episode reward: [(0, '59.610'), (1, '55.700')] -[2023-10-12 07:02:20,678][78091] Updated weights for policy 0, policy_version 89410 (0.0008) -[2023-10-12 07:02:21,053][78091] Updated weights for policy 0, policy_version 89420 (0.0011) -[2023-10-12 07:02:21,414][78091] Updated weights for policy 0, policy_version 89430 (0.0010) -[2023-10-12 07:02:21,779][78091] Updated weights for policy 0, policy_version 89440 (0.0009) -[2023-10-12 07:02:22,979][78123] Updated weights for policy 1, policy_version 89000 (0.0011) -[2023-10-12 07:02:23,354][78123] Updated weights for policy 1, policy_version 89010 (0.0009) -[2023-10-12 07:02:23,719][78123] Updated weights for policy 1, policy_version 89020 (0.0007) -[2023-10-12 07:02:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 182747136. Throughput: 0: 1595.0, 1: 1603.6. Samples: 45697818. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-12 07:02:25,201][77203] Avg episode reward: [(0, '55.770'), (1, '51.000')] -[2023-10-12 07:02:26,036][78091] Updated weights for policy 0, policy_version 89450 (0.0007) -[2023-10-12 07:02:26,401][78091] Updated weights for policy 0, policy_version 89460 (0.0009) -[2023-10-12 07:02:26,778][78091] Updated weights for policy 0, policy_version 89470 (0.0010) -[2023-10-12 07:02:28,223][78123] Updated weights for policy 1, policy_version 89030 (0.0010) -[2023-10-12 07:02:28,596][78123] Updated weights for policy 1, policy_version 89040 (0.0008) -[2023-10-12 07:02:28,970][78123] Updated weights for policy 1, policy_version 89050 (0.0009) -[2023-10-12 07:02:30,201][77203] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 182812672. Throughput: 0: 1589.0, 1: 1615.1. Samples: 45707554. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-12 07:02:30,202][77203] Avg episode reward: [(0, '60.460'), (1, '52.960')] -[2023-10-12 07:02:31,204][78091] Updated weights for policy 0, policy_version 89480 (0.0010) -[2023-10-12 07:02:31,570][78091] Updated weights for policy 0, policy_version 89490 (0.0007) -[2023-10-12 07:02:31,942][78091] Updated weights for policy 0, policy_version 89500 (0.0007) -[2023-10-12 07:02:33,298][78123] Updated weights for policy 1, policy_version 89060 (0.0010) -[2023-10-12 07:02:33,669][78123] Updated weights for policy 1, policy_version 89070 (0.0009) -[2023-10-12 07:02:34,033][78123] Updated weights for policy 1, policy_version 89080 (0.0010) -[2023-10-12 07:02:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 182878208. Throughput: 0: 1589.2, 1: 1607.2. Samples: 45726358. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-12 07:02:35,202][77203] Avg episode reward: [(0, '54.650'), (1, '53.000')] -[2023-10-12 07:02:36,241][78091] Updated weights for policy 0, policy_version 89510 (0.0009) -[2023-10-12 07:02:36,606][78091] Updated weights for policy 0, policy_version 89520 (0.0011) -[2023-10-12 07:02:36,978][78091] Updated weights for policy 0, policy_version 89530 (0.0008) -[2023-10-12 07:02:38,436][78123] Updated weights for policy 1, policy_version 89090 (0.0008) -[2023-10-12 07:02:38,810][78123] Updated weights for policy 1, policy_version 89100 (0.0008) -[2023-10-12 07:02:39,183][78123] Updated weights for policy 1, policy_version 89110 (0.0008) -[2023-10-12 07:02:39,543][78123] Updated weights for policy 1, policy_version 89120 (0.0010) -[2023-10-12 07:02:40,201][77203] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 182943744. Throughput: 0: 1591.5, 1: 1590.4. Samples: 45745198. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-12 07:02:40,202][77203] Avg episode reward: [(0, '58.210'), (1, '48.780')] -[2023-10-12 07:02:41,337][78091] Updated weights for policy 0, policy_version 89540 (0.0008) -[2023-10-12 07:02:41,704][78091] Updated weights for policy 0, policy_version 89550 (0.0011) -[2023-10-12 07:02:42,078][78091] Updated weights for policy 0, policy_version 89560 (0.0008) -[2023-10-12 07:02:43,941][78123] Updated weights for policy 1, policy_version 89130 (0.0007) -[2023-10-12 07:02:44,295][78123] Updated weights for policy 1, policy_version 89140 (0.0008) -[2023-10-12 07:02:44,665][78123] Updated weights for policy 1, policy_version 89150 (0.0008) -[2023-10-12 07:02:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 183009280. Throughput: 0: 1586.1, 1: 1603.6. Samples: 45755042. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-12 07:02:45,201][77203] Avg episode reward: [(0, '54.350'), (1, '45.320')] -[2023-10-12 07:02:46,407][78091] Updated weights for policy 0, policy_version 89570 (0.0009) -[2023-10-12 07:02:46,776][78091] Updated weights for policy 0, policy_version 89580 (0.0009) -[2023-10-12 07:02:47,135][78091] Updated weights for policy 0, policy_version 89590 (0.0009) -[2023-10-12 07:02:47,514][78091] Updated weights for policy 0, policy_version 89600 (0.0008) -[2023-10-12 07:02:48,902][78123] Updated weights for policy 1, policy_version 89160 (0.0011) -[2023-10-12 07:02:49,266][78123] Updated weights for policy 1, policy_version 89170 (0.0009) -[2023-10-12 07:02:49,632][78123] Updated weights for policy 1, policy_version 89180 (0.0007) -[2023-10-12 07:02:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 183074816. Throughput: 0: 1591.5, 1: 1611.3. Samples: 45774640. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-12 07:02:50,201][77203] Avg episode reward: [(0, '54.440'), (1, '49.640')] -[2023-10-12 07:02:51,756][78091] Updated weights for policy 0, policy_version 89610 (0.0009) -[2023-10-12 07:02:52,123][78091] Updated weights for policy 0, policy_version 89620 (0.0007) -[2023-10-12 07:02:52,483][78091] Updated weights for policy 0, policy_version 89630 (0.0010) -[2023-10-12 07:02:53,973][78123] Updated weights for policy 1, policy_version 89190 (0.0009) -[2023-10-12 07:02:54,351][78123] Updated weights for policy 1, policy_version 89200 (0.0011) -[2023-10-12 07:02:54,724][78123] Updated weights for policy 1, policy_version 89210 (0.0008) -[2023-10-12 07:02:55,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 183140352. Throughput: 0: 1589.5, 1: 1593.0. Samples: 45793268. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-12 07:02:55,201][77203] Avg episode reward: [(0, '56.750'), (1, '42.020')] -[2023-10-12 07:02:56,969][78091] Updated weights for policy 0, policy_version 89640 (0.0008) -[2023-10-12 07:02:57,330][78091] Updated weights for policy 0, policy_version 89650 (0.0007) -[2023-10-12 07:02:57,706][78091] Updated weights for policy 0, policy_version 89660 (0.0008) -[2023-10-12 07:02:58,953][78123] Updated weights for policy 1, policy_version 89220 (0.0008) -[2023-10-12 07:02:59,348][78123] Updated weights for policy 1, policy_version 89230 (0.0009) -[2023-10-12 07:02:59,716][78123] Updated weights for policy 1, policy_version 89240 (0.0008) -[2023-10-12 07:03:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 183205888. Throughput: 0: 1589.8, 1: 1596.3. Samples: 45802998. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-12 07:03:00,202][77203] Avg episode reward: [(0, '57.790'), (1, '50.170')] -[2023-10-12 07:03:02,015][78091] Updated weights for policy 0, policy_version 89670 (0.0008) -[2023-10-12 07:03:02,397][78091] Updated weights for policy 0, policy_version 89680 (0.0008) -[2023-10-12 07:03:02,756][78091] Updated weights for policy 0, policy_version 89690 (0.0007) -[2023-10-12 07:03:03,889][78123] Updated weights for policy 1, policy_version 89250 (0.0008) -[2023-10-12 07:03:04,260][78123] Updated weights for policy 1, policy_version 89260 (0.0009) -[2023-10-12 07:03:04,640][78123] Updated weights for policy 1, policy_version 89270 (0.0011) -[2023-10-12 07:03:05,011][78123] Updated weights for policy 1, policy_version 89280 (0.0009) -[2023-10-12 07:03:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 183271424. Throughput: 0: 1590.2, 1: 1609.8. Samples: 45822314. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-12 07:03:05,201][77203] Avg episode reward: [(0, '53.290'), (1, '45.430')] -[2023-10-12 07:03:06,863][78091] Updated weights for policy 0, policy_version 89700 (0.0008) -[2023-10-12 07:03:07,234][78091] Updated weights for policy 0, policy_version 89710 (0.0007) -[2023-10-12 07:03:07,596][78091] Updated weights for policy 0, policy_version 89720 (0.0008) -[2023-10-12 07:03:09,295][78123] Updated weights for policy 1, policy_version 89290 (0.0008) -[2023-10-12 07:03:09,661][78123] Updated weights for policy 1, policy_version 89300 (0.0009) -[2023-10-12 07:03:10,033][78123] Updated weights for policy 1, policy_version 89310 (0.0009) -[2023-10-12 07:03:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 183336960. Throughput: 0: 1594.3, 1: 1594.8. Samples: 45841324. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-12 07:03:10,202][77203] Avg episode reward: [(0, '53.290'), (1, '47.780')] -[2023-10-12 07:03:10,210][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000089312_91455488.pth... -[2023-10-12 07:03:10,210][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000089728_91881472.pth... -[2023-10-12 07:03:10,240][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000087808_89915392.pth -[2023-10-12 07:03:10,244][77950] Saving a milestone ./train_atari/atari_hero_APPO/checkpoint_p1/milestones/checkpoint_000089312_91455488.pth -[2023-10-12 07:03:10,254][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000088224_90341376.pth -[2023-10-12 07:03:10,260][77792] Saving a milestone ./train_atari/atari_hero_APPO/checkpoint_p0/milestones/checkpoint_000089728_91881472.pth -[2023-10-12 07:03:11,780][78091] Updated weights for policy 0, policy_version 89730 (0.0009) -[2023-10-12 07:03:12,140][78091] Updated weights for policy 0, policy_version 89740 (0.0008) -[2023-10-12 07:03:12,509][78091] Updated weights for policy 0, policy_version 89750 (0.0011) -[2023-10-12 07:03:12,895][78091] Updated weights for policy 0, policy_version 89760 (0.0009) -[2023-10-12 07:03:14,341][78123] Updated weights for policy 1, policy_version 89320 (0.0009) -[2023-10-12 07:03:14,712][78123] Updated weights for policy 1, policy_version 89330 (0.0011) -[2023-10-12 07:03:15,071][78123] Updated weights for policy 1, policy_version 89340 (0.0010) -[2023-10-12 07:03:15,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 183369728. Throughput: 0: 1595.8, 1: 1586.4. Samples: 45850754. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:03:15,201][77203] Avg episode reward: [(0, '64.770'), (1, '47.780')] -[2023-10-12 07:03:17,189][78091] Updated weights for policy 0, policy_version 89770 (0.0008) -[2023-10-12 07:03:17,551][78091] Updated weights for policy 0, policy_version 89780 (0.0007) -[2023-10-12 07:03:17,928][78091] Updated weights for policy 0, policy_version 89790 (0.0007) -[2023-10-12 07:03:19,518][78123] Updated weights for policy 1, policy_version 89350 (0.0010) -[2023-10-12 07:03:19,891][78123] Updated weights for policy 1, policy_version 89360 (0.0010) -[2023-10-12 07:03:20,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 183435264. Throughput: 0: 1599.4, 1: 1602.8. Samples: 45870456. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:03:20,201][77203] Avg episode reward: [(0, '55.760'), (1, '57.640')] -[2023-10-12 07:03:20,261][78123] Updated weights for policy 1, policy_version 89370 (0.0008) -[2023-10-12 07:03:22,128][78091] Updated weights for policy 0, policy_version 89800 (0.0008) -[2023-10-12 07:03:22,495][78091] Updated weights for policy 0, policy_version 89810 (0.0009) -[2023-10-12 07:03:22,867][78091] Updated weights for policy 0, policy_version 89820 (0.0009) -[2023-10-12 07:03:24,654][78123] Updated weights for policy 1, policy_version 89380 (0.0007) -[2023-10-12 07:03:25,014][78123] Updated weights for policy 1, policy_version 89390 (0.0008) -[2023-10-12 07:03:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 183500800. Throughput: 0: 1604.8, 1: 1613.7. Samples: 45890030. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:03:25,201][77203] Avg episode reward: [(0, '57.270'), (1, '62.280')] -[2023-10-12 07:03:25,380][78123] Updated weights for policy 1, policy_version 89400 (0.0008) -[2023-10-12 07:03:27,141][78091] Updated weights for policy 0, policy_version 89830 (0.0008) -[2023-10-12 07:03:27,515][78091] Updated weights for policy 0, policy_version 89840 (0.0008) -[2023-10-12 07:03:27,879][78091] Updated weights for policy 0, policy_version 89850 (0.0008) -[2023-10-12 07:03:29,551][78123] Updated weights for policy 1, policy_version 89410 (0.0009) -[2023-10-12 07:03:29,914][78123] Updated weights for policy 1, policy_version 89420 (0.0010) -[2023-10-12 07:03:30,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 183566336. Throughput: 0: 1613.1, 1: 1593.3. Samples: 45899330. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:03:30,202][77203] Avg episode reward: [(0, '54.390'), (1, '57.830')] -[2023-10-12 07:03:30,277][78123] Updated weights for policy 1, policy_version 89430 (0.0009) -[2023-10-12 07:03:30,650][78123] Updated weights for policy 1, policy_version 89440 (0.0009) -[2023-10-12 07:03:32,166][78091] Updated weights for policy 0, policy_version 89860 (0.0008) -[2023-10-12 07:03:32,541][78091] Updated weights for policy 0, policy_version 89870 (0.0010) -[2023-10-12 07:03:32,908][78091] Updated weights for policy 0, policy_version 89880 (0.0011) -[2023-10-12 07:03:35,108][78123] Updated weights for policy 1, policy_version 89450 (0.0009) -[2023-10-12 07:03:35,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 183631872. Throughput: 0: 1602.4, 1: 1595.6. Samples: 45918550. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:03:35,202][77203] Avg episode reward: [(0, '57.290'), (1, '58.060')] -[2023-10-12 07:03:35,479][78123] Updated weights for policy 1, policy_version 89460 (0.0008) -[2023-10-12 07:03:35,845][78123] Updated weights for policy 1, policy_version 89470 (0.0008) -[2023-10-12 07:03:37,222][78091] Updated weights for policy 0, policy_version 89890 (0.0011) -[2023-10-12 07:03:37,586][78091] Updated weights for policy 0, policy_version 89900 (0.0010) -[2023-10-12 07:03:37,953][78091] Updated weights for policy 0, policy_version 89910 (0.0011) -[2023-10-12 07:03:38,325][78091] Updated weights for policy 0, policy_version 89920 (0.0009) -[2023-10-12 07:03:40,011][78123] Updated weights for policy 1, policy_version 89480 (0.0009) -[2023-10-12 07:03:40,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 183697408. Throughput: 0: 1602.8, 1: 1614.7. Samples: 45938060. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:03:40,203][77203] Avg episode reward: [(0, '61.640'), (1, '58.400')] -[2023-10-12 07:03:40,376][78123] Updated weights for policy 1, policy_version 89490 (0.0007) -[2023-10-12 07:03:40,741][78123] Updated weights for policy 1, policy_version 89500 (0.0008) -[2023-10-12 07:03:42,797][78091] Updated weights for policy 0, policy_version 89930 (0.0010) -[2023-10-12 07:03:43,181][78091] Updated weights for policy 0, policy_version 89940 (0.0011) -[2023-10-12 07:03:43,554][78091] Updated weights for policy 0, policy_version 89950 (0.0010) -[2023-10-12 07:03:45,164][78123] Updated weights for policy 1, policy_version 89510 (0.0009) -[2023-10-12 07:03:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 183762944. Throughput: 0: 1615.0, 1: 1594.2. Samples: 45947412. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:03:45,202][77203] Avg episode reward: [(0, '62.530'), (1, '56.170')] -[2023-10-12 07:03:45,543][78123] Updated weights for policy 1, policy_version 89520 (0.0008) -[2023-10-12 07:03:45,898][78123] Updated weights for policy 1, policy_version 89530 (0.0007) -[2023-10-12 07:03:48,004][78091] Updated weights for policy 0, policy_version 89960 (0.0008) -[2023-10-12 07:03:48,378][78091] Updated weights for policy 0, policy_version 89970 (0.0007) -[2023-10-12 07:03:48,744][78091] Updated weights for policy 0, policy_version 89980 (0.0007) -[2023-10-12 07:03:50,201][77203] Fps is (10 sec: 13107.7, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 183828480. Throughput: 0: 1600.1, 1: 1595.2. Samples: 45966104. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:03:50,202][77203] Avg episode reward: [(0, '51.980'), (1, '50.780')] -[2023-10-12 07:03:50,263][78123] Updated weights for policy 1, policy_version 89540 (0.0008) -[2023-10-12 07:03:50,632][78123] Updated weights for policy 1, policy_version 89550 (0.0007) -[2023-10-12 07:03:51,000][78123] Updated weights for policy 1, policy_version 89560 (0.0008) -[2023-10-12 07:03:53,137][78091] Updated weights for policy 0, policy_version 89990 (0.0008) -[2023-10-12 07:03:53,513][78091] Updated weights for policy 0, policy_version 90000 (0.0009) -[2023-10-12 07:03:53,876][78091] Updated weights for policy 0, policy_version 90010 (0.0009) -[2023-10-12 07:03:55,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 183894016. Throughput: 0: 1596.4, 1: 1610.3. Samples: 45985624. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:03:55,202][77203] Avg episode reward: [(0, '53.410'), (1, '54.550')] -[2023-10-12 07:03:55,224][78123] Updated weights for policy 1, policy_version 89570 (0.0010) -[2023-10-12 07:03:55,599][78123] Updated weights for policy 1, policy_version 89580 (0.0010) -[2023-10-12 07:03:55,964][78123] Updated weights for policy 1, policy_version 89590 (0.0010) -[2023-10-12 07:03:56,327][78123] Updated weights for policy 1, policy_version 89600 (0.0010) -[2023-10-12 07:03:58,132][78091] Updated weights for policy 0, policy_version 90020 (0.0009) -[2023-10-12 07:03:58,503][78091] Updated weights for policy 0, policy_version 90030 (0.0008) -[2023-10-12 07:03:58,875][78091] Updated weights for policy 0, policy_version 90040 (0.0009) -[2023-10-12 07:04:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 183959552. Throughput: 0: 1620.6, 1: 1592.3. Samples: 45995334. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:04:00,201][77203] Avg episode reward: [(0, '59.180'), (1, '52.450')] -[2023-10-12 07:04:00,601][78123] Updated weights for policy 1, policy_version 89610 (0.0011) -[2023-10-12 07:04:00,962][78123] Updated weights for policy 1, policy_version 89620 (0.0011) -[2023-10-12 07:04:01,331][78123] Updated weights for policy 1, policy_version 89630 (0.0008) -[2023-10-12 07:04:03,177][78091] Updated weights for policy 0, policy_version 90050 (0.0009) -[2023-10-12 07:04:03,546][78091] Updated weights for policy 0, policy_version 90060 (0.0008) -[2023-10-12 07:04:03,915][78091] Updated weights for policy 0, policy_version 90070 (0.0007) -[2023-10-12 07:04:04,281][78091] Updated weights for policy 0, policy_version 90080 (0.0007) -[2023-10-12 07:04:05,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 184025088. Throughput: 0: 1604.3, 1: 1588.2. Samples: 46014118. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:04:05,202][77203] Avg episode reward: [(0, '62.510'), (1, '44.660')] -[2023-10-12 07:04:05,706][78123] Updated weights for policy 1, policy_version 89640 (0.0008) -[2023-10-12 07:04:06,067][78123] Updated weights for policy 1, policy_version 89650 (0.0008) -[2023-10-12 07:04:06,429][78123] Updated weights for policy 1, policy_version 89660 (0.0007) -[2023-10-12 07:04:08,621][78091] Updated weights for policy 0, policy_version 90090 (0.0010) -[2023-10-12 07:04:09,001][78091] Updated weights for policy 0, policy_version 90100 (0.0010) -[2023-10-12 07:04:09,378][78091] Updated weights for policy 0, policy_version 90110 (0.0008) -[2023-10-12 07:04:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 184090624. Throughput: 0: 1588.6, 1: 1590.0. Samples: 46033066. Policy #0 lag: (min: 30.0, avg: 37.0, max: 62.0) -[2023-10-12 07:04:10,202][77203] Avg episode reward: [(0, '51.930'), (1, '43.160')] -[2023-10-12 07:04:10,929][78123] Updated weights for policy 1, policy_version 89670 (0.0008) -[2023-10-12 07:04:11,300][78123] Updated weights for policy 1, policy_version 89680 (0.0008) -[2023-10-12 07:04:11,664][78123] Updated weights for policy 1, policy_version 89690 (0.0009) -[2023-10-12 07:04:13,570][78091] Updated weights for policy 0, policy_version 90120 (0.0009) -[2023-10-12 07:04:13,938][78091] Updated weights for policy 0, policy_version 90130 (0.0009) -[2023-10-12 07:04:14,309][78091] Updated weights for policy 0, policy_version 90140 (0.0008) -[2023-10-12 07:04:15,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 184156160. Throughput: 0: 1610.9, 1: 1581.2. Samples: 46042974. Policy #0 lag: (min: 30.0, avg: 37.0, max: 62.0) -[2023-10-12 07:04:15,201][77203] Avg episode reward: [(0, '54.820'), (1, '42.990')] -[2023-10-12 07:04:15,964][78123] Updated weights for policy 1, policy_version 89700 (0.0010) -[2023-10-12 07:04:16,339][78123] Updated weights for policy 1, policy_version 89710 (0.0007) -[2023-10-12 07:04:16,710][78123] Updated weights for policy 1, policy_version 89720 (0.0008) -[2023-10-12 07:04:18,597][78091] Updated weights for policy 0, policy_version 90150 (0.0009) -[2023-10-12 07:04:18,970][78091] Updated weights for policy 0, policy_version 90160 (0.0007) -[2023-10-12 07:04:19,339][78091] Updated weights for policy 0, policy_version 90170 (0.0009) -[2023-10-12 07:04:20,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 184221696. Throughput: 0: 1608.2, 1: 1585.2. Samples: 46062254. Policy #0 lag: (min: 30.0, avg: 37.0, max: 62.0) -[2023-10-12 07:04:20,202][77203] Avg episode reward: [(0, '56.730'), (1, '40.150')] -[2023-10-12 07:04:20,890][78123] Updated weights for policy 1, policy_version 89730 (0.0008) -[2023-10-12 07:04:21,253][78123] Updated weights for policy 1, policy_version 89740 (0.0007) -[2023-10-12 07:04:21,624][78123] Updated weights for policy 1, policy_version 89750 (0.0007) -[2023-10-12 07:04:21,983][78123] Updated weights for policy 1, policy_version 89760 (0.0007) -[2023-10-12 07:04:23,559][78091] Updated weights for policy 0, policy_version 90180 (0.0008) -[2023-10-12 07:04:23,931][78091] Updated weights for policy 0, policy_version 90190 (0.0008) -[2023-10-12 07:04:24,304][78091] Updated weights for policy 0, policy_version 90200 (0.0009) -[2023-10-12 07:04:25,201][77203] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 184287232. Throughput: 0: 1591.8, 1: 1587.6. Samples: 46081134. Policy #0 lag: (min: 30.0, avg: 37.0, max: 62.0) -[2023-10-12 07:04:25,202][77203] Avg episode reward: [(0, '56.740'), (1, '41.900')] -[2023-10-12 07:04:26,181][78123] Updated weights for policy 1, policy_version 89770 (0.0012) -[2023-10-12 07:04:26,544][78123] Updated weights for policy 1, policy_version 89780 (0.0008) -[2023-10-12 07:04:26,914][78123] Updated weights for policy 1, policy_version 89790 (0.0009) -[2023-10-12 07:04:28,647][78091] Updated weights for policy 0, policy_version 90210 (0.0008) -[2023-10-12 07:04:29,029][78091] Updated weights for policy 0, policy_version 90220 (0.0008) -[2023-10-12 07:04:29,395][78091] Updated weights for policy 0, policy_version 90230 (0.0008) -[2023-10-12 07:04:29,764][78091] Updated weights for policy 0, policy_version 90240 (0.0010) -[2023-10-12 07:04:30,201][77203] Fps is (10 sec: 13107.7, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 184352768. Throughput: 0: 1605.3, 1: 1584.5. Samples: 46090954. Policy #0 lag: (min: 30.0, avg: 37.0, max: 62.0) -[2023-10-12 07:04:30,201][77203] Avg episode reward: [(0, '57.750'), (1, '44.090')] -[2023-10-12 07:04:31,393][78123] Updated weights for policy 1, policy_version 89800 (0.0009) -[2023-10-12 07:04:31,777][78123] Updated weights for policy 1, policy_version 89810 (0.0009) -[2023-10-12 07:04:32,150][78123] Updated weights for policy 1, policy_version 89820 (0.0008) -[2023-10-12 07:04:34,129][78091] Updated weights for policy 0, policy_version 90250 (0.0009) -[2023-10-12 07:04:34,507][78091] Updated weights for policy 0, policy_version 90260 (0.0009) -[2023-10-12 07:04:34,877][78091] Updated weights for policy 0, policy_version 90270 (0.0009) -[2023-10-12 07:04:35,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 184418304. Throughput: 0: 1617.5, 1: 1581.0. Samples: 46110036. Policy #0 lag: (min: 30.0, avg: 37.0, max: 62.0) -[2023-10-12 07:04:35,202][77203] Avg episode reward: [(0, '57.770'), (1, '48.740')] -[2023-10-12 07:04:36,731][78123] Updated weights for policy 1, policy_version 89830 (0.0008) -[2023-10-12 07:04:37,096][78123] Updated weights for policy 1, policy_version 89840 (0.0010) -[2023-10-12 07:04:37,464][78123] Updated weights for policy 1, policy_version 89850 (0.0008) -[2023-10-12 07:04:39,234][78091] Updated weights for policy 0, policy_version 90280 (0.0009) -[2023-10-12 07:04:39,602][78091] Updated weights for policy 0, policy_version 90290 (0.0010) -[2023-10-12 07:04:39,970][78091] Updated weights for policy 0, policy_version 90300 (0.0010) -[2023-10-12 07:04:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 12774.0). Total num frames: 184483840. Throughput: 0: 1599.7, 1: 1582.1. Samples: 46128806. Policy #0 lag: (min: 30.0, avg: 37.0, max: 62.0) -[2023-10-12 07:04:40,201][77203] Avg episode reward: [(0, '54.350'), (1, '50.280')] -[2023-10-12 07:04:41,567][78123] Updated weights for policy 1, policy_version 89860 (0.0009) -[2023-10-12 07:04:41,943][78123] Updated weights for policy 1, policy_version 89870 (0.0008) -[2023-10-12 07:04:42,309][78123] Updated weights for policy 1, policy_version 89880 (0.0009) -[2023-10-12 07:04:44,183][78091] Updated weights for policy 0, policy_version 90310 (0.0011) -[2023-10-12 07:04:44,554][78091] Updated weights for policy 0, policy_version 90320 (0.0007) -[2023-10-12 07:04:44,937][78091] Updated weights for policy 0, policy_version 90330 (0.0007) -[2023-10-12 07:04:45,201][77203] Fps is (10 sec: 13107.7, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 184549376. Throughput: 0: 1592.9, 1: 1585.4. Samples: 46138358. Policy #0 lag: (min: 30.0, avg: 37.0, max: 62.0) -[2023-10-12 07:04:45,201][77203] Avg episode reward: [(0, '59.060'), (1, '49.200')] -[2023-10-12 07:04:46,629][78123] Updated weights for policy 1, policy_version 89890 (0.0007) -[2023-10-12 07:04:46,996][78123] Updated weights for policy 1, policy_version 89900 (0.0007) -[2023-10-12 07:04:47,360][78123] Updated weights for policy 1, policy_version 89910 (0.0008) -[2023-10-12 07:04:47,729][78123] Updated weights for policy 1, policy_version 89920 (0.0007) -[2023-10-12 07:04:49,149][78091] Updated weights for policy 0, policy_version 90340 (0.0008) -[2023-10-12 07:04:49,511][78091] Updated weights for policy 0, policy_version 90350 (0.0010) -[2023-10-12 07:04:49,885][78091] Updated weights for policy 0, policy_version 90360 (0.0009) -[2023-10-12 07:04:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 184614912. Throughput: 0: 1611.3, 1: 1586.9. Samples: 46158036. Policy #0 lag: (min: 30.0, avg: 37.0, max: 62.0) -[2023-10-12 07:04:50,201][77203] Avg episode reward: [(0, '62.640'), (1, '52.010')] -[2023-10-12 07:04:52,102][78123] Updated weights for policy 1, policy_version 89930 (0.0008) -[2023-10-12 07:04:52,480][78123] Updated weights for policy 1, policy_version 89940 (0.0007) -[2023-10-12 07:04:52,843][78123] Updated weights for policy 1, policy_version 89950 (0.0007) -[2023-10-12 07:04:54,335][78091] Updated weights for policy 0, policy_version 90370 (0.0009) -[2023-10-12 07:04:54,708][78091] Updated weights for policy 0, policy_version 90380 (0.0008) -[2023-10-12 07:04:55,079][78091] Updated weights for policy 0, policy_version 90390 (0.0009) -[2023-10-12 07:04:55,201][77203] Fps is (10 sec: 9830.