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.1700946348.rhmmedcatt-proliant-ml350-gen10 b/.summary/0/events.out.tfevents.1700946348.rhmmedcatt-proliant-ml350-gen10 new file mode 100644 index 0000000000000000000000000000000000000000..6001286f87a63872eb40ee0cf42a3f423150cead --- /dev/null +++ b/.summary/0/events.out.tfevents.1700946348.rhmmedcatt-proliant-ml350-gen10 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:932534f7a4d7e159fd3aebd12fc1ce6636cf80e746c288e241daf6a1148a5c41 +size 89936761 diff --git a/.summary/1/events.out.tfevents.1700946348.rhmmedcatt-proliant-ml350-gen10 b/.summary/1/events.out.tfevents.1700946348.rhmmedcatt-proliant-ml350-gen10 new file mode 100644 index 0000000000000000000000000000000000000000..242f2aa95e850342335735e572d7a8a27181c0fb --- /dev/null +++ b/.summary/1/events.out.tfevents.1700946348.rhmmedcatt-proliant-ml350-gen10 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a832c59073baa33ccc11e20859c293f148d24ba88f757b68a9cb70a31b086ee +size 47233294 diff --git a/README.md b/README.md index 61c855a863f09c37490e393edf53ab5da2e2f134..d5641326180ffad68c35a68a49ff4251a4d99560 100644 --- a/README.md +++ b/README.md @@ -15,35 +15,39 @@ model-index: type: atari_seaquest metrics: - type: mean_reward - value: 1856.00 +/- 28.00 + value: 2874.00 +/- 12.81 name: mean_reward verified: false --- -A(n) **APPO** model trained on the **atari_seaquest** 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_seaquest -``` +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_seaquest** 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_seaquest +``` + + ## Using the model To run the model after download, use the `enjoy` script corresponding to this environment: diff --git a/checkpoint_p0/best_001913536_489865216_reward_36.080.pth b/checkpoint_p0/best_001913536_489865216_reward_36.080.pth new file mode 100644 index 0000000000000000000000000000000000000000..14b62e69f432f88541b2aacca8285fc13090a0d4 --- /dev/null +++ b/checkpoint_p0/best_001913536_489865216_reward_36.080.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1ed1067b2bd0a31249b09c09290a2467c29eaa011b5378a8b01206bc82f5f6a +size 20795763 diff --git a/checkpoint_p0/checkpoint_001957968_502497280.pth b/checkpoint_p0/checkpoint_001957968_502497280.pth new file mode 100644 index 0000000000000000000000000000000000000000..4d66790431a3742f0ee8d3aaf386088a1881a514 --- /dev/null +++ b/checkpoint_p0/checkpoint_001957968_502497280.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38a58d0035c8380c345ff1dd49d6a9a6803a5f5016feba166b7b6d2df79de340 +size 20796099 diff --git a/checkpoint_p0/checkpoint_001958192_502611968.pth b/checkpoint_p0/checkpoint_001958192_502611968.pth new file mode 100644 index 0000000000000000000000000000000000000000..a720ed0f360638bdd1c2dbf5b98cd5c266d6a6f4 --- /dev/null +++ b/checkpoint_p0/checkpoint_001958192_502611968.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c430a2a191e6bcee41ec5a57210c6aeabed572404b6663986199ad4cc611a57c +size 20796099 diff --git a/checkpoint_p0/milestones/checkpoint_000012448_3186688.pth b/checkpoint_p0/milestones/checkpoint_000012448_3186688.pth new file mode 100644 index 0000000000000000000000000000000000000000..6e653e9c3fefbcbd3320c3c4f0cf8521a516d1c6 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000012448_3186688.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:997c83f821c2ea2f4ed46dbaaaa1a7c2914c90783bdf576a2148d330820bbbe1 +size 20796955 diff --git a/checkpoint_p0/milestones/checkpoint_000025184_6447104.pth b/checkpoint_p0/milestones/checkpoint_000025184_6447104.pth new file mode 100644 index 0000000000000000000000000000000000000000..d9d8c2115ae9437fe942029d468142dd8777bae9 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000025184_6447104.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8aaa7e67441686e0976dc66b19217ca4152947357e287009b7e9742e97a6a36c +size 20796955 diff --git a/checkpoint_p0/milestones/checkpoint_000037888_9699328.pth b/checkpoint_p0/milestones/checkpoint_000037888_9699328.pth new file mode 100644 index 0000000000000000000000000000000000000000..7c5efc099cf21bd7ecb216fcf652d721a630a51e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000037888_9699328.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a16cde45ed7e61871cb69314fcd751792c2739979b025b784375f2410d36e9ec +size 20796955 diff --git a/checkpoint_p0/milestones/checkpoint_000050656_12967936.pth b/checkpoint_p0/milestones/checkpoint_000050656_12967936.pth new file mode 100644 index 0000000000000000000000000000000000000000..31406dc3f2246bbaf17501d0d8d7e3063187e64b --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000050656_12967936.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:288bc5336cab62298208a2c4292088484ae19f5ce89892e2557ae4263034b2e6 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000063456_16244736.pth b/checkpoint_p0/milestones/checkpoint_000063456_16244736.pth new file mode 100644 index 0000000000000000000000000000000000000000..4ab64457066ebef8960884eb8cdc8f151626b2b9 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000063456_16244736.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36d9691a94bb3a5d07fbb3edbaef92a8379c96bf933a4abb2c706e2ae9e6c3b5 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000076224_19513344.pth b/checkpoint_p0/milestones/checkpoint_000076224_19513344.pth new file mode 100644 index 0000000000000000000000000000000000000000..ac226aafaf28c0168b962e6678f8e0e9f3838521 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000076224_19513344.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2787925f7c09a55ec7c3657362ee6f2d555223831d6d1cdc5c7f7bb5a91cd32 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000088992_22781952.pth b/checkpoint_p0/milestones/checkpoint_000088992_22781952.pth new file mode 100644 index 0000000000000000000000000000000000000000..b90f8db0f681ea5427739ccb2d9dd0cdb3a99670 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000088992_22781952.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de68cccaccca6f27e7a181790fd9df51e27c637c69eb23ace922b93777587f7a +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000101792_26058752.pth b/checkpoint_p0/milestones/checkpoint_000101792_26058752.pth new file mode 100644 index 0000000000000000000000000000000000000000..0e509bcf29d7f5741cad20ab06d32d1f1dd7e149 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000101792_26058752.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:624a2218f55d0356913b4c03ae610506c3fd450d1f690413c8c518baeaea766b +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000114144_29220864.pth b/checkpoint_p0/milestones/checkpoint_000114144_29220864.pth new file mode 100644 index 0000000000000000000000000000000000000000..22a52981358fad371e49b60a53e390e5a9af5576 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000114144_29220864.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb889dba2917d77e57cf7fcbb2869bd80a6e7a1369d0580c1727f3d9f3b1429d +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000126720_32440320.pth b/checkpoint_p0/milestones/checkpoint_000126720_32440320.pth new file mode 100644 index 0000000000000000000000000000000000000000..e1839dd0305c7b4cce1d62b5592005ce08445426 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000126720_32440320.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80b194f4e46ca8c17447d22a45a7c723cd079e970b73e3bab870d8728c89ba30 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000139584_35733504.pth b/checkpoint_p0/milestones/checkpoint_000139584_35733504.pth new file mode 100644 index 0000000000000000000000000000000000000000..6adac93f53276e0d1f3568d8022879e146fc162b --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000139584_35733504.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb48d7cbc4345938a02f9cf3ec14114e11d5a8a79264cb88e7a210c21e87af83 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000152320_38993920.pth b/checkpoint_p0/milestones/checkpoint_000152320_38993920.pth new file mode 100644 index 0000000000000000000000000000000000000000..18b8954c1c260da017269bf4eea610a933de61bd --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000152320_38993920.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca05d120a3da29960db5038cf015115eaa2c9d026b639e6c3883226384d61884 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000165216_42295296.pth b/checkpoint_p0/milestones/checkpoint_000165216_42295296.pth new file mode 100644 index 0000000000000000000000000000000000000000..02f3b30a0f0cf3e0782ad4783101d4c6a92d19dc --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000165216_42295296.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:116ce2601aa92a69a393cb9bc8a7bb95c6cfd710c3e2d2eeba9484717031c607 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000178112_45596672.pth b/checkpoint_p0/milestones/checkpoint_000178112_45596672.pth new file mode 100644 index 0000000000000000000000000000000000000000..ce2562832ad23a279e5988b077bd5f36e457dabc --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000178112_45596672.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:480d35abd84b2a0587fa0927fa4e144d3b275de9db2627e3d261c7f21b9956e4 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000191040_48906240.pth b/checkpoint_p0/milestones/checkpoint_000191040_48906240.pth new file mode 100644 index 0000000000000000000000000000000000000000..e3e0b2712bf20b4fc789de7d20a667f8101975e7 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000191040_48906240.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89ba7eef1bcd95b2ff16b4f056a7f54df32a7907f3bfd4075ea254c065879914 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000204000_52224000.pth b/checkpoint_p0/milestones/checkpoint_000204000_52224000.pth new file mode 100644 index 0000000000000000000000000000000000000000..b628224139fd7e9bae95a248f5c74ed83a1e4924 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000204000_52224000.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a7a41d371da2123e1a3ac43c8c9e846ac8114e8eeac49ea4a17e0c2b51bc64e +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000216928_55533568.pth b/checkpoint_p0/milestones/checkpoint_000216928_55533568.pth new file mode 100644 index 0000000000000000000000000000000000000000..d80114cb8c07808e1438c119d3385eb5e59716ec --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000216928_55533568.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04d99383c907ececbfccfc74c22649717a5a31eb094b3b15cda6c7caa14d8753 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000229856_58843136.pth b/checkpoint_p0/milestones/checkpoint_000229856_58843136.pth new file mode 100644 index 0000000000000000000000000000000000000000..f79a0db74d785ac017822265e1f36ac3f1d43abd --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000229856_58843136.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6965e109e1397ca88c0bc99b6c35b80af6b7fc7d0d54c756e8dac73870628b3d +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000242752_62144512.pth b/checkpoint_p0/milestones/checkpoint_000242752_62144512.pth new file mode 100644 index 0000000000000000000000000000000000000000..1f6563bdd0b213173800694d983fcef07a3d6786 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000242752_62144512.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6d440ac52d10354bf46486728d56f90c02316970a885c5093a759a812b5895e +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000255616_65437696.pth b/checkpoint_p0/milestones/checkpoint_000255616_65437696.pth new file mode 100644 index 0000000000000000000000000000000000000000..e22e2a2f6584abdf7033e5b48ffed982bf2b1a45 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000255616_65437696.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dce40f7056430a2555d2b66bf3c67a1d850165b59f6ba91252bf39d059f7f001 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000268512_68739072.pth b/checkpoint_p0/milestones/checkpoint_000268512_68739072.pth new file mode 100644 index 0000000000000000000000000000000000000000..d1890eea0fa4de80cba1b0403512f1f30f56debf --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000268512_68739072.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8401f7d55f27ef840c35bb714b7d9f35660f90af989ed78509bcf4d41ea56f77 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000281376_72032256.pth b/checkpoint_p0/milestones/checkpoint_000281376_72032256.pth new file mode 100644 index 0000000000000000000000000000000000000000..a3ae54f7d6c049f4469f4060c66b5abcafa9f587 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000281376_72032256.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02424c61e2cfc10ad851429d9cc344fce44f25d6bfea652c40e69efbfc94f72a +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000294304_75341824.pth b/checkpoint_p0/milestones/checkpoint_000294304_75341824.pth new file mode 100644 index 0000000000000000000000000000000000000000..0c006bfb5cbbc2f976917e98335c5a631d07479c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000294304_75341824.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0b1045f56ef76a7ab9e504bdc5179ea69c2336b4d11ad8959ff5fb133a9d9fe +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000307168_78635008.pth b/checkpoint_p0/milestones/checkpoint_000307168_78635008.pth new file mode 100644 index 0000000000000000000000000000000000000000..0c1e0ff0e2f9bea7271e0350aee32dda95445340 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000307168_78635008.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a00e7aeb5525dcf4aa6f5a3a6e5b6cad33bed787bd9b3805dcf7ea7a4e243190 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000320064_81936384.pth b/checkpoint_p0/milestones/checkpoint_000320064_81936384.pth new file mode 100644 index 0000000000000000000000000000000000000000..06394baee7a3b85319fd691a301eb44dd9d9e518 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000320064_81936384.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:545a24d96f68ecbbb458c30bd9a709c6162a04937b42f6e817f31887b5e356b1 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000332928_85229568.pth b/checkpoint_p0/milestones/checkpoint_000332928_85229568.pth new file mode 100644 index 0000000000000000000000000000000000000000..b203a740401f9a4eec5a9e2b6ea11c301fa0e3aa --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000332928_85229568.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9fe2218212353e734d4e67363e1716e1abb79824a798334e9cba595eb16c567 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000345792_88522752.pth b/checkpoint_p0/milestones/checkpoint_000345792_88522752.pth new file mode 100644 index 0000000000000000000000000000000000000000..ec7cacc27e185d41bbd2d11d1e7b2d03eb22ee7f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000345792_88522752.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb747b859e71fe89af4268c65532d9799a349fdd1bab58ef2be256ff7e6ac2be +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000358720_91832320.pth b/checkpoint_p0/milestones/checkpoint_000358720_91832320.pth new file mode 100644 index 0000000000000000000000000000000000000000..6579fd55ba83202a686fe08e263c2e5d1ea4b931 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000358720_91832320.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:302ee1367aa9a4ea44b5e8d105edb93499400be56906204c2b0f52a587b01b63 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000371616_95133696.pth b/checkpoint_p0/milestones/checkpoint_000371616_95133696.pth new file mode 100644 index 0000000000000000000000000000000000000000..cef1452ec717153ac444d88579a447c450eebdc9 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000371616_95133696.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f25c06a684d779bf4933830644528b8f7fb2348dbeb2d4863a299a0e1e581224 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000384448_98418688.pth b/checkpoint_p0/milestones/checkpoint_000384448_98418688.pth new file mode 100644 index 0000000000000000000000000000000000000000..15644e679fef8d700e850f9cd79260520792a0ab --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000384448_98418688.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86bf2121ad320946f7dd79837203b92f572de940b709d40f58d50aa007727a50 +size 20797011 diff --git a/checkpoint_p0/milestones/checkpoint_000397280_101703680.pth b/checkpoint_p0/milestones/checkpoint_000397280_101703680.pth new file mode 100644 index 0000000000000000000000000000000000000000..91ae6d3986fed5a08f3c10d7bdad2cd19a2bbc0c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000397280_101703680.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25ab7f733d9f20d565ad2806fdcb0a4ea3e3aa3605df01f6a03bbefc1f662af8 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000410144_104996864.pth b/checkpoint_p0/milestones/checkpoint_000410144_104996864.pth new file mode 100644 index 0000000000000000000000000000000000000000..d42f48564139a2da779d0ac025d55f7c08870015 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000410144_104996864.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d82aea8dde801cc633ccc51f43bb17a563f147c732c87a6d6317a138fee44ea4 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000422976_108281856.pth b/checkpoint_p0/milestones/checkpoint_000422976_108281856.pth new file mode 100644 index 0000000000000000000000000000000000000000..dc1ecd0c8b83dedc973b3437df2a638df2b4a482 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000422976_108281856.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8973e3bbdbe08e206098cd6b30f1aefa2cb57c65e2cc7d789c2c7ac57bfbc7f +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000435808_111566848.pth b/checkpoint_p0/milestones/checkpoint_000435808_111566848.pth new file mode 100644 index 0000000000000000000000000000000000000000..deb8d3bb3ef46b2aa4a4b4298a7987580c0aa8d2 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000435808_111566848.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6090a3a7e1eb7d0c276ef41ae8a0261f64dbdb7760723a75455b034b990efdc3 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000448608_114843648.pth b/checkpoint_p0/milestones/checkpoint_000448608_114843648.pth new file mode 100644 index 0000000000000000000000000000000000000000..b586b34919c626b166ff063b1069290f0fcc28ce --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000448608_114843648.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f27ea6678f0033611a18a7f25ecbad366628e81f414b0e4d1dfa42be16e7afaf +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000461280_118087680.pth b/checkpoint_p0/milestones/checkpoint_000461280_118087680.pth new file mode 100644 index 0000000000000000000000000000000000000000..dd2c95d060a6b0c494538c63717b97cc04385a1f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000461280_118087680.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba2ad6b1deea74f65345754f31f546056393da13bc3fede41c268cd66753a555 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000474080_121364480.pth b/checkpoint_p0/milestones/checkpoint_000474080_121364480.pth new file mode 100644 index 0000000000000000000000000000000000000000..0bddd0178238962805cdba041d2fbfbc7a0a1334 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000474080_121364480.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2260efd75e82a15a2c946514a997307def18ac7d2632e523b139d614cd8f4ff4 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000486816_124624896.pth b/checkpoint_p0/milestones/checkpoint_000486816_124624896.pth new file mode 100644 index 0000000000000000000000000000000000000000..313ee62dfd1d6319263d34612e6f13210d1f930c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000486816_124624896.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:575c8b8b3fd40a13a9f5f48de8a53fd8965084dc4f50001b911db5dc7ebc1318 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000499520_127877120.pth b/checkpoint_p0/milestones/checkpoint_000499520_127877120.pth new file mode 100644 index 0000000000000000000000000000000000000000..922f6512b5db7a2427b23a504482265fed314142 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000499520_127877120.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a59c508a82ad3ddcd79b0f8321ed3cf54b470864711eec8c575445355c5ce3cc +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000512288_131145728.pth b/checkpoint_p0/milestones/checkpoint_000512288_131145728.pth new file mode 100644 index 0000000000000000000000000000000000000000..8dcff63828d9ef99ff2a23d438d7aeb0e04a12e1 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000512288_131145728.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a72cc99c2e655803857c63a369e6da12dfe3c8d65b794b5f210718f90dfb178b +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000525024_134406144.pth b/checkpoint_p0/milestones/checkpoint_000525024_134406144.pth new file mode 100644 index 0000000000000000000000000000000000000000..4fa526d83507e0391ad2f454438fb28bc5a1d712 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000525024_134406144.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fd945df16d7d2dd4fdf7a36863b84f36ece8dc6542ef689a16b98823d14262b +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000537824_137682944.pth b/checkpoint_p0/milestones/checkpoint_000537824_137682944.pth new file mode 100644 index 0000000000000000000000000000000000000000..d7bb3242a8b377f1afd26886323b756cc1e67972 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000537824_137682944.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42a5d7f96a8260bfe53f7897c615071292644931788d76269d067f10d18b77a1 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000550624_140959744.pth b/checkpoint_p0/milestones/checkpoint_000550624_140959744.pth new file mode 100644 index 0000000000000000000000000000000000000000..992baf3e69d49256c640f3a60473242791806c25 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000550624_140959744.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d22d26d10a6f83407d449c9e5116fa82ea1c911205d8be65f466cb99f6c00842 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000563392_144228352.pth b/checkpoint_p0/milestones/checkpoint_000563392_144228352.pth new file mode 100644 index 0000000000000000000000000000000000000000..00cb451ddc98c286f4251be1b767d9d6441aaa2e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000563392_144228352.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9893c933a8c66b6595f476aea89d77e8ba39bac9f565c3a65b6a40be3900b023 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000576128_147488768.pth b/checkpoint_p0/milestones/checkpoint_000576128_147488768.pth new file mode 100644 index 0000000000000000000000000000000000000000..f8ba15f10d6a181b5a41c37d8289da1b04f1a87e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000576128_147488768.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4ad56e7398bb3a118d2018f52bf676481eef033d42f4bb3bc1e327b481b0efa +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000588960_150773760.pth b/checkpoint_p0/milestones/checkpoint_000588960_150773760.pth new file mode 100644 index 0000000000000000000000000000000000000000..5a200d402074d0f828fe3034276638fa601cf3ce --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000588960_150773760.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd2f0f0fb0fd7bc429988f4a90e23189cd1101370bb256812cc39a88bd406006 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000601632_154017792.pth b/checkpoint_p0/milestones/checkpoint_000601632_154017792.pth new file mode 100644 index 0000000000000000000000000000000000000000..0522dc968a9f52065476d059834ae07d302b8183 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000601632_154017792.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67bd2f4acc55689fa7c89b16cdf0f54257bc474f74ecf4c5a965e9b4f97fc8e9 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000614432_157294592.pth b/checkpoint_p0/milestones/checkpoint_000614432_157294592.pth new file mode 100644 index 0000000000000000000000000000000000000000..e0a2dce9807055cabd9d8eccddd2921f313113fe --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000614432_157294592.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60ccd1a914ca1eac23919416378feb2a77321cc88262c0c062d91738c00476f5 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000627264_160579584.pth b/checkpoint_p0/milestones/checkpoint_000627264_160579584.pth new file mode 100644 index 0000000000000000000000000000000000000000..f29ab45349bd3139e978b51816377d0d328dde28 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000627264_160579584.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f165f4991cd66ab674ab4ae4c189921cf04f4c73acbe0ef5211cbc914a2462f8 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000640192_163889152.pth b/checkpoint_p0/milestones/checkpoint_000640192_163889152.pth new file mode 100644 index 0000000000000000000000000000000000000000..a69d2a18fb797230fa92b790f485a5b57637b0ee --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000640192_163889152.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fbb92f749d7afda1ac15c295930cac4a8e78a7a291edb5f20c8a2296c255bc5 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000653056_167182336.pth b/checkpoint_p0/milestones/checkpoint_000653056_167182336.pth new file mode 100644 index 0000000000000000000000000000000000000000..a4e5d371ebe8d349e542db580492bab9dcf1d9ed --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000653056_167182336.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8eb9a46ee2e28cbaa9e4a55ed2213fe39497e9ef161819268b0825f45c98ffa +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000665984_170491904.pth b/checkpoint_p0/milestones/checkpoint_000665984_170491904.pth new file mode 100644 index 0000000000000000000000000000000000000000..2ee6faa52bbf2a2a71f0b99913073fc1f8cdc895 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000665984_170491904.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0727804e994534210ac8b2f3100d37f18ee4b8031c04908d451aac9d8827bc9 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000678880_173793280.pth b/checkpoint_p0/milestones/checkpoint_000678880_173793280.pth new file mode 100644 index 0000000000000000000000000000000000000000..67372ee828ab1982ed5d6c16329437bcb834be35 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000678880_173793280.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db92b1a23deb9d339222cc7dea819a796c0a1de723dcc03d7020af89a130f1b8 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000691744_177086464.pth b/checkpoint_p0/milestones/checkpoint_000691744_177086464.pth new file mode 100644 index 0000000000000000000000000000000000000000..d75d9ebe12516279cb670950f0273a2340907078 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000691744_177086464.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d824744e155b7d24221b1c273b7507da7c11a6e876bb5cccf7c8add9d1109852 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000704608_180379648.pth b/checkpoint_p0/milestones/checkpoint_000704608_180379648.pth new file mode 100644 index 0000000000000000000000000000000000000000..04e285d0cb40111ca3b8089a51408baf61b29b27 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000704608_180379648.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9e582f8f5f913341d9abc50cdea16f68c6d426df3448fb7023a7af7dcb6e525 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000717568_183697408.pth b/checkpoint_p0/milestones/checkpoint_000717568_183697408.pth new file mode 100644 index 0000000000000000000000000000000000000000..9f981faac8aabe9ffb6cf639c5fc228e00a808ca --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000717568_183697408.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12d196de4b19ce275fd54d0a9878d606e2507b27c60e11abd419ff8cbe961db2 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000730464_186998784.pth b/checkpoint_p0/milestones/checkpoint_000730464_186998784.pth new file mode 100644 index 0000000000000000000000000000000000000000..4167b21b0c4efec8a7de3a55613074e320ba2442 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000730464_186998784.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6ba696cc73c258f328b41c087b002d548d05b8f485a1c75795cd190173ea2e6 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000743392_190308352.pth b/checkpoint_p0/milestones/checkpoint_000743392_190308352.pth new file mode 100644 index 0000000000000000000000000000000000000000..33414842c1eecf556a14e3328c4facc8b4c3d28d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000743392_190308352.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd3a30ce0b51824783a7aa693b1dd77db918e9bfa768ceba2db639de82ee33cd +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000756288_193609728.pth b/checkpoint_p0/milestones/checkpoint_000756288_193609728.pth new file mode 100644 index 0000000000000000000000000000000000000000..b2eb30fc8f53583ff10fb2bf894a152df657c523 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000756288_193609728.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:add8a69cc8164f75ec503423eba5210b78f2fd2ca3615ebd86ce7d876ed13f67 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000769120_196894720.pth b/checkpoint_p0/milestones/checkpoint_000769120_196894720.pth new file mode 100644 index 0000000000000000000000000000000000000000..936df72c4636855df78dfc982d1cc9fedbd2b8f0 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000769120_196894720.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef4b0584d70d686633dbe5851491defb7b230b0c3754dd8e21158ec157e57b1e +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000782016_200196096.pth b/checkpoint_p0/milestones/checkpoint_000782016_200196096.pth new file mode 100644 index 0000000000000000000000000000000000000000..556d2f9f80e0a684aa42fd76beb5b4f13ffe526a --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000782016_200196096.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8044a63cb6ff85aa30174a1b75d0f0728e91b35a0b7122a008e90bb129c3469a +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000794912_203497472.pth b/checkpoint_p0/milestones/checkpoint_000794912_203497472.pth new file mode 100644 index 0000000000000000000000000000000000000000..ae8595772ac6be52dccba1a85f78faf9102d5f03 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000794912_203497472.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0877c94ddeba515cab80874ecb21ce7011d2a0ae498cdd1897a894c024fe74f +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000807808_206798848.pth b/checkpoint_p0/milestones/checkpoint_000807808_206798848.pth new file mode 100644 index 0000000000000000000000000000000000000000..e0a69174bc074ab6369441171d6dd25fa0ac2470 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000807808_206798848.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71586c909547aceb65d3ec1b07dc2a3aa107af25a33ae851ecfd8b2be2d7d27f +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000820672_210092032.pth b/checkpoint_p0/milestones/checkpoint_000820672_210092032.pth new file mode 100644 index 0000000000000000000000000000000000000000..52ea92dc4196754dfddd581d1dcbe7a637efa7e2 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000820672_210092032.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e356b870bca402452ba5e41a952a7affbe0d04104ae83fee27bb5fe1a8aba2b0 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000833568_213393408.pth b/checkpoint_p0/milestones/checkpoint_000833568_213393408.pth new file mode 100644 index 0000000000000000000000000000000000000000..4e0cc685fed052acc7e0bd41fb85459291ac4024 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000833568_213393408.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42aa864e388b70659b00f2bdc9743d5b09a2331d14394534bc8f2f4354a2f651 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000846464_216694784.pth b/checkpoint_p0/milestones/checkpoint_000846464_216694784.pth new file mode 100644 index 0000000000000000000000000000000000000000..733005d2692df4de47a18cb50691dca1d9898b8f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000846464_216694784.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e5018da282173db6dfb61f6087dd9d0966a1f743dcf9e90675799d4def87fba +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000859360_219996160.pth b/checkpoint_p0/milestones/checkpoint_000859360_219996160.pth new file mode 100644 index 0000000000000000000000000000000000000000..9eb231628c0c7fd581e6fe4f96215ee4ebaad5e2 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000859360_219996160.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e63163c648f7a5c8efd7fcc7f72a992796307c8a55486a36a2b40503c2603b45 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000872224_223289344.pth b/checkpoint_p0/milestones/checkpoint_000872224_223289344.pth new file mode 100644 index 0000000000000000000000000000000000000000..f66d1111d9cf7bc250c86ea0bf79449e51057e8f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000872224_223289344.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7a9d6b5aef2ac7e6c8deb1a0749aae0f355be80c50c4c69985eda065286131b +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000885120_226590720.pth b/checkpoint_p0/milestones/checkpoint_000885120_226590720.pth new file mode 100644 index 0000000000000000000000000000000000000000..4acad0a6837d620f7146da8915affa2c114f56b8 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000885120_226590720.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:039202f9d1151c19969e2f7d3ca46383417c10c04956a23eda9c570b70fc64bb +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000897984_229883904.pth b/checkpoint_p0/milestones/checkpoint_000897984_229883904.pth new file mode 100644 index 0000000000000000000000000000000000000000..1080bb3a3cb214c6fb02e8ced4bb5199cd8ec5c9 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000897984_229883904.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea104596f1a2353094a5218ebb71ab2fe9ca8fee35139c86781ff75345c9e1e7 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000910912_233193472.pth b/checkpoint_p0/milestones/checkpoint_000910912_233193472.pth new file mode 100644 index 0000000000000000000000000000000000000000..13ff678e85d363f588eb9d80a796593dcd456ee1 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000910912_233193472.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39c3f3c2d4b7ab9737a34c10247153575b286c175883d03f23cb90fbdd0196aa +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000923616_236445696.pth b/checkpoint_p0/milestones/checkpoint_000923616_236445696.pth new file mode 100644 index 0000000000000000000000000000000000000000..c80eeab5317d748aeece04de22c58e900d72ac4c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000923616_236445696.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a82c883a7b5038669d35bf91a5d769ff05be27708030b7a069ff21c9a485db73 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000936320_239697920.pth b/checkpoint_p0/milestones/checkpoint_000936320_239697920.pth new file mode 100644 index 0000000000000000000000000000000000000000..8f2edd8103ccfd4f7bae9570301e5edbd05e0ed1 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000936320_239697920.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4a94596f91127eb389566d961aca228e5ba4fca309ba5442f8586b86e1e9e94 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000949024_242950144.pth b/checkpoint_p0/milestones/checkpoint_000949024_242950144.pth new file mode 100644 index 0000000000000000000000000000000000000000..2232b0d2e5a198a91a1842cfa556e6d59e645a60 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000949024_242950144.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fea13b4531e1c4c4f5f00af6f4b41ae7be0d0fb6986b15442910f258157313e +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000961728_246202368.pth b/checkpoint_p0/milestones/checkpoint_000961728_246202368.pth new file mode 100644 index 0000000000000000000000000000000000000000..df4482d478bb57cc6e6cfd41a338cd004cdbbb8d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000961728_246202368.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57e00cb67ae26ac9433e6a0bf5c96ea368170cabf9a849692c892d1e88d7d15d +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000974528_249479168.pth b/checkpoint_p0/milestones/checkpoint_000974528_249479168.pth new file mode 100644 index 0000000000000000000000000000000000000000..996e9a696878c23701e4b030111d944bc733a97b --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000974528_249479168.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bcf5c2ae5ce53f133d169c2a505785037a05abebcbf32356fe6548b1677dd82 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_000987328_252755968.pth b/checkpoint_p0/milestones/checkpoint_000987328_252755968.pth new file mode 100644 index 0000000000000000000000000000000000000000..8cad2d26ddfecf7c9e3b7108b2efcc23b5d18cf2 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000987328_252755968.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25018a3e66f3ccbc60e86dfff0d8ca346297738347b6968fb8b65a5f3d98b638 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001000096_256024576.pth b/checkpoint_p0/milestones/checkpoint_001000096_256024576.pth new file mode 100644 index 0000000000000000000000000000000000000000..24a227ab1453e64495aadd094938cfe60482e89c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001000096_256024576.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:561f75201810813ebe10779ab72bd348ddb2e4ec606e8e02bbb2c72712911124 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001012928_259309568.pth b/checkpoint_p0/milestones/checkpoint_001012928_259309568.pth new file mode 100644 index 0000000000000000000000000000000000000000..a5d88e3adbefe0713d41702d353b8d85032c64be --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001012928_259309568.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15ce57c9dafa44f64e0c2dba1d85fae7e6ff8de8ea5046a68fb9c2fe7caa9879 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001025696_262578176.pth b/checkpoint_p0/milestones/checkpoint_001025696_262578176.pth new file mode 100644 index 0000000000000000000000000000000000000000..d81bb0657fd98244d628383d7d12ee3d34e18b96 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001025696_262578176.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f0a752e930a119e7caae0f88d8a67bf4a589d3285f2559fcaee2f52dce4ca55 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001038208_265781248.pth b/checkpoint_p0/milestones/checkpoint_001038208_265781248.pth new file mode 100644 index 0000000000000000000000000000000000000000..4c89cae3a25dbc19afc34cf37be8c23a9fef2a63 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001038208_265781248.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9be97925daa1cd8f3b20c2fc35eb71c9725bcaa93955551e239b352cb6d61ad2 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001050912_269033472.pth b/checkpoint_p0/milestones/checkpoint_001050912_269033472.pth new file mode 100644 index 0000000000000000000000000000000000000000..4324f0ab2d2613a8a0d72e648949f585ac848d4d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001050912_269033472.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db7599fb44a7504555f0f69952a11dcc3938346d2f1eae69e4ba4cb56221d503 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001063680_272302080.pth b/checkpoint_p0/milestones/checkpoint_001063680_272302080.pth new file mode 100644 index 0000000000000000000000000000000000000000..f26ed0c853b5a0aee5450d59edc6ab422a06558a --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001063680_272302080.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8151490c5e9cd6814476cacebb8c2280feb371fcac625546da9fb886d98a5ad5 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001076480_275578880.pth b/checkpoint_p0/milestones/checkpoint_001076480_275578880.pth new file mode 100644 index 0000000000000000000000000000000000000000..1cede25d26c2894950d6e1df79bc97e2e23b1c20 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001076480_275578880.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b15f5737bc987a028c7d0a0fade6438d170ffb27c309c38d6a9cfa1262b63f4a +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001089312_278863872.pth b/checkpoint_p0/milestones/checkpoint_001089312_278863872.pth new file mode 100644 index 0000000000000000000000000000000000000000..ae2e52e6a131f4e6ee1cbfb8e7250871f4b84a3d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001089312_278863872.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec5b963b84dd55c606f97690d3d92ee85decdb7c43fe1e93fab3b81b5fede6bc +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001102208_282165248.pth b/checkpoint_p0/milestones/checkpoint_001102208_282165248.pth new file mode 100644 index 0000000000000000000000000000000000000000..b719fadb225db8b9ae6f6eaac6a3991f7815fb20 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001102208_282165248.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3cf056b9c5b07c0fd70a2df0815b891dc8b923fe7225febd37d375a81115f67 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001115104_285466624.pth b/checkpoint_p0/milestones/checkpoint_001115104_285466624.pth new file mode 100644 index 0000000000000000000000000000000000000000..8f29ff27b2ef451ebbaf96cdf1af748c4129045e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001115104_285466624.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:220185a990404aa3c947903a61efbd4135e6f2a93803e5dfc363ca4afe98abcc +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001127968_288759808.pth b/checkpoint_p0/milestones/checkpoint_001127968_288759808.pth new file mode 100644 index 0000000000000000000000000000000000000000..8f59c08e346bf0e5801ed36ca6e075736dbd81c0 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001127968_288759808.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46c9641eb248028877cc51c843eebf94e7355a3625296a7f763ad3d736627bda +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001140832_292052992.pth b/checkpoint_p0/milestones/checkpoint_001140832_292052992.pth new file mode 100644 index 0000000000000000000000000000000000000000..cbb403f787f897629875224c4bbf0f15839442a5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001140832_292052992.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc96eec6ce4aa0f852cb843f38005f97aa5bea50a1393bb90155c4c037b69954 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001153632_295329792.pth b/checkpoint_p0/milestones/checkpoint_001153632_295329792.pth new file mode 100644 index 0000000000000000000000000000000000000000..86f91a6db76b4b9e1bdda7027f85fade40ddf80f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001153632_295329792.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d07fc99343446efd71617ff8b638c7cb15d6ea7ea7b85457a01b0cc6461e5028 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001166528_298631168.pth b/checkpoint_p0/milestones/checkpoint_001166528_298631168.pth new file mode 100644 index 0000000000000000000000000000000000000000..f46dc0e6eae6c0b1718ae5ebc35ae04f0a51238c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001166528_298631168.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c16ff6803f6a97c9960926af0f963a1ff1022e179cdbf407953eb313b9a71955 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001179360_301916160.pth b/checkpoint_p0/milestones/checkpoint_001179360_301916160.pth new file mode 100644 index 0000000000000000000000000000000000000000..15556d829d7a8024bdb55e8e1386d5f8c4ecc466 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001179360_301916160.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60e32424958cbfd3c86338418ab63090096518825d57914c0358783200acce74 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001192256_305217536.pth b/checkpoint_p0/milestones/checkpoint_001192256_305217536.pth new file mode 100644 index 0000000000000000000000000000000000000000..b63b18a7b3fcf7f9f60975286a27c013532f58f1 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001192256_305217536.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a8aaf05fef510500cd37c9187869428837dea94a465bc1a6f3de63dcee2081e +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001205152_308518912.pth b/checkpoint_p0/milestones/checkpoint_001205152_308518912.pth new file mode 100644 index 0000000000000000000000000000000000000000..a4eefb4185804b4263c9512932d9b3cb13128655 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001205152_308518912.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5999aabe15440789c97607d5858e8a154ae73ee14c376074422dcc9ded8833ef +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001218016_311812096.pth b/checkpoint_p0/milestones/checkpoint_001218016_311812096.pth new file mode 100644 index 0000000000000000000000000000000000000000..7fdedc4eabce7adfabb059a80ae27775dce441c6 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001218016_311812096.