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 184647680. Throughput: 0: 1613.1, 1: 1587.2. Samples: 46177078. Policy #0 lag: (min: 30.0, avg: 37.0, max: 62.0) -[2023-10-12 07:04:55,202][77203] Avg episode reward: [(0, '53.940'), (1, '47.330')] -[2023-10-12 07:04:55,450][78091] Updated weights for policy 0, policy_version 90400 (0.0009) -[2023-10-12 07:04:57,139][78123] Updated weights for policy 1, policy_version 89960 (0.0011) -[2023-10-12 07:04:57,503][78123] Updated weights for policy 1, policy_version 89970 (0.0008) -[2023-10-12 07:04:57,869][78123] Updated weights for policy 1, policy_version 89980 (0.0008) -[2023-10-12 07:04:59,428][78091] Updated weights for policy 0, policy_version 90410 (0.0010) -[2023-10-12 07:04:59,801][78091] Updated weights for policy 0, policy_version 90420 (0.0009) -[2023-10-12 07:05:00,175][78091] Updated weights for policy 0, policy_version 90430 (0.0009) -[2023-10-12 07:05:00,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 184713216. Throughput: 0: 1595.8, 1: 1597.9. Samples: 46186688. Policy #0 lag: (min: 30.0, avg: 37.0, max: 62.0) -[2023-10-12 07:05:00,201][77203] Avg episode reward: [(0, '51.080'), (1, '52.370')] -[2023-10-12 07:05:02,391][78123] Updated weights for policy 1, policy_version 89990 (0.0010) -[2023-10-12 07:05:02,752][78123] Updated weights for policy 1, policy_version 90000 (0.0010) -[2023-10-12 07:05:03,114][78123] Updated weights for policy 1, policy_version 90010 (0.0011) -[2023-10-12 07:05:04,589][78091] Updated weights for policy 0, policy_version 90440 (0.0010) -[2023-10-12 07:05:04,950][78091] Updated weights for policy 0, policy_version 90450 (0.0009) -[2023-10-12 07:05:05,201][77203] Fps is (10 sec: 13107.6, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 184778752. Throughput: 0: 1609.0, 1: 1580.9. Samples: 46205796. Policy #0 lag: (min: 30.0, avg: 37.0, max: 62.0) -[2023-10-12 07:05:05,201][77203] Avg episode reward: [(0, '55.980'), (1, '57.410')] -[2023-10-12 07:05:05,316][78091] Updated weights for policy 0, policy_version 90460 (0.0008) -[2023-10-12 07:05:07,315][78123] Updated weights for policy 1, policy_version 90020 (0.0010) -[2023-10-12 07:05:07,687][78123] Updated weights for policy 1, policy_version 90030 (0.0009) -[2023-10-12 07:05:08,062][78123] Updated weights for policy 1, policy_version 90040 (0.0007) -[2023-10-12 07:05:09,484][78091] Updated weights for policy 0, policy_version 90470 (0.0008) -[2023-10-12 07:05:09,860][78091] Updated weights for policy 0, policy_version 90480 (0.0008) -[2023-10-12 07:05:10,201][77203] Fps is (10 sec: 13106.7, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 184844288. Throughput: 0: 1615.9, 1: 1583.2. Samples: 46225090. Policy #0 lag: (min: 2.0, avg: 12.5, max: 34.0) -[2023-10-12 07:05:10,202][77203] Avg episode reward: [(0, '57.400'), (1, '50.500')] -[2023-10-12 07:05:10,215][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000090048_92209152.pth... -[2023-10-12 07:05:10,225][78091] Updated weights for policy 0, policy_version 90490 (0.0011) -[2023-10-12 07:05:10,246][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000088544_90669056.pth -[2023-10-12 07:05:10,445][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000090496_92667904.pth... -[2023-10-12 07:05:10,480][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000088992_91127808.pth -[2023-10-12 07:05:12,201][78123] Updated weights for policy 1, policy_version 90050 (0.0008) -[2023-10-12 07:05:12,569][78123] Updated weights for policy 1, policy_version 90060 (0.0007) -[2023-10-12 07:05:12,940][78123] Updated weights for policy 1, policy_version 90070 (0.0008) -[2023-10-12 07:05:13,304][78123] Updated weights for policy 1, policy_version 90080 (0.0008) -[2023-10-12 07:05:14,587][78091] Updated weights for policy 0, policy_version 90500 (0.0009) -[2023-10-12 07:05:14,960][78091] Updated weights for policy 0, policy_version 90510 (0.0007) -[2023-10-12 07:05:15,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 184909824. Throughput: 0: 1599.4, 1: 1598.2. Samples: 46234846. Policy #0 lag: (min: 2.0, avg: 12.5, max: 34.0) -[2023-10-12 07:05:15,202][77203] Avg episode reward: [(0, '54.700'), (1, '57.830')] -[2023-10-12 07:05:15,326][78091] Updated weights for policy 0, policy_version 90520 (0.0007) -[2023-10-12 07:05:17,710][78123] Updated weights for policy 1, policy_version 90090 (0.0008) -[2023-10-12 07:05:18,071][78123] Updated weights for policy 1, policy_version 90100 (0.0009) -[2023-10-12 07:05:18,445][78123] Updated weights for policy 1, policy_version 90110 (0.0009) -[2023-10-12 07:05:19,686][78091] Updated weights for policy 0, policy_version 90530 (0.0008) -[2023-10-12 07:05:20,074][78091] Updated weights for policy 0, policy_version 90540 (0.0008) -[2023-10-12 07:05:20,201][77203] Fps is (10 sec: 13107.6, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 184975360. Throughput: 0: 1605.6, 1: 1589.1. Samples: 46253798. Policy #0 lag: (min: 2.0, avg: 12.5, max: 34.0) -[2023-10-12 07:05:20,201][77203] Avg episode reward: [(0, '51.810'), (1, '48.580')] -[2023-10-12 07:05:20,436][78091] Updated weights for policy 0, policy_version 90550 (0.0010) -[2023-10-12 07:05:20,805][78091] Updated weights for policy 0, policy_version 90560 (0.0009) -[2023-10-12 07:05:22,863][78123] Updated weights for policy 1, policy_version 90120 (0.0009) -[2023-10-12 07:05:23,233][78123] Updated weights for policy 1, policy_version 90130 (0.0009) -[2023-10-12 07:05:23,595][78123] Updated weights for policy 1, policy_version 90140 (0.0009) -[2023-10-12 07:05:25,037][78091] Updated weights for policy 0, policy_version 90570 (0.0009) -[2023-10-12 07:05:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 185040896. Throughput: 0: 1621.8, 1: 1585.1. Samples: 46273114. Policy #0 lag: (min: 2.0, avg: 12.5, max: 34.0) -[2023-10-12 07:05:25,201][77203] Avg episode reward: [(0, '59.840'), (1, '45.810')] -[2023-10-12 07:05:25,400][78091] Updated weights for policy 0, policy_version 90580 (0.0008) -[2023-10-12 07:05:25,763][78091] Updated weights for policy 0, policy_version 90590 (0.0009) -[2023-10-12 07:05:28,022][78123] Updated weights for policy 1, policy_version 90150 (0.0009) -[2023-10-12 07:05:28,399][78123] Updated weights for policy 1, policy_version 90160 (0.0008) -[2023-10-12 07:05:28,769][78123] Updated weights for policy 1, policy_version 90170 (0.0010) -[2023-10-12 07:05:30,101][78091] Updated weights for policy 0, policy_version 90600 (0.0008) -[2023-10-12 07:05:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 185106432. Throughput: 0: 1603.4, 1: 1607.2. Samples: 46282836. Policy #0 lag: (min: 2.0, avg: 12.5, max: 34.0) -[2023-10-12 07:05:30,201][77203] Avg episode reward: [(0, '59.860'), (1, '53.390')] -[2023-10-12 07:05:30,478][78091] Updated weights for policy 0, policy_version 90610 (0.0011) -[2023-10-12 07:05:30,846][78091] Updated weights for policy 0, policy_version 90620 (0.0010) -[2023-10-12 07:05:33,249][78123] Updated weights for policy 1, policy_version 90180 (0.0009) -[2023-10-12 07:05:33,615][78123] Updated weights for policy 1, policy_version 90190 (0.0007) -[2023-10-12 07:05:33,972][78123] Updated weights for policy 1, policy_version 90200 (0.0010) -[2023-10-12 07:05:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 185171968. Throughput: 0: 1600.2, 1: 1591.0. Samples: 46301638. Policy #0 lag: (min: 2.0, avg: 12.5, max: 34.0) -[2023-10-12 07:05:35,201][77203] Avg episode reward: [(0, '57.410'), (1, '53.050')] -[2023-10-12 07:05:35,238][78091] Updated weights for policy 0, policy_version 90630 (0.0007) -[2023-10-12 07:05:35,613][78091] Updated weights for policy 0, policy_version 90640 (0.0007) -[2023-10-12 07:05:35,980][78091] Updated weights for policy 0, policy_version 90650 (0.0008) -[2023-10-12 07:05:38,300][78123] Updated weights for policy 1, policy_version 90210 (0.0010) -[2023-10-12 07:05:38,671][78123] Updated weights for policy 1, policy_version 90220 (0.0010) -[2023-10-12 07:05:39,029][78123] Updated weights for policy 1, policy_version 90230 (0.0010) -[2023-10-12 07:05:39,394][78123] Updated weights for policy 1, policy_version 90240 (0.0009) -[2023-10-12 07:05:40,124][78091] Updated weights for policy 0, policy_version 90660 (0.0009) -[2023-10-12 07:05:40,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 185237504. Throughput: 0: 1613.9, 1: 1581.8. Samples: 46320886. Policy #0 lag: (min: 2.0, avg: 12.5, max: 34.0) -[2023-10-12 07:05:40,201][77203] Avg episode reward: [(0, '47.970'), (1, '48.390')] -[2023-10-12 07:05:40,481][78091] Updated weights for policy 0, policy_version 90670 (0.0011) -[2023-10-12 07:05:40,860][78091] Updated weights for policy 0, policy_version 90680 (0.0008) -[2023-10-12 07:05:43,693][78123] Updated weights for policy 1, policy_version 90250 (0.0007) -[2023-10-12 07:05:44,056][78123] Updated weights for policy 1, policy_version 90260 (0.0009) -[2023-10-12 07:05:44,421][78123] Updated weights for policy 1, policy_version 90270 (0.0008) -[2023-10-12 07:05:45,145][78091] Updated weights for policy 0, policy_version 90690 (0.0009) -[2023-10-12 07:05:45,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 185303040. Throughput: 0: 1601.2, 1: 1597.5. Samples: 46330630. Policy #0 lag: (min: 2.0, avg: 12.5, max: 34.0) -[2023-10-12 07:05:45,201][77203] Avg episode reward: [(0, '55.650'), (1, '49.750')] -[2023-10-12 07:05:45,515][78091] Updated weights for policy 0, policy_version 90700 (0.0007) -[2023-10-12 07:05:45,886][78091] Updated weights for policy 0, policy_version 90710 (0.0007) -[2023-10-12 07:05:46,250][78091] Updated weights for policy 0, policy_version 90720 (0.0007) -[2023-10-12 07:05:48,761][78123] Updated weights for policy 1, policy_version 90280 (0.0009) -[2023-10-12 07:05:49,126][78123] Updated weights for policy 1, policy_version 90290 (0.0010) -[2023-10-12 07:05:49,496][78123] Updated weights for policy 1, policy_version 90300 (0.0009) -[2023-10-12 07:05:50,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 185368576. Throughput: 0: 1602.9, 1: 1602.4. Samples: 46350038. Policy #0 lag: (min: 2.0, avg: 12.5, max: 34.0) -[2023-10-12 07:05:50,201][77203] Avg episode reward: [(0, '59.180'), (1, '52.230')] -[2023-10-12 07:05:50,453][78091] Updated weights for policy 0, policy_version 90730 (0.0009) -[2023-10-12 07:05:50,832][78091] Updated weights for policy 0, policy_version 90740 (0.0009) -[2023-10-12 07:05:51,197][78091] Updated weights for policy 0, policy_version 90750 (0.0008) -[2023-10-12 07:05:53,843][78123] Updated weights for policy 1, policy_version 90310 (0.0008) -[2023-10-12 07:05:54,199][78123] Updated weights for policy 1, policy_version 90320 (0.0009) -[2023-10-12 07:05:54,562][78123] Updated weights for policy 1, policy_version 90330 (0.0007) -[2023-10-12 07:05:55,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 185434112. Throughput: 0: 1615.5, 1: 1586.0. Samples: 46369154. Policy #0 lag: (min: 2.0, avg: 12.5, max: 34.0) -[2023-10-12 07:05:55,201][77203] Avg episode reward: [(0, '54.430'), (1, '48.130')] -[2023-10-12 07:05:55,550][78091] Updated weights for policy 0, policy_version 90760 (0.0007) -[2023-10-12 07:05:55,929][78091] Updated weights for policy 0, policy_version 90770 (0.0007) -[2023-10-12 07:05:56,292][78091] Updated weights for policy 0, policy_version 90780 (0.0007) -[2023-10-12 07:05:59,016][78123] Updated weights for policy 1, policy_version 90340 (0.0008) -[2023-10-12 07:05:59,385][78123] Updated weights for policy 1, policy_version 90350 (0.0009) -[2023-10-12 07:05:59,763][78123] Updated weights for policy 1, policy_version 90360 (0.0008) -[2023-10-12 07:06:00,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 185499648. Throughput: 0: 1607.7, 1: 1594.8. Samples: 46378958. Policy #0 lag: (min: 2.0, avg: 12.5, max: 34.0) -[2023-10-12 07:06:00,201][77203] Avg episode reward: [(0, '54.030'), (1, '53.090')] -[2023-10-12 07:06:00,543][78091] Updated weights for policy 0, policy_version 90790 (0.0008) -[2023-10-12 07:06:00,913][78091] Updated weights for policy 0, policy_version 90800 (0.0007) -[2023-10-12 07:06:01,286][78091] Updated weights for policy 0, policy_version 90810 (0.0007) -[2023-10-12 07:06:04,198][78123] Updated weights for policy 1, policy_version 90370 (0.0008) -[2023-10-12 07:06:04,608][78123] Updated weights for policy 1, policy_version 90380 (0.0007) -[2023-10-12 07:06:04,980][78123] Updated weights for policy 1, policy_version 90390 (0.0009) -[2023-10-12 07:06:05,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 185532416. Throughput: 0: 1606.8, 1: 1609.3. Samples: 46398524. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:06:05,201][77203] Avg episode reward: [(0, '53.010'), (1, '53.590')] -[2023-10-12 07:06:05,341][78123] Updated weights for policy 1, policy_version 90400 (0.0009) -[2023-10-12 07:06:05,572][78091] Updated weights for policy 0, policy_version 90820 (0.0008) -[2023-10-12 07:06:05,961][78091] Updated weights for policy 0, policy_version 90830 (0.0008) -[2023-10-12 07:06:06,331][78091] Updated weights for policy 0, policy_version 90840 (0.0007) -[2023-10-12 07:06:09,735][78123] Updated weights for policy 1, policy_version 90410 (0.0009) -[2023-10-12 07:06:10,102][78123] Updated weights for policy 1, policy_version 90420 (0.0010) -[2023-10-12 07:06:10,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 185597952. Throughput: 0: 1609.6, 1: 1599.2. Samples: 46417508. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:06:10,201][77203] Avg episode reward: [(0, '58.780'), (1, '51.300')] -[2023-10-12 07:06:10,458][78123] Updated weights for policy 1, policy_version 90430 (0.0010) -[2023-10-12 07:06:10,640][78091] Updated weights for policy 0, policy_version 90850 (0.0008) -[2023-10-12 07:06:11,013][78091] Updated weights for policy 0, policy_version 90860 (0.0007) -[2023-10-12 07:06:11,375][78091] Updated weights for policy 0, policy_version 90870 (0.0008) -[2023-10-12 07:06:11,752][78091] Updated weights for policy 0, policy_version 90880 (0.0010) -[2023-10-12 07:06:14,816][78123] Updated weights for policy 1, policy_version 90440 (0.0009) -[2023-10-12 07:06:15,187][78123] Updated weights for policy 1, policy_version 90450 (0.0008) -[2023-10-12 07:06:15,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 185663488. Throughput: 0: 1607.1, 1: 1583.7. Samples: 46426424. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:06:15,202][77203] Avg episode reward: [(0, '57.020'), (1, '46.850')] -[2023-10-12 07:06:15,549][78123] Updated weights for policy 1, policy_version 90460 (0.0007) -[2023-10-12 07:06:16,159][78091] Updated weights for policy 0, policy_version 90890 (0.0009) -[2023-10-12 07:06:16,533][78091] Updated weights for policy 0, policy_version 90900 (0.0008) -[2023-10-12 07:06:16,908][78091] Updated weights for policy 0, policy_version 90910 (0.0008) -[2023-10-12 07:06:19,740][78123] Updated weights for policy 1, policy_version 90470 (0.0007) -[2023-10-12 07:06:20,102][78123] Updated weights for policy 1, policy_version 90480 (0.0008) -[2023-10-12 07:06:20,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 185729024. Throughput: 0: 1610.6, 1: 1599.8. Samples: 46446106. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:06:20,202][77203] Avg episode reward: [(0, '54.500'), (1, '47.020')] -[2023-10-12 07:06:20,460][78123] Updated weights for policy 1, policy_version 90490 (0.0008) -[2023-10-12 07:06:21,022][78091] Updated weights for policy 0, policy_version 90920 (0.0010) -[2023-10-12 07:06:21,393][78091] Updated weights for policy 0, policy_version 90930 (0.0009) -[2023-10-12 07:06:21,772][78091] Updated weights for policy 0, policy_version 90940 (0.0007) -[2023-10-12 07:06:24,782][78123] Updated weights for policy 1, policy_version 90500 (0.0009) -[2023-10-12 07:06:25,154][78123] Updated weights for policy 1, policy_version 90510 (0.0009) -[2023-10-12 07:06:25,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12773.9). Total num frames: 185794560. Throughput: 0: 1606.4, 1: 1605.1. Samples: 46465406. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:06:25,202][77203] Avg episode reward: [(0, '60.850'), (1, '47.460')] -[2023-10-12 07:06:25,523][78123] Updated weights for policy 1, policy_version 90520 (0.0010) -[2023-10-12 07:06:26,018][78091] Updated weights for policy 0, policy_version 90950 (0.0009) -[2023-10-12 07:06:26,400][78091] Updated weights for policy 0, policy_version 90960 (0.0008) -[2023-10-12 07:06:26,762][78091] Updated weights for policy 0, policy_version 90970 (0.0007) -[2023-10-12 07:06:29,863][78123] Updated weights for policy 1, policy_version 90530 (0.0008) -[2023-10-12 07:06:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 185860096. Throughput: 0: 1608.7, 1: 1582.0. Samples: 46474212. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:06:30,202][77203] Avg episode reward: [(0, '54.700'), (1, '49.940')] -[2023-10-12 07:06:30,240][78123] Updated weights for policy 1, policy_version 90540 (0.0009) -[2023-10-12 07:06:30,605][78123] Updated weights for policy 1, policy_version 90550 (0.0009) -[2023-10-12 07:06:30,969][78123] Updated weights for policy 1, policy_version 90560 (0.0008) -[2023-10-12 07:06:30,969][78091] Updated weights for policy 0, policy_version 90980 (0.0008) -[2023-10-12 07:06:31,330][78091] Updated weights for policy 0, policy_version 90990 (0.0010) -[2023-10-12 07:06:31,703][78091] Updated weights for policy 0, policy_version 91000 (0.0010) -[2023-10-12 07:06:35,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 185925632. Throughput: 0: 1606.9, 1: 1586.6. Samples: 46493744. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:06:35,202][77203] Avg episode reward: [(0, '60.490'), (1, '54.950')] -[2023-10-12 07:06:35,422][78123] Updated weights for policy 1, policy_version 90570 (0.0010) -[2023-10-12 07:06:35,797][78123] Updated weights for policy 1, policy_version 90580 (0.0011) -[2023-10-12 07:06:35,953][78091] Updated weights for policy 0, policy_version 91010 (0.0007) -[2023-10-12 07:06:36,154][78123] Updated weights for policy 1, policy_version 90590 (0.0010) -[2023-10-12 07:06:36,327][78091] Updated weights for policy 0, policy_version 91020 (0.0010) -[2023-10-12 07:06:36,701][78091] Updated weights for policy 0, policy_version 91030 (0.0008) -[2023-10-12 07:06:37,066][78091] Updated weights for policy 0, policy_version 91040 (0.0007) -[2023-10-12 07:06:40,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 185991168. Throughput: 0: 1607.4, 1: 1592.6. Samples: 46513154. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:06:40,202][77203] Avg episode reward: [(0, '59.160'), (1, '56.090')] -[2023-10-12 07:06:40,681][78123] Updated weights for policy 1, policy_version 90600 (0.0008) -[2023-10-12 07:06:41,054][78123] Updated weights for policy 1, policy_version 90610 (0.0008) -[2023-10-12 07:06:41,238][78091] Updated weights for policy 0, policy_version 91050 (0.0009) -[2023-10-12 07:06:41,416][78123] Updated weights for policy 1, policy_version 90620 (0.0009) -[2023-10-12 07:06:41,609][78091] Updated weights for policy 0, policy_version 91060 (0.0008) -[2023-10-12 07:06:41,970][78091] Updated weights for policy 0, policy_version 91070 (0.0009) -[2023-10-12 07:06:45,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 186056704. Throughput: 0: 1604.8, 1: 1566.6. Samples: 46521674. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:06:45,201][77203] Avg episode reward: [(0, '58.360'), (1, '55.420')] -[2023-10-12 07:06:45,566][78123] Updated weights for policy 1, policy_version 90630 (0.0008) -[2023-10-12 07:06:45,930][78123] Updated weights for policy 1, policy_version 90640 (0.0007) -[2023-10-12 07:06:46,295][78091] Updated weights for policy 0, policy_version 91080 (0.0008) -[2023-10-12 07:06:46,308][78123] Updated weights for policy 1, policy_version 90650 (0.0008) -[2023-10-12 07:06:46,659][78091] Updated weights for policy 0, policy_version 91090 (0.0010) -[2023-10-12 07:06:47,032][78091] Updated weights for policy 0, policy_version 91100 (0.0011) -[2023-10-12 07:06:50,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 186122240. Throughput: 0: 1608.6, 1: 1572.3. Samples: 46541666. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:06:50,202][77203] Avg episode reward: [(0, '58.820'), (1, '52.920')] -[2023-10-12 07:06:50,558][78123] Updated weights for policy 1, policy_version 90660 (0.0008) -[2023-10-12 07:06:50,940][78123] Updated weights for policy 1, policy_version 90670 (0.0007) -[2023-10-12 07:06:51,302][78123] Updated weights for policy 1, policy_version 90680 (0.0008) -[2023-10-12 07:06:51,388][78091] Updated weights for policy 0, policy_version 91110 (0.0009) -[2023-10-12 07:06:51,770][78091] Updated weights for policy 0, policy_version 91120 (0.0009) -[2023-10-12 07:06:52,144][78091] Updated weights for policy 0, policy_version 91130 (0.0008) -[2023-10-12 07:06:55,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 186187776. Throughput: 0: 1606.3, 1: 1585.3. Samples: 46561130. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:06:55,202][77203] Avg episode reward: [(0, '56.010'), (1, '53.830')] -[2023-10-12 07:06:55,495][78123] Updated weights for policy 1, policy_version 90690 (0.0008) -[2023-10-12 07:06:55,863][78123] Updated weights for policy 1, policy_version 90700 (0.0009) -[2023-10-12 07:06:56,228][78123] Updated weights for policy 1, policy_version 90710 (0.0008) -[2023-10-12 07:06:56,312][78091] Updated weights for policy 0, policy_version 91140 (0.0010) -[2023-10-12 07:06:56,593][78123] Updated weights for policy 1, policy_version 90720 (0.0008) -[2023-10-12 07:06:56,682][78091] Updated weights for policy 0, policy_version 91150 (0.0007) -[2023-10-12 07:06:57,058][78091] Updated weights for policy 0, policy_version 91160 (0.0008) -[2023-10-12 07:07:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 186253312. Throughput: 0: 1606.4, 1: 1575.2. Samples: 46569596. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:07:00,202][77203] Avg episode reward: [(0, '61.790'), (1, '56.630')] -[2023-10-12 07:07:01,103][78123] Updated weights for policy 1, policy_version 90730 (0.0007) -[2023-10-12 07:07:01,461][78123] Updated weights for policy 1, policy_version 90740 (0.0009) -[2023-10-12 07:07:01,463][78091] Updated weights for policy 0, policy_version 91170 (0.0007) -[2023-10-12 07:07:01,825][78123] Updated weights for policy 1, policy_version 90750 (0.0010) -[2023-10-12 07:07:01,839][78091] Updated weights for policy 0, policy_version 91180 (0.0008) -[2023-10-12 07:07:02,214][78091] Updated weights for policy 0, policy_version 91190 (0.0009) -[2023-10-12 07:07:02,578][78091] Updated weights for policy 0, policy_version 91200 (0.0009) -[2023-10-12 07:07:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 186318848. Throughput: 0: 1599.9, 1: 1577.6. Samples: 46589092. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 07:07:05,202][77203] Avg episode reward: [(0, '66.910'), (1, '56.760')] -[2023-10-12 07:07:06,227][78123] Updated weights for policy 1, policy_version 90760 (0.0008) -[2023-10-12 07:07:06,589][78123] Updated weights for policy 1, policy_version 90770 (0.0007) -[2023-10-12 07:07:06,815][78091] Updated weights for policy 0, policy_version 91210 (0.0009) -[2023-10-12 07:07:06,956][78123] Updated weights for policy 1, policy_version 90780 (0.0007) -[2023-10-12 07:07:07,191][78091] Updated weights for policy 0, policy_version 91220 (0.0007) -[2023-10-12 07:07:07,551][78091] Updated weights for policy 0, policy_version 91230 (0.0010) -[2023-10-12 07:07:10,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 186384384. Throughput: 0: 1603.6, 1: 1578.1. Samples: 46608580. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 07:07:10,202][77203] Avg episode reward: [(0, '67.330'), (1, '57.290')] -[2023-10-12 07:07:10,209][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000090784_92962816.pth... -[2023-10-12 07:07:10,209][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000091232_93421568.pth... -[2023-10-12 07:07:10,251][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000089728_91881472.pth -[2023-10-12 07:07:10,254][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000089312_91455488.pth -[2023-10-12 07:07:11,378][78123] Updated weights for policy 1, policy_version 90790 (0.0008) -[2023-10-12 07:07:11,749][78123] Updated weights for policy 1, policy_version 90800 (0.0008) -[2023-10-12 07:07:11,890][78091] Updated weights for policy 0, policy_version 91240 (0.0007) -[2023-10-12 07:07:12,116][78123] Updated weights for policy 1, policy_version 90810 (0.0007) -[2023-10-12 07:07:12,262][78091] Updated weights for policy 0, policy_version 91250 (0.0008) -[2023-10-12 07:07:12,623][78091] Updated weights for policy 0, policy_version 91260 (0.0011) -[2023-10-12 07:07:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 186449920. Throughput: 0: 1601.0, 1: 1578.0. Samples: 46617268. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 07:07:15,202][77203] Avg episode reward: [(0, '67.590'), (1, '52.570')] -[2023-10-12 07:07:16,261][78123] Updated weights for policy 1, policy_version 90820 (0.0010) -[2023-10-12 07:07:16,639][78123] Updated weights for policy 1, policy_version 90830 (0.0009) -[2023-10-12 07:07:16,846][78091] Updated weights for policy 0, policy_version 91270 (0.0009) -[2023-10-12 07:07:16,993][78123] Updated weights for policy 1, policy_version 90840 (0.0009) -[2023-10-12 07:07:17,219][78091] Updated weights for policy 0, policy_version 91280 (0.0010) -[2023-10-12 07:07:17,590][78091] Updated weights for policy 0, policy_version 91290 (0.0009) -[2023-10-12 07:07:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 186515456. Throughput: 0: 1599.3, 1: 1582.8. Samples: 46636938. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 07:07:20,202][77203] Avg episode reward: [(0, '56.540'), (1, '59.880')] -[2023-10-12 07:07:21,453][78123] Updated weights for policy 1, policy_version 90850 (0.0007) -[2023-10-12 07:07:21,814][78123] Updated weights for policy 1, policy_version 90860 (0.0008) -[2023-10-12 07:07:21,974][78091] Updated weights for policy 0, policy_version 91300 (0.0009) -[2023-10-12 07:07:22,182][78123] Updated weights for policy 1, policy_version 90870 (0.0009) -[2023-10-12 07:07:22,346][78091] Updated weights for policy 0, policy_version 91310 (0.0008) -[2023-10-12 07:07:22,549][78123] Updated weights for policy 1, policy_version 90880 (0.0008) -[2023-10-12 07:07:22,717][78091] Updated weights for policy 0, policy_version 91320 (0.0011) -[2023-10-12 07:07:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 186580992. Throughput: 0: 1596.9, 1: 1588.3. Samples: 46656488. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 07:07:25,202][77203] Avg episode reward: [(0, '58.280'), (1, '59.990')] -[2023-10-12 07:07:26,878][78123] Updated weights for policy 1, policy_version 90890 (0.0008) -[2023-10-12 07:07:27,020][78091] Updated weights for policy 0, policy_version 91330 (0.0008) -[2023-10-12 07:07:27,248][78123] Updated weights for policy 1, policy_version 90900 (0.0008) -[2023-10-12 07:07:27,385][78091] Updated weights for policy 0, policy_version 91340 (0.0008) -[2023-10-12 07:07:27,609][78123] Updated weights for policy 1, policy_version 90910 (0.0008) -[2023-10-12 07:07:27,751][78091] Updated weights for policy 0, policy_version 91350 (0.0008) -[2023-10-12 07:07:28,124][78091] Updated weights for policy 0, policy_version 91360 (0.0008) -[2023-10-12 07:07:30,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 186646528. Throughput: 0: 1607.1, 1: 1589.0. Samples: 46665500. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 07:07:30,201][77203] Avg episode reward: [(0, '55.450'), (1, '55.980')] -[2023-10-12 07:07:31,931][78123] Updated weights for policy 1, policy_version 90920 (0.0008) -[2023-10-12 07:07:32,296][78123] Updated weights for policy 1, policy_version 90930 (0.0010) -[2023-10-12 07:07:32,356][78091] Updated weights for policy 0, policy_version 91370 (0.0009) -[2023-10-12 07:07:32,671][78123] Updated weights for policy 1, policy_version 90940 (0.0009) -[2023-10-12 07:07:32,728][78091] Updated weights for policy 0, policy_version 91380 (0.0009) -[2023-10-12 07:07:33,100][78091] Updated weights for policy 0, policy_version 91390 (0.0008) -[2023-10-12 07:07:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 186712064. Throughput: 0: 1592.6, 1: 1581.4. Samples: 46684496. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 07:07:35,202][77203] Avg episode reward: [(0, '51.060'), (1, '56.830')] -[2023-10-12 07:07:37,127][78123] Updated weights for policy 1, policy_version 90950 (0.0008) -[2023-10-12 07:07:37,488][78091] Updated weights for policy 0, policy_version 91400 (0.0010) -[2023-10-12 07:07:37,496][78123] Updated weights for policy 1, policy_version 90960 (0.0008) -[2023-10-12 07:07:37,865][78091] Updated weights for policy 0, policy_version 91410 (0.0007) -[2023-10-12 07:07:37,871][78123] Updated weights for policy 1, policy_version 90970 (0.0008) -[2023-10-12 07:07:38,238][78091] Updated weights for policy 0, policy_version 91420 (0.0008) -[2023-10-12 07:07:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 186777600. Throughput: 0: 1590.4, 1: 1579.1. Samples: 46703758. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 07:07:40,202][77203] Avg episode reward: [(0, '59.760'), (1, '57.060')] -[2023-10-12 07:07:42,159][78123] Updated weights for policy 1, policy_version 90980 (0.0009) -[2023-10-12 07:07:42,519][78123] Updated weights for policy 1, policy_version 90990 (0.0007) -[2023-10-12 07:07:42,582][78091] Updated weights for policy 0, policy_version 91430 (0.0007) -[2023-10-12 07:07:42,887][78123] Updated weights for policy 1, policy_version 91000 (0.0008) -[2023-10-12 07:07:42,950][78091] Updated weights for policy 0, policy_version 91440 (0.0008) -[2023-10-12 07:07:43,317][78091] Updated weights for policy 0, policy_version 91450 (0.0010) -[2023-10-12 07:07:45,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 186843136. Throughput: 0: 1608.1, 1: 1593.1. Samples: 46713648. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 07:07:45,202][77203] Avg episode reward: [(0, '54.530'), (1, '57.250')] -[2023-10-12 07:07:47,320][78123] Updated weights for policy 1, policy_version 91010 (0.0007) -[2023-10-12 07:07:47,682][78123] Updated weights for policy 1, policy_version 91020 (0.0008) -[2023-10-12 07:07:47,712][78091] Updated weights for policy 0, policy_version 91460 (0.0010) -[2023-10-12 07:07:48,052][78123] Updated weights for policy 1, policy_version 91030 (0.0007) -[2023-10-12 07:07:48,081][78091] Updated weights for policy 0, policy_version 91470 (0.0009) -[2023-10-12 07:07:48,411][78123] Updated weights for policy 1, policy_version 91040 (0.0007) -[2023-10-12 07:07:48,453][78091] Updated weights for policy 0, policy_version 91480 (0.0008) -[2023-10-12 07:07:50,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 186908672. Throughput: 0: 1592.7, 1: 1581.6. Samples: 46731936. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 07:07:50,202][77203] Avg episode reward: [(0, '51.570'), (1, '56.860')] -[2023-10-12 07:07:52,722][78123] Updated weights for policy 1, policy_version 91050 (0.0009) -[2023-10-12 07:07:52,883][78091] Updated weights for policy 0, policy_version 91490 (0.0007) -[2023-10-12 07:07:53,092][78123] Updated weights for policy 1, policy_version 91060 (0.0008) -[2023-10-12 07:07:53,238][78091] Updated weights for policy 0, policy_version 91500 (0.0009) -[2023-10-12 07:07:53,447][78123] Updated weights for policy 1, policy_version 91070 (0.0009) -[2023-10-12 07:07:53,606][78091] Updated weights for policy 0, policy_version 91510 (0.0009) -[2023-10-12 07:07:53,974][78091] Updated weights for policy 0, policy_version 91520 (0.0009) -[2023-10-12 07:07:55,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 186974208. Throughput: 0: 1589.1, 1: 1588.3. Samples: 46751566. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-12 07:07:55,202][77203] Avg episode reward: [(0, '55.020'), (1, '56.610')] -[2023-10-12 07:07:57,670][78123] Updated weights for policy 1, policy_version 91080 (0.0008) -[2023-10-12 07:07:58,034][78123] Updated weights for policy 1, policy_version 91090 (0.0009) -[2023-10-12 07:07:58,106][78091] Updated weights for policy 0, policy_version 91530 (0.0008) -[2023-10-12 07:07:58,399][78123] Updated weights for policy 1, policy_version 91100 (0.0008) -[2023-10-12 07:07:58,467][78091] Updated weights for policy 0, policy_version 91540 (0.0009) -[2023-10-12 07:07:58,832][78091] Updated weights for policy 0, policy_version 91550 (0.0008) -[2023-10-12 07:08:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 187039744. Throughput: 0: 1621.3, 1: 1603.6. Samples: 46762388. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-12 07:08:00,202][77203] Avg episode reward: [(0, '58.300'), (1, '53.880')] -[2023-10-12 07:08:02,837][78123] Updated weights for policy 1, policy_version 91110 (0.0008) -[2023-10-12 07:08:03,188][78091] Updated weights for policy 0, policy_version 91560 (0.0009) -[2023-10-12 07:08:03,206][78123] Updated weights for policy 1, policy_version 91120 (0.0007) -[2023-10-12 07:08:03,557][78091] Updated weights for policy 0, policy_version 91570 (0.0008) -[2023-10-12 07:08:03,575][78123] Updated weights for policy 1, policy_version 91130 (0.0009) -[2023-10-12 07:08:03,928][78091] Updated weights for policy 0, policy_version 91580 (0.0010) -[2023-10-12 07:08:05,201][77203] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 187105280. Throughput: 0: 1600.0, 1: 1588.7. Samples: 46780430. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-12 07:08:05,201][77203] Avg episode reward: [(0, '56.300'), (1, '56.880')] -[2023-10-12 07:08:07,930][78123] Updated weights for policy 1, policy_version 91140 (0.0010) -[2023-10-12 07:08:08,056][78091] Updated weights for policy 0, policy_version 91590 (0.0010) -[2023-10-12 07:08:08,289][78123] Updated weights for policy 1, policy_version 91150 (0.0008) -[2023-10-12 07:08:08,433][78091] Updated weights for policy 0, policy_version 91600 (0.0009) -[2023-10-12 07:08:08,662][78123] Updated weights for policy 1, policy_version 91160 (0.0008) -[2023-10-12 07:08:08,801][78091] Updated weights for policy 0, policy_version 91610 (0.0008) -[2023-10-12 07:08:10,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 187170816. Throughput: 0: 1593.8, 1: 1582.6. Samples: 46799426. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-12 07:08:10,202][77203] Avg episode reward: [(0, '60.650'), (1, '50.510')] -[2023-10-12 07:08:12,940][78123] Updated weights for policy 1, policy_version 91170 (0.0007) -[2023-10-12 07:08:13,306][78123] Updated weights for policy 1, policy_version 91180 (0.0009) -[2023-10-12 07:08:13,339][78091] Updated weights for policy 0, policy_version 91620 (0.0009) -[2023-10-12 07:08:13,683][78123] Updated weights for policy 1, policy_version 91190 (0.0008) -[2023-10-12 07:08:13,704][78091] Updated weights for policy 0, policy_version 91630 (0.0007) -[2023-10-12 07:08:14,051][78123] Updated weights for policy 1, policy_version 91200 (0.0008) -[2023-10-12 07:08:14,065][78091] Updated weights for policy 0, policy_version 91640 (0.0008) -[2023-10-12 07:08:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 187236352. Throughput: 0: 1609.6, 1: 1607.3. Samples: 46810260. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-12 07:08:15,202][77203] Avg episode reward: [(0, '51.940'), (1, '45.220')] -[2023-10-12 07:08:18,366][78091] Updated weights for policy 0, policy_version 91650 (0.0011) -[2023-10-12 07:08:18,402][78123] Updated weights for policy 1, policy_version 91210 (0.0009) -[2023-10-12 07:08:18,739][78091] Updated weights for policy 0, policy_version 91660 (0.0012) -[2023-10-12 07:08:18,768][78123] Updated weights for policy 1, policy_version 91220 (0.0008) -[2023-10-12 07:08:19,110][78091] Updated weights for policy 0, policy_version 91670 (0.0007) -[2023-10-12 07:08:19,134][78123] Updated weights for policy 1, policy_version 91230 (0.0008) -[2023-10-12 07:08:19,479][78091] Updated weights for policy 0, policy_version 91680 (0.0008) -[2023-10-12 07:08:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 187301888. Throughput: 0: 1607.9, 1: 1595.4. Samples: 46828644. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-12 07:08:20,201][77203] Avg episode reward: [(0, '54.940'), (1, '47.430')] -[2023-10-12 07:08:23,427][78123] Updated weights for policy 1, policy_version 91240 (0.0009) -[2023-10-12 07:08:23,795][78123] Updated weights for policy 1, policy_version 91250 (0.0007) -[2023-10-12 07:08:23,893][78091] Updated weights for policy 0, policy_version 91690 (0.0008) -[2023-10-12 07:08:24,153][78123] Updated weights for policy 1, policy_version 91260 (0.0008) -[2023-10-12 07:08:24,257][78091] Updated weights for policy 0, policy_version 91700 (0.0008) -[2023-10-12 07:08:24,629][78091] Updated weights for policy 0, policy_version 91710 (0.0009) -[2023-10-12 07:08:25,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 187367424. Throughput: 0: 1587.9, 1: 1590.0. Samples: 46846762. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-12 07:08:25,202][77203] Avg episode reward: [(0, '54.920'), (1, '47.580')] -[2023-10-12 07:08:28,435][78123] Updated weights for policy 1, policy_version 91270 (0.0010) -[2023-10-12 07:08:28,804][78123] Updated weights for policy 1, policy_version 91280 (0.0009) -[2023-10-12 07:08:28,871][78091] Updated weights for policy 0, policy_version 91720 (0.0008) -[2023-10-12 07:08:29,163][78123] Updated weights for policy 1, policy_version 91290 (0.0010) -[2023-10-12 07:08:29,248][78091] Updated weights for policy 0, policy_version 91730 (0.0007) -[2023-10-12 07:08:29,610][78091] Updated weights for policy 0, policy_version 91740 (0.0008) -[2023-10-12 07:08:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 187432960. Throughput: 0: 1599.5, 1: 1604.0. Samples: 46857808. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-12 07:08:30,201][77203] Avg episode reward: [(0, '56.830'), (1, '52.030')] -[2023-10-12 07:08:33,365][78123] Updated weights for policy 1, policy_version 91300 (0.0010) -[2023-10-12 07:08:33,724][78123] Updated weights for policy 1, policy_version 91310 (0.0009) -[2023-10-12 07:08:33,985][78091] Updated weights for policy 0, policy_version 91750 (0.0010) -[2023-10-12 07:08:34,092][78123] Updated weights for policy 1, policy_version 91320 (0.0010) -[2023-10-12 07:08:34,357][78091] Updated weights for policy 0, policy_version 91760 (0.0009) -[2023-10-12 07:08:34,722][78091] Updated weights for policy 0, policy_version 91770 (0.0011) -[2023-10-12 07:08:35,201][77203] Fps is (10 sec: 13107.6, 60 sec: 13107.3, 300 sec: 12885.1). Total num frames: 187498496. Throughput: 0: 1615.0, 1: 1606.4. Samples: 46876898. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-12 07:08:35,201][77203] Avg episode reward: [(0, '56.350'), (1, '57.190')] -[2023-10-12 07:08:38,441][78123] Updated weights for policy 1, policy_version 91330 (0.0008) -[2023-10-12 07:08:38,800][78123] Updated weights for policy 1, policy_version 91340 (0.0009) -[2023-10-12 07:08:39,124][78091] Updated weights for policy 0, policy_version 91780 (0.0009) -[2023-10-12 07:08:39,162][78123] Updated weights for policy 1, policy_version 91350 (0.0007) -[2023-10-12 07:08:39,489][78091] Updated weights for policy 0, policy_version 91790 (0.0007) -[2023-10-12 07:08:39,536][78123] Updated weights for policy 1, policy_version 91360 (0.0008) -[2023-10-12 07:08:39,861][78091] Updated weights for policy 0, policy_version 91800 (0.0009) -[2023-10-12 07:08:40,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 187564032. Throughput: 0: 1595.5, 1: 1588.7. Samples: 46894856. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-12 07:08:40,202][77203] Avg episode reward: [(0, '58.970'), (1, '56.770')] -[2023-10-12 07:08:44,014][78123] Updated weights for policy 1, policy_version 91370 (0.0009) -[2023-10-12 07:08:44,170][78091] Updated weights for policy 0, policy_version 91810 (0.0008) -[2023-10-12 07:08:44,379][78123] Updated weights for policy 1, policy_version 91380 (0.0007) -[2023-10-12 07:08:44,534][78091] Updated weights for policy 0, policy_version 91820 (0.0008) -[2023-10-12 07:08:44,741][78123] Updated weights for policy 1, policy_version 91390 (0.0008) -[2023-10-12 07:08:44,894][78091] Updated weights for policy 0, policy_version 91830 (0.0008) -[2023-10-12 07:08:45,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 187596800. Throughput: 0: 1579.2, 1: 1596.7. Samples: 46905302. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-12 07:08:45,201][77203] Avg episode reward: [(0, '59.080'), (1, '59.610')] -[2023-10-12 07:08:45,265][78091] Updated weights for policy 0, policy_version 91840 (0.0008) -[2023-10-12 07:08:49,126][78123] Updated weights for policy 1, policy_version 91400 (0.0008) -[2023-10-12 07:08:49,493][78123] Updated weights for policy 1, policy_version 91410 (0.0010) -[2023-10-12 07:08:49,497][78091] Updated weights for policy 0, policy_version 91850 (0.0009) -[2023-10-12 07:08:49,856][78123] Updated weights for policy 1, policy_version 91420 (0.0008) -[2023-10-12 07:08:49,866][78091] Updated weights for policy 0, policy_version 91860 (0.0007) -[2023-10-12 07:08:50,201][77203] Fps is (10 sec: 9830.6, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 187662336. Throughput: 0: 1600.9, 1: 1609.2. Samples: 46924886. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-12 07:08:50,201][77203] Avg episode reward: [(0, '64.020'), (1, '57.220')] -[2023-10-12 07:08:50,232][78091] Updated weights for policy 0, policy_version 91870 (0.0010) -[2023-10-12 07:08:54,210][78123] Updated weights for policy 1, policy_version 91430 (0.0007) -[2023-10-12 07:08:54,462][78091] Updated weights for policy 0, policy_version 91880 (0.0010) -[2023-10-12 07:08:54,582][78123] Updated weights for policy 1, policy_version 91440 (0.0008) -[2023-10-12 07:08:54,830][78091] Updated weights for policy 0, policy_version 91890 (0.0009) -[2023-10-12 07:08:54,939][78123] Updated weights for policy 1, policy_version 91450 (0.0008) -[2023-10-12 07:08:55,194][78091] Updated weights for policy 0, policy_version 91900 (0.0008) -[2023-10-12 07:08:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 187727872. Throughput: 0: 1599.6, 1: 1600.0. Samples: 46943408. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-12 07:08:55,201][77203] Avg episode reward: [(0, '63.670'), (1, '57.500')] -[2023-10-12 07:08:59,293][78123] Updated weights for policy 1, policy_version 91460 (0.0007) -[2023-10-12 07:08:59,509][78091] Updated weights for policy 0, policy_version 91910 (0.0009) -[2023-10-12 07:08:59,657][78123] Updated weights for policy 1, policy_version 91470 (0.0008) -[2023-10-12 07:08:59,880][78091] Updated weights for policy 0, policy_version 91920 (0.0009) -[2023-10-12 07:09:00,021][78123] Updated weights for policy 1, policy_version 91480 (0.0008) -[2023-10-12 07:09:00,201][77203] Fps is (10 sec: 9829.9, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 187760640. Throughput: 0: 1586.1, 1: 1593.8. Samples: 46953356. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-12 07:09:00,202][77203] Avg episode reward: [(0, '53.940'), (1, '54.490')] -[2023-10-12 07:09:00,253][78091] Updated weights for policy 0, policy_version 91930 (0.0009) -[2023-10-12 07:09:04,460][78123] Updated weights for policy 1, policy_version 91490 (0.0007) -[2023-10-12 07:09:04,637][78091] Updated weights for policy 0, policy_version 91940 (0.0007) -[2023-10-12 07:09:04,826][78123] Updated weights for policy 1, policy_version 91500 (0.0009) -[2023-10-12 07:09:05,005][78091] Updated weights for policy 0, policy_version 91950 (0.0008) -[2023-10-12 07:09:05,187][78123] Updated weights for policy 1, policy_version 91510 (0.0010) -[2023-10-12 07:09:05,201][77203] Fps is (10 sec: 9830.2, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 187826176. Throughput: 0: 1595.5, 1: 1607.6. Samples: 46972784. Policy #0 lag: (min: 4.0, avg: 14.6, max: 36.0) -[2023-10-12 07:09:05,202][77203] Avg episode reward: [(0, '59.870'), (1, '54.890')] -[2023-10-12 07:09:05,373][78091] Updated weights for policy 0, policy_version 91960 (0.0007) -[2023-10-12 07:09:05,555][78123] Updated weights for policy 1, policy_version 91520 (0.0008) -[2023-10-12 07:09:09,820][78091] Updated weights for policy 0, policy_version 91970 (0.0007) -[2023-10-12 07:09:09,867][78123] Updated weights for policy 1, policy_version 91530 (0.0008) -[2023-10-12 07:09:10,201][77203] Fps is (10 sec: 13107.8, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 187891712. Throughput: 0: 1615.9, 1: 1606.9. Samples: 46991786. Policy #0 lag: (min: 4.0, avg: 14.6, max: 36.0) -[2023-10-12 07:09:10,201][77203] Avg episode reward: [(0, '60.960'), (1, '55.220')] -[2023-10-12 07:09:10,218][78091] Updated weights for policy 0, policy_version 91980 (0.0009) -[2023-10-12 07:09:10,239][78123] Updated weights for policy 1, policy_version 91540 (0.0008) -[2023-10-12 07:09:10,571][78091] Updated weights for policy 0, policy_version 91990 (0.0009) -[2023-10-12 07:09:10,597][78123] Updated weights for policy 1, policy_version 91550 (0.0009) -[2023-10-12 07:09:10,668][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000091552_93749248.pth... -[2023-10-12 07:09:10,697][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000090048_92209152.pth -[2023-10-12 07:09:10,937][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000092000_94208000.pth... -[2023-10-12 07:09:10,945][78091] Updated weights for policy 0, policy_version 92000 (0.0008) -[2023-10-12 07:09:10,971][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000090496_92667904.pth -[2023-10-12 07:09:14,685][78123] Updated weights for policy 1, policy_version 91560 (0.0009) -[2023-10-12 07:09:15,057][78123] Updated weights for policy 1, policy_version 91570 (0.0009) -[2023-10-12 07:09:15,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 187957248. Throughput: 0: 1587.7, 1: 1586.9. Samples: 47000668. Policy #0 lag: (min: 4.0, avg: 14.6, max: 36.0) -[2023-10-12 07:09:15,201][77203] Avg episode reward: [(0, '58.190'), (1, '60.250')] -[2023-10-12 07:09:15,360][78091] Updated weights for policy 0, policy_version 92010 (0.0009) -[2023-10-12 07:09:15,424][78123] Updated weights for policy 1, policy_version 91580 (0.0008) -[2023-10-12 07:09:15,728][78091] Updated weights for policy 0, policy_version 92020 (0.0007) -[2023-10-12 07:09:16,106][78091] Updated weights for policy 0, policy_version 92030 (0.0007) -[2023-10-12 07:09:19,794][78123] Updated weights for policy 1, policy_version 91590 (0.0008) -[2023-10-12 07:09:20,153][78123] Updated weights for policy 1, policy_version 91600 (0.0010) -[2023-10-12 07:09:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 188022784. Throughput: 0: 1587.8, 1: 1598.6. Samples: 47020284. Policy #0 lag: (min: 4.0, avg: 14.6, max: 36.0) -[2023-10-12 07:09:20,201][77203] Avg episode reward: [(0, '63.720'), (1, '57.210')] -[2023-10-12 07:09:20,305][78091] Updated weights for policy 0, policy_version 92040 (0.0010) -[2023-10-12 07:09:20,529][78123] Updated weights for policy 1, policy_version 91610 (0.0008) -[2023-10-12 07:09:20,675][78091] Updated weights for policy 0, policy_version 92050 (0.0010) -[2023-10-12 07:09:21,045][78091] Updated weights for policy 0, policy_version 92060 (0.0007) -[2023-10-12 07:09:24,695][78123] Updated weights for policy 1, policy_version 91620 (0.0008) -[2023-10-12 07:09:25,054][78123] Updated weights for policy 1, policy_version 91630 (0.0007) -[2023-10-12 07:09:25,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 188088320. Throughput: 0: 1605.8, 1: 1613.3. Samples: 47039716. Policy #0 lag: (min: 4.0, avg: 14.6, max: 36.0) -[2023-10-12 07:09:25,201][77203] Avg episode reward: [(0, '58.900'), (1, '51.160')] -[2023-10-12 07:09:25,421][78123] Updated weights for policy 1, policy_version 91640 (0.0009) -[2023-10-12 07:09:25,492][78091] Updated weights for policy 0, policy_version 92070 (0.0009) -[2023-10-12 07:09:25,867][78091] Updated weights for policy 0, policy_version 92080 (0.0011) -[2023-10-12 07:09:26,246][78091] Updated weights for policy 0, policy_version 92090 (0.0010) -[2023-10-12 07:09:29,867][78123] Updated weights for policy 1, policy_version 91650 (0.0007) -[2023-10-12 07:09:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 188153856. Throughput: 0: 1588.9, 1: 1593.2. Samples: 47048500. Policy #0 lag: (min: 4.0, avg: 14.6, max: 36.0) -[2023-10-12 07:09:30,201][77203] Avg episode reward: [(0, '59.480'), (1, '53.330')] -[2023-10-12 07:09:30,226][78123] Updated weights for policy 1, policy_version 91660 (0.0009) -[2023-10-12 07:09:30,513][78091] Updated weights for policy 0, policy_version 92100 (0.0008) -[2023-10-12 07:09:30,589][78123] Updated weights for policy 1, policy_version 91670 (0.0009) -[2023-10-12 07:09:30,884][78091] Updated weights for policy 0, policy_version 92110 (0.0010) -[2023-10-12 07:09:30,960][78123] Updated weights for policy 1, policy_version 91680 (0.0008) -[2023-10-12 07:09:31,253][78091] Updated weights for policy 0, policy_version 92120 (0.0010) -[2023-10-12 07:09:35,191][78123] Updated weights for policy 1, policy_version 91690 (0.0010) -[2023-10-12 07:09:35,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 188219392. Throughput: 0: 1588.7, 1: 1594.9. Samples: 47068150. Policy #0 lag: (min: 4.0, avg: 14.6, max: 36.0) -[2023-10-12 07:09:35,201][77203] Avg episode reward: [(0, '60.430'), (1, '50.920')] -[2023-10-12 07:09:35,488][78091] Updated weights for policy 0, policy_version 92130 (0.0009) -[2023-10-12 07:09:35,562][78123] Updated weights for policy 1, policy_version 91700 (0.0009) -[2023-10-12 07:09:35,846][78091] Updated weights for policy 0, policy_version 92140 (0.0007) -[2023-10-12 07:09:35,920][78123] Updated weights for policy 1, policy_version 91710 (0.0008) -[2023-10-12 07:09:36,213][78091] Updated weights for policy 0, policy_version 92150 (0.0007) -[2023-10-12 07:09:36,583][78091] Updated weights for policy 0, policy_version 92160 (0.0008) -[2023-10-12 07:09:40,190][78123] Updated weights for policy 1, policy_version 91720 (0.0008) -[2023-10-12 07:09:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 188284928. Throughput: 0: 1595.4, 1: 1607.8. Samples: 47087552. Policy #0 lag: (min: 4.0, avg: 14.6, max: 36.0) -[2023-10-12 07:09:40,202][77203] Avg episode reward: [(0, '61.360'), (1, '51.120')] -[2023-10-12 07:09:40,560][78123] Updated weights for policy 1, policy_version 91730 (0.0008) -[2023-10-12 07:09:40,925][78123] Updated weights for policy 1, policy_version 91740 (0.0007) -[2023-10-12 07:09:41,027][78091] Updated weights for policy 0, policy_version 92170 (0.0010) -[2023-10-12 07:09:41,404][78091] Updated weights for policy 0, policy_version 92180 (0.0010) -[2023-10-12 07:09:41,779][78091] Updated weights for policy 0, policy_version 92190 (0.0009) -[2023-10-12 07:09:45,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 188350464. Throughput: 0: 1579.9, 1: 1591.7. Samples: 47096074. Policy #0 lag: (min: 4.0, avg: 14.6, max: 36.0) -[2023-10-12 07:09:45,202][77203] Avg episode reward: [(0, '55.550'), (1, '54.500')] -[2023-10-12 07:09:45,277][78123] Updated weights for policy 1, policy_version 91750 (0.0009) -[2023-10-12 07:09:45,644][78123] Updated weights for policy 1, policy_version 91760 (0.0009) -[2023-10-12 07:09:46,013][78123] Updated weights for policy 1, policy_version 91770 (0.0008) -[2023-10-12 07:09:46,246][78091] Updated weights for policy 0, policy_version 92200 (0.0010) -[2023-10-12 07:09:46,619][78091] Updated weights for policy 0, policy_version 92210 (0.0008) -[2023-10-12 07:09:46,985][78091] Updated weights for policy 0, policy_version 92220 (0.0009) -[2023-10-12 07:09:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 188416000. Throughput: 0: 1581.8, 1: 1591.2. Samples: 47115570. Policy #0 lag: (min: 4.0, avg: 14.6, max: 36.0) -[2023-10-12 07:09:50,201][77203] Avg episode reward: [(0, '58.110'), (1, '54.420')] -[2023-10-12 07:09:50,565][78123] Updated weights for policy 1, policy_version 91780 (0.0008) -[2023-10-12 07:09:50,938][78123] Updated weights for policy 1, policy_version 91790 (0.0009) -[2023-10-12 07:09:51,302][78123] Updated weights for policy 1, policy_version 91800 (0.0008) -[2023-10-12 07:09:51,385][78091] Updated weights for policy 0, policy_version 92230 (0.0008) -[2023-10-12 07:09:51,753][78091] Updated weights for policy 0, policy_version 92240 (0.0009) -[2023-10-12 07:09:52,131][78091] Updated weights for policy 0, policy_version 92250 (0.0008) -[2023-10-12 07:09:55,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 188481536. Throughput: 0: 1586.3, 1: 1597.9. Samples: 47135072. Policy #0 lag: (min: 4.0, avg: 14.6, max: 36.0) -[2023-10-12 07:09:55,202][77203] Avg episode reward: [(0, '54.750'), (1, '54.210')] -[2023-10-12 07:09:55,595][78123] Updated weights for policy 1, policy_version 91810 (0.0009) -[2023-10-12 07:09:55,989][78123] Updated weights for policy 1, policy_version 91820 (0.0008) -[2023-10-12 07:09:56,258][78091] Updated weights for policy 0, policy_version 92260 (0.0009) -[2023-10-12 07:09:56,358][78123] Updated weights for policy 1, policy_version 91830 (0.0008) -[2023-10-12 07:09:56,645][78091] Updated weights for policy 0, policy_version 92270 (0.0009) -[2023-10-12 07:09:56,719][78123] Updated weights for policy 1, policy_version 91840 (0.0009) -[2023-10-12 07:09:57,016][78091] Updated weights for policy 0, policy_version 92280 (0.0011) -[2023-10-12 07:10:00,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 188547072. Throughput: 0: 1584.2, 1: 1590.9. Samples: 47143546. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-12 07:10:00,202][77203] Avg episode reward: [(0, '56.150'), (1, '53.910')] -[2023-10-12 07:10:01,110][78123] Updated weights for policy 1, policy_version 91850 (0.0008) -[2023-10-12 07:10:01,188][78091] Updated weights for policy 0, policy_version 92290 (0.0010) -[2023-10-12 07:10:01,464][78123] Updated weights for policy 1, policy_version 91860 (0.0007) -[2023-10-12 07:10:01,551][78091] Updated weights for policy 0, policy_version 92300 (0.0008) -[2023-10-12 07:10:01,834][78123] Updated weights for policy 1, policy_version 91870 (0.0008) -[2023-10-12 07:10:01,917][78091] Updated weights for policy 0, policy_version 92310 (0.0010) -[2023-10-12 07:10:02,289][78091] Updated weights for policy 0, policy_version 92320 (0.0009) -[2023-10-12 07:10:05,201][77203] Fps is (10 sec: 13107.6, 60 sec: 13107.3, 300 sec: 12774.0). Total num frames: 188612608. Throughput: 0: 1583.1, 1: 1589.4. Samples: 47163046. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-12 07:10:05,201][77203] Avg episode reward: [(0, '55.970'), (1, '56.110')] -[2023-10-12 07:10:06,158][78123] Updated weights for policy 1, policy_version 91880 (0.0008) -[2023-10-12 07:10:06,530][78123] Updated weights for policy 1, policy_version 91890 (0.0008) -[2023-10-12 07:10:06,810][78091] Updated weights for policy 0, policy_version 92330 (0.0009) -[2023-10-12 07:10:06,891][78123] Updated weights for policy 1, policy_version 91900 (0.0007) -[2023-10-12 07:10:07,179][78091] Updated weights for policy 0, policy_version 92340 (0.0008) -[2023-10-12 07:10:07,548][78091] Updated weights for policy 0, policy_version 92350 (0.0008) -[2023-10-12 07:10:10,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 188678144. Throughput: 0: 1580.5, 1: 1594.4. Samples: 47182588. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-12 07:10:10,202][77203] Avg episode reward: [(0, '54.490'), (1, '58.460')] -[2023-10-12 07:10:11,170][78123] Updated weights for policy 1, policy_version 91910 (0.0008) -[2023-10-12 07:10:11,539][78123] Updated weights for policy 1, policy_version 91920 (0.0007) -[2023-10-12 07:10:11,609][78091] Updated weights for policy 0, policy_version 92360 (0.0008) -[2023-10-12 07:10:11,893][78123] Updated weights for policy 1, policy_version 91930 (0.0007) -[2023-10-12 07:10:11,976][78091] Updated weights for policy 0, policy_version 92370 (0.0009) -[2023-10-12 07:10:12,340][78091] Updated weights for policy 0, policy_version 92380 (0.0009) -[2023-10-12 07:10:15,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 188743680. Throughput: 0: 1583.1, 1: 1588.4. Samples: 47191218. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-12 07:10:15,202][77203] Avg episode reward: [(0, '55.510'), (1, '55.370')] -[2023-10-12 07:10:16,289][78123] Updated weights for policy 1, policy_version 91940 (0.0008) -[2023-10-12 07:10:16,533][78091] Updated weights for policy 0, policy_version 92390 (0.0009) -[2023-10-12 07:10:16,648][78123] Updated weights for policy 1, policy_version 91950 (0.0009) -[2023-10-12 07:10:16,900][78091] Updated weights for policy 0, policy_version 92400 (0.0007) -[2023-10-12 07:10:17,023][78123] Updated weights for policy 1, policy_version 91960 (0.0009) -[2023-10-12 07:10:17,276][78091] Updated weights for policy 0, policy_version 92410 (0.0009) -[2023-10-12 07:10:20,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 188809216. Throughput: 0: 1587.3, 1: 1586.2. Samples: 47210960. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-12 07:10:20,201][77203] Avg episode reward: [(0, '51.090'), (1, '55.430')] -[2023-10-12 07:10:21,365][78123] Updated weights for policy 1, policy_version 91970 (0.0007) -[2023-10-12 07:10:21,641][78091] Updated weights for policy 0, policy_version 92420 (0.0008) -[2023-10-12 07:10:21,733][78123] Updated weights for policy 1, policy_version 91980 (0.0007) -[2023-10-12 07:10:22,022][78091] Updated weights for policy 0, policy_version 92430 (0.0009) -[2023-10-12 07:10:22,092][78123] Updated weights for policy 1, policy_version 91990 (0.0009) -[2023-10-12 07:10:22,385][78091] Updated weights for policy 0, policy_version 92440 (0.0007) -[2023-10-12 07:10:22,458][78123] Updated weights for policy 1, policy_version 92000 (0.0007) -[2023-10-12 07:10:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 188874752. Throughput: 0: 1590.7, 1: 1582.7. Samples: 47230352. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-12 07:10:25,202][77203] Avg episode reward: [(0, '60.510'), (1, '57.960')] -[2023-10-12 07:10:26,720][78123] Updated weights for policy 1, policy_version 92010 (0.0007) -[2023-10-12 07:10:26,723][78091] Updated weights for policy 0, policy_version 92450 (0.0008) -[2023-10-12 07:10:27,082][78123] Updated weights for policy 1, policy_version 92020 (0.0009) -[2023-10-12 07:10:27,085][78091] Updated weights for policy 0, policy_version 92460 (0.0008) -[2023-10-12 07:10:27,452][78123] Updated weights for policy 1, policy_version 92030 (0.0009) -[2023-10-12 07:10:27,452][78091] Updated weights for policy 0, policy_version 92470 (0.0008) -[2023-10-12 07:10:27,824][78091] Updated weights for policy 0, policy_version 92480 (0.0008) -[2023-10-12 07:10:30,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 188940288. Throughput: 0: 1597.6, 1: 1584.0. Samples: 47239246. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-12 07:10:30,202][77203] Avg episode reward: [(0, '55.620'), (1, '50.000')] -[2023-10-12 07:10:31,883][78123] Updated weights for policy 1, policy_version 92040 (0.0007) -[2023-10-12 07:10:32,210][78091] Updated weights for policy 0, policy_version 92490 (0.0007) -[2023-10-12 07:10:32,254][78123] Updated weights for policy 1, policy_version 92050 (0.0007) -[2023-10-12 07:10:32,576][78091] Updated weights for policy 0, policy_version 92500 (0.0007) -[2023-10-12 07:10:32,611][78123] Updated weights for policy 1, policy_version 92060 (0.0011) -[2023-10-12 07:10:32,953][78091] Updated weights for policy 0, policy_version 92510 (0.0008) -[2023-10-12 07:10:35,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 189005824. Throughput: 0: 1596.3, 1: 1582.4. Samples: 47258612. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-12 07:10:35,202][77203] Avg episode reward: [(0, '56.500'), (1, '50.000')] -[2023-10-12 07:10:36,931][78123] Updated weights for policy 1, policy_version 92070 (0.0009) -[2023-10-12 07:10:37,260][78091] Updated weights for policy 0, policy_version 92520 (0.0008) -[2023-10-12 07:10:37,299][78123] Updated weights for policy 1, policy_version 92080 (0.0008) -[2023-10-12 07:10:37,629][78091] Updated weights for policy 0, policy_version 92530 (0.0009) -[2023-10-12 07:10:37,669][78123] Updated weights for policy 1, policy_version 92090 (0.0008) -[2023-10-12 07:10:37,995][78091] Updated weights for policy 0, policy_version 92540 (0.0007) -[2023-10-12 07:10:40,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 189071360. Throughput: 0: 1594.1, 1: 1583.8. Samples: 47278078. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-12 07:10:40,202][77203] Avg episode reward: [(0, '62.380'), (1, '51.300')] -[2023-10-12 07:10:42,168][78123] Updated weights for policy 1, policy_version 92100 (0.0007) -[2023-10-12 07:10:42,337][78091] Updated weights for policy 0, policy_version 92550 (0.0008) -[2023-10-12 07:10:42,547][78123] Updated weights for policy 1, policy_version 92110 (0.0009) -[2023-10-12 07:10:42,721][78091] Updated weights for policy 0, policy_version 92560 (0.0009) -[2023-10-12 07:10:42,919][78123] Updated weights for policy 1, policy_version 92120 (0.0010) -[2023-10-12 07:10:43,083][78091] Updated weights for policy 0, policy_version 92570 (0.0007) -[2023-10-12 07:10:45,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 189136896. Throughput: 0: 1606.3, 1: 1593.1. Samples: 47287518. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-12 07:10:45,202][77203] Avg episode reward: [(0, '59.700'), (1, '53.510')] -[2023-10-12 07:10:47,139][78123] Updated weights for policy 1, policy_version 92130 (0.0007) -[2023-10-12 07:10:47,300][78091] Updated weights for policy 0, policy_version 92580 (0.0007) -[2023-10-12 07:10:47,505][78123] Updated weights for policy 1, policy_version 92140 (0.0009) -[2023-10-12 07:10:47,670][78091] Updated weights for policy 0, policy_version 92590 (0.0007) -[2023-10-12 07:10:47,873][78123] Updated weights for policy 1, policy_version 92150 (0.0008) -[2023-10-12 07:10:48,036][78091] Updated weights for policy 0, policy_version 92600 (0.0007) -[2023-10-12 07:10:48,243][78123] Updated weights for policy 1, policy_version 92160 (0.0009) -[2023-10-12 07:10:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 189202432. Throughput: 0: 1596.8, 1: 1579.4. Samples: 47305974. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-12 07:10:50,202][77203] Avg episode reward: [(0, '56.620'), (1, '55.890')] -[2023-10-12 07:10:52,410][78123] Updated weights for policy 1, policy_version 92170 (0.0009) -[2023-10-12 07:10:52,493][78091] Updated weights for policy 0, policy_version 92610 (0.0007) -[2023-10-12 07:10:52,760][78123] Updated weights for policy 1, policy_version 92180 (0.0008) -[2023-10-12 07:10:52,866][78091] Updated weights for policy 0, policy_version 92620 (0.0007) -[2023-10-12 07:10:53,127][78123] Updated weights for policy 1, policy_version 92190 (0.0008) -[2023-10-12 07:10:53,223][78091] Updated weights for policy 0, policy_version 92630 (0.0008) -[2023-10-12 07:10:53,594][78091] Updated weights for policy 0, policy_version 92640 (0.0007) -[2023-10-12 07:10:55,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 12774.0). Total num frames: 189267968. Throughput: 0: 1598.7, 1: 1579.2. Samples: 47325594. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-12 07:10:55,201][77203] Avg episode reward: [(0, '60.120'), (1, '56.050')] -[2023-10-12 07:10:57,616][78123] Updated weights for policy 1, policy_version 92200 (0.0009) -[2023-10-12 07:10:57,970][78123] Updated weights for policy 1, policy_version 92210 (0.0008) -[2023-10-12 07:10:57,992][78091] Updated weights for policy 0, policy_version 92650 (0.0008) -[2023-10-12 07:10:58,332][78123] Updated weights for policy 1, policy_version 92220 (0.0009) -[2023-10-12 07:10:58,367][78091] Updated weights for policy 0, policy_version 92660 (0.0008) -[2023-10-12 07:10:58,743][78091] Updated weights for policy 0, policy_version 92670 (0.0009) -[2023-10-12 07:11:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 189333504. Throughput: 0: 1617.2, 1: 1597.0. Samples: 47335860. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-12 07:11:00,202][77203] Avg episode reward: [(0, '54.410'), (1, '53.260')] -[2023-10-12 07:11:02,704][78123] Updated weights for policy 1, policy_version 92230 (0.0008) -[2023-10-12 07:11:03,031][78091] Updated weights for policy 0, policy_version 92680 (0.0008) -[2023-10-12 07:11:03,066][78123] Updated weights for policy 1, policy_version 92240 (0.0010) -[2023-10-12 07:11:03,400][78091] Updated weights for policy 0, policy_version 92690 (0.0008) -[2023-10-12 07:11:03,438][78123] Updated weights for policy 1, policy_version 92250 (0.0007) -[2023-10-12 07:11:03,775][78091] Updated weights for policy 0, policy_version 92700 (0.0008) -[2023-10-12 07:11:05,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 189399040. Throughput: 0: 1593.6, 1: 1578.7. Samples: 47353710. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-12 07:11:05,202][77203] Avg episode reward: [(0, '59.390'), (1, '54.690')] -[2023-10-12 07:11:07,934][78123] Updated weights for policy 1, policy_version 92260 (0.0007) -[2023-10-12 07:11:08,149][78091] Updated weights for policy 0, policy_version 92710 (0.0007) -[2023-10-12 07:11:08,307][78123] Updated weights for policy 1, policy_version 92270 (0.0009) -[2023-10-12 07:11:08,520][78091] Updated weights for policy 0, policy_version 92720 (0.0009) -[2023-10-12 07:11:08,672][78123] Updated weights for policy 1, policy_version 92280 (0.0007) -[2023-10-12 07:11:08,896][78091] Updated weights for policy 0, policy_version 92730 (0.0009) -[2023-10-12 07:11:10,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 189464576. Throughput: 0: 1585.2, 1: 1580.3. Samples: 47372800. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-12 07:11:10,201][77203] Avg episode reward: [(0, '55.240'), (1, '52.790')] -[2023-10-12 07:11:10,209][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000092288_94502912.pth... -[2023-10-12 07:11:10,210][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000092736_94961664.pth... -[2023-10-12 07:11:10,244][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000091232_93421568.pth -[2023-10-12 07:11:10,248][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000090784_92962816.pth -[2023-10-12 07:11:12,994][78123] Updated weights for policy 1, policy_version 92290 (0.0009) -[2023-10-12 07:11:13,314][78091] Updated weights for policy 0, policy_version 92740 (0.0010) -[2023-10-12 07:11:13,359][78123] Updated weights for policy 1, policy_version 92300 (0.0008) -[2023-10-12 07:11:13,683][78091] Updated weights for policy 0, policy_version 92750 (0.0007) -[2023-10-12 07:11:13,739][78123] Updated weights for policy 1, policy_version 92310 (0.0008) -[2023-10-12 07:11:14,047][78091] Updated weights for policy 0, policy_version 92760 (0.0007) -[2023-10-12 07:11:14,096][78123] Updated weights for policy 1, policy_version 92320 (0.0008) -[2023-10-12 07:11:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 189530112. Throughput: 0: 1606.2, 1: 1601.9. Samples: 47383610. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-12 07:11:15,201][77203] Avg episode reward: [(0, '54.980'), (1, '50.210')] -[2023-10-12 07:11:18,338][78123] Updated weights for policy 1, policy_version 92330 (0.0008) -[2023-10-12 07:11:18,365][78091] Updated weights for policy 0, policy_version 92770 (0.0008) -[2023-10-12 07:11:18,700][78123] Updated weights for policy 1, policy_version 92340 (0.0009) -[2023-10-12 07:11:18,735][78091] Updated weights for policy 0, policy_version 92780 (0.0008) -[2023-10-12 07:11:19,062][78123] Updated weights for policy 1, policy_version 92350 (0.0009) -[2023-10-12 07:11:19,115][78091] Updated weights for policy 0, policy_version 92790 (0.0009) -[2023-10-12 07:11:19,480][78091] Updated weights for policy 0, policy_version 92800 (0.0009) -[2023-10-12 07:11:20,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 189595648. Throughput: 0: 1596.8, 1: 1588.2. Samples: 47401936. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-12 07:11:20,202][77203] Avg episode reward: [(0, '59.230'), (1, '50.260')] -[2023-10-12 07:11:23,564][78123] Updated weights for policy 1, policy_version 92360 (0.0007) -[2023-10-12 07:11:23,714][78091] Updated weights for policy 0, policy_version 92810 (0.0009) -[2023-10-12 07:11:23,927][78123] Updated weights for policy 1, policy_version 92370 (0.0007) -[2023-10-12 07:11:24,082][78091] Updated weights for policy 0, policy_version 92820 (0.0008) -[2023-10-12 07:11:24,301][78123] Updated weights for policy 1, policy_version 92380 (0.0009) -[2023-10-12 07:11:24,445][78091] Updated weights for policy 0, policy_version 92830 (0.0007) -[2023-10-12 07:11:25,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 189661184. Throughput: 0: 1584.6, 1: 1578.6. Samples: 47420424. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-12 07:11:25,202][77203] Avg episode reward: [(0, '48.030'), (1, '55.080')] -[2023-10-12 07:11:28,619][78123] Updated weights for policy 1, policy_version 92390 (0.0008) -[2023-10-12 07:11:28,807][78091] Updated weights for policy 0, policy_version 92840 (0.0009) -[2023-10-12 07:11:28,997][78123] Updated weights for policy 1, policy_version 92400 (0.0007) -[2023-10-12 07:11:29,180][78091] Updated weights for policy 0, policy_version 92850 (0.0008) -[2023-10-12 07:11:29,361][78123] Updated weights for policy 1, policy_version 92410 (0.0008) -[2023-10-12 07:11:29,555][78091] Updated weights for policy 0, policy_version 92860 (0.0010) -[2023-10-12 07:11:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 189726720. Throughput: 0: 1600.9, 1: 1598.5. Samples: 47431492. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-12 07:11:30,202][77203] Avg episode reward: [(0, '63.670'), (1, '50.390')] -[2023-10-12 07:11:33,415][78123] Updated weights for policy 1, policy_version 92420 (0.0008) -[2023-10-12 07:11:33,784][78123] Updated weights for policy 1, policy_version 92430 (0.0007) -[2023-10-12 07:11:33,857][78091] Updated weights for policy 0, policy_version 92870 (0.0008) -[2023-10-12 07:11:34,139][78123] Updated weights for policy 1, policy_version 92440 (0.0007) -[2023-10-12 07:11:34,224][78091] Updated weights for policy 0, policy_version 92880 (0.0008) -[2023-10-12 07:11:34,586][78091] Updated weights for policy 0, policy_version 92890 (0.0010) -[2023-10-12 07:11:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 189792256. Throughput: 0: 1607.4, 1: 1604.3. Samples: 47450498. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-12 07:11:35,202][77203] Avg episode reward: [(0, '61.260'), (1, '50.280')] -[2023-10-12 07:11:38,504][78123] Updated weights for policy 1, policy_version 92450 (0.0008) -[2023-10-12 07:11:38,868][78123] Updated weights for policy 1, policy_version 92460 (0.0010) -[2023-10-12 07:11:39,119][78091] Updated weights for policy 0, policy_version 92900 (0.0009) -[2023-10-12 07:11:39,236][78123] Updated weights for policy 1, policy_version 92470 (0.0009) -[2023-10-12 07:11:39,484][78091] Updated weights for policy 0, policy_version 92910 (0.0007) -[2023-10-12 07:11:39,602][78123] Updated weights for policy 1, policy_version 92480 (0.0007) -[2023-10-12 07:11:39,860][78091] Updated weights for policy 0, policy_version 92920 (0.0007) -[2023-10-12 07:11:40,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 189857792. Throughput: 0: 1593.4, 1: 1585.9. Samples: 47468662. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-12 07:11:40,201][77203] Avg episode reward: [(0, '57.740'), (1, '47.750')] -[2023-10-12 07:11:44,061][78123] Updated weights for policy 1, policy_version 92490 (0.0009) -[2023-10-12 07:11:44,199][78091] Updated weights for policy 0, policy_version 92930 (0.0009) -[2023-10-12 07:11:44,442][78123] Updated weights for policy 1, policy_version 92500 (0.0010) -[2023-10-12 07:11:44,580][78091] Updated weights for policy 0, policy_version 92940 (0.0009) -[2023-10-12 07:11:44,804][78123] Updated weights for policy 1, policy_version 92510 (0.0009) -[2023-10-12 07:11:44,943][78091] Updated weights for policy 0, policy_version 92950 (0.0009) -[2023-10-12 07:11:45,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 189890560. Throughput: 0: 1590.4, 1: 1592.1. Samples: 47479076. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-12 07:11:45,202][77203] Avg episode reward: [(0, '55.830'), (1, '50.100')] -[2023-10-12 07:11:45,312][78091] Updated weights for policy 0, policy_version 92960 (0.0007) -[2023-10-12 07:11:49,326][78123] Updated weights for policy 1, policy_version 92520 (0.0008) -[2023-10-12 07:11:49,438][78091] Updated weights for policy 0, policy_version 92970 (0.0007) -[2023-10-12 07:11:49,680][78123] Updated weights for policy 1, policy_version 92530 (0.0007) -[2023-10-12 07:11:49,803][78091] Updated weights for policy 0, policy_version 92980 (0.0007) -[2023-10-12 07:11:50,062][78123] Updated weights for policy 1, policy_version 92540 (0.0008) -[2023-10-12 07:11:50,166][78091] Updated weights for policy 0, policy_version 92990 (0.0008) -[2023-10-12 07:11:50,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 189956096. Throughput: 0: 1611.1, 1: 1606.6. Samples: 47498506. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-12 07:11:50,202][77203] Avg episode reward: [(0, '52.940'), (1, '52.780')] -[2023-10-12 07:11:54,138][78123] Updated weights for policy 1, policy_version 92550 (0.0009) -[2023-10-12 07:11:54,451][78091] Updated weights for policy 0, policy_version 93000 (0.0009) -[2023-10-12 07:11:54,505][78123] Updated weights for policy 1, policy_version 92560 (0.0009) -[2023-10-12 07:11:54,814][78091] Updated weights for policy 0, policy_version 93010 (0.0007) -[2023-10-12 07:11:54,876][78123] Updated weights for policy 1, policy_version 92570 (0.0008) -[2023-10-12 07:11:55,186][78091] Updated weights for policy 0, policy_version 93020 (0.0007) -[2023-10-12 07:11:55,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 190021632. Throughput: 0: 1603.0, 1: 1598.5. Samples: 47516868. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-12 07:11:55,202][77203] Avg episode reward: [(0, '56.810'), (1, '53.190')] -[2023-10-12 07:11:59,240][78091] Updated weights for policy 0, policy_version 93030 (0.0008) -[2023-10-12 07:11:59,261][78123] Updated weights for policy 1, policy_version 92580 (0.0008) -[2023-10-12 07:11:59,614][78091] Updated weights for policy 0, policy_version 93040 (0.0008) -[2023-10-12 07:11:59,626][78123] Updated weights for policy 1, policy_version 92590 (0.0009) -[2023-10-12 07:11:59,978][78091] Updated weights for policy 0, policy_version 93050 (0.0009) -[2023-10-12 07:11:59,990][78123] Updated weights for policy 1, policy_version 92600 (0.0010) -[2023-10-12 07:12:00,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 190087168. Throughput: 0: 1594.8, 1: 1586.8. Samples: 47526782. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-12 07:12:00,201][77203] Avg episode reward: [(0, '50.080'), (1, '53.730')] -[2023-10-12 07:12:04,276][78091] Updated weights for policy 0, policy_version 93060 (0.0010) -[2023-10-12 07:12:04,282][78123] Updated weights for policy 1, policy_version 92610 (0.0009) -[2023-10-12 07:12:04,653][78091] Updated weights for policy 0, policy_version 93070 (0.0008) -[2023-10-12 07:12:04,657][78123] Updated weights for policy 1, policy_version 92620 (0.0008) -[2023-10-12 07:12:05,020][78123] Updated weights for policy 1, policy_version 92630 (0.0009) -[2023-10-12 07:12:05,025][78091] Updated weights for policy 0, policy_version 93080 (0.0009) -[2023-10-12 07:12:05,201][77203] Fps is (10 sec: 9830.6, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 190119936. Throughput: 0: 1612.0, 1: 1605.0. Samples: 47546700. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-12 07:12:05,201][77203] Avg episode reward: [(0, '53.860'), (1, '51.780')] -[2023-10-12 07:12:05,388][78123] Updated weights for policy 1, policy_version 92640 (0.0007) -[2023-10-12 07:12:09,362][78091] Updated weights for policy 0, policy_version 93090 (0.0007) -[2023-10-12 07:12:09,727][78091] Updated weights for policy 0, policy_version 93100 (0.0008) -[2023-10-12 07:12:09,777][78123] Updated weights for policy 1, policy_version 92650 (0.0008) -[2023-10-12 07:12:10,091][78091] Updated weights for policy 0, policy_version 93110 (0.0007) -[2023-10-12 07:12:10,144][78123] Updated weights for policy 1, policy_version 92660 (0.0011) -[2023-10-12 07:12:10,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 190185472. Throughput: 0: 1613.4, 1: 1604.4. Samples: 47565226. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-12 07:12:10,201][77203] Avg episode reward: [(0, '54.030'), (1, '52.000')] -[2023-10-12 07:12:10,465][78091] Updated weights for policy 0, policy_version 93120 (0.0008) -[2023-10-12 07:12:10,505][78123] Updated weights for policy 1, policy_version 92670 (0.0011) -[2023-10-12 07:12:14,772][78091] Updated weights for policy 0, policy_version 93130 (0.0011) -[2023-10-12 07:12:15,075][78123] Updated weights for policy 1, policy_version 92680 (0.0010) -[2023-10-12 07:12:15,133][78091] Updated weights for policy 0, policy_version 93140 (0.0009) -[2023-10-12 07:12:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 190251008. Throughput: 0: 1600.8, 1: 1583.6. Samples: 47574792. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-12 07:12:15,202][77203] Avg episode reward: [(0, '59.870'), (1, '56.140')] -[2023-10-12 07:12:15,451][78123] Updated weights for policy 1, policy_version 92690 (0.0008) -[2023-10-12 07:12:15,503][78091] Updated weights for policy 0, policy_version 93150 (0.0007) -[2023-10-12 07:12:15,826][78123] Updated weights for policy 1, policy_version 92700 (0.0009) -[2023-10-12 07:12:19,863][78091] Updated weights for policy 0, policy_version 93160 (0.0009) -[2023-10-12 07:12:20,160][78123] Updated weights for policy 1, policy_version 92710 (0.0007) -[2023-10-12 07:12:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 190316544. Throughput: 0: 1600.2, 1: 1583.4. Samples: 47593758. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-12 07:12:20,201][77203] Avg episode reward: [(0, '56.160'), (1, '53.260')] -[2023-10-12 07:12:20,241][78091] Updated weights for policy 0, policy_version 93170 (0.0008) -[2023-10-12 07:12:20,521][78123] Updated weights for policy 1, policy_version 92720 (0.0007) -[2023-10-12 07:12:20,607][78091] Updated weights for policy 0, policy_version 93180 (0.0009) -[2023-10-12 07:12:20,884][78123] Updated weights for policy 1, policy_version 92730 (0.0010) -[2023-10-12 07:12:24,886][78091] Updated weights for policy 0, policy_version 93190 (0.0008) -[2023-10-12 07:12:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 190382080. Throughput: 0: 1612.5, 1: 1595.2. Samples: 47613010. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-12 07:12:25,201][77203] Avg episode reward: [(0, '55.250'), (1, '53.960')] -[2023-10-12 07:12:25,246][78091] Updated weights for policy 0, policy_version 93200 (0.0008) -[2023-10-12 07:12:25,343][78123] Updated weights for policy 1, policy_version 92740 (0.0010) -[2023-10-12 07:12:25,621][78091] Updated weights for policy 0, policy_version 93210 (0.0008) -[2023-10-12 07:12:25,717][78123] Updated weights for policy 1, policy_version 92750 (0.0007) -[2023-10-12 07:12:26,090][78123] Updated weights for policy 1, policy_version 92760 (0.0008) -[2023-10-12 07:12:29,870][78091] Updated weights for policy 0, policy_version 93220 (0.0008) -[2023-10-12 07:12:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 190447616. Throughput: 0: 1598.4, 1: 1573.7. Samples: 47621820. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-12 07:12:30,201][77203] Avg episode reward: [(0, '63.960'), (1, '56.220')] -[2023-10-12 07:12:30,244][78091] Updated weights for policy 0, policy_version 93230 (0.0008) -[2023-10-12 07:12:30,419][78123] Updated weights for policy 1, policy_version 92770 (0.0009) -[2023-10-12 07:12:30,608][78091] Updated weights for policy 0, policy_version 93240 (0.0007) -[2023-10-12 07:12:30,781][78123] Updated weights for policy 1, policy_version 92780 (0.0007) -[2023-10-12 07:12:31,145][78123] Updated weights for policy 1, policy_version 92790 (0.0008) -[2023-10-12 07:12:31,509][78123] Updated weights for policy 1, policy_version 92800 (0.0010) -[2023-10-12 07:12:35,047][78091] Updated weights for policy 0, policy_version 93250 (0.0008) -[2023-10-12 07:12:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 190513152. Throughput: 0: 1599.6, 1: 1573.5. Samples: 47641296. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-12 07:12:35,201][77203] Avg episode reward: [(0, '55.440'), (1, '51.770')] -[2023-10-12 07:12:35,417][78091] Updated weights for policy 0, policy_version 93260 (0.0008) -[2023-10-12 07:12:35,780][78091] Updated weights for policy 0, policy_version 93270 (0.0009) -[2023-10-12 07:12:36,006][78123] Updated weights for policy 1, policy_version 92810 (0.0008) -[2023-10-12 07:12:36,145][78091] Updated weights for policy 0, policy_version 93280 (0.0007) -[2023-10-12 07:12:36,371][78123] Updated weights for policy 1, policy_version 92820 (0.0008) -[2023-10-12 07:12:36,743][78123] Updated weights for policy 1, policy_version 92830 (0.0009) -[2023-10-12 07:12:40,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 190578688. Throughput: 0: 1609.5, 1: 1586.5. Samples: 47660688. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-12 07:12:40,202][77203] Avg episode reward: [(0, '60.760'), (1, '46.460')] -[2023-10-12 07:12:40,532][78091] Updated weights for policy 0, policy_version 93290 (0.0007) -[2023-10-12 07:12:40,908][78091] Updated weights for policy 0, policy_version 93300 (0.0007) -[2023-10-12 07:12:41,075][78123] Updated weights for policy 1, policy_version 92840 (0.0008) -[2023-10-12 07:12:41,272][78091] Updated weights for policy 0, policy_version 93310 (0.0009) -[2023-10-12 07:12:41,440][78123] Updated weights for policy 1, policy_version 92850 (0.0008) -[2023-10-12 07:12:41,806][78123] Updated weights for policy 1, policy_version 92860 (0.0010) -[2023-10-12 07:12:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 190644224. Throughput: 0: 1593.6, 1: 1572.8. Samples: 47669268. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-12 07:12:45,201][77203] Avg episode reward: [(0, '54.960'), (1, '41.770')] -[2023-10-12 07:12:45,586][78091] Updated weights for policy 0, policy_version 93320 (0.0009) -[2023-10-12 07:12:45,969][78091] Updated weights for policy 0, policy_version 93330 (0.0009) -[2023-10-12 07:12:46,159][78123] Updated weights for policy 1, policy_version 92870 (0.0008) -[2023-10-12 07:12:46,328][78091] Updated weights for policy 0, policy_version 93340 (0.0008) -[2023-10-12 07:12:46,519][78123] Updated weights for policy 1, policy_version 92880 (0.0008) -[2023-10-12 07:12:46,894][78123] Updated weights for policy 1, policy_version 92890 (0.0008) -[2023-10-12 07:12:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 190709760. Throughput: 0: 1587.2, 1: 1569.9. Samples: 47688768. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-12 07:12:50,203][77203] Avg episode reward: [(0, '60.120'), (1, '47.880')] -[2023-10-12 07:12:50,696][78091] Updated weights for policy 0, policy_version 93350 (0.0008) -[2023-10-12 07:12:51,059][78091] Updated weights for policy 0, policy_version 93360 (0.0009) -[2023-10-12 07:12:51,201][78123] Updated weights for policy 1, policy_version 92900 (0.0008) -[2023-10-12 07:12:51,425][78091] Updated weights for policy 0, policy_version 93370 (0.0008) -[2023-10-12 07:12:51,570][78123] Updated weights for policy 1, policy_version 92910 (0.0009) -[2023-10-12 07:12:51,930][78123] Updated weights for policy 1, policy_version 92920 (0.0008) -[2023-10-12 07:12:55,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 190775296. Throughput: 0: 1598.1, 1: 1582.8. Samples: 47708368. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-12 07:12:55,201][77203] Avg episode reward: [(0, '57.790'), (1, '51.070')] -[2023-10-12 07:12:55,900][78091] Updated weights for policy 0, policy_version 93380 (0.0009) -[2023-10-12 07:12:56,269][78091] Updated weights for policy 0, policy_version 93390 (0.0007) -[2023-10-12 07:12:56,284][78123] Updated weights for policy 1, policy_version 92930 (0.0008) -[2023-10-12 07:12:56,640][78091] Updated weights for policy 0, policy_version 93400 (0.0008) -[2023-10-12 07:12:56,659][78123] Updated weights for policy 1, policy_version 92940 (0.0008) -[2023-10-12 07:12:57,026][78123] Updated weights for policy 1, policy_version 92950 (0.0009) -[2023-10-12 07:12:57,395][78123] Updated weights for policy 1, policy_version 92960 (0.0010) -[2023-10-12 07:13:00,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 190840832. Throughput: 0: 1581.4, 1: 1576.2. Samples: 47716886. Policy #0 lag: (min: 20.0, avg: 31.2, max: 52.0) -[2023-10-12 07:13:00,202][77203] Avg episode reward: [(0, '55.300'), (1, '54.950')] -[2023-10-12 07:13:01,022][78091] Updated weights for policy 0, policy_version 93410 (0.0008) -[2023-10-12 07:13:01,415][78091] Updated weights for policy 0, policy_version 93420 (0.0009) -[2023-10-12 07:13:01,780][78091] Updated weights for policy 0, policy_version 93430 (0.0007) -[2023-10-12 07:13:01,902][78123] Updated weights for policy 1, policy_version 92970 (0.0008) -[2023-10-12 07:13:02,143][78091] Updated weights for policy 0, policy_version 93440 (0.0007) -[2023-10-12 07:13:02,271][78123] Updated weights for policy 1, policy_version 92980 (0.0011) -[2023-10-12 07:13:02,631][78123] Updated weights for policy 1, policy_version 92990 (0.0009) -[2023-10-12 07:13:05,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 190906368. Throughput: 0: 1586.8, 1: 1576.9. Samples: 47736126. Policy #0 lag: (min: 20.0, avg: 31.2, max: 52.0) -[2023-10-12 07:13:05,202][77203] Avg episode reward: [(0, '60.860'), (1, '52.810')] -[2023-10-12 07:13:06,460][78091] Updated weights for policy 0, policy_version 93450 (0.0007) -[2023-10-12 07:13:06,717][78123] Updated weights for policy 1, policy_version 93000 (0.0009) -[2023-10-12 07:13:06,826][78091] Updated weights for policy 0, policy_version 93460 (0.0007) -[2023-10-12 07:13:07,087][78123] Updated weights for policy 1, policy_version 93010 (0.0009) -[2023-10-12 07:13:07,198][78091] Updated weights for policy 0, policy_version 93470 (0.0007) -[2023-10-12 07:13:07,454][78123] Updated weights for policy 1, policy_version 93020 (0.0009) -[2023-10-12 07:13:10,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 190971904. Throughput: 0: 1585.4, 1: 1585.2. Samples: 47755684. Policy #0 lag: (min: 20.0, avg: 31.2, max: 52.0) -[2023-10-12 07:13:10,201][77203] Avg episode reward: [(0, '55.120'), (1, '51.630')] -[2023-10-12 07:13:10,210][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000093472_95715328.pth... -[2023-10-12 07:13:10,211][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000093024_95256576.pth... -[2023-10-12 07:13:10,247][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000091552_93749248.pth -[2023-10-12 07:13:10,248][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000092000_94208000.pth -[2023-10-12 07:13:11,475][78091] Updated weights for policy 0, policy_version 93480 (0.0007) -[2023-10-12 07:13:11,769][78123] Updated weights for policy 1, policy_version 93030 (0.0007) -[2023-10-12 07:13:11,851][78091] Updated weights for policy 0, policy_version 93490 (0.0008) -[2023-10-12 07:13:12,142][78123] Updated weights for policy 1, policy_version 93040 (0.0007) -[2023-10-12 07:13:12,226][78091] Updated weights for policy 0, policy_version 93500 (0.0007) -[2023-10-12 07:13:12,510][78123] Updated weights for policy 1, policy_version 93050 (0.0010) -[2023-10-12 07:13:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 191037440. Throughput: 0: 1581.4, 1: 1582.7. Samples: 47764204. Policy #0 lag: (min: 20.0, avg: 31.2, max: 52.0) -[2023-10-12 07:13:15,202][77203] Avg episode reward: [(0, '60.370'), (1, '52.940')] -[2023-10-12 07:13:16,510][78091] Updated weights for policy 0, policy_version 93510 (0.0008) -[2023-10-12 07:13:16,885][78091] Updated weights for policy 0, policy_version 93520 (0.0009) -[2023-10-12 07:13:16,947][78123] Updated weights for policy 1, policy_version 93060 (0.0008) -[2023-10-12 07:13:17,258][78091] Updated weights for policy 0, policy_version 93530 (0.0009) -[2023-10-12 07:13:17,318][78123] Updated weights for policy 1, policy_version 93070 (0.0008) -[2023-10-12 07:13:17,677][78123] Updated weights for policy 1, policy_version 93080 (0.0008) -[2023-10-12 07:13:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 191102976. Throughput: 0: 1578.2, 1: 1579.8. Samples: 47783408. Policy #0 lag: (min: 20.0, avg: 31.2, max: 52.0) -[2023-10-12 07:13:20,201][77203] Avg episode reward: [(0, '53.640'), (1, '55.670')] -[2023-10-12 07:13:21,547][78091] Updated weights for policy 0, policy_version 93540 (0.0008) -[2023-10-12 07:13:21,932][78091] Updated weights for policy 0, policy_version 93550 (0.0007) -[2023-10-12 07:13:22,043][78123] Updated weights for policy 1, policy_version 93090 (0.0010) -[2023-10-12 07:13:22,308][78091] Updated weights for policy 0, policy_version 93560 (0.0008) -[2023-10-12 07:13:22,410][78123] Updated weights for policy 1, policy_version 93100 (0.0008) -[2023-10-12 07:13:22,774][78123] Updated weights for policy 1, policy_version 93110 (0.0008) -[2023-10-12 07:13:23,147][78123] Updated weights for policy 1, policy_version 93120 (0.0007) -[2023-10-12 07:13:25,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 191168512. Throughput: 0: 1585.9, 1: 1574.5. Samples: 47802904. Policy #0 lag: (min: 20.0, avg: 31.2, max: 52.0) -[2023-10-12 07:13:25,201][77203] Avg episode reward: [(0, '53.530'), (1, '57.870')] -[2023-10-12 07:13:26,651][78091] Updated weights for policy 0, policy_version 93570 (0.0007) -[2023-10-12 07:13:27,024][78091] Updated weights for policy 0, policy_version 93580 (0.0008) -[2023-10-12 07:13:27,389][78091] Updated weights for policy 0, policy_version 93590 (0.0008) -[2023-10-12 07:13:27,544][78123] Updated weights for policy 1, policy_version 93130 (0.0008) -[2023-10-12 07:13:27,756][78091] Updated weights for policy 0, policy_version 93600 (0.0008) -[2023-10-12 07:13:27,916][78123] Updated weights for policy 1, policy_version 93140 (0.0008) -[2023-10-12 07:13:28,278][78123] Updated weights for policy 1, policy_version 93150 (0.0011) -[2023-10-12 07:13:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 191234048. Throughput: 0: 1585.8, 1: 1590.3. Samples: 47812194. Policy #0 lag: (min: 20.0, avg: 31.2, max: 52.0) -[2023-10-12 07:13:30,201][77203] Avg episode reward: [(0, '56.420'), (1, '57.360')] -[2023-10-12 07:13:32,152][78091] Updated weights for policy 0, policy_version 93610 (0.0007) -[2023-10-12 07:13:32,525][78091] Updated weights for policy 0, policy_version 93620 (0.0009) -[2023-10-12 07:13:32,596][78123] Updated weights for policy 1, policy_version 93160 (0.0009) -[2023-10-12 07:13:32,888][78091] Updated weights for policy 0, policy_version 93630 (0.0009) -[2023-10-12 07:13:32,961][78123] Updated weights for policy 1, policy_version 93170 (0.0009) -[2023-10-12 07:13:33,337][78123] Updated weights for policy 1, policy_version 93180 (0.0009) -[2023-10-12 07:13:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 191299584. Throughput: 0: 1586.3, 1: 1578.8. Samples: 47831200. Policy #0 lag: (min: 20.0, avg: 31.2, max: 52.0) -[2023-10-12 07:13:35,202][77203] Avg episode reward: [(0, '57.270'), (1, '61.200')] -[2023-10-12 07:13:37,116][78091] Updated weights for policy 0, policy_version 93640 (0.0007) -[2023-10-12 07:13:37,488][78091] Updated weights for policy 0, policy_version 93650 (0.0009) -[2023-10-12 07:13:37,733][78123] Updated weights for policy 1, policy_version 93190 (0.0009) -[2023-10-12 07:13:37,848][78091] Updated weights for policy 0, policy_version 93660 (0.0009) -[2023-10-12 07:13:38,095][78123] Updated weights for policy 1, policy_version 93200 (0.0008) -[2023-10-12 07:13:38,463][78123] Updated weights for policy 1, policy_version 93210 (0.0010) -[2023-10-12 07:13:40,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 191365120. Throughput: 0: 1586.5, 1: 1579.8. Samples: 47850852. Policy #0 lag: (min: 20.0, avg: 31.2, max: 52.0) -[2023-10-12 07:13:40,202][77203] Avg episode reward: [(0, '58.490'), (1, '62.750')] -[2023-10-12 07:13:42,204][78091] Updated weights for policy 0, policy_version 93670 (0.0008) -[2023-10-12 07:13:42,576][78091] Updated weights for policy 0, policy_version 93680 (0.0010) -[2023-10-12 07:13:42,675][78123] Updated weights for policy 1, policy_version 93220 (0.0009) -[2023-10-12 07:13:42,944][78091] Updated weights for policy 0, policy_version 93690 (0.0008) -[2023-10-12 07:13:43,037][78123] Updated weights for policy 1, policy_version 93230 (0.0007) -[2023-10-12 07:13:43,403][78123] Updated weights for policy 1, policy_version 93240 (0.0009) -[2023-10-12 07:13:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 191430656. Throughput: 0: 1596.8, 1: 1602.1. Samples: 47860834. Policy #0 lag: (min: 20.0, avg: 31.2, max: 52.0) -[2023-10-12 07:13:45,202][77203] Avg episode reward: [(0, '50.790'), (1, '57.100')] -[2023-10-12 07:13:47,333][78091] Updated weights for policy 0, policy_version 93700 (0.0008) -[2023-10-12 07:13:47,570][78123] Updated weights for policy 1, policy_version 93250 (0.0010) -[2023-10-12 07:13:47,698][78091] Updated weights for policy 0, policy_version 93710 (0.0009) -[2023-10-12 07:13:47,929][78123] Updated weights for policy 1, policy_version 93260 (0.0009) -[2023-10-12 07:13:48,066][78091] Updated weights for policy 0, policy_version 93720 (0.0008) -[2023-10-12 07:13:48,291][78123] Updated weights for policy 1, policy_version 93270 (0.0008) -[2023-10-12 07:13:48,654][78123] Updated weights for policy 1, policy_version 93280 (0.0009) -[2023-10-12 07:13:50,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 191496192. Throughput: 0: 1589.1, 1: 1585.3. Samples: 47878974. Policy #0 lag: (min: 20.0, avg: 31.2, max: 52.0) -[2023-10-12 07:13:50,202][77203] Avg episode reward: [(0, '54.090'), (1, '53.650')] -[2023-10-12 07:13:52,315][78091] Updated weights for policy 0, policy_version 93730 (0.0008) -[2023-10-12 07:13:52,692][78091] Updated weights for policy 0, policy_version 93740 (0.0007) -[2023-10-12 07:13:52,934][78123] Updated weights for policy 1, policy_version 93290 (0.0007) -[2023-10-12 07:13:53,067][78091] Updated weights for policy 0, policy_version 93750 (0.0007) -[2023-10-12 07:13:53,301][78123] Updated weights for policy 1, policy_version 93300 (0.0007) -[2023-10-12 07:13:53,427][78091] Updated weights for policy 0, policy_version 93760 (0.0007) -[2023-10-12 07:13:53,663][78123] Updated weights for policy 1, policy_version 93310 (0.0008) -[2023-10-12 07:13:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 191561728. Throughput: 0: 1596.7, 1: 1575.2. Samples: 47898422. Policy #0 lag: (min: 20.0, avg: 31.2, max: 52.0) -[2023-10-12 07:13:55,202][77203] Avg episode reward: [(0, '65.220'), (1, '52.450')] -[2023-10-12 07:13:57,756][78091] Updated weights for policy 0, policy_version 93770 (0.0008) -[2023-10-12 07:13:58,061][78123] Updated weights for policy 1, policy_version 93320 (0.0008) -[2023-10-12 07:13:58,118][78091] Updated weights for policy 0, policy_version 93780 (0.0007) -[2023-10-12 07:13:58,429][78123] Updated weights for policy 1, policy_version 93330 (0.0009) -[2023-10-12 07:13:58,483][78091] Updated weights for policy 0, policy_version 93790 (0.0007) -[2023-10-12 07:13:58,800][78123] Updated weights for policy 1, policy_version 93340 (0.0008) -[2023-10-12 07:14:00,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 191627264. Throughput: 0: 1614.1, 1: 1602.8. Samples: 47908968. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-12 07:14:00,202][77203] Avg episode reward: [(0, '59.270'), (1, '46.310')] -[2023-10-12 07:14:02,930][78091] Updated weights for policy 0, policy_version 93800 (0.0009) -[2023-10-12 07:14:03,151][78123] Updated weights for policy 1, policy_version 93350 (0.0008) -[2023-10-12 07:14:03,300][78091] Updated weights for policy 0, policy_version 93810 (0.0007) -[2023-10-12 07:14:03,525][78123] Updated weights for policy 1, policy_version 93360 (0.0008) -[2023-10-12 07:14:03,682][78091] Updated weights for policy 0, policy_version 93820 (0.0009) -[2023-10-12 07:14:03,885][78123] Updated weights for policy 1, policy_version 93370 (0.0008) -[2023-10-12 07:14:05,201][77203] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 191692800. Throughput: 0: 1595.5, 1: 1594.9. Samples: 47926978. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-12 07:14:05,202][77203] Avg episode reward: [(0, '54.740'), (1, '48.670')] -[2023-10-12 07:14:07,880][78091] Updated weights for policy 0, policy_version 93830 (0.0008) -[2023-10-12 07:14:08,251][78091] Updated weights for policy 0, policy_version 93840 (0.0009) -[2023-10-12 07:14:08,280][78123] Updated weights for policy 1, policy_version 93380 (0.0008) -[2023-10-12 07:14:08,631][78091] Updated weights for policy 0, policy_version 93850 (0.0009) -[2023-10-12 07:14:08,648][78123] Updated weights for policy 1, policy_version 93390 (0.0007) -[2023-10-12 07:14:09,011][78123] Updated weights for policy 1, policy_version 93400 (0.0008) -[2023-10-12 07:14:10,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 191758336. Throughput: 0: 1590.4, 1: 1587.0. Samples: 47945886. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-12 07:14:10,202][77203] Avg episode reward: [(0, '54.380'), (1, '49.290')] -[2023-10-12 07:14:12,933][78091] Updated weights for policy 0, policy_version 93860 (0.0009) -[2023-10-12 07:14:13,305][78091] Updated weights for policy 0, policy_version 93870 (0.0010) -[2023-10-12 07:14:13,455][78123] Updated weights for policy 1, policy_version 93410 (0.0010) -[2023-10-12 07:14:13,669][78091] Updated weights for policy 0, policy_version 93880 (0.0010) -[2023-10-12 07:14:13,822][78123] Updated weights for policy 1, policy_version 93420 (0.0007) -[2023-10-12 07:14:14,185][78123] Updated weights for policy 1, policy_version 93430 (0.0010) -[2023-10-12 07:14:14,547][78123] Updated weights for policy 1, policy_version 93440 (0.0010) -[2023-10-12 07:14:15,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 191823872. Throughput: 0: 1615.2, 1: 1602.3. Samples: 47956982. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-12 07:14:15,202][77203] Avg episode reward: [(0, '62.900'), (1, '52.990')] -[2023-10-12 07:14:18,068][78091] Updated weights for policy 0, policy_version 93890 (0.0009) -[2023-10-12 07:14:18,432][78091] Updated weights for policy 0, policy_version 93900 (0.0007) -[2023-10-12 07:14:18,804][78091] Updated weights for policy 0, policy_version 93910 (0.0007) -[2023-10-12 07:14:19,078][78123] Updated weights for policy 1, policy_version 93450 (0.0009) -[2023-10-12 07:14:19,163][78091] Updated weights for policy 0, policy_version 93920 (0.0007) -[2023-10-12 07:14:19,435][78123] Updated weights for policy 1, policy_version 93460 (0.0010) -[2023-10-12 07:14:19,811][78123] Updated weights for policy 1, policy_version 93470 (0.0010) -[2023-10-12 07:14:20,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 191889408. Throughput: 0: 1594.1, 1: 1611.8. Samples: 47975468. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-12 07:14:20,201][77203] Avg episode reward: [(0, '60.080'), (1, '48.220')] -[2023-10-12 07:14:23,443][78091] Updated weights for policy 0, policy_version 93930 (0.0007) -[2023-10-12 07:14:23,814][78091] Updated weights for policy 0, policy_version 93940 (0.0008) -[2023-10-12 07:14:24,105][78123] Updated weights for policy 1, policy_version 93480 (0.0008) -[2023-10-12 07:14:24,179][78091] Updated weights for policy 0, policy_version 93950 (0.0009) -[2023-10-12 07:14:24,468][78123] Updated weights for policy 1, policy_version 93490 (0.0011) -[2023-10-12 07:14:24,842][78123] Updated weights for policy 1, policy_version 93500 (0.0008) -[2023-10-12 07:14:25,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 191954944. Throughput: 0: 1587.8, 1: 1591.7. Samples: 47993932. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-12 07:14:25,201][77203] Avg episode reward: [(0, '57.260'), (1, '50.770')] -[2023-10-12 07:14:28,439][78091] Updated weights for policy 0, policy_version 93960 (0.0008) -[2023-10-12 07:14:28,815][78091] Updated weights for policy 0, policy_version 93970 (0.0010) -[2023-10-12 07:14:29,179][78091] Updated weights for policy 0, policy_version 93980 (0.0008) -[2023-10-12 07:14:29,217][78123] Updated weights for policy 1, policy_version 93510 (0.0007) -[2023-10-12 07:14:29,575][78123] Updated weights for policy 1, policy_version 93520 (0.0009) -[2023-10-12 07:14:29,943][78123] Updated weights for policy 1, policy_version 93530 (0.0008) -[2023-10-12 07:14:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 192020480. Throughput: 0: 1605.6, 1: 1588.9. Samples: 48004584. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-12 07:14:30,201][77203] Avg episode reward: [(0, '57.340'), (1, '54.050')] -[2023-10-12 07:14:33,579][78091] Updated weights for policy 0, policy_version 93990 (0.0009) -[2023-10-12 07:14:33,957][78091] Updated weights for policy 0, policy_version 94000 (0.0008) -[2023-10-12 07:14:34,324][78091] Updated weights for policy 0, policy_version 94010 (0.0009) -[2023-10-12 07:14:34,372][78123] Updated weights for policy 1, policy_version 93540 (0.0008) -[2023-10-12 07:14:34,746][78123] Updated weights for policy 1, policy_version 93550 (0.0009) -[2023-10-12 07:14:35,119][78123] Updated weights for policy 1, policy_version 93560 (0.0009) -[2023-10-12 07:14:35,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 192053248. Throughput: 0: 1602.1, 1: 1608.9. Samples: 48023472. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-12 07:14:35,201][77203] Avg episode reward: [(0, '49.750'), (1, '52.670')] -[2023-10-12 07:14:38,711][78091] Updated weights for policy 0, policy_version 94020 (0.0009) -[2023-10-12 07:14:39,069][78091] Updated weights for policy 0, policy_version 94030 (0.0011) -[2023-10-12 07:14:39,402][78123] Updated weights for policy 1, policy_version 93570 (0.0010) -[2023-10-12 07:14:39,438][78091] Updated weights for policy 0, policy_version 94040 (0.0008) -[2023-10-12 07:14:39,820][78123] Updated weights for policy 1, policy_version 93580 (0.0008) -[2023-10-12 07:14:40,200][78123] Updated weights for policy 1, policy_version 93590 (0.0008) -[2023-10-12 07:14:40,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 192118784. Throughput: 0: 1579.1, 1: 1604.8. Samples: 48041698. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-12 07:14:40,202][77203] Avg episode reward: [(0, '57.970'), (1, '53.940')] -[2023-10-12 07:14:40,563][78123] Updated weights for policy 1, policy_version 93600 (0.0008) -[2023-10-12 07:14:43,910][78091] Updated weights for policy 0, policy_version 94050 (0.0007) -[2023-10-12 07:14:44,286][78091] Updated weights for policy 0, policy_version 94060 (0.0008) -[2023-10-12 07:14:44,665][78091] Updated weights for policy 0, policy_version 94070 (0.0008) -[2023-10-12 07:14:44,673][78123] Updated weights for policy 1, policy_version 93610 (0.0008) -[2023-10-12 07:14:45,023][78091] Updated weights for policy 0, policy_version 94080 (0.0008) -[2023-10-12 07:14:45,043][78123] Updated weights for policy 1, policy_version 93620 (0.0009) -[2023-10-12 07:14:45,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 192184320. Throughput: 0: 1587.8, 1: 1587.2. Samples: 48051844. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-12 07:14:45,202][77203] Avg episode reward: [(0, '57.150'), (1, '55.200')] -[2023-10-12 07:14:45,419][78123] Updated weights for policy 1, policy_version 93630 (0.0008) -[2023-10-12 07:14:49,468][78091] Updated weights for policy 0, policy_version 94090 (0.0010) -[2023-10-12 07:14:49,833][78091] Updated weights for policy 0, policy_version 94100 (0.0008) -[2023-10-12 07:14:49,878][78123] Updated weights for policy 1, policy_version 93640 (0.0009) -[2023-10-12 07:14:50,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 192217088. Throughput: 0: 1604.6, 1: 1599.9. Samples: 48071178. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-12 07:14:50,202][77203] Avg episode reward: [(0, '54.740'), (1, '55.110')] -[2023-10-12 07:14:50,203][78091] Updated weights for policy 0, policy_version 94110 (0.0008) -[2023-10-12 07:14:50,241][78123] Updated weights for policy 1, policy_version 93650 (0.0007) -[2023-10-12 07:14:50,608][78123] Updated weights for policy 1, policy_version 93660 (0.0009) -[2023-10-12 07:14:54,341][78091] Updated weights for policy 0, policy_version 94120 (0.0007) -[2023-10-12 07:14:54,621][78123] Updated weights for policy 1, policy_version 93670 (0.0008) -[2023-10-12 07:14:54,708][78091] Updated weights for policy 0, policy_version 94130 (0.0008) -[2023-10-12 07:14:54,982][78123] Updated weights for policy 1, policy_version 93680 (0.0007) -[2023-10-12 07:14:55,078][78091] Updated weights for policy 0, policy_version 94140 (0.0008) -[2023-10-12 07:14:55,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 192282624. Throughput: 0: 1591.5, 1: 1608.0. Samples: 48089864. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-12 07:14:55,201][77203] Avg episode reward: [(0, '54.620'), (1, '56.980')] -[2023-10-12 07:14:55,343][78123] Updated weights for policy 1, policy_version 93690 (0.0010) -[2023-10-12 07:14:59,461][78091] Updated weights for policy 0, policy_version 94150 (0.0007) -[2023-10-12 07:14:59,768][78123] Updated weights for policy 1, policy_version 93700 (0.0010) -[2023-10-12 07:14:59,823][78091] Updated weights for policy 0, policy_version 94160 (0.0008) -[2023-10-12 07:15:00,131][78123] Updated weights for policy 1, policy_version 93710 (0.0009) -[2023-10-12 07:15:00,201][77203] Fps is (10 sec: 13107.6, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 192348160. Throughput: 0: 1579.7, 1: 1586.5. Samples: 48099456. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-12 07:15:00,201][77203] Avg episode reward: [(0, '60.360'), (1, '54.530')] -[2023-10-12 07:15:00,204][78091] Updated weights for policy 0, policy_version 94170 (0.0008) -[2023-10-12 07:15:00,494][78123] Updated weights for policy 1, policy_version 93720 (0.0010) -[2023-10-12 07:15:04,469][78091] Updated weights for policy 0, policy_version 94180 (0.0008) -[2023-10-12 07:15:04,847][78091] Updated weights for policy 0, policy_version 94190 (0.0009) -[2023-10-12 07:15:04,984][78123] Updated weights for policy 1, policy_version 93730 (0.0008) -[2023-10-12 07:15:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 192413696. Throughput: 0: 1606.9, 1: 1586.3. Samples: 48119162. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-12 07:15:05,201][77203] Avg episode reward: [(0, '57.430'), (1, '47.830')] -[2023-10-12 07:15:05,215][78091] Updated weights for policy 0, policy_version 94200 (0.0008) -[2023-10-12 07:15:05,352][78123] Updated weights for policy 1, policy_version 93740 (0.0008) -[2023-10-12 07:15:05,714][78123] Updated weights for policy 1, policy_version 93750 (0.0008) -[2023-10-12 07:15:06,079][78123] Updated weights for policy 1, policy_version 93760 (0.0010) -[2023-10-12 07:15:09,424][78091] Updated weights for policy 0, policy_version 94210 (0.0009) -[2023-10-12 07:15:09,790][78091] Updated weights for policy 0, policy_version 94220 (0.0009) -[2023-10-12 07:15:10,165][78091] Updated weights for policy 0, policy_version 94230 (0.0009) -[2023-10-12 07:15:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 192479232. Throughput: 0: 1605.1, 1: 1604.2. Samples: 48138348. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-12 07:15:10,201][77203] Avg episode reward: [(0, '57.930'), (1, '55.800')] -[2023-10-12 07:15:10,317][78123] Updated weights for policy 1, policy_version 93770 (0.0007) -[2023-10-12 07:15:10,519][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000094240_96501760.pth... -[2023-10-12 07:15:10,521][78091] Updated weights for policy 0, policy_version 94240 (0.0009) -[2023-10-12 07:15:10,549][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000092736_94961664.pth -[2023-10-12 07:15:10,678][78123] Updated weights for policy 1, policy_version 93780 (0.0009) -[2023-10-12 07:15:11,043][78123] Updated weights for policy 1, policy_version 93790 (0.0007) -[2023-10-12 07:15:11,116][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000093792_96043008.pth... -[2023-10-12 07:15:11,156][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000092288_94502912.pth -[2023-10-12 07:15:14,734][78091] Updated weights for policy 0, policy_version 94250 (0.0007) -[2023-10-12 07:15:15,102][78091] Updated weights for policy 0, policy_version 94260 (0.0009) -[2023-10-12 07:15:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12015.0, 300 sec: 12662.9). Total num frames: 192544768. Throughput: 0: 1590.4, 1: 1587.5. Samples: 48147588. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-12 07:15:15,201][77203] Avg episode reward: [(0, '52.690'), (1, '49.040')] -[2023-10-12 07:15:15,368][78123] Updated weights for policy 1, policy_version 93800 (0.0008) -[2023-10-12 07:15:15,472][78091] Updated weights for policy 0, policy_version 94270 (0.0008) -[2023-10-12 07:15:15,737][78123] Updated weights for policy 1, policy_version 93810 (0.0009) -[2023-10-12 07:15:16,107][78123] Updated weights for policy 1, policy_version 93820 (0.0009) -[2023-10-12 07:15:19,939][78091] Updated weights for policy 0, policy_version 94280 (0.0010) -[2023-10-12 07:15:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 192610304. Throughput: 0: 1603.6, 1: 1585.1. Samples: 48166962. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-12 07:15:20,201][77203] Avg episode reward: [(0, '60.960'), (1, '51.520')] -[2023-10-12 07:15:20,316][78091] Updated weights for policy 0, policy_version 94290 (0.0009) -[2023-10-12 07:15:20,571][78123] Updated weights for policy 1, policy_version 93830 (0.0008) -[2023-10-12 07:15:20,690][78091] Updated weights for policy 0, policy_version 94300 (0.0008) -[2023-10-12 07:15:20,933][78123] Updated weights for policy 1, policy_version 93840 (0.0008) -[2023-10-12 07:15:21,305][78123] Updated weights for policy 1, policy_version 93850 (0.0009) -[2023-10-12 07:15:24,738][78091] Updated weights for policy 0, policy_version 94310 (0.0008) -[2023-10-12 07:15:25,109][78091] Updated weights for policy 0, policy_version 94320 (0.0007) -[2023-10-12 07:15:25,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 192675840. Throughput: 0: 1622.8, 1: 1594.1. Samples: 48186460. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-12 07:15:25,201][77203] Avg episode reward: [(0, '55.180'), (1, '46.760')] -[2023-10-12 07:15:25,467][78091] Updated weights for policy 0, policy_version 94330 (0.0008) -[2023-10-12 07:15:25,732][78123] Updated weights for policy 1, policy_version 93860 (0.0009) -[2023-10-12 07:15:26,117][78123] Updated weights for policy 1, policy_version 93870 (0.0009) -[2023-10-12 07:15:26,492][78123] Updated weights for policy 1, policy_version 93880 (0.0009) -[2023-10-12 07:15:29,763][78091] Updated weights for policy 0, policy_version 94340 (0.0008) -[2023-10-12 07:15:30,136][78091] Updated weights for policy 0, policy_version 94350 (0.0008) -[2023-10-12 07:15:30,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 192741376. Throughput: 0: 1603.5, 1: 1583.0. Samples: 48195236. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-12 07:15:30,202][77203] Avg episode reward: [(0, '58.010'), (1, '48.140')] -[2023-10-12 07:15:30,499][78091] Updated weights for policy 0, policy_version 94360 (0.0007) -[2023-10-12 07:15:30,776][78123] Updated weights for policy 1, policy_version 93890 (0.0008) -[2023-10-12 07:15:31,143][78123] Updated weights for policy 1, policy_version 93900 (0.0008) -[2023-10-12 07:15:31,510][78123] Updated weights for policy 1, policy_version 93910 (0.0007) -[2023-10-12 07:15:31,865][78123] Updated weights for policy 1, policy_version 93920 (0.0009) -[2023-10-12 07:15:34,831][78091] Updated weights for policy 0, policy_version 94370 (0.0010) -[2023-10-12 07:15:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 192806912. Throughput: 0: 1607.2, 1: 1587.3. Samples: 48214930. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-12 07:15:35,201][77203] Avg episode reward: [(0, '57.410'), (1, '42.300')] -[2023-10-12 07:15:35,209][78091] Updated weights for policy 0, policy_version 94380 (0.0009) -[2023-10-12 07:15:35,585][78091] Updated weights for policy 0, policy_version 94390 (0.0009) -[2023-10-12 07:15:35,956][78091] Updated weights for policy 0, policy_version 94400 (0.0008) -[2023-10-12 07:15:36,393][78123] Updated weights for policy 1, policy_version 93930 (0.0009) -[2023-10-12 07:15:36,759][78123] Updated weights for policy 1, policy_version 93940 (0.0010) -[2023-10-12 07:15:37,125][78123] Updated weights for policy 1, policy_version 93950 (0.0007) -[2023-10-12 07:15:40,137][78091] Updated weights for policy 0, policy_version 94410 (0.0008) -[2023-10-12 07:15:40,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 192872448. Throughput: 0: 1620.2, 1: 1590.0. Samples: 48234322. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-12 07:15:40,201][77203] Avg episode reward: [(0, '54.050'), (1, '46.920')] -[2023-10-12 07:15:40,497][78091] Updated weights for policy 0, policy_version 94420 (0.0010) -[2023-10-12 07:15:40,866][78091] Updated weights for policy 0, policy_version 94430 (0.0008) -[2023-10-12 07:15:41,493][78123] Updated weights for policy 1, policy_version 93960 (0.0010) -[2023-10-12 07:15:41,856][78123] Updated weights for policy 1, policy_version 93970 (0.0011) -[2023-10-12 07:15:42,219][78123] Updated weights for policy 1, policy_version 93980 (0.0011) -[2023-10-12 07:15:45,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 192937984. Throughput: 0: 1608.3, 1: 1580.4. Samples: 48242946. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-12 07:15:45,201][77203] Avg episode reward: [(0, '56.960'), (1, '50.760')] -[2023-10-12 07:15:45,327][78091] Updated weights for policy 0, policy_version 94440 (0.0009) -[2023-10-12 07:15:45,708][78091] Updated weights for policy 0, policy_version 94450 (0.0010) -[2023-10-12 07:15:46,086][78091] Updated weights for policy 0, policy_version 94460 (0.0009) -[2023-10-12 07:15:46,522][78123] Updated weights for policy 1, policy_version 93990 (0.0009) -[2023-10-12 07:15:46,879][78123] Updated weights for policy 1, policy_version 94000 (0.0008) -[2023-10-12 07:15:47,260][78123] Updated weights for policy 1, policy_version 94010 (0.0009) -[2023-10-12 07:15:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 193003520. Throughput: 0: 1595.3, 1: 1585.4. Samples: 48262294. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-12 07:15:50,202][77203] Avg episode reward: [(0, '54.470'), (1, '48.950')] -[2023-10-12 07:15:50,400][78091] Updated weights for policy 0, policy_version 94470 (0.0008) -[2023-10-12 07:15:50,768][78091] Updated weights for policy 0, policy_version 94480 (0.0009) -[2023-10-12 07:15:51,145][78091] Updated weights for policy 0, policy_version 94490 (0.0007) -[2023-10-12 07:15:51,439][78123] Updated weights for policy 1, policy_version 94020 (0.0009) -[2023-10-12 07:15:51,800][78123] Updated weights for policy 1, policy_version 94030 (0.0008) -[2023-10-12 07:15:52,159][78123] Updated weights for policy 1, policy_version 94040 (0.0009) -[2023-10-12 07:15:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 193069056. Throughput: 0: 1601.9, 1: 1588.7. Samples: 48281924. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-12 07:15:55,201][77203] Avg episode reward: [(0, '53.500'), (1, '45.550')] -[2023-10-12 07:15:55,509][78091] Updated weights for policy 0, policy_version 94500 (0.0007) -[2023-10-12 07:15:55,870][78091] Updated weights for policy 0, policy_version 94510 (0.0009) -[2023-10-12 07:15:56,212][78123] Updated weights for policy 1, policy_version 94050 (0.0008) -[2023-10-12 07:15:56,232][78091] Updated weights for policy 0, policy_version 94520 (0.0009) -[2023-10-12 07:15:56,583][78123] Updated weights for policy 1, policy_version 94060 (0.0009) -[2023-10-12 07:15:56,942][78123] Updated weights for policy 1, policy_version 94070 (0.0008) -[2023-10-12 07:15:57,297][78123] Updated weights for policy 1, policy_version 94080 (0.0008) -[2023-10-12 07:16:00,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 193134592. Throughput: 0: 1588.2, 1: 1589.9. Samples: 48290604. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-12 07:16:00,201][77203] Avg episode reward: [(0, '60.470'), (1, '42.960')] -[2023-10-12 07:16:00,665][78091] Updated weights for policy 0, policy_version 94530 (0.0007) -[2023-10-12 07:16:01,032][78091] Updated weights for policy 0, policy_version 94540 (0.0008) -[2023-10-12 07:16:01,401][78091] Updated weights for policy 0, policy_version 94550 (0.0007) -[2023-10-12 07:16:01,701][78123] Updated weights for policy 1, policy_version 94090 (0.0009) -[2023-10-12 07:16:01,767][78091] Updated weights for policy 0, policy_version 94560 (0.0007) -[2023-10-12 07:16:02,055][78123] Updated weights for policy 1, policy_version 94100 (0.0010) -[2023-10-12 07:16:02,427][78123] Updated weights for policy 1, policy_version 94110 (0.0009) -[2023-10-12 07:16:05,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.1, 300 sec: 12662.9). Total num frames: 193200128. Throughput: 0: 1587.7, 1: 1593.1. Samples: 48310098. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-12 07:16:05,202][77203] Avg episode reward: [(0, '60.000'), (1, '49.720')] -[2023-10-12 07:16:06,244][78091] Updated weights for policy 0, policy_version 94570 (0.0009) -[2023-10-12 07:16:06,613][78091] Updated weights for policy 0, policy_version 94580 (0.0009) -[2023-10-12 07:16:06,651][78123] Updated weights for policy 1, policy_version 94120 (0.0008) -[2023-10-12 07:16:06,989][78091] Updated weights for policy 0, policy_version 94590 (0.0007) -[2023-10-12 07:16:07,032][78123] Updated weights for policy 1, policy_version 94130 (0.0008) -[2023-10-12 07:16:07,397][78123] Updated weights for policy 1, policy_version 94140 (0.0009) -[2023-10-12 07:16:10,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 12662.9). Total num frames: 193265664. Throughput: 0: 1587.7, 1: 1592.1. Samples: 48329550. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-12 07:16:10,202][77203] Avg episode reward: [(0, '58.480'), (1, '52.020')] -[2023-10-12 07:16:11,116][78091] Updated weights for policy 0, policy_version 94600 (0.0010) -[2023-10-12 07:16:11,486][78091] Updated weights for policy 0, policy_version 94610 (0.0011) -[2023-10-12 07:16:11,858][78091] Updated weights for policy 0, policy_version 94620 (0.0008) -[2023-10-12 07:16:11,918][78123] Updated weights for policy 1, policy_version 94150 (0.0007) -[2023-10-12 07:16:12,297][78123] Updated weights for policy 1, policy_version 94160 (0.0010) -[2023-10-12 07:16:12,665][78123] Updated weights for policy 1, policy_version 94170 (0.0010) -[2023-10-12 07:16:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 193331200. Throughput: 0: 1581.1, 1: 1597.3. Samples: 48338266. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-12 07:16:15,202][77203] Avg episode reward: [(0, '59.520'), (1, '52.230')] -[2023-10-12 07:16:16,306][78091] Updated weights for policy 0, policy_version 94630 (0.0007) -[2023-10-12 07:16:16,676][78091] Updated weights for policy 0, policy_version 94640 (0.0008) -[2023-10-12 07:16:17,049][78091] Updated weights for policy 0, policy_version 94650 (0.0009) -[2023-10-12 07:16:17,062][78123] Updated weights for policy 1, policy_version 94180 (0.0010) -[2023-10-12 07:16:17,422][78123] Updated weights for policy 1, policy_version 94190 (0.0008) -[2023-10-12 07:16:17,794][78123] Updated weights for policy 1, policy_version 94200 (0.0008) -[2023-10-12 07:16:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 193396736. Throughput: 0: 1574.4, 1: 1591.0. Samples: 48357376. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-12 07:16:20,202][77203] Avg episode reward: [(0, '51.800'), (1, '47.050')] -[2023-10-12 07:16:21,410][78091] Updated weights for policy 0, policy_version 94660 (0.0009) -[2023-10-12 07:16:21,775][78091] Updated weights for policy 0, policy_version 94670 (0.0008) -[2023-10-12 07:16:22,060][78123] Updated weights for policy 1, policy_version 94210 (0.0009) -[2023-10-12 07:16:22,147][78091] Updated weights for policy 0, policy_version 94680 (0.0008) -[2023-10-12 07:16:22,420][78123] Updated weights for policy 1, policy_version 94220 (0.0008) -[2023-10-12 07:16:22,785][78123] Updated weights for policy 1, policy_version 94230 (0.0010) -[2023-10-12 07:16:23,149][78123] Updated weights for policy 1, policy_version 94240 (0.0011) -[2023-10-12 07:16:25,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 193462272. Throughput: 0: 1577.7, 1: 1593.4. Samples: 48377022. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-12 07:16:25,202][77203] Avg episode reward: [(0, '60.940'), (1, '42.430')] -[2023-10-12 07:16:26,382][78091] Updated weights for policy 0, policy_version 94690 (0.0009) -[2023-10-12 07:16:26,753][78091] Updated weights for policy 0, policy_version 94700 (0.0009) -[2023-10-12 07:16:27,125][78091] Updated weights for policy 0, policy_version 94710 (0.0007) -[2023-10-12 07:16:27,336][78123] Updated weights for policy 1, policy_version 94250 (0.0009) -[2023-10-12 07:16:27,487][78091] Updated weights for policy 0, policy_version 94720 (0.0007) -[2023-10-12 07:16:27,704][78123] Updated weights for policy 1, policy_version 94260 (0.0010) -[2023-10-12 07:16:28,077][78123] Updated weights for policy 1, policy_version 94270 (0.0009) -[2023-10-12 07:16:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 193527808. Throughput: 0: 1577.5, 1: 1607.0. Samples: 48386250. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-12 07:16:30,202][77203] Avg episode reward: [(0, '54.570'), (1, '47.370')] -[2023-10-12 07:16:31,781][78091] Updated weights for policy 0, policy_version 94730 (0.0007) -[2023-10-12 07:16:32,150][78091] Updated weights for policy 0, policy_version 94740 (0.0008) -[2023-10-12 07:16:32,435][78123] Updated weights for policy 1, policy_version 94280 (0.0010) -[2023-10-12 07:16:32,514][78091] Updated weights for policy 0, policy_version 94750 (0.0009) -[2023-10-12 07:16:32,800][78123] Updated weights for policy 1, policy_version 94290 (0.0010) -[2023-10-12 07:16:33,164][78123] Updated weights for policy 1, policy_version 94300 (0.0009) -[2023-10-12 07:16:35,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12662.9). Total num frames: 193593344. Throughput: 0: 1587.7, 1: 1591.9. Samples: 48405376. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-12 07:16:35,201][77203] Avg episode reward: [(0, '54.160'), (1, '43.050')] -[2023-10-12 07:16:37,005][78091] Updated weights for policy 0, policy_version 94760 (0.0009) -[2023-10-12 07:16:37,375][78091] Updated weights for policy 0, policy_version 94770 (0.0009) -[2023-10-12 07:16:37,489][78123] Updated weights for policy 1, policy_version 94310 (0.0009) -[2023-10-12 07:16:37,748][78091] Updated weights for policy 0, policy_version 94780 (0.0009) -[2023-10-12 07:16:37,869][78123] Updated weights for policy 1, policy_version 94320 (0.0007) -[2023-10-12 07:16:38,244][78123] Updated weights for policy 1, policy_version 94330 (0.0010) -[2023-10-12 07:16:40,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 193658880. Throughput: 0: 1584.6, 1: 1587.6. Samples: 48424676. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-12 07:16:40,202][77203] Avg episode reward: [(0, '57.850'), (1, '47.890')] -[2023-10-12 07:16:42,006][78091] Updated weights for policy 0, policy_version 94790 (0.0010) -[2023-10-12 07:16:42,367][78091] Updated weights for policy 0, policy_version 94800 (0.0007) -[2023-10-12 07:16:42,377][78123] Updated weights for policy 1, policy_version 94340 (0.0010) -[2023-10-12 07:16:42,733][78091] Updated weights for policy 0, policy_version 94810 (0.0007) -[2023-10-12 07:16:42,743][78123] Updated weights for policy 1, policy_version 94350 (0.0008) -[2023-10-12 07:16:43,115][78123] Updated weights for policy 1, policy_version 94360 (0.0010) -[2023-10-12 07:16:45,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 193724416. Throughput: 0: 1590.7, 1: 1603.5. Samples: 48434342. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-12 07:16:45,201][77203] Avg episode reward: [(0, '58.800'), (1, '55.360')] -[2023-10-12 07:16:47,012][78091] Updated weights for policy 0, policy_version 94820 (0.0007) -[2023-10-12 07:16:47,381][78091] Updated weights for policy 0, policy_version 94830 (0.0008) -[2023-10-12 07:16:47,708][78123] Updated weights for policy 1, policy_version 94370 (0.0010) -[2023-10-12 07:16:47,748][78091] Updated weights for policy 0, policy_version 94840 (0.0007) -[2023-10-12 07:16:48,076][78123] Updated weights for policy 1, policy_version 94380 (0.0008) -[2023-10-12 07:16:48,442][78123] Updated weights for policy 1, policy_version 94390 (0.0007) -[2023-10-12 07:16:48,805][78123] Updated weights for policy 1, policy_version 94400 (0.0008) -[2023-10-12 07:16:50,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 193789952. Throughput: 0: 1589.5, 1: 1588.9. Samples: 48453126. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-12 07:16:50,202][77203] Avg episode reward: [(0, '58.300'), (1, '53.210')] -[2023-10-12 07:16:52,217][78091] Updated weights for policy 0, policy_version 94850 (0.0008) -[2023-10-12 07:16:52,596][78091] Updated weights for policy 0, policy_version 94860 (0.0009) -[2023-10-12 07:16:52,971][78091] Updated weights for policy 0, policy_version 94870 (0.0010) -[2023-10-12 07:16:53,065][78123] Updated weights for policy 1, policy_version 94410 (0.0007) -[2023-10-12 07:16:53,336][78091] Updated weights for policy 0, policy_version 94880 (0.0008) -[2023-10-12 07:16:53,435][78123] Updated weights for policy 1, policy_version 94420 (0.0007) -[2023-10-12 07:16:53,800][78123] Updated weights for policy 1, policy_version 94430 (0.0007) -[2023-10-12 07:16:55,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 193855488. Throughput: 0: 1588.9, 1: 1582.1. Samples: 48472246. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-12 07:16:55,202][77203] Avg episode reward: [(0, '59.740'), (1, '50.780')] -[2023-10-12 07:16:57,499][78091] Updated weights for policy 0, policy_version 94890 (0.0009) -[2023-10-12 07:16:57,873][78091] Updated weights for policy 0, policy_version 94900 (0.0009) -[2023-10-12 07:16:58,240][78091] Updated weights for policy 0, policy_version 94910 (0.0008) -[2023-10-12 07:16:58,316][78123] Updated weights for policy 1, policy_version 94440 (0.0010) -[2023-10-12 07:16:58,680][78123] Updated weights for policy 1, policy_version 94450 (0.0011) -[2023-10-12 07:16:59,046][78123] Updated weights for policy 1, policy_version 94460 (0.0009) -[2023-10-12 07:17:00,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 193921024. Throughput: 0: 1602.1, 1: 1602.7. Samples: 48482478. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-12 07:17:00,201][77203] Avg episode reward: [(0, '59.250'), (1, '52.180')] -[2023-10-12 07:17:02,362][78091] Updated weights for policy 0, policy_version 94920 (0.0009) -[2023-10-12 07:17:02,738][78091] Updated weights for policy 0, policy_version 94930 (0.0008) -[2023-10-12 07:17:03,112][78091] Updated weights for policy 0, policy_version 94940 (0.0008) -[2023-10-12 07:17:03,286][78123] Updated weights for policy 1, policy_version 94470 (0.0007) -[2023-10-12 07:17:03,650][78123] Updated weights for policy 1, policy_version 94480 (0.0007) -[2023-10-12 07:17:04,009][78123] Updated weights for policy 1, policy_version 94490 (0.0008) -[2023-10-12 07:17:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 193986560. Throughput: 0: 1598.8, 1: 1588.5. Samples: 48500804. Policy #0 lag: (min: 22.0, avg: 22.6, max: 38.0) -[2023-10-12 07:17:05,202][77203] Avg episode reward: [(0, '61.090'), (1, '58.900')] -[2023-10-12 07:17:07,370][78091] Updated weights for policy 0, policy_version 94950 (0.0009) -[2023-10-12 07:17:07,735][78091] Updated weights for policy 0, policy_version 94960 (0.0009) -[2023-10-12 07:17:08,103][78091] Updated weights for policy 0, policy_version 94970 (0.0007) -[2023-10-12 07:17:08,380][78123] Updated weights for policy 1, policy_version 94500 (0.0008) -[2023-10-12 07:17:08,759][78123] Updated weights for policy 1, policy_version 94510 (0.0010) -[2023-10-12 07:17:09,123][78123] Updated weights for policy 1, policy_version 94520 (0.0009) -[2023-10-12 07:17:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 194052096. Throughput: 0: 1597.3, 1: 1578.8. Samples: 48519946. Policy #0 lag: (min: 22.0, avg: 22.6, max: 38.0) -[2023-10-12 07:17:10,201][77203] Avg episode reward: [(0, '52.420'), (1, '54.870')] -[2023-10-12 07:17:10,211][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000094528_96796672.pth... -[2023-10-12 07:17:10,211][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000094976_97255424.pth... -[2023-10-12 07:17:10,244][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000093024_95256576.pth -[2023-10-12 07:17:10,253][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000093472_95715328.pth -[2023-10-12 07:17:12,327][78091] Updated weights for policy 0, policy_version 94980 (0.0008) -[2023-10-12 07:17:12,703][78091] Updated weights for policy 0, policy_version 94990 (0.0008) -[2023-10-12 07:17:13,068][78091] Updated weights for policy 0, policy_version 95000 (0.0008) -[2023-10-12 07:17:13,502][78123] Updated weights for policy 1, policy_version 94530 (0.0009) -[2023-10-12 07:17:13,867][78123] Updated weights for policy 1, policy_version 94540 (0.0010) -[2023-10-12 07:17:14,240][78123] Updated weights for policy 1, policy_version 94550 (0.0010) -[2023-10-12 07:17:14,604][78123] Updated weights for policy 1, policy_version 94560 (0.0009) -[2023-10-12 07:17:15,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 194117632. Throughput: 0: 1610.3, 1: 1590.5. Samples: 48530286. Policy #0 lag: (min: 22.0, avg: 22.6, max: 38.0) -[2023-10-12 07:17:15,201][77203] Avg episode reward: [(0, '57.180'), (1, '52.820')] -[2023-10-12 07:17:17,385][78091] Updated weights for policy 0, policy_version 95010 (0.0008) -[2023-10-12 07:17:17,761][78091] Updated weights for policy 0, policy_version 95020 (0.0010) -[2023-10-12 07:17:18,133][78091] Updated weights for policy 0, policy_version 95030 (0.0007) -[2023-10-12 07:17:18,511][78091] Updated weights for policy 0, policy_version 95040 (0.0008) -[2023-10-12 07:17:19,025][78123] Updated weights for policy 1, policy_version 94570 (0.0009) -[2023-10-12 07:17:19,402][78123] Updated weights for policy 1, policy_version 94580 (0.0008) -[2023-10-12 07:17:19,764][78123] Updated weights for policy 1, policy_version 94590 (0.0007) -[2023-10-12 07:17:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 194183168. Throughput: 0: 1590.8, 1: 1604.2. Samples: 48549148. Policy #0 lag: (min: 22.0, avg: 22.6, max: 38.0) -[2023-10-12 07:17:20,201][77203] Avg episode reward: [(0, '57.500'), (1, '52.960')] -[2023-10-12 07:17:22,937][78091] Updated weights for policy 0, policy_version 95050 (0.0011) -[2023-10-12 07:17:23,305][78091] Updated weights for policy 0, policy_version 95060 (0.0010) -[2023-10-12 07:17:23,682][78091] Updated weights for policy 0, policy_version 95070 (0.0007) -[2023-10-12 07:17:24,101][78123] Updated weights for policy 1, policy_version 94600 (0.0008) -[2023-10-12 07:17:24,468][78123] Updated weights for policy 1, policy_version 94610 (0.0009) -[2023-10-12 07:17:24,850][78123] Updated weights for policy 1, policy_version 94620 (0.0010) -[2023-10-12 07:17:25,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 194248704. Throughput: 0: 1594.6, 1: 1589.6. Samples: 48567966. Policy #0 lag: (min: 22.0, avg: 22.6, max: 38.0) -[2023-10-12 07:17:25,201][77203] Avg episode reward: [(0, '55.450'), (1, '46.160')] -[2023-10-12 07:17:28,120][78091] Updated weights for policy 0, policy_version 95080 (0.0008) -[2023-10-12 07:17:28,489][78091] Updated weights for policy 0, policy_version 95090 (0.0008) -[2023-10-12 07:17:28,855][78091] Updated weights for policy 0, policy_version 95100 (0.0009) -[2023-10-12 07:17:29,303][78123] Updated weights for policy 1, policy_version 94630 (0.0008) -[2023-10-12 07:17:29,677][78123] Updated weights for policy 1, policy_version 94640 (0.0009) -[2023-10-12 07:17:30,048][78123] Updated weights for policy 1, policy_version 94650 (0.0009) -[2023-10-12 07:17:30,201][77203] Fps is (10 sec: 9830.