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fae222d68384320f600f0b20019ba4da79012998ac47d5d07dfc39ff8e054111 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001230944_315121664.pth b/checkpoint_p0/milestones/checkpoint_001230944_315121664.pth new file mode 100644 index 0000000000000000000000000000000000000000..3fc73f512b8de98217de08d87b394d17d3dfdd07 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001230944_315121664.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0a2374bf75ce3ea17ab0c14c77a243755b39328d585bb4d74f210e2bac21a40 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001243840_318423040.pth b/checkpoint_p0/milestones/checkpoint_001243840_318423040.pth new file mode 100644 index 0000000000000000000000000000000000000000..ea994dd489d6685997421545cd4727ae0ed69f44 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001243840_318423040.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ce4bd8c76e2203c2f9de2ab45cd9412d92a481f7716b84a8a5dfc79d61cb4c4 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001256672_321708032.pth b/checkpoint_p0/milestones/checkpoint_001256672_321708032.pth new file mode 100644 index 0000000000000000000000000000000000000000..61b202584249dc20aa5b074f4f8b22bfcf1b99d0 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001256672_321708032.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ea9822b3c849a1b4be129cbf811e4f93e310ca6517c3c0248da47411dadb082 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001269600_325017600.pth b/checkpoint_p0/milestones/checkpoint_001269600_325017600.pth new file mode 100644 index 0000000000000000000000000000000000000000..c0b2712ed6c7cac6c860d16eb341d2c8318ae744 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001269600_325017600.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b92868a12e60fbde2a71f94c12d36f72f055516022b13a9cc9e91089e37931bd +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001282496_328318976.pth b/checkpoint_p0/milestones/checkpoint_001282496_328318976.pth new file mode 100644 index 0000000000000000000000000000000000000000..25dce4d23b0d13096c4b142e37abbed9b3836d46 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001282496_328318976.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14d1670148288e72bad7cc7712b2bbc9a505eaa03fbacd949370f96c7a829e59 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001295392_331620352.pth b/checkpoint_p0/milestones/checkpoint_001295392_331620352.pth new file mode 100644 index 0000000000000000000000000000000000000000..43bbf4d010a3987a1aea381d6629dc08b4765c9a --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001295392_331620352.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76b936c9f428d0f82adc3d0f22b08e7136cfdb58f27801e817bddbfd87b04f99 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001308160_334888960.pth b/checkpoint_p0/milestones/checkpoint_001308160_334888960.pth new file mode 100644 index 0000000000000000000000000000000000000000..a78ec1694abd323a40ce94aca6dbaec686983cb8 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001308160_334888960.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b077d344b1986ffa7a58f7bc1f34890219aeb82c9d00e4a5ade2260877732f47 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001320960_338165760.pth b/checkpoint_p0/milestones/checkpoint_001320960_338165760.pth new file mode 100644 index 0000000000000000000000000000000000000000..c2668ac05f7abc31d180b352a2b0fb3589a585a5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001320960_338165760.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fb99e1a2fb09e706fa40bfead356dfe14f157866b410aeda92687963b015844 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001333728_341434368.pth b/checkpoint_p0/milestones/checkpoint_001333728_341434368.pth new file mode 100644 index 0000000000000000000000000000000000000000..c3c2a4446d1b074ec527a0705e251efe8381f3dc --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001333728_341434368.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1f8ece541039162bc2aff3beca06f6512182988d1da54bf41b9a1ab20875679 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001346464_344694784.pth b/checkpoint_p0/milestones/checkpoint_001346464_344694784.pth new file mode 100644 index 0000000000000000000000000000000000000000..ba03f7a362802e4f19dd7742bd279a16b4d23e43 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001346464_344694784.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:463a5566e7878ea15dec20fb871f84e0b3576a7d0163ff5f12d365fc511b83ec +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001359040_347914240.pth b/checkpoint_p0/milestones/checkpoint_001359040_347914240.pth new file mode 100644 index 0000000000000000000000000000000000000000..15231a74215521f01a7770e009c299f1f0f79b89 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001359040_347914240.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3737de403b078b388c58c0abf974b8a49858b4500061e80c93f80fe2e4d7bbf0 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001371872_351199232.pth b/checkpoint_p0/milestones/checkpoint_001371872_351199232.pth new file mode 100644 index 0000000000000000000000000000000000000000..50e9f53c276d888fb3697ff2ce489ede0fb8d873 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001371872_351199232.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b556412c2545a8efb8264750162cd48f3873cff423d1102f2c18f31d5173d6c +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001384544_354443264.pth b/checkpoint_p0/milestones/checkpoint_001384544_354443264.pth new file mode 100644 index 0000000000000000000000000000000000000000..35cbdaeb28d149a20ec8717f2b071b72691710b7 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001384544_354443264.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76d7a7d991508f8fc60177ed38bf393218c472b708f8314f71620de5e5e63786 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001397312_357711872.pth b/checkpoint_p0/milestones/checkpoint_001397312_357711872.pth new file mode 100644 index 0000000000000000000000000000000000000000..64730ca645255d7ea24e0548f0260fb724578197 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001397312_357711872.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14c5fc0e7bf53ac2386841a7ea0ab433c82530fd88cc9aa70bc94b240f6e954a +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001410112_360988672.pth b/checkpoint_p0/milestones/checkpoint_001410112_360988672.pth new file mode 100644 index 0000000000000000000000000000000000000000..7075add7e86e9e4841bf275b51923249837ed9a2 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001410112_360988672.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c51d10065d5f00ac783064b1f0a932850d93711882cf6be2906ce996de110044 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001422880_364257280.pth b/checkpoint_p0/milestones/checkpoint_001422880_364257280.pth new file mode 100644 index 0000000000000000000000000000000000000000..104803e69bf49aecfa259b14669137d899de8d0e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001422880_364257280.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f24d4ba04ac3b9cd8bcbd8ef486acbce348b0f2dd4b406a3e3b982065454732c +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001435648_367525888.pth b/checkpoint_p0/milestones/checkpoint_001435648_367525888.pth new file mode 100644 index 0000000000000000000000000000000000000000..6fd853ff43bb123148570d39556b812f162a1234 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001435648_367525888.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0be11ab9b0f6df716a4867c262312614f6d5d2111a822db0b24ae05fccd1f9e +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001448448_370802688.pth b/checkpoint_p0/milestones/checkpoint_001448448_370802688.pth new file mode 100644 index 0000000000000000000000000000000000000000..1b66d22947cdc525ad1c2d193d83c88e3cd0d449 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001448448_370802688.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a313c64656f44ef05d2c6fa1eff723f845c964a7c4e2e7578f0bc63935d4e969 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001461184_374063104.pth b/checkpoint_p0/milestones/checkpoint_001461184_374063104.pth new file mode 100644 index 0000000000000000000000000000000000000000..9f14dd9285026c8d87418008199400fb4b4c8128 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001461184_374063104.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0db81af1145d04de64357fc7355f7474c914aa6dc42dcaeda23ab528d40abdd3 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001474048_377356288.pth b/checkpoint_p0/milestones/checkpoint_001474048_377356288.pth new file mode 100644 index 0000000000000000000000000000000000000000..05d7b4ffb2e3d885ffc5e3ddc8a3f6a09ad646df --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001474048_377356288.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c474b38a194c5b2e93e5c90d4c9b654285fc649df87acc65cba40de5f88df6fb +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001486944_380657664.pth b/checkpoint_p0/milestones/checkpoint_001486944_380657664.pth new file mode 100644 index 0000000000000000000000000000000000000000..213a272ca0fd61d3504ce29a5e708016b722b7fa --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001486944_380657664.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19106d5f98d83f303ce7b26ee33cbc8ad1859f71f820e5cc305b1671f3c0af55 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001499808_383950848.pth b/checkpoint_p0/milestones/checkpoint_001499808_383950848.pth new file mode 100644 index 0000000000000000000000000000000000000000..0a12843f383a56c3440b91a3aee342ccc75c98fc --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001499808_383950848.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d1578acdcbef211c57f5cc5062a7d1f4ee59e7019290b5653745f03ca293b72 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001512672_387244032.pth b/checkpoint_p0/milestones/checkpoint_001512672_387244032.pth new file mode 100644 index 0000000000000000000000000000000000000000..3dddc6f00b149616a2248ccd56050712eadb425f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001512672_387244032.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aebc589a52f09f02fa5cd68edecb89876b244f68289901a9a08b1337959c2759 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001525536_390537216.pth b/checkpoint_p0/milestones/checkpoint_001525536_390537216.pth new file mode 100644 index 0000000000000000000000000000000000000000..9c01b8c6e2e4bb3cdc1c5720bfcce7d01427f468 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001525536_390537216.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1c6af230eae1d0c268fde91218cf39a57c367c907130de4cae86e90745171e0 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001538432_393838592.pth b/checkpoint_p0/milestones/checkpoint_001538432_393838592.pth new file mode 100644 index 0000000000000000000000000000000000000000..9e2669845d525c70217dec6d618b1d5c1026f448 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001538432_393838592.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ea5aea42eb062d8bc42ce5f656406e78ec5788520e17786d4fa83e825e1f5f3 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001551296_397131776.pth b/checkpoint_p0/milestones/checkpoint_001551296_397131776.pth new file mode 100644 index 0000000000000000000000000000000000000000..c153a14bc4b76f128b2aaea20dd6f7541e8185f1 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001551296_397131776.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:284adec59de33b60cbad6682a9649392fc16edff2a0b8bd108ba3d4a41e26dda +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001564192_400433152.pth b/checkpoint_p0/milestones/checkpoint_001564192_400433152.pth new file mode 100644 index 0000000000000000000000000000000000000000..90733ed29a5f46ed2f8a1a93a2d5eac0c8cbe0ce --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001564192_400433152.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ecb1e341542c79186860d7a21afc1086167a0cb67e8242324bd4d813e4b4474 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001577056_403726336.pth b/checkpoint_p0/milestones/checkpoint_001577056_403726336.pth new file mode 100644 index 0000000000000000000000000000000000000000..20fcd54862b15f8fd65a213c7a45548db9f9bdd6 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001577056_403726336.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c01b6223733d7a51eca61619b4f4b10b5456c854fa56bbc187fab1a2d0f0aaee +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001589952_407027712.pth b/checkpoint_p0/milestones/checkpoint_001589952_407027712.pth new file mode 100644 index 0000000000000000000000000000000000000000..c84755038a3a193dcd96460e79406d99c579bd14 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001589952_407027712.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d80964e6c41483c30f9ab462acd6a6f0ef92e177cd1520980f0b0d854d7663c +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001602848_410329088.pth b/checkpoint_p0/milestones/checkpoint_001602848_410329088.pth new file mode 100644 index 0000000000000000000000000000000000000000..165cad65f7900cb97f1b9eb8333d866c9714ca18 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001602848_410329088.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e36e026cf2a5eb3bb07467f69643b0a4975be45b6283fe0278413b27035693d +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001615712_413622272.pth b/checkpoint_p0/milestones/checkpoint_001615712_413622272.pth new file mode 100644 index 0000000000000000000000000000000000000000..c0afdfc166ea7fe8959f8a995caba4f8cae03b24 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001615712_413622272.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b13fb8d21a6c867ae022b5deb36bf8570dd0739905de56e7790b6370486147a +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001628672_416940032.pth b/checkpoint_p0/milestones/checkpoint_001628672_416940032.pth new file mode 100644 index 0000000000000000000000000000000000000000..969b06ae77d5517d5c0cafba8a649831f6d340aa --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001628672_416940032.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76cce9ff8186cdd9516ddae1d12ca93bbd7441e5fc10259522dfcaa872bf3b23 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001641536_420233216.pth b/checkpoint_p0/milestones/checkpoint_001641536_420233216.pth new file mode 100644 index 0000000000000000000000000000000000000000..142c51cc23ecc297015b37d6f90fa3bd6fcd7cce --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001641536_420233216.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b8478333093e9d26b386d3b5ee79334123f91176bb2baf548870d89091d6bc7 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001654432_423534592.pth b/checkpoint_p0/milestones/checkpoint_001654432_423534592.pth new file mode 100644 index 0000000000000000000000000000000000000000..e989a691f5cee2cb48c0b4cceb73c60449589837 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001654432_423534592.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b329633938e88bc5fdc80d302637db19e621f57cd6737d9c9c8acc78c773723 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001667328_426835968.pth b/checkpoint_p0/milestones/checkpoint_001667328_426835968.pth new file mode 100644 index 0000000000000000000000000000000000000000..89ef47fc398b9615040c3032193f6dc72474eea2 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001667328_426835968.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:295f19fbd0f29f6f72f8104d1f87ee9e978ef8fd7ca6888ced799937b634e7ec +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001680224_430137344.pth b/checkpoint_p0/milestones/checkpoint_001680224_430137344.pth new file mode 100644 index 0000000000000000000000000000000000000000..89aae184f60e200540d3de9c08a1ad5e54e3a665 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001680224_430137344.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9491340361b2d825d887ab165e1ca2b010e950fcdd34d75982f29703592cbd28 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001693120_433438720.pth b/checkpoint_p0/milestones/checkpoint_001693120_433438720.pth new file mode 100644 index 0000000000000000000000000000000000000000..8c43ecd70f2ebea370b618fe3ec25b76392ca664 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001693120_433438720.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f59779a59009d43860bf9a70408fe478e795dbffe5abc173539440665656c275 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001705952_436723712.pth b/checkpoint_p0/milestones/checkpoint_001705952_436723712.pth new file mode 100644 index 0000000000000000000000000000000000000000..d931cc5357192e85555dfe2b2638200a7570442b --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001705952_436723712.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e73703de74ccce49d3092bcdb09369f2b9c9a35968186fcebce06a8b5553c6a +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001718944_440049664.pth b/checkpoint_p0/milestones/checkpoint_001718944_440049664.pth new file mode 100644 index 0000000000000000000000000000000000000000..f9b7b51090e3ec713a76e03fbe7a80032783b3cb --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001718944_440049664.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:832648a350b37691d015c8ec87749143b721de4c302629159d08658ddeb261bf +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001731776_443334656.pth b/checkpoint_p0/milestones/checkpoint_001731776_443334656.pth new file mode 100644 index 0000000000000000000000000000000000000000..8e620578a62d130be54b53fef05a70d1ccdd2f47 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001731776_443334656.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2f43f675b5cff04ddfaa2df24e9d9afbbff025ed38cc88e530afb44545afdbf +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001744672_446636032.pth b/checkpoint_p0/milestones/checkpoint_001744672_446636032.pth new file mode 100644 index 0000000000000000000000000000000000000000..586b6dc094b917a88dfe61e71a4a3f839835ad2f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001744672_446636032.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f8dda32a87f9c2119ebe4b5a19cf548d4de085703a6e8b8b94c41a5ec328cb3 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001757600_449945600.pth b/checkpoint_p0/milestones/checkpoint_001757600_449945600.pth new file mode 100644 index 0000000000000000000000000000000000000000..007e955db21b7dcf0442d88d5617102d4efd1f88 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001757600_449945600.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:494d56086e016866778738c13915ace69ab0a76d27a8a5db67754d7c504e0f59 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001770528_453255168.pth b/checkpoint_p0/milestones/checkpoint_001770528_453255168.pth new file mode 100644 index 0000000000000000000000000000000000000000..048d177b3a919101e9bc02764cdc8e438b7327cc --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001770528_453255168.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4ca4bf24df4a3217c11935533a46e2319fd13826bb901824edebb76edb8b8aa +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001783360_456540160.pth b/checkpoint_p0/milestones/checkpoint_001783360_456540160.pth new file mode 100644 index 0000000000000000000000000000000000000000..892574f4466157eb16f15cca4875c63db77cc9e5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001783360_456540160.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:802d4d47cb91b31ed57a38f98f533194be4a58b9efda36df58b1b7196a3e41ea +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001796224_459833344.pth b/checkpoint_p0/milestones/checkpoint_001796224_459833344.pth new file mode 100644 index 0000000000000000000000000000000000000000..9abf912e0c1ad5ef13fe15871c03b9347e1f317b --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001796224_459833344.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:196a1827e69017d1f197e10b5e1a8878d8b750b513e579fd8a704cf7b316c940 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001809120_463134720.pth b/checkpoint_p0/milestones/checkpoint_001809120_463134720.pth new file mode 100644 index 0000000000000000000000000000000000000000..03ccabffd79b3df2932f71f3f172756b810bb461 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001809120_463134720.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ce6a7ae07df9e4cd6bf7b950b02bb1d925e088c4bcbac3e9fae78d4981cd282 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001822048_466444288.pth b/checkpoint_p0/milestones/checkpoint_001822048_466444288.pth new file mode 100644 index 0000000000000000000000000000000000000000..7ec7d274d84c529208bf8465c877fa07667b7055 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001822048_466444288.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edf0d3d40770b63bbad52c1b1a02beeb99408e55d9cf9295875e41ad66b225a5 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001834912_469737472.pth b/checkpoint_p0/milestones/checkpoint_001834912_469737472.pth new file mode 100644 index 0000000000000000000000000000000000000000..a50d642820cb74d571f869e43e70f6f6a803647e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001834912_469737472.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c27b8cea7ae5d1274ef6a5331fdc314c0741ab490ae988bb4d9435ccbace4b3b +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001847840_473047040.pth b/checkpoint_p0/milestones/checkpoint_001847840_473047040.pth new file mode 100644 index 0000000000000000000000000000000000000000..817be7ccbb39e0d4c86103d009e4aef37947409d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001847840_473047040.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97d96daa25ca21dd1c995c9a405ac5c676703d160c512ce9e3aa1cb7fa0168b7 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001860768_476356608.pth b/checkpoint_p0/milestones/checkpoint_001860768_476356608.pth new file mode 100644 index 0000000000000000000000000000000000000000..3dbd5bc4426add0fe0323a3654b5966d5ef073e1 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001860768_476356608.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35feb859d7a39784218e570d7cd9150d375bc235d4cc70d17256e6bcf65f7abf +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001873664_479657984.pth b/checkpoint_p0/milestones/checkpoint_001873664_479657984.pth new file mode 100644 index 0000000000000000000000000000000000000000..867b41f020436a45adca2cd41d161d81dc0fd9fa --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001873664_479657984.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:052af24a2dad2e659b74fa861c5316b87b06ca065e57a53c499ecb3c65584f23 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001886560_482959360.pth b/checkpoint_p0/milestones/checkpoint_001886560_482959360.pth new file mode 100644 index 0000000000000000000000000000000000000000..fb03d101a61c614603ae759aa6d47aa5566109f2 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001886560_482959360.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fcc5f1e92355eb28cbe9cc1d44c22defdba368307161a62fe33bae72c298f1c +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001899424_486252544.pth b/checkpoint_p0/milestones/checkpoint_001899424_486252544.pth new file mode 100644 index 0000000000000000000000000000000000000000..6e4aae8e2213198e85ba7461aa0044da205613e8 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001899424_486252544.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:362135e9145c431fe3556681faf0b37fcf969616e1c4041b73a96331fb07ed60 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001912320_489553920.pth b/checkpoint_p0/milestones/checkpoint_001912320_489553920.pth new file mode 100644 index 0000000000000000000000000000000000000000..062e92a7698b8d63a7b85fd27a38530bdfa7a056 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001912320_489553920.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02be022fb78d5648426eeaffd7d177dee187e674beb338b2a1ed358c8d769668 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001925216_492855296.pth b/checkpoint_p0/milestones/checkpoint_001925216_492855296.pth new file mode 100644 index 0000000000000000000000000000000000000000..19a070aa657b3cf1a1bb561553e463ba14706885 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001925216_492855296.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64f5317db16a871311d99d68f6bbbf5dbf4060f04114b47469009c9c9f38b606 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001938112_496156672.pth b/checkpoint_p0/milestones/checkpoint_001938112_496156672.pth new file mode 100644 index 0000000000000000000000000000000000000000..f8d45e06e50b19ea63ae1407c4c111c23372ffa0 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001938112_496156672.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc747e0a2c660205fcd85c4329f17d2ed8e915d31ed73d4ce2e789ad6d3a68b5 +size 20797067 diff --git a/checkpoint_p0/milestones/checkpoint_001950976_499449856.pth b/checkpoint_p0/milestones/checkpoint_001950976_499449856.pth new file mode 100644 index 0000000000000000000000000000000000000000..e9aede0529648be91153a01c0814543d17d383f7 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001950976_499449856.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bc93d58ab5a1a42963ab885bbf8e737711ab76a68542d2d8a31053474125967 +size 20797067 diff --git a/checkpoint_p1/best_001869856_478683136_reward_35.960.pth b/checkpoint_p1/best_001869856_478683136_reward_35.960.pth new file mode 100644 index 0000000000000000000000000000000000000000..cc836e2c2bae5b1b7ace3dec756bb2ba6baf8461 --- /dev/null +++ b/checkpoint_p1/best_001869856_478683136_reward_35.960.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87f8244537a437002e0ad212c4cbe561007d9aa163723145826b3c6034cfc732 +size 20795763 diff --git a/checkpoint_p1/checkpoint_001952704_499892224.pth b/checkpoint_p1/checkpoint_001952704_499892224.pth new file mode 100644 index 0000000000000000000000000000000000000000..e57698e42c38cebadc2244115040513c273c674d --- /dev/null +++ b/checkpoint_p1/checkpoint_001952704_499892224.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccac280f67c52efe1845fd13e9fda469aa2d0a56f441d39f44f602a6a0857f99 +size 20796099 diff --git a/checkpoint_p1/checkpoint_001953120_500006912.pth b/checkpoint_p1/checkpoint_001953120_500006912.pth new file mode 100644 index 0000000000000000000000000000000000000000..2100ecabdd5b634cec6c4bc55880363373dee7ab --- /dev/null +++ b/checkpoint_p1/checkpoint_001953120_500006912.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3842241bc18412d4b8430f2fc0b7658ab3ec7dcafad7398295aba5d80538ae5 +size 20796099 diff --git a/checkpoint_p1/milestones/checkpoint_000012352_3162112.pth b/checkpoint_p1/milestones/checkpoint_000012352_3162112.pth new file mode 100644 index 0000000000000000000000000000000000000000..b27721aa61643db3900e002db66d5dabec641b75 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000012352_3162112.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84e3fcb3a4bf6d8bd6e74215b64b3fe8ac3e18f321072268fbe0b36e0526f267 +size 20796955 diff --git a/checkpoint_p1/milestones/checkpoint_000025024_6406144.pth b/checkpoint_p1/milestones/checkpoint_000025024_6406144.pth new file mode 100644 index 0000000000000000000000000000000000000000..c039f1bd4dadb866d04bf524c3836662cc17a77b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000025024_6406144.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77737fe95f8688708a3e378b05c652ce579263943b05505092f2ab9be030408d +size 20796955 diff --git a/checkpoint_p1/milestones/checkpoint_000037696_9650176.pth b/checkpoint_p1/milestones/checkpoint_000037696_9650176.pth new file mode 100644 index 0000000000000000000000000000000000000000..a52c0d530af23ee493a3c66075e54143f126f7c6 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000037696_9650176.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64d2f5cd72284c2507f32bc72bbf79b60c823f082521e449b428a52b46cb4117 +size 20796955 diff --git a/checkpoint_p1/milestones/checkpoint_000050368_12894208.pth b/checkpoint_p1/milestones/checkpoint_000050368_12894208.pth new file mode 100644 index 0000000000000000000000000000000000000000..65d37b14b444a26c4b49df04d4799f0f91a83330 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000050368_12894208.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:840bd1e870d8135d6e118f7198c7e17bfade1f26ee99220e9adfcfa3d0515532 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000063168_16171008.pth b/checkpoint_p1/milestones/checkpoint_000063168_16171008.pth new file mode 100644 index 0000000000000000000000000000000000000000..64d14238cbcb46c5622034673ca4e5d7823ac990 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000063168_16171008.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53747e01752437dbcfc6a416dfe51026708b76f55952fda818dfd97abbf8a4b0 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000075904_19431424.pth b/checkpoint_p1/milestones/checkpoint_000075904_19431424.pth new file mode 100644 index 0000000000000000000000000000000000000000..6bee08069c6df7b55521ad2ef97df48b3ff0e740 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000075904_19431424.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6eb7b82373acec343a8ffab6292171f65df931f871f87aade11a3c181bcf98b +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000088544_22667264.pth b/checkpoint_p1/milestones/checkpoint_000088544_22667264.pth new file mode 100644 index 0000000000000000000000000000000000000000..8c077609a54c8cd6e251e57a7497b2fc6e0939ad --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000088544_22667264.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9564afbfd864be9aa32bc04248d31416d2f759f5fec5776f2d314cc3a8080270 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000101280_25927680.pth b/checkpoint_p1/milestones/checkpoint_000101280_25927680.pth new file mode 100644 index 0000000000000000000000000000000000000000..53c74045ba171e49b940f68a6e6e8b2a2d600719 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000101280_25927680.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8abc74a76ffb0a14e6f01c36673e51034ee0e48cec9ae80d3821f7e1f2e28197 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000113568_29073408.pth b/checkpoint_p1/milestones/checkpoint_000113568_29073408.pth new file mode 100644 index 0000000000000000000000000000000000000000..4dbf98c1b61c37bc11aed24e78b4055e4e444c91 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000113568_29073408.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c7610ebe2b67dce634ce33d670f9e72702054f743fb0cb6916445cf32048635 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000126112_32284672.pth b/checkpoint_p1/milestones/checkpoint_000126112_32284672.pth new file mode 100644 index 0000000000000000000000000000000000000000..6ed6ec64d40d9e7801d1c53073714ef5b682fa08 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000126112_32284672.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70c940dbe503c44308efb49a2e474747e6f76723ae61857d1d3199fda1adff21 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000138848_35545088.pth b/checkpoint_p1/milestones/checkpoint_000138848_35545088.pth new file mode 100644 index 0000000000000000000000000000000000000000..7f5d27c0e1ac3e9dd74399d0f2b6b5f5d29a29db --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000138848_35545088.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3146ce5e8df18f2203d360ec9e623b4464c8d2db0ac727f63f59949a2e0b620a +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000151520_38789120.pth b/checkpoint_p1/milestones/checkpoint_000151520_38789120.pth new file mode 100644 index 0000000000000000000000000000000000000000..4207de974c301133bba36aa9caf9cf9b8e7a8c63 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000151520_38789120.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bddcea6ba445cbe56c8f15e9776032a59e1ae5b5fd8ab6ced5dceb3a366be64 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000164352_42074112.pth b/checkpoint_p1/milestones/checkpoint_000164352_42074112.pth new file mode 100644 index 0000000000000000000000000000000000000000..bd48cd94f76e74c910f5c13a17c01526dd09e30f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000164352_42074112.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:896873011e5c3e6ae70c0ab05d3964b630fdc347b88c1561bd7e28cd342b1a37 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000177152_45350912.pth b/checkpoint_p1/milestones/checkpoint_000177152_45350912.pth new file mode 100644 index 0000000000000000000000000000000000000000..d0cb8e0a445146055380e7b2c7900be533b2d1c3 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000177152_45350912.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1940c5153d9da8b44bdc3ece308e8c45cd2b9f892b9e40ebca9f98086cc4e821 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000189984_48635904.pth b/checkpoint_p1/milestones/checkpoint_000189984_48635904.pth new file mode 100644 index 0000000000000000000000000000000000000000..3df97e5fc57634218eb10628028f2c84adb63e0c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000189984_48635904.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a4a2d50563465c7b0d2802ecacf44c31054e458cf90e388bc17b620dd6bfc62 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000202752_51904512.pth b/checkpoint_p1/milestones/checkpoint_000202752_51904512.pth new file mode 100644 index 0000000000000000000000000000000000000000..38b453853a6e37669328456947bbd07a22fe3ab0 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000202752_51904512.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66bed465d9464c7fda2bac4e1b49be639eb8915168a6c51d1b1f4b199c25e329 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000215552_55181312.pth b/checkpoint_p1/milestones/checkpoint_000215552_55181312.pth new file mode 100644 index 0000000000000000000000000000000000000000..b4842f1e929da9c210980848dee270bf61a523da --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000215552_55181312.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3204c2ca0e492b6fe26b439e01afc77b9aee7cb924e0c559668d953c374dca62 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000228352_58458112.pth b/checkpoint_p1/milestones/checkpoint_000228352_58458112.pth new file mode 100644 index 0000000000000000000000000000000000000000..86516d701091e273ebd8356170ec39c31ba07a46 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000228352_58458112.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84570fad9853d9d653170f6d612e63670a3a5cfd8ba51711de55ea4c8cc3defc +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000241216_61751296.pth b/checkpoint_p1/milestones/checkpoint_000241216_61751296.pth new file mode 100644 index 0000000000000000000000000000000000000000..ff6755ef524350b3bd65d10c5483b4ae542132dd --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000241216_61751296.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a56ac9e46244340ea99ea4dcb5054980da61dafa2f0610a49c9669bc97c0b13 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000254016_65028096.pth b/checkpoint_p1/milestones/checkpoint_000254016_65028096.pth new file mode 100644 index 0000000000000000000000000000000000000000..f49315c9fa9a615df20174c6917ff8492aed9e1b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000254016_65028096.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88b9c15eb07feef89e6d36bad0e4260b09f4c579fee15dffaa26994d925bd458 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000266752_68288512.pth b/checkpoint_p1/milestones/checkpoint_000266752_68288512.pth new file mode 100644 index 0000000000000000000000000000000000000000..06ae6e70e1cf798aff25e9cc08045b07758d1343 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000266752_68288512.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71f6ba4dfba8a832bb2c11d571b71ad81ee283f91a567d8dfbc565b6317ca053 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000279616_71581696.pth b/checkpoint_p1/milestones/checkpoint_000279616_71581696.pth new file mode 100644 index 0000000000000000000000000000000000000000..f448f53d57b9da1394bcb48149bd88b25e245ebf --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000279616_71581696.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e251dc35d254f6b25c40ae7e6a9504a9a5c48a9318b9c836f5c8b8400e968095 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000292416_74858496.pth b/checkpoint_p1/milestones/checkpoint_000292416_74858496.pth new file mode 100644 index 0000000000000000000000000000000000000000..6e8ea406baeb47157efd072cdccf2aa8e2985c38 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000292416_74858496.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:733c429f6d45a1bf2394442d87234bfa8016b0db64c676dbc5cacdd0eed6f178 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000305184_78127104.pth b/checkpoint_p1/milestones/checkpoint_000305184_78127104.pth new file mode 100644 index 0000000000000000000000000000000000000000..1c75317b6d5700478592387b00bfc061ca5ef159 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000305184_78127104.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fd9f771082de417327839eb30f22db038071828e2de2bd173f9da96a32cc72e +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000317984_81403904.pth b/checkpoint_p1/milestones/checkpoint_000317984_81403904.pth new file mode 100644 index 0000000000000000000000000000000000000000..c705f2d083fadbca0e20b846997640d78bd1414b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000317984_81403904.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80a3920d1cdc2b979357cb04f11ac832480149194eace813a0f0bb85d80ac8b9 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000330880_84705280.pth b/checkpoint_p1/milestones/checkpoint_000330880_84705280.pth new file mode 100644 index 0000000000000000000000000000000000000000..17a0a916da1a9e446e0ab1ec6e2f55d20cec70b6 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000330880_84705280.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a03a025807bfbc887fb95ce4ffc0b02b4446db9e4aa141e20fd0190f557fa511 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000343648_87973888.pth b/checkpoint_p1/milestones/checkpoint_000343648_87973888.pth new file mode 100644 index 0000000000000000000000000000000000000000..645d35a4736a76b6a7dba51a7a71f39343cec170 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000343648_87973888.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61826d617777ecb6788e54f47ac06d1993016ba58e83378e151150fdbb155cad +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000356480_91258880.pth b/checkpoint_p1/milestones/checkpoint_000356480_91258880.pth new file mode 100644 index 0000000000000000000000000000000000000000..59207e41586aa5528be58a9b252d9f1061aaadb1 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000356480_91258880.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10e6a7c523915ab8aba0e94f00b119b6c3be59b2c638098255f03653a35a3992 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000369280_94535680.pth b/checkpoint_p1/milestones/checkpoint_000369280_94535680.pth new file mode 100644 index 0000000000000000000000000000000000000000..57753465b6ecba66fb3ac1f9627f4dfe4ad09f72 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000369280_94535680.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90f04c965774e38da20de39cb3f9e9c5c1f6c631092301c0da10fcac4e39688d +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000382112_97820672.pth b/checkpoint_p1/milestones/checkpoint_000382112_97820672.pth new file mode 100644 index 0000000000000000000000000000000000000000..02da6f4eed76b7ade6bf92189e3d86e62d2674fe --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000382112_97820672.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51607d9d15e3d74aa8a87053be27b55df6bcb086a7019a05b1a8f605bd749da5 +size 20797011 diff --git a/checkpoint_p1/milestones/checkpoint_000394912_101097472.pth b/checkpoint_p1/milestones/checkpoint_000394912_101097472.pth new file mode 100644 index 0000000000000000000000000000000000000000..31b28eda26f671fc555bfcd618c099d8d03531c7 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000394912_101097472.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2bda049b4e6e5c004d16d8de470304af649089b8b542ada3208fd80665ee04a +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000407776_104390656.pth b/checkpoint_p1/milestones/checkpoint_000407776_104390656.pth new file mode 100644 index 0000000000000000000000000000000000000000..b1a11ddf503cd74e69ea09a0e7445a207a8a4821 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000407776_104390656.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1576e146cabbf0664e3fec93b3cfd3806216e29ccbd821c8b60233389947e24 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000420608_107675648.pth b/checkpoint_p1/milestones/checkpoint_000420608_107675648.pth new file mode 100644 index 0000000000000000000000000000000000000000..4103c4f949571288cd2104a1542a95dc1b5d7265 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000420608_107675648.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcd0b3a704a1ff7fa1bc30e59238851d6ffd3afea169ea43b4e2f0f42054088a +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000433440_110960640.pth b/checkpoint_p1/milestones/checkpoint_000433440_110960640.pth new file mode 100644 index 0000000000000000000000000000000000000000..e86f6d6f560f57c13225935e0569f53b473534db --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000433440_110960640.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86dccd28bbfbf4f0f5d11b3a1ee98d2c3fa360aaa54a52d9aa6a5a8b168a3f67 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000446208_114229248.pth b/checkpoint_p1/milestones/checkpoint_000446208_114229248.pth new file mode 100644 index 0000000000000000000000000000000000000000..3306bd82c141fac418c46128d861e066f3000d88 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000446208_114229248.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cd79c1def9fc21642829b53b83d74ec05d4f1dd7bb466025ca2d04101fc5c33 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000458880_117473280.pth b/checkpoint_p1/milestones/checkpoint_000458880_117473280.pth new file mode 100644 index 0000000000000000000000000000000000000000..d09de7e230054d28422677b68495b09c3ef861ac --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000458880_117473280.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c9b15ac0d93eab812d1973330f1c70310831b1823780d87072fded325d01dd4 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000471584_120725504.pth b/checkpoint_p1/milestones/checkpoint_000471584_120725504.pth new file mode 100644 index 0000000000000000000000000000000000000000..7551ebab5f32a8dbc45bc9fae419930195d28ea5 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000471584_120725504.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b11cc541efcd7b58aac43d0be8720596733b8b0496bd34669e41d94c3b7a6d9 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000484320_123985920.pth b/checkpoint_p1/milestones/checkpoint_000484320_123985920.pth new file mode 100644 index 0000000000000000000000000000000000000000..02c1d02639891f647c4a8dcde9026c21ab044275 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000484320_123985920.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e32ab924f9fa0568a0fa3603156a77a83c34bd237e9ace6d0b7758d38a425383 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000497024_127238144.pth b/checkpoint_p1/milestones/checkpoint_000497024_127238144.pth new file mode 100644 index 0000000000000000000000000000000000000000..83227d4151453be6deef40ca4abe978058513c32 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000497024_127238144.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f943e4a83ed0ac29cc2f3223151bd774b78f6b2c090667d88353bd5a4b567eef +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000509792_130506752.pth b/checkpoint_p1/milestones/checkpoint_000509792_130506752.pth new file mode 100644 index 0000000000000000000000000000000000000000..bac0213e62efb3c80744d418886d4f808277bc83 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000509792_130506752.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92acd031d0a8eecaed5639f2c6784dc2b0beba77ed7894a0d591e622f8daf4be +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000522528_133767168.pth b/checkpoint_p1/milestones/checkpoint_000522528_133767168.pth new file mode 100644 index 0000000000000000000000000000000000000000..82dfe0814fc712546fe76ff442c0d8a564f95c24 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000522528_133767168.