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 194281472. Throughput: 0: 1615.7, 1: 1588.8. Samples: 48578544. Policy #0 lag: (min: 22.0, avg: 22.6, max: 38.0) -[2023-10-12 07:17:30,202][77203] Avg episode reward: [(0, '55.010'), (1, '46.370')] -[2023-10-12 07:17:33,157][78091] Updated weights for policy 0, policy_version 95110 (0.0009) -[2023-10-12 07:17:33,531][78091] Updated weights for policy 0, policy_version 95120 (0.0009) -[2023-10-12 07:17:33,904][78091] Updated weights for policy 0, policy_version 95130 (0.0007) -[2023-10-12 07:17:34,359][78123] Updated weights for policy 1, policy_version 94660 (0.0010) -[2023-10-12 07:17:34,716][78123] Updated weights for policy 1, policy_version 94670 (0.0009) -[2023-10-12 07:17:35,095][78123] Updated weights for policy 1, policy_version 94680 (0.0009) -[2023-10-12 07:17:35,201][77203] Fps is (10 sec: 9830.2, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 194347008. Throughput: 0: 1597.8, 1: 1607.3. Samples: 48597356. Policy #0 lag: (min: 22.0, avg: 22.6, max: 38.0) -[2023-10-12 07:17:35,202][77203] Avg episode reward: [(0, '51.310'), (1, '50.770')] -[2023-10-12 07:17:38,205][78091] Updated weights for policy 0, policy_version 95140 (0.0010) -[2023-10-12 07:17:38,578][78091] Updated weights for policy 0, policy_version 95150 (0.0009) -[2023-10-12 07:17:38,945][78091] Updated weights for policy 0, policy_version 95160 (0.0010) -[2023-10-12 07:17:39,366][78123] Updated weights for policy 1, policy_version 94690 (0.0010) -[2023-10-12 07:17:39,738][78123] Updated weights for policy 1, policy_version 94700 (0.0008) -[2023-10-12 07:17:40,105][78123] Updated weights for policy 1, policy_version 94710 (0.0007) -[2023-10-12 07:17:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 194412544. Throughput: 0: 1592.5, 1: 1602.5. Samples: 48616020. Policy #0 lag: (min: 22.0, avg: 22.6, max: 38.0) -[2023-10-12 07:17:40,202][77203] Avg episode reward: [(0, '56.490'), (1, '45.330')] -[2023-10-12 07:17:40,475][78123] Updated weights for policy 1, policy_version 94720 (0.0009) -[2023-10-12 07:17:43,160][78091] Updated weights for policy 0, policy_version 95170 (0.0009) -[2023-10-12 07:17:43,533][78091] Updated weights for policy 0, policy_version 95180 (0.0009) -[2023-10-12 07:17:43,898][78091] Updated weights for policy 0, policy_version 95190 (0.0010) -[2023-10-12 07:17:44,275][78091] Updated weights for policy 0, policy_version 95200 (0.0007) -[2023-10-12 07:17:44,882][78123] Updated weights for policy 1, policy_version 94730 (0.0011) -[2023-10-12 07:17:45,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 194478080. Throughput: 0: 1609.0, 1: 1590.0. Samples: 48626432. Policy #0 lag: (min: 22.0, avg: 22.6, max: 38.0) -[2023-10-12 07:17:45,202][77203] Avg episode reward: [(0, '57.110'), (1, '45.450')] -[2023-10-12 07:17:45,263][78123] Updated weights for policy 1, policy_version 94740 (0.0008) -[2023-10-12 07:17:45,633][78123] Updated weights for policy 1, policy_version 94750 (0.0009) -[2023-10-12 07:17:48,658][78091] Updated weights for policy 0, policy_version 95210 (0.0008) -[2023-10-12 07:17:49,026][78091] Updated weights for policy 0, policy_version 95220 (0.0009) -[2023-10-12 07:17:49,390][78091] Updated weights for policy 0, policy_version 95230 (0.0008) -[2023-10-12 07:17:49,805][78123] Updated weights for policy 1, policy_version 94760 (0.0007) -[2023-10-12 07:17:50,181][78123] Updated weights for policy 1, policy_version 94770 (0.0009) -[2023-10-12 07:17:50,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 194543616. Throughput: 0: 1604.5, 1: 1604.8. Samples: 48645218. Policy #0 lag: (min: 22.0, avg: 22.6, max: 38.0) -[2023-10-12 07:17:50,201][77203] Avg episode reward: [(0, '52.410'), (1, '47.810')] -[2023-10-12 07:17:50,542][78123] Updated weights for policy 1, policy_version 94780 (0.0008) -[2023-10-12 07:17:53,813][78091] Updated weights for policy 0, policy_version 95240 (0.0009) -[2023-10-12 07:17:54,183][78091] Updated weights for policy 0, policy_version 95250 (0.0010) -[2023-10-12 07:17:54,541][78091] Updated weights for policy 0, policy_version 95260 (0.0010) -[2023-10-12 07:17:54,877][78123] Updated weights for policy 1, policy_version 94790 (0.0009) -[2023-10-12 07:17:55,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 194609152. Throughput: 0: 1587.3, 1: 1615.0. Samples: 48664050. Policy #0 lag: (min: 22.0, avg: 22.6, max: 38.0) -[2023-10-12 07:17:55,201][77203] Avg episode reward: [(0, '59.100'), (1, '56.830')] -[2023-10-12 07:17:55,238][78123] Updated weights for policy 1, policy_version 94800 (0.0008) -[2023-10-12 07:17:55,607][78123] Updated weights for policy 1, policy_version 94810 (0.0007) -[2023-10-12 07:17:58,907][78091] Updated weights for policy 0, policy_version 95270 (0.0008) -[2023-10-12 07:17:59,286][78091] Updated weights for policy 0, policy_version 95280 (0.0008) -[2023-10-12 07:17:59,658][78091] Updated weights for policy 0, policy_version 95290 (0.0009) -[2023-10-12 07:17:59,790][78123] Updated weights for policy 1, policy_version 94820 (0.0007) -[2023-10-12 07:18:00,163][78123] Updated weights for policy 1, policy_version 94830 (0.0009) -[2023-10-12 07:18:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 194674688. Throughput: 0: 1598.1, 1: 1593.7. Samples: 48673918. Policy #0 lag: (min: 22.0, avg: 22.6, max: 38.0) -[2023-10-12 07:18:00,201][77203] Avg episode reward: [(0, '51.930'), (1, '52.350')] -[2023-10-12 07:18:00,534][78123] Updated weights for policy 1, policy_version 94840 (0.0009) -[2023-10-12 07:18:03,722][78091] Updated weights for policy 0, policy_version 95300 (0.0008) -[2023-10-12 07:18:04,081][78091] Updated weights for policy 0, policy_version 95310 (0.0009) -[2023-10-12 07:18:04,449][78091] Updated weights for policy 0, policy_version 95320 (0.0009) -[2023-10-12 07:18:04,724][78123] Updated weights for policy 1, policy_version 94850 (0.0009) -[2023-10-12 07:18:05,095][78123] Updated weights for policy 1, policy_version 94860 (0.0009) -[2023-10-12 07:18:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 194740224. Throughput: 0: 1612.9, 1: 1597.6. Samples: 48693622. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:18:05,201][77203] Avg episode reward: [(0, '51.400'), (1, '48.050')] -[2023-10-12 07:18:05,469][78123] Updated weights for policy 1, policy_version 94870 (0.0009) -[2023-10-12 07:18:05,837][78123] Updated weights for policy 1, policy_version 94880 (0.0009) -[2023-10-12 07:18:08,626][78091] Updated weights for policy 0, policy_version 95330 (0.0007) -[2023-10-12 07:18:08,990][78091] Updated weights for policy 0, policy_version 95340 (0.0007) -[2023-10-12 07:18:09,355][78091] Updated weights for policy 0, policy_version 95350 (0.0007) -[2023-10-12 07:18:09,721][78091] Updated weights for policy 0, policy_version 95360 (0.0009) -[2023-10-12 07:18:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 194805760. Throughput: 0: 1595.2, 1: 1612.2. Samples: 48712298. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:18:10,201][77203] Avg episode reward: [(0, '57.300'), (1, '54.810')] -[2023-10-12 07:18:10,218][78123] Updated weights for policy 1, policy_version 94890 (0.0010) -[2023-10-12 07:18:10,579][78123] Updated weights for policy 1, policy_version 94900 (0.0007) -[2023-10-12 07:18:10,953][78123] Updated weights for policy 1, policy_version 94910 (0.0010) -[2023-10-12 07:18:14,130][78091] Updated weights for policy 0, policy_version 95370 (0.0009) -[2023-10-12 07:18:14,504][78091] Updated weights for policy 0, policy_version 95380 (0.0007) -[2023-10-12 07:18:14,869][78091] Updated weights for policy 0, policy_version 95390 (0.0007) -[2023-10-12 07:18:15,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 194871296. Throughput: 0: 1596.0, 1: 1592.2. Samples: 48722012. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:18:15,201][77203] Avg episode reward: [(0, '55.400'), (1, '54.440')] -[2023-10-12 07:18:15,272][78123] Updated weights for policy 1, policy_version 94920 (0.0008) -[2023-10-12 07:18:15,646][78123] Updated weights for policy 1, policy_version 94930 (0.0008) -[2023-10-12 07:18:16,000][78123] Updated weights for policy 1, policy_version 94940 (0.0009) -[2023-10-12 07:18:19,038][78091] Updated weights for policy 0, policy_version 95400 (0.0010) -[2023-10-12 07:18:19,411][78091] Updated weights for policy 0, policy_version 95410 (0.0009) -[2023-10-12 07:18:19,785][78091] Updated weights for policy 0, policy_version 95420 (0.0008) -[2023-10-12 07:18:20,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 194936832. Throughput: 0: 1617.4, 1: 1589.6. Samples: 48741670. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:18:20,202][77203] Avg episode reward: [(0, '57.250'), (1, '52.270')] -[2023-10-12 07:18:20,369][78123] Updated weights for policy 1, policy_version 94950 (0.0008) -[2023-10-12 07:18:20,736][78123] Updated weights for policy 1, policy_version 94960 (0.0007) -[2023-10-12 07:18:21,101][78123] Updated weights for policy 1, policy_version 94970 (0.0007) -[2023-10-12 07:18:24,057][78091] Updated weights for policy 0, policy_version 95430 (0.0008) -[2023-10-12 07:18:24,433][78091] Updated weights for policy 0, policy_version 95440 (0.0009) -[2023-10-12 07:18:24,805][78091] Updated weights for policy 0, policy_version 95450 (0.0007) -[2023-10-12 07:18:25,201][77203] Fps is (10 sec: 13106.8, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 195002368. Throughput: 0: 1606.8, 1: 1598.5. Samples: 48760262. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:18:25,202][77203] Avg episode reward: [(0, '60.150'), (1, '48.580')] -[2023-10-12 07:18:25,460][78123] Updated weights for policy 1, policy_version 94980 (0.0009) -[2023-10-12 07:18:25,827][78123] Updated weights for policy 1, policy_version 94990 (0.0009) -[2023-10-12 07:18:26,202][78123] Updated weights for policy 1, policy_version 95000 (0.0008) -[2023-10-12 07:18:29,035][78091] Updated weights for policy 0, policy_version 95460 (0.0007) -[2023-10-12 07:18:29,403][78091] Updated weights for policy 0, policy_version 95470 (0.0008) -[2023-10-12 07:18:29,771][78091] Updated weights for policy 0, policy_version 95480 (0.0007) -[2023-10-12 07:18:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 195067904. Throughput: 0: 1602.0, 1: 1587.1. Samples: 48769940. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:18:30,202][77203] Avg episode reward: [(0, '56.320'), (1, '46.380')] -[2023-10-12 07:18:30,625][78123] Updated weights for policy 1, policy_version 95010 (0.0008) -[2023-10-12 07:18:31,043][78123] Updated weights for policy 1, policy_version 95020 (0.0009) -[2023-10-12 07:18:31,411][78123] Updated weights for policy 1, policy_version 95030 (0.0010) -[2023-10-12 07:18:31,785][78123] Updated weights for policy 1, policy_version 95040 (0.0009) -[2023-10-12 07:18:34,139][78091] Updated weights for policy 0, policy_version 95490 (0.0008) -[2023-10-12 07:18:34,502][78091] Updated weights for policy 0, policy_version 95500 (0.0010) -[2023-10-12 07:18:34,881][78091] Updated weights for policy 0, policy_version 95510 (0.0010) -[2023-10-12 07:18:35,201][77203] Fps is (10 sec: 9830.7, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 195100672. Throughput: 0: 1614.4, 1: 1589.4. Samples: 48789392. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:18:35,201][77203] Avg episode reward: [(0, '54.040'), (1, '46.620')] -[2023-10-12 07:18:35,253][78091] Updated weights for policy 0, policy_version 95520 (0.0007) -[2023-10-12 07:18:36,047][78123] Updated weights for policy 1, policy_version 95050 (0.0009) -[2023-10-12 07:18:36,409][78123] Updated weights for policy 1, policy_version 95060 (0.0011) -[2023-10-12 07:18:36,776][78123] Updated weights for policy 1, policy_version 95070 (0.0010) -[2023-10-12 07:18:39,614][78091] Updated weights for policy 0, policy_version 95530 (0.0007) -[2023-10-12 07:18:39,984][78091] Updated weights for policy 0, policy_version 95540 (0.0008) -[2023-10-12 07:18:40,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 195166208. Throughput: 0: 1623.1, 1: 1589.5. Samples: 48808618. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:18:40,201][77203] Avg episode reward: [(0, '54.400'), (1, '40.530')] -[2023-10-12 07:18:40,347][78091] Updated weights for policy 0, policy_version 95550 (0.0009) -[2023-10-12 07:18:41,081][78123] Updated weights for policy 1, policy_version 95080 (0.0009) -[2023-10-12 07:18:41,456][78123] Updated weights for policy 1, policy_version 95090 (0.0009) -[2023-10-12 07:18:41,833][78123] Updated weights for policy 1, policy_version 95100 (0.0008) -[2023-10-12 07:18:44,665][78091] Updated weights for policy 0, policy_version 95560 (0.0007) -[2023-10-12 07:18:45,027][78091] Updated weights for policy 0, policy_version 95570 (0.0008) -[2023-10-12 07:18:45,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 195231744. Throughput: 0: 1609.3, 1: 1584.8. Samples: 48817654. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:18:45,202][77203] Avg episode reward: [(0, '55.310'), (1, '37.290')] -[2023-10-12 07:18:45,407][78091] Updated weights for policy 0, policy_version 95580 (0.0007) -[2023-10-12 07:18:46,404][78123] Updated weights for policy 1, policy_version 95110 (0.0008) -[2023-10-12 07:18:46,766][78123] Updated weights for policy 1, policy_version 95120 (0.0008) -[2023-10-12 07:18:47,135][78123] Updated weights for policy 1, policy_version 95130 (0.0007) -[2023-10-12 07:18:49,670][78091] Updated weights for policy 0, policy_version 95590 (0.0008) -[2023-10-12 07:18:50,030][78091] Updated weights for policy 0, policy_version 95600 (0.0007) -[2023-10-12 07:18:50,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 195297280. Throughput: 0: 1608.8, 1: 1575.4. Samples: 48836914. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:18:50,201][77203] Avg episode reward: [(0, '50.020'), (1, '38.130')] -[2023-10-12 07:18:50,405][78091] Updated weights for policy 0, policy_version 95610 (0.0008) -[2023-10-12 07:18:51,281][78123] Updated weights for policy 1, policy_version 95140 (0.0007) -[2023-10-12 07:18:51,660][78123] Updated weights for policy 1, policy_version 95150 (0.0007) -[2023-10-12 07:18:52,028][78123] Updated weights for policy 1, policy_version 95160 (0.0007) -[2023-10-12 07:18:54,952][78091] Updated weights for policy 0, policy_version 95620 (0.0007) -[2023-10-12 07:18:55,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 195362816. Throughput: 0: 1618.7, 1: 1580.1. Samples: 48856244. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:18:55,201][77203] Avg episode reward: [(0, '53.890'), (1, '39.720')] -[2023-10-12 07:18:55,334][78091] Updated weights for policy 0, policy_version 95630 (0.0008) -[2023-10-12 07:18:55,707][78091] Updated weights for policy 0, policy_version 95640 (0.0009) -[2023-10-12 07:18:56,166][78123] Updated weights for policy 1, policy_version 95170 (0.0007) -[2023-10-12 07:18:56,530][78123] Updated weights for policy 1, policy_version 95180 (0.0007) -[2023-10-12 07:18:56,886][78123] Updated weights for policy 1, policy_version 95190 (0.0008) -[2023-10-12 07:18:57,245][78123] Updated weights for policy 1, policy_version 95200 (0.0008) -[2023-10-12 07:19:00,085][78091] Updated weights for policy 0, policy_version 95650 (0.0010) -[2023-10-12 07:19:00,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 195428352. Throughput: 0: 1594.2, 1: 1584.0. Samples: 48865030. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:19:00,201][77203] Avg episode reward: [(0, '50.470'), (1, '47.240')] -[2023-10-12 07:19:00,462][78091] Updated weights for policy 0, policy_version 95660 (0.0011) -[2023-10-12 07:19:00,823][78091] Updated weights for policy 0, policy_version 95670 (0.0010) -[2023-10-12 07:19:01,184][78091] Updated weights for policy 0, policy_version 95680 (0.0009) -[2023-10-12 07:19:01,597][78123] Updated weights for policy 1, policy_version 95210 (0.0011) -[2023-10-12 07:19:01,953][78123] Updated weights for policy 1, policy_version 95220 (0.0008) -[2023-10-12 07:19:02,327][78123] Updated weights for policy 1, policy_version 95230 (0.0010) -[2023-10-12 07:19:05,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 195493888. Throughput: 0: 1591.3, 1: 1583.1. Samples: 48884516. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:19:05,202][77203] Avg episode reward: [(0, '58.610'), (1, '50.980')] -[2023-10-12 07:19:05,635][78091] Updated weights for policy 0, policy_version 95690 (0.0010) -[2023-10-12 07:19:06,007][78091] Updated weights for policy 0, policy_version 95700 (0.0008) -[2023-10-12 07:19:06,373][78091] Updated weights for policy 0, policy_version 95710 (0.0009) -[2023-10-12 07:19:06,742][78123] Updated weights for policy 1, policy_version 95240 (0.0009) -[2023-10-12 07:19:07,107][78123] Updated weights for policy 1, policy_version 95250 (0.0008) -[2023-10-12 07:19:07,478][78123] Updated weights for policy 1, policy_version 95260 (0.0010) -[2023-10-12 07:19:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 195559424. Throughput: 0: 1611.7, 1: 1585.1. Samples: 48904116. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-12 07:19:10,201][77203] Avg episode reward: [(0, '63.890'), (1, '48.440')] -[2023-10-12 07:19:10,209][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000095264_97550336.pth... -[2023-10-12 07:19:10,245][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000093792_96043008.pth -[2023-10-12 07:19:10,623][78091] Updated weights for policy 0, policy_version 95720 (0.0011) -[2023-10-12 07:19:10,987][78091] Updated weights for policy 0, policy_version 95730 (0.0009) -[2023-10-12 07:19:11,361][78091] Updated weights for policy 0, policy_version 95740 (0.0008) -[2023-10-12 07:19:11,499][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000095744_98041856.pth... -[2023-10-12 07:19:11,527][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000094240_96501760.pth -[2023-10-12 07:19:11,724][78123] Updated weights for policy 1, policy_version 95270 (0.0010) -[2023-10-12 07:19:12,084][78123] Updated weights for policy 1, policy_version 95280 (0.0010) -[2023-10-12 07:19:12,455][78123] Updated weights for policy 1, policy_version 95290 (0.0011) -[2023-10-12 07:19:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 195624960. Throughput: 0: 1586.4, 1: 1589.0. Samples: 48912832. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-12 07:19:15,202][77203] Avg episode reward: [(0, '56.150'), (1, '50.480')] -[2023-10-12 07:19:15,557][78091] Updated weights for policy 0, policy_version 95750 (0.0009) -[2023-10-12 07:19:15,928][78091] Updated weights for policy 0, policy_version 95760 (0.0010) -[2023-10-12 07:19:16,302][78091] Updated weights for policy 0, policy_version 95770 (0.0009) -[2023-10-12 07:19:16,650][78123] Updated weights for policy 1, policy_version 95300 (0.0010) -[2023-10-12 07:19:17,010][78123] Updated weights for policy 1, policy_version 95310 (0.0008) -[2023-10-12 07:19:17,385][78123] Updated weights for policy 1, policy_version 95320 (0.0007) -[2023-10-12 07:19:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 195690496. Throughput: 0: 1585.7, 1: 1596.6. Samples: 48932594. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-12 07:19:20,201][77203] Avg episode reward: [(0, '61.310'), (1, '47.750')] -[2023-10-12 07:19:20,723][78091] Updated weights for policy 0, policy_version 95780 (0.0009) -[2023-10-12 07:19:21,108][78091] Updated weights for policy 0, policy_version 95790 (0.0009) -[2023-10-12 07:19:21,476][78091] Updated weights for policy 0, policy_version 95800 (0.0008) -[2023-10-12 07:19:21,837][78123] Updated weights for policy 1, policy_version 95330 (0.0008) -[2023-10-12 07:19:22,258][78123] Updated weights for policy 1, policy_version 95340 (0.0009) -[2023-10-12 07:19:22,620][78123] Updated weights for policy 1, policy_version 95350 (0.0008) -[2023-10-12 07:19:22,997][78123] Updated weights for policy 1, policy_version 95360 (0.0007) -[2023-10-12 07:19:25,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 195756032. Throughput: 0: 1596.5, 1: 1594.6. Samples: 48952220. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-12 07:19:25,201][77203] Avg episode reward: [(0, '53.070'), (1, '48.400')] -[2023-10-12 07:19:25,491][78091] Updated weights for policy 0, policy_version 95810 (0.0009) -[2023-10-12 07:19:25,863][78091] Updated weights for policy 0, policy_version 95820 (0.0008) -[2023-10-12 07:19:26,237][78091] Updated weights for policy 0, policy_version 95830 (0.0007) -[2023-10-12 07:19:26,608][78091] Updated weights for policy 0, policy_version 95840 (0.0008) -[2023-10-12 07:19:27,259][78123] Updated weights for policy 1, policy_version 95370 (0.0008) -[2023-10-12 07:19:27,629][78123] Updated weights for policy 1, policy_version 95380 (0.0009) -[2023-10-12 07:19:28,009][78123] Updated weights for policy 1, policy_version 95390 (0.0009) -[2023-10-12 07:19:30,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 195821568. Throughput: 0: 1585.9, 1: 1605.7. Samples: 48961274. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-12 07:19:30,202][77203] Avg episode reward: [(0, '62.070'), (1, '53.050')] -[2023-10-12 07:19:30,978][78091] Updated weights for policy 0, policy_version 95850 (0.0010) -[2023-10-12 07:19:31,344][78091] Updated weights for policy 0, policy_version 95860 (0.0008) -[2023-10-12 07:19:31,723][78091] Updated weights for policy 0, policy_version 95870 (0.0007) -[2023-10-12 07:19:32,306][78123] Updated weights for policy 1, policy_version 95400 (0.0008) -[2023-10-12 07:19:32,679][78123] Updated weights for policy 1, policy_version 95410 (0.0011) -[2023-10-12 07:19:33,046][78123] Updated weights for policy 1, policy_version 95420 (0.0007) -[2023-10-12 07:19:35,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 12774.0). Total num frames: 195887104. Throughput: 0: 1588.0, 1: 1604.9. Samples: 48980596. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-12 07:19:35,202][77203] Avg episode reward: [(0, '57.250'), (1, '57.460')] -[2023-10-12 07:19:35,952][78091] Updated weights for policy 0, policy_version 95880 (0.0008) -[2023-10-12 07:19:36,322][78091] Updated weights for policy 0, policy_version 95890 (0.0009) -[2023-10-12 07:19:36,700][78091] Updated weights for policy 0, policy_version 95900 (0.0009) -[2023-10-12 07:19:37,424][78123] Updated weights for policy 1, policy_version 95430 (0.0009) -[2023-10-12 07:19:37,798][78123] Updated weights for policy 1, policy_version 95440 (0.0010) -[2023-10-12 07:19:38,164][78123] Updated weights for policy 1, policy_version 95450 (0.0009) -[2023-10-12 07:19:40,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 195952640. Throughput: 0: 1597.2, 1: 1600.1. Samples: 49000124. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-12 07:19:40,201][77203] Avg episode reward: [(0, '59.140'), (1, '49.270')] -[2023-10-12 07:19:40,941][78091] Updated weights for policy 0, policy_version 95910 (0.0008) -[2023-10-12 07:19:41,304][78091] Updated weights for policy 0, policy_version 95920 (0.0008) -[2023-10-12 07:19:41,669][78091] Updated weights for policy 0, policy_version 95930 (0.0007) -[2023-10-12 07:19:42,381][78123] Updated weights for policy 1, policy_version 95460 (0.0008) -[2023-10-12 07:19:42,739][78123] Updated weights for policy 1, policy_version 95470 (0.0010) -[2023-10-12 07:19:43,103][78123] Updated weights for policy 1, policy_version 95480 (0.0008) -[2023-10-12 07:19:45,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.1). Total num frames: 196018176. Throughput: 0: 1598.1, 1: 1615.0. Samples: 49009620. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-12 07:19:45,202][77203] Avg episode reward: [(0, '53.220'), (1, '44.500')] -[2023-10-12 07:19:46,077][78091] Updated weights for policy 0, policy_version 95940 (0.0008) -[2023-10-12 07:19:46,449][78091] Updated weights for policy 0, policy_version 95950 (0.0009) -[2023-10-12 07:19:46,818][78091] Updated weights for policy 0, policy_version 95960 (0.0010) -[2023-10-12 07:19:47,163][78123] Updated weights for policy 1, policy_version 95490 (0.0008) -[2023-10-12 07:19:47,526][78123] Updated weights for policy 1, policy_version 95500 (0.0010) -[2023-10-12 07:19:47,896][78123] Updated weights for policy 1, policy_version 95510 (0.0009) -[2023-10-12 07:19:48,270][78123] Updated weights for policy 1, policy_version 95520 (0.0010) -[2023-10-12 07:19:50,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 196083712. Throughput: 0: 1593.9, 1: 1605.6. Samples: 49028492. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-12 07:19:50,202][77203] Avg episode reward: [(0, '54.740'), (1, '49.330')] -[2023-10-12 07:19:51,300][78091] Updated weights for policy 0, policy_version 95970 (0.0009) -[2023-10-12 07:19:51,674][78091] Updated weights for policy 0, policy_version 95980 (0.0007) -[2023-10-12 07:19:52,034][78091] Updated weights for policy 0, policy_version 95990 (0.0008) -[2023-10-12 07:19:52,402][78091] Updated weights for policy 0, policy_version 96000 (0.0010) -[2023-10-12 07:19:52,557][78123] Updated weights for policy 1, policy_version 95530 (0.0009) -[2023-10-12 07:19:52,916][78123] Updated weights for policy 1, policy_version 95540 (0.0010) -[2023-10-12 07:19:53,277][78123] Updated weights for policy 1, policy_version 95550 (0.0009) -[2023-10-12 07:19:55,201][77203] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 12885.0). Total num frames: 196149248. Throughput: 0: 1589.5, 1: 1606.6. Samples: 49047944. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-12 07:19:55,203][77203] Avg episode reward: [(0, '54.740'), (1, '51.690')] -[2023-10-12 07:19:56,795][78091] Updated weights for policy 0, policy_version 96010 (0.0008) -[2023-10-12 07:19:57,161][78091] Updated weights for policy 0, policy_version 96020 (0.0009) -[2023-10-12 07:19:57,537][78091] Updated weights for policy 0, policy_version 96030 (0.0011) -[2023-10-12 07:19:57,710][78123] Updated weights for policy 1, policy_version 95560 (0.0011) -[2023-10-12 07:19:58,081][78123] Updated weights for policy 1, policy_version 95570 (0.0008) -[2023-10-12 07:19:58,443][78123] Updated weights for policy 1, policy_version 95580 (0.0008) -[2023-10-12 07:20:00,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 196214784. Throughput: 0: 1586.2, 1: 1623.3. Samples: 49057260. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-12 07:20:00,201][77203] Avg episode reward: [(0, '55.280'), (1, '59.120')] -[2023-10-12 07:20:01,848][78091] Updated weights for policy 0, policy_version 96040 (0.0008) -[2023-10-12 07:20:02,204][78091] Updated weights for policy 0, policy_version 96050 (0.0008) -[2023-10-12 07:20:02,583][78091] Updated weights for policy 0, policy_version 96060 (0.0010) -[2023-10-12 07:20:02,831][78123] Updated weights for policy 1, policy_version 95590 (0.0009) -[2023-10-12 07:20:03,193][78123] Updated weights for policy 1, policy_version 95600 (0.0009) -[2023-10-12 07:20:03,560][78123] Updated weights for policy 1, policy_version 95610 (0.0007) -[2023-10-12 07:20:05,201][77203] Fps is (10 sec: 13107.8, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 196280320. Throughput: 0: 1590.4, 1: 1599.2. Samples: 49076126. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-12 07:20:05,201][77203] Avg episode reward: [(0, '56.430'), (1, '56.940')] -[2023-10-12 07:20:06,972][78091] Updated weights for policy 0, policy_version 96070 (0.0010) -[2023-10-12 07:20:07,334][78091] Updated weights for policy 0, policy_version 96080 (0.0010) -[2023-10-12 07:20:07,701][78091] Updated weights for policy 0, policy_version 96090 (0.0011) -[2023-10-12 07:20:08,141][78123] Updated weights for policy 1, policy_version 95620 (0.0011) -[2023-10-12 07:20:08,538][78123] Updated weights for policy 1, policy_version 95630 (0.0007) -[2023-10-12 07:20:08,902][78123] Updated weights for policy 1, policy_version 95640 (0.0009) -[2023-10-12 07:20:10,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 196345856. Throughput: 0: 1591.0, 1: 1590.9. Samples: 49095404. Policy #0 lag: (min: 31.0, avg: 32.5, max: 59.0) -[2023-10-12 07:20:10,202][77203] Avg episode reward: [(0, '52.890'), (1, '55.360')] -[2023-10-12 07:20:11,885][78091] Updated weights for policy 0, policy_version 96100 (0.0009) -[2023-10-12 07:20:12,248][78091] Updated weights for policy 0, policy_version 96110 (0.0007) -[2023-10-12 07:20:12,628][78091] Updated weights for policy 0, policy_version 96120 (0.0007) -[2023-10-12 07:20:13,167][78123] Updated weights for policy 1, policy_version 95650 (0.0009) -[2023-10-12 07:20:13,545][78123] Updated weights for policy 1, policy_version 95660 (0.0009) -[2023-10-12 07:20:13,909][78123] Updated weights for policy 1, policy_version 95670 (0.0008) -[2023-10-12 07:20:14,283][78123] Updated weights for policy 1, policy_version 95680 (0.0008) -[2023-10-12 07:20:15,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 196411392. Throughput: 0: 1596.8, 1: 1608.2. Samples: 49105496. Policy #0 lag: (min: 31.0, avg: 32.5, max: 59.0) -[2023-10-12 07:20:15,202][77203] Avg episode reward: [(0, '50.010'), (1, '50.730')] -[2023-10-12 07:20:16,754][78091] Updated weights for policy 0, policy_version 96130 (0.0008) -[2023-10-12 07:20:17,121][78091] Updated weights for policy 0, policy_version 96140 (0.0010) -[2023-10-12 07:20:17,494][78091] Updated weights for policy 0, policy_version 96150 (0.0008) -[2023-10-12 07:20:17,869][78091] Updated weights for policy 0, policy_version 96160 (0.0009) -[2023-10-12 07:20:18,610][78123] Updated weights for policy 1, policy_version 95690 (0.0009) -[2023-10-12 07:20:18,975][78123] Updated weights for policy 1, policy_version 95700 (0.0010) -[2023-10-12 07:20:19,342][78123] Updated weights for policy 1, policy_version 95710 (0.0011) -[2023-10-12 07:20:20,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 196476928. Throughput: 0: 1598.0, 1: 1605.2. Samples: 49124742. Policy #0 lag: (min: 31.0, avg: 32.5, max: 59.0) -[2023-10-12 07:20:20,202][77203] Avg episode reward: [(0, '54.840'), (1, '52.940')] -[2023-10-12 07:20:22,160][78091] Updated weights for policy 0, policy_version 96170 (0.0008) -[2023-10-12 07:20:22,532][78091] Updated weights for policy 0, policy_version 96180 (0.0007) -[2023-10-12 07:20:22,906][78091] Updated weights for policy 0, policy_version 96190 (0.0007) -[2023-10-12 07:20:23,680][78123] Updated weights for policy 1, policy_version 95720 (0.0009) -[2023-10-12 07:20:24,040][78123] Updated weights for policy 1, policy_version 95730 (0.0009) -[2023-10-12 07:20:24,412][78123] Updated weights for policy 1, policy_version 95740 (0.0009) -[2023-10-12 07:20:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 196542464. Throughput: 0: 1598.8, 1: 1591.8. Samples: 49143700. Policy #0 lag: (min: 31.0, avg: 32.5, max: 59.0) -[2023-10-12 07:20:25,201][77203] Avg episode reward: [(0, '61.030'), (1, '48.170')] -[2023-10-12 07:20:27,210][78091] Updated weights for policy 0, policy_version 96200 (0.0007) -[2023-10-12 07:20:27,584][78091] Updated weights for policy 0, policy_version 96210 (0.0008) -[2023-10-12 07:20:27,948][78091] Updated weights for policy 0, policy_version 96220 (0.0008) -[2023-10-12 07:20:28,695][78123] Updated weights for policy 1, policy_version 95750 (0.0009) -[2023-10-12 07:20:29,067][78123] Updated weights for policy 1, policy_version 95760 (0.0007) -[2023-10-12 07:20:29,432][78123] Updated weights for policy 1, policy_version 95770 (0.0007) -[2023-10-12 07:20:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 196608000. Throughput: 0: 1603.1, 1: 1598.7. Samples: 49153702. Policy #0 lag: (min: 31.0, avg: 32.5, max: 59.0) -[2023-10-12 07:20:30,202][77203] Avg episode reward: [(0, '62.560'), (1, '48.650')] -[2023-10-12 07:20:32,369][78091] Updated weights for policy 0, policy_version 96230 (0.0009) -[2023-10-12 07:20:32,744][78091] Updated weights for policy 0, policy_version 96240 (0.0009) -[2023-10-12 07:20:33,116][78091] Updated weights for policy 0, policy_version 96250 (0.0009) -[2023-10-12 07:20:33,563][78123] Updated weights for policy 1, policy_version 95780 (0.0007) -[2023-10-12 07:20:33,926][78123] Updated weights for policy 1, policy_version 95790 (0.0008) -[2023-10-12 07:20:34,301][78123] Updated weights for policy 1, policy_version 95800 (0.0008) -[2023-10-12 07:20:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 196673536. Throughput: 0: 1599.9, 1: 1602.1. Samples: 49172580. Policy #0 lag: (min: 31.0, avg: 32.5, max: 59.0) -[2023-10-12 07:20:35,202][77203] Avg episode reward: [(0, '53.890'), (1, '62.670')] -[2023-10-12 07:20:37,172][78091] Updated weights for policy 0, policy_version 96260 (0.0009) -[2023-10-12 07:20:37,540][78091] Updated weights for policy 0, policy_version 96270 (0.0007) -[2023-10-12 07:20:37,901][78091] Updated weights for policy 0, policy_version 96280 (0.0007) -[2023-10-12 07:20:38,796][78123] Updated weights for policy 1, policy_version 95810 (0.0011) -[2023-10-12 07:20:39,156][78123] Updated weights for policy 1, policy_version 95820 (0.0008) -[2023-10-12 07:20:39,511][78123] Updated weights for policy 1, policy_version 95830 (0.0009) -[2023-10-12 07:20:39,884][78123] Updated weights for policy 1, policy_version 95840 (0.0008) -[2023-10-12 07:20:40,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 196739072. Throughput: 0: 1607.4, 1: 1584.5. Samples: 49191578. Policy #0 lag: (min: 31.0, avg: 32.5, max: 59.0) -[2023-10-12 07:20:40,202][77203] Avg episode reward: [(0, '51.210'), (1, '54.810')] -[2023-10-12 07:20:42,257][78091] Updated weights for policy 0, policy_version 96290 (0.0008) -[2023-10-12 07:20:42,647][78091] Updated weights for policy 0, policy_version 96300 (0.0008) -[2023-10-12 07:20:43,029][78091] Updated weights for policy 0, policy_version 96310 (0.0009) -[2023-10-12 07:20:43,400][78091] Updated weights for policy 0, policy_version 96320 (0.0009) -[2023-10-12 07:20:44,111][78123] Updated weights for policy 1, policy_version 95850 (0.0008) -[2023-10-12 07:20:44,485][78123] Updated weights for policy 1, policy_version 95860 (0.0008) -[2023-10-12 07:20:44,849][78123] Updated weights for policy 1, policy_version 95870 (0.0009) -[2023-10-12 07:20:45,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 196804608. Throughput: 0: 1625.2, 1: 1588.7. Samples: 49201882. Policy #0 lag: (min: 31.0, avg: 32.5, max: 59.0) -[2023-10-12 07:20:45,202][77203] Avg episode reward: [(0, '58.470'), (1, '48.870')] -[2023-10-12 07:20:47,603][78091] Updated weights for policy 0, policy_version 96330 (0.0008) -[2023-10-12 07:20:47,974][78091] Updated weights for policy 0, policy_version 96340 (0.0007) -[2023-10-12 07:20:48,354][78091] Updated weights for policy 0, policy_version 96350 (0.0008) -[2023-10-12 07:20:49,132][78123] Updated weights for policy 1, policy_version 95880 (0.0009) -[2023-10-12 07:20:49,495][78123] Updated weights for policy 1, policy_version 95890 (0.0011) -[2023-10-12 07:20:49,872][78123] Updated weights for policy 1, policy_version 95900 (0.0010) -[2023-10-12 07:20:50,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 196870144. Throughput: 0: 1607.5, 1: 1612.0. Samples: 49221004. Policy #0 lag: (min: 31.0, avg: 32.5, max: 59.0) -[2023-10-12 07:20:50,201][77203] Avg episode reward: [(0, '58.360'), (1, '46.860')] -[2023-10-12 07:20:52,650][78091] Updated weights for policy 0, policy_version 96360 (0.0009) -[2023-10-12 07:20:53,024][78091] Updated weights for policy 0, policy_version 96370 (0.0007) -[2023-10-12 07:20:53,383][78091] Updated weights for policy 0, policy_version 96380 (0.0008) -[2023-10-12 07:20:54,330][78123] Updated weights for policy 1, policy_version 95910 (0.0008) -[2023-10-12 07:20:54,706][78123] Updated weights for policy 1, policy_version 95920 (0.0008) -[2023-10-12 07:20:55,069][78123] Updated weights for policy 1, policy_version 95930 (0.0007) -[2023-10-12 07:20:55,201][77203] Fps is (10 sec: 9830.