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6761c350ec3b460e44a2633959b9c87c7394d23e6e150a7baf22cae6ac33a41 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000535264_137027584.pth b/checkpoint_p1/milestones/checkpoint_000535264_137027584.pth new file mode 100644 index 0000000000000000000000000000000000000000..d8c1b373ad9327fac535d2a04fd97082f31c10f5 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000535264_137027584.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d56d21135f4e4559d11c4039724e058429ab0bbdc4522fba26fc287a5d26d0c0 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000547968_140279808.pth b/checkpoint_p1/milestones/checkpoint_000547968_140279808.pth new file mode 100644 index 0000000000000000000000000000000000000000..be0df5bbe978782955d17ec19c9f5452e3c7fabc --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000547968_140279808.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcab2cb33ef1fc9c5baf7c2968b99b2c004fc4d5c77b7fb01970c58c1c03bed0 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000560640_143523840.pth b/checkpoint_p1/milestones/checkpoint_000560640_143523840.pth new file mode 100644 index 0000000000000000000000000000000000000000..f86f043eee8bd633192274e31cf6880fd5afec34 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000560640_143523840.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a78994b88c2795e384d843e0627c598f05267c3db9fefdc41e11aab08a8c297e +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000573344_146776064.pth b/checkpoint_p1/milestones/checkpoint_000573344_146776064.pth new file mode 100644 index 0000000000000000000000000000000000000000..85b3cceca28b1eab165ff015cde123162ac3cea0 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000573344_146776064.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47df9a6775aa115cd0b5a9221db92038bc900b0219ce9c568103d4e4948f0cd9 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000586080_150036480.pth b/checkpoint_p1/milestones/checkpoint_000586080_150036480.pth new file mode 100644 index 0000000000000000000000000000000000000000..6fffb3466269c11f45bfb80e6d7518c7ac5b6b1e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000586080_150036480.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a79d40a5cb0f249f87e737973c61aa26d44baac7faa0e83ca15a9eb6a990af60 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000598784_153288704.pth b/checkpoint_p1/milestones/checkpoint_000598784_153288704.pth new file mode 100644 index 0000000000000000000000000000000000000000..cf957aed639d59f8a682471276144ea0fbc73c1f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000598784_153288704.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ff04ca5256f02cfd1c7738da5f82ed9e4374647456244840b8fed48ba21b0a8 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000611456_156532736.pth b/checkpoint_p1/milestones/checkpoint_000611456_156532736.pth new file mode 100644 index 0000000000000000000000000000000000000000..e2b3624c337db2f7bc55773ec5af3acdd95fad5a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000611456_156532736.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:571070971231d80fbc22809f9d8fde0ea61c433c92fe896e18acf21756cf3dc0 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000624256_159809536.pth b/checkpoint_p1/milestones/checkpoint_000624256_159809536.pth new file mode 100644 index 0000000000000000000000000000000000000000..a642441abc4176bfcec581934019ffcbd481843f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000624256_159809536.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f88cf26c6dd60147b8d2e80c533a45b6a7e5e52663599348caa80e6625bcbd37 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000637120_163102720.pth b/checkpoint_p1/milestones/checkpoint_000637120_163102720.pth new file mode 100644 index 0000000000000000000000000000000000000000..22dc4c87d6dfe8c6e28cfa2f437315f6cf1bb3c1 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000637120_163102720.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b862408b68287067cbe1f2bd09d33c058b860104a4566db7d5a0b4ba3cb3120 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000649888_166371328.pth b/checkpoint_p1/milestones/checkpoint_000649888_166371328.pth new file mode 100644 index 0000000000000000000000000000000000000000..fd588f994a95e98df168fba81b0b9eebb913bcae --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000649888_166371328.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e3a9f64cc72ff4499edef3d87ca45b70a067bb3758355aa2f0e5cced1e73897 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000662688_169648128.pth b/checkpoint_p1/milestones/checkpoint_000662688_169648128.pth new file mode 100644 index 0000000000000000000000000000000000000000..f830597bb5dddf2a24b5b6d1cb08e10845adaec2 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000662688_169648128.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0758fb12ff300e43c0f1330cc9fcc7263c0922d33dc50eab39411d9c1a294cd0 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000675392_172900352.pth b/checkpoint_p1/milestones/checkpoint_000675392_172900352.pth new file mode 100644 index 0000000000000000000000000000000000000000..ef772da751527e1f65698d362c0181fb490bfba0 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000675392_172900352.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a44f5092ace83e2be55e95978014cf2c81519d13230af198181ee16181b7d8cf +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000688160_176168960.pth b/checkpoint_p1/milestones/checkpoint_000688160_176168960.pth new file mode 100644 index 0000000000000000000000000000000000000000..c26a4a1842fb6d1cf368466ee667f4da16498a5b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000688160_176168960.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e53e9fb42e6826df68d4170e05a6bc786e92b943b1610ba2598ef0a77e2492e9 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000700992_179453952.pth b/checkpoint_p1/milestones/checkpoint_000700992_179453952.pth new file mode 100644 index 0000000000000000000000000000000000000000..eebba4164a74748ead03c5774ee4da30a00c77c7 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000700992_179453952.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f0a0c1f14b83b8fa01809ec524ef9d30466b42d21d625ca1173489468096b6c +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000713792_182730752.pth b/checkpoint_p1/milestones/checkpoint_000713792_182730752.pth new file mode 100644 index 0000000000000000000000000000000000000000..f5c9bfd2f25f794591145bec8b664a3422d151f0 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000713792_182730752.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a4044911db876a285e041e5e62fbca116c7d661044b1a8cd62abe172de74964 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000726624_186015744.pth b/checkpoint_p1/milestones/checkpoint_000726624_186015744.pth new file mode 100644 index 0000000000000000000000000000000000000000..88cd3812b29eeb95b9de487a685e3bf405515e53 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000726624_186015744.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74bfb99df488fa3554132bacab88699af1371bb82b72e60690cab0aebf5b08bc +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000739424_189292544.pth b/checkpoint_p1/milestones/checkpoint_000739424_189292544.pth new file mode 100644 index 0000000000000000000000000000000000000000..0d634502d98091494e367ec608ec3a2d114ac90d --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000739424_189292544.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:685df42c8005ccb1e9a66d72509c09bb701e1194b828dcab57f565fa6f920540 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000752256_192577536.pth b/checkpoint_p1/milestones/checkpoint_000752256_192577536.pth new file mode 100644 index 0000000000000000000000000000000000000000..96e4f4fdf16961eab92bf8b616b278b0d591b066 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000752256_192577536.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:810eb2ef8d6ebb32ba9e2ef376ef96659f4b12abbeb653ad8c0117804f3684ac +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000765024_195846144.pth b/checkpoint_p1/milestones/checkpoint_000765024_195846144.pth new file mode 100644 index 0000000000000000000000000000000000000000..7b3359b4cb04c8de133e29d3b6f81fd264627f32 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000765024_195846144.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13d7a495d073e35e5122c3c915dccfa7c1206c9f21c5284617ad5604a835e5bb +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000777856_199131136.pth b/checkpoint_p1/milestones/checkpoint_000777856_199131136.pth new file mode 100644 index 0000000000000000000000000000000000000000..54f5a48f1b0265dc8c63250bc84d2d679d73dcc0 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000777856_199131136.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4316500af910c97dae283407309e0ee09401922bc5b5d27145def640b668d1e0 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000790656_202407936.pth b/checkpoint_p1/milestones/checkpoint_000790656_202407936.pth new file mode 100644 index 0000000000000000000000000000000000000000..614ef17c438a16a98814f470aec28a03bad2a36e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000790656_202407936.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6658edd333a9b4739ab45ae02dc5c95fb9441bc93dc056a605463a6c1ca9137a +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000803488_205692928.pth b/checkpoint_p1/milestones/checkpoint_000803488_205692928.pth new file mode 100644 index 0000000000000000000000000000000000000000..51b16ac51de682f6bfc83eab6758f06bbf3cd9bc --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000803488_205692928.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4408557612e87c1e1db3bdd514220d819f68352b3eda68a3d5dac31758c6db6a +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000816320_208977920.pth b/checkpoint_p1/milestones/checkpoint_000816320_208977920.pth new file mode 100644 index 0000000000000000000000000000000000000000..dd1fd7418f56d0b5bd5658028424905c56e41a72 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000816320_208977920.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5580a07f2bf98d0f64237d4e87a9f773fda2015a2afd3308aae1590644f6d432 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000829152_212262912.pth b/checkpoint_p1/milestones/checkpoint_000829152_212262912.pth new file mode 100644 index 0000000000000000000000000000000000000000..83d7c9deb71488e07d1310ad4f05324079ab9528 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000829152_212262912.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf695a3a22dac78240c74aa67d97949c3ae93f41db482ff1d4964fa85d22815a +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000842016_215556096.pth b/checkpoint_p1/milestones/checkpoint_000842016_215556096.pth new file mode 100644 index 0000000000000000000000000000000000000000..5039ee04693c8c8bd28959a0369dcacb6aacd530 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000842016_215556096.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86f0c7d14a8b5392cc95d0f3eda420de92bb41888884bd8564a70eca616278c8 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000854848_218841088.pth b/checkpoint_p1/milestones/checkpoint_000854848_218841088.pth new file mode 100644 index 0000000000000000000000000000000000000000..c130c3e17e9d593be5e39de5ff9395906bfc9b91 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000854848_218841088.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cb575f03ca924357725ea4329f401aa4476adada9f96c46627425f9d27a7f3c +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000867680_222126080.pth b/checkpoint_p1/milestones/checkpoint_000867680_222126080.pth new file mode 100644 index 0000000000000000000000000000000000000000..016946e4e99feb523ca37d3e1e3fdc7dd41ef7b6 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000867680_222126080.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9689dbca7eef7d459f399f8e7586f1d64562884e0ef95664001999e88c1a0a63 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000880416_225386496.pth b/checkpoint_p1/milestones/checkpoint_000880416_225386496.pth new file mode 100644 index 0000000000000000000000000000000000000000..0d1ac560d421000478172adac6f24818c1b2e332 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000880416_225386496.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:225d35ac0e29226dd4a6970caff365634cf3272ba5f284d001c91886a2656971 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000893248_228671488.pth b/checkpoint_p1/milestones/checkpoint_000893248_228671488.pth new file mode 100644 index 0000000000000000000000000000000000000000..0c78ed0be7bcbdd9359167d96378d4b9ee3c540f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000893248_228671488.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2598bd0f7a32e96b5e2dd1dd579ab3434d2ecbeee0e9441d0688232f7a0c342 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000906112_231964672.pth b/checkpoint_p1/milestones/checkpoint_000906112_231964672.pth new file mode 100644 index 0000000000000000000000000000000000000000..8a91a393927600f955a48167bf44b32afa7686c3 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000906112_231964672.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdf26dba0a7c409999352193a17333d41837299c7fe9596dae9c9f890138151f +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000918784_235208704.pth b/checkpoint_p1/milestones/checkpoint_000918784_235208704.pth new file mode 100644 index 0000000000000000000000000000000000000000..9c65504f033745a382de0daa0efcff410fe52167 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000918784_235208704.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc1091d3577a8e7228fe9971cb70aa2a9774b7a79ea7259b64b6f5c783a89420 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000931488_238460928.pth b/checkpoint_p1/milestones/checkpoint_000931488_238460928.pth new file mode 100644 index 0000000000000000000000000000000000000000..18b6350b66551865c39aff352b2b7e9ee4a613aa --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000931488_238460928.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9f0bf1315b1f108a20e355cd7188a3e393bd0ef5f028d543d815899654e63f0 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000944128_241696768.pth b/checkpoint_p1/milestones/checkpoint_000944128_241696768.pth new file mode 100644 index 0000000000000000000000000000000000000000..a3ae72e49619678a6cc727db40bf7374fff5f1a1 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000944128_241696768.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29320cd52ebdf976f5f6acea34c459c12fc2fc0da83434d610516989c1b4ee23 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000956736_244924416.pth b/checkpoint_p1/milestones/checkpoint_000956736_244924416.pth new file mode 100644 index 0000000000000000000000000000000000000000..107d02e4db7ae42c7b76eeba07c1406e31fade80 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000956736_244924416.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a03580007e1d4ffd580297afe124e87897006f16023ff6bea57cee1bb6d7bdfc +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000969472_248184832.pth b/checkpoint_p1/milestones/checkpoint_000969472_248184832.pth new file mode 100644 index 0000000000000000000000000000000000000000..ce3ec12ed978f5c9b3431b96932c23f22a7fb684 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000969472_248184832.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f85a39bc63dd100cc4a0187fb71055a8a8e9d47a726d3bee971d70075e1d0f3d +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000982208_251445248.pth b/checkpoint_p1/milestones/checkpoint_000982208_251445248.pth new file mode 100644 index 0000000000000000000000000000000000000000..84c9af338348eb4db8026540b72a7b88cad4b1f2 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000982208_251445248.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a7cee946c46a43247698eca019a8394f287cdfb17fea2ccada019da72e2acff +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_000994944_254705664.pth b/checkpoint_p1/milestones/checkpoint_000994944_254705664.pth new file mode 100644 index 0000000000000000000000000000000000000000..67f8dbbfab2222442d09f06c1a88771b226744f4 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000994944_254705664.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd5dc27ac999c4bec7cd118e8feb03b654c37bb3cb385ce9ddd8c9d98c1620a6 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001007648_257957888.pth b/checkpoint_p1/milestones/checkpoint_001007648_257957888.pth new file mode 100644 index 0000000000000000000000000000000000000000..d2ea4b8f28c535ea00b592aa3efc26f3202e114b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001007648_257957888.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81120575ba79b0cc6828204cb8548196e5c2309420978893d2dd4d90620f95ef +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001020416_261226496.pth b/checkpoint_p1/milestones/checkpoint_001020416_261226496.pth new file mode 100644 index 0000000000000000000000000000000000000000..022d56fb3c3c9a9c1b13339ab15ea401800d3a7b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001020416_261226496.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8051fca5c6759e0f4a423feb2e58bc47e4eeb2507b4e43ed503b4bcbb9010b7c +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001032864_264413184.pth b/checkpoint_p1/milestones/checkpoint_001032864_264413184.pth new file mode 100644 index 0000000000000000000000000000000000000000..af61a1cdc55937b13ab582c75f6d071566e349a4 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001032864_264413184.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a83490319f917245bf35317bd2d48407396dc7249791c0b05b548a54a15e934 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001045472_267640832.pth b/checkpoint_p1/milestones/checkpoint_001045472_267640832.pth new file mode 100644 index 0000000000000000000000000000000000000000..4f37c5cddfa13c25663754160586a7f7707839ac --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001045472_267640832.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:316f66998a82eb2a1ed56e0c0902dec54b2c1c436a951cec561cd8839ac68577 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001058176_270893056.pth b/checkpoint_p1/milestones/checkpoint_001058176_270893056.pth new file mode 100644 index 0000000000000000000000000000000000000000..124d92dc7e10abce6f96349f0fea8270c945279b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001058176_270893056.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb807ca551e41973cdb6bf91a2872764ed9feaac7308ecee2ce215bf31bc7e3f +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001070880_274145280.pth b/checkpoint_p1/milestones/checkpoint_001070880_274145280.pth new file mode 100644 index 0000000000000000000000000000000000000000..8180f8a69acd2b6f9b7192a2369ae594a46bc8c5 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001070880_274145280.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51122c183c705f3e98e71a0c517d577a531e0c45478661e26056cf1827570b5c +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001083680_277422080.pth b/checkpoint_p1/milestones/checkpoint_001083680_277422080.pth new file mode 100644 index 0000000000000000000000000000000000000000..19d92594fafc8af2856b6fae559498c1338ad28f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001083680_277422080.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dd00e72289d9cdecb174f2f94e43ee78153c11a12a35c51b57c8a4ef8969b53 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001096448_280690688.pth b/checkpoint_p1/milestones/checkpoint_001096448_280690688.pth new file mode 100644 index 0000000000000000000000000000000000000000..daea6d897af22f274b96dbb911d999f8a33c7a70 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001096448_280690688.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80f4a812baeaca27db0acb9df37172c00ec33a090ec945f163527b2c310346c1 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001109280_283975680.pth b/checkpoint_p1/milestones/checkpoint_001109280_283975680.pth new file mode 100644 index 0000000000000000000000000000000000000000..304248c7e5ee173f6873eaef0440ee9f4b1aeb4f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001109280_283975680.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:becf5dca8bb6c01845d8f6cd74c6e1c58135d578847a17e4c644cd89a011a0db +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001122112_287260672.pth b/checkpoint_p1/milestones/checkpoint_001122112_287260672.pth new file mode 100644 index 0000000000000000000000000000000000000000..13191ee3d6285bb433537d076fd395cc080c3d7d --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001122112_287260672.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a9e3ddc9cabfad88329b3ec7f50e78c2cf2784037fdfe1f31d5e18dcc9bf22d +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001134976_290553856.pth b/checkpoint_p1/milestones/checkpoint_001134976_290553856.pth new file mode 100644 index 0000000000000000000000000000000000000000..3e089a34c2f41476ebe714d7c3bfdb8ace608df0 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001134976_290553856.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:356277f33708398d624c303f1ee28b6e870411bda92df8e9d789a5423e76a921 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001147840_293847040.pth b/checkpoint_p1/milestones/checkpoint_001147840_293847040.pth new file mode 100644 index 0000000000000000000000000000000000000000..54d9f6dac892374f55f912bbf3a9ac49dda15388 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001147840_293847040.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a136c8bdc1922ca7143ead3c15f77b37f8ebb29ad45a2a0ebecfe36d92d40771 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001160640_297123840.pth b/checkpoint_p1/milestones/checkpoint_001160640_297123840.pth new file mode 100644 index 0000000000000000000000000000000000000000..3b9610a5f42212514db5302072bb1e11a8fb4c4b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001160640_297123840.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:037cf1ed879b5b295ab5c9fb01d49aef5cef52a4c5915c446fda4f67c3e7fb6a +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001173440_300400640.pth b/checkpoint_p1/milestones/checkpoint_001173440_300400640.pth new file mode 100644 index 0000000000000000000000000000000000000000..021c8075f931b9707d15022ac4af1773e2c5bae6 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001173440_300400640.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:076915a58f207fb497534a463f334cff6abcc363375442ff58aa73c86437df3f +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001186240_303677440.pth b/checkpoint_p1/milestones/checkpoint_001186240_303677440.pth new file mode 100644 index 0000000000000000000000000000000000000000..f03aaf17a9d659b8b95a45b67b242a654b9179aa --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001186240_303677440.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:686d2f96c85a6295b885ecd7ce80e310acbc3e0cd60e118b59a42c2438959578 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001199136_306978816.pth b/checkpoint_p1/milestones/checkpoint_001199136_306978816.pth new file mode 100644 index 0000000000000000000000000000000000000000..ed02c704dd5a9c6c469e5dd317b1c3ce1a1a21b0 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001199136_306978816.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5fd3027624e31e499763fa0cec8c418e14c9e04e481a45fa1f5ea75eff6f973 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001212000_310272000.pth b/checkpoint_p1/milestones/checkpoint_001212000_310272000.pth new file mode 100644 index 0000000000000000000000000000000000000000..4adb1fc0cf87cdaf74c0d5a277436e5a7c9ff1a1 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001212000_310272000.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82c8ef268588f0ad4e737c76005d616cc8ca6d820c51c4dda24e3e4003f4b95f +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001224800_313548800.pth b/checkpoint_p1/milestones/checkpoint_001224800_313548800.pth new file mode 100644 index 0000000000000000000000000000000000000000..b6b4785f7f45020acc101417f483982d732d0b8d --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001224800_313548800.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd1bdf01e044289deedfcc306b1faa2a1f42d56df4e71d2fd576f6710140e282 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001237568_316817408.pth b/checkpoint_p1/milestones/checkpoint_001237568_316817408.pth new file mode 100644 index 0000000000000000000000000000000000000000..be49c8010e984288032a31a8ce755c1d5a326ec6 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001237568_316817408.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6fe644917af51e0cbc0fa9cbefeb2072a8986c2968f3b5c7b8b02ab27c16fc6 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001250336_320086016.pth b/checkpoint_p1/milestones/checkpoint_001250336_320086016.pth new file mode 100644 index 0000000000000000000000000000000000000000..6a3670555025c1d121e3ff4f547f1b8654d154fb --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001250336_320086016.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f024c58f659700feef45796f71604bef0e6f2000428f7c69945d7285b403f8d +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001263104_323354624.pth b/checkpoint_p1/milestones/checkpoint_001263104_323354624.pth new file mode 100644 index 0000000000000000000000000000000000000000..6253090d2f5571d77fcc609eb1e4118c2c06aa92 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001263104_323354624.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93447742257c7bfb3aef9ea7a4e39a466315bfe7748df30b71cd913a1bd2800f +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001275904_326631424.pth b/checkpoint_p1/milestones/checkpoint_001275904_326631424.pth new file mode 100644 index 0000000000000000000000000000000000000000..501bfd4d6c1fcd5553642ab6aabe92a62f3d6ac5 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001275904_326631424.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98a9c59adb438602f61c1052f361bde304e8740dbb229d1aae8e9a3e6a6fe261 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001288768_329924608.pth b/checkpoint_p1/milestones/checkpoint_001288768_329924608.pth new file mode 100644 index 0000000000000000000000000000000000000000..8f61edb19e04e10bbd22a9ee9ffd89fc3a2d8e60 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001288768_329924608.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c21857377879e76a42e96d2f8e70b867d5c820314e321526447b0601f412434 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001301504_333185024.pth b/checkpoint_p1/milestones/checkpoint_001301504_333185024.pth new file mode 100644 index 0000000000000000000000000000000000000000..554060a8472972f89e350b39497e78d18b20f4d4 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001301504_333185024.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c317e9b832b95d4cb33153b847403c1c39c7ed610f959eea87ca19816e89e0e7 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001314208_336437248.pth b/checkpoint_p1/milestones/checkpoint_001314208_336437248.pth new file mode 100644 index 0000000000000000000000000000000000000000..a8a50bc13675ce3ba2e6a887eeb41f82b585fa9a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001314208_336437248.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:002c3fb2a31c05933052bc3f83f65b1f3a98b51b4af3bbd452edb69c94cc11cf +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001326880_339681280.pth b/checkpoint_p1/milestones/checkpoint_001326880_339681280.pth new file mode 100644 index 0000000000000000000000000000000000000000..34b877b2827285c2d47e6f244d9d43444983aa10 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001326880_339681280.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:677cc281b7b77e93d5fb2f473ffb1ec6588c53121af3c720e3ec81bf24b40a18 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001339584_342933504.pth b/checkpoint_p1/milestones/checkpoint_001339584_342933504.pth new file mode 100644 index 0000000000000000000000000000000000000000..cd8c06125b70edbd8879378734901b8a1c202bb3 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001339584_342933504.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54bb0fa63ea673994f317293b6b41fec67850b533a675da5ff993c0b6b2b5a4e +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001352064_346128384.pth b/checkpoint_p1/milestones/checkpoint_001352064_346128384.pth new file mode 100644 index 0000000000000000000000000000000000000000..4a4ac9f05536a1ce339f71afaa8e3fb422ab749b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001352064_346128384.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac296217d45627254e5854134595c052844888117bd4fdcdf55ee5fe1bb342b2 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001364736_349372416.pth b/checkpoint_p1/milestones/checkpoint_001364736_349372416.pth new file mode 100644 index 0000000000000000000000000000000000000000..5021e9779e835cf6cff9f86095b8b77e26a0d159 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001364736_349372416.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b986efbee1e8943d944fbe972dec53a111ddd58ed1d321cdf1d29c015eb738f9 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001377344_352600064.pth b/checkpoint_p1/milestones/checkpoint_001377344_352600064.pth new file mode 100644 index 0000000000000000000000000000000000000000..c3a43d83b82aea827be22ea5b113700fcc54719e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001377344_352600064.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a110829a56f4799b79ecea0903cf22a5aa7fd6d72b55ec0d47d25f257cd9cce +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001390016_355844096.pth b/checkpoint_p1/milestones/checkpoint_001390016_355844096.pth new file mode 100644 index 0000000000000000000000000000000000000000..08ac02cc4022cc05fb3126f56ff7a53e32b70bf9 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001390016_355844096.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:882c8df902e719f1f367211e49b1b30261d3fba884cb5acbbee1f2e720cb188d +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001402688_359088128.pth b/checkpoint_p1/milestones/checkpoint_001402688_359088128.pth new file mode 100644 index 0000000000000000000000000000000000000000..4f1645788f434c4e1ce2d33f0660335471c5b975 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001402688_359088128.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d422413b3f5074e356294d10869cc2f33e0d0d5fcae144c7f7e2a6b71ab855d +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001415456_362356736.pth b/checkpoint_p1/milestones/checkpoint_001415456_362356736.pth new file mode 100644 index 0000000000000000000000000000000000000000..510e6afd8538a4628e625f27411f9c74aa0a6831 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001415456_362356736.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c83d7fbf30bdab49e3483ad09850aa35b9c725908f174d10fe3dfe392ef080b6 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001428160_365608960.pth b/checkpoint_p1/milestones/checkpoint_001428160_365608960.pth new file mode 100644 index 0000000000000000000000000000000000000000..0e6d5ee5d0e9044d6885987f33fe72be954b15bf --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001428160_365608960.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20fad49c8688787fb2012805fe41844902a4b7bf6dd6faf20891f1cf529e94c1 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001440864_368861184.pth b/checkpoint_p1/milestones/checkpoint_001440864_368861184.pth new file mode 100644 index 0000000000000000000000000000000000000000..b1bf32e074b1c97fe0c3e044091d15f1faab9ff9 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001440864_368861184.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85d9af91d650dee2d5a28b3b50cb2d75712c339ce3364a8a02ef797e85b2882e +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001453536_372105216.pth b/checkpoint_p1/milestones/checkpoint_001453536_372105216.pth new file mode 100644 index 0000000000000000000000000000000000000000..a46ea98cc42b2c4a0b82b1d1c4a58e37dfade022 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001453536_372105216.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:713c9eb7c6a5f44360cc22385262feb066be8d604c47431d7237d377903a7eea +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001466240_375357440.pth b/checkpoint_p1/milestones/checkpoint_001466240_375357440.pth new file mode 100644 index 0000000000000000000000000000000000000000..bb81b323e1035e15ca4bb52fb90545683d27d72c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001466240_375357440.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:caef7cfa525953795b0495ce6b3c4c11536015011a972c7ec6957e2cd39d0544 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001479104_378650624.pth b/checkpoint_p1/milestones/checkpoint_001479104_378650624.pth new file mode 100644 index 0000000000000000000000000000000000000000..8c356e808204647c691e41a2527a8f9af3cc7263 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001479104_378650624.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58f10de23ccb3cb44ab69ed4d9710b283457c6a25ac717e3c9fe40882a8c485d +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001491904_381927424.pth b/checkpoint_p1/milestones/checkpoint_001491904_381927424.pth new file mode 100644 index 0000000000000000000000000000000000000000..a1ddb3d080177026ca19e17852a0904d831e1de8 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001491904_381927424.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24ed2a0b632b76ccf745048a2c21ddc3c3744d1c2ff6b047496113f8b487a6d0 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001504704_385204224.pth b/checkpoint_p1/milestones/checkpoint_001504704_385204224.pth new file mode 100644 index 0000000000000000000000000000000000000000..c222830b58a598caee9a6bfc2efe17431e44e987 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001504704_385204224.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01da0913fbe0cbe181ffc9ea2d3cd57dffaeda668c258e2b1f8f98ae95490c95 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001517472_388472832.pth b/checkpoint_p1/milestones/checkpoint_001517472_388472832.pth new file mode 100644 index 0000000000000000000000000000000000000000..acf88ad4379752fe6363c75ad210324d7e68d2e5 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001517472_388472832.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b6394c5e8536154e5a08183be8d70665f0becf11dd7c4784d46106cf6920e8a +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001530304_391757824.pth b/checkpoint_p1/milestones/checkpoint_001530304_391757824.pth new file mode 100644 index 0000000000000000000000000000000000000000..1403319ccc28cf2fb14d7a02c196c2b3a9d937a2 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001530304_391757824.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55616f1f6795ef8f6bb6b3a2c1c7c79d9f188dcc911643ac1fd26f430ca5f013 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001543104_395034624.pth b/checkpoint_p1/milestones/checkpoint_001543104_395034624.pth new file mode 100644 index 0000000000000000000000000000000000000000..bd8b1efb1631068ded51471b3aa25dbe3cd696cd --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001543104_395034624.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14292f31080fcb440b1088bbf9c05421e5391276a76f0871cf0fde7848572c04 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001555968_398327808.pth b/checkpoint_p1/milestones/checkpoint_001555968_398327808.pth new file mode 100644 index 0000000000000000000000000000000000000000..f427a80ff5e4378d28d2d148dcf629028135f71b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001555968_398327808.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:894e5caaf82062a32c5b7c6820395c8a6d9f3daa1eb6f39ab0b173e93d84b96c +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001568832_401620992.pth b/checkpoint_p1/milestones/checkpoint_001568832_401620992.pth new file mode 100644 index 0000000000000000000000000000000000000000..02c0c769b9a84b08e80b109afc2ff0c1c2c85e1c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001568832_401620992.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb5c7a9b0fc4e50937c2c62b089e595e796b4e7d79654e537795c21f32a30d76 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001581664_404905984.pth b/checkpoint_p1/milestones/checkpoint_001581664_404905984.pth new file mode 100644 index 0000000000000000000000000000000000000000..43fedcaf1d3aefe75429f44f7cf6c201fbca9656 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001581664_404905984.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ab045da04cf1f988fa65bcb6b3c243c96bf3e8e1a234cd33f0faefc1cc1f49b +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001594528_408199168.pth b/checkpoint_p1/milestones/checkpoint_001594528_408199168.pth new file mode 100644 index 0000000000000000000000000000000000000000..202421cb70cb0445eb4c2ff2512df4ed7d93cd64 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001594528_408199168.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bece0ad18ab7bd8c3cbab04a046c91fe8605eb377ac7db0e757d68d05bde6e22 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001607328_411475968.pth b/checkpoint_p1/milestones/checkpoint_001607328_411475968.pth new file mode 100644 index 0000000000000000000000000000000000000000..da19dcbca79facded77456d7e967c53d87b6b630 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001607328_411475968.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e1cb152994a9b470fd4abe2620d06899244f5bb0fec3f0b131138588103e23e +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..5e9aeb19e3cd88b32e6bac29ac1ddc199324ead3 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001620096_414744576.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c8ef4845457366673699dd18b242d36cb69f6ee35ea4fcddf1582cbf61ca853 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001632992_418045952.pth b/checkpoint_p1/milestones/checkpoint_001632992_418045952.pth new file mode 100644 index 0000000000000000000000000000000000000000..d4b3998e424fe71e83e5d7f340df8adacd6e48e1 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001632992_418045952.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:345e191d335a4c0d0e3530efeb4ddf1365d84d3a3fe552a12e5a1b680e7a8a4d +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001645824_421330944.pth b/checkpoint_p1/milestones/checkpoint_001645824_421330944.pth new file mode 100644 index 0000000000000000000000000000000000000000..0387411cf89a59a49ece3ce83acb5ac5a9f003f5 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001645824_421330944.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bfc523dd1dee6c96455490f67aeb335bf9abd8430f49b3cb2c887ab21e6f828 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001658688_424624128.pth b/checkpoint_p1/milestones/checkpoint_001658688_424624128.pth new file mode 100644 index 0000000000000000000000000000000000000000..daf6bd57746c02d85f6d5a64bf8203910e96fe44 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001658688_424624128.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c49bea6c70ca43ace8197f4d5e82705dd523dbf0545c5a5224246aa8e5904fe +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001671488_427900928.pth b/checkpoint_p1/milestones/checkpoint_001671488_427900928.pth new file mode 100644 index 0000000000000000000000000000000000000000..38a2d2929506a662ae433191e1f994e248bd731f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001671488_427900928.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2cd306234131ab2e72d23639808e3f96f48bb077c784d96749ab8e2ec467419 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001684352_431194112.pth b/checkpoint_p1/milestones/checkpoint_001684352_431194112.pth new file mode 100644 index 0000000000000000000000000000000000000000..17bb81b2812115a0118c0522036dbd7bfbeeea02 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001684352_431194112.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11ab803aad0531edf3299a20de0d485b0dc3363a025bdf19ce08877b248e07d2 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001697248_434495488.pth b/checkpoint_p1/milestones/checkpoint_001697248_434495488.pth new file mode 100644 index 0000000000000000000000000000000000000000..69e1f4ee6c93ab4c9e5b3f567126059889086ef2 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001697248_434495488.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e270abc6946b1351e856773c8816aaf0aa9b20cb0ea56e487353e906c0a0596 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001710080_437780480.pth b/checkpoint_p1/milestones/checkpoint_001710080_437780480.pth new file mode 100644 index 0000000000000000000000000000000000000000..2af034b03ef32c1e700d2724ff1e317b478a34fa --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001710080_437780480.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68c4a7529bda1125594805bfb111490875269608b3c9ba3413ed6651edc09e47 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001722944_441073664.pth b/checkpoint_p1/milestones/checkpoint_001722944_441073664.pth new file mode 100644 index 0000000000000000000000000000000000000000..21fe9e83d356c7ed956bea19dd6b7ce349c7bdca --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001722944_441073664.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:042016620805f62ad133214981c94753993d1a8050886b0a7d8cc5db0be80e6f +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001735808_444366848.pth b/checkpoint_p1/milestones/checkpoint_001735808_444366848.pth new file mode 100644 index 0000000000000000000000000000000000000000..5af57348196af7675c8101f4458203a105abc6b8 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001735808_444366848.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eca21623aa800ef06299606d5f8b19da65100e9c2cce6d577dc5dc192fbe8b99 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001748608_447643648.pth b/checkpoint_p1/milestones/checkpoint_001748608_447643648.pth new file mode 100644 index 0000000000000000000000000000000000000000..a69bc2f5651a695aee338500efb3c9c0ea7cf266 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001748608_447643648.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ee6f1b4070faf51d63b9098d5e44a821055ab082a755a99f43cb1c63ee71fc5 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001761440_450928640.pth b/checkpoint_p1/milestones/checkpoint_001761440_450928640.pth new file mode 100644 index 0000000000000000000000000000000000000000..fc7991f13da0ab2ee3828cf8dc5078e2f042ad95 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001761440_450928640.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51577341f26189bf216bc52ef3e5a59ccc5a18da9415bed9ee91be46b3fef2f7 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001774304_454221824.pth b/checkpoint_p1/milestones/checkpoint_001774304_454221824.pth new file mode 100644 index 0000000000000000000000000000000000000000..487fcdca214c3d76848db627fc1add3fc9360150 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001774304_454221824.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1921e7e6c54fdb0de9816a44f46bd18d428cf5e71a67e8e46ff77cc81da0593f +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001787136_457506816.pth b/checkpoint_p1/milestones/checkpoint_001787136_457506816.pth new file mode 100644 index 0000000000000000000000000000000000000000..55e15886abc3f473b34e06b025f2fef4cdf032cd --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001787136_457506816.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:246c8bbd57ae236489cba3b93e2c99eebc84be4d3d603aea3e8cc2fd0a860f9b +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001799968_460791808.pth b/checkpoint_p1/milestones/checkpoint_001799968_460791808.pth new file mode 100644 index 0000000000000000000000000000000000000000..1455dcf4f194922308b5b6d6cc99dafce354e859 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001799968_460791808.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14b324508236bec91781b0ef3d5f2aee3b650b6e22af0fc09e7d3821abc34a1f +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001812800_464076800.pth b/checkpoint_p1/milestones/checkpoint_001812800_464076800.pth new file mode 100644 index 0000000000000000000000000000000000000000..b232a1c596caee38fc45527805c61065d0e61f8e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001812800_464076800.