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 196902912. Throughput: 0: 1605.5, 1: 1606.0. Samples: 49239924. Policy #0 lag: (min: 31.0, avg: 32.5, max: 59.0) -[2023-10-12 07:20:55,201][77203] Avg episode reward: [(0, '51.650'), (1, '50.050')] -[2023-10-12 07:20:57,704][78091] Updated weights for policy 0, policy_version 96390 (0.0009) -[2023-10-12 07:20:58,071][78091] Updated weights for policy 0, policy_version 96400 (0.0008) -[2023-10-12 07:20:58,444][78091] Updated weights for policy 0, policy_version 96410 (0.0009) -[2023-10-12 07:20:59,658][78123] Updated weights for policy 1, policy_version 95940 (0.0007) -[2023-10-12 07:21:00,027][78123] Updated weights for policy 1, policy_version 95950 (0.0008) -[2023-10-12 07:21:00,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 196968448. Throughput: 0: 1619.7, 1: 1588.2. Samples: 49249852. Policy #0 lag: (min: 31.0, avg: 32.5, max: 59.0) -[2023-10-12 07:21:00,202][77203] Avg episode reward: [(0, '52.080'), (1, '49.610')] -[2023-10-12 07:21:00,387][78123] Updated weights for policy 1, policy_version 95960 (0.0009) -[2023-10-12 07:21:02,754][78091] Updated weights for policy 0, policy_version 96420 (0.0008) -[2023-10-12 07:21:03,118][78091] Updated weights for policy 0, policy_version 96430 (0.0008) -[2023-10-12 07:21:03,490][78091] Updated weights for policy 0, policy_version 96440 (0.0008) -[2023-10-12 07:21:04,602][78123] Updated weights for policy 1, policy_version 95970 (0.0008) -[2023-10-12 07:21:04,969][78123] Updated weights for policy 1, policy_version 95980 (0.0007) -[2023-10-12 07:21:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 197033984. Throughput: 0: 1598.5, 1: 1598.9. Samples: 49268628. Policy #0 lag: (min: 31.0, avg: 32.5, max: 59.0) -[2023-10-12 07:21:05,201][77203] Avg episode reward: [(0, '57.360'), (1, '51.920')] -[2023-10-12 07:21:05,334][78123] Updated weights for policy 1, policy_version 95990 (0.0009) -[2023-10-12 07:21:05,698][78123] Updated weights for policy 1, policy_version 96000 (0.0008) -[2023-10-12 07:21:07,878][78091] Updated weights for policy 0, policy_version 96450 (0.0010) -[2023-10-12 07:21:08,254][78091] Updated weights for policy 0, policy_version 96460 (0.0007) -[2023-10-12 07:21:08,634][78091] Updated weights for policy 0, policy_version 96470 (0.0007) -[2023-10-12 07:21:09,006][78091] Updated weights for policy 0, policy_version 96480 (0.0009) -[2023-10-12 07:21:09,953][78123] Updated weights for policy 1, policy_version 96010 (0.0011) -[2023-10-12 07:21:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 197099520. Throughput: 0: 1595.1, 1: 1611.1. Samples: 49287978. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-12 07:21:10,202][77203] Avg episode reward: [(0, '58.360'), (1, '61.580')] -[2023-10-12 07:21:10,211][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000096480_98795520.pth... -[2023-10-12 07:21:10,247][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000094976_97255424.pth -[2023-10-12 07:21:10,319][78123] Updated weights for policy 1, policy_version 96020 (0.0009) -[2023-10-12 07:21:10,685][78123] Updated weights for policy 1, policy_version 96030 (0.0008) -[2023-10-12 07:21:10,758][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000096032_98336768.pth... -[2023-10-12 07:21:10,788][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000094528_96796672.pth -[2023-10-12 07:21:13,157][78091] Updated weights for policy 0, policy_version 96490 (0.0008) -[2023-10-12 07:21:13,527][78091] Updated weights for policy 0, policy_version 96500 (0.0009) -[2023-10-12 07:21:13,893][78091] Updated weights for policy 0, policy_version 96510 (0.0009) -[2023-10-12 07:21:14,965][78123] Updated weights for policy 1, policy_version 96040 (0.0009) -[2023-10-12 07:21:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 197165056. Throughput: 0: 1619.3, 1: 1593.2. Samples: 49298266. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-12 07:21:15,201][77203] Avg episode reward: [(0, '55.190'), (1, '56.820')] -[2023-10-12 07:21:15,325][78123] Updated weights for policy 1, policy_version 96050 (0.0010) -[2023-10-12 07:21:15,691][78123] Updated weights for policy 1, policy_version 96060 (0.0010) -[2023-10-12 07:21:18,167][78091] Updated weights for policy 0, policy_version 96520 (0.0008) -[2023-10-12 07:21:18,551][78091] Updated weights for policy 0, policy_version 96530 (0.0007) -[2023-10-12 07:21:18,911][78091] Updated weights for policy 0, policy_version 96540 (0.0007) -[2023-10-12 07:21:19,739][78123] Updated weights for policy 1, policy_version 96070 (0.0010) -[2023-10-12 07:21:20,105][78123] Updated weights for policy 1, policy_version 96080 (0.0009) -[2023-10-12 07:21:20,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 197230592. Throughput: 0: 1610.3, 1: 1607.8. Samples: 49317392. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-12 07:21:20,201][77203] Avg episode reward: [(0, '55.710'), (1, '54.900')] -[2023-10-12 07:21:20,479][78123] Updated weights for policy 1, policy_version 96090 (0.0009) -[2023-10-12 07:21:23,047][78091] Updated weights for policy 0, policy_version 96550 (0.0010) -[2023-10-12 07:21:23,430][78091] Updated weights for policy 0, policy_version 96560 (0.0009) -[2023-10-12 07:21:23,804][78091] Updated weights for policy 0, policy_version 96570 (0.0010) -[2023-10-12 07:21:24,797][78123] Updated weights for policy 1, policy_version 96100 (0.0008) -[2023-10-12 07:21:25,161][78123] Updated weights for policy 1, policy_version 96110 (0.0007) -[2023-10-12 07:21:25,201][77203] Fps is (10 sec: 13106.9, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 197296128. Throughput: 0: 1600.6, 1: 1624.2. Samples: 49336696. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-12 07:21:25,202][77203] Avg episode reward: [(0, '56.710'), (1, '50.650')] -[2023-10-12 07:21:25,525][78123] Updated weights for policy 1, policy_version 96120 (0.0007) -[2023-10-12 07:21:28,291][78091] Updated weights for policy 0, policy_version 96580 (0.0008) -[2023-10-12 07:21:28,684][78091] Updated weights for policy 0, policy_version 96590 (0.0010) -[2023-10-12 07:21:29,054][78091] Updated weights for policy 0, policy_version 96600 (0.0009) -[2023-10-12 07:21:29,784][78123] Updated weights for policy 1, policy_version 96130 (0.0010) -[2023-10-12 07:21:30,153][78123] Updated weights for policy 1, policy_version 96140 (0.0009) -[2023-10-12 07:21:30,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 197361664. Throughput: 0: 1612.4, 1: 1602.5. Samples: 49346554. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-12 07:21:30,201][77203] Avg episode reward: [(0, '58.670'), (1, '54.260')] -[2023-10-12 07:21:30,520][78123] Updated weights for policy 1, policy_version 96150 (0.0008) -[2023-10-12 07:21:30,890][78123] Updated weights for policy 1, policy_version 96160 (0.0008) -[2023-10-12 07:21:33,413][78091] Updated weights for policy 0, policy_version 96610 (0.0008) -[2023-10-12 07:21:33,779][78091] Updated weights for policy 0, policy_version 96620 (0.0008) -[2023-10-12 07:21:34,145][78091] Updated weights for policy 0, policy_version 96630 (0.0008) -[2023-10-12 07:21:34,521][78091] Updated weights for policy 0, policy_version 96640 (0.0008) -[2023-10-12 07:21:35,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 197427200. Throughput: 0: 1612.7, 1: 1602.4. Samples: 49365682. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-12 07:21:35,201][77203] Avg episode reward: [(0, '56.720'), (1, '50.730')] -[2023-10-12 07:21:35,266][78123] Updated weights for policy 1, policy_version 96170 (0.0009) -[2023-10-12 07:21:35,638][78123] Updated weights for policy 1, policy_version 96180 (0.0008) -[2023-10-12 07:21:35,999][78123] Updated weights for policy 1, policy_version 96190 (0.0008) -[2023-10-12 07:21:38,714][78091] Updated weights for policy 0, policy_version 96650 (0.0010) -[2023-10-12 07:21:39,076][78091] Updated weights for policy 0, policy_version 96660 (0.0007) -[2023-10-12 07:21:39,440][78091] Updated weights for policy 0, policy_version 96670 (0.0009) -[2023-10-12 07:21:40,201][77203] Fps is (10 sec: 13106.8, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 197492736. Throughput: 0: 1595.7, 1: 1618.4. Samples: 49384560. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-12 07:21:40,202][77203] Avg episode reward: [(0, '55.170'), (1, '52.490')] -[2023-10-12 07:21:40,263][78123] Updated weights for policy 1, policy_version 96200 (0.0008) -[2023-10-12 07:21:40,641][78123] Updated weights for policy 1, policy_version 96210 (0.0007) -[2023-10-12 07:21:41,001][78123] Updated weights for policy 1, policy_version 96220 (0.0008) -[2023-10-12 07:21:43,808][78091] Updated weights for policy 0, policy_version 96680 (0.0007) -[2023-10-12 07:21:44,172][78091] Updated weights for policy 0, policy_version 96690 (0.0009) -[2023-10-12 07:21:44,543][78091] Updated weights for policy 0, policy_version 96700 (0.0011) -[2023-10-12 07:21:45,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 197558272. Throughput: 0: 1602.0, 1: 1605.6. Samples: 49394196. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-12 07:21:45,201][77203] Avg episode reward: [(0, '55.460'), (1, '55.710')] -[2023-10-12 07:21:45,370][78123] Updated weights for policy 1, policy_version 96230 (0.0008) -[2023-10-12 07:21:45,732][78123] Updated weights for policy 1, policy_version 96240 (0.0009) -[2023-10-12 07:21:46,102][78123] Updated weights for policy 1, policy_version 96250 (0.0011) -[2023-10-12 07:21:49,039][78091] Updated weights for policy 0, policy_version 96710 (0.0008) -[2023-10-12 07:21:49,413][78091] Updated weights for policy 0, policy_version 96720 (0.0010) -[2023-10-12 07:21:49,781][78091] Updated weights for policy 0, policy_version 96730 (0.0010) -[2023-10-12 07:21:50,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 197623808. Throughput: 0: 1623.1, 1: 1600.6. Samples: 49413698. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-12 07:21:50,202][77203] Avg episode reward: [(0, '57.440'), (1, '62.810')] -[2023-10-12 07:21:50,368][78123] Updated weights for policy 1, policy_version 96260 (0.0009) -[2023-10-12 07:21:50,747][78123] Updated weights for policy 1, policy_version 96270 (0.0009) -[2023-10-12 07:21:51,122][78123] Updated weights for policy 1, policy_version 96280 (0.0009) -[2023-10-12 07:21:54,003][78091] Updated weights for policy 0, policy_version 96740 (0.0009) -[2023-10-12 07:21:54,379][78091] Updated weights for policy 0, policy_version 96750 (0.0010) -[2023-10-12 07:21:54,746][78091] Updated weights for policy 0, policy_version 96760 (0.0009) -[2023-10-12 07:21:55,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 197689344. Throughput: 0: 1605.3, 1: 1607.7. Samples: 49432566. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-12 07:21:55,202][77203] Avg episode reward: [(0, '59.950'), (1, '50.460')] -[2023-10-12 07:21:55,477][78123] Updated weights for policy 1, policy_version 96290 (0.0007) -[2023-10-12 07:21:55,846][78123] Updated weights for policy 1, policy_version 96300 (0.0009) -[2023-10-12 07:21:56,211][78123] Updated weights for policy 1, policy_version 96310 (0.0009) -[2023-10-12 07:21:56,578][78123] Updated weights for policy 1, policy_version 96320 (0.0009) -[2023-10-12 07:21:58,980][78091] Updated weights for policy 0, policy_version 96770 (0.0009) -[2023-10-12 07:21:59,347][78091] Updated weights for policy 0, policy_version 96780 (0.0010) -[2023-10-12 07:21:59,721][78091] Updated weights for policy 0, policy_version 96790 (0.0008) -[2023-10-12 07:22:00,091][78091] Updated weights for policy 0, policy_version 96800 (0.0010) -[2023-10-12 07:22:00,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 197754880. Throughput: 0: 1597.0, 1: 1602.2. Samples: 49442230. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-12 07:22:00,202][77203] Avg episode reward: [(0, '56.110'), (1, '53.060')] -[2023-10-12 07:22:00,964][78123] Updated weights for policy 1, policy_version 96330 (0.0008) -[2023-10-12 07:22:01,330][78123] Updated weights for policy 1, policy_version 96340 (0.0007) -[2023-10-12 07:22:01,689][78123] Updated weights for policy 1, policy_version 96350 (0.0011) -[2023-10-12 07:22:04,256][78091] Updated weights for policy 0, policy_version 96810 (0.0009) -[2023-10-12 07:22:04,629][78091] Updated weights for policy 0, policy_version 96820 (0.0009) -[2023-10-12 07:22:04,986][78091] Updated weights for policy 0, policy_version 96830 (0.0009) -[2023-10-12 07:22:05,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 197820416. Throughput: 0: 1612.5, 1: 1595.0. Samples: 49461730. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-12 07:22:05,201][77203] Avg episode reward: [(0, '59.410'), (1, '46.630')] -[2023-10-12 07:22:05,838][78123] Updated weights for policy 1, policy_version 96360 (0.0009) -[2023-10-12 07:22:06,205][78123] Updated weights for policy 1, policy_version 96370 (0.0008) -[2023-10-12 07:22:06,578][78123] Updated weights for policy 1, policy_version 96380 (0.0010) -[2023-10-12 07:22:09,237][78091] Updated weights for policy 0, policy_version 96840 (0.0010) -[2023-10-12 07:22:09,599][78091] Updated weights for policy 0, policy_version 96850 (0.0010) -[2023-10-12 07:22:09,969][78091] Updated weights for policy 0, policy_version 96860 (0.0011) -[2023-10-12 07:22:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 197885952. Throughput: 0: 1600.6, 1: 1594.8. Samples: 49480490. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-12 07:22:10,201][77203] Avg episode reward: [(0, '56.710'), (1, '47.770')] -[2023-10-12 07:22:11,105][78123] Updated weights for policy 1, policy_version 96390 (0.0009) -[2023-10-12 07:22:11,473][78123] Updated weights for policy 1, policy_version 96400 (0.0009) -[2023-10-12 07:22:11,836][78123] Updated weights for policy 1, policy_version 96410 (0.0009) -[2023-10-12 07:22:14,378][78091] Updated weights for policy 0, policy_version 96870 (0.0010) -[2023-10-12 07:22:14,757][78091] Updated weights for policy 0, policy_version 96880 (0.0007) -[2023-10-12 07:22:15,130][78091] Updated weights for policy 0, policy_version 96890 (0.0008) -[2023-10-12 07:22:15,201][77203] Fps is (10 sec: 9830.3, 60 sec: 12561.0, 300 sec: 12662.9). Total num frames: 197918720. Throughput: 0: 1593.8, 1: 1590.6. Samples: 49489852. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-12 07:22:15,202][77203] Avg episode reward: [(0, '59.080'), (1, '51.310')] -[2023-10-12 07:22:16,160][78123] Updated weights for policy 1, policy_version 96420 (0.0010) -[2023-10-12 07:22:16,530][78123] Updated weights for policy 1, policy_version 96430 (0.0009) -[2023-10-12 07:22:16,893][78123] Updated weights for policy 1, policy_version 96440 (0.0007) -[2023-10-12 07:22:19,354][78091] Updated weights for policy 0, policy_version 96900 (0.0008) -[2023-10-12 07:22:19,718][78091] Updated weights for policy 0, policy_version 96910 (0.0007) -[2023-10-12 07:22:20,093][78091] Updated weights for policy 0, policy_version 96920 (0.0008) -[2023-10-12 07:22:20,201][77203] Fps is (10 sec: 9830.4, 60 sec: 12561.1, 300 sec: 12662.9). Total num frames: 197984256. Throughput: 0: 1608.4, 1: 1583.5. Samples: 49509316. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-12 07:22:20,201][77203] Avg episode reward: [(0, '51.970'), (1, '53.720')] -[2023-10-12 07:22:21,425][78123] Updated weights for policy 1, policy_version 96450 (0.0010) -[2023-10-12 07:22:21,783][78123] Updated weights for policy 1, policy_version 96460 (0.0008) -[2023-10-12 07:22:22,152][78123] Updated weights for policy 1, policy_version 96470 (0.0008) -[2023-10-12 07:22:22,515][78123] Updated weights for policy 1, policy_version 96480 (0.0009) -[2023-10-12 07:22:24,459][78091] Updated weights for policy 0, policy_version 96930 (0.0008) -[2023-10-12 07:22:24,834][78091] Updated weights for policy 0, policy_version 96940 (0.0010) -[2023-10-12 07:22:25,199][78091] Updated weights for policy 0, policy_version 96950 (0.0009) -[2023-10-12 07:22:25,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 198049792. Throughput: 0: 1612.7, 1: 1582.7. Samples: 49528352. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-12 07:22:25,201][77203] Avg episode reward: [(0, '55.650'), (1, '60.310')] -[2023-10-12 07:22:25,573][78091] Updated weights for policy 0, policy_version 96960 (0.0007) -[2023-10-12 07:22:26,913][78123] Updated weights for policy 1, policy_version 96490 (0.0009) -[2023-10-12 07:22:27,278][78123] Updated weights for policy 1, policy_version 96500 (0.0008) -[2023-10-12 07:22:27,648][78123] Updated weights for policy 1, policy_version 96510 (0.0007) -[2023-10-12 07:22:29,773][78091] Updated weights for policy 0, policy_version 96970 (0.0010) -[2023-10-12 07:22:30,142][78091] Updated weights for policy 0, policy_version 96980 (0.0008) -[2023-10-12 07:22:30,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 198115328. Throughput: 0: 1598.0, 1: 1588.0. Samples: 49537566. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-12 07:22:30,201][77203] Avg episode reward: [(0, '53.150'), (1, '55.100')] -[2023-10-12 07:22:30,518][78091] Updated weights for policy 0, policy_version 96990 (0.0008) -[2023-10-12 07:22:31,784][78123] Updated weights for policy 1, policy_version 96520 (0.0008) -[2023-10-12 07:22:32,160][78123] Updated weights for policy 1, policy_version 96530 (0.0008) -[2023-10-12 07:22:32,521][78123] Updated weights for policy 1, policy_version 96540 (0.0009) -[2023-10-12 07:22:34,769][78091] Updated weights for policy 0, policy_version 97000 (0.0011) -[2023-10-12 07:22:35,126][78091] Updated weights for policy 0, policy_version 97010 (0.0010) -[2023-10-12 07:22:35,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 198180864. Throughput: 0: 1596.0, 1: 1591.2. Samples: 49557120. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-12 07:22:35,201][77203] Avg episode reward: [(0, '52.130'), (1, '52.210')] -[2023-10-12 07:22:35,504][78091] Updated weights for policy 0, policy_version 97020 (0.0009) -[2023-10-12 07:22:36,842][78123] Updated weights for policy 1, policy_version 96550 (0.0009) -[2023-10-12 07:22:37,205][78123] Updated weights for policy 1, policy_version 96560 (0.0008) -[2023-10-12 07:22:37,579][78123] Updated weights for policy 1, policy_version 96570 (0.0008) -[2023-10-12 07:22:39,649][78091] Updated weights for policy 0, policy_version 97030 (0.0009) -[2023-10-12 07:22:40,027][78091] Updated weights for policy 0, policy_version 97040 (0.0007) -[2023-10-12 07:22:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 198246400. Throughput: 0: 1612.3, 1: 1581.6. Samples: 49576292. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-12 07:22:40,201][77203] Avg episode reward: [(0, '52.450'), (1, '50.990')] -[2023-10-12 07:22:40,391][78091] Updated weights for policy 0, policy_version 97050 (0.0007) -[2023-10-12 07:22:42,005][78123] Updated weights for policy 1, policy_version 96580 (0.0011) -[2023-10-12 07:22:42,369][78123] Updated weights for policy 1, policy_version 96590 (0.0007) -[2023-10-12 07:22:42,732][78123] Updated weights for policy 1, policy_version 96600 (0.0009) -[2023-10-12 07:22:44,793][78091] Updated weights for policy 0, policy_version 97060 (0.0007) -[2023-10-12 07:22:45,160][78091] Updated weights for policy 0, policy_version 97070 (0.0008) -[2023-10-12 07:22:45,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 198311936. Throughput: 0: 1597.9, 1: 1588.6. Samples: 49585622. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-12 07:22:45,201][77203] Avg episode reward: [(0, '57.470'), (1, '51.660')] -[2023-10-12 07:22:45,534][78091] Updated weights for policy 0, policy_version 97080 (0.0008) -[2023-10-12 07:22:47,014][78123] Updated weights for policy 1, policy_version 96610 (0.0007) -[2023-10-12 07:22:47,377][78123] Updated weights for policy 1, policy_version 96620 (0.0009) -[2023-10-12 07:22:47,748][78123] Updated weights for policy 1, policy_version 96630 (0.0008) -[2023-10-12 07:22:48,126][78123] Updated weights for policy 1, policy_version 96640 (0.0008) -[2023-10-12 07:22:49,953][78091] Updated weights for policy 0, policy_version 97090 (0.0009) -[2023-10-12 07:22:50,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 198377472. Throughput: 0: 1599.7, 1: 1577.6. Samples: 49604706. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-12 07:22:50,202][77203] Avg episode reward: [(0, '51.060'), (1, '53.180')] -[2023-10-12 07:22:50,328][78091] Updated weights for policy 0, policy_version 97100 (0.0009) -[2023-10-12 07:22:50,695][78091] Updated weights for policy 0, policy_version 97110 (0.0008) -[2023-10-12 07:22:51,069][78091] Updated weights for policy 0, policy_version 97120 (0.0008) -[2023-10-12 07:22:52,471][78123] Updated weights for policy 1, policy_version 96650 (0.0009) -[2023-10-12 07:22:52,836][78123] Updated weights for policy 1, policy_version 96660 (0.0009) -[2023-10-12 07:22:53,198][78123] Updated weights for policy 1, policy_version 96670 (0.0009) -[2023-10-12 07:22:55,134][78091] Updated weights for policy 0, policy_version 97130 (0.0007) -[2023-10-12 07:22:55,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 198443008. Throughput: 0: 1620.7, 1: 1573.4. Samples: 49624224. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-12 07:22:55,201][77203] Avg episode reward: [(0, '51.710'), (1, '51.640')] -[2023-10-12 07:22:55,508][78091] Updated weights for policy 0, policy_version 97140 (0.0007) -[2023-10-12 07:22:55,882][78091] Updated weights for policy 0, policy_version 97150 (0.0007) -[2023-10-12 07:22:57,675][78123] Updated weights for policy 1, policy_version 96680 (0.0008) -[2023-10-12 07:22:58,049][78123] Updated weights for policy 1, policy_version 96690 (0.0008) -[2023-10-12 07:22:58,425][78123] Updated weights for policy 1, policy_version 96700 (0.0009) -[2023-10-12 07:23:00,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 198508544. Throughput: 0: 1603.6, 1: 1591.0. Samples: 49633610. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-12 07:23:00,201][77203] Avg episode reward: [(0, '53.620'), (1, '46.100')] -[2023-10-12 07:23:00,253][78091] Updated weights for policy 0, policy_version 97160 (0.0009) -[2023-10-12 07:23:00,630][78091] Updated weights for policy 0, policy_version 97170 (0.0008) -[2023-10-12 07:23:00,996][78091] Updated weights for policy 0, policy_version 97180 (0.0007) -[2023-10-12 07:23:02,801][78123] Updated weights for policy 1, policy_version 96710 (0.0009) -[2023-10-12 07:23:03,166][78123] Updated weights for policy 1, policy_version 96720 (0.0010) -[2023-10-12 07:23:03,543][78123] Updated weights for policy 1, policy_version 96730 (0.0007) -[2023-10-12 07:23:05,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 198574080. Throughput: 0: 1602.8, 1: 1575.2. Samples: 49652328. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-12 07:23:05,202][77203] Avg episode reward: [(0, '59.980'), (1, '47.490')] -[2023-10-12 07:23:05,307][78091] Updated weights for policy 0, policy_version 97190 (0.0010) -[2023-10-12 07:23:05,684][78091] Updated weights for policy 0, policy_version 97200 (0.0010) -[2023-10-12 07:23:06,060][78091] Updated weights for policy 0, policy_version 97210 (0.0009) -[2023-10-12 07:23:07,852][78123] Updated weights for policy 1, policy_version 96740 (0.0008) -[2023-10-12 07:23:08,218][78123] Updated weights for policy 1, policy_version 96750 (0.0008) -[2023-10-12 07:23:08,589][78123] Updated weights for policy 1, policy_version 96760 (0.0009) -[2023-10-12 07:23:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 198639616. Throughput: 0: 1613.0, 1: 1571.6. Samples: 49671660. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-12 07:23:10,201][77203] Avg episode reward: [(0, '56.280'), (1, '51.100')] -[2023-10-12 07:23:10,208][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000096768_99090432.pth... -[2023-10-12 07:23:10,244][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000095264_97550336.pth -[2023-10-12 07:23:10,249][77950] Saving a milestone ./train_atari/atari_hero_APPO/checkpoint_p1/milestones/checkpoint_000096768_99090432.pth -[2023-10-12 07:23:10,405][78091] Updated weights for policy 0, policy_version 97220 (0.0009) -[2023-10-12 07:23:10,782][78091] Updated weights for policy 0, policy_version 97230 (0.0010) -[2023-10-12 07:23:11,149][78091] Updated weights for policy 0, policy_version 97240 (0.0007) -[2023-10-12 07:23:11,447][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000097248_99581952.pth... -[2023-10-12 07:23:11,484][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000095744_98041856.pth -[2023-10-12 07:23:11,489][77792] Saving a milestone ./train_atari/atari_hero_APPO/checkpoint_p0/milestones/checkpoint_000097248_99581952.pth -[2023-10-12 07:23:12,996][78123] Updated weights for policy 1, policy_version 96770 (0.0008) -[2023-10-12 07:23:13,382][78123] Updated weights for policy 1, policy_version 96780 (0.0007) -[2023-10-12 07:23:13,756][78123] Updated weights for policy 1, policy_version 96790 (0.0007) -[2023-10-12 07:23:14,127][78123] Updated weights for policy 1, policy_version 96800 (0.0008) -[2023-10-12 07:23:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 198705152. Throughput: 0: 1601.1, 1: 1596.1. Samples: 49681438. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-12 07:23:15,202][77203] Avg episode reward: [(0, '54.560'), (1, '48.310')] -[2023-10-12 07:23:15,439][78091] Updated weights for policy 0, policy_version 97250 (0.0008) -[2023-10-12 07:23:15,816][78091] Updated weights for policy 0, policy_version 97260 (0.0010) -[2023-10-12 07:23:16,179][78091] Updated weights for policy 0, policy_version 97270 (0.0011) -[2023-10-12 07:23:16,557][78091] Updated weights for policy 0, policy_version 97280 (0.0010) -[2023-10-12 07:23:18,379][78123] Updated weights for policy 1, policy_version 96810 (0.0007) -[2023-10-12 07:23:18,752][78123] Updated weights for policy 1, policy_version 96820 (0.0007) -[2023-10-12 07:23:19,119][78123] Updated weights for policy 1, policy_version 96830 (0.0007) -[2023-10-12 07:23:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 198770688. Throughput: 0: 1603.6, 1: 1581.8. Samples: 49700464. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-12 07:23:20,201][77203] Avg episode reward: [(0, '54.060'), (1, '48.060')] -[2023-10-12 07:23:20,798][78091] Updated weights for policy 0, policy_version 97290 (0.0009) -[2023-10-12 07:23:21,157][78091] Updated weights for policy 0, policy_version 97300 (0.0008) -[2023-10-12 07:23:21,536][78091] Updated weights for policy 0, policy_version 97310 (0.0009) -[2023-10-12 07:23:23,382][78123] Updated weights for policy 1, policy_version 96840 (0.0009) -[2023-10-12 07:23:23,753][78123] Updated weights for policy 1, policy_version 96850 (0.0009) -[2023-10-12 07:23:24,106][78123] Updated weights for policy 1, policy_version 96860 (0.0008) -[2023-10-12 07:23:25,201][77203] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 198836224. Throughput: 0: 1607.5, 1: 1574.9. Samples: 49719500. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-12 07:23:25,201][77203] Avg episode reward: [(0, '56.990'), (1, '50.950')] -[2023-10-12 07:23:25,956][78091] Updated weights for policy 0, policy_version 97320 (0.0008) -[2023-10-12 07:23:26,327][78091] Updated weights for policy 0, policy_version 97330 (0.0008) -[2023-10-12 07:23:26,699][78091] Updated weights for policy 0, policy_version 97340 (0.0009) -[2023-10-12 07:23:28,593][78123] Updated weights for policy 1, policy_version 96870 (0.0008) -[2023-10-12 07:23:28,955][78123] Updated weights for policy 1, policy_version 96880 (0.0009) -[2023-10-12 07:23:29,326][78123] Updated weights for policy 1, policy_version 96890 (0.0010) -[2023-10-12 07:23:30,201][77203] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 12885.0). Total num frames: 198901760. Throughput: 0: 1600.2, 1: 1589.6. Samples: 49729162. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-12 07:23:30,202][77203] Avg episode reward: [(0, '55.460'), (1, '51.200')] -[2023-10-12 07:23:30,803][78091] Updated weights for policy 0, policy_version 97350 (0.0009) -[2023-10-12 07:23:31,164][78091] Updated weights for policy 0, policy_version 97360 (0.0007) -[2023-10-12 07:23:31,550][78091] Updated weights for policy 0, policy_version 97370 (0.0008) -[2023-10-12 07:23:33,563][78123] Updated weights for policy 1, policy_version 96900 (0.0009) -[2023-10-12 07:23:33,925][78123] Updated weights for policy 1, policy_version 96910 (0.0009) -[2023-10-12 07:23:34,298][78123] Updated weights for policy 1, policy_version 96920 (0.0009) -[2023-10-12 07:23:35,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 198967296. Throughput: 0: 1602.0, 1: 1592.6. Samples: 49748464. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-12 07:23:35,202][77203] Avg episode reward: [(0, '58.310'), (1, '56.120')] -[2023-10-12 07:23:35,857][78091] Updated weights for policy 0, policy_version 97380 (0.0008) -[2023-10-12 07:23:36,240][78091] Updated weights for policy 0, policy_version 97390 (0.0010) -[2023-10-12 07:23:36,613][78091] Updated weights for policy 0, policy_version 97400 (0.0009) -[2023-10-12 07:23:38,754][78123] Updated weights for policy 1, policy_version 96930 (0.0008) -[2023-10-12 07:23:39,120][78123] Updated weights for policy 1, policy_version 96940 (0.0009) -[2023-10-12 07:23:39,488][78123] Updated weights for policy 1, policy_version 96950 (0.0009) -[2023-10-12 07:23:39,848][78123] Updated weights for policy 1, policy_version 96960 (0.0009) -[2023-10-12 07:23:40,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.1, 300 sec: 12885.0). Total num frames: 199032832. Throughput: 0: 1594.8, 1: 1582.4. Samples: 49767200. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-12 07:23:40,202][77203] Avg episode reward: [(0, '60.040'), (1, '57.860')] -[2023-10-12 07:23:41,077][78091] Updated weights for policy 0, policy_version 97410 (0.0008) -[2023-10-12 07:23:41,438][78091] Updated weights for policy 0, policy_version 97420 (0.0009) -[2023-10-12 07:23:41,820][78091] Updated weights for policy 0, policy_version 97430 (0.0008) -[2023-10-12 07:23:42,194][78091] Updated weights for policy 0, policy_version 97440 (0.0007) -[2023-10-12 07:23:44,112][78123] Updated weights for policy 1, policy_version 96970 (0.0010) -[2023-10-12 07:23:44,484][78123] Updated weights for policy 1, policy_version 96980 (0.0009) -[2023-10-12 07:23:44,842][78123] Updated weights for policy 1, policy_version 96990 (0.0007) -[2023-10-12 07:23:45,201][77203] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12885.0). Total num frames: 199098368. Throughput: 0: 1591.9, 1: 1588.7. Samples: 49776740. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-12 07:23:45,202][77203] Avg episode reward: [(0, '61.400'), (1, '50.890')] -[2023-10-12 07:23:46,579][78091] Updated weights for policy 0, policy_version 97450 (0.0009) -[2023-10-12 07:23:46,955][78091] Updated weights for policy 0, policy_version 97460 (0.0009) -[2023-10-12 07:23:47,319][78091] Updated weights for policy 0, policy_version 97470 (0.0009) -[2023-10-12 07:23:49,375][78123] Updated weights for policy 1, policy_version 97000 (0.0008) -[2023-10-12 07:23:49,741][78123] Updated weights for policy 1, policy_version 97010 (0.0009) -[2023-10-12 07:23:50,112][78123] Updated weights for policy 1, policy_version 97020 (0.0009) -[2023-10-12 07:23:50,201][77203] Fps is (10 sec: 9830.6, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 199131136. Throughput: 0: 1590.8, 1: 1606.6. Samples: 49796210. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-12 07:23:50,202][77203] Avg episode reward: [(0, '61.750'), (1, '50.760')] -[2023-10-12 07:23:51,694][78091] Updated weights for policy 0, policy_version 97480 (0.0010) -[2023-10-12 07:23:52,068][78091] Updated weights for policy 0, policy_version 97490 (0.0008) -[2023-10-12 07:23:52,442][78091] Updated weights for policy 0, policy_version 97500 (0.0010) -[2023-10-12 07:23:54,458][78123] Updated weights for policy 1, policy_version 97030 (0.0008) -[2023-10-12 07:23:54,818][78123] Updated weights for policy 1, policy_version 97040 (0.0008) -[2023-10-12 07:23:55,174][78123] Updated weights for policy 1, policy_version 97050 (0.0008) -[2023-10-12 07:23:55,201][77203] Fps is (10 sec: 9830.6, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 199196672. Throughput: 0: 1590.5, 1: 1600.3. Samples: 49815246. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-12 07:23:55,201][77203] Avg episode reward: [(0, '57.470'), (1, '52.500')] -[2023-10-12 07:23:56,849][78091] Updated weights for policy 0, policy_version 97510 (0.0009) -[2023-10-12 07:23:57,207][78091] Updated weights for policy 0, policy_version 97520 (0.0008) -[2023-10-12 07:23:57,582][78091] Updated weights for policy 0, policy_version 97530 (0.0007) -[2023-10-12 07:23:59,662][78123] Updated weights for policy 1, policy_version 97060 (0.0008) -[2023-10-12 07:24:00,062][78123] Updated weights for policy 1, policy_version 97070 (0.0009) -[2023-10-12 07:24:00,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 199262208. Throughput: 0: 1587.7, 1: 1588.3. Samples: 49824356. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-12 07:24:00,201][77203] Avg episode reward: [(0, '52.760'), (1, '58.760')] -[2023-10-12 07:24:00,429][78123] Updated weights for policy 1, policy_version 97080 (0.0007) -[2023-10-12 07:24:01,543][78091] Updated weights for policy 0, policy_version 97540 (0.0008) -[2023-10-12 07:24:01,919][78091] Updated weights for policy 0, policy_version 97550 (0.0009) -[2023-10-12 07:24:02,285][78091] Updated weights for policy 0, policy_version 97560 (0.0008) -[2023-10-12 07:24:04,623][78123] Updated weights for policy 1, policy_version 97090 (0.0007) -[2023-10-12 07:24:04,997][78123] Updated weights for policy 1, policy_version 97100 (0.0009) -[2023-10-12 07:24:05,201][77203] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 199327744. Throughput: 0: 1589.5, 1: 1600.2. Samples: 49844000. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-12 07:24:05,201][77203] Avg episode reward: [(0, '53.780'), (1, '58.010')] -[2023-10-12 07:24:05,362][78123] Updated weights for policy 1, policy_version 97110 (0.0007) -[2023-10-12 07:24:05,732][78123] Updated weights for policy 1, policy_version 97120 (0.0007) -[2023-10-12 07:24:06,672][78091] Updated weights for policy 0, policy_version 97570 (0.0009) -[2023-10-12 07:24:07,046][78091] Updated weights for policy 0, policy_version 97580 (0.0008) -[2023-10-12 07:24:07,421][78091] Updated weights for policy 0, policy_version 97590 (0.0009) -[2023-10-12 07:24:07,792][78091] Updated weights for policy 0, policy_version 97600 (0.0007) -[2023-10-12 07:24:09,799][78123] Updated weights for policy 1, policy_version 97130 (0.0007) -[2023-10-12 07:24:10,171][78123] Updated weights for policy 1, policy_version 97140 (0.0008) -[2023-10-12 07:24:10,201][77203] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 199393280. Throughput: 0: 1590.9, 1: 1606.9. Samples: 49863402. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-12 07:24:10,201][77203] Avg episode reward: [(0, '57.800'), (1, '55.020')] -[2023-10-12 07:24:10,534][78123] Updated weights for policy 1, policy_version 97150 (0.0009) -[2023-10-12 07:24:12,036][78091] Updated weights for policy 0, policy_version 97610 (0.0009) -[2023-10-12 07:24:12,398][78091] Updated weights for policy 0, policy_version 97620 (0.0007) -[2023-10-12 07:24:12,771][78091] Updated weights for policy 0, policy_version 97630 (0.0007) -[2023-10-12 07:24:14,788][78123] Updated weights for policy 1, policy_version 97160 (0.0010) -[2023-10-12 07:24:15,157][78123] Updated weights for policy 1, policy_version 97170 (0.0007) -[2023-10-12 07:24:15,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 199458816. Throughput: 0: 1594.5, 1: 1595.2. Samples: 49872698. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:24:15,201][77203] Avg episode reward: [(0, '53.930'), (1, '50.610')] -[2023-10-12 07:24:15,529][78123] Updated weights for policy 1, policy_version 97180 (0.0007) -[2023-10-12 07:24:17,191][78091] Updated weights for policy 0, policy_version 97640 (0.0009) -[2023-10-12 07:24:17,560][78091] Updated weights for policy 0, policy_version 97650 (0.0007) -[2023-10-12 07:24:17,929][78091] Updated weights for policy 0, policy_version 97660 (0.0007) -[2023-10-12 07:24:19,762][78123] Updated weights for policy 1, policy_version 97190 (0.0009) -[2023-10-12 07:24:20,137][78123] Updated weights for policy 1, policy_version 97200 (0.0008) -[2023-10-12 07:24:20,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 199524352. Throughput: 0: 1588.8, 1: 1606.2. Samples: 49892240. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:24:20,202][77203] Avg episode reward: [(0, '55.300'), (1, '53.050')] -[2023-10-12 07:24:20,496][78123] Updated weights for policy 1, policy_version 97210 (0.0007) -[2023-10-12 07:24:22,262][78091] Updated weights for policy 0, policy_version 97670 (0.0009) -[2023-10-12 07:24:22,625][78091] Updated weights for policy 0, policy_version 97680 (0.0007) -[2023-10-12 07:24:22,995][78091] Updated weights for policy 0, policy_version 97690 (0.0008) -[2023-10-12 07:24:24,960][78123] Updated weights for policy 1, policy_version 97220 (0.0008) -[2023-10-12 07:24:25,201][77203] Fps is (10 sec: 13107.0, 60 sec: 12561.0, 300 sec: 12774.0). Total num frames: 199589888. Throughput: 0: 1592.8, 1: 1619.5. Samples: 49911752. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:24:25,202][77203] Avg episode reward: [(0, '56.630'), (1, '48.540')] -[2023-10-12 07:24:25,326][78123] Updated weights for policy 1, policy_version 97230 (0.0008) -[2023-10-12 07:24:25,692][78123] Updated weights for policy 1, policy_version 97240 (0.0008) -[2023-10-12 07:24:27,252][78091] Updated weights for policy 0, policy_version 97700 (0.0008) -[2023-10-12 07:24:27,634][78091] Updated weights for policy 0, policy_version 97710 (0.0007) -[2023-10-12 07:24:27,994][78091] Updated weights for policy 0, policy_version 97720 (0.0007) -[2023-10-12 07:24:30,187][78123] Updated weights for policy 1, policy_version 97250 (0.0008) -[2023-10-12 07:24:30,201][77203] Fps is (10 sec: 13107.5, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 199655424. Throughput: 0: 1607.3, 1: 1594.5. Samples: 49920822. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:24:30,201][77203] Avg episode reward: [(0, '54.760'), (1, '50.330')] -[2023-10-12 07:24:30,559][78123] Updated weights for policy 1, policy_version 97260 (0.0010) -[2023-10-12 07:24:30,928][78123] Updated weights for policy 1, policy_version 97270 (0.0007) -[2023-10-12 07:24:31,295][78123] Updated weights for policy 1, policy_version 97280 (0.0007) -[2023-10-12 07:24:32,181][78091] Updated weights for policy 0, policy_version 97730 (0.0008) -[2023-10-12 07:24:32,548][78091] Updated weights for policy 0, policy_version 97740 (0.0009) -[2023-10-12 07:24:32,914][78091] Updated weights for policy 0, policy_version 97750 (0.0008) -[2023-10-12 07:24:33,285][78091] Updated weights for policy 0, policy_version 97760 (0.0008) -[2023-10-12 07:24:35,201][77203] Fps is (10 sec: 13107.4, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 199720960. Throughput: 0: 1598.5, 1: 1596.8. Samples: 49940000. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:24:35,201][77203] Avg episode reward: [(0, '63.430'), (1, '53.370')] -[2023-10-12 07:24:35,442][78123] Updated weights for policy 1, policy_version 97290 (0.0009) -[2023-10-12 07:24:35,800][78123] Updated weights for policy 1, policy_version 97300 (0.0008) -[2023-10-12 07:24:36,172][78123] Updated weights for policy 1, policy_version 97310 (0.0009) -[2023-10-12 07:24:37,804][78091] Updated weights for policy 0, policy_version 97770 (0.0008) -[2023-10-12 07:24:38,183][78091] Updated weights for policy 0, policy_version 97780 (0.0010) -[2023-10-12 07:24:38,554][78091] Updated weights for policy 0, policy_version 97790 (0.0009) -[2023-10-12 07:24:40,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 199786496. Throughput: 0: 1595.9, 1: 1608.4. Samples: 49959436. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:24:40,201][77203] Avg episode reward: [(0, '62.240'), (1, '52.760')] -[2023-10-12 07:24:40,418][78123] Updated weights for policy 1, policy_version 97320 (0.0009) -[2023-10-12 07:24:40,790][78123] Updated weights for policy 1, policy_version 97330 (0.0010) -[2023-10-12 07:24:41,153][78123] Updated weights for policy 1, policy_version 97340 (0.0009) -[2023-10-12 07:24:42,744][78091] Updated weights for policy 0, policy_version 97800 (0.0009) -[2023-10-12 07:24:43,119][78091] Updated weights for policy 0, policy_version 97810 (0.0009) -[2023-10-12 07:24:43,487][78091] Updated weights for policy 0, policy_version 97820 (0.0009) -[2023-10-12 07:24:45,201][77203] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12774.0). Total num frames: 199852032. Throughput: 0: 1620.0, 1: 1592.0. Samples: 49968894. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:24:45,201][77203] Avg episode reward: [(0, '55.690'), (1, '54.730')] -[2023-10-12 07:24:45,661][78123] Updated weights for policy 1, policy_version 97350 (0.0008) -[2023-10-12 07:24:46,034][78123] Updated weights for policy 1, policy_version 97360 (0.0007) -[2023-10-12 07:24:46,409][78123] Updated weights for policy 1, policy_version 97370 (0.0010) -[2023-10-12 07:24:47,984][78091] Updated weights for policy 0, policy_version 97830 (0.0008) -[2023-10-12 07:24:48,359][78091] Updated weights for policy 0, policy_version 97840 (0.0007) -[2023-10-12 07:24:48,727][78091] Updated weights for policy 0, policy_version 97850 (0.0008) -[2023-10-12 07:24:50,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 199917568. Throughput: 0: 1600.5, 1: 1590.3. Samples: 49987588. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:24:50,202][77203] Avg episode reward: [(0, '54.690'), (1, '49.030')] -[2023-10-12 07:24:50,635][78123] Updated weights for policy 1, policy_version 97380 (0.0008) -[2023-10-12 07:24:50,999][78123] Updated weights for policy 1, policy_version 97390 (0.0007) -[2023-10-12 07:24:51,367][78123] Updated weights for policy 1, policy_version 97400 (0.0008) -[2023-10-12 07:24:53,044][78091] Updated weights for policy 0, policy_version 97860 (0.0009) -[2023-10-12 07:24:53,414][78091] Updated weights for policy 0, policy_version 97870 (0.0007) -[2023-10-12 07:24:53,778][78091] Updated weights for policy 0, policy_version 97880 (0.0007) -[2023-10-12 07:24:55,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 199983104. Throughput: 0: 1596.9, 1: 1591.9. Samples: 50006900. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:24:55,202][77203] Avg episode reward: [(0, '54.710'), (1, '48.820')] -[2023-10-12 07:24:55,821][78123] Updated weights for policy 1, policy_version 97410 (0.0009) -[2023-10-12 07:24:56,198][78123] Updated weights for policy 1, policy_version 97420 (0.0007) -[2023-10-12 07:24:56,563][78123] Updated weights for policy 1, policy_version 97430 (0.0007) -[2023-10-12 07:24:56,929][78123] Updated weights for policy 1, policy_version 97440 (0.0007) -[2023-10-12 07:24:58,001][78091] Updated weights for policy 0, policy_version 97890 (0.0009) -[2023-10-12 07:24:58,377][78091] Updated weights for policy 0, policy_version 97900 (0.0010) -[2023-10-12 07:24:58,749][78091] Updated weights for policy 0, policy_version 97910 (0.0008) -[2023-10-12 07:24:59,124][78091] Updated weights for policy 0, policy_version 97920 (0.0009) -[2023-10-12 07:25:00,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 200048640. Throughput: 0: 1624.9, 1: 1579.4. Samples: 50016894. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:25:00,201][77203] Avg episode reward: [(0, '53.760'), (1, '52.390')] -[2023-10-12 07:25:01,233][78123] Updated weights for policy 1, policy_version 97450 (0.0011) -[2023-10-12 07:25:01,603][78123] Updated weights for policy 1, policy_version 97460 (0.0009) -[2023-10-12 07:25:01,974][78123] Updated weights for policy 1, policy_version 97470 (0.0007) -[2023-10-12 07:25:03,147][78091] Updated weights for policy 0, policy_version 97930 (0.0008) -[2023-10-12 07:25:03,508][78091] Updated weights for policy 0, policy_version 97940 (0.0007) -[2023-10-12 07:25:03,882][78091] Updated weights for policy 0, policy_version 97950 (0.0009) -[2023-10-12 07:25:05,201][77203] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 200114176. Throughput: 0: 1612.0, 1: 1572.8. Samples: 50035558. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:25:05,201][77203] Avg episode reward: [(0, '55.130'), (1, '50.420')] -[2023-10-12 07:25:06,329][78123] Updated weights for policy 1, policy_version 97480 (0.0007) -[2023-10-12 07:25:06,689][78123] Updated weights for policy 1, policy_version 97490 (0.0010) -[2023-10-12 07:25:07,053][78123] Updated weights for policy 1, policy_version 97500 (0.0010) -[2023-10-12 07:25:08,109][78091] Updated weights for policy 0, policy_version 97960 (0.0008) -[2023-10-12 07:25:08,480][78091] Updated weights for policy 0, policy_version 97970 (0.0007) -[2023-10-12 07:25:08,843][78091] Updated weights for policy 0, policy_version 97980 (0.0008) -[2023-10-12 07:25:10,201][77203] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 200179712. Throughput: 0: 1604.9, 1: 1574.8. Samples: 50054836. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-12 07:25:10,201][77203] Avg episode reward: [(0, '52.450'), (1, '48.110')] -[2023-10-12 07:25:10,209][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000097984_100335616.pth... -[2023-10-12 07:25:10,209][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000097504_99844096.pth... -[2023-10-12 07:25:10,238][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000096480_98795520.pth -[2023-10-12 07:25:10,248][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000096032_98336768.pth -[2023-10-12 07:25:11,293][78123] Updated weights for policy 1, policy_version 97510 (0.0008) -[2023-10-12 07:25:11,669][78123] Updated weights for policy 1, policy_version 97520 (0.0007) -[2023-10-12 07:25:12,050][78123] Updated weights for policy 1, policy_version 97530 (0.0007) -[2023-10-12 07:25:13,096][78091] Updated weights for policy 0, policy_version 97990 (0.0008) -[2023-10-12 07:25:13,474][78091] Updated weights for policy 0, policy_version 98000 (0.0007) -[2023-10-12 07:25:13,851][78091] Updated weights for policy 0, policy_version 98010 (0.0007) -[2023-10-12 07:25:15,201][77203] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 200245248. Throughput: 0: 1622.4, 1: 1581.5. Samples: 50064998. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-12 07:25:15,202][77203] Avg episode reward: [(0, '56.360'), (1, '54.460')] -[2023-10-12 07:25:16,448][78123] Updated weights for policy 1, policy_version 97540 (0.0007) -[2023-10-12 07:25:16,812][78123] Updated weights for policy 1, policy_version 97550 (0.0008) -[2023-10-12 07:25:17,179][78123] Updated weights for policy 1, policy_version 97560 (0.0009) -[2023-10-12 07:25:18,192][78091] Updated weights for policy 0, policy_version 98020 (0.0010) -[2023-10-12 07:25:18,556][78091] Updated weights for policy 0, policy_version 98030 (0.0009) -[2023-10-12 07:25:18,927][78091] Updated weights for policy 0, policy_version 98040 (0.0009) -[2023-10-12 07:25:20,201][77203] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 200310784. Throughput: 0: 1616.8, 1: 1579.7. Samples: 50083844. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-12 07:25:20,201][77203] Avg episode reward: [(0, '57.680'), (1, '59.120')] -[2023-10-12 07:25:21,492][78123] Updated weights for policy 1, policy_version 97570 (0.0008) -[2023-10-12 07:25:21,870][78123] Updated weights for policy 1, policy_version 97580 (0.0009) -[2023-10-12 07:25:22,234][78123] Updated weights for policy 1, policy_version 97590 (0.0009) -[2023-10-12 07:25:22,605][78123] Updated weights for policy 1, policy_version 97600 (0.0009) -[2023-10-12 07:25:23,344][78091] Updated weights for policy 0, policy_version 98050 (0.0008) -[2023-10-12 07:25:23,724][78091] Updated weights for policy 0, policy_version 98060 (0.0007) -[2023-10-12 07:25:24,104][78091] Updated weights for policy 0, policy_version 98070 (0.0007) -[2023-10-12 07:25:24,458][78091] Updated weights for policy 0, policy_version 98080 (0.0007) -[2023-10-12 07:25:25,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 200376320. Throughput: 0: 1610.4, 1: 1575.2. Samples: 50102788. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-12 07:25:25,202][77203] Avg episode reward: [(0, '63.400'), (1, '58.740')] -[2023-10-12 07:25:27,029][78123] Updated weights for policy 1, policy_version 97610 (0.0007) -[2023-10-12 07:25:27,399][78123] Updated weights for policy 1, policy_version 97620 (0.0008) -[2023-10-12 07:25:27,760][78123] Updated weights for policy 1, policy_version 97630 (0.0008) -[2023-10-12 07:25:28,733][78091] Updated weights for policy 0, policy_version 98090 (0.0007) -[2023-10-12 07:25:29,099][78091] Updated weights for policy 0, policy_version 98100 (0.0007) -[2023-10-12 07:25:29,476][78091] Updated weights for policy 0, policy_version 98110 (0.0008) -[2023-10-12 07:25:30,201][77203] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12774.0). Total num frames: 200441856. Throughput: 0: 1614.1, 1: 1582.0. Samples: 50112720. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-12 07:25:30,201][77203] Avg episode reward: [(0, '54.880'), (1, '59.120')] -[2023-10-12 07:25:32,230][78123] Updated weights for policy 1, policy_version 97640 (0.0010) -[2023-10-12 07:25:32,601][78123] Updated weights for policy 1, policy_version 97650 (0.0009) -[2023-10-12 07:25:32,968][78123] Updated weights for policy 1, policy_version 97660 (0.0007) -[2023-10-12 07:25:33,809][78091] Updated weights for policy 0, policy_version 98120 (0.0008) -[2023-10-12 07:25:34,172][78091] Updated weights for policy 0, policy_version 98130 (0.0009) -[2023-10-12 07:25:34,545][78091] Updated weights for policy 0, policy_version 98140 (0.0008) -[2023-10-12 07:25:34,692][78130] Stopping RolloutWorker_w5... -[2023-10-12 07:25:34,692][78129] Stopping RolloutWorker_w4... -[2023-10-12 07:25:34,692][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000097664_100007936.pth... -[2023-10-12 07:25:34,692][78128] Stopping RolloutWorker_w2... -[2023-10-12 07:25:34,692][78136] Stopping RolloutWorker_w10... -[2023-10-12 07:25:34,692][78127] Stopping RolloutWorker_w3... -[2023-10-12 07:25:34,692][78130] Loop rollout_proc5_evt_loop terminating... -[2023-10-12 07:25:34,692][78129] Loop rollout_proc4_evt_loop terminating... -[2023-10-12 07:25:34,692][78137] Stopping RolloutWorker_w12... -[2023-10-12 07:25:34,692][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000098144_100499456.pth... -[2023-10-12 07:25:34,692][78136] Loop rollout_proc10_evt_loop terminating... -[2023-10-12 07:25:34,692][78128] Loop rollout_proc2_evt_loop terminating... -[2023-10-12 07:25:34,692][78138] Stopping RolloutWorker_w13... -[2023-10-12 07:25:34,692][78135] Stopping RolloutWorker_w11... -[2023-10-12 07:25:34,692][78127] Loop rollout_proc3_evt_loop terminating... -[2023-10-12 07:25:34,693][78137] Loop rollout_proc12_evt_loop terminating... -[2023-10-12 07:25:34,693][78135] Loop rollout_proc11_evt_loop terminating... -[2023-10-12 07:25:34,693][78138] Loop rollout_proc13_evt_loop terminating... -[2023-10-12 07:25:34,693][78134] Stopping RolloutWorker_w9... -[2023-10-12 07:25:34,693][77203] Component RolloutWorker_w5 stopped! -[2023-10-12 07:25:34,693][78134] Loop rollout_proc9_evt_loop terminating... -[2023-10-12 07:25:34,694][78133] Stopping RolloutWorker_w8... -[2023-10-12 07:25:34,694][78124] Stopping RolloutWorker_w0... -[2023-10-12 07:25:34,694][77203] Component RolloutWorker_w4 stopped! -[2023-10-12 07:25:34,694][78133] Loop rollout_proc8_evt_loop terminating... -[2023-10-12 07:25:34,694][78124] Loop rollout_proc0_evt_loop terminating... -[2023-10-12 07:25:34,694][77203] Component RolloutWorker_w3 stopped! -[2023-10-12 07:25:34,695][77203] Component RolloutWorker_w10 stopped! -[2023-10-12 07:25:34,696][78759] Stopping RolloutWorker_w15... -[2023-10-12 07:25:34,696][77203] Component RolloutWorker_w2 stopped! -[2023-10-12 07:25:34,697][78759] Loop rollout_proc15_evt_loop terminating... -[2023-10-12 07:25:34,697][78725] Stopping RolloutWorker_w14... -[2023-10-12 07:25:34,697][78725] Loop rollout_proc14_evt_loop terminating... -[2023-10-12 07:25:34,697][77203] Component RolloutWorker_w12 stopped! -[2023-10-12 07:25:34,697][78131] Stopping RolloutWorker_w6... -[2023-10-12 07:25:34,698][77950] Stopping Batcher_1... -[2023-10-12 07:25:34,698][78131] Loop rollout_proc6_evt_loop terminating... -[2023-10-12 07:25:34,692][77792] Stopping Batcher_0... -[2023-10-12 07:25:34,698][77203] Component Batcher_0 stopped! -[2023-10-12 07:25:34,699][77203] Component RolloutWorker_w13 stopped! -[2023-10-12 07:25:34,699][78125] Stopping RolloutWorker_w1... -[2023-10-12 07:25:34,700][78125] Loop rollout_proc1_evt_loop terminating... -[2023-10-12 07:25:34,699][77203] Component RolloutWorker_w11 stopped! -[2023-10-12 07:25:34,700][77203] Component Batcher_1 stopped! -[2023-10-12 07:25:34,701][78132] Stopping RolloutWorker_w7... -[2023-10-12 07:25:34,701][78132] Loop rollout_proc7_evt_loop terminating... -[2023-10-12 07:25:34,701][77203] Component RolloutWorker_w9 stopped! -[2023-10-12 07:25:34,701][77203] Component RolloutWorker_w8 stopped! -[2023-10-12 07:25:34,702][77203] Component RolloutWorker_w0 stopped! -[2023-10-12 07:25:34,702][77203] Component RolloutWorker_w15 stopped! -[2023-10-12 07:25:34,702][77203] Component RolloutWorker_w14 stopped! -[2023-10-12 07:25:34,703][77203] Component RolloutWorker_w6 stopped! -[2023-10-12 07:25:34,703][77203] Component RolloutWorker_w1 stopped! -[2023-10-12 07:25:34,703][77203] Component RolloutWorker_w7 stopped! -[2023-10-12 07:25:34,717][78123] Weights refcount: 2 0 -[2023-10-12 07:25:34,719][78123] Stopping InferenceWorker_p1-w0... -[2023-10-12 07:25:34,719][77203] Component InferenceWorker_p1-w0 stopped! -[2023-10-12 07:25:34,720][78123] Loop inference_proc1-0_evt_loop terminating... -[2023-10-12 07:25:34,721][78091] Weights refcount: 2 0 -[2023-10-12 07:25:34,711][77950] Loop batcher_evt_loop terminating... -[2023-10-12 07:25:34,722][78091] Stopping InferenceWorker_p0-w0... -[2023-10-12 07:25:34,722][78091] Loop inference_proc0-0_evt_loop terminating... -[2023-10-12 07:25:34,722][77203] Component InferenceWorker_p0-w0 stopped! -[2023-10-12 07:25:34,712][77792] Loop batcher_evt_loop terminating... -[2023-10-12 07:25:34,732][77950] Removing ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000096768_99090432.pth -[2023-10-12 07:25:34,736][77950] Saving ./train_atari/atari_hero_APPO/checkpoint_p1/checkpoint_000097664_100007936.pth... -[2023-10-12 07:25:34,739][77792] Removing ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000097248_99581952.pth -[2023-10-12 07:25:34,745][77792] Saving ./train_atari/atari_hero_APPO/checkpoint_p0/checkpoint_000098144_100499456.pth... -[2023-10-12 07:25:34,776][77950] Stopping LearnerWorker_p1... -[2023-10-12 07:25:34,776][77950] Loop learner_proc1_evt_loop terminating... -[2023-10-12 07:25:34,776][77203] Component LearnerWorker_p1 stopped! -[2023-10-12 07:25:34,804][77792] Stopping LearnerWorker_p0... -[2023-10-12 07:25:34,805][77792] Loop learner_proc0_evt_loop terminating... -[2023-10-12 07:25:34,804][77203] Component LearnerWorker_p0 stopped! -[2023-10-12 07:25:34,805][77203] Waiting for process learner_proc0 to stop... -[2023-10-12 07:25:35,713][77203] Waiting for process learner_proc1 to stop... -[2023-10-12 07:25:35,714][77203] Waiting for process inference_proc0-0 to join... -[2023-10-12 07:25:35,715][77203] Waiting for process inference_proc1-0 to join... -[2023-10-12 07:25:35,716][77203] Waiting for process rollout_proc0 to join... -[2023-10-12 07:25:35,717][77203] Waiting for process rollout_proc1 to join... -[2023-10-12 07:25:35,717][77203] Waiting for process rollout_proc2 to join... -[2023-10-12 07:25:35,718][77203] Waiting for process rollout_proc3 to join... -[2023-10-12 07:25:35,719][77203] Waiting for process rollout_proc4 to join... -[2023-10-12 07:25:35,719][77203] Waiting for process rollout_proc5 to join... -[2023-10-12 07:25:35,720][77203] Waiting for process rollout_proc6 to join... -[2023-10-12 07:25:35,721][77203] Waiting for process rollout_proc7 to join... -[2023-10-12 07:25:35,721][77203] Waiting for process rollout_proc8 to join... -[2023-10-12 07:25:35,722][77203] Waiting for process rollout_proc9 to join... -[2023-10-12 07:25:35,723][77203] Waiting for process rollout_proc10 to join... -[2023-10-12 07:25:35,723][77203] Waiting for process rollout_proc11 to join... -[2023-10-12 07:25:35,724][77203] Waiting for process rollout_proc12 to join... -[2023-10-12 07:25:35,724][77203] Waiting for process rollout_proc13 to join... -[2023-10-12 07:25:35,724][77203] Waiting for process rollout_proc14 to join... -[2023-10-12 07:25:35,725][77203] Waiting for process rollout_proc15 to join... -[2023-10-12 07:25:35,725][77203] Batcher 0 profile tree view: -batching: 169.9066, releasing_batches: 0.0926 -[2023-10-12 07:25:35,725][77203] Batcher 1 profile tree view: -batching: 168.1214, releasing_batches: 0.0937 -[2023-10-12 07:25:35,726][77203] InferenceWorker_p0-w0 profile tree view: -wait_policy: 0.0001 - wait_policy_total: 3192.4058 -update_model: 213.8491 - weight_update: 0.0009 -one_step: 0.0038 - handle_policy_step: 11602.0232 - deserialize: 66.7221, stack: 199.0852, obs_to_device_normalize: 2604.8385, forward: 5254.2309, prepare_outputs: 2479.5816, send_messages: 480.2616 -[2023-10-12 07:25:35,726][77203] InferenceWorker_p1-w0 profile tree view: -wait_policy: 0.0000 - wait_policy_total: 3302.3818 -update_model: 208.2144 - weight_update: 0.0008 -one_step: 0.0021 - handle_policy_step: 11501.9556 - deserialize: 65.1190, stack: 197.5257, obs_to_device_normalize: 2585.1990, forward: 5214.4056, prepare_outputs: 2454.6067, send_messages: 473.9531 -[2023-10-12 07:25:35,726][77203] Learner 0 profile tree view: -misc: 0.0190, prepare_batch: 271.3593 -train: 3654.0658 - epoch_init: 0.1849, minibatch_init: 12.8996, losses_postprocess: 901.9171, kl_divergence: 32.3712, update: 383.4224, after_optimizer: 2136.1697 - calculate_losses: 170.3932 - losses_init: 0.3740, forward_head: 59.4330, bptt_initial: 1.4397, bptt: 1.8914, tail: 38.3300, advantages_returns: 11.2399, losses: 43.8756 -[2023-10-12 07:25:35,726][77203] Learner 1 profile tree view: -misc: 0.0199, prepare_batch: 270.0159 -train: 3604.1328 - epoch_init: 0.1870, minibatch_init: 12.9522, losses_postprocess: 890.1811, kl_divergence: 31.3340, update: 381.5005, after_optimizer: 2100.5631 - calculate_losses: 170.7462 - losses_init: 0.3846, forward_head: 59.7042, bptt_initial: 1.4375, bptt: 2.0070, tail: 38.4240, advantages_returns: 11.1024, losses: 43.8974 -[2023-10-12 07:25:35,727][77203] RolloutWorker_w0 profile tree view: -wait_for_trajectories: 1.2371, enqueue_policy_requests: 409.9213, process_policy_outputs: 193.6437, env_step: 8558.4252, finalize_trajectories: 3.5119, complete_rollouts: 2.9992 -post_env_step: 380.2933 - process_env_step: 84.5246 -[2023-10-12 07:25:35,727][77203] RolloutWorker_w15 profile tree view: -wait_for_trajectories: 1.2407, enqueue_policy_requests: 406.5512, process_policy_outputs: 193.7827, env_step: 8540.3132, finalize_trajectories: 3.5415, complete_rollouts: 2.9247 -post_env_step: 381.8361 - process_env_step: 85.4500 -[2023-10-12 07:25:35,727][77203] Loop Runner_EvtLoop terminating... -[2023-10-12 07:25:35,728][77203] Runner profile tree view: -main_loop: 15740.9825 -[2023-10-12 07:25:35,728][77203] Collected {0: 100499456, 1: 100007936}, FPS: 12737.9 +version https://git-lfs.github.com/spec/v1 +oid sha256:2982bec0ddef662b37b682cebeaede2ab7c12f23fe44bff0df150581783e5ec2 +size 42512481