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb196f86c80aef83b8aad9d6ef47992d65a45d2a2ced1dd933d1270eb239ef25 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001825664_467369984.pth b/checkpoint_p1/milestones/checkpoint_001825664_467369984.pth new file mode 100644 index 0000000000000000000000000000000000000000..91d8c2f53d1bfe54799f1cb9198af86db9d99243 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001825664_467369984.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b496ba64db98b3042df318d6eb1d5168db66776e729313c69a5d2b1eb4911d8 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001838528_470663168.pth b/checkpoint_p1/milestones/checkpoint_001838528_470663168.pth new file mode 100644 index 0000000000000000000000000000000000000000..f83cfea5be0e6b86f9dc0047b91e637821b490c8 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001838528_470663168.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:219db319b95868ad0371b8a83103541ca52f6af91ef7bc1f20947bdfa9061a75 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001851456_473972736.pth b/checkpoint_p1/milestones/checkpoint_001851456_473972736.pth new file mode 100644 index 0000000000000000000000000000000000000000..76ccb9930b3239abb2ff53fbca6752365891906f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001851456_473972736.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6066cd4230c5684a17f067028b85a89159eae595707f8311e88237904cb90d3 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001864224_477241344.pth b/checkpoint_p1/milestones/checkpoint_001864224_477241344.pth new file mode 100644 index 0000000000000000000000000000000000000000..d280a8e16bea79a265fde31dda181f15e1425d80 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001864224_477241344.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cdda23a78b1fcf31e65e9f7475cf2887762edcf5357d280f7621b531e0cd5d3 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001877024_480518144.pth b/checkpoint_p1/milestones/checkpoint_001877024_480518144.pth new file mode 100644 index 0000000000000000000000000000000000000000..c27480e180d679718efc3815c3cb860c170baa3a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001877024_480518144.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:471e274fde9bddf3cd24ee9e14bea65c93e3bf333f1dfa9c47c561ebe90e8c0c +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001889856_483803136.pth b/checkpoint_p1/milestones/checkpoint_001889856_483803136.pth new file mode 100644 index 0000000000000000000000000000000000000000..8f994bd1ef0251dd4c6d2f8ad902c8d6b79d7968 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001889856_483803136.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6aea51b93c8b906b761e28ebf53b1be5908c3247e37fb91fe3c7b4c864d8de9 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001902752_487104512.pth b/checkpoint_p1/milestones/checkpoint_001902752_487104512.pth new file mode 100644 index 0000000000000000000000000000000000000000..0be538497ac02692d147be06c79e6320c513654c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001902752_487104512.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34e9851d186cfa0316a3c359ebb064ff6057e5749c42afbc217210d981daeece +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001915584_490389504.pth b/checkpoint_p1/milestones/checkpoint_001915584_490389504.pth new file mode 100644 index 0000000000000000000000000000000000000000..9f841798ccfb5738ae09d623984fda95d0ae6f84 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001915584_490389504.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d988c56a4381e4254dbdeb4cc0ac603758918e813888cef011dc38c1a925477 +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001928416_493674496.pth b/checkpoint_p1/milestones/checkpoint_001928416_493674496.pth new file mode 100644 index 0000000000000000000000000000000000000000..00ebca53a606db247f7750c5b56b2069e55a541a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001928416_493674496.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d342dc512d099381d46917cd2a511380633341cad2842d183128187b60734fb +size 20797067 diff --git a/checkpoint_p1/milestones/checkpoint_001941344_496984064.pth b/checkpoint_p1/milestones/checkpoint_001941344_496984064.pth new file mode 100644 index 0000000000000000000000000000000000000000..6d971b80dd8e739a72d14193f313add854011ae5 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001941344_496984064.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d9c7407889939ce149f82e8132405e07cd98ea5e756b672f4cfe2d1244bee5a +size 20797067 diff --git a/config.json b/config.json index 7361bb412c214ed5932895d46e13a582b0efb16a..ed7fc89660a6ae8739889d8c5cb8c41153520aad 100644 --- a/config.json +++ b/config.json @@ -4,7 +4,7 @@ "env": "atari_seaquest", "experiment": "atari_seaquest_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_seaquest --experiment=atari_seaquest_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_seaquest --wandb_job_type=SF --wandb_tags=atari", + "command_line": "--algo=APPO --env=atari_seaquest --experiment=atari_seaquest_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_seaquest --wandb_job_type=SF --wandb_tags=atari", "cli_args": { "algo": "APPO", "env": "atari_seaquest", "experiment": "atari_seaquest_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_seaquest_APPO_20231015_021255_948214" + "wandb_unique_id": "atari_seaquest_APPO_20231125_210544_253155" } \ 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 5ce50d34868639d51b57b3780dee6c65e04628aa..1ef319278da1d9efa1faea1167ac54d03708ce3b 100644 --- a/replay.mp4 +++ b/replay.mp4 @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:64793ece4c8f55f1a558e5aa0e829cd9b689068e293b9f36db3d6a256ca1ccef -size 4170963 +oid sha256:52c508f2d8b0f81ff78d3312d4847ed161a91f2127d2ab3413474079fdae55cd +size 3696250 diff --git a/sf_log.txt b/sf_log.txt index e18e14cca45a21779cf23d7cbedc4ed5e2159df6..2f5a538546e981a677e15390dafd359fa2c33c44 100644 --- a/sf_log.txt +++ b/sf_log.txt @@ -1,26505 +1,3 @@ -[2023-10-15 02:13:02,425][87330] Saving configuration to ./train_atari/atari_seaquest_APPO/config.json... -[2023-10-15 02:13:02,742][87330] Rollout worker 0 uses device cpu -[2023-10-15 02:13:02,743][87330] Rollout worker 1 uses device cpu -[2023-10-15 02:13:02,743][87330] Rollout worker 2 uses device cpu -[2023-10-15 02:13:02,744][87330] Rollout worker 3 uses device cpu -[2023-10-15 02:13:02,744][87330] Rollout worker 4 uses device cpu -[2023-10-15 02:13:02,745][87330] Rollout worker 5 uses device cpu -[2023-10-15 02:13:02,746][87330] Rollout worker 6 uses device cpu -[2023-10-15 02:13:02,746][87330] Rollout worker 7 uses device cpu -[2023-10-15 02:13:02,747][87330] Rollout worker 8 uses device cpu -[2023-10-15 02:13:02,747][87330] Rollout worker 9 uses device cpu -[2023-10-15 02:13:02,748][87330] Rollout worker 10 uses device cpu -[2023-10-15 02:13:02,748][87330] Rollout worker 11 uses device cpu -[2023-10-15 02:13:02,749][87330] Rollout worker 12 uses device cpu -[2023-10-15 02:13:02,749][87330] Rollout worker 13 uses device cpu -[2023-10-15 02:13:02,749][87330] Rollout worker 14 uses device cpu -[2023-10-15 02:13:02,749][87330] Rollout worker 15 uses device cpu -[2023-10-15 02:13:03,034][87330] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-10-15 02:13:03,034][87330] InferenceWorker_p0-w0: min num requests: 2 -[2023-10-15 02:13:03,037][87330] Using GPUs [1] for process 1 (actually maps to GPUs [1]) -[2023-10-15 02:13:03,038][87330] InferenceWorker_p1-w0: min num requests: 2 -[2023-10-15 02:13:03,084][87330] Starting all processes... -[2023-10-15 02:13:03,085][87330] Starting process learner_proc0 -[2023-10-15 02:13:04,788][87330] Starting process learner_proc1 -[2023-10-15 02:13:04,792][87905] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-10-15 02:13:04,792][87905] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 -[2023-10-15 02:13:04,811][87905] Num visible devices: 1 -[2023-10-15 02:13:04,830][87905] Setting fixed seed 1234 -[2023-10-15 02:13:04,831][87905] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-10-15 02:13:04,831][87905] Initializing actor-critic model on device cuda:0 -[2023-10-15 02:13:04,832][87905] RunningMeanStd input shape: (4, 84, 84) -[2023-10-15 02:13:04,832][87905] RunningMeanStd input shape: (1,) -[2023-10-15 02:13:04,843][87905] ConvEncoder: input_channels=4 -[2023-10-15 02:13:04,996][87905] Conv encoder output size: 512 -[2023-10-15 02:13:04,998][87905] Created Actor Critic model with architecture: -[2023-10-15 02:13:04,998][87905] 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) - ) -) -[2023-10-15 02:13:05,567][87905] Using optimizer -[2023-10-15 02:13:05,568][87905] No checkpoints found -[2023-10-15 02:13:05,568][87905] Did not load from checkpoint, starting from scratch! -[2023-10-15 02:13:05,568][87905] Initialized policy 0 weights for model version 0 -[2023-10-15 02:13:05,570][87905] LearnerWorker_p0 finished initialization! -[2023-10-15 02:13:05,570][87905] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-10-15 02:13:06,548][87330] Starting all processes... -[2023-10-15 02:13:06,552][88033] Using GPUs [1] for process 1 (actually maps to GPUs [1]) -[2023-10-15 02:13:06,552][88033] Set environment var CUDA_VISIBLE_DEVICES to '1' (GPU indices [1]) for learning process 1 -[2023-10-15 02:13:06,556][87330] Starting process inference_proc0-0 -[2023-10-15 02:13:06,556][87330] Starting process inference_proc1-0 -[2023-10-15 02:13:06,556][87330] Starting process rollout_proc0 -[2023-10-15 02:13:06,556][87330] Starting process rollout_proc1 -[2023-10-15 02:13:06,557][87330] Starting process rollout_proc2 -[2023-10-15 02:13:06,571][88033] Num visible devices: 1 -[2023-10-15 02:13:06,557][87330] Starting process rollout_proc3 -[2023-10-15 02:13:06,559][87330] Starting process rollout_proc4 -[2023-10-15 02:13:06,560][87330] Starting process rollout_proc5 -[2023-10-15 02:13:06,561][87330] Starting process rollout_proc6 -[2023-10-15 02:13:06,563][87330] Starting process rollout_proc7 -[2023-10-15 02:13:06,566][87330] Starting process rollout_proc8 -[2023-10-15 02:13:06,598][88033] Setting fixed seed 1234 -[2023-10-15 02:13:06,599][88033] Using GPUs [0] for process 1 (actually maps to GPUs [1]) -[2023-10-15 02:13:06,599][88033] Initializing actor-critic model on device cuda:0 -[2023-10-15 02:13:06,600][88033] RunningMeanStd input shape: (4, 84, 84) -[2023-10-15 02:13:06,600][88033] RunningMeanStd input shape: (1,) -[2023-10-15 02:13:06,567][87330] Starting process rollout_proc9 -[2023-10-15 02:13:06,567][87330] Starting process rollout_proc10 -[2023-10-15 02:13:06,569][87330] Starting process rollout_proc11 -[2023-10-15 02:13:06,570][87330] Starting process rollout_proc12 -[2023-10-15 02:13:06,612][88033] ConvEncoder: input_channels=4 -[2023-10-15 02:13:06,571][87330] Starting process rollout_proc13 -[2023-10-15 02:13:06,922][88033] Conv encoder output size: 512 -[2023-10-15 02:13:06,940][88033] Created Actor Critic model with architecture: -[2023-10-15 02:13:06,942][88033] 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) - ) -) -[2023-10-15 02:13:07,822][88033] Using optimizer -[2023-10-15 02:13:07,823][88033] No checkpoints found -[2023-10-15 02:13:07,823][88033] Did not load from checkpoint, starting from scratch! -[2023-10-15 02:13:07,823][88033] Initialized policy 1 weights for model version 0 -[2023-10-15 02:13:07,825][88033] LearnerWorker_p1 finished initialization! -[2023-10-15 02:13:07,826][88033] Using GPUs [0] for process 1 (actually maps to GPUs [1]) -[2023-10-15 02:13:08,771][87330] Starting process rollout_proc14 -[2023-10-15 02:13:08,776][88346] Worker 5 uses CPU cores [10, 11] -[2023-10-15 02:13:08,787][87330] Starting process rollout_proc15 -[2023-10-15 02:13:08,791][88305] Worker 0 uses CPU cores [0, 1] -[2023-10-15 02:13:08,798][88342] Worker 3 uses CPU cores [6, 7] -[2023-10-15 02:13:08,867][88311] Worker 2 uses CPU cores [4, 5] -[2023-10-15 02:13:08,871][88298] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-10-15 02:13:08,871][88298] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 -[2023-10-15 02:13:08,873][88351] Worker 12 uses CPU cores [24, 25] -[2023-10-15 02:13:08,913][88298] Num visible devices: 1 -[2023-10-15 02:13:09,097][88344] Worker 6 uses CPU cores [12, 13] -[2023-10-15 02:13:09,099][88341] Worker 4 uses CPU cores [8, 9] -[2023-10-15 02:13:09,185][88349] Worker 11 uses CPU cores [22, 23] -[2023-10-15 02:13:09,187][88350] Worker 10 uses CPU cores [20, 21] -[2023-10-15 02:13:09,248][88306] Worker 1 uses CPU cores [2, 3] -[2023-10-15 02:13:09,289][88348] Worker 9 uses CPU cores [18, 19] -[2023-10-15 02:13:09,321][88347] Worker 7 uses CPU cores [14, 15] -[2023-10-15 02:13:09,372][88300] Using GPUs [1] for process 1 (actually maps to GPUs [1]) -[2023-10-15 02:13:09,373][88300] Set environment var CUDA_VISIBLE_DEVICES to '1' (GPU indices [1]) for inference process 1 -[2023-10-15 02:13:09,384][88352] Worker 13 uses CPU cores [26, 27] -[2023-10-15 02:13:09,392][88300] Num visible devices: 1 -[2023-10-15 02:13:09,477][88345] Worker 8 uses CPU cores [16, 17] -[2023-10-15 02:13:09,593][88298] RunningMeanStd input shape: (4, 84, 84) -[2023-10-15 02:13:09,594][88298] RunningMeanStd input shape: (1,) -[2023-10-15 02:13:09,605][88298] ConvEncoder: input_channels=4 -[2023-10-15 02:13:09,706][88298] Conv encoder output size: 512 -[2023-10-15 02:13:09,996][88300] RunningMeanStd input shape: (4, 84, 84) -[2023-10-15 02:13:09,996][88300] RunningMeanStd input shape: (1,) -[2023-10-15 02:13:10,008][88300] ConvEncoder: input_channels=4 -[2023-10-15 02:13:10,112][88300] Conv encoder output size: 512 -[2023-10-15 02:13:10,614][88948] Worker 14 uses CPU cores [28, 29] -[2023-10-15 02:13:10,656][87330] Inference worker 0-0 is ready! -[2023-10-15 02:13:10,657][87330] Inference worker 1-0 is ready! -[2023-10-15 02:13:10,658][88980] Worker 15 uses CPU cores [30, 31] -[2023-10-15 02:13:10,658][87330] All inference workers are ready! Signal rollout workers to start! -[2023-10-15 02:13:10,659][88344] EnvRunner 6-0 uses policy 0 -[2023-10-15 02:13:10,659][88311] EnvRunner 2-0 uses policy 0 -[2023-10-15 02:13:10,659][88352] EnvRunner 13-0 uses policy 1 -[2023-10-15 02:13:10,659][88306] EnvRunner 1-0 uses policy 1 -[2023-10-15 02:13:10,659][88341] EnvRunner 4-0 uses policy 0 -[2023-10-15 02:13:10,659][88345] EnvRunner 8-0 uses policy 0 -[2023-10-15 02:13:10,659][88305] EnvRunner 0-0 uses policy 0 -[2023-10-15 02:13:10,659][88348] EnvRunner 9-0 uses policy 1 -[2023-10-15 02:13:10,660][88342] EnvRunner 3-0 uses policy 1 -[2023-10-15 02:13:10,659][88347] EnvRunner 7-0 uses policy 1 -[2023-10-15 02:13:10,660][88349] EnvRunner 11-0 uses policy 1 -[2023-10-15 02:13:10,660][88346] EnvRunner 5-0 uses policy 1 -[2023-10-15 02:13:10,660][88350] EnvRunner 10-0 uses policy 0 -[2023-10-15 02:13:10,660][88351] EnvRunner 12-0 uses policy 0 -[2023-10-15 02:13:10,660][87330] 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) -[2023-10-15 02:13:10,724][88948] EnvRunner 14-0 uses policy 0 -[2023-10-15 02:13:10,770][88980] EnvRunner 15-0 uses policy 1 -[2023-10-15 02:13:13,022][87330] Heartbeat connected on Batcher_0 -[2023-10-15 02:13:13,024][87330] Heartbeat connected on LearnerWorker_p0 -[2023-10-15 02:13:13,027][87330] Heartbeat connected on Batcher_1 -[2023-10-15 02:13:13,030][87330] Heartbeat connected on LearnerWorker_p1 -[2023-10-15 02:13:13,036][87330] Heartbeat connected on InferenceWorker_p0-w0 -[2023-10-15 02:13:13,040][87330] Heartbeat connected on InferenceWorker_p1-w0 -[2023-10-15 02:13:13,046][87330] Heartbeat connected on RolloutWorker_w1 -[2023-10-15 02:13:13,047][87330] Heartbeat connected on RolloutWorker_w0 -[2023-10-15 02:13:13,050][87330] Heartbeat connected on RolloutWorker_w3 -[2023-10-15 02:13:13,051][87330] Heartbeat connected on RolloutWorker_w2 -[2023-10-15 02:13:13,053][87330] Heartbeat connected on RolloutWorker_w4 -[2023-10-15 02:13:13,059][87330] Heartbeat connected on RolloutWorker_w5 -[2023-10-15 02:13:13,062][87330] Heartbeat connected on RolloutWorker_w6 -[2023-10-15 02:13:13,064][87330] Heartbeat connected on RolloutWorker_w8 -[2023-10-15 02:13:13,065][87330] Heartbeat connected on RolloutWorker_w7 -[2023-10-15 02:13:13,068][87330] Heartbeat connected on RolloutWorker_w9 -[2023-10-15 02:13:13,073][87330] Heartbeat connected on RolloutWorker_w11 -[2023-10-15 02:13:13,074][87330] Heartbeat connected on RolloutWorker_w10 -[2023-10-15 02:13:13,076][87330] Heartbeat connected on RolloutWorker_w12 -[2023-10-15 02:13:13,077][87330] Heartbeat connected on RolloutWorker_w13 -[2023-10-15 02:13:13,080][87330] Heartbeat connected on RolloutWorker_w14 -[2023-10-15 02:13:13,085][87330] Heartbeat connected on RolloutWorker_w15 -[2023-10-15 02:13:13,534][87330] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 305.5, 1: 732.0. Samples: 2982. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) -[2023-10-15 02:13:13,535][87330] Avg episode reward: [(0, '0.455'), (1, '0.333')] -[2023-10-15 02:13:18,534][87330] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 864.3, 1: 1027.7. Samples: 14898. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) -[2023-10-15 02:13:18,534][87330] Avg episode reward: [(0, '0.785'), (1, '0.630')] -[2023-10-15 02:13:20,529][88300] Updated weights for policy 1, policy_version 10 (0.0010) -[2023-10-15 02:13:20,735][88298] Updated weights for policy 0, policy_version 10 (0.0007) -[2023-10-15 02:13:20,885][88300] Updated weights for policy 1, policy_version 20 (0.0008) -[2023-10-15 02:13:21,105][88298] Updated weights for policy 0, policy_version 20 (0.0008) -[2023-10-15 02:13:21,247][88300] Updated weights for policy 1, policy_version 30 (0.0008) -[2023-10-15 02:13:21,477][88298] Updated weights for policy 0, policy_version 30 (0.0008) -[2023-10-15 02:13:23,428][88300] Updated weights for policy 1, policy_version 40 (0.0009) -[2023-10-15 02:13:23,534][87330] Fps is (10 sec: 6553.6, 60 sec: 5090.4, 300 sec: 5090.4). Total num frames: 65536. Throughput: 0: 1168.5, 1: 1279.9. Samples: 31522. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-15 02:13:23,535][87330] Avg episode reward: [(0, '0.850'), (1, '0.640')] -[2023-10-15 02:13:23,789][88300] Updated weights for policy 1, policy_version 50 (0.0009) -[2023-10-15 02:13:23,837][88298] Updated weights for policy 0, policy_version 40 (0.0008) -[2023-10-15 02:13:24,159][88300] Updated weights for policy 1, policy_version 60 (0.0007) -[2023-10-15 02:13:24,210][88298] Updated weights for policy 0, policy_version 50 (0.0009) -[2023-10-15 02:13:24,580][88298] Updated weights for policy 0, policy_version 60 (0.0010) -[2023-10-15 02:13:27,770][88300] Updated weights for policy 1, policy_version 70 (0.0008) -[2023-10-15 02:13:28,050][88298] Updated weights for policy 0, policy_version 70 (0.0008) -[2023-10-15 02:13:28,143][88300] Updated weights for policy 1, policy_version 80 (0.0008) -[2023-10-15 02:13:28,412][88298] Updated weights for policy 0, policy_version 80 (0.0007) -[2023-10-15 02:13:28,507][88300] Updated weights for policy 1, policy_version 90 (0.0008) -[2023-10-15 02:13:28,534][87330] Fps is (10 sec: 13106.9, 60 sec: 7333.0, 300 sec: 7333.0). Total num frames: 131072. Throughput: 0: 1437.4, 1: 1475.0. Samples: 52056. Policy #0 lag: (min: 33.0, avg: 33.0, max: 33.0) -[2023-10-15 02:13:28,535][87330] Avg episode reward: [(0, '1.010'), (1, '1.000')] -[2023-10-15 02:13:28,778][88298] Updated weights for policy 0, policy_version 90 (0.0008) -[2023-10-15 02:13:32,155][88300] Updated weights for policy 1, policy_version 100 (0.0008) -[2023-10-15 02:13:32,515][88300] Updated weights for policy 1, policy_version 110 (0.0008) -[2023-10-15 02:13:32,532][88298] Updated weights for policy 0, policy_version 100 (0.0010) -[2023-10-15 02:13:32,878][88300] Updated weights for policy 1, policy_version 120 (0.0007) -[2023-10-15 02:13:32,899][88298] Updated weights for policy 0, policy_version 110 (0.0007) -[2023-10-15 02:13:33,274][88298] Updated weights for policy 0, policy_version 120 (0.0007) -[2023-10-15 02:13:33,534][87330] Fps is (10 sec: 16384.3, 60 sec: 10027.7, 300 sec: 10027.7). Total num frames: 229376. Throughput: 0: 1327.8, 1: 1394.5. Samples: 62270. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:13:33,534][87330] Avg episode reward: [(0, '1.190'), (1, '1.470')] -[2023-10-15 02:13:33,535][88033] Saving new best policy, reward=1.470! -[2023-10-15 02:13:36,861][88300] Updated weights for policy 1, policy_version 130 (0.0007) -[2023-10-15 02:13:37,216][88300] Updated weights for policy 1, policy_version 140 (0.0010) -[2023-10-15 02:13:37,301][88298] Updated weights for policy 0, policy_version 130 (0.0007) -[2023-10-15 02:13:37,583][88300] Updated weights for policy 1, policy_version 150 (0.0008) -[2023-10-15 02:13:37,677][88298] Updated weights for policy 0, policy_version 140 (0.0008) -[2023-10-15 02:13:37,943][88300] Updated weights for policy 1, policy_version 160 (0.0007) -[2023-10-15 02:13:38,052][88298] Updated weights for policy 0, policy_version 150 (0.0009) -[2023-10-15 02:13:38,426][88298] Updated weights for policy 0, policy_version 160 (0.0007) -[2023-10-15 02:13:38,534][87330] Fps is (10 sec: 19661.2, 60 sec: 11755.7, 300 sec: 11755.7). Total num frames: 327680. Throughput: 0: 1473.3, 1: 1508.7. Samples: 83122. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-10-15 02:13:38,534][87330] Avg episode reward: [(0, '1.300'), (1, '1.720')] -[2023-10-15 02:13:38,535][88033] Saving new best policy, reward=1.720! -[2023-10-15 02:13:38,535][87905] Saving new best policy, reward=1.300! -[2023-10-15 02:13:41,862][88300] Updated weights for policy 1, policy_version 170 (0.0007) -[2023-10-15 02:13:42,223][88300] Updated weights for policy 1, policy_version 180 (0.0008) -[2023-10-15 02:13:42,390][88298] Updated weights for policy 0, policy_version 170 (0.0010) -[2023-10-15 02:13:42,589][88300] Updated weights for policy 1, policy_version 190 (0.0008) -[2023-10-15 02:13:42,757][88298] Updated weights for policy 0, policy_version 180 (0.0007) -[2023-10-15 02:13:43,127][88298] Updated weights for policy 0, policy_version 190 (0.0007) -[2023-10-15 02:13:43,534][87330] Fps is (10 sec: 16383.7, 60 sec: 11961.2, 300 sec: 11961.2). Total num frames: 393216. Throughput: 0: 1550.7, 1: 1583.5. Samples: 103034. Policy #0 lag: (min: 31.0, avg: 39.9, max: 63.0) -[2023-10-15 02:13:43,535][87330] Avg episode reward: [(0, '1.690'), (1, '2.100')] -[2023-10-15 02:13:43,542][87905] Saving new best policy, reward=1.690! -[2023-10-15 02:13:43,544][88033] Saving new best policy, reward=2.100! -[2023-10-15 02:13:46,453][88300] Updated weights for policy 1, policy_version 200 (0.0010) -[2023-10-15 02:13:46,809][88300] Updated weights for policy 1, policy_version 210 (0.0009) -[2023-10-15 02:13:47,094][88298] Updated weights for policy 0, policy_version 200 (0.0007) -[2023-10-15 02:13:47,172][88300] Updated weights for policy 1, policy_version 220 (0.0008) -[2023-10-15 02:13:47,463][88298] Updated weights for policy 0, policy_version 210 (0.0008) -[2023-10-15 02:13:47,827][88298] Updated weights for policy 0, policy_version 220 (0.0008) -[2023-10-15 02:13:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 12112.6, 300 sec: 12112.6). Total num frames: 458752. Throughput: 0: 1490.1, 1: 1533.0. Samples: 114498. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-15 02:13:48,534][87330] Avg episode reward: [(0, '2.130'), (1, '2.550')] -[2023-10-15 02:13:48,535][87905] Saving new best policy, reward=2.130! -[2023-10-15 02:13:48,535][88033] Saving new best policy, reward=2.550! -[2023-10-15 02:13:51,292][88300] Updated weights for policy 1, policy_version 230 (0.0008) -[2023-10-15 02:13:51,603][88298] Updated weights for policy 0, policy_version 230 (0.0009) -[2023-10-15 02:13:51,657][88300] Updated weights for policy 1, policy_version 240 (0.0008) -[2023-10-15 02:13:51,974][88298] Updated weights for policy 0, policy_version 240 (0.0007) -[2023-10-15 02:13:52,022][88300] Updated weights for policy 1, policy_version 250 (0.0007) -[2023-10-15 02:13:52,342][88298] Updated weights for policy 0, policy_version 250 (0.0008) -[2023-10-15 02:13:53,534][87330] Fps is (10 sec: 13107.4, 60 sec: 12228.5, 300 sec: 12228.5). Total num frames: 524288. Throughput: 0: 1556.3, 1: 1576.8. Samples: 134330. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-15 02:13:53,534][87330] Avg episode reward: [(0, '2.430'), (1, '2.710')] -[2023-10-15 02:13:53,535][88033] Saving new best policy, reward=2.710! -[2023-10-15 02:13:53,535][87905] Saving new best policy, reward=2.430! -[2023-10-15 02:13:55,916][88300] Updated weights for policy 1, policy_version 260 (0.0009) -[2023-10-15 02:13:56,277][88300] Updated weights for policy 1, policy_version 270 (0.0008) -[2023-10-15 02:13:56,373][88298] Updated weights for policy 0, policy_version 260 (0.0007) -[2023-10-15 02:13:56,650][88300] Updated weights for policy 1, policy_version 280 (0.0007) -[2023-10-15 02:13:56,742][88298] Updated weights for policy 0, policy_version 270 (0.0007) -[2023-10-15 02:13:57,110][88298] Updated weights for policy 0, policy_version 280 (0.0007) -[2023-10-15 02:13:58,534][87330] Fps is (10 sec: 13107.0, 60 sec: 12320.3, 300 sec: 12320.3). Total num frames: 589824. Throughput: 0: 1681.1, 1: 1693.9. Samples: 154858. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:13:58,534][87330] Avg episode reward: [(0, '2.450'), (1, '3.500')] -[2023-10-15 02:13:58,545][87905] Saving new best policy, reward=2.450! -[2023-10-15 02:13:58,545][88033] Saving new best policy, reward=3.500! -[2023-10-15 02:14:00,595][88300] Updated weights for policy 1, policy_version 290 (0.0007) -[2023-10-15 02:14:00,993][88298] Updated weights for policy 0, policy_version 290 (0.0009) -[2023-10-15 02:14:01,002][88300] Updated weights for policy 1, policy_version 300 (0.0009) -[2023-10-15 02:14:01,354][88298] Updated weights for policy 0, policy_version 300 (0.0009) -[2023-10-15 02:14:01,372][88300] Updated weights for policy 1, policy_version 310 (0.0008) -[2023-10-15 02:14:01,719][88298] Updated weights for policy 0, policy_version 310 (0.0009) -[2023-10-15 02:14:01,728][88300] Updated weights for policy 1, policy_version 320 (0.0008) -[2023-10-15 02:14:02,097][88298] Updated weights for policy 0, policy_version 320 (0.0008) -[2023-10-15 02:14:03,534][87330] Fps is (10 sec: 13106.9, 60 sec: 12394.6, 300 sec: 12394.6). Total num frames: 655360. Throughput: 0: 1684.5, 1: 1679.2. Samples: 166264. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:14:03,535][87330] Avg episode reward: [(0, '2.460'), (1, '3.660')] -[2023-10-15 02:14:03,536][87905] Saving new best policy, reward=2.460! -[2023-10-15 02:14:03,537][88033] Saving new best policy, reward=3.660! -[2023-10-15 02:14:05,583][88300] Updated weights for policy 1, policy_version 330 (0.0009) -[2023-10-15 02:14:05,954][88300] Updated weights for policy 1, policy_version 340 (0.0008) -[2023-10-15 02:14:06,021][88298] Updated weights for policy 0, policy_version 330 (0.0008) -[2023-10-15 02:14:06,312][88300] Updated weights for policy 1, policy_version 350 (0.0008) -[2023-10-15 02:14:06,384][88298] Updated weights for policy 0, policy_version 340 (0.0007) -[2023-10-15 02:14:06,751][88298] Updated weights for policy 0, policy_version 350 (0.0008) -[2023-10-15 02:14:08,534][87330] Fps is (10 sec: 13107.1, 60 sec: 12456.2, 300 sec: 12456.2). Total num frames: 720896. Throughput: 0: 1708.8, 1: 1718.3. Samples: 185740. Policy #0 lag: (min: 26.0, avg: 36.5, max: 58.0) -[2023-10-15 02:14:08,535][87330] Avg episode reward: [(0, '2.660'), (1, '3.250')] -[2023-10-15 02:14:08,536][87905] Saving new best policy, reward=2.660! -[2023-10-15 02:14:10,165][88300] Updated weights for policy 1, policy_version 360 (0.0010) -[2023-10-15 02:14:10,528][88300] Updated weights for policy 1, policy_version 370 (0.0007) -[2023-10-15 02:14:10,755][88298] Updated weights for policy 0, policy_version 360 (0.0007) -[2023-10-15 02:14:10,885][88300] Updated weights for policy 1, policy_version 380 (0.0007) -[2023-10-15 02:14:11,136][88298] Updated weights for policy 0, policy_version 370 (0.0007) -[2023-10-15 02:14:11,506][88298] Updated weights for policy 0, policy_version 380 (0.0009) -[2023-10-15 02:14:13,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12508.0). Total num frames: 786432. Throughput: 0: 1702.9, 1: 1739.2. Samples: 206950. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-15 02:14:13,535][87330] Avg episode reward: [(0, '2.820'), (1, '2.980')] -[2023-10-15 02:14:13,547][87905] Saving new best policy, reward=2.820! -[2023-10-15 02:14:14,835][88300] Updated weights for policy 1, policy_version 390 (0.0008) -[2023-10-15 02:14:15,197][88300] Updated weights for policy 1, policy_version 400 (0.0007) -[2023-10-15 02:14:15,435][88298] Updated weights for policy 0, policy_version 390 (0.0007) -[2023-10-15 02:14:15,574][88300] Updated weights for policy 1, policy_version 410 (0.0007) -[2023-10-15 02:14:15,801][88298] Updated weights for policy 0, policy_version 400 (0.0008) -[2023-10-15 02:14:16,173][88298] Updated weights for policy 0, policy_version 410 (0.0011) -[2023-10-15 02:14:18,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 12552.1). Total num frames: 851968. Throughput: 0: 1718.9, 1: 1722.9. Samples: 217154. Policy #0 lag: (min: 22.0, avg: 25.0, max: 54.0) -[2023-10-15 02:14:18,535][87330] Avg episode reward: [(0, '2.800'), (1, '3.300')] -[2023-10-15 02:14:19,397][88300] Updated weights for policy 1, policy_version 420 (0.0010) -[2023-10-15 02:14:19,749][88300] Updated weights for policy 1, policy_version 430 (0.0010) -[2023-10-15 02:14:20,114][88300] Updated weights for policy 1, policy_version 440 (0.0010) -[2023-10-15 02:14:20,196][88298] Updated weights for policy 0, policy_version 420 (0.0008) -[2023-10-15 02:14:20,563][88298] Updated weights for policy 0, policy_version 430 (0.0007) -[2023-10-15 02:14:20,926][88298] Updated weights for policy 0, policy_version 440 (0.0008) -[2023-10-15 02:14:23,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 12590.2). Total num frames: 917504. Throughput: 0: 1703.5, 1: 1742.7. Samples: 238206. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:14:23,535][87330] Avg episode reward: [(0, '2.740'), (1, '3.680')] -[2023-10-15 02:14:23,537][88033] Saving new best policy, reward=3.680! -[2023-10-15 02:14:24,128][88300] Updated weights for policy 1, policy_version 450 (0.0008) -[2023-10-15 02:14:24,495][88300] Updated weights for policy 1, policy_version 460 (0.0008) -[2023-10-15 02:14:24,837][88298] Updated weights for policy 0, policy_version 450 (0.0007) -[2023-10-15 02:14:24,859][88300] Updated weights for policy 1, policy_version 470 (0.0008) -[2023-10-15 02:14:25,207][88298] Updated weights for policy 0, policy_version 460 (0.0008) -[2023-10-15 02:14:25,229][88300] Updated weights for policy 1, policy_version 480 (0.0008) -[2023-10-15 02:14:25,580][88298] Updated weights for policy 0, policy_version 470 (0.0008) -[2023-10-15 02:14:25,940][88298] Updated weights for policy 0, policy_version 480 (0.0008) -[2023-10-15 02:14:28,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 12623.4). Total num frames: 983040. Throughput: 0: 1723.1, 1: 1760.7. Samples: 259802. Policy #0 lag: (min: 1.0, avg: 9.9, max: 33.0) -[2023-10-15 02:14:28,534][87330] Avg episode reward: [(0, '2.880'), (1, '3.450')] -[2023-10-15 02:14:28,542][87905] Saving new best policy, reward=2.880! -[2023-10-15 02:14:29,213][88300] Updated weights for policy 1, policy_version 490 (0.0010) -[2023-10-15 02:14:29,576][88300] Updated weights for policy 1, policy_version 500 (0.0009) -[2023-10-15 02:14:29,917][88298] Updated weights for policy 0, policy_version 490 (0.0009) -[2023-10-15 02:14:29,941][88300] Updated weights for policy 1, policy_version 510 (0.0007) -[2023-10-15 02:14:30,282][88298] Updated weights for policy 0, policy_version 500 (0.0007) -[2023-10-15 02:14:30,650][88298] Updated weights for policy 0, policy_version 510 (0.0007) -[2023-10-15 02:14:33,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 12652.6). Total num frames: 1048576. Throughput: 0: 1708.9, 1: 1733.3. Samples: 269398. Policy #0 lag: (min: 26.0, avg: 34.9, max: 58.0) -[2023-10-15 02:14:33,534][87330] Avg episode reward: [(0, '3.210'), (1, '3.600')] -[2023-10-15 02:14:33,535][87905] Saving new best policy, reward=3.210! -[2023-10-15 02:14:33,861][88300] Updated weights for policy 1, policy_version 520 (0.0007) -[2023-10-15 02:14:34,218][88300] Updated weights for policy 1, policy_version 530 (0.0008) -[2023-10-15 02:14:34,589][88300] Updated weights for policy 1, policy_version 540 (0.0008) -[2023-10-15 02:14:34,623][88298] Updated weights for policy 0, policy_version 520 (0.0009) -[2023-10-15 02:14:34,995][88298] Updated weights for policy 0, policy_version 530 (0.0010) -[2023-10-15 02:14:35,364][88298] Updated weights for policy 0, policy_version 540 (0.0010) -[2023-10-15 02:14:38,520][88300] Updated weights for policy 1, policy_version 550 (0.0009) -[2023-10-15 02:14:38,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12678.5). Total num frames: 1114112. Throughput: 0: 1713.0, 1: 1762.0. Samples: 290706. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:14:38,535][87330] Avg episode reward: [(0, '3.360'), (1, '3.460')] -[2023-10-15 02:14:38,535][87905] Saving new best policy, reward=3.360! -[2023-10-15 02:14:38,884][88300] Updated weights for policy 1, policy_version 560 (0.0010) -[2023-10-15 02:14:39,247][88300] Updated weights for policy 1, policy_version 570 (0.0008) -[2023-10-15 02:14:39,387][88298] Updated weights for policy 0, policy_version 550 (0.0008) -[2023-10-15 02:14:39,759][88298] Updated weights for policy 0, policy_version 560 (0.0009) -[2023-10-15 02:14:40,136][88298] Updated weights for policy 0, policy_version 570 (0.0009) -[2023-10-15 02:14:43,101][88300] Updated weights for policy 1, policy_version 580 (0.0007) -[2023-10-15 02:14:43,477][88300] Updated weights for policy 1, policy_version 590 (0.0009) -[2023-10-15 02:14:43,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 12701.6). Total num frames: 1179648. Throughput: 0: 1735.7, 1: 1757.1. Samples: 312034. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 02:14:43,535][87330] Avg episode reward: [(0, '3.690'), (1, '3.600')] -[2023-10-15 02:14:43,542][87905] Saving new best policy, reward=3.690! -[2023-10-15 02:14:43,839][88300] Updated weights for policy 1, policy_version 600 (0.0008) -[2023-10-15 02:14:44,005][88298] Updated weights for policy 0, policy_version 580 (0.0008) -[2023-10-15 02:14:44,372][88298] Updated weights for policy 0, policy_version 590 (0.0008) -[2023-10-15 02:14:44,744][88298] Updated weights for policy 0, policy_version 600 (0.0007) -[2023-10-15 02:14:47,733][88300] Updated weights for policy 1, policy_version 610 (0.0008) -[2023-10-15 02:14:48,122][88300] Updated weights for policy 1, policy_version 620 (0.0008) -[2023-10-15 02:14:48,483][88300] Updated weights for policy 1, policy_version 630 (0.0009) -[2023-10-15 02:14:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12722.3). Total num frames: 1245184. Throughput: 0: 1708.1, 1: 1752.4. Samples: 321986. Policy #0 lag: (min: 17.0, avg: 19.2, max: 42.0) -[2023-10-15 02:14:48,534][87330] Avg episode reward: [(0, '3.340'), (1, '3.570')] -[2023-10-15 02:14:48,768][88298] Updated weights for policy 0, policy_version 610 (0.0008) -[2023-10-15 02:14:48,851][88300] Updated weights for policy 1, policy_version 640 (0.0009) -[2023-10-15 02:14:49,138][88298] Updated weights for policy 0, policy_version 620 (0.0008) -[2023-10-15 02:14:49,509][88298] Updated weights for policy 0, policy_version 630 (0.0008) -[2023-10-15 02:14:49,880][88298] Updated weights for policy 0, policy_version 640 (0.0007) -[2023-10-15 02:14:52,722][88300] Updated weights for policy 1, policy_version 650 (0.0007) -[2023-10-15 02:14:53,087][88300] Updated weights for policy 1, policy_version 660 (0.0010) -[2023-10-15 02:14:53,453][88300] Updated weights for policy 1, policy_version 670 (0.0008) -[2023-10-15 02:14:53,535][87330] Fps is (10 sec: 16382.4, 60 sec: 13653.1, 300 sec: 13059.4). Total num frames: 1343488. Throughput: 0: 1735.3, 1: 1760.9. Samples: 343074. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-15 02:14:53,536][87330] Avg episode reward: [(0, '3.340'), (1, '3.560')] -[2023-10-15 02:14:53,812][88298] Updated weights for policy 0, policy_version 650 (0.0008) -[2023-10-15 02:14:54,186][88298] Updated weights for policy 0, policy_version 660 (0.0008) -[2023-10-15 02:14:54,555][88298] Updated weights for policy 0, policy_version 670 (0.0008) -[2023-10-15 02:14:57,432][88300] Updated weights for policy 1, policy_version 680 (0.0008) -[2023-10-15 02:14:57,810][88300] Updated weights for policy 1, policy_version 690 (0.0010) -[2023-10-15 02:14:58,174][88300] Updated weights for policy 1, policy_version 700 (0.0007) -[2023-10-15 02:14:58,390][88298] Updated weights for policy 0, policy_version 680 (0.0007) -[2023-10-15 02:14:58,534][87330] Fps is (10 sec: 16383.6, 60 sec: 13653.3, 300 sec: 13061.7). Total num frames: 1409024. Throughput: 0: 1745.3, 1: 1735.1. Samples: 363568. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:14:58,535][87330] Avg episode reward: [(0, '3.690'), (1, '3.560')] -[2023-10-15 02:14:58,544][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000000704_720896.pth... -[2023-10-15 02:14:58,770][88298] Updated weights for policy 0, policy_version 690 (0.0008) -[2023-10-15 02:14:59,146][88298] Updated weights for policy 0, policy_version 700 (0.0008) -[2023-10-15 02:14:59,299][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000000704_720896.pth... -[2023-10-15 02:15:01,846][88300] Updated weights for policy 1, policy_version 710 (0.0007) -[2023-10-15 02:15:02,212][88300] Updated weights for policy 1, policy_version 720 (0.0008) -[2023-10-15 02:15:02,587][88300] Updated weights for policy 1, policy_version 730 (0.0008) -[2023-10-15 02:15:02,918][88298] Updated weights for policy 0, policy_version 710 (0.0009) -[2023-10-15 02:15:03,291][88298] Updated weights for policy 0, policy_version 720 (0.0007) -[2023-10-15 02:15:03,534][87330] Fps is (10 sec: 13108.6, 60 sec: 13653.4, 300 sec: 13063.8). Total num frames: 1474560. Throughput: 0: 1724.8, 1: 1767.7. Samples: 374318. Policy #0 lag: (min: 15.0, avg: 17.9, max: 47.0) -[2023-10-15 02:15:03,534][87330] Avg episode reward: [(0, '3.470'), (1, '3.360')] -[2023-10-15 02:15:03,673][88298] Updated weights for policy 0, policy_version 730 (0.0009) -[2023-10-15 02:15:06,435][88300] Updated weights for policy 1, policy_version 740 (0.0009) -[2023-10-15 02:15:06,805][88300] Updated weights for policy 1, policy_version 750 (0.0010) -[2023-10-15 02:15:07,169][88300] Updated weights for policy 1, policy_version 760 (0.0007) -[2023-10-15 02:15:07,574][88298] Updated weights for policy 0, policy_version 740 (0.0010) -[2023-10-15 02:15:07,944][88298] Updated weights for policy 0, policy_version 750 (0.0008) -[2023-10-15 02:15:08,327][88298] Updated weights for policy 0, policy_version 760 (0.0010) -[2023-10-15 02:15:08,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13065.6). Total num frames: 1540096. Throughput: 0: 1743.9, 1: 1741.6. Samples: 395052. Policy #0 lag: (min: 4.0, avg: 6.0, max: 34.0) -[2023-10-15 02:15:08,534][87330] Avg episode reward: [(0, '3.630'), (1, '3.710')] -[2023-10-15 02:15:08,535][88033] Saving new best policy, reward=3.710! -[2023-10-15 02:15:11,109][88300] Updated weights for policy 1, policy_version 770 (0.0008) -[2023-10-15 02:15:11,484][88300] Updated weights for policy 1, policy_version 780 (0.0009) -[2023-10-15 02:15:11,849][88300] Updated weights for policy 1, policy_version 790 (0.0009) -[2023-10-15 02:15:12,215][88300] Updated weights for policy 1, policy_version 800 (0.0009) -[2023-10-15 02:15:12,377][88298] Updated weights for policy 0, policy_version 770 (0.0010) -[2023-10-15 02:15:12,757][88298] Updated weights for policy 0, policy_version 780 (0.0007) -[2023-10-15 02:15:13,134][88298] Updated weights for policy 0, policy_version 790 (0.0008) -[2023-10-15 02:15:13,504][88298] Updated weights for policy 0, policy_version 800 (0.0010) -[2023-10-15 02:15:13,534][87330] Fps is (10 sec: 16383.5, 60 sec: 14199.5, 300 sec: 13333.9). Total num frames: 1638400. Throughput: 0: 1731.5, 1: 1729.2. Samples: 415536. Policy #0 lag: (min: 15.0, avg: 19.3, max: 47.0) -[2023-10-15 02:15:13,535][87330] Avg episode reward: [(0, '3.830'), (1, '3.900')] -[2023-10-15 02:15:13,547][88033] Saving new best policy, reward=3.900! -[2023-10-15 02:15:13,547][87905] Saving new best policy, reward=3.830! -[2023-10-15 02:15:16,176][88300] Updated weights for policy 1, policy_version 810 (0.0010) -[2023-10-15 02:15:16,553][88300] Updated weights for policy 1, policy_version 820 (0.0007) -[2023-10-15 02:15:16,911][88300] Updated weights for policy 1, policy_version 830 (0.0008) -[2023-10-15 02:15:17,244][88298] Updated weights for policy 0, policy_version 810 (0.0008) -[2023-10-15 02:15:17,608][88298] Updated weights for policy 0, policy_version 820 (0.0007) -[2023-10-15 02:15:17,981][88298] Updated weights for policy 0, policy_version 830 (0.0008) -[2023-10-15 02:15:18,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13325.1). Total num frames: 1703936. Throughput: 0: 1744.0, 1: 1747.9. Samples: 426532. Policy #0 lag: (min: 12.0, avg: 18.3, max: 44.0) -[2023-10-15 02:15:18,535][87330] Avg episode reward: [(0, '4.380'), (1, '4.270')] -[2023-10-15 02:15:18,536][87905] Saving new best policy, reward=4.380! -[2023-10-15 02:15:18,536][88033] Saving new best policy, reward=4.270! -[2023-10-15 02:15:20,742][88300] Updated weights for policy 1, policy_version 840 (0.0010) -[2023-10-15 02:15:21,109][88300] Updated weights for policy 1, policy_version 850 (0.0011) -[2023-10-15 02:15:21,481][88300] Updated weights for policy 1, policy_version 860 (0.0009) -[2023-10-15 02:15:21,880][88298] Updated weights for policy 0, policy_version 840 (0.0007) -[2023-10-15 02:15:22,248][88298] Updated weights for policy 0, policy_version 850 (0.0007) -[2023-10-15 02:15:22,627][88298] Updated weights for policy 0, policy_version 860 (0.0007) -[2023-10-15 02:15:23,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13316.9). Total num frames: 1769472. Throughput: 0: 1746.7, 1: 1725.5. Samples: 446954. Policy #0 lag: (min: 8.0, avg: 36.2, max: 40.0) -[2023-10-15 02:15:23,534][87330] Avg episode reward: [(0, '4.280'), (1, '4.110')] -[2023-10-15 02:15:25,423][88300] Updated weights for policy 1, policy_version 870 (0.0007) -[2023-10-15 02:15:25,788][88300] Updated weights for policy 1, policy_version 880 (0.0007) -[2023-10-15 02:15:26,156][88300] Updated weights for policy 1, policy_version 890 (0.0008) -[2023-10-15 02:15:26,521][88298] Updated weights for policy 0, policy_version 870 (0.0009) -[2023-10-15 02:15:26,895][88298] Updated weights for policy 0, policy_version 880 (0.0009) -[2023-10-15 02:15:27,267][88298] Updated weights for policy 0, policy_version 890 (0.0011) -[2023-10-15 02:15:28,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13309.3). Total num frames: 1835008. Throughput: 0: 1717.9, 1: 1734.6. Samples: 467398. Policy #0 lag: (min: 16.0, avg: 44.3, max: 48.0) -[2023-10-15 02:15:28,535][87330] Avg episode reward: [(0, '4.170'), (1, '4.270')] -[2023-10-15 02:15:29,910][88300] Updated weights for policy 1, policy_version 900 (0.0007) -[2023-10-15 02:15:30,278][88300] Updated weights for policy 1, policy_version 910 (0.0007) -[2023-10-15 02:15:30,649][88300] Updated weights for policy 1, policy_version 920 (0.0008) -[2023-10-15 02:15:31,136][88298] Updated weights for policy 0, policy_version 900 (0.0009) -[2023-10-15 02:15:31,494][88298] Updated weights for policy 0, policy_version 910 (0.0010) -[2023-10-15 02:15:31,867][88298] Updated weights for policy 0, policy_version 920 (0.0009) -[2023-10-15 02:15:33,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13302.2). Total num frames: 1900544. Throughput: 0: 1748.3, 1: 1722.6. Samples: 478174. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-10-15 02:15:33,535][87330] Avg episode reward: [(0, '4.050'), (1, '4.000')] -[2023-10-15 02:15:34,579][88300] Updated weights for policy 1, policy_version 930 (0.0010) -[2023-10-15 02:15:34,947][88300] Updated weights for policy 1, policy_version 940 (0.0008) -[2023-10-15 02:15:35,312][88300] Updated weights for policy 1, policy_version 950 (0.0007) -[2023-10-15 02:15:35,648][88298] Updated weights for policy 0, policy_version 930 (0.0009) -[2023-10-15 02:15:35,675][88300] Updated weights for policy 1, policy_version 960 (0.0009) -[2023-10-15 02:15:36,012][88298] Updated weights for policy 0, policy_version 940 (0.0010) -[2023-10-15 02:15:36,380][88298] Updated weights for policy 0, policy_version 950 (0.0011) -[2023-10-15 02:15:36,753][88298] Updated weights for policy 0, policy_version 960 (0.0010) -[2023-10-15 02:15:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13295.6). Total num frames: 1966080. Throughput: 0: 1722.6, 1: 1729.3. Samples: 498406. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-15 02:15:38,535][87330] Avg episode reward: [(0, '4.150'), (1, '4.100')] -[2023-10-15 02:15:39,680][88300] Updated weights for policy 1, policy_version 970 (0.0011) -[2023-10-15 02:15:40,046][88300] Updated weights for policy 1, policy_version 980 (0.0009) -[2023-10-15 02:15:40,416][88300] Updated weights for policy 1, policy_version 990 (0.0008) -[2023-10-15 02:15:40,737][88298] Updated weights for policy 0, policy_version 970 (0.0007) -[2023-10-15 02:15:41,109][88298] Updated weights for policy 0, policy_version 980 (0.0007) -[2023-10-15 02:15:41,490][88298] Updated weights for policy 0, policy_version 990 (0.0007) -[2023-10-15 02:15:43,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13289.4). Total num frames: 2031616. Throughput: 0: 1721.0, 1: 1752.4. Samples: 519872. Policy #0 lag: (min: 21.0, avg: 23.8, max: 53.0) -[2023-10-15 02:15:43,535][87330] Avg episode reward: [(0, '4.130'), (1, '4.210')] -[2023-10-15 02:15:44,431][88300] Updated weights for policy 1, policy_version 1000 (0.0008) -[2023-10-15 02:15:44,804][88300] Updated weights for policy 1, policy_version 1010 (0.0009) -[2023-10-15 02:15:45,159][88300] Updated weights for policy 1, policy_version 1020 (0.0008) -[2023-10-15 02:15:45,374][88298] Updated weights for policy 0, policy_version 1000 (0.0009) -[2023-10-15 02:15:45,756][88298] Updated weights for policy 0, policy_version 1010 (0.0008) -[2023-10-15 02:15:46,126][88298] Updated weights for policy 0, policy_version 1020 (0.0010) -[2023-10-15 02:15:48,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13283.7). Total num frames: 2097152. Throughput: 0: 1737.1, 1: 1718.7. Samples: 529828. Policy #0 lag: (min: 13.0, avg: 13.4, max: 27.0) -[2023-10-15 02:15:48,534][87330] Avg episode reward: [(0, '3.730'), (1, '4.510')] -[2023-10-15 02:15:48,535][88033] Saving new best policy, reward=4.510! -[2023-10-15 02:15:49,077][88300] Updated weights for policy 1, policy_version 1030 (0.0008) -[2023-10-15 02:15:49,443][88300] Updated weights for policy 1, policy_version 1040 (0.0009) -[2023-10-15 02:15:49,807][88300] Updated weights for policy 1, policy_version 1050 (0.0008) -[2023-10-15 02:15:50,098][88298] Updated weights for policy 0, policy_version 1030 (0.0009) -[2023-10-15 02:15:50,476][88298] Updated weights for policy 0, policy_version 1040 (0.0007) -[2023-10-15 02:15:50,847][88298] Updated weights for policy 0, policy_version 1050 (0.0007) -[2023-10-15 02:15:53,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.5, 300 sec: 13278.3). Total num frames: 2162688. Throughput: 0: 1714.8, 1: 1735.3. Samples: 550310. Policy #0 lag: (min: 3.0, avg: 9.9, max: 35.0) -[2023-10-15 02:15:53,535][87330] Avg episode reward: [(0, '3.700'), (1, '4.990')] -[2023-10-15 02:15:53,705][88300] Updated weights for policy 1, policy_version 1060 (0.0007) -[2023-10-15 02:15:54,068][88300] Updated weights for policy 1, policy_version 1070 (0.0010) -[2023-10-15 02:15:54,434][88300] Updated weights for policy 1, policy_version 1080 (0.0008) -[2023-10-15 02:15:54,667][88298] Updated weights for policy 0, policy_version 1060 (0.0008) -[2023-10-15 02:15:54,728][88033] Saving new best policy, reward=4.990! -[2023-10-15 02:15:55,036][88298] Updated weights for policy 0, policy_version 1070 (0.0008) -[2023-10-15 02:15:55,414][88298] Updated weights for policy 0, policy_version 1080 (0.0008) -[2023-10-15 02:15:58,293][88300] Updated weights for policy 1, policy_version 1090 (0.0008) -[2023-10-15 02:15:58,534][87330] Fps is (10 sec: 13106.7, 60 sec: 13653.3, 300 sec: 13273.1). Total num frames: 2228224. Throughput: 0: 1725.3, 1: 1752.1. Samples: 572018. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-15 02:15:58,535][87330] Avg episode reward: [(0, '4.150'), (1, '5.090')] -[2023-10-15 02:15:58,672][88300] Updated weights for policy 1, policy_version 1100 (0.0010) -[2023-10-15 02:15:59,042][88300] Updated weights for policy 1, policy_version 1110 (0.0008) -[2023-10-15 02:15:59,303][88298] Updated weights for policy 0, policy_version 1090 (0.0008) -[2023-10-15 02:15:59,410][88033] Saving new best policy, reward=5.090! -[2023-10-15 02:15:59,414][88300] Updated weights for policy 1, policy_version 1120 (0.0009) -[2023-10-15 02:15:59,670][88298] Updated weights for policy 0, policy_version 1100 (0.0008) -[2023-10-15 02:16:00,049][88298] Updated weights for policy 0, policy_version 1110 (0.0008) -[2023-10-15 02:16:00,416][88298] Updated weights for policy 0, policy_version 1120 (0.0008) -[2023-10-15 02:16:03,262][88300] Updated weights for policy 1, policy_version 1130 (0.0007) -[2023-10-15 02:16:03,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13268.4). Total num frames: 2293760. Throughput: 0: 1712.8, 1: 1729.3. Samples: 581424. Policy #0 lag: (min: 6.0, avg: 12.0, max: 38.0) -[2023-10-15 02:16:03,534][87330] Avg episode reward: [(0, '4.550'), (1, '5.560')] -[2023-10-15 02:16:03,535][87905] Saving new best policy, reward=4.550! -[2023-10-15 02:16:03,628][88300] Updated weights for policy 1, policy_version 1140 (0.0011) -[2023-10-15 02:16:04,006][88300] Updated weights for policy 1, policy_version 1150 (0.0010) -[2023-10-15 02:16:04,071][88033] Saving new best policy, reward=5.560! -[2023-10-15 02:16:04,471][88298] Updated weights for policy 0, policy_version 1130 (0.0007) -[2023-10-15 02:16:04,839][88298] Updated weights for policy 0, policy_version 1140 (0.0009) -[2023-10-15 02:16:05,208][88298] Updated weights for policy 0, policy_version 1150 (0.0010) -[2023-10-15 02:16:07,868][88300] Updated weights for policy 1, policy_version 1160 (0.0008) -[2023-10-15 02:16:08,228][88300] Updated weights for policy 1, policy_version 1170 (0.0007) -[2023-10-15 02:16:08,534][87330] Fps is (10 sec: 13107.7, 60 sec: 13653.3, 300 sec: 13263.8). Total num frames: 2359296. Throughput: 0: 1711.0, 1: 1753.1. Samples: 602836. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) -[2023-10-15 02:16:08,535][87330] Avg episode reward: [(0, '4.690'), (1, '5.630')] -[2023-10-15 02:16:08,535][87905] Saving new best policy, reward=4.690! -[2023-10-15 02:16:08,599][88300] Updated weights for policy 1, policy_version 1180 (0.0007) -[2023-10-15 02:16:08,740][88033] Saving new best policy, reward=5.630! -[2023-10-15 02:16:09,215][88298] Updated weights for policy 0, policy_version 1160 (0.0009) -[2023-10-15 02:16:09,579][88298] Updated weights for policy 0, policy_version 1170 (0.0010) -[2023-10-15 02:16:09,959][88298] Updated weights for policy 0, policy_version 1180 (0.0007) -[2023-10-15 02:16:12,489][88300] Updated weights for policy 1, policy_version 1190 (0.0007) -[2023-10-15 02:16:12,861][88300] Updated weights for policy 1, policy_version 1200 (0.0008) -[2023-10-15 02:16:13,231][88300] Updated weights for policy 1, policy_version 1210 (0.0007) -[2023-10-15 02:16:13,534][87330] Fps is (10 sec: 16383.8, 60 sec: 13653.4, 300 sec: 13438.7). Total num frames: 2457600. Throughput: 0: 1743.9, 1: 1731.0. Samples: 623766. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-15 02:16:13,534][87330] Avg episode reward: [(0, '4.560'), (1, '5.430')] -[2023-10-15 02:16:13,983][88298] Updated weights for policy 0, policy_version 1190 (0.0007) -[2023-10-15 02:16:14,347][88298] Updated weights for policy 0, policy_version 1200 (0.0009) -[2023-10-15 02:16:14,713][88298] Updated weights for policy 0, policy_version 1210 (0.0007) -[2023-10-15 02:16:17,097][88300] Updated weights for policy 1, policy_version 1220 (0.0007) -[2023-10-15 02:16:17,466][88300] Updated weights for policy 1, policy_version 1230 (0.0008) -[2023-10-15 02:16:17,834][88300] Updated weights for policy 1, policy_version 1240 (0.0008) -[2023-10-15 02:16:18,534][87330] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13429.9). Total num frames: 2523136. Throughput: 0: 1715.6, 1: 1757.9. Samples: 634482. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:16:18,535][87330] Avg episode reward: [(0, '4.750'), (1, '5.300')] -[2023-10-15 02:16:18,592][88298] Updated weights for policy 0, policy_version 1220 (0.0008) -[2023-10-15 02:16:18,957][88298] Updated weights for policy 0, policy_version 1230 (0.0009) -[2023-10-15 02:16:19,336][88298] Updated weights for policy 0, policy_version 1240 (0.0009) -[2023-10-15 02:16:19,628][87905] Saving new best policy, reward=4.750! -[2023-10-15 02:16:21,756][88300] Updated weights for policy 1, policy_version 1250 (0.0010) -[2023-10-15 02:16:22,124][88300] Updated weights for policy 1, policy_version 1260 (0.0009) -[2023-10-15 02:16:22,484][88300] Updated weights for policy 1, policy_version 1270 (0.0008) -[2023-10-15 02:16:22,860][88300] Updated weights for policy 1, policy_version 1280 (0.0008) -[2023-10-15 02:16:23,286][88298] Updated weights for policy 0, policy_version 1250 (0.0008) -[2023-10-15 02:16:23,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13421.5). Total num frames: 2588672. Throughput: 0: 1743.6, 1: 1741.6. Samples: 655244. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-15 02:16:23,535][87330] Avg episode reward: [(0, '4.970'), (1, '5.260')] -[2023-10-15 02:16:23,653][88298] Updated weights for policy 0, policy_version 1260 (0.0009) -[2023-10-15 02:16:24,027][88298] Updated weights for policy 0, policy_version 1270 (0.0008) -[2023-10-15 02:16:24,397][88298] Updated weights for policy 0, policy_version 1280 (0.0007) -[2023-10-15 02:16:24,398][87905] Saving new best policy, reward=4.970! -[2023-10-15 02:16:26,779][88300] Updated weights for policy 1, policy_version 1290 (0.0009) -[2023-10-15 02:16:27,145][88300] Updated weights for policy 1, policy_version 1300 (0.0009) -[2023-10-15 02:16:27,517][88300] Updated weights for policy 1, policy_version 1310 (0.0009) -[2023-10-15 02:16:28,244][88298] Updated weights for policy 0, policy_version 1290 (0.0007) -[2023-10-15 02:16:28,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13413.6). Total num frames: 2654208. Throughput: 0: 1744.4, 1: 1721.1. Samples: 675818. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-15 02:16:28,535][87330] Avg episode reward: [(0, '5.260'), (1, '5.480')] -[2023-10-15 02:16:28,613][88298] Updated weights for policy 0, policy_version 1300 (0.0007) -[2023-10-15 02:16:28,994][88298] Updated weights for policy 0, policy_version 1310 (0.0008) -[2023-10-15 02:16:29,063][87905] Saving new best policy, reward=5.260! -[2023-10-15 02:16:31,285][88300] Updated weights for policy 1, policy_version 1320 (0.0009) -[2023-10-15 02:16:31,661][88300] Updated weights for policy 1, policy_version 1330 (0.0010) -[2023-10-15 02:16:32,029][88300] Updated weights for policy 1, policy_version 1340 (0.0010) -[2023-10-15 02:16:33,027][88298] Updated weights for policy 0, policy_version 1320 (0.0010) -[2023-10-15 02:16:33,407][88298] Updated weights for policy 0, policy_version 1330 (0.0011) -[2023-10-15 02:16:33,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13406.1). Total num frames: 2719744. Throughput: 0: 1731.1, 1: 1750.1. Samples: 686482. Policy #0 lag: (min: 26.0, avg: 34.4, max: 58.0) -[2023-10-15 02:16:33,535][87330] Avg episode reward: [(0, '5.000'), (1, '5.520')] -[2023-10-15 02:16:33,774][88298] Updated weights for policy 0, policy_version 1340 (0.0010) -[2023-10-15 02:16:35,945][88300] Updated weights for policy 1, policy_version 1350 (0.0009) -[2023-10-15 02:16:36,318][88300] Updated weights for policy 1, policy_version 1360 (0.0007) -[2023-10-15 02:16:36,686][88300] Updated weights for policy 1, policy_version 1370 (0.0007) -[2023-10-15 02:16:37,711][88298] Updated weights for policy 0, policy_version 1350 (0.0008) -[2023-10-15 02:16:38,090][88298] Updated weights for policy 0, policy_version 1360 (0.0007) -[2023-10-15 02:16:38,450][88298] Updated weights for policy 0, policy_version 1370 (0.0007) -[2023-10-15 02:16:38,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13398.9). Total num frames: 2785280. Throughput: 0: 1745.1, 1: 1726.5. Samples: 706532. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-15 02:16:38,535][87330] Avg episode reward: [(0, '5.360'), (1, '5.680')] -[2023-10-15 02:16:38,536][88033] Saving new best policy, reward=5.680! -[2023-10-15 02:16:38,673][87905] Saving new best policy, reward=5.360! -[2023-10-15 02:16:40,586][88300] Updated weights for policy 1, policy_version 1380 (0.0007) -[2023-10-15 02:16:40,961][88300] Updated weights for policy 1, policy_version 1390 (0.0010) -[2023-10-15 02:16:41,325][88300] Updated weights for policy 1, policy_version 1400 (0.0009) -[2023-10-15 02:16:42,518][88298] Updated weights for policy 0, policy_version 1380 (0.0009) -[2023-10-15 02:16:42,893][88298] Updated weights for policy 0, policy_version 1390 (0.0008) -[2023-10-15 02:16:43,261][88298] Updated weights for policy 0, policy_version 1400 (0.0007) -[2023-10-15 02:16:43,534][87330] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13392.0). Total num frames: 2850816. Throughput: 0: 1733.5, 1: 1728.4. Samples: 727800. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-15 02:16:43,535][87330] Avg episode reward: [(0, '5.500'), (1, '5.390')] -[2023-10-15 02:16:43,558][87905] Saving new best policy, reward=5.500! -[2023-10-15 02:16:45,174][88300] Updated weights for policy 1, policy_version 1410 (0.0010) -[2023-10-15 02:16:45,550][88300] Updated weights for policy 1, policy_version 1420 (0.0009) -[2023-10-15 02:16:45,925][88300] Updated weights for policy 1, policy_version 1430 (0.0007) -[2023-10-15 02:16:46,288][88300] Updated weights for policy 1, policy_version 1440 (0.0009) -[2023-10-15 02:16:47,120][88298] Updated weights for policy 0, policy_version 1410 (0.0007) -[2023-10-15 02:16:47,492][88298] Updated weights for policy 0, policy_version 1420 (0.0007) -[2023-10-15 02:16:47,861][88298] Updated weights for policy 0, policy_version 1430 (0.0007) -[2023-10-15 02:16:48,235][88298] Updated weights for policy 0, policy_version 1440 (0.0007) -[2023-10-15 02:16:48,534][87330] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 13535.9). Total num frames: 2949120. Throughput: 0: 1740.5, 1: 1736.8. Samples: 737904. Policy #0 lag: (min: 15.0, avg: 23.3, max: 47.0) -[2023-10-15 02:16:48,534][87330] Avg episode reward: [(0, '5.650'), (1, '5.620')] -[2023-10-15 02:16:48,535][87905] Saving new best policy, reward=5.650! -[2023-10-15 02:16:50,237][88300] Updated weights for policy 1, policy_version 1450 (0.0009) -[2023-10-15 02:16:50,597][88300] Updated weights for policy 1, policy_version 1460 (0.0008) -[2023-10-15 02:16:50,964][88300] Updated weights for policy 1, policy_version 1470 (0.0008) -[2023-10-15 02:16:52,128][88298] Updated weights for policy 0, policy_version 1450 (0.0009) -[2023-10-15 02:16:52,509][88298] Updated weights for policy 0, policy_version 1460 (0.0010) -[2023-10-15 02:16:52,876][88298] Updated weights for policy 0, policy_version 1470 (0.0009) -[2023-10-15 02:16:53,534][87330] Fps is (10 sec: 16384.8, 60 sec: 14199.5, 300 sec: 13526.3). Total num frames: 3014656. Throughput: 0: 1744.3, 1: 1731.1. Samples: 759226. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:16:53,534][87330] Avg episode reward: [(0, '5.460'), (1, '5.630')] -[2023-10-15 02:16:54,701][88300] Updated weights for policy 1, policy_version 1480 (0.0009) -[2023-10-15 02:16:55,079][88300] Updated weights for policy 1, policy_version 1490 (0.0008) -[2023-10-15 02:16:55,451][88300] Updated weights for policy 1, policy_version 1500 (0.0007) -[2023-10-15 02:16:56,549][88298] Updated weights for policy 0, policy_version 1480 (0.0009) -[2023-10-15 02:16:56,918][88298] Updated weights for policy 0, policy_version 1490 (0.0008) -[2023-10-15 02:16:57,296][88298] Updated weights for policy 0, policy_version 1500 (0.0007) -[2023-10-15 02:16:58,534][87330] Fps is (10 sec: 13106.7, 60 sec: 14199.5, 300 sec: 13517.1). Total num frames: 3080192. Throughput: 0: 1713.8, 1: 1750.3. Samples: 779648. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 02:16:58,535][87330] Avg episode reward: [(0, '4.970'), (1, '5.260')] -[2023-10-15 02:16:58,547][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000001504_1540096.pth... -[2023-10-15 02:16:58,547][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000001504_1540096.pth... -[2023-10-15 02:16:59,443][88300] Updated weights for policy 1, policy_version 1510 (0.0008) -[2023-10-15 02:16:59,803][88300] Updated weights for policy 1, policy_version 1520 (0.0010) -[2023-10-15 02:17:00,172][88300] Updated weights for policy 1, policy_version 1530 (0.0007) -[2023-10-15 02:17:01,284][88298] Updated weights for policy 0, policy_version 1510 (0.0009) -[2023-10-15 02:17:01,651][88298] Updated weights for policy 0, policy_version 1520 (0.0008) -[2023-10-15 02:17:02,034][88298] Updated weights for policy 0, policy_version 1530 (0.0007) -[2023-10-15 02:17:03,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13508.3). Total num frames: 3145728. Throughput: 0: 1742.1, 1: 1726.3. Samples: 790558. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-15 02:17:03,534][87330] Avg episode reward: [(0, '5.530'), (1, '5.380')] -[2023-10-15 02:17:04,047][88300] Updated weights for policy 1, policy_version 1540 (0.0008) -[2023-10-15 02:17:04,417][88300] Updated weights for policy 1, policy_version 1550 (0.0007) -[2023-10-15 02:17:04,791][88300] Updated weights for policy 1, policy_version 1560 (0.0010) -[2023-10-15 02:17:05,922][88298] Updated weights for policy 0, policy_version 1540 (0.0007) -[2023-10-15 02:17:06,287][88298] Updated weights for policy 0, policy_version 1550 (0.0007) -[2023-10-15 02:17:06,668][88298] Updated weights for policy 0, policy_version 1560 (0.0008) -[2023-10-15 02:17:08,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 13499.8). Total num frames: 3211264. Throughput: 0: 1720.3, 1: 1740.3. Samples: 810968. Policy #0 lag: (min: 17.0, avg: 35.4, max: 49.0) -[2023-10-15 02:17:08,535][87330] Avg episode reward: [(0, '5.620'), (1, '5.280')] -[2023-10-15 02:17:08,763][88300] Updated weights for policy 1, policy_version 1570 (0.0008) -[2023-10-15 02:17:09,134][88300] Updated weights for policy 1, policy_version 1580 (0.0008) -[2023-10-15 02:17:09,509][88300] Updated weights for policy 1, policy_version 1590 (0.0007) -[2023-10-15 02:17:09,869][88300] Updated weights for policy 1, policy_version 1600 (0.0010) -[2023-10-15 02:17:10,524][88298] Updated weights for policy 0, policy_version 1570 (0.0008) -[2023-10-15 02:17:10,901][88298] Updated weights for policy 0, policy_version 1580 (0.0009) -[2023-10-15 02:17:11,277][88298] Updated weights for policy 0, policy_version 1590 (0.0011) -[2023-10-15 02:17:11,640][88298] Updated weights for policy 0, policy_version 1600 (0.0009) -[2023-10-15 02:17:13,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13491.8). Total num frames: 3276800. Throughput: 0: 1711.1, 1: 1765.6. Samples: 832266. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-15 02:17:13,534][87330] Avg episode reward: [(0, '6.270'), (1, '5.200')] -[2023-10-15 02:17:13,541][87905] Saving new best policy, reward=6.270! -[2023-10-15 02:17:13,688][88300] Updated weights for policy 1, policy_version 1610 (0.0010) -[2023-10-15 02:17:14,058][88300] Updated weights for policy 1, policy_version 1620 (0.0007) -[2023-10-15 02:17:14,417][88300] Updated weights for policy 1, policy_version 1630 (0.0007) -[2023-10-15 02:17:15,616][88298] Updated weights for policy 0, policy_version 1610 (0.0009) -[2023-10-15 02:17:15,988][88298] Updated weights for policy 0, policy_version 1620 (0.0008) -[2023-10-15 02:17:16,363][88298] Updated weights for policy 0, policy_version 1630 (0.0009) -[2023-10-15 02:17:18,185][88300] Updated weights for policy 1, policy_version 1640 (0.0009) -[2023-10-15 02:17:18,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13484.0). Total num frames: 3342336. Throughput: 0: 1729.6, 1: 1737.4. Samples: 842496. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-15 02:17:18,535][87330] Avg episode reward: [(0, '6.170'), (1, '5.660')] -[2023-10-15 02:17:18,554][88300] Updated weights for policy 1, policy_version 1650 (0.0008) -[2023-10-15 02:17:18,923][88300] Updated weights for policy 1, policy_version 1660 (0.0009) -[2023-10-15 02:17:20,215][88298] Updated weights for policy 0, policy_version 1640 (0.0010) -[2023-10-15 02:17:20,589][88298] Updated weights for policy 0, policy_version 1650 (0.0009) -[2023-10-15 02:17:20,963][88298] Updated weights for policy 0, policy_version 1660 (0.0007) -[2023-10-15 02:17:22,934][88300] Updated weights for policy 1, policy_version 1670 (0.0010) -[2023-10-15 02:17:23,314][88300] Updated weights for policy 1, policy_version 1680 (0.0011) -[2023-10-15 02:17:23,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13476.6). Total num frames: 3407872. Throughput: 0: 1716.2, 1: 1766.3. Samples: 863244. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-15 02:17:23,534][87330] Avg episode reward: [(0, '5.370'), (1, '5.280')] -[2023-10-15 02:17:23,674][88300] Updated weights for policy 1, policy_version 1690 (0.0007) -[2023-10-15 02:17:24,790][88298] Updated weights for policy 0, policy_version 1670 (0.0008) -[2023-10-15 02:17:25,166][88298] Updated weights for policy 0, policy_version 1680 (0.0008) -[2023-10-15 02:17:25,539][88298] Updated weights for policy 0, policy_version 1690 (0.0008) -[2023-10-15 02:17:27,659][88300] Updated weights for policy 1, policy_version 1700 (0.0008) -[2023-10-15 02:17:28,029][88300] Updated weights for policy 1, policy_version 1710 (0.0008) -[2023-10-15 02:17:28,404][88300] Updated weights for policy 1, policy_version 1720 (0.0008) -[2023-10-15 02:17:28,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13469.4). Total num frames: 3473408. Throughput: 0: 1728.3, 1: 1739.5. Samples: 883850. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-15 02:17:28,534][87330] Avg episode reward: [(0, '5.520'), (1, '5.750')] -[2023-10-15 02:17:28,694][88033] Saving new best policy, reward=5.750! -[2023-10-15 02:17:29,519][88298] Updated weights for policy 0, policy_version 1700 (0.0008) -[2023-10-15 02:17:29,890][88298] Updated weights for policy 0, policy_version 1710 (0.0009) -[2023-10-15 02:17:30,272][88298] Updated weights for policy 0, policy_version 1720 (0.0010) -[2023-10-15 02:17:32,225][88300] Updated weights for policy 1, policy_version 1730 (0.0008) -[2023-10-15 02:17:32,592][88300] Updated weights for policy 1, policy_version 1740 (0.0008) -[2023-10-15 02:17:32,961][88300] Updated weights for policy 1, policy_version 1750 (0.0008) -[2023-10-15 02:17:33,332][88300] Updated weights for policy 1, policy_version 1760 (0.0008) -[2023-10-15 02:17:33,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13587.2). Total num frames: 3571712. Throughput: 0: 1718.4, 1: 1750.9. Samples: 894024. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-15 02:17:33,534][87330] Avg episode reward: [(0, '5.630'), (1, '6.120')] -[2023-10-15 02:17:33,535][88033] Saving new best policy, reward=6.120! -[2023-10-15 02:17:34,280][88298] Updated weights for policy 0, policy_version 1730 (0.0007) -[2023-10-15 02:17:34,649][88298] Updated weights for policy 0, policy_version 1740 (0.0008) -[2023-10-15 02:17:35,010][88298] Updated weights for policy 0, policy_version 1750 (0.0009) -[2023-10-15 02:17:35,383][88298] Updated weights for policy 0, policy_version 1760 (0.0008) -[2023-10-15 02:17:37,188][88300] Updated weights for policy 1, policy_version 1770 (0.0007) -[2023-10-15 02:17:37,553][88300] Updated weights for policy 1, policy_version 1780 (0.0009) -[2023-10-15 02:17:37,915][88300] Updated weights for policy 1, policy_version 1790 (0.0008) -[2023-10-15 02:17:38,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13578.2). Total num frames: 3637248. Throughput: 0: 1718.0, 1: 1746.3. Samples: 915118. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:17:38,534][87330] Avg episode reward: [(0, '6.140'), (1, '6.300')] -[2023-10-15 02:17:38,535][88033] Saving new best policy, reward=6.300! -[2023-10-15 02:17:39,299][88298] Updated weights for policy 0, policy_version 1770 (0.0007) -[2023-10-15 02:17:39,663][88298] Updated weights for policy 0, policy_version 1780 (0.0007) -[2023-10-15 02:17:40,036][88298] Updated weights for policy 0, policy_version 1790 (0.0007) -[2023-10-15 02:17:41,908][88300] Updated weights for policy 1, policy_version 1800 (0.0007) -[2023-10-15 02:17:42,280][88300] Updated weights for policy 1, policy_version 1810 (0.0008) -[2023-10-15 02:17:42,645][88300] Updated weights for policy 1, policy_version 1820 (0.0009) -[2023-10-15 02:17:43,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13569.6). Total num frames: 3702784. Throughput: 0: 1749.3, 1: 1724.5. Samples: 935968. Policy #0 lag: (min: 8.0, avg: 30.2, max: 40.0) -[2023-10-15 02:17:43,535][87330] Avg episode reward: [(0, '6.150'), (1, '6.780')] -[2023-10-15 02:17:43,545][88033] Saving new best policy, reward=6.780! -[2023-10-15 02:17:43,958][88298] Updated weights for policy 0, policy_version 1800 (0.0007) -[2023-10-15 02:17:44,339][88298] Updated weights for policy 0, policy_version 1810 (0.0007) -[2023-10-15 02:17:44,713][88298] Updated weights for policy 0, policy_version 1820 (0.0007) -[2023-10-15 02:17:46,574][88300] Updated weights for policy 1, policy_version 1830 (0.0009) -[2023-10-15 02:17:46,938][88300] Updated weights for policy 1, policy_version 1840 (0.0008) -[2023-10-15 02:17:47,306][88300] Updated weights for policy 1, policy_version 1850 (0.0007) -[2023-10-15 02:17:48,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13561.2). Total num frames: 3768320. Throughput: 0: 1717.0, 1: 1755.3. Samples: 946812. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-15 02:17:48,535][87330] Avg episode reward: [(0, '6.110'), (1, '6.730')] -[2023-10-15 02:17:48,580][88298] Updated weights for policy 0, policy_version 1830 (0.0009) -[2023-10-15 02:17:48,957][88298] Updated weights for policy 0, policy_version 1840 (0.0007) -[2023-10-15 02:17:49,325][88298] Updated weights for policy 0, policy_version 1850 (0.0007) -[2023-10-15 02:17:51,247][88300] Updated weights for policy 1, policy_version 1860 (0.0009) -[2023-10-15 02:17:51,612][88300] Updated weights for policy 1, policy_version 1870 (0.0008) -[2023-10-15 02:17:51,983][88300] Updated weights for policy 1, policy_version 1880 (0.0008) -[2023-10-15 02:17:53,103][88298] Updated weights for policy 0, policy_version 1860 (0.0008) -[2023-10-15 02:17:53,478][88298] Updated weights for policy 0, policy_version 1870 (0.0008) -[2023-10-15 02:17:53,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13553.2). Total num frames: 3833856. Throughput: 0: 1742.5, 1: 1728.0. Samples: 967138. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) -[2023-10-15 02:17:53,534][87330] Avg episode reward: [(0, '6.790'), (1, '6.720')] -[2023-10-15 02:17:53,846][88298] Updated weights for policy 0, policy_version 1880 (0.0009) -[2023-10-15 02:17:54,147][87905] Saving new best policy, reward=6.790! -[2023-10-15 02:17:55,790][88300] Updated weights for policy 1, policy_version 1890 (0.0009) -[2023-10-15 02:17:56,148][88300] Updated weights for policy 1, policy_version 1900 (0.0010) -[2023-10-15 02:17:56,520][88300] Updated weights for policy 1, policy_version 1910 (0.0008) -[2023-10-15 02:17:56,897][88300] Updated weights for policy 1, policy_version 1920 (0.0010) -[2023-10-15 02:17:57,849][88298] Updated weights for policy 0, policy_version 1890 (0.0009) -[2023-10-15 02:17:58,214][88298] Updated weights for policy 0, policy_version 1900 (0.0009) -[2023-10-15 02:17:58,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13545.5). Total num frames: 3899392. Throughput: 0: 1746.8, 1: 1726.4. Samples: 988562. Policy #0 lag: (min: 26.0, avg: 31.1, max: 58.0) -[2023-10-15 02:17:58,534][87330] Avg episode reward: [(0, '7.030'), (1, '6.780')] -[2023-10-15 02:17:58,585][88298] Updated weights for policy 0, policy_version 1910 (0.0009) -[2023-10-15 02:17:58,963][87905] Saving new best policy, reward=7.030! -[2023-10-15 02:17:58,964][88298] Updated weights for policy 0, policy_version 1920 (0.0007) -[2023-10-15 02:18:00,863][88300] Updated weights for policy 1, policy_version 1930 (0.0008) -[2023-10-15 02:18:01,236][88300] Updated weights for policy 1, policy_version 1940 (0.0009) -[2023-10-15 02:18:01,612][88300] Updated weights for policy 1, policy_version 1950 (0.0008) -[2023-10-15 02:18:02,762][88298] Updated weights for policy 0, policy_version 1930 (0.0007) -[2023-10-15 02:18:03,140][88298] Updated weights for policy 0, policy_version 1940 (0.0008) -[2023-10-15 02:18:03,516][88298] Updated weights for policy 0, policy_version 1950 (0.0008) -[2023-10-15 02:18:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13538.0). Total num frames: 3964928. Throughput: 0: 1729.4, 1: 1732.9. Samples: 998298. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:18:03,534][87330] Avg episode reward: [(0, '7.460'), (1, '6.760')] -[2023-10-15 02:18:03,589][87905] Saving new best policy, reward=7.460! -[2023-10-15 02:18:05,604][88300] Updated weights for policy 1, policy_version 1960 (0.0009) -[2023-10-15 02:18:05,970][88300] Updated weights for policy 1, policy_version 1970 (0.0008) -[2023-10-15 02:18:06,341][88300] Updated weights for policy 1, policy_version 1980 (0.0009) -[2023-10-15 02:18:07,514][88298] Updated weights for policy 0, policy_version 1960 (0.0007) -[2023-10-15 02:18:07,879][88298] Updated weights for policy 0, policy_version 1970 (0.0007) -[2023-10-15 02:18:08,267][88298] Updated weights for policy 0, policy_version 1980 (0.0008) -[2023-10-15 02:18:08,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 4063232. Throughput: 0: 1749.1, 1: 1715.5. Samples: 1019152. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) -[2023-10-15 02:18:08,534][87330] Avg episode reward: [(0, '7.730'), (1, '7.000')] -[2023-10-15 02:18:08,535][88033] Saving new best policy, reward=7.000! -[2023-10-15 02:18:08,535][87905] Saving new best policy, reward=7.730! -[2023-10-15 02:18:10,137][88300] Updated weights for policy 1, policy_version 1990 (0.0009) -[2023-10-15 02:18:10,506][88300] Updated weights for policy 1, policy_version 2000 (0.0008) -[2023-10-15 02:18:10,880][88300] Updated weights for policy 1, policy_version 2010 (0.0009) -[2023-10-15 02:18:12,374][88298] Updated weights for policy 0, policy_version 1990 (0.0009) -[2023-10-15 02:18:12,747][88298] Updated weights for policy 0, policy_version 2000 (0.0008) -[2023-10-15 02:18:13,130][88298] Updated weights for policy 0, policy_version 2010 (0.0008) -[2023-10-15 02:18:13,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 4128768. Throughput: 0: 1726.9, 1: 1737.9. Samples: 1039766. Policy #0 lag: (min: 1.0, avg: 8.8, max: 33.0) -[2023-10-15 02:18:13,534][87330] Avg episode reward: [(0, '7.530'), (1, '7.180')] -[2023-10-15 02:18:13,542][88033] Saving new best policy, reward=7.180! -[2023-10-15 02:18:14,852][88300] Updated weights for policy 1, policy_version 2020 (0.0009) -[2023-10-15 02:18:15,217][88300] Updated weights for policy 1, policy_version 2030 (0.0009) -[2023-10-15 02:18:15,595][88300] Updated weights for policy 1, policy_version 2040 (0.0010) -[2023-10-15 02:18:16,928][88298] Updated weights for policy 0, policy_version 2020 (0.0007) -[2023-10-15 02:18:17,310][88298] Updated weights for policy 0, policy_version 2030 (0.0008) -[2023-10-15 02:18:17,677][88298] Updated weights for policy 0, policy_version 2040 (0.0010) -[2023-10-15 02:18:18,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 4194304. Throughput: 0: 1743.6, 1: 1717.4. Samples: 1049768. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:18:18,535][87330] Avg episode reward: [(0, '7.850'), (1, '6.970')] -[2023-10-15 02:18:18,535][87905] Saving new best policy, reward=7.850! -[2023-10-15 02:18:19,361][88300] Updated weights for policy 1, policy_version 2050 (0.0009) -[2023-10-15 02:18:19,726][88300] Updated weights for policy 1, policy_version 2060 (0.0007) -[2023-10-15 02:18:20,088][88300] Updated weights for policy 1, policy_version 2070 (0.0008) -[2023-10-15 02:18:20,456][88300] Updated weights for policy 1, policy_version 2080 (0.0009) -[2023-10-15 02:18:21,633][88298] Updated weights for policy 0, policy_version 2050 (0.0011) -[2023-10-15 02:18:22,005][88298] Updated weights for policy 0, policy_version 2060 (0.0008) -[2023-10-15 02:18:22,389][88298] Updated weights for policy 0, policy_version 2070 (0.0007) -[2023-10-15 02:18:22,767][88298] Updated weights for policy 0, policy_version 2080 (0.0008) -[2023-10-15 02:18:23,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 4259840. Throughput: 0: 1739.6, 1: 1736.0. Samples: 1071522. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:18:23,535][87330] Avg episode reward: [(0, '8.170'), (1, '7.070')] -[2023-10-15 02:18:23,536][87905] Saving new best policy, reward=8.170! -[2023-10-15 02:18:24,340][88300] Updated weights for policy 1, policy_version 2090 (0.0009) -[2023-10-15 02:18:24,711][88300] Updated weights for policy 1, policy_version 2100 (0.0007) -[2023-10-15 02:18:25,078][88300] Updated weights for policy 1, policy_version 2110 (0.0008) -[2023-10-15 02:18:26,772][88298] Updated weights for policy 0, policy_version 2090 (0.0008) -[2023-10-15 02:18:27,141][88298] Updated weights for policy 0, policy_version 2100 (0.0008) -[2023-10-15 02:18:27,511][88298] Updated weights for policy 0, policy_version 2110 (0.0008) -[2023-10-15 02:18:28,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 4325376. Throughput: 0: 1707.6, 1: 1754.5. Samples: 1091758. Policy #0 lag: (min: 26.0, avg: 26.9, max: 47.0) -[2023-10-15 02:18:28,534][87330] Avg episode reward: [(0, '8.370'), (1, '7.120')] -[2023-10-15 02:18:28,542][87905] Saving new best policy, reward=8.370! -[2023-10-15 02:18:29,038][88300] Updated weights for policy 1, policy_version 2120 (0.0008) -[2023-10-15 02:18:29,418][88300] Updated weights for policy 1, policy_version 2130 (0.0007) -[2023-10-15 02:18:29,785][88300] Updated weights for policy 1, policy_version 2140 (0.0008) -[2023-10-15 02:18:31,416][88298] Updated weights for policy 0, policy_version 2120 (0.0008) -[2023-10-15 02:18:31,797][88298] Updated weights for policy 0, policy_version 2130 (0.0008) -[2023-10-15 02:18:32,167][88298] Updated weights for policy 0, policy_version 2140 (0.0009) -[2023-10-15 02:18:33,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 4390912. Throughput: 0: 1740.1, 1: 1725.0. Samples: 1102740. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:18:33,534][87330] Avg episode reward: [(0, '8.830'), (1, '7.740')] -[2023-10-15 02:18:33,535][87905] Saving new best policy, reward=8.830! -[2023-10-15 02:18:33,708][88300] Updated weights for policy 1, policy_version 2150 (0.0008) -[2023-10-15 02:18:34,072][88300] Updated weights for policy 1, policy_version 2160 (0.0008) -[2023-10-15 02:18:34,447][88300] Updated weights for policy 1, policy_version 2170 (0.0007) -[2023-10-15 02:18:34,664][88033] Saving new best policy, reward=7.740! -[2023-10-15 02:18:36,139][88298] Updated weights for policy 0, policy_version 2150 (0.0009) -[2023-10-15 02:18:36,510][88298] Updated weights for policy 0, policy_version 2160 (0.0007) -[2023-10-15 02:18:36,883][88298] Updated weights for policy 0, policy_version 2170 (0.0007) -[2023-10-15 02:18:38,401][88300] Updated weights for policy 1, policy_version 2180 (0.0009) -[2023-10-15 02:18:38,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 4456448. Throughput: 0: 1717.6, 1: 1754.5. Samples: 1123382. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-15 02:18:38,534][87330] Avg episode reward: [(0, '8.750'), (1, '7.710')] -[2023-10-15 02:18:38,759][88300] Updated weights for policy 1, policy_version 2190 (0.0009) -[2023-10-15 02:18:39,138][88300] Updated weights for policy 1, policy_version 2200 (0.0007) -[2023-10-15 02:18:40,777][88298] Updated weights for policy 0, policy_version 2180 (0.0008) -[2023-10-15 02:18:41,145][88298] Updated weights for policy 0, policy_version 2190 (0.0007) -[2023-10-15 02:18:41,517][88298] Updated weights for policy 0, policy_version 2200 (0.0007) -[2023-10-15 02:18:43,139][88300] Updated weights for policy 1, policy_version 2210 (0.0008) -[2023-10-15 02:18:43,512][88300] Updated weights for policy 1, policy_version 2220 (0.0009) -[2023-10-15 02:18:43,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 4521984. Throughput: 0: 1714.8, 1: 1748.4. Samples: 1144404. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-15 02:18:43,534][87330] Avg episode reward: [(0, '9.140'), (1, '7.500')] -[2023-10-15 02:18:43,544][87905] Saving new best policy, reward=9.140! -[2023-10-15 02:18:43,886][88300] Updated weights for policy 1, policy_version 2230 (0.0008) -[2023-10-15 02:18:44,251][88300] Updated weights for policy 1, policy_version 2240 (0.0008) -[2023-10-15 02:18:45,302][88298] Updated weights for policy 0, policy_version 2210 (0.0007) -[2023-10-15 02:18:45,672][88298] Updated weights for policy 0, policy_version 2220 (0.0007) -[2023-10-15 02:18:46,041][88298] Updated weights for policy 0, policy_version 2230 (0.0008) -[2023-10-15 02:18:46,408][88298] Updated weights for policy 0, policy_version 2240 (0.0008) -[2023-10-15 02:18:48,116][88300] Updated weights for policy 1, policy_version 2250 (0.0008) -[2023-10-15 02:18:48,487][88300] Updated weights for policy 1, policy_version 2260 (0.0008) -[2023-10-15 02:18:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 4587520. Throughput: 0: 1733.7, 1: 1743.0. Samples: 1154752. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 02:18:48,534][87330] Avg episode reward: [(0, '9.350'), (1, '7.360')] -[2023-10-15 02:18:48,535][87905] Saving new best policy, reward=9.350! -[2023-10-15 02:18:48,847][88300] Updated weights for policy 1, policy_version 2270 (0.0008) -[2023-10-15 02:18:50,342][88298] Updated weights for policy 0, policy_version 2250 (0.0009) -[2023-10-15 02:18:50,713][88298] Updated weights for policy 0, policy_version 2260 (0.0007) -[2023-10-15 02:18:51,087][88298] Updated weights for policy 0, policy_version 2270 (0.0008) -[2023-10-15 02:18:52,554][88300] Updated weights for policy 1, policy_version 2280 (0.0007) -[2023-10-15 02:18:52,926][88300] Updated weights for policy 1, policy_version 2290 (0.0007) -[2023-10-15 02:18:53,301][88300] Updated weights for policy 1, policy_version 2300 (0.0010) -[2023-10-15 02:18:53,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 4685824. Throughput: 0: 1716.3, 1: 1764.4. Samples: 1175780. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 02:18:53,534][87330] Avg episode reward: [(0, '9.690'), (1, '7.110')] -[2023-10-15 02:18:53,535][87905] Saving new best policy, reward=9.690! -[2023-10-15 02:18:55,056][88298] Updated weights for policy 0, policy_version 2280 (0.0008) -[2023-10-15 02:18:55,430][88298] Updated weights for policy 0, policy_version 2290 (0.0009) -[2023-10-15 02:18:55,794][88298] Updated weights for policy 0, policy_version 2300 (0.0007) -[2023-10-15 02:18:57,213][88300] Updated weights for policy 1, policy_version 2310 (0.0007) -[2023-10-15 02:18:57,577][88300] Updated weights for policy 1, policy_version 2320 (0.0010) -[2023-10-15 02:18:57,953][88300] Updated weights for policy 1, policy_version 2330 (0.0009) -[2023-10-15 02:18:58,534][87330] Fps is (10 sec: 16383.4, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 4751360. Throughput: 0: 1742.2, 1: 1738.2. Samples: 1196384. Policy #0 lag: (min: 9.0, avg: 22.7, max: 41.0) -[2023-10-15 02:18:58,535][87330] Avg episode reward: [(0, '10.410'), (1, '7.470')] -[2023-10-15 02:18:58,547][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000002304_2359296.pth... -[2023-10-15 02:18:58,547][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000002336_2392064.pth... -[2023-10-15 02:18:58,584][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000000704_720896.pth -[2023-10-15 02:18:58,585][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000000704_720896.pth -[2023-10-15 02:18:58,589][87905] Saving new best policy, reward=10.410! -[2023-10-15 02:18:59,562][88298] Updated weights for policy 0, policy_version 2310 (0.0009) -[2023-10-15 02:18:59,940][88298] Updated weights for policy 0, policy_version 2320 (0.0007) -[2023-10-15 02:19:00,311][88298] Updated weights for policy 0, policy_version 2330 (0.0008) -[2023-10-15 02:19:01,979][88300] Updated weights for policy 1, policy_version 2340 (0.0010) -[2023-10-15 02:19:02,352][88300] Updated weights for policy 1, policy_version 2350 (0.0011) -[2023-10-15 02:19:02,724][88300] Updated weights for policy 1, policy_version 2360 (0.0010) -[2023-10-15 02:19:03,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 4816896. Throughput: 0: 1725.2, 1: 1769.3. Samples: 1207020. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:19:03,535][87330] Avg episode reward: [(0, '10.880'), (1, '7.340')] -[2023-10-15 02:19:03,536][87905] Saving new best policy, reward=10.880! -[2023-10-15 02:19:04,145][88298] Updated weights for policy 0, policy_version 2340 (0.0007) -[2023-10-15 02:19:04,518][88298] Updated weights for policy 0, policy_version 2350 (0.0007) -[2023-10-15 02:19:04,892][88298] Updated weights for policy 0, policy_version 2360 (0.0011) -[2023-10-15 02:19:06,724][88300] Updated weights for policy 1, policy_version 2370 (0.0009) -[2023-10-15 02:19:07,091][88300] Updated weights for policy 1, policy_version 2380 (0.0008) -[2023-10-15 02:19:07,455][88300] Updated weights for policy 1, policy_version 2390 (0.0009) -[2023-10-15 02:19:07,826][88300] Updated weights for policy 1, policy_version 2400 (0.0008) -[2023-10-15 02:19:08,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 4882432. Throughput: 0: 1733.3, 1: 1739.5. Samples: 1227800. Policy #0 lag: (min: 14.0, avg: 14.2, max: 23.0) -[2023-10-15 02:19:08,535][87330] Avg episode reward: [(0, '11.590'), (1, '7.750')] -[2023-10-15 02:19:08,536][87905] Saving new best policy, reward=11.590! -[2023-10-15 02:19:08,536][88033] Saving new best policy, reward=7.750! -[2023-10-15 02:19:08,812][88298] Updated weights for policy 0, policy_version 2370 (0.0011) -[2023-10-15 02:19:09,183][88298] Updated weights for policy 0, policy_version 2380 (0.0008) -[2023-10-15 02:19:09,561][88298] Updated weights for policy 0, policy_version 2390 (0.0008) -[2023-10-15 02:19:09,931][88298] Updated weights for policy 0, policy_version 2400 (0.0009) -[2023-10-15 02:19:11,607][88300] Updated weights for policy 1, policy_version 2410 (0.0007) -[2023-10-15 02:19:11,973][88300] Updated weights for policy 1, policy_version 2420 (0.0008) -[2023-10-15 02:19:12,338][88300] Updated weights for policy 1, policy_version 2430 (0.0007) -[2023-10-15 02:19:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 4947968. Throughput: 0: 1760.8, 1: 1726.9. Samples: 1248708. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-10-15 02:19:13,535][87330] Avg episode reward: [(0, '11.990'), (1, '7.290')] -[2023-10-15 02:19:13,936][88298] Updated weights for policy 0, policy_version 2410 (0.0009) -[2023-10-15 02:19:14,303][88298] Updated weights for policy 0, policy_version 2420 (0.0008) -[2023-10-15 02:19:14,685][88298] Updated weights for policy 0, policy_version 2430 (0.0008) -[2023-10-15 02:19:14,753][87905] Saving new best policy, reward=11.990! -[2023-10-15 02:19:16,001][88300] Updated weights for policy 1, policy_version 2440 (0.0008) -[2023-10-15 02:19:16,367][88300] Updated weights for policy 1, policy_version 2450 (0.0007) -[2023-10-15 02:19:16,736][88300] Updated weights for policy 1, policy_version 2460 (0.0007) -[2023-10-15 02:19:18,449][88298] Updated weights for policy 0, policy_version 2440 (0.0010) -[2023-10-15 02:19:18,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 5013504. Throughput: 0: 1726.3, 1: 1750.3. Samples: 1259190. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-15 02:19:18,535][87330] Avg episode reward: [(0, '12.390'), (1, '7.590')] -[2023-10-15 02:19:18,821][88298] Updated weights for policy 0, policy_version 2450 (0.0009) -[2023-10-15 02:19:19,174][88298] Updated weights for policy 0, policy_version 2460 (0.0009) -[2023-10-15 02:19:19,325][87905] Saving new best policy, reward=12.390! -[2023-10-15 02:19:20,541][88300] Updated weights for policy 1, policy_version 2470 (0.0007) -[2023-10-15 02:19:20,911][88300] Updated weights for policy 1, policy_version 2480 (0.0007) -[2023-10-15 02:19:21,287][88300] Updated weights for policy 1, policy_version 2490 (0.0009) -[2023-10-15 02:19:23,165][88298] Updated weights for policy 0, policy_version 2470 (0.0008) -[2023-10-15 02:19:23,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 5079040. Throughput: 0: 1750.3, 1: 1734.3. Samples: 1280188. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) -[2023-10-15 02:19:23,534][87330] Avg episode reward: [(0, '13.290'), (1, '7.900')] -[2023-10-15 02:19:23,534][88298] Updated weights for policy 0, policy_version 2480 (0.0009) -[2023-10-15 02:19:23,535][88033] Saving new best policy, reward=7.900! -[2023-10-15 02:19:23,908][88298] Updated weights for policy 0, policy_version 2490 (0.0009) -[2023-10-15 02:19:24,131][87905] Saving new best policy, reward=13.290! -[2023-10-15 02:19:25,126][88300] Updated weights for policy 1, policy_version 2500 (0.0009) -[2023-10-15 02:19:25,496][88300] Updated weights for policy 1, policy_version 2510 (0.0010) -[2023-10-15 02:19:25,861][88300] Updated weights for policy 1, policy_version 2520 (0.0008) -[2023-10-15 02:19:27,964][88298] Updated weights for policy 0, policy_version 2500 (0.0009) -[2023-10-15 02:19:28,336][88298] Updated weights for policy 0, policy_version 2510 (0.0008) -[2023-10-15 02:19:28,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 5144576. Throughput: 0: 1749.7, 1: 1739.9. Samples: 1301436. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-15 02:19:28,534][87330] Avg episode reward: [(0, '13.850'), (1, '7.280')] -[2023-10-15 02:19:28,714][88298] Updated weights for policy 0, policy_version 2520 (0.0008) -[2023-10-15 02:19:29,018][87905] Saving new best policy, reward=13.850! -[2023-10-15 02:19:29,748][88300] Updated weights for policy 1, policy_version 2530 (0.0008) -[2023-10-15 02:19:30,114][88300] Updated weights for policy 1, policy_version 2540 (0.0011) -[2023-10-15 02:19:30,490][88300] Updated weights for policy 1, policy_version 2550 (0.0010) -[2023-10-15 02:19:30,867][88300] Updated weights for policy 1, policy_version 2560 (0.0009) -[2023-10-15 02:19:32,631][88298] Updated weights for policy 0, policy_version 2530 (0.0009) -[2023-10-15 02:19:33,003][88298] Updated weights for policy 0, policy_version 2540 (0.0007) -[2023-10-15 02:19:33,377][88298] Updated weights for policy 0, policy_version 2550 (0.0007) -[2023-10-15 02:19:33,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 5210112. Throughput: 0: 1731.3, 1: 1738.3. Samples: 1310886. Policy #0 lag: (min: 18.0, avg: 19.2, max: 35.0) -[2023-10-15 02:19:33,534][87330] Avg episode reward: [(0, '14.100'), (1, '7.710')] -[2023-10-15 02:19:33,753][87905] Saving new best policy, reward=14.100! -[2023-10-15 02:19:33,756][88298] Updated weights for policy 0, policy_version 2560 (0.0007) -[2023-10-15 02:19:34,771][88300] Updated weights for policy 1, policy_version 2570 (0.0010) -[2023-10-15 02:19:35,132][88300] Updated weights for policy 1, policy_version 2580 (0.0008) -[2023-10-15 02:19:35,500][88300] Updated weights for policy 1, policy_version 2590 (0.0007) -[2023-10-15 02:19:37,569][88298] Updated weights for policy 0, policy_version 2570 (0.0009) -[2023-10-15 02:19:37,937][88298] Updated weights for policy 0, policy_version 2580 (0.0010) -[2023-10-15 02:19:38,315][88298] Updated weights for policy 0, policy_version 2590 (0.0008) -[2023-10-15 02:19:38,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 5308416. Throughput: 0: 1748.6, 1: 1732.8. Samples: 1332444. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:19:38,534][87330] Avg episode reward: [(0, '13.980'), (1, '7.320')] -[2023-10-15 02:19:39,445][88300] Updated weights for policy 1, policy_version 2600 (0.0008) -[2023-10-15 02:19:39,810][88300] Updated weights for policy 1, policy_version 2610 (0.0009) -[2023-10-15 02:19:40,186][88300] Updated weights for policy 1, policy_version 2620 (0.0007) -[2023-10-15 02:19:42,258][88298] Updated weights for policy 0, policy_version 2600 (0.0008) -[2023-10-15 02:19:42,629][88298] Updated weights for policy 0, policy_version 2610 (0.0009) -[2023-10-15 02:19:43,004][88298] Updated weights for policy 0, policy_version 2620 (0.0007) -[2023-10-15 02:19:43,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 5373952. Throughput: 0: 1724.1, 1: 1761.0. Samples: 1353212. Policy #0 lag: (min: 31.0, avg: 31.9, max: 51.0) -[2023-10-15 02:19:43,534][87330] Avg episode reward: [(0, '14.720'), (1, '7.660')] -[2023-10-15 02:19:43,542][87905] Saving new best policy, reward=14.720! -[2023-10-15 02:19:44,218][88300] Updated weights for policy 1, policy_version 2630 (0.0008) -[2023-10-15 02:19:44,590][88300] Updated weights for policy 1, policy_version 2640 (0.0009) -[2023-10-15 02:19:44,963][88300] Updated weights for policy 1, policy_version 2650 (0.0008) -[2023-10-15 02:19:46,978][88298] Updated weights for policy 0, policy_version 2630 (0.0008) -[2023-10-15 02:19:47,343][88298] Updated weights for policy 0, policy_version 2640 (0.0008) -[2023-10-15 02:19:47,712][88298] Updated weights for policy 0, policy_version 2650 (0.0008) -[2023-10-15 02:19:48,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 5439488. Throughput: 0: 1747.1, 1: 1735.6. Samples: 1363742. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 02:19:48,534][87330] Avg episode reward: [(0, '14.870'), (1, '8.430')] -[2023-10-15 02:19:48,535][87905] Saving new best policy, reward=14.870! -[2023-10-15 02:19:48,717][88300] Updated weights for policy 1, policy_version 2660 (0.0008) -[2023-10-15 02:19:49,084][88300] Updated weights for policy 1, policy_version 2670 (0.0009) -[2023-10-15 02:19:49,456][88300] Updated weights for policy 1, policy_version 2680 (0.0007) -[2023-10-15 02:19:49,743][88033] Saving new best policy, reward=8.430! -[2023-10-15 02:19:51,566][88298] Updated weights for policy 0, policy_version 2660 (0.0009) -[2023-10-15 02:19:51,930][88298] Updated weights for policy 0, policy_version 2670 (0.0010) -[2023-10-15 02:19:52,298][88298] Updated weights for policy 0, policy_version 2680 (0.0010) -[2023-10-15 02:19:53,517][88300] Updated weights for policy 1, policy_version 2690 (0.0011) -[2023-10-15 02:19:53,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 5505024. Throughput: 0: 1734.5, 1: 1753.7. Samples: 1384768. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 02:19:53,534][87330] Avg episode reward: [(0, '14.420'), (1, '8.310')] -[2023-10-15 02:19:53,896][88300] Updated weights for policy 1, policy_version 2700 (0.0010) -[2023-10-15 02:19:54,255][88300] Updated weights for policy 1, policy_version 2710 (0.0007) -[2023-10-15 02:19:54,621][88300] Updated weights for policy 1, policy_version 2720 (0.0011) -[2023-10-15 02:19:56,195][88298] Updated weights for policy 0, policy_version 2690 (0.0007) -[2023-10-15 02:19:56,572][88298] Updated weights for policy 0, policy_version 2700 (0.0008) -[2023-10-15 02:19:56,936][88298] Updated weights for policy 0, policy_version 2710 (0.0008) -[2023-10-15 02:19:57,314][88298] Updated weights for policy 0, policy_version 2720 (0.0008) -[2023-10-15 02:19:58,428][88300] Updated weights for policy 1, policy_version 2730 (0.0008) -[2023-10-15 02:19:58,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 5570560. Throughput: 0: 1712.1, 1: 1767.3. Samples: 1405284. Policy #0 lag: (min: 14.0, avg: 15.9, max: 45.0) -[2023-10-15 02:19:58,535][87330] Avg episode reward: [(0, '14.590'), (1, '8.670')] -[2023-10-15 02:19:58,796][88300] Updated weights for policy 1, policy_version 2740 (0.0008) -[2023-10-15 02:19:59,174][88300] Updated weights for policy 1, policy_version 2750 (0.0009) -[2023-10-15 02:19:59,243][88033] Saving new best policy, reward=8.670! -[2023-10-15 02:20:01,043][88298] Updated weights for policy 0, policy_version 2730 (0.0008) -[2023-10-15 02:20:01,413][88298] Updated weights for policy 0, policy_version 2740 (0.0007) -[2023-10-15 02:20:01,780][88298] Updated weights for policy 0, policy_version 2750 (0.0008) -[2023-10-15 02:20:03,138][88300] Updated weights for policy 1, policy_version 2760 (0.0009) -[2023-10-15 02:20:03,507][88300] Updated weights for policy 1, policy_version 2770 (0.0010) -[2023-10-15 02:20:03,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 5636096. Throughput: 0: 1742.5, 1: 1744.3. Samples: 1416094. Policy #0 lag: (min: 15.0, avg: 22.9, max: 47.0) -[2023-10-15 02:20:03,535][87330] Avg episode reward: [(0, '14.560'), (1, '8.710')] -[2023-10-15 02:20:03,876][88300] Updated weights for policy 1, policy_version 2780 (0.0008) -[2023-10-15 02:20:04,022][88033] Saving new best policy, reward=8.710! -[2023-10-15 02:20:05,549][88298] Updated weights for policy 0, policy_version 2760 (0.0007) -[2023-10-15 02:20:05,932][88298] Updated weights for policy 0, policy_version 2770 (0.0008) -[2023-10-15 02:20:06,302][88298] Updated weights for policy 0, policy_version 2780 (0.0011) -[2023-10-15 02:20:07,706][88300] Updated weights for policy 1, policy_version 2790 (0.0009) -[2023-10-15 02:20:08,064][88300] Updated weights for policy 1, policy_version 2800 (0.0008) -[2023-10-15 02:20:08,427][88300] Updated weights for policy 1, policy_version 2810 (0.0007) -[2023-10-15 02:20:08,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 5701632. Throughput: 0: 1713.7, 1: 1758.2. Samples: 1436426. Policy #0 lag: (min: 25.0, avg: 27.2, max: 51.0) -[2023-10-15 02:20:08,534][87330] Avg episode reward: [(0, '14.690'), (1, '8.380')] -[2023-10-15 02:20:10,071][88298] Updated weights for policy 0, policy_version 2790 (0.0009) -[2023-10-15 02:20:10,431][88298] Updated weights for policy 0, policy_version 2800 (0.0009) -[2023-10-15 02:20:10,810][88298] Updated weights for policy 0, policy_version 2810 (0.0009) -[2023-10-15 02:20:12,202][88300] Updated weights for policy 1, policy_version 2820 (0.0008) -[2023-10-15 02:20:12,563][88300] Updated weights for policy 1, policy_version 2830 (0.0010) -[2023-10-15 02:20:12,931][88300] Updated weights for policy 1, policy_version 2840 (0.0010) -[2023-10-15 02:20:13,534][87330] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 5799936. Throughput: 0: 1728.1, 1: 1732.7. Samples: 1457172. Policy #0 lag: (min: 19.0, avg: 23.4, max: 51.0) -[2023-10-15 02:20:13,534][87330] Avg episode reward: [(0, '14.470'), (1, '8.600')] -[2023-10-15 02:20:14,681][88298] Updated weights for policy 0, policy_version 2820 (0.0010) -[2023-10-15 02:20:15,056][88298] Updated weights for policy 0, policy_version 2830 (0.0009) -[2023-10-15 02:20:15,419][88298] Updated weights for policy 0, policy_version 2840 (0.0007) -[2023-10-15 02:20:16,873][88300] Updated weights for policy 1, policy_version 2850 (0.0009) -[2023-10-15 02:20:17,243][88300] Updated weights for policy 1, policy_version 2860 (0.0009) -[2023-10-15 02:20:17,600][88300] Updated weights for policy 1, policy_version 2870 (0.0008) -[2023-10-15 02:20:17,965][88300] Updated weights for policy 1, policy_version 2880 (0.0008) -[2023-10-15 02:20:18,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 5865472. Throughput: 0: 1732.4, 1: 1763.9. Samples: 1468218. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:20:18,535][87330] Avg episode reward: [(0, '14.530'), (1, '8.710')] -[2023-10-15 02:20:19,326][88298] Updated weights for policy 0, policy_version 2850 (0.0007) -[2023-10-15 02:20:19,702][88298] Updated weights for policy 0, policy_version 2860 (0.0009) -[2023-10-15 02:20:20,074][88298] Updated weights for policy 0, policy_version 2870 (0.0009) -[2023-10-15 02:20:20,440][88298] Updated weights for policy 0, policy_version 2880 (0.0009) -[2023-10-15 02:20:21,814][88300] Updated weights for policy 1, policy_version 2890 (0.0008) -[2023-10-15 02:20:22,185][88300] Updated weights for policy 1, policy_version 2900 (0.0007) -[2023-10-15 02:20:22,561][88300] Updated weights for policy 1, policy_version 2910 (0.0007) -[2023-10-15 02:20:23,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 5931008. Throughput: 0: 1736.8, 1: 1749.8. Samples: 1489344. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:20:23,534][87330] Avg episode reward: [(0, '14.390'), (1, '9.120')] -[2023-10-15 02:20:23,536][88033] Saving new best policy, reward=9.120! -[2023-10-15 02:20:24,370][88298] Updated weights for policy 0, policy_version 2890 (0.0010) -[2023-10-15 02:20:24,736][88298] Updated weights for policy 0, policy_version 2900 (0.0010) -[2023-10-15 02:20:25,108][88298] Updated weights for policy 0, policy_version 2910 (0.0011) -[2023-10-15 02:20:26,387][88300] Updated weights for policy 1, policy_version 2920 (0.0008) -[2023-10-15 02:20:26,766][88300] Updated weights for policy 1, policy_version 2930 (0.0009) -[2023-10-15 02:20:27,135][88300] Updated weights for policy 1, policy_version 2940 (0.0011) -[2023-10-15 02:20:28,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 5996544. Throughput: 0: 1760.7, 1: 1732.3. Samples: 1510396. Policy #0 lag: (min: 15.0, avg: 15.1, max: 21.0) -[2023-10-15 02:20:28,535][87330] Avg episode reward: [(0, '14.870'), (1, '9.600')] -[2023-10-15 02:20:28,546][88033] Saving new best policy, reward=9.600! -[2023-10-15 02:20:29,258][88298] Updated weights for policy 0, policy_version 2920 (0.0009) -[2023-10-15 02:20:29,646][88298] Updated weights for policy 0, policy_version 2930 (0.0007) -[2023-10-15 02:20:30,012][88298] Updated weights for policy 0, policy_version 2940 (0.0007) -[2023-10-15 02:20:31,122][88300] Updated weights for policy 1, policy_version 2950 (0.0010) -[2023-10-15 02:20:31,485][88300] Updated weights for policy 1, policy_version 2960 (0.0009) -[2023-10-15 02:20:31,855][88300] Updated weights for policy 1, policy_version 2970 (0.0008) -[2023-10-15 02:20:33,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13884.8). Total num frames: 6062080. Throughput: 0: 1734.5, 1: 1755.2. Samples: 1520778. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-15 02:20:33,535][87330] Avg episode reward: [(0, '14.990'), (1, '9.790')] -[2023-10-15 02:20:33,536][88033] Saving new best policy, reward=9.790! -[2023-10-15 02:20:33,788][88298] Updated weights for policy 0, policy_version 2950 (0.0009) -[2023-10-15 02:20:34,160][88298] Updated weights for policy 0, policy_version 2960 (0.0008) -[2023-10-15 02:20:34,531][88298] Updated weights for policy 0, policy_version 2970 (0.0009) -[2023-10-15 02:20:34,748][87905] Saving new best policy, reward=14.990! -[2023-10-15 02:20:35,851][88300] Updated weights for policy 1, policy_version 2980 (0.0010) -[2023-10-15 02:20:36,225][88300] Updated weights for policy 1, policy_version 2990 (0.0010) -[2023-10-15 02:20:36,586][88300] Updated weights for policy 1, policy_version 3000 (0.0009) -[2023-10-15 02:20:38,403][88298] Updated weights for policy 0, policy_version 2980 (0.0008) -[2023-10-15 02:20:38,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 6127616. Throughput: 0: 1748.8, 1: 1731.1. Samples: 1541366. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:20:38,534][87330] Avg episode reward: [(0, '15.090'), (1, '10.300')] -[2023-10-15 02:20:38,535][88033] Saving new best policy, reward=10.300! -[2023-10-15 02:20:38,773][88298] Updated weights for policy 0, policy_version 2990 (0.0008) -[2023-10-15 02:20:39,132][88298] Updated weights for policy 0, policy_version 3000 (0.0007) -[2023-10-15 02:20:39,424][87905] Saving new best policy, reward=15.090! -[2023-10-15 02:20:40,560][88300] Updated weights for policy 1, policy_version 3010 (0.0008) -[2023-10-15 02:20:40,931][88300] Updated weights for policy 1, policy_version 3020 (0.0007) -[2023-10-15 02:20:41,299][88300] Updated weights for policy 1, policy_version 3030 (0.0011) -[2023-10-15 02:20:41,665][88300] Updated weights for policy 1, policy_version 3040 (0.0008) -[2023-10-15 02:20:43,176][88298] Updated weights for policy 0, policy_version 3010 (0.0008) -[2023-10-15 02:20:43,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 6193152. Throughput: 0: 1768.2, 1: 1728.8. Samples: 1562648. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:20:43,535][87330] Avg episode reward: [(0, '15.720'), (1, '10.040')] -[2023-10-15 02:20:43,554][88298] Updated weights for policy 0, policy_version 3020 (0.0008) -[2023-10-15 02:20:43,919][88298] Updated weights for policy 0, policy_version 3030 (0.0008) -[2023-10-15 02:20:44,286][87905] Saving new best policy, reward=15.720! -[2023-10-15 02:20:44,287][88298] Updated weights for policy 0, policy_version 3040 (0.0010) -[2023-10-15 02:20:45,580][88300] Updated weights for policy 1, policy_version 3050 (0.0007) -[2023-10-15 02:20:45,954][88300] Updated weights for policy 1, policy_version 3060 (0.0007) -[2023-10-15 02:20:46,328][88300] Updated weights for policy 1, policy_version 3070 (0.0010) -[2023-10-15 02:20:48,307][88298] Updated weights for policy 0, policy_version 3050 (0.0010) -[2023-10-15 02:20:48,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 6258688. Throughput: 0: 1735.9, 1: 1733.1. Samples: 1572198. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-15 02:20:48,535][87330] Avg episode reward: [(0, '15.700'), (1, '10.250')] -[2023-10-15 02:20:48,673][88298] Updated weights for policy 0, policy_version 3060 (0.0010) -[2023-10-15 02:20:49,047][88298] Updated weights for policy 0, policy_version 3070 (0.0007) -[2023-10-15 02:20:50,101][88300] Updated weights for policy 1, policy_version 3080 (0.0008) -[2023-10-15 02:20:50,478][88300] Updated weights for policy 1, policy_version 3090 (0.0008) -[2023-10-15 02:20:50,853][88300] Updated weights for policy 1, policy_version 3100 (0.0007) -[2023-10-15 02:20:52,922][88298] Updated weights for policy 0, policy_version 3080 (0.0008) -[2023-10-15 02:20:53,291][88298] Updated weights for policy 0, policy_version 3090 (0.0007) -[2023-10-15 02:20:53,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 6324224. Throughput: 0: 1758.4, 1: 1726.9. Samples: 1593264. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-15 02:20:53,535][87330] Avg episode reward: [(0, '15.910'), (1, '10.200')] -[2023-10-15 02:20:53,669][88298] Updated weights for policy 0, policy_version 3100 (0.0008) -[2023-10-15 02:20:53,819][87905] Saving new best policy, reward=15.910! -[2023-10-15 02:20:54,706][88300] Updated weights for policy 1, policy_version 3110 (0.0008) -[2023-10-15 02:20:55,079][88300] Updated weights for policy 1, policy_version 3120 (0.0008) -[2023-10-15 02:20:55,448][88300] Updated weights for policy 1, policy_version 3130 (0.0009) -[2023-10-15 02:20:57,554][88298] Updated weights for policy 0, policy_version 3110 (0.0010) -[2023-10-15 02:20:57,926][88298] Updated weights for policy 0, policy_version 3120 (0.0007) -[2023-10-15 02:20:58,298][88298] Updated weights for policy 0, policy_version 3130 (0.0007) -[2023-10-15 02:20:58,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 6422528. Throughput: 0: 1735.7, 1: 1752.3. Samples: 1614130. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-10-15 02:20:58,535][87330] Avg episode reward: [(0, '16.190'), (1, '9.570')] -[2023-10-15 02:20:58,541][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000003136_3211264.pth... -[2023-10-15 02:20:58,541][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000003136_3211264.pth... -[2023-10-15 02:20:58,570][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000001504_1540096.pth -[2023-10-15 02:20:58,574][87905] Saving new best policy, reward=16.190! -[2023-10-15 02:20:58,582][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000001504_1540096.pth -[2023-10-15 02:20:59,281][88300] Updated weights for policy 1, policy_version 3140 (0.0009) -[2023-10-15 02:20:59,642][88300] Updated weights for policy 1, policy_version 3150 (0.0009) -[2023-10-15 02:21:00,020][88300] Updated weights for policy 1, policy_version 3160 (0.0010) -[2023-10-15 02:21:02,131][88298] Updated weights for policy 0, policy_version 3140 (0.0007) -[2023-10-15 02:21:02,493][88298] Updated weights for policy 0, policy_version 3150 (0.0007) -[2023-10-15 02:21:02,872][88298] Updated weights for policy 0, policy_version 3160 (0.0009) -[2023-10-15 02:21:03,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 6488064. Throughput: 0: 1745.7, 1: 1721.4. Samples: 1624236. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-10-15 02:21:03,535][87330] Avg episode reward: [(0, '16.150'), (1, '10.530')] -[2023-10-15 02:21:03,536][88033] Saving new best policy, reward=10.530! -[2023-10-15 02:21:03,804][88300] Updated weights for policy 1, policy_version 3170 (0.0010) -[2023-10-15 02:21:04,169][88300] Updated weights for policy 1, policy_version 3180 (0.0008) -[2023-10-15 02:21:04,546][88300] Updated weights for policy 1, policy_version 3190 (0.0007) -[2023-10-15 02:21:04,908][88300] Updated weights for policy 1, policy_version 3200 (0.0007) -[2023-10-15 02:21:06,877][88298] Updated weights for policy 0, policy_version 3170 (0.0009) -[2023-10-15 02:21:07,251][88298] Updated weights for policy 0, policy_version 3180 (0.0008) -[2023-10-15 02:21:07,622][88298] Updated weights for policy 0, policy_version 3190 (0.0007) -[2023-10-15 02:21:08,001][88298] Updated weights for policy 0, policy_version 3200 (0.0007) -[2023-10-15 02:21:08,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 6553600. Throughput: 0: 1739.8, 1: 1738.2. Samples: 1645852. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-15 02:21:08,535][87330] Avg episode reward: [(0, '16.370'), (1, '10.690')] -[2023-10-15 02:21:08,536][87905] Saving new best policy, reward=16.370! -[2023-10-15 02:21:08,827][88300] Updated weights for policy 1, policy_version 3210 (0.0007) -[2023-10-15 02:21:09,196][88300] Updated weights for policy 1, policy_version 3220 (0.0007) -[2023-10-15 02:21:09,557][88300] Updated weights for policy 1, policy_version 3230 (0.0007) -[2023-10-15 02:21:09,629][88033] Saving new best policy, reward=10.690! -[2023-10-15 02:21:12,002][88298] Updated weights for policy 0, policy_version 3210 (0.0007) -[2023-10-15 02:21:12,370][88298] Updated weights for policy 0, policy_version 3220 (0.0008) -[2023-10-15 02:21:12,742][88298] Updated weights for policy 0, policy_version 3230 (0.0007) -[2023-10-15 02:21:13,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 6619136. Throughput: 0: 1705.5, 1: 1754.6. Samples: 1666100. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-15 02:21:13,534][87330] Avg episode reward: [(0, '16.450'), (1, '10.200')] -[2023-10-15 02:21:13,544][87905] Saving new best policy, reward=16.450! -[2023-10-15 02:21:13,547][88300] Updated weights for policy 1, policy_version 3240 (0.0009) -[2023-10-15 02:21:13,909][88300] Updated weights for policy 1, policy_version 3250 (0.0009) -[2023-10-15 02:21:14,285][88300] Updated weights for policy 1, policy_version 3260 (0.0007) -[2023-10-15 02:21:16,895][88298] Updated weights for policy 0, policy_version 3240 (0.0009) -[2023-10-15 02:21:17,267][88298] Updated weights for policy 0, policy_version 3250 (0.0009) -[2023-10-15 02:21:17,648][88298] Updated weights for policy 0, policy_version 3260 (0.0009) -[2023-10-15 02:21:18,040][88300] Updated weights for policy 1, policy_version 3270 (0.0007) -[2023-10-15 02:21:18,409][88300] Updated weights for policy 1, policy_version 3280 (0.0008) -[2023-10-15 02:21:18,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 6684672. Throughput: 0: 1737.0, 1: 1729.6. Samples: 1676772. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-15 02:21:18,534][87330] Avg episode reward: [(0, '17.000'), (1, '10.570')] -[2023-10-15 02:21:18,535][87905] Saving new best policy, reward=17.000! -[2023-10-15 02:21:18,774][88300] Updated weights for policy 1, policy_version 3290 (0.0009) -[2023-10-15 02:21:21,482][88298] Updated weights for policy 0, policy_version 3270 (0.0008) -[2023-10-15 02:21:21,848][88298] Updated weights for policy 0, policy_version 3280 (0.0007) -[2023-10-15 02:21:22,228][88298] Updated weights for policy 0, policy_version 3290 (0.0007) -[2023-10-15 02:21:22,791][88300] Updated weights for policy 1, policy_version 3300 (0.0009) -[2023-10-15 02:21:23,165][88300] Updated weights for policy 1, policy_version 3310 (0.0009) -[2023-10-15 02:21:23,526][88300] Updated weights for policy 1, policy_version 3320 (0.0007) -[2023-10-15 02:21:23,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 6750208. Throughput: 0: 1716.3, 1: 1755.3. Samples: 1697590. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:21:23,535][87330] Avg episode reward: [(0, '17.100'), (1, '11.330')] -[2023-10-15 02:21:23,536][87905] Saving new best policy, reward=17.100! -[2023-10-15 02:21:23,817][88033] Saving new best policy, reward=11.330! -[2023-10-15 02:21:26,159][88298] Updated weights for policy 0, policy_version 3300 (0.0008) -[2023-10-15 02:21:26,526][88298] Updated weights for policy 0, policy_version 3310 (0.0009) -[2023-10-15 02:21:26,894][88298] Updated weights for policy 0, policy_version 3320 (0.0008) -[2023-10-15 02:21:27,378][88300] Updated weights for policy 1, policy_version 3330 (0.0012) -[2023-10-15 02:21:27,748][88300] Updated weights for policy 1, policy_version 3340 (0.0008) -[2023-10-15 02:21:28,109][88300] Updated weights for policy 1, policy_version 3350 (0.0010) -[2023-10-15 02:21:28,475][88300] Updated weights for policy 1, policy_version 3360 (0.0010) -[2023-10-15 02:21:28,534][87330] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 6848512. Throughput: 0: 1698.6, 1: 1736.9. Samples: 1717242. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:21:28,535][87330] Avg episode reward: [(0, '17.370'), (1, '10.740')] -[2023-10-15 02:21:28,543][87905] Saving new best policy, reward=17.370! -[2023-10-15 02:21:30,801][88298] Updated weights for policy 0, policy_version 3330 (0.0007) -[2023-10-15 02:21:31,172][88298] Updated weights for policy 0, policy_version 3340 (0.0007) -[2023-10-15 02:21:31,542][88298] Updated weights for policy 0, policy_version 3350 (0.0010) -[2023-10-15 02:21:31,908][88298] Updated weights for policy 0, policy_version 3360 (0.0011) -[2023-10-15 02:21:32,525][88300] Updated weights for policy 1, policy_version 3370 (0.0009) -[2023-10-15 02:21:32,892][88300] Updated weights for policy 1, policy_version 3380 (0.0009) -[2023-10-15 02:21:33,267][88300] Updated weights for policy 1, policy_version 3390 (0.0009) -[2023-10-15 02:21:33,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 6914048. Throughput: 0: 1729.4, 1: 1751.7. Samples: 1728848. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 02:21:33,534][87330] Avg episode reward: [(0, '17.630'), (1, '11.310')] -[2023-10-15 02:21:33,535][87905] Saving new best policy, reward=17.630! -[2023-10-15 02:21:35,786][88298] Updated weights for policy 0, policy_version 3370 (0.0007) -[2023-10-15 02:21:36,158][88298] Updated weights for policy 0, policy_version 3380 (0.0009) -[2023-10-15 02:21:36,522][88298] Updated weights for policy 0, policy_version 3390 (0.0009) -[2023-10-15 02:21:37,111][88300] Updated weights for policy 1, policy_version 3400 (0.0008) -[2023-10-15 02:21:37,477][88300] Updated weights for policy 1, policy_version 3410 (0.0008) -[2023-10-15 02:21:37,845][88300] Updated weights for policy 1, policy_version 3420 (0.0008) -[2023-10-15 02:21:38,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 6979584. Throughput: 0: 1700.8, 1: 1754.0. Samples: 1748730. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 02:21:38,535][87330] Avg episode reward: [(0, '17.470'), (1, '11.690')] -[2023-10-15 02:21:38,537][88033] Saving new best policy, reward=11.690! -[2023-10-15 02:21:40,493][88298] Updated weights for policy 0, policy_version 3400 (0.0008) -[2023-10-15 02:21:40,862][88298] Updated weights for policy 0, policy_version 3410 (0.0008) -[2023-10-15 02:21:41,231][88298] Updated weights for policy 0, policy_version 3420 (0.0008) -[2023-10-15 02:21:41,770][88300] Updated weights for policy 1, policy_version 3430 (0.0008) -[2023-10-15 02:21:42,142][88300] Updated weights for policy 1, policy_version 3440 (0.0007) -[2023-10-15 02:21:42,518][88300] Updated weights for policy 1, policy_version 3450 (0.0009) -[2023-10-15 02:21:43,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 7045120. Throughput: 0: 1718.9, 1: 1734.2. Samples: 1769520. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-15 02:21:43,535][87330] Avg episode reward: [(0, '17.450'), (1, '11.970')] -[2023-10-15 02:21:43,546][88033] Saving new best policy, reward=11.970! -[2023-10-15 02:21:45,123][88298] Updated weights for policy 0, policy_version 3430 (0.0008) -[2023-10-15 02:21:45,500][88298] Updated weights for policy 0, policy_version 3440 (0.0009) -[2023-10-15 02:21:45,880][88298] Updated weights for policy 0, policy_version 3450 (0.0008) -[2023-10-15 02:21:46,147][88300] Updated weights for policy 1, policy_version 3460 (0.0009) -[2023-10-15 02:21:46,511][88300] Updated weights for policy 1, policy_version 3470 (0.0007) -[2023-10-15 02:21:46,870][88300] Updated weights for policy 1, policy_version 3480 (0.0009) -[2023-10-15 02:21:48,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 7110656. Throughput: 0: 1714.4, 1: 1761.7. Samples: 1780658. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-15 02:21:48,534][87330] Avg episode reward: [(0, '17.480'), (1, '11.940')] -[2023-10-15 02:21:49,769][88298] Updated weights for policy 0, policy_version 3460 (0.0008) -[2023-10-15 02:21:50,146][88298] Updated weights for policy 0, policy_version 3470 (0.0007) -[2023-10-15 02:21:50,509][88298] Updated weights for policy 0, policy_version 3480 (0.0009) -[2023-10-15 02:21:50,811][88300] Updated weights for policy 1, policy_version 3490 (0.0009) -[2023-10-15 02:21:51,181][88300] Updated weights for policy 1, policy_version 3500 (0.0009) -[2023-10-15 02:21:51,550][88300] Updated weights for policy 1, policy_version 3510 (0.0010) -[2023-10-15 02:21:51,920][88300] Updated weights for policy 1, policy_version 3520 (0.0008) -[2023-10-15 02:21:53,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 7176192. Throughput: 0: 1706.2, 1: 1732.2. Samples: 1800580. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-15 02:21:53,535][87330] Avg episode reward: [(0, '17.570'), (1, '12.670')] -[2023-10-15 02:21:53,535][88033] Saving new best policy, reward=12.670! -[2023-10-15 02:21:54,274][88298] Updated weights for policy 0, policy_version 3490 (0.0008) -[2023-10-15 02:21:54,648][88298] Updated weights for policy 0, policy_version 3500 (0.0008) -[2023-10-15 02:21:55,031][88298] Updated weights for policy 0, policy_version 3510 (0.0009) -[2023-10-15 02:21:55,399][88298] Updated weights for policy 0, policy_version 3520 (0.0007) -[2023-10-15 02:21:55,796][88300] Updated weights for policy 1, policy_version 3530 (0.0009) -[2023-10-15 02:21:56,158][88300] Updated weights for policy 1, policy_version 3540 (0.0007) -[2023-10-15 02:21:56,522][88300] Updated weights for policy 1, policy_version 3550 (0.0008) -[2023-10-15 02:21:58,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 7241728. Throughput: 0: 1747.1, 1: 1732.8. Samples: 1822696. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:21:58,534][87330] Avg episode reward: [(0, '17.630'), (1, '12.910')] -[2023-10-15 02:21:58,543][88033] Saving new best policy, reward=12.910! -[2023-10-15 02:21:59,139][88298] Updated weights for policy 0, policy_version 3530 (0.0008) -[2023-10-15 02:21:59,511][88298] Updated weights for policy 0, policy_version 3540 (0.0010) -[2023-10-15 02:21:59,884][88298] Updated weights for policy 0, policy_version 3550 (0.0011) -[2023-10-15 02:22:00,534][88300] Updated weights for policy 1, policy_version 3560 (0.0007) -[2023-10-15 02:22:00,916][88300] Updated weights for policy 1, policy_version 3570 (0.0007) -[2023-10-15 02:22:01,280][88300] Updated weights for policy 1, policy_version 3580 (0.0008) -[2023-10-15 02:22:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 7307264. Throughput: 0: 1719.2, 1: 1736.8. Samples: 1832290. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:22:03,534][87330] Avg episode reward: [(0, '17.880'), (1, '13.160')] -[2023-10-15 02:22:03,535][88033] Saving new best policy, reward=13.160! -[2023-10-15 02:22:03,823][88298] Updated weights for policy 0, policy_version 3560 (0.0009) -[2023-10-15 02:22:04,190][88298] Updated weights for policy 0, policy_version 3570 (0.0007) -[2023-10-15 02:22:04,570][88298] Updated weights for policy 0, policy_version 3580 (0.0008) -[2023-10-15 02:22:04,716][87905] Saving new best policy, reward=17.880! -[2023-10-15 02:22:05,068][88300] Updated weights for policy 1, policy_version 3590 (0.0008) -[2023-10-15 02:22:05,446][88300] Updated weights for policy 1, policy_version 3600 (0.0007) -[2023-10-15 02:22:05,815][88300] Updated weights for policy 1, policy_version 3610 (0.0007) -[2023-10-15 02:22:08,417][88298] Updated weights for policy 0, policy_version 3590 (0.0008) -[2023-10-15 02:22:08,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 7372800. Throughput: 0: 1737.1, 1: 1729.9. Samples: 1853604. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:22:08,535][87330] Avg episode reward: [(0, '17.980'), (1, '13.020')] -[2023-10-15 02:22:08,783][88298] Updated weights for policy 0, policy_version 3600 (0.0008) -[2023-10-15 02:22:09,158][88298] Updated weights for policy 0, policy_version 3610 (0.0008) -[2023-10-15 02:22:09,378][87905] Saving new best policy, reward=17.980! -[2023-10-15 02:22:09,620][88300] Updated weights for policy 1, policy_version 3620 (0.0011) -[2023-10-15 02:22:09,993][88300] Updated weights for policy 1, policy_version 3630 (0.0010) -[2023-10-15 02:22:10,376][88300] Updated weights for policy 1, policy_version 3640 (0.0008) -[2023-10-15 02:22:13,146][88298] Updated weights for policy 0, policy_version 3620 (0.0009) -[2023-10-15 02:22:13,511][88298] Updated weights for policy 0, policy_version 3630 (0.0008) -[2023-10-15 02:22:13,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 7438336. Throughput: 0: 1752.8, 1: 1753.4. Samples: 1875024. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:22:13,535][87330] Avg episode reward: [(0, '17.820'), (1, '13.270')] -[2023-10-15 02:22:13,545][88033] Saving new best policy, reward=13.270! -[2023-10-15 02:22:13,889][88298] Updated weights for policy 0, policy_version 3640 (0.0008) -[2023-10-15 02:22:14,350][88300] Updated weights for policy 1, policy_version 3650 (0.0009) -[2023-10-15 02:22:14,713][88300] Updated weights for policy 1, policy_version 3660 (0.0009) -[2023-10-15 02:22:15,079][88300] Updated weights for policy 1, policy_version 3670 (0.0009) -[2023-10-15 02:22:15,444][88300] Updated weights for policy 1, policy_version 3680 (0.0009) -[2023-10-15 02:22:17,805][88298] Updated weights for policy 0, policy_version 3650 (0.0008) -[2023-10-15 02:22:18,180][88298] Updated weights for policy 0, policy_version 3660 (0.0007) -[2023-10-15 02:22:18,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 7503872. Throughput: 0: 1728.0, 1: 1730.5. Samples: 1884482. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:22:18,535][87330] Avg episode reward: [(0, '17.800'), (1, '13.080')] -[2023-10-15 02:22:18,541][88298] Updated weights for policy 0, policy_version 3670 (0.0007) -[2023-10-15 02:22:18,906][88298] Updated weights for policy 0, policy_version 3680 (0.0008) -[2023-10-15 02:22:19,439][88300] Updated weights for policy 1, policy_version 3690 (0.0007) -[2023-10-15 02:22:19,797][88300] Updated weights for policy 1, policy_version 3700 (0.0007) -[2023-10-15 02:22:20,169][88300] Updated weights for policy 1, policy_version 3710 (0.0010) -[2023-10-15 02:22:22,826][88298] Updated weights for policy 0, policy_version 3690 (0.0007) -[2023-10-15 02:22:23,201][88298] Updated weights for policy 0, policy_version 3700 (0.0009) -[2023-10-15 02:22:23,534][87330] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 7569408. Throughput: 0: 1757.3, 1: 1732.1. Samples: 1905754. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:22:23,534][87330] Avg episode reward: [(0, '17.990'), (1, '13.100')] -[2023-10-15 02:22:23,574][88298] Updated weights for policy 0, policy_version 3710 (0.0011) -[2023-10-15 02:22:23,648][87905] Saving new best policy, reward=17.990! -[2023-10-15 02:22:24,111][88300] Updated weights for policy 1, policy_version 3720 (0.0009) -[2023-10-15 02:22:24,479][88300] Updated weights for policy 1, policy_version 3730 (0.0007) -[2023-10-15 02:22:24,852][88300] Updated weights for policy 1, policy_version 3740 (0.0007) -[2023-10-15 02:22:27,593][88298] Updated weights for policy 0, policy_version 3720 (0.0012) -[2023-10-15 02:22:27,969][88298] Updated weights for policy 0, policy_version 3730 (0.0009) -[2023-10-15 02:22:28,338][88298] Updated weights for policy 0, policy_version 3740 (0.0007) -[2023-10-15 02:22:28,534][87330] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 7667712. Throughput: 0: 1745.1, 1: 1755.8. Samples: 1927058. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:22:28,535][87330] Avg episode reward: [(0, '17.920'), (1, '13.040')] -[2023-10-15 02:22:28,739][88300] Updated weights for policy 1, policy_version 3750 (0.0008) -[2023-10-15 02:22:29,107][88300] Updated weights for policy 1, policy_version 3760 (0.0007) -[2023-10-15 02:22:29,480][88300] Updated weights for policy 1, policy_version 3770 (0.0007) -[2023-10-15 02:22:32,189][88298] Updated weights for policy 0, policy_version 3750 (0.0008) -[2023-10-15 02:22:32,554][88298] Updated weights for policy 0, policy_version 3760 (0.0008) -[2023-10-15 02:22:32,927][88298] Updated weights for policy 0, policy_version 3770 (0.0009) -[2023-10-15 02:22:33,426][88300] Updated weights for policy 1, policy_version 3780 (0.0008) -[2023-10-15 02:22:33,534][87330] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 7733248. Throughput: 0: 1753.0, 1: 1725.2. Samples: 1937178. Policy #0 lag: (min: 25.0, avg: 45.4, max: 48.0) -[2023-10-15 02:22:33,534][87330] Avg episode reward: [(0, '17.630'), (1, '13.660')] -[2023-10-15 02:22:33,786][88300] Updated weights for policy 1, policy_version 3790 (0.0008) -[2023-10-15 02:22:34,151][88300] Updated weights for policy 1, policy_version 3800 (0.0008) -[2023-10-15 02:22:34,445][88033] Saving new best policy, reward=13.660! -[2023-10-15 02:22:36,931][88298] Updated weights for policy 0, policy_version 3780 (0.0008) -[2023-10-15 02:22:37,300][88298] Updated weights for policy 0, policy_version 3790 (0.0009) -[2023-10-15 02:22:37,676][88298] Updated weights for policy 0, policy_version 3800 (0.0010) -[2023-10-15 02:22:38,018][88300] Updated weights for policy 1, policy_version 3810 (0.0009) -[2023-10-15 02:22:38,384][88300] Updated weights for policy 1, policy_version 3820 (0.0008) -[2023-10-15 02:22:38,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 7798784. Throughput: 0: 1758.4, 1: 1754.0. Samples: 1958638. Policy #0 lag: (min: 31.0, avg: 31.7, max: 49.0) -[2023-10-15 02:22:38,535][87330] Avg episode reward: [(0, '18.030'), (1, '13.360')] -[2023-10-15 02:22:38,535][87905] Saving new best policy, reward=18.030! -[2023-10-15 02:22:38,742][88300] Updated weights for policy 1, policy_version 3830 (0.0008) -[2023-10-15 02:22:39,115][88300] Updated weights for policy 1, policy_version 3840 (0.0008) -[2023-10-15 02:22:41,612][88298] Updated weights for policy 0, policy_version 3810 (0.0009) -[2023-10-15 02:22:41,983][88298] Updated weights for policy 0, policy_version 3820 (0.0010) -[2023-10-15 02:22:42,352][88298] Updated weights for policy 0, policy_version 3830 (0.0008) -[2023-10-15 02:22:42,729][88298] Updated weights for policy 0, policy_version 3840 (0.0009) -[2023-10-15 02:22:42,980][88300] Updated weights for policy 1, policy_version 3850 (0.0009) -[2023-10-15 02:22:43,350][88300] Updated weights for policy 1, policy_version 3860 (0.0008) -[2023-10-15 02:22:43,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 7864320. Throughput: 0: 1717.7, 1: 1740.4. Samples: 1978314. Policy #0 lag: (min: 31.0, avg: 31.7, max: 49.0) -[2023-10-15 02:22:43,534][87330] Avg episode reward: [(0, '18.290'), (1, '13.730')] -[2023-10-15 02:22:43,543][87905] Saving new best policy, reward=18.290! -[2023-10-15 02:22:43,715][88300] Updated weights for policy 1, policy_version 3870 (0.0007) -[2023-10-15 02:22:43,784][88033] Saving new best policy, reward=13.730! -[2023-10-15 02:22:46,735][88298] Updated weights for policy 0, policy_version 3850 (0.0009) -[2023-10-15 02:22:47,107][88298] Updated weights for policy 0, policy_version 3860 (0.0009) -[2023-10-15 02:22:47,476][88298] Updated weights for policy 0, policy_version 3870 (0.0008) -[2023-10-15 02:22:47,591][88300] Updated weights for policy 1, policy_version 3880 (0.0009) -[2023-10-15 02:22:47,974][88300] Updated weights for policy 1, policy_version 3890 (0.0010) -[2023-10-15 02:22:48,352][88300] Updated weights for policy 1, policy_version 3900 (0.0007) -[2023-10-15 02:22:48,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 7962624. Throughput: 0: 1746.2, 1: 1754.2. Samples: 1989810. Policy #0 lag: (min: 17.0, avg: 25.4, max: 49.0) -[2023-10-15 02:22:48,534][87330] Avg episode reward: [(0, '18.060'), (1, '14.070')] -[2023-10-15 02:22:48,536][88033] Saving new best policy, reward=14.070! -[2023-10-15 02:22:51,451][88298] Updated weights for policy 0, policy_version 3880 (0.0009) -[2023-10-15 02:22:51,827][88298] Updated weights for policy 0, policy_version 3890 (0.0009) -[2023-10-15 02:22:52,202][88298] Updated weights for policy 0, policy_version 3900 (0.0008) -[2023-10-15 02:22:52,433][88300] Updated weights for policy 1, policy_version 3910 (0.0008) -[2023-10-15 02:22:52,804][88300] Updated weights for policy 1, policy_version 3920 (0.0008) -[2023-10-15 02:22:53,177][88300] Updated weights for policy 1, policy_version 3930 (0.0007) -[2023-10-15 02:22:53,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 8028160. Throughput: 0: 1724.4, 1: 1755.4. Samples: 2010194. Policy #0 lag: (min: 17.0, avg: 25.4, max: 49.0) -[2023-10-15 02:22:53,534][87330] Avg episode reward: [(0, '18.270'), (1, '13.620')] -[2023-10-15 02:22:56,030][88298] Updated weights for policy 0, policy_version 3910 (0.0008) -[2023-10-15 02:22:56,400][88298] Updated weights for policy 0, policy_version 3920 (0.0007) -[2023-10-15 02:22:56,767][88298] Updated weights for policy 0, policy_version 3930 (0.0007) -[2023-10-15 02:22:57,072][88300] Updated weights for policy 1, policy_version 3940 (0.0007) -[2023-10-15 02:22:57,439][88300] Updated weights for policy 1, policy_version 3950 (0.0007) -[2023-10-15 02:22:57,807][88300] Updated weights for policy 1, policy_version 3960 (0.0008) -[2023-10-15 02:22:58,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 8093696. Throughput: 0: 1714.0, 1: 1724.8. Samples: 2029770. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:22:58,535][87330] Avg episode reward: [(0, '18.130'), (1, '13.610')] -[2023-10-15 02:22:58,548][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000003968_4063232.pth... -[2023-10-15 02:22:58,548][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000003936_4030464.pth... -[2023-10-15 02:22:58,581][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000002304_2359296.pth -[2023-10-15 02:22:58,583][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000002336_2392064.pth -[2023-10-15 02:23:00,660][88298] Updated weights for policy 0, policy_version 3940 (0.0008) -[2023-10-15 02:23:01,028][88298] Updated weights for policy 0, policy_version 3950 (0.0009) -[2023-10-15 02:23:01,395][88298] Updated weights for policy 0, policy_version 3960 (0.0009) -[2023-10-15 02:23:01,523][88300] Updated weights for policy 1, policy_version 3970 (0.0007) -[2023-10-15 02:23:01,893][88300] Updated weights for policy 1, policy_version 3980 (0.0007) -[2023-10-15 02:23:02,265][88300] Updated weights for policy 1, policy_version 3990 (0.0009) -[2023-10-15 02:23:02,626][88300] Updated weights for policy 1, policy_version 4000 (0.0009) -[2023-10-15 02:23:03,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 8159232. Throughput: 0: 1733.7, 1: 1761.7. Samples: 2041774. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:23:03,534][87330] Avg episode reward: [(0, '18.620'), (1, '13.340')] -[2023-10-15 02:23:03,535][87905] Saving new best policy, reward=18.620! -[2023-10-15 02:23:05,213][88298] Updated weights for policy 0, policy_version 3970 (0.0007) -[2023-10-15 02:23:05,591][88298] Updated weights for policy 0, policy_version 3980 (0.0007) -[2023-10-15 02:23:05,979][88298] Updated weights for policy 0, policy_version 3990 (0.0007) -[2023-10-15 02:23:06,345][88298] Updated weights for policy 0, policy_version 4000 (0.0008) -[2023-10-15 02:23:06,633][88300] Updated weights for policy 1, policy_version 4010 (0.0008) -[2023-10-15 02:23:06,999][88300] Updated weights for policy 1, policy_version 4020 (0.0007) -[2023-10-15 02:23:07,365][88300] Updated weights for policy 1, policy_version 4030 (0.0007) -[2023-10-15 02:23:08,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 8224768. Throughput: 0: 1715.0, 1: 1743.1. Samples: 2061368. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-15 02:23:08,535][87330] Avg episode reward: [(0, '18.600'), (1, '13.150')] -[2023-10-15 02:23:10,230][88298] Updated weights for policy 0, policy_version 4010 (0.0009) -[2023-10-15 02:23:10,600][88298] Updated weights for policy 0, policy_version 4020 (0.0009) -[2023-10-15 02:23:10,967][88298] Updated weights for policy 0, policy_version 4030 (0.0010) -[2023-10-15 02:23:11,280][88300] Updated weights for policy 1, policy_version 4040 (0.0009) -[2023-10-15 02:23:11,653][88300] Updated weights for policy 1, policy_version 4050 (0.0008) -[2023-10-15 02:23:12,019][88300] Updated weights for policy 1, policy_version 4060 (0.0007) -[2023-10-15 02:23:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 8290304. Throughput: 0: 1728.9, 1: 1731.8. Samples: 2082786. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-15 02:23:13,534][87330] Avg episode reward: [(0, '18.610'), (1, '13.580')] -[2023-10-15 02:23:14,744][88298] Updated weights for policy 0, policy_version 4040 (0.0008) -[2023-10-15 02:23:15,123][88298] Updated weights for policy 0, policy_version 4050 (0.0009) -[2023-10-15 02:23:15,494][88298] Updated weights for policy 0, policy_version 4060 (0.0008) -[2023-10-15 02:23:15,669][88300] Updated weights for policy 1, policy_version 4070 (0.0008) -[2023-10-15 02:23:16,053][88300] Updated weights for policy 1, policy_version 4080 (0.0009) -[2023-10-15 02:23:16,417][88300] Updated weights for policy 1, policy_version 4090 (0.0010) -[2023-10-15 02:23:18,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 8355840. Throughput: 0: 1713.1, 1: 1744.1. Samples: 2092750. Policy #0 lag: (min: 9.0, avg: 10.0, max: 26.0) -[2023-10-15 02:23:18,534][87330] Avg episode reward: [(0, '19.100'), (1, '13.960')] -[2023-10-15 02:23:18,535][87905] Saving new best policy, reward=19.100! -[2023-10-15 02:23:19,452][88298] Updated weights for policy 0, policy_version 4070 (0.0008) -[2023-10-15 02:23:19,818][88298] Updated weights for policy 0, policy_version 4080 (0.0010) -[2023-10-15 02:23:20,192][88298] Updated weights for policy 0, policy_version 4090 (0.0010) -[2023-10-15 02:23:20,194][88300] Updated weights for policy 1, policy_version 4100 (0.0009) -[2023-10-15 02:23:20,561][88300] Updated weights for policy 1, policy_version 4110 (0.0008) -[2023-10-15 02:23:20,923][88300] Updated weights for policy 1, policy_version 4120 (0.0010) -[2023-10-15 02:23:23,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 8421376. Throughput: 0: 1721.0, 1: 1729.6. Samples: 2113916. Policy #0 lag: (min: 2.0, avg: 2.9, max: 21.0) -[2023-10-15 02:23:23,534][87330] Avg episode reward: [(0, '19.070'), (1, '13.710')] -[2023-10-15 02:23:23,969][88298] Updated weights for policy 0, policy_version 4100 (0.0008) -[2023-10-15 02:23:24,350][88298] Updated weights for policy 0, policy_version 4110 (0.0009) -[2023-10-15 02:23:24,725][88298] Updated weights for policy 0, policy_version 4120 (0.0010) -[2023-10-15 02:23:24,808][88300] Updated weights for policy 1, policy_version 4130 (0.0009) -[2023-10-15 02:23:25,171][88300] Updated weights for policy 1, policy_version 4140 (0.0008) -[2023-10-15 02:23:25,549][88300] Updated weights for policy 1, policy_version 4150 (0.0008) -[2023-10-15 02:23:25,918][88300] Updated weights for policy 1, policy_version 4160 (0.0008) -[2023-10-15 02:23:28,534][87330] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 8486912. Throughput: 0: 1758.3, 1: 1740.6. Samples: 2135764. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-15 02:23:28,535][87330] Avg episode reward: [(0, '19.200'), (1, '14.150')] -[2023-10-15 02:23:28,544][88033] Saving new best policy, reward=14.150! -[2023-10-15 02:23:28,594][88298] Updated weights for policy 0, policy_version 4130 (0.0008) -[2023-10-15 02:23:28,966][88298] Updated weights for policy 0, policy_version 4140 (0.0007) -[2023-10-15 02:23:29,334][88298] Updated weights for policy 0, policy_version 4150 (0.0008) -[2023-10-15 02:23:29,699][87905] Saving new best policy, reward=19.200! -[2023-10-15 02:23:29,700][88298] Updated weights for policy 0, policy_version 4160 (0.0007) -[2023-10-15 02:23:29,759][88300] Updated weights for policy 1, policy_version 4170 (0.0008) -[2023-10-15 02:23:30,122][88300] Updated weights for policy 1, policy_version 4180 (0.0007) -[2023-10-15 02:23:30,500][88300] Updated weights for policy 1, policy_version 4190 (0.0008) -[2023-10-15 02:23:33,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 8552448. Throughput: 0: 1727.1, 1: 1723.1. Samples: 2145066. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-15 02:23:33,535][87330] Avg episode reward: [(0, '19.400'), (1, '14.750')] -[2023-10-15 02:23:33,537][88033] Saving new best policy, reward=14.750! -[2023-10-15 02:23:33,875][88298] Updated weights for policy 0, policy_version 4170 (0.0008) -[2023-10-15 02:23:34,249][88298] Updated weights for policy 0, policy_version 4180 (0.0009) -[2023-10-15 02:23:34,406][88300] Updated weights for policy 1, policy_version 4200 (0.0008) -[2023-10-15 02:23:34,628][88298] Updated weights for policy 0, policy_version 4190 (0.0009) -[2023-10-15 02:23:34,697][87905] Saving new best policy, reward=19.400! -[2023-10-15 02:23:34,775][88300] Updated weights for policy 1, policy_version 4210 (0.0007) -[2023-10-15 02:23:35,144][88300] Updated weights for policy 1, policy_version 4220 (0.0010) -[2023-10-15 02:23:38,510][88298] Updated weights for policy 0, policy_version 4200 (0.0008) -[2023-10-15 02:23:38,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 8617984. Throughput: 0: 1743.9, 1: 1732.8. Samples: 2166648. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-15 02:23:38,535][87330] Avg episode reward: [(0, '19.500'), (1, '14.690')] -[2023-10-15 02:23:38,884][88298] Updated weights for policy 0, policy_version 4210 (0.0007) -[2023-10-15 02:23:39,039][88300] Updated weights for policy 1, policy_version 4230 (0.0008) -[2023-10-15 02:23:39,248][88298] Updated weights for policy 0, policy_version 4220 (0.0007) -[2023-10-15 02:23:39,399][87905] Saving new best policy, reward=19.500! -[2023-10-15 02:23:39,403][88300] Updated weights for policy 1, policy_version 4240 (0.0008) -[2023-10-15 02:23:39,764][88300] Updated weights for policy 1, policy_version 4250 (0.0009) -[2023-10-15 02:23:43,151][88298] Updated weights for policy 0, policy_version 4230 (0.0007) -[2023-10-15 02:23:43,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 8683520. Throughput: 0: 1755.1, 1: 1764.0. Samples: 2188132. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:23:43,535][88298] Updated weights for policy 0, policy_version 4240 (0.0007) -[2023-10-15 02:23:43,535][87330] Avg episode reward: [(0, '19.870'), (1, '14.800')] -[2023-10-15 02:23:43,545][88033] Saving new best policy, reward=14.800! -[2023-10-15 02:23:43,819][88300] Updated weights for policy 1, policy_version 4260 (0.0009) -[2023-10-15 02:23:43,900][88298] Updated weights for policy 0, policy_version 4250 (0.0008) -[2023-10-15 02:23:44,118][87905] Saving new best policy, reward=19.870! -[2023-10-15 02:23:44,185][88300] Updated weights for policy 1, policy_version 4270 (0.0009) -[2023-10-15 02:23:44,549][88300] Updated weights for policy 1, policy_version 4280 (0.0008) -[2023-10-15 02:23:47,624][88298] Updated weights for policy 0, policy_version 4260 (0.0008) -[2023-10-15 02:23:47,991][88298] Updated weights for policy 0, policy_version 4270 (0.0008) -[2023-10-15 02:23:48,372][88298] Updated weights for policy 0, policy_version 4280 (0.0009) -[2023-10-15 02:23:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 8749056. Throughput: 0: 1735.1, 1: 1728.8. Samples: 2197650. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:23:48,535][87330] Avg episode reward: [(0, '19.480'), (1, '14.890')] -[2023-10-15 02:23:48,542][88300] Updated weights for policy 1, policy_version 4290 (0.0010) -[2023-10-15 02:23:48,899][88300] Updated weights for policy 1, policy_version 4300 (0.0009) -[2023-10-15 02:23:49,275][88300] Updated weights for policy 1, policy_version 4310 (0.0011) -[2023-10-15 02:23:49,642][88033] Saving new best policy, reward=14.890! -[2023-10-15 02:23:49,645][88300] Updated weights for policy 1, policy_version 4320 (0.0010) -[2023-10-15 02:23:52,389][88298] Updated weights for policy 0, policy_version 4290 (0.0010) -[2023-10-15 02:23:52,761][88298] Updated weights for policy 0, policy_version 4300 (0.0008) -[2023-10-15 02:23:53,148][88298] Updated weights for policy 0, policy_version 4310 (0.0009) -[2023-10-15 02:23:53,517][88298] Updated weights for policy 0, policy_version 4320 (0.0007) -[2023-10-15 02:23:53,534][87330] Fps is (10 sec: 16384.5, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 8847360. Throughput: 0: 1757.2, 1: 1751.7. Samples: 2219268. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:23:53,534][87330] Avg episode reward: [(0, '19.520'), (1, '15.660')] -[2023-10-15 02:23:53,620][88300] Updated weights for policy 1, policy_version 4330 (0.0008) -[2023-10-15 02:23:53,993][88300] Updated weights for policy 1, policy_version 4340 (0.0009) -[2023-10-15 02:23:54,362][88300] Updated weights for policy 1, policy_version 4350 (0.0009) -[2023-10-15 02:23:54,431][88033] Saving new best policy, reward=15.660! -[2023-10-15 02:23:57,445][88298] Updated weights for policy 0, policy_version 4330 (0.0008) -[2023-10-15 02:23:57,821][88298] Updated weights for policy 0, policy_version 4340 (0.0009) -[2023-10-15 02:23:58,189][88298] Updated weights for policy 0, policy_version 4350 (0.0008) -[2023-10-15 02:23:58,296][88300] Updated weights for policy 1, policy_version 4360 (0.0008) -[2023-10-15 02:23:58,534][87330] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 8912896. Throughput: 0: 1732.1, 1: 1752.0. Samples: 2239572. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:23:58,535][87330] Avg episode reward: [(0, '19.550'), (1, '16.130')] -[2023-10-15 02:23:58,676][88300] Updated weights for policy 1, policy_version 4370 (0.0008) -[2023-10-15 02:23:59,041][88300] Updated weights for policy 1, policy_version 4380 (0.0008) -[2023-10-15 02:23:59,184][88033] Saving new best policy, reward=16.130! -[2023-10-15 02:24:02,020][88298] Updated weights for policy 0, policy_version 4360 (0.0007) -[2023-10-15 02:24:02,397][88298] Updated weights for policy 0, policy_version 4370 (0.0009) -[2023-10-15 02:24:02,764][88298] Updated weights for policy 0, policy_version 4380 (0.0008) -[2023-10-15 02:24:02,799][88300] Updated weights for policy 1, policy_version 4390 (0.0007) -[2023-10-15 02:24:03,171][88300] Updated weights for policy 1, policy_version 4400 (0.0008) -[2023-10-15 02:24:03,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 8978432. Throughput: 0: 1751.9, 1: 1749.9. Samples: 2250330. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:24:03,534][87330] Avg episode reward: [(0, '19.340'), (1, '16.320')] -[2023-10-15 02:24:03,543][88300] Updated weights for policy 1, policy_version 4410 (0.0010) -[2023-10-15 02:24:03,753][88033] Saving new best policy, reward=16.320! -[2023-10-15 02:24:06,639][88298] Updated weights for policy 0, policy_version 4390 (0.0008) -[2023-10-15 02:24:07,014][88298] Updated weights for policy 0, policy_version 4400 (0.0007) -[2023-10-15 02:24:07,361][88300] Updated weights for policy 1, policy_version 4420 (0.0008) -[2023-10-15 02:24:07,376][88298] Updated weights for policy 0, policy_version 4410 (0.0008) -[2023-10-15 02:24:07,723][88300] Updated weights for policy 1, policy_version 4430 (0.0008) -[2023-10-15 02:24:08,089][88300] Updated weights for policy 1, policy_version 4440 (0.0011) -[2023-10-15 02:24:08,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 9076736. Throughput: 0: 1735.9, 1: 1762.1. Samples: 2271326. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:24:08,535][87330] Avg episode reward: [(0, '19.460'), (1, '16.340')] -[2023-10-15 02:24:08,536][88033] Saving new best policy, reward=16.340! -[2023-10-15 02:24:11,212][88298] Updated weights for policy 0, policy_version 4420 (0.0009) -[2023-10-15 02:24:11,585][88298] Updated weights for policy 0, policy_version 4430 (0.0008) -[2023-10-15 02:24:11,931][88300] Updated weights for policy 1, policy_version 4450 (0.0010) -[2023-10-15 02:24:11,957][88298] Updated weights for policy 0, policy_version 4440 (0.0009) -[2023-10-15 02:24:12,308][88300] Updated weights for policy 1, policy_version 4460 (0.0009) -[2023-10-15 02:24:12,690][88300] Updated weights for policy 1, policy_version 4470 (0.0011) -[2023-10-15 02:24:13,063][88300] Updated weights for policy 1, policy_version 4480 (0.0010) -[2023-10-15 02:24:13,534][87330] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 9142272. Throughput: 0: 1712.1, 1: 1732.0. Samples: 2290750. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:24:13,535][87330] Avg episode reward: [(0, '19.330'), (1, '16.520')] -[2023-10-15 02:24:13,548][88033] Saving new best policy, reward=16.520! -[2023-10-15 02:24:15,748][88298] Updated weights for policy 0, policy_version 4450 (0.0007) -[2023-10-15 02:24:16,118][88298] Updated weights for policy 0, policy_version 4460 (0.0010) -[2023-10-15 02:24:16,485][88298] Updated weights for policy 0, policy_version 4470 (0.0010) -[2023-10-15 02:24:16,860][88298] Updated weights for policy 0, policy_version 4480 (0.0009) -[2023-10-15 02:24:17,051][88300] Updated weights for policy 1, policy_version 4490 (0.0010) -[2023-10-15 02:24:17,406][88300] Updated weights for policy 1, policy_version 4500 (0.0011) -[2023-10-15 02:24:17,773][88300] Updated weights for policy 1, policy_version 4510 (0.0009) -[2023-10-15 02:24:18,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 9207808. Throughput: 0: 1744.2, 1: 1760.9. Samples: 2302796. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:24:18,535][87330] Avg episode reward: [(0, '19.680'), (1, '16.120')] -[2023-10-15 02:24:20,958][88298] Updated weights for policy 0, policy_version 4490 (0.0008) -[2023-10-15 02:24:21,325][88298] Updated weights for policy 0, policy_version 4500 (0.0009) -[2023-10-15 02:24:21,700][88298] Updated weights for policy 0, policy_version 4510 (0.0009) -[2023-10-15 02:24:21,817][88300] Updated weights for policy 1, policy_version 4520 (0.0008) -[2023-10-15 02:24:22,201][88300] Updated weights for policy 1, policy_version 4530 (0.0008) -[2023-10-15 02:24:22,575][88300] Updated weights for policy 1, policy_version 4540 (0.0010) -[2023-10-15 02:24:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 9273344. Throughput: 0: 1722.0, 1: 1734.8. Samples: 2322204. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:24:23,535][87330] Avg episode reward: [(0, '19.640'), (1, '15.800')] -[2023-10-15 02:24:25,793][88298] Updated weights for policy 0, policy_version 4520 (0.0007) -[2023-10-15 02:24:26,161][88298] Updated weights for policy 0, policy_version 4530 (0.0007) -[2023-10-15 02:24:26,381][88300] Updated weights for policy 1, policy_version 4550 (0.0009) -[2023-10-15 02:24:26,534][88298] Updated weights for policy 0, policy_version 4540 (0.0009) -[2023-10-15 02:24:26,739][88300] Updated weights for policy 1, policy_version 4560 (0.0008) -[2023-10-15 02:24:27,121][88300] Updated weights for policy 1, policy_version 4570 (0.0009) -[2023-10-15 02:24:28,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 9338880. Throughput: 0: 1725.2, 1: 1717.6. Samples: 2343054. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:24:28,535][87330] Avg episode reward: [(0, '19.500'), (1, '15.710')] -[2023-10-15 02:24:30,417][88298] Updated weights for policy 0, policy_version 4550 (0.0008) -[2023-10-15 02:24:30,795][88298] Updated weights for policy 0, policy_version 4560 (0.0009) -[2023-10-15 02:24:31,089][88300] Updated weights for policy 1, policy_version 4580 (0.0009) -[2023-10-15 02:24:31,162][88298] Updated weights for policy 0, policy_version 4570 (0.0009) -[2023-10-15 02:24:31,451][88300] Updated weights for policy 1, policy_version 4590 (0.0009) -[2023-10-15 02:24:31,832][88300] Updated weights for policy 1, policy_version 4600 (0.0008) -[2023-10-15 02:24:33,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 9404416. Throughput: 0: 1736.5, 1: 1739.9. Samples: 2354088. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:24:33,534][87330] Avg episode reward: [(0, '19.720'), (1, '15.740')] -[2023-10-15 02:24:34,953][88298] Updated weights for policy 0, policy_version 4580 (0.0008) -[2023-10-15 02:24:35,330][88298] Updated weights for policy 0, policy_version 4590 (0.0008) -[2023-10-15 02:24:35,700][88298] Updated weights for policy 0, policy_version 4600 (0.0008) -[2023-10-15 02:24:35,887][88300] Updated weights for policy 1, policy_version 4610 (0.0008) -[2023-10-15 02:24:36,252][88300] Updated weights for policy 1, policy_version 4620 (0.0008) -[2023-10-15 02:24:36,628][88300] Updated weights for policy 1, policy_version 4630 (0.0009) -[2023-10-15 02:24:37,001][88300] Updated weights for policy 1, policy_version 4640 (0.0008) -[2023-10-15 02:24:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 9469952. Throughput: 0: 1721.7, 1: 1713.4. Samples: 2373846. Policy #0 lag: (min: 10.0, avg: 21.0, max: 42.0) -[2023-10-15 02:24:38,535][87330] Avg episode reward: [(0, '19.840'), (1, '15.970')] -[2023-10-15 02:24:39,368][88298] Updated weights for policy 0, policy_version 4610 (0.0008) -[2023-10-15 02:24:39,735][88298] Updated weights for policy 0, policy_version 4620 (0.0010) -[2023-10-15 02:24:40,110][88298] Updated weights for policy 0, policy_version 4630 (0.0010) -[2023-10-15 02:24:40,479][88298] Updated weights for policy 0, policy_version 4640 (0.0010) -[2023-10-15 02:24:41,054][88300] Updated weights for policy 1, policy_version 4650 (0.0007) -[2023-10-15 02:24:41,414][88300] Updated weights for policy 1, policy_version 4660 (0.0009) -[2023-10-15 02:24:41,777][88300] Updated weights for policy 1, policy_version 4670 (0.0010) -[2023-10-15 02:24:43,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 9535488. Throughput: 0: 1745.9, 1: 1724.9. Samples: 2395756. Policy #0 lag: (min: 10.0, avg: 21.0, max: 42.0) -[2023-10-15 02:24:43,534][87330] Avg episode reward: [(0, '19.770'), (1, '16.180')] -[2023-10-15 02:24:44,474][88298] Updated weights for policy 0, policy_version 4650 (0.0008) -[2023-10-15 02:24:44,844][88298] Updated weights for policy 0, policy_version 4660 (0.0008) -[2023-10-15 02:24:45,212][88298] Updated weights for policy 0, policy_version 4670 (0.0008) -[2023-10-15 02:24:45,698][88300] Updated weights for policy 1, policy_version 4680 (0.0008) -[2023-10-15 02:24:46,074][88300] Updated weights for policy 1, policy_version 4690 (0.0007) -[2023-10-15 02:24:46,441][88300] Updated weights for policy 1, policy_version 4700 (0.0008) -[2023-10-15 02:24:48,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 9601024. Throughput: 0: 1724.8, 1: 1724.7. Samples: 2405562. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:24:48,535][87330] Avg episode reward: [(0, '19.770'), (1, '16.540')] -[2023-10-15 02:24:48,537][88033] Saving new best policy, reward=16.540! -[2023-10-15 02:24:49,216][88298] Updated weights for policy 0, policy_version 4680 (0.0008) -[2023-10-15 02:24:49,591][88298] Updated weights for policy 0, policy_version 4690 (0.0009) -[2023-10-15 02:24:49,959][88298] Updated weights for policy 0, policy_version 4700 (0.0008) -[2023-10-15 02:24:50,340][88300] Updated weights for policy 1, policy_version 4710 (0.0009) -[2023-10-15 02:24:50,717][88300] Updated weights for policy 1, policy_version 4720 (0.0009) -[2023-10-15 02:24:51,076][88300] Updated weights for policy 1, policy_version 4730 (0.0009) -[2023-10-15 02:24:53,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 9666560. Throughput: 0: 1735.6, 1: 1713.3. Samples: 2426524. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:24:53,534][87330] Avg episode reward: [(0, '19.920'), (1, '16.780')] -[2023-10-15 02:24:53,535][88033] Saving new best policy, reward=16.780! -[2023-10-15 02:24:53,762][88298] Updated weights for policy 0, policy_version 4710 (0.0008) -[2023-10-15 02:24:54,135][88298] Updated weights for policy 0, policy_version 4720 (0.0011) -[2023-10-15 02:24:54,509][88298] Updated weights for policy 0, policy_version 4730 (0.0009) -[2023-10-15 02:24:54,681][88300] Updated weights for policy 1, policy_version 4740 (0.0008) -[2023-10-15 02:24:54,729][87905] Saving new best policy, reward=19.920! -[2023-10-15 02:24:55,050][88300] Updated weights for policy 1, policy_version 4750 (0.0010) -[2023-10-15 02:24:55,425][88300] Updated weights for policy 1, policy_version 4760 (0.0011) -[2023-10-15 02:24:58,418][88298] Updated weights for policy 0, policy_version 4740 (0.0009) -[2023-10-15 02:24:58,534][87330] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 9732096. Throughput: 0: 1753.5, 1: 1746.4. Samples: 2448246. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:24:58,534][87330] Avg episode reward: [(0, '19.940'), (1, '16.710')] -[2023-10-15 02:24:58,544][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000004768_4882432.pth... -[2023-10-15 02:24:58,573][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000003136_3211264.pth -[2023-10-15 02:24:58,799][88298] Updated weights for policy 0, policy_version 4750 (0.0007) -[2023-10-15 02:24:59,167][88298] Updated weights for policy 0, policy_version 4760 (0.0009) -[2023-10-15 02:24:59,365][88300] Updated weights for policy 1, policy_version 4770 (0.0008) -[2023-10-15 02:24:59,457][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000004768_4882432.pth... -[2023-10-15 02:24:59,487][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000003136_3211264.pth -[2023-10-15 02:24:59,492][87905] Saving new best policy, reward=19.940! -[2023-10-15 02:24:59,723][88300] Updated weights for policy 1, policy_version 4780 (0.0009) -[2023-10-15 02:25:00,102][88300] Updated weights for policy 1, policy_version 4790 (0.0007) -[2023-10-15 02:25:00,470][88300] Updated weights for policy 1, policy_version 4800 (0.0007) -[2023-10-15 02:25:03,173][88298] Updated weights for policy 0, policy_version 4770 (0.0008) -[2023-10-15 02:25:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 9797632. Throughput: 0: 1722.5, 1: 1719.2. Samples: 2457670. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:25:03,534][87330] Avg episode reward: [(0, '20.050'), (1, '16.770')] -[2023-10-15 02:25:03,543][88298] Updated weights for policy 0, policy_version 4780 (0.0009) -[2023-10-15 02:25:03,916][88298] Updated weights for policy 0, policy_version 4790 (0.0008) -[2023-10-15 02:25:04,283][87905] Saving new best policy, reward=20.050! -[2023-10-15 02:25:04,287][88298] Updated weights for policy 0, policy_version 4800 (0.0009) -[2023-10-15 02:25:04,436][88300] Updated weights for policy 1, policy_version 4810 (0.0008) -[2023-10-15 02:25:04,800][88300] Updated weights for policy 1, policy_version 4820 (0.0008) -[2023-10-15 02:25:05,168][88300] Updated weights for policy 1, policy_version 4830 (0.0007) -[2023-10-15 02:25:08,194][88298] Updated weights for policy 0, policy_version 4810 (0.0008) -[2023-10-15 02:25:08,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 9863168. Throughput: 0: 1745.6, 1: 1736.2. Samples: 2478884. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-15 02:25:08,535][87330] Avg episode reward: [(0, '19.760'), (1, '16.220')] -[2023-10-15 02:25:08,555][88298] Updated weights for policy 0, policy_version 4820 (0.0010) -[2023-10-15 02:25:08,926][88298] Updated weights for policy 0, policy_version 4830 (0.0008) -[2023-10-15 02:25:09,093][88300] Updated weights for policy 1, policy_version 4840 (0.0008) -[2023-10-15 02:25:09,483][88300] Updated weights for policy 1, policy_version 4850 (0.0007) -[2023-10-15 02:25:09,838][88300] Updated weights for policy 1, policy_version 4860 (0.0008) -[2023-10-15 02:25:12,879][88298] Updated weights for policy 0, policy_version 4840 (0.0007) -[2023-10-15 02:25:13,259][88298] Updated weights for policy 0, policy_version 4850 (0.0007) -[2023-10-15 02:25:13,520][88300] Updated weights for policy 1, policy_version 4870 (0.0009) -[2023-10-15 02:25:13,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 9928704. Throughput: 0: 1736.7, 1: 1751.3. Samples: 2500014. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-15 02:25:13,535][87330] Avg episode reward: [(0, '19.730'), (1, '16.210')] -[2023-10-15 02:25:13,632][88298] Updated weights for policy 0, policy_version 4860 (0.0009) -[2023-10-15 02:25:13,884][88300] Updated weights for policy 1, policy_version 4880 (0.0009) -[2023-10-15 02:25:14,263][88300] Updated weights for policy 1, policy_version 4890 (0.0010) -[2023-10-15 02:25:17,484][88298] Updated weights for policy 0, policy_version 4870 (0.0010) -[2023-10-15 02:25:17,865][88298] Updated weights for policy 0, policy_version 4880 (0.0010) -[2023-10-15 02:25:18,210][88300] Updated weights for policy 1, policy_version 4900 (0.0009) -[2023-10-15 02:25:18,231][88298] Updated weights for policy 0, policy_version 4890 (0.0009) -[2023-10-15 02:25:18,534][87330] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 10027008. Throughput: 0: 1727.1, 1: 1727.3. Samples: 2509538. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-15 02:25:18,535][87330] Avg episode reward: [(0, '19.810'), (1, '16.290')] -[2023-10-15 02:25:18,574][88300] Updated weights for policy 1, policy_version 4910 (0.0008) -[2023-10-15 02:25:18,948][88300] Updated weights for policy 1, policy_version 4920 (0.0007) -[2023-10-15 02:25:22,202][88298] Updated weights for policy 0, policy_version 4900 (0.0008) -[2023-10-15 02:25:22,573][88298] Updated weights for policy 0, policy_version 4910 (0.0011) -[2023-10-15 02:25:22,938][88298] Updated weights for policy 0, policy_version 4920 (0.0009) -[2023-10-15 02:25:22,942][88300] Updated weights for policy 1, policy_version 4930 (0.0008) -[2023-10-15 02:25:23,312][88300] Updated weights for policy 1, policy_version 4940 (0.0008) -[2023-10-15 02:25:23,534][87330] Fps is (10 sec: 16384.3, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 10092544. Throughput: 0: 1741.3, 1: 1752.5. Samples: 2531066. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:25:23,534][87330] Avg episode reward: [(0, '19.660'), (1, '16.440')] -[2023-10-15 02:25:23,684][88300] Updated weights for policy 1, policy_version 4950 (0.0008) -[2023-10-15 02:25:24,057][88300] Updated weights for policy 1, policy_version 4960 (0.0009) -[2023-10-15 02:25:26,993][88298] Updated weights for policy 0, policy_version 4930 (0.0009) -[2023-10-15 02:25:27,363][88298] Updated weights for policy 0, policy_version 4940 (0.0007) -[2023-10-15 02:25:27,736][88298] Updated weights for policy 0, policy_version 4950 (0.0010) -[2023-10-15 02:25:27,956][88300] Updated weights for policy 1, policy_version 4970 (0.0007) -[2023-10-15 02:25:28,101][88298] Updated weights for policy 0, policy_version 4960 (0.0007) -[2023-10-15 02:25:28,322][88300] Updated weights for policy 1, policy_version 4980 (0.0007) -[2023-10-15 02:25:28,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 10158080. Throughput: 0: 1714.3, 1: 1731.9. Samples: 2550838. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:25:28,535][87330] Avg episode reward: [(0, '19.930'), (1, '16.700')] -[2023-10-15 02:25:28,693][88300] Updated weights for policy 1, policy_version 4990 (0.0007) -[2023-10-15 02:25:31,969][88298] Updated weights for policy 0, policy_version 4970 (0.0007) -[2023-10-15 02:25:32,346][88298] Updated weights for policy 0, policy_version 4980 (0.0008) -[2023-10-15 02:25:32,592][88300] Updated weights for policy 1, policy_version 5000 (0.0007) -[2023-10-15 02:25:32,716][88298] Updated weights for policy 0, policy_version 4990 (0.0009) -[2023-10-15 02:25:32,969][88300] Updated weights for policy 1, policy_version 5010 (0.0009) -[2023-10-15 02:25:33,356][88300] Updated weights for policy 1, policy_version 5020 (0.0011) -[2023-10-15 02:25:33,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 10256384. Throughput: 0: 1737.2, 1: 1738.4. Samples: 2561962. Policy #0 lag: (min: 8.0, avg: 30.4, max: 40.0) -[2023-10-15 02:25:33,534][87330] Avg episode reward: [(0, '19.710'), (1, '17.050')] -[2023-10-15 02:25:33,535][88033] Saving new best policy, reward=17.050! -[2023-10-15 02:25:36,663][88298] Updated weights for policy 0, policy_version 5000 (0.0010) -[2023-10-15 02:25:37,032][88298] Updated weights for policy 0, policy_version 5010 (0.0010) -[2023-10-15 02:25:37,408][88298] Updated weights for policy 0, policy_version 5020 (0.0008) -[2023-10-15 02:25:37,415][88300] Updated weights for policy 1, policy_version 5030 (0.0008) -[2023-10-15 02:25:37,787][88300] Updated weights for policy 1, policy_version 5040 (0.0009) -[2023-10-15 02:25:38,159][88300] Updated weights for policy 1, policy_version 5050 (0.0010) -[2023-10-15 02:25:38,534][87330] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 10321920. Throughput: 0: 1727.1, 1: 1743.6. Samples: 2582708. Policy #0 lag: (min: 8.0, avg: 30.4, max: 40.0) -[2023-10-15 02:25:38,534][87330] Avg episode reward: [(0, '19.720'), (1, '17.810')] -[2023-10-15 02:25:38,535][88033] Saving new best policy, reward=17.810! -[2023-10-15 02:25:41,392][88298] Updated weights for policy 0, policy_version 5030 (0.0010) -[2023-10-15 02:25:41,765][88298] Updated weights for policy 0, policy_version 5040 (0.0009) -[2023-10-15 02:25:42,128][88300] Updated weights for policy 1, policy_version 5060 (0.0009) -[2023-10-15 02:25:42,131][88298] Updated weights for policy 0, policy_version 5050 (0.0008) -[2023-10-15 02:25:42,493][88300] Updated weights for policy 1, policy_version 5070 (0.0008) -[2023-10-15 02:25:42,860][88300] Updated weights for policy 1, policy_version 5080 (0.0009) -[2023-10-15 02:25:43,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 10387456. Throughput: 0: 1705.7, 1: 1705.6. Samples: 2601756. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-15 02:25:43,534][87330] Avg episode reward: [(0, '20.170'), (1, '17.920')] -[2023-10-15 02:25:43,545][87905] Saving new best policy, reward=20.170! -[2023-10-15 02:25:43,546][88033] Saving new best policy, reward=17.920! -[2023-10-15 02:25:45,936][88298] Updated weights for policy 0, policy_version 5060 (0.0010) -[2023-10-15 02:25:46,316][88298] Updated weights for policy 0, policy_version 5070 (0.0011) -[2023-10-15 02:25:46,680][88298] Updated weights for policy 0, policy_version 5080 (0.0011) -[2023-10-15 02:25:46,983][88300] Updated weights for policy 1, policy_version 5090 (0.0007) -[2023-10-15 02:25:47,359][88300] Updated weights for policy 1, policy_version 5100 (0.0007) -[2023-10-15 02:25:47,718][88300] Updated weights for policy 1, policy_version 5110 (0.0008) -[2023-10-15 02:25:48,098][88300] Updated weights for policy 1, policy_version 5120 (0.0008) -[2023-10-15 02:25:48,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 10452992. Throughput: 0: 1741.0, 1: 1729.6. Samples: 2613846. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-15 02:25:48,535][87330] Avg episode reward: [(0, '20.040'), (1, '18.390')] -[2023-10-15 02:25:48,536][88033] Saving new best policy, reward=18.390! -[2023-10-15 02:25:50,785][88298] Updated weights for policy 0, policy_version 5090 (0.0008) -[2023-10-15 02:25:51,156][88298] Updated weights for policy 0, policy_version 5100 (0.0007) -[2023-10-15 02:25:51,535][88298] Updated weights for policy 0, policy_version 5110 (0.0008) -[2023-10-15 02:25:51,896][88298] Updated weights for policy 0, policy_version 5120 (0.0007) -[2023-10-15 02:25:52,135][88300] Updated weights for policy 1, policy_version 5130 (0.0009) -[2023-10-15 02:25:52,503][88300] Updated weights for policy 1, policy_version 5140 (0.0009) -[2023-10-15 02:25:52,872][88300] Updated weights for policy 1, policy_version 5150 (0.0010) -[2023-10-15 02:25:53,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 10518528. Throughput: 0: 1710.6, 1: 1720.4. Samples: 2633282. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:25:53,535][87330] Avg episode reward: [(0, '20.040'), (1, '18.340')] -[2023-10-15 02:25:55,823][88298] Updated weights for policy 0, policy_version 5130 (0.0009) -[2023-10-15 02:25:56,188][88298] Updated weights for policy 0, policy_version 5140 (0.0011) -[2023-10-15 02:25:56,559][88298] Updated weights for policy 0, policy_version 5150 (0.0010) -[2023-10-15 02:25:56,966][88300] Updated weights for policy 1, policy_version 5160 (0.0008) -[2023-10-15 02:25:57,344][88300] Updated weights for policy 1, policy_version 5170 (0.0008) -[2023-10-15 02:25:57,720][88300] Updated weights for policy 1, policy_version 5180 (0.0010) -[2023-10-15 02:25:58,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 10584064. Throughput: 0: 1714.0, 1: 1693.0. Samples: 2653328. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:25:58,535][87330] Avg episode reward: [(0, '20.120'), (1, '18.240')] -[2023-10-15 02:26:00,646][88298] Updated weights for policy 0, policy_version 5160 (0.0007) -[2023-10-15 02:26:01,028][88298] Updated weights for policy 0, policy_version 5170 (0.0007) -[2023-10-15 02:26:01,396][88298] Updated weights for policy 0, policy_version 5180 (0.0007) -[2023-10-15 02:26:01,555][88300] Updated weights for policy 1, policy_version 5190 (0.0009) -[2023-10-15 02:26:01,924][88300] Updated weights for policy 1, policy_version 5200 (0.0007) -[2023-10-15 02:26:02,291][88300] Updated weights for policy 1, policy_version 5210 (0.0008) -[2023-10-15 02:26:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 10649600. Throughput: 0: 1726.6, 1: 1728.2. Samples: 2665006. Policy #0 lag: (min: 26.0, avg: 34.0, max: 58.0) -[2023-10-15 02:26:03,535][87330] Avg episode reward: [(0, '20.190'), (1, '18.330')] -[2023-10-15 02:26:03,536][87905] Saving new best policy, reward=20.190! -[2023-10-15 02:26:05,213][88298] Updated weights for policy 0, policy_version 5190 (0.0008) -[2023-10-15 02:26:05,584][88298] Updated weights for policy 0, policy_version 5200 (0.0007) -[2023-10-15 02:26:05,950][88298] Updated weights for policy 0, policy_version 5210 (0.0009) -[2023-10-15 02:26:06,123][88300] Updated weights for policy 1, policy_version 5220 (0.0009) -[2023-10-15 02:26:06,496][88300] Updated weights for policy 1, policy_version 5230 (0.0008) -[2023-10-15 02:26:06,864][88300] Updated weights for policy 1, policy_version 5240 (0.0009) -[2023-10-15 02:26:08,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 10715136. Throughput: 0: 1707.9, 1: 1700.9. Samples: 2684460. Policy #0 lag: (min: 26.0, avg: 34.0, max: 58.0) -[2023-10-15 02:26:08,535][87330] Avg episode reward: [(0, '20.410'), (1, '17.770')] -[2023-10-15 02:26:08,536][87905] Saving new best policy, reward=20.410! -[2023-10-15 02:26:09,820][88298] Updated weights for policy 0, policy_version 5220 (0.0009) -[2023-10-15 02:26:10,194][88298] Updated weights for policy 0, policy_version 5230 (0.0007) -[2023-10-15 02:26:10,557][88298] Updated weights for policy 0, policy_version 5240 (0.0007) -[2023-10-15 02:26:10,596][88300] Updated weights for policy 1, policy_version 5250 (0.0009) -[2023-10-15 02:26:10,968][88300] Updated weights for policy 1, policy_version 5260 (0.0007) -[2023-10-15 02:26:11,338][88300] Updated weights for policy 1, policy_version 5270 (0.0010) -[2023-10-15 02:26:11,706][88300] Updated weights for policy 1, policy_version 5280 (0.0010) -[2023-10-15 02:26:13,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 10780672. Throughput: 0: 1731.3, 1: 1720.9. Samples: 2706184. Policy #0 lag: (min: 1.0, avg: 14.7, max: 33.0) -[2023-10-15 02:26:13,534][87330] Avg episode reward: [(0, '20.230'), (1, '17.480')] -[2023-10-15 02:26:14,454][88298] Updated weights for policy 0, policy_version 5250 (0.0007) -[2023-10-15 02:26:14,811][88298] Updated weights for policy 0, policy_version 5260 (0.0010) -[2023-10-15 02:26:15,181][88298] Updated weights for policy 0, policy_version 5270 (0.0008) -[2023-10-15 02:26:15,549][88298] Updated weights for policy 0, policy_version 5280 (0.0009) -[2023-10-15 02:26:15,553][88300] Updated weights for policy 1, policy_version 5290 (0.0007) -[2023-10-15 02:26:15,921][88300] Updated weights for policy 1, policy_version 5300 (0.0008) -[2023-10-15 02:26:16,294][88300] Updated weights for policy 1, policy_version 5310 (0.0008) -[2023-10-15 02:26:18,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 10846208. Throughput: 0: 1707.1, 1: 1713.6. Samples: 2715898. Policy #0 lag: (min: 1.0, avg: 14.7, max: 33.0) -[2023-10-15 02:26:18,535][87330] Avg episode reward: [(0, '20.230'), (1, '16.930')] -[2023-10-15 02:26:19,526][88298] Updated weights for policy 0, policy_version 5290 (0.0008) -[2023-10-15 02:26:19,887][88298] Updated weights for policy 0, policy_version 5300 (0.0007) -[2023-10-15 02:26:19,994][88300] Updated weights for policy 1, policy_version 5320 (0.0007) -[2023-10-15 02:26:20,252][88298] Updated weights for policy 0, policy_version 5310 (0.0009) -[2023-10-15 02:26:20,355][88300] Updated weights for policy 1, policy_version 5330 (0.0007) -[2023-10-15 02:26:20,718][88300] Updated weights for policy 1, policy_version 5340 (0.0010) -[2023-10-15 02:26:23,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 10911744. Throughput: 0: 1719.2, 1: 1716.6. Samples: 2737320. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:26:23,534][87330] Avg episode reward: [(0, '20.400'), (1, '17.110')] -[2023-10-15 02:26:24,067][88298] Updated weights for policy 0, policy_version 5320 (0.0007) -[2023-10-15 02:26:24,447][88298] Updated weights for policy 0, policy_version 5330 (0.0007) -[2023-10-15 02:26:24,792][88300] Updated weights for policy 1, policy_version 5350 (0.0008) -[2023-10-15 02:26:24,821][88298] Updated weights for policy 0, policy_version 5340 (0.0009) -[2023-10-15 02:26:25,157][88300] Updated weights for policy 1, policy_version 5360 (0.0009) -[2023-10-15 02:26:25,526][88300] Updated weights for policy 1, policy_version 5370 (0.0007) -[2023-10-15 02:26:28,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 10977280. Throughput: 0: 1744.0, 1: 1748.4. Samples: 2758914. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:26:28,535][87330] Avg episode reward: [(0, '20.450'), (1, '17.100')] -[2023-10-15 02:26:28,703][88298] Updated weights for policy 0, policy_version 5350 (0.0010) -[2023-10-15 02:26:29,084][88298] Updated weights for policy 0, policy_version 5360 (0.0009) -[2023-10-15 02:26:29,395][88300] Updated weights for policy 1, policy_version 5380 (0.0008) -[2023-10-15 02:26:29,464][88298] Updated weights for policy 0, policy_version 5370 (0.0010) -[2023-10-15 02:26:29,675][87905] Saving new best policy, reward=20.450! -[2023-10-15 02:26:29,761][88300] Updated weights for policy 1, policy_version 5390 (0.0007) -[2023-10-15 02:26:30,127][88300] Updated weights for policy 1, policy_version 5400 (0.0007) -[2023-10-15 02:26:33,407][88298] Updated weights for policy 0, policy_version 5380 (0.0008) -[2023-10-15 02:26:33,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 11042816. Throughput: 0: 1710.5, 1: 1725.9. Samples: 2768486. Policy #0 lag: (min: 4.0, avg: 8.6, max: 36.0) -[2023-10-15 02:26:33,535][87330] Avg episode reward: [(0, '20.420'), (1, '17.220')] -[2023-10-15 02:26:33,787][88298] Updated weights for policy 0, policy_version 5390 (0.0007) -[2023-10-15 02:26:33,955][88300] Updated weights for policy 1, policy_version 5410 (0.0010) -[2023-10-15 02:26:34,151][88298] Updated weights for policy 0, policy_version 5400 (0.0007) -[2023-10-15 02:26:34,321][88300] Updated weights for policy 1, policy_version 5420 (0.0008) -[2023-10-15 02:26:34,692][88300] Updated weights for policy 1, policy_version 5430 (0.0010) -[2023-10-15 02:26:35,054][88300] Updated weights for policy 1, policy_version 5440 (0.0010) -[2023-10-15 02:26:38,139][88298] Updated weights for policy 0, policy_version 5410 (0.0008) -[2023-10-15 02:26:38,501][88298] Updated weights for policy 0, policy_version 5420 (0.0009) -[2023-10-15 02:26:38,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 11108352. Throughput: 0: 1741.9, 1: 1739.6. Samples: 2789946. Policy #0 lag: (min: 4.0, avg: 8.6, max: 36.0) -[2023-10-15 02:26:38,534][87330] Avg episode reward: [(0, '20.390'), (1, '17.650')] -[2023-10-15 02:26:38,884][88298] Updated weights for policy 0, policy_version 5430 (0.0008) -[2023-10-15 02:26:39,021][88300] Updated weights for policy 1, policy_version 5450 (0.0008) -[2023-10-15 02:26:39,248][88298] Updated weights for policy 0, policy_version 5440 (0.0009) -[2023-10-15 02:26:39,391][88300] Updated weights for policy 1, policy_version 5460 (0.0008) -[2023-10-15 02:26:39,764][88300] Updated weights for policy 1, policy_version 5470 (0.0011) -[2023-10-15 02:26:43,132][88298] Updated weights for policy 0, policy_version 5450 (0.0011) -[2023-10-15 02:26:43,505][88298] Updated weights for policy 0, policy_version 5460 (0.0009) -[2023-10-15 02:26:43,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 11173888. Throughput: 0: 1747.1, 1: 1769.2. Samples: 2811560. Policy #0 lag: (min: 2.0, avg: 3.3, max: 27.0) -[2023-10-15 02:26:43,534][87330] Avg episode reward: [(0, '20.620'), (1, '17.770')] -[2023-10-15 02:26:43,769][88300] Updated weights for policy 1, policy_version 5480 (0.0008) -[2023-10-15 02:26:43,874][88298] Updated weights for policy 0, policy_version 5470 (0.0009) -[2023-10-15 02:26:43,942][87905] Saving new best policy, reward=20.620! -[2023-10-15 02:26:44,154][88300] Updated weights for policy 1, policy_version 5490 (0.0010) -[2023-10-15 02:26:44,512][88300] Updated weights for policy 1, policy_version 5500 (0.0008) -[2023-10-15 02:26:47,879][88298] Updated weights for policy 0, policy_version 5480 (0.0010) -[2023-10-15 02:26:48,245][88298] Updated weights for policy 0, policy_version 5490 (0.0008) -[2023-10-15 02:26:48,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 11239424. Throughput: 0: 1732.4, 1: 1730.4. Samples: 2820832. Policy #0 lag: (min: 2.0, avg: 3.3, max: 27.0) -[2023-10-15 02:26:48,535][87330] Avg episode reward: [(0, '20.530'), (1, '18.120')] -[2023-10-15 02:26:48,616][88298] Updated weights for policy 0, policy_version 5500 (0.0010) -[2023-10-15 02:26:48,646][88300] Updated weights for policy 1, policy_version 5512 (0.0008) -[2023-10-15 02:26:49,012][88300] Updated weights for policy 1, policy_version 5522 (0.0007) -[2023-10-15 02:26:49,376][88300] Updated weights for policy 1, policy_version 5532 (0.0008) -[2023-10-15 02:26:52,519][88298] Updated weights for policy 0, policy_version 5510 (0.0007) -[2023-10-15 02:26:52,897][88298] Updated weights for policy 0, policy_version 5520 (0.0007) -[2023-10-15 02:26:53,211][88300] Updated weights for policy 1, policy_version 5542 (0.0009) -[2023-10-15 02:26:53,259][88298] Updated weights for policy 0, policy_version 5530 (0.0007) -[2023-10-15 02:26:53,534][87330] Fps is (10 sec: 16384.2, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 11337728. Throughput: 0: 1748.7, 1: 1760.6. Samples: 2842378. Policy #0 lag: (min: 17.0, avg: 33.7, max: 49.0) -[2023-10-15 02:26:53,534][87330] Avg episode reward: [(0, '20.390'), (1, '18.000')] -[2023-10-15 02:26:53,571][88300] Updated weights for policy 1, policy_version 5552 (0.0010) -[2023-10-15 02:26:53,948][88300] Updated weights for policy 1, policy_version 5562 (0.0010) -[2023-10-15 02:26:57,112][88298] Updated weights for policy 0, policy_version 5540 (0.0009) -[2023-10-15 02:26:57,482][88298] Updated weights for policy 0, policy_version 5550 (0.0009) -[2023-10-15 02:26:57,724][88300] Updated weights for policy 1, policy_version 5572 (0.0008) -[2023-10-15 02:26:57,857][88298] Updated weights for policy 0, policy_version 5560 (0.0007) -[2023-10-15 02:26:58,091][88300] Updated weights for policy 1, policy_version 5582 (0.0009) -[2023-10-15 02:26:58,464][88300] Updated weights for policy 1, policy_version 5592 (0.0009) -[2023-10-15 02:26:58,534][87330] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 11403264. Throughput: 0: 1730.1, 1: 1746.6. Samples: 2862634. Policy #0 lag: (min: 17.0, avg: 28.2, max: 49.0) -[2023-10-15 02:26:58,535][87330] Avg episode reward: [(0, '20.540'), (1, '18.280')] -[2023-10-15 02:26:58,548][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000005568_5701632.pth... -[2023-10-15 02:26:58,581][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000003936_4030464.pth -[2023-10-15 02:26:58,755][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000005600_5734400.pth... -[2023-10-15 02:26:58,792][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000003968_4063232.pth -[2023-10-15 02:27:01,873][88298] Updated weights for policy 0, policy_version 5570 (0.0007) -[2023-10-15 02:27:02,246][88298] Updated weights for policy 0, policy_version 5580 (0.0008) -[2023-10-15 02:27:02,403][88300] Updated weights for policy 1, policy_version 5602 (0.0009) -[2023-10-15 02:27:02,623][88298] Updated weights for policy 0, policy_version 5590 (0.0008) -[2023-10-15 02:27:02,775][88300] Updated weights for policy 1, policy_version 5612 (0.0008) -[2023-10-15 02:27:02,991][88298] Updated weights for policy 0, policy_version 5600 (0.0009) -[2023-10-15 02:27:03,151][88300] Updated weights for policy 1, policy_version 5622 (0.0009) -[2023-10-15 02:27:03,516][88300] Updated weights for policy 1, policy_version 5632 (0.0008) -[2023-10-15 02:27:03,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 11501568. Throughput: 0: 1748.3, 1: 1754.0. Samples: 2873500. Policy #0 lag: (min: 17.0, avg: 28.2, max: 49.0) -[2023-10-15 02:27:03,534][87330] Avg episode reward: [(0, '20.490'), (1, '18.590')] -[2023-10-15 02:27:03,535][88033] Saving new best policy, reward=18.590! -[2023-10-15 02:27:06,907][88298] Updated weights for policy 0, policy_version 5610 (0.0010) -[2023-10-15 02:27:07,269][88298] Updated weights for policy 0, policy_version 5620 (0.0007) -[2023-10-15 02:27:07,314][88300] Updated weights for policy 1, policy_version 5642 (0.0008) -[2023-10-15 02:27:07,644][88298] Updated weights for policy 0, policy_version 5630 (0.0007) -[2023-10-15 02:27:07,680][88300] Updated weights for policy 1, policy_version 5652 (0.0008) -[2023-10-15 02:27:08,051][88300] Updated weights for policy 1, policy_version 5662 (0.0007) -[2023-10-15 02:27:08,534][87330] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 11567104. Throughput: 0: 1735.2, 1: 1752.7. Samples: 2894274. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:27:08,534][87330] Avg episode reward: [(0, '20.610'), (1, '18.410')] -[2023-10-15 02:27:11,596][88298] Updated weights for policy 0, policy_version 5640 (0.0008) -[2023-10-15 02:27:11,969][88298] Updated weights for policy 0, policy_version 5650 (0.0008) -[2023-10-15 02:27:11,999][88300] Updated weights for policy 1, policy_version 5672 (0.0008) -[2023-10-15 02:27:12,340][88298] Updated weights for policy 0, policy_version 5660 (0.0007) -[2023-10-15 02:27:12,368][88300] Updated weights for policy 1, policy_version 5682 (0.0008) -[2023-10-15 02:27:12,733][88300] Updated weights for policy 1, policy_version 5692 (0.0008) -[2023-10-15 02:27:13,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 11632640. Throughput: 0: 1708.4, 1: 1730.6. Samples: 2913668. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:27:13,534][87330] Avg episode reward: [(0, '20.600'), (1, '18.750')] -[2023-10-15 02:27:13,544][88033] Saving new best policy, reward=18.750! -[2023-10-15 02:27:16,164][88298] Updated weights for policy 0, policy_version 5670 (0.0010) -[2023-10-15 02:27:16,536][88298] Updated weights for policy 0, policy_version 5680 (0.0008) -[2023-10-15 02:27:16,629][88300] Updated weights for policy 1, policy_version 5702 (0.0009) -[2023-10-15 02:27:16,915][88298] Updated weights for policy 0, policy_version 5690 (0.0009) -[2023-10-15 02:27:16,995][88300] Updated weights for policy 1, policy_version 5712 (0.0008) -[2023-10-15 02:27:17,364][88300] Updated weights for policy 1, policy_version 5722 (0.0009) -[2023-10-15 02:27:18,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 11698176. Throughput: 0: 1740.1, 1: 1757.3. Samples: 2925870. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:27:18,535][87330] Avg episode reward: [(0, '20.360'), (1, '18.760')] -[2023-10-15 02:27:18,537][88033] Saving new best policy, reward=18.760! -[2023-10-15 02:27:20,823][88298] Updated weights for policy 0, policy_version 5700 (0.0008) -[2023-10-15 02:27:21,191][88298] Updated weights for policy 0, policy_version 5710 (0.0008) -[2023-10-15 02:27:21,339][88300] Updated weights for policy 1, policy_version 5732 (0.0009) -[2023-10-15 02:27:21,571][88298] Updated weights for policy 0, policy_version 5720 (0.0008) -[2023-10-15 02:27:21,701][88300] Updated weights for policy 1, policy_version 5742 (0.0008) -[2023-10-15 02:27:22,070][88300] Updated weights for policy 1, policy_version 5752 (0.0009) -[2023-10-15 02:27:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 11763712. Throughput: 0: 1714.3, 1: 1730.2. Samples: 2944946. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:27:23,534][87330] Avg episode reward: [(0, '20.520'), (1, '19.090')] -[2023-10-15 02:27:23,535][88033] Saving new best policy, reward=19.090! -[2023-10-15 02:27:25,516][88298] Updated weights for policy 0, policy_version 5730 (0.0007) -[2023-10-15 02:27:25,836][88300] Updated weights for policy 1, policy_version 5762 (0.0007) -[2023-10-15 02:27:25,893][88298] Updated weights for policy 0, policy_version 5740 (0.0007) -[2023-10-15 02:27:26,201][88300] Updated weights for policy 1, policy_version 5772 (0.0008) -[2023-10-15 02:27:26,263][88298] Updated weights for policy 0, policy_version 5750 (0.0008) -[2023-10-15 02:27:26,559][88300] Updated weights for policy 1, policy_version 5782 (0.0008) -[2023-10-15 02:27:26,632][88298] Updated weights for policy 0, policy_version 5760 (0.0008) -[2023-10-15 02:27:26,926][88300] Updated weights for policy 1, policy_version 5792 (0.0008) -[2023-10-15 02:27:28,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 11829248. Throughput: 0: 1709.9, 1: 1729.5. Samples: 2966336. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-15 02:27:28,535][87330] Avg episode reward: [(0, '20.610'), (1, '19.340')] -[2023-10-15 02:27:28,545][88033] Saving new best policy, reward=19.340! -[2023-10-15 02:27:30,550][88298] Updated weights for policy 0, policy_version 5770 (0.0008) -[2023-10-15 02:27:30,818][88300] Updated weights for policy 1, policy_version 5802 (0.0008) -[2023-10-15 02:27:30,926][88298] Updated weights for policy 0, policy_version 5780 (0.0007) -[2023-10-15 02:27:31,186][88300] Updated weights for policy 1, policy_version 5812 (0.0009) -[2023-10-15 02:27:31,294][88298] Updated weights for policy 0, policy_version 5790 (0.0009) -[2023-10-15 02:27:31,554][88300] Updated weights for policy 1, policy_version 5822 (0.0007) -[2023-10-15 02:27:33,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 11894784. Throughput: 0: 1726.7, 1: 1744.8. Samples: 2977050. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-15 02:27:33,534][87330] Avg episode reward: [(0, '20.780'), (1, '18.860')] -[2023-10-15 02:27:33,535][87905] Saving new best policy, reward=20.780! -[2023-10-15 02:27:35,165][88298] Updated weights for policy 0, policy_version 5800 (0.0009) -[2023-10-15 02:27:35,404][88300] Updated weights for policy 1, policy_version 5832 (0.0008) -[2023-10-15 02:27:35,538][88298] Updated weights for policy 0, policy_version 5810 (0.0008) -[2023-10-15 02:27:35,775][88300] Updated weights for policy 1, policy_version 5842 (0.0007) -[2023-10-15 02:27:35,904][88298] Updated weights for policy 0, policy_version 5820 (0.0008) -[2023-10-15 02:27:36,140][88300] Updated weights for policy 1, policy_version 5852 (0.0007) -[2023-10-15 02:27:38,534][87330] Fps is (10 sec: 13107.6, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 11960320. Throughput: 0: 1712.1, 1: 1727.4. Samples: 2997158. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:27:38,534][87330] Avg episode reward: [(0, '20.820'), (1, '19.060')] -[2023-10-15 02:27:38,535][87905] Saving new best policy, reward=20.820! -[2023-10-15 02:27:40,090][88298] Updated weights for policy 0, policy_version 5830 (0.0007) -[2023-10-15 02:27:40,142][88300] Updated weights for policy 1, policy_version 5862 (0.0007) -[2023-10-15 02:27:40,467][88298] Updated weights for policy 0, policy_version 5840 (0.0007) -[2023-10-15 02:27:40,507][88300] Updated weights for policy 1, policy_version 5872 (0.0007) -[2023-10-15 02:27:40,836][88298] Updated weights for policy 0, policy_version 5850 (0.0008) -[2023-10-15 02:27:40,881][88300] Updated weights for policy 1, policy_version 5882 (0.0007) -[2023-10-15 02:27:43,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 12025856. Throughput: 0: 1726.4, 1: 1735.0. Samples: 3018398. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:27:43,535][87330] Avg episode reward: [(0, '20.940'), (1, '19.280')] -[2023-10-15 02:27:43,542][87905] Saving new best policy, reward=20.940! -[2023-10-15 02:27:44,648][88298] Updated weights for policy 0, policy_version 5860 (0.0008) -[2023-10-15 02:27:44,932][88300] Updated weights for policy 1, policy_version 5892 (0.0007) -[2023-10-15 02:27:45,029][88298] Updated weights for policy 0, policy_version 5870 (0.0009) -[2023-10-15 02:27:45,293][88300] Updated weights for policy 1, policy_version 5902 (0.0008) -[2023-10-15 02:27:45,404][88298] Updated weights for policy 0, policy_version 5880 (0.0008) -[2023-10-15 02:27:45,663][88300] Updated weights for policy 1, policy_version 5912 (0.0008) -[2023-10-15 02:27:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 12091392. Throughput: 0: 1711.6, 1: 1720.4. Samples: 3027942. Policy #0 lag: (min: 31.0, avg: 33.2, max: 62.0) -[2023-10-15 02:27:48,534][87330] Avg episode reward: [(0, '21.170'), (1, '19.140')] -[2023-10-15 02:27:48,535][87905] Saving new best policy, reward=21.170! -[2023-10-15 02:27:49,118][88298] Updated weights for policy 0, policy_version 5890 (0.0009) -[2023-10-15 02:27:49,485][88298] Updated weights for policy 0, policy_version 5900 (0.0009) -[2023-10-15 02:27:49,597][88300] Updated weights for policy 1, policy_version 5922 (0.0008) -[2023-10-15 02:27:49,855][88298] Updated weights for policy 0, policy_version 5910 (0.0007) -[2023-10-15 02:27:49,968][88300] Updated weights for policy 1, policy_version 5932 (0.0007) -[2023-10-15 02:27:50,221][88298] Updated weights for policy 0, policy_version 5920 (0.0008) -[2023-10-15 02:27:50,339][88300] Updated weights for policy 1, policy_version 5942 (0.0008) -[2023-10-15 02:27:50,708][88300] Updated weights for policy 1, policy_version 5952 (0.0007) -[2023-10-15 02:27:53,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 12156928. Throughput: 0: 1722.7, 1: 1723.1. Samples: 3049334. Policy #0 lag: (min: 31.0, avg: 33.2, max: 62.0) -[2023-10-15 02:27:53,534][87330] Avg episode reward: [(0, '21.180'), (1, '18.980')] -[2023-10-15 02:27:53,535][87905] Saving new best policy, reward=21.180! -[2023-10-15 02:27:54,081][88298] Updated weights for policy 0, policy_version 5930 (0.0010) -[2023-10-15 02:27:54,455][88298] Updated weights for policy 0, policy_version 5940 (0.0008) -[2023-10-15 02:27:54,582][88300] Updated weights for policy 1, policy_version 5962 (0.0008) -[2023-10-15 02:27:54,828][88298] Updated weights for policy 0, policy_version 5950 (0.0008) -[2023-10-15 02:27:54,940][88300] Updated weights for policy 1, policy_version 5972 (0.0008) -[2023-10-15 02:27:55,306][88300] Updated weights for policy 1, policy_version 5982 (0.0009) -[2023-10-15 02:27:58,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 12222464. Throughput: 0: 1752.7, 1: 1744.6. Samples: 3071048. Policy #0 lag: (min: 17.0, avg: 17.4, max: 30.0) -[2023-10-15 02:27:58,534][87330] Avg episode reward: [(0, '21.210'), (1, '18.770')] -[2023-10-15 02:27:58,774][88298] Updated weights for policy 0, policy_version 5960 (0.0009) -[2023-10-15 02:27:59,151][88298] Updated weights for policy 0, policy_version 5970 (0.0009) -[2023-10-15 02:27:59,299][88300] Updated weights for policy 1, policy_version 5992 (0.0008) -[2023-10-15 02:27:59,524][88298] Updated weights for policy 0, policy_version 5980 (0.0008) -[2023-10-15 02:27:59,656][88300] Updated weights for policy 1, policy_version 6002 (0.0007) -[2023-10-15 02:27:59,671][87905] Saving new best policy, reward=21.210! -[2023-10-15 02:28:00,029][88300] Updated weights for policy 1, policy_version 6012 (0.0009) -[2023-10-15 02:28:03,433][88298] Updated weights for policy 0, policy_version 5990 (0.0008) -[2023-10-15 02:28:03,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 12288000. Throughput: 0: 1720.0, 1: 1715.0. Samples: 3080444. Policy #0 lag: (min: 17.0, avg: 17.4, max: 30.0) -[2023-10-15 02:28:03,535][87330] Avg episode reward: [(0, '21.220'), (1, '19.360')] -[2023-10-15 02:28:03,536][88033] Saving new best policy, reward=19.360! -[2023-10-15 02:28:03,806][88298] Updated weights for policy 0, policy_version 6000 (0.0008) -[2023-10-15 02:28:03,931][88300] Updated weights for policy 1, policy_version 6022 (0.0010) -[2023-10-15 02:28:04,174][88298] Updated weights for policy 0, policy_version 6010 (0.0008) -[2023-10-15 02:28:04,303][88300] Updated weights for policy 1, policy_version 6032 (0.0008) -[2023-10-15 02:28:04,393][87905] Saving new best policy, reward=21.220! -[2023-10-15 02:28:04,669][88300] Updated weights for policy 1, policy_version 6042 (0.0009) -[2023-10-15 02:28:08,039][88298] Updated weights for policy 0, policy_version 6020 (0.0008) -[2023-10-15 02:28:08,408][88298] Updated weights for policy 0, policy_version 6030 (0.0008) -[2023-10-15 02:28:08,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 12353536. Throughput: 0: 1747.5, 1: 1739.8. Samples: 3101872. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-15 02:28:08,534][87330] Avg episode reward: [(0, '21.150'), (1, '19.430')] -[2023-10-15 02:28:08,625][88300] Updated weights for policy 1, policy_version 6052 (0.0010) -[2023-10-15 02:28:08,779][88298] Updated weights for policy 0, policy_version 6040 (0.0008) -[2023-10-15 02:28:08,989][88300] Updated weights for policy 1, policy_version 6062 (0.0008) -[2023-10-15 02:28:09,359][88300] Updated weights for policy 1, policy_version 6072 (0.0007) -[2023-10-15 02:28:09,655][88033] Saving new best policy, reward=19.430! -[2023-10-15 02:28:12,588][88298] Updated weights for policy 0, policy_version 6050 (0.0010) -[2023-10-15 02:28:12,963][88298] Updated weights for policy 0, policy_version 6060 (0.0009) -[2023-10-15 02:28:13,266][88300] Updated weights for policy 1, policy_version 6082 (0.0010) -[2023-10-15 02:28:13,342][88298] Updated weights for policy 0, policy_version 6070 (0.0008) -[2023-10-15 02:28:13,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 12419072. Throughput: 0: 1748.0, 1: 1734.6. Samples: 3123054. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-15 02:28:13,535][87330] Avg episode reward: [(0, '21.030'), (1, '19.070')] -[2023-10-15 02:28:13,630][88300] Updated weights for policy 1, policy_version 6092 (0.0007) -[2023-10-15 02:28:13,712][88298] Updated weights for policy 0, policy_version 6080 (0.0008) -[2023-10-15 02:28:14,004][88300] Updated weights for policy 1, policy_version 6102 (0.0010) -[2023-10-15 02:28:14,372][88300] Updated weights for policy 1, policy_version 6112 (0.0008) -[2023-10-15 02:28:17,846][88298] Updated weights for policy 0, policy_version 6090 (0.0010) -[2023-10-15 02:28:18,217][88298] Updated weights for policy 0, policy_version 6100 (0.0007) -[2023-10-15 02:28:18,419][88300] Updated weights for policy 1, policy_version 6122 (0.0008) -[2023-10-15 02:28:18,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 12484608. Throughput: 0: 1730.4, 1: 1722.6. Samples: 3132432. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) -[2023-10-15 02:28:18,535][87330] Avg episode reward: [(0, '21.020'), (1, '18.860')] -[2023-10-15 02:28:18,589][88298] Updated weights for policy 0, policy_version 6110 (0.0008) -[2023-10-15 02:28:18,792][88300] Updated weights for policy 1, policy_version 6132 (0.0007) -[2023-10-15 02:28:19,168][88300] Updated weights for policy 1, policy_version 6142 (0.0007) -[2023-10-15 02:28:22,660][88298] Updated weights for policy 0, policy_version 6120 (0.0008) -[2023-10-15 02:28:23,029][88298] Updated weights for policy 0, policy_version 6130 (0.0007) -[2023-10-15 02:28:23,194][88300] Updated weights for policy 1, policy_version 6152 (0.0010) -[2023-10-15 02:28:23,399][88298] Updated weights for policy 0, policy_version 6140 (0.0009) -[2023-10-15 02:28:23,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 12550144. Throughput: 0: 1743.4, 1: 1731.2. Samples: 3153514. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) -[2023-10-15 02:28:23,535][87330] Avg episode reward: [(0, '21.030'), (1, '19.110')] -[2023-10-15 02:28:23,561][88300] Updated weights for policy 1, policy_version 6162 (0.0008) -[2023-10-15 02:28:23,929][88300] Updated weights for policy 1, policy_version 6172 (0.0008) -[2023-10-15 02:28:27,364][88298] Updated weights for policy 0, policy_version 6150 (0.0010) -[2023-10-15 02:28:27,739][88298] Updated weights for policy 0, policy_version 6160 (0.0008) -[2023-10-15 02:28:27,739][88300] Updated weights for policy 1, policy_version 6182 (0.0010) -[2023-10-15 02:28:28,105][88300] Updated weights for policy 1, policy_version 6192 (0.0009) -[2023-10-15 02:28:28,115][88298] Updated weights for policy 0, policy_version 6170 (0.0009) -[2023-10-15 02:28:28,465][88300] Updated weights for policy 1, policy_version 6202 (0.0009) -[2023-10-15 02:28:28,534][87330] Fps is (10 sec: 16383.7, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 12648448. Throughput: 0: 1731.7, 1: 1717.3. Samples: 3173606. Policy #0 lag: (min: 10.0, avg: 14.3, max: 42.0) -[2023-10-15 02:28:28,535][87330] Avg episode reward: [(0, '20.850'), (1, '19.040')] -[2023-10-15 02:28:32,092][88298] Updated weights for policy 0, policy_version 6180 (0.0007) -[2023-10-15 02:28:32,240][88300] Updated weights for policy 1, policy_version 6212 (0.0009) -[2023-10-15 02:28:32,468][88298] Updated weights for policy 0, policy_version 6190 (0.0007) -[2023-10-15 02:28:32,605][88300] Updated weights for policy 1, policy_version 6222 (0.0009) -[2023-10-15 02:28:32,835][88298] Updated weights for policy 0, policy_version 6200 (0.0008) -[2023-10-15 02:28:32,979][88300] Updated weights for policy 1, policy_version 6232 (0.0008) -[2023-10-15 02:28:33,534][87330] Fps is (10 sec: 19660.6, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 12746752. Throughput: 0: 1744.4, 1: 1738.7. Samples: 3184686. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-15 02:28:33,535][87330] Avg episode reward: [(0, '20.860'), (1, '19.110')] -[2023-10-15 02:28:36,759][88298] Updated weights for policy 0, policy_version 6210 (0.0010) -[2023-10-15 02:28:36,936][88300] Updated weights for policy 1, policy_version 6242 (0.0008) -[2023-10-15 02:28:37,125][88298] Updated weights for policy 0, policy_version 6220 (0.0008) -[2023-10-15 02:28:37,311][88300] Updated weights for policy 1, policy_version 6252 (0.0007) -[2023-10-15 02:28:37,487][88298] Updated weights for policy 0, policy_version 6230 (0.0008) -[2023-10-15 02:28:37,687][88300] Updated weights for policy 1, policy_version 6262 (0.0009) -[2023-10-15 02:28:37,865][88298] Updated weights for policy 0, policy_version 6240 (0.0008) -[2023-10-15 02:28:38,053][88300] Updated weights for policy 1, policy_version 6272 (0.0009) -[2023-10-15 02:28:38,534][87330] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 12812288. Throughput: 0: 1739.0, 1: 1734.4. Samples: 3205638. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-15 02:28:38,534][87330] Avg episode reward: [(0, '20.890'), (1, '19.200')] -[2023-10-15 02:28:41,858][88298] Updated weights for policy 0, policy_version 6250 (0.0007) -[2023-10-15 02:28:41,985][88300] Updated weights for policy 1, policy_version 6282 (0.0007) -[2023-10-15 02:28:42,229][88298] Updated weights for policy 0, policy_version 6260 (0.0009) -[2023-10-15 02:28:42,337][88300] Updated weights for policy 1, policy_version 6292 (0.0008) -[2023-10-15 02:28:42,604][88298] Updated weights for policy 0, policy_version 6270 (0.0008) -[2023-10-15 02:28:42,706][88300] Updated weights for policy 1, policy_version 6302 (0.0007) -[2023-10-15 02:28:43,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 12877824. Throughput: 0: 1699.6, 1: 1712.9. Samples: 3224610. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:28:43,534][87330] Avg episode reward: [(0, '20.740'), (1, '19.460')] -[2023-10-15 02:28:43,543][88033] Saving new best policy, reward=19.460! -[2023-10-15 02:28:46,564][88298] Updated weights for policy 0, policy_version 6280 (0.0007) -[2023-10-15 02:28:46,697][88300] Updated weights for policy 1, policy_version 6312 (0.0008) -[2023-10-15 02:28:46,938][88298] Updated weights for policy 0, policy_version 6290 (0.0007) -[2023-10-15 02:28:47,061][88300] Updated weights for policy 1, policy_version 6322 (0.0008) -[2023-10-15 02:28:47,310][88298] Updated weights for policy 0, policy_version 6300 (0.0009) -[2023-10-15 02:28:47,428][88300] Updated weights for policy 1, policy_version 6332 (0.0008) -[2023-10-15 02:28:48,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 12943360. Throughput: 0: 1731.5, 1: 1741.2. Samples: 3236714. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:28:48,535][87330] Avg episode reward: [(0, '20.750'), (1, '19.110')] -[2023-10-15 02:28:51,209][88298] Updated weights for policy 0, policy_version 6310 (0.0010) -[2023-10-15 02:28:51,375][88300] Updated weights for policy 1, policy_version 6342 (0.0007) -[2023-10-15 02:28:51,581][88298] Updated weights for policy 0, policy_version 6320 (0.0008) -[2023-10-15 02:28:51,749][88300] Updated weights for policy 1, policy_version 6352 (0.0008) -[2023-10-15 02:28:51,952][88298] Updated weights for policy 0, policy_version 6330 (0.0007) -[2023-10-15 02:28:52,107][88300] Updated weights for policy 1, policy_version 6362 (0.0008) -[2023-10-15 02:28:53,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 13008896. Throughput: 0: 1710.0, 1: 1716.9. Samples: 3256082. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:28:53,535][87330] Avg episode reward: [(0, '20.680'), (1, '19.200')] -[2023-10-15 02:28:55,780][88298] Updated weights for policy 0, policy_version 6340 (0.0007) -[2023-10-15 02:28:55,920][88300] Updated weights for policy 1, policy_version 6372 (0.0007) -[2023-10-15 02:28:56,151][88298] Updated weights for policy 0, policy_version 6350 (0.0008) -[2023-10-15 02:28:56,288][88300] Updated weights for policy 1, policy_version 6382 (0.0007) -[2023-10-15 02:28:56,518][88298] Updated weights for policy 0, policy_version 6360 (0.0008) -[2023-10-15 02:28:56,661][88300] Updated weights for policy 1, policy_version 6392 (0.0007) -[2023-10-15 02:28:58,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 13074432. Throughput: 0: 1703.3, 1: 1718.6. Samples: 3277040. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:28:58,534][87330] Avg episode reward: [(0, '20.870'), (1, '19.330')] -[2023-10-15 02:28:58,543][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000006400_6553600.pth... -[2023-10-15 02:28:58,543][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000006368_6520832.pth... -[2023-10-15 02:28:58,578][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000004768_4882432.pth -[2023-10-15 02:28:58,582][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000004768_4882432.pth -[2023-10-15 02:29:00,393][88298] Updated weights for policy 0, policy_version 6370 (0.0008) -[2023-10-15 02:29:00,591][88300] Updated weights for policy 1, policy_version 6402 (0.0008) -[2023-10-15 02:29:00,769][88298] Updated weights for policy 0, policy_version 6380 (0.0008) -[2023-10-15 02:29:00,963][88300] Updated weights for policy 1, policy_version 6412 (0.0008) -[2023-10-15 02:29:01,134][88298] Updated weights for policy 0, policy_version 6390 (0.0008) -[2023-10-15 02:29:01,326][88300] Updated weights for policy 1, policy_version 6422 (0.0007) -[2023-10-15 02:29:01,509][88298] Updated weights for policy 0, policy_version 6400 (0.0009) -[2023-10-15 02:29:01,704][88300] Updated weights for policy 1, policy_version 6432 (0.0009) -[2023-10-15 02:29:03,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 13139968. Throughput: 0: 1719.0, 1: 1736.3. Samples: 3287918. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-10-15 02:29:03,534][87330] Avg episode reward: [(0, '20.890'), (1, '19.270')] -[2023-10-15 02:29:05,528][88298] Updated weights for policy 0, policy_version 6410 (0.0009) -[2023-10-15 02:29:05,649][88300] Updated weights for policy 1, policy_version 6442 (0.0009) -[2023-10-15 02:29:05,910][88298] Updated weights for policy 0, policy_version 6420 (0.0009) -[2023-10-15 02:29:06,028][88300] Updated weights for policy 1, policy_version 6452 (0.0007) -[2023-10-15 02:29:06,283][88298] Updated weights for policy 0, policy_version 6430 (0.0008) -[2023-10-15 02:29:06,388][88300] Updated weights for policy 1, policy_version 6462 (0.0009) -[2023-10-15 02:29:08,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 13205504. Throughput: 0: 1700.5, 1: 1729.3. Samples: 3307854. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-10-15 02:29:08,535][87330] Avg episode reward: [(0, '20.810'), (1, '19.050')] -[2023-10-15 02:29:09,988][88298] Updated weights for policy 0, policy_version 6440 (0.0007) -[2023-10-15 02:29:10,365][88298] Updated weights for policy 0, policy_version 6450 (0.0007) -[2023-10-15 02:29:10,385][88300] Updated weights for policy 1, policy_version 6472 (0.0008) -[2023-10-15 02:29:10,739][88298] Updated weights for policy 0, policy_version 6460 (0.0008) -[2023-10-15 02:29:10,748][88300] Updated weights for policy 1, policy_version 6482 (0.0007) -[2023-10-15 02:29:11,114][88300] Updated weights for policy 1, policy_version 6492 (0.0008) -[2023-10-15 02:29:13,534][87330] Fps is (10 sec: 13106.6, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 13271040. Throughput: 0: 1725.5, 1: 1746.4. Samples: 3329842. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:29:13,535][87330] Avg episode reward: [(0, '20.990'), (1, '19.250')] -[2023-10-15 02:29:14,610][88298] Updated weights for policy 0, policy_version 6470 (0.0007) -[2023-10-15 02:29:14,985][88298] Updated weights for policy 0, policy_version 6480 (0.0009) -[2023-10-15 02:29:15,012][88300] Updated weights for policy 1, policy_version 6502 (0.0010) -[2023-10-15 02:29:15,348][88298] Updated weights for policy 0, policy_version 6490 (0.0009) -[2023-10-15 02:29:15,376][88300] Updated weights for policy 1, policy_version 6512 (0.0007) -[2023-10-15 02:29:15,748][88300] Updated weights for policy 1, policy_version 6522 (0.0007) -[2023-10-15 02:29:18,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 13336576. Throughput: 0: 1706.6, 1: 1723.6. Samples: 3339046. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:29:18,535][87330] Avg episode reward: [(0, '21.150'), (1, '19.690')] -[2023-10-15 02:29:18,536][88033] Saving new best policy, reward=19.690! -[2023-10-15 02:29:19,199][88298] Updated weights for policy 0, policy_version 6500 (0.0008) -[2023-10-15 02:29:19,571][88298] Updated weights for policy 0, policy_version 6510 (0.0007) -[2023-10-15 02:29:19,629][88300] Updated weights for policy 1, policy_version 6532 (0.0008) -[2023-10-15 02:29:19,940][88298] Updated weights for policy 0, policy_version 6520 (0.0008) -[2023-10-15 02:29:20,004][88300] Updated weights for policy 1, policy_version 6542 (0.0009) -[2023-10-15 02:29:20,369][88300] Updated weights for policy 1, policy_version 6552 (0.0010) -[2023-10-15 02:29:23,534][87330] Fps is (10 sec: 13107.8, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 13402112. Throughput: 0: 1715.3, 1: 1725.6. Samples: 3360480. Policy #0 lag: (min: 0.0, avg: 20.6, max: 32.0) -[2023-10-15 02:29:23,534][87330] Avg episode reward: [(0, '21.270'), (1, '19.930')] -[2023-10-15 02:29:23,535][87905] Saving new best policy, reward=21.270! -[2023-10-15 02:29:23,535][88033] Saving new best policy, reward=19.930! -[2023-10-15 02:29:23,979][88298] Updated weights for policy 0, policy_version 6530 (0.0008) -[2023-10-15 02:29:24,333][88300] Updated weights for policy 1, policy_version 6562 (0.0010) -[2023-10-15 02:29:24,356][88298] Updated weights for policy 0, policy_version 6540 (0.0008) -[2023-10-15 02:29:24,704][88300] Updated weights for policy 1, policy_version 6572 (0.0007) -[2023-10-15 02:29:24,731][88298] Updated weights for policy 0, policy_version 6550 (0.0007) -[2023-10-15 02:29:25,064][88300] Updated weights for policy 1, policy_version 6582 (0.0009) -[2023-10-15 02:29:25,100][88298] Updated weights for policy 0, policy_version 6560 (0.0008) -[2023-10-15 02:29:25,435][88300] Updated weights for policy 1, policy_version 6592 (0.0007) -[2023-10-15 02:29:28,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 13467648. Throughput: 0: 1747.1, 1: 1751.1. Samples: 3382026. Policy #0 lag: (min: 0.0, avg: 20.6, max: 32.0) -[2023-10-15 02:29:28,534][87330] Avg episode reward: [(0, '21.170'), (1, '20.050')] -[2023-10-15 02:29:28,547][88033] Saving new best policy, reward=20.050! -[2023-10-15 02:29:29,126][88298] Updated weights for policy 0, policy_version 6570 (0.0007) -[2023-10-15 02:29:29,431][88300] Updated weights for policy 1, policy_version 6602 (0.0007) -[2023-10-15 02:29:29,492][88298] Updated weights for policy 0, policy_version 6580 (0.0007) -[2023-10-15 02:29:29,795][88300] Updated weights for policy 1, policy_version 6612 (0.0008) -[2023-10-15 02:29:29,860][88298] Updated weights for policy 0, policy_version 6590 (0.0008) -[2023-10-15 02:29:30,166][88300] Updated weights for policy 1, policy_version 6622 (0.0008) -[2023-10-15 02:29:33,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 13533184. Throughput: 0: 1717.2, 1: 1721.7. Samples: 3391466. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-15 02:29:33,535][87330] Avg episode reward: [(0, '21.160'), (1, '20.160')] -[2023-10-15 02:29:33,536][88033] Saving new best policy, reward=20.160! -[2023-10-15 02:29:33,792][88298] Updated weights for policy 0, policy_version 6600 (0.0008) -[2023-10-15 02:29:34,042][88300] Updated weights for policy 1, policy_version 6632 (0.0008) -[2023-10-15 02:29:34,158][88298] Updated weights for policy 0, policy_version 6610 (0.0008) -[2023-10-15 02:29:34,412][88300] Updated weights for policy 1, policy_version 6642 (0.0007) -[2023-10-15 02:29:34,533][88298] Updated weights for policy 0, policy_version 6620 (0.0008) -[2023-10-15 02:29:34,783][88300] Updated weights for policy 1, policy_version 6652 (0.0007) -[2023-10-15 02:29:38,488][88298] Updated weights for policy 0, policy_version 6630 (0.0008) -[2023-10-15 02:29:38,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 13598720. Throughput: 0: 1734.1, 1: 1746.5. Samples: 3412708. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-15 02:29:38,535][87330] Avg episode reward: [(0, '21.170'), (1, '20.360')] -[2023-10-15 02:29:38,624][88300] Updated weights for policy 1, policy_version 6662 (0.0009) -[2023-10-15 02:29:38,861][88298] Updated weights for policy 0, policy_version 6640 (0.0007) -[2023-10-15 02:29:38,987][88300] Updated weights for policy 1, policy_version 6672 (0.0009) -[2023-10-15 02:29:39,227][88298] Updated weights for policy 0, policy_version 6650 (0.0008) -[2023-10-15 02:29:39,349][88300] Updated weights for policy 1, policy_version 6682 (0.0007) -[2023-10-15 02:29:39,564][88033] Saving new best policy, reward=20.360! -[2023-10-15 02:29:43,223][88300] Updated weights for policy 1, policy_version 6692 (0.0008) -[2023-10-15 02:29:43,234][88298] Updated weights for policy 0, policy_version 6660 (0.0009) -[2023-10-15 02:29:43,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 13664256. Throughput: 0: 1741.3, 1: 1744.6. Samples: 3433904. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) -[2023-10-15 02:29:43,535][87330] Avg episode reward: [(0, '21.120'), (1, '20.420')] -[2023-10-15 02:29:43,599][88300] Updated weights for policy 1, policy_version 6702 (0.0008) -[2023-10-15 02:29:43,605][88298] Updated weights for policy 0, policy_version 6670 (0.0007) -[2023-10-15 02:29:43,962][88300] Updated weights for policy 1, policy_version 6712 (0.0010) -[2023-10-15 02:29:43,976][88298] Updated weights for policy 0, policy_version 6680 (0.0007) -[2023-10-15 02:29:44,258][88033] Saving new best policy, reward=20.420! -[2023-10-15 02:29:47,944][88298] Updated weights for policy 0, policy_version 6690 (0.0008) -[2023-10-15 02:29:47,994][88300] Updated weights for policy 1, policy_version 6722 (0.0009) -[2023-10-15 02:29:48,321][88298] Updated weights for policy 0, policy_version 6700 (0.0008) -[2023-10-15 02:29:48,363][88300] Updated weights for policy 1, policy_version 6732 (0.0010) -[2023-10-15 02:29:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 13729792. Throughput: 0: 1724.9, 1: 1729.9. Samples: 3443384. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) -[2023-10-15 02:29:48,534][87330] Avg episode reward: [(0, '21.190'), (1, '20.250')] -[2023-10-15 02:29:48,694][88298] Updated weights for policy 0, policy_version 6710 (0.0007) -[2023-10-15 02:29:48,742][88300] Updated weights for policy 1, policy_version 6742 (0.0007) -[2023-10-15 02:29:49,060][88298] Updated weights for policy 0, policy_version 6720 (0.0007) -[2023-10-15 02:29:49,112][88300] Updated weights for policy 1, policy_version 6752 (0.0008) -[2023-10-15 02:29:52,901][88300] Updated weights for policy 1, policy_version 6762 (0.0007) -[2023-10-15 02:29:53,026][88298] Updated weights for policy 0, policy_version 6730 (0.0008) -[2023-10-15 02:29:53,272][88300] Updated weights for policy 1, policy_version 6772 (0.0009) -[2023-10-15 02:29:53,393][88298] Updated weights for policy 0, policy_version 6740 (0.0008) -[2023-10-15 02:29:53,534][87330] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 13795328. Throughput: 0: 1745.9, 1: 1745.3. Samples: 3464960. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:29:53,534][87330] Avg episode reward: [(0, '21.150'), (1, '20.380')] -[2023-10-15 02:29:53,653][88300] Updated weights for policy 1, policy_version 6782 (0.0010) -[2023-10-15 02:29:53,764][88298] Updated weights for policy 0, policy_version 6750 (0.0007) -[2023-10-15 02:29:57,567][88298] Updated weights for policy 0, policy_version 6760 (0.0007) -[2023-10-15 02:29:57,588][88300] Updated weights for policy 1, policy_version 6792 (0.0008) -[2023-10-15 02:29:57,938][88298] Updated weights for policy 0, policy_version 6770 (0.0009) -[2023-10-15 02:29:57,950][88300] Updated weights for policy 1, policy_version 6802 (0.0008) -[2023-10-15 02:29:58,309][88298] Updated weights for policy 0, policy_version 6780 (0.0008) -[2023-10-15 02:29:58,321][88300] Updated weights for policy 1, policy_version 6812 (0.0008) -[2023-10-15 02:29:58,534][87330] Fps is (10 sec: 19660.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 13926400. Throughput: 0: 1728.0, 1: 1713.8. Samples: 3484722. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:29:58,534][87330] Avg episode reward: [(0, '21.100'), (1, '20.400')] -[2023-10-15 02:30:02,167][88300] Updated weights for policy 1, policy_version 6822 (0.0007) -[2023-10-15 02:30:02,295][88298] Updated weights for policy 0, policy_version 6790 (0.0009) -[2023-10-15 02:30:02,529][88300] Updated weights for policy 1, policy_version 6832 (0.0008) -[2023-10-15 02:30:02,679][88298] Updated weights for policy 0, policy_version 6800 (0.0009) -[2023-10-15 02:30:02,901][88300] Updated weights for policy 1, policy_version 6842 (0.0008) -[2023-10-15 02:30:03,052][88298] Updated weights for policy 0, policy_version 6810 (0.0007) -[2023-10-15 02:30:03,534][87330] Fps is (10 sec: 19660.7, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 13991936. Throughput: 0: 1745.1, 1: 1739.2. Samples: 3495842. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:30:03,535][87330] Avg episode reward: [(0, '21.110'), (1, '20.540')] -[2023-10-15 02:30:03,536][88033] Saving new best policy, reward=20.540! -[2023-10-15 02:30:06,854][88300] Updated weights for policy 1, policy_version 6852 (0.0008) -[2023-10-15 02:30:06,972][88298] Updated weights for policy 0, policy_version 6820 (0.0009) -[2023-10-15 02:30:07,223][88300] Updated weights for policy 1, policy_version 6862 (0.0007) -[2023-10-15 02:30:07,345][88298] Updated weights for policy 0, policy_version 6830 (0.0007) -[2023-10-15 02:30:07,595][88300] Updated weights for policy 1, policy_version 6872 (0.0007) -[2023-10-15 02:30:07,716][88298] Updated weights for policy 0, policy_version 6840 (0.0008) -[2023-10-15 02:30:08,534][87330] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 14057472. Throughput: 0: 1740.1, 1: 1731.9. Samples: 3516722. Policy #0 lag: (min: 14.0, avg: 17.3, max: 46.0) -[2023-10-15 02:30:08,535][87330] Avg episode reward: [(0, '21.010'), (1, '20.410')] -[2023-10-15 02:30:11,603][88300] Updated weights for policy 1, policy_version 6882 (0.0008) -[2023-10-15 02:30:11,698][88298] Updated weights for policy 0, policy_version 6850 (0.0007) -[2023-10-15 02:30:11,964][88300] Updated weights for policy 1, policy_version 6892 (0.0008) -[2023-10-15 02:30:12,069][88298] Updated weights for policy 0, policy_version 6860 (0.0007) -[2023-10-15 02:30:12,330][88300] Updated weights for policy 1, policy_version 6902 (0.0008) -[2023-10-15 02:30:12,435][88298] Updated weights for policy 0, policy_version 6870 (0.0007) -[2023-10-15 02:30:12,698][88300] Updated weights for policy 1, policy_version 6912 (0.0008) -[2023-10-15 02:30:12,808][88298] Updated weights for policy 0, policy_version 6880 (0.0008) -[2023-10-15 02:30:13,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 14123008. Throughput: 0: 1709.0, 1: 1711.5. Samples: 3535946. Policy #0 lag: (min: 14.0, avg: 17.3, max: 46.0) -[2023-10-15 02:30:13,535][87330] Avg episode reward: [(0, '21.020'), (1, '20.480')] -[2023-10-15 02:30:16,547][88300] Updated weights for policy 1, policy_version 6922 (0.0009) -[2023-10-15 02:30:16,694][88298] Updated weights for policy 0, policy_version 6890 (0.0007) -[2023-10-15 02:30:16,905][88300] Updated weights for policy 1, policy_version 6932 (0.0009) -[2023-10-15 02:30:17,067][88298] Updated weights for policy 0, policy_version 6900 (0.0008) -[2023-10-15 02:30:17,269][88300] Updated weights for policy 1, policy_version 6942 (0.0008) -[2023-10-15 02:30:17,437][88298] Updated weights for policy 0, policy_version 6910 (0.0009) -[2023-10-15 02:30:18,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 14188544. Throughput: 0: 1737.9, 1: 1742.3. Samples: 3548074. Policy #0 lag: (min: 28.0, avg: 53.2, max: 56.0) -[2023-10-15 02:30:18,535][87330] Avg episode reward: [(0, '21.180'), (1, '20.430')] -[2023-10-15 02:30:21,238][88300] Updated weights for policy 1, policy_version 6952 (0.0008) -[2023-10-15 02:30:21,272][88298] Updated weights for policy 0, policy_version 6920 (0.0009) -[2023-10-15 02:30:21,604][88300] Updated weights for policy 1, policy_version 6962 (0.0008) -[2023-10-15 02:30:21,634][88298] Updated weights for policy 0, policy_version 6930 (0.0007) -[2023-10-15 02:30:21,968][88300] Updated weights for policy 1, policy_version 6972 (0.0007) -[2023-10-15 02:30:22,001][88298] Updated weights for policy 0, policy_version 6940 (0.0008) -[2023-10-15 02:30:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 14254080. Throughput: 0: 1722.4, 1: 1714.8. Samples: 3567380. Policy #0 lag: (min: 28.0, avg: 53.2, max: 56.0) -[2023-10-15 02:30:23,535][87330] Avg episode reward: [(0, '21.280'), (1, '20.720')] -[2023-10-15 02:30:23,536][87905] Saving new best policy, reward=21.280! -[2023-10-15 02:30:23,536][88033] Saving new best policy, reward=20.720! -[2023-10-15 02:30:25,876][88300] Updated weights for policy 1, policy_version 6982 (0.0007) -[2023-10-15 02:30:26,006][88298] Updated weights for policy 0, policy_version 6950 (0.0008) -[2023-10-15 02:30:26,242][88300] Updated weights for policy 1, policy_version 6992 (0.0008) -[2023-10-15 02:30:26,380][88298] Updated weights for policy 0, policy_version 6960 (0.0009) -[2023-10-15 02:30:26,605][88300] Updated weights for policy 1, policy_version 7002 (0.0008) -[2023-10-15 02:30:26,753][88298] Updated weights for policy 0, policy_version 6970 (0.0008) -[2023-10-15 02:30:28,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 14319616. Throughput: 0: 1709.6, 1: 1722.5. Samples: 3588348. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:30:28,535][87330] Avg episode reward: [(0, '21.220'), (1, '20.550')] -[2023-10-15 02:30:30,452][88300] Updated weights for policy 1, policy_version 7012 (0.0007) -[2023-10-15 02:30:30,654][88298] Updated weights for policy 0, policy_version 6980 (0.0009) -[2023-10-15 02:30:30,824][88300] Updated weights for policy 1, policy_version 7022 (0.0008) -[2023-10-15 02:30:31,023][88298] Updated weights for policy 0, policy_version 6990 (0.0007) -[2023-10-15 02:30:31,193][88300] Updated weights for policy 1, policy_version 7032 (0.0009) -[2023-10-15 02:30:31,391][88298] Updated weights for policy 0, policy_version 7000 (0.0008) -[2023-10-15 02:30:33,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 14385152. Throughput: 0: 1733.5, 1: 1735.4. Samples: 3599484. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:30:33,534][87330] Avg episode reward: [(0, '21.330'), (1, '20.450')] -[2023-10-15 02:30:33,535][87905] Saving new best policy, reward=21.330! -[2023-10-15 02:30:35,062][88300] Updated weights for policy 1, policy_version 7042 (0.0008) -[2023-10-15 02:30:35,262][88298] Updated weights for policy 0, policy_version 7010 (0.0008) -[2023-10-15 02:30:35,430][88300] Updated weights for policy 1, policy_version 7052 (0.0007) -[2023-10-15 02:30:35,629][88298] Updated weights for policy 0, policy_version 7020 (0.0008) -[2023-10-15 02:30:35,798][88300] Updated weights for policy 1, policy_version 7062 (0.0008) -[2023-10-15 02:30:35,996][88298] Updated weights for policy 0, policy_version 7030 (0.0009) -[2023-10-15 02:30:36,156][88300] Updated weights for policy 1, policy_version 7072 (0.0009) -[2023-10-15 02:30:36,376][88298] Updated weights for policy 0, policy_version 7040 (0.0009) -[2023-10-15 02:30:38,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 14450688. Throughput: 0: 1709.7, 1: 1725.7. Samples: 3619554. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:30:38,534][87330] Avg episode reward: [(0, '21.310'), (1, '20.420')] -[2023-10-15 02:30:39,878][88300] Updated weights for policy 1, policy_version 7082 (0.0009) -[2023-10-15 02:30:40,237][88300] Updated weights for policy 1, policy_version 7092 (0.0008) -[2023-10-15 02:30:40,298][88298] Updated weights for policy 0, policy_version 7050 (0.0007) -[2023-10-15 02:30:40,609][88300] Updated weights for policy 1, policy_version 7102 (0.0008) -[2023-10-15 02:30:40,666][88298] Updated weights for policy 0, policy_version 7060 (0.0007) -[2023-10-15 02:30:41,036][88298] Updated weights for policy 0, policy_version 7070 (0.0009) -[2023-10-15 02:30:43,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 14516224. Throughput: 0: 1719.0, 1: 1762.2. Samples: 3641374. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:30:43,534][87330] Avg episode reward: [(0, '21.370'), (1, '20.420')] -[2023-10-15 02:30:43,546][87905] Saving new best policy, reward=21.370! -[2023-10-15 02:30:44,547][88300] Updated weights for policy 1, policy_version 7112 (0.0009) -[2023-10-15 02:30:44,916][88300] Updated weights for policy 1, policy_version 7122 (0.0009) -[2023-10-15 02:30:44,950][88298] Updated weights for policy 0, policy_version 7080 (0.0008) -[2023-10-15 02:30:45,284][88300] Updated weights for policy 1, policy_version 7132 (0.0008) -[2023-10-15 02:30:45,320][88298] Updated weights for policy 0, policy_version 7090 (0.0008) -[2023-10-15 02:30:45,696][88298] Updated weights for policy 0, policy_version 7100 (0.0008) -[2023-10-15 02:30:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 14581760. Throughput: 0: 1708.0, 1: 1737.0. Samples: 3650866. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:30:48,534][87330] Avg episode reward: [(0, '21.290'), (1, '20.130')] -[2023-10-15 02:30:49,303][88300] Updated weights for policy 1, policy_version 7142 (0.0008) -[2023-10-15 02:30:49,671][88300] Updated weights for policy 1, policy_version 7152 (0.0008) -[2023-10-15 02:30:49,686][88298] Updated weights for policy 0, policy_version 7110 (0.0007) -[2023-10-15 02:30:50,036][88300] Updated weights for policy 1, policy_version 7162 (0.0009) -[2023-10-15 02:30:50,057][88298] Updated weights for policy 0, policy_version 7120 (0.0007) -[2023-10-15 02:30:50,429][88298] Updated weights for policy 0, policy_version 7130 (0.0007) -[2023-10-15 02:30:53,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 14647296. Throughput: 0: 1701.1, 1: 1746.6. Samples: 3671868. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:30:53,535][87330] Avg episode reward: [(0, '21.250'), (1, '19.910')] -[2023-10-15 02:30:53,689][88300] Updated weights for policy 1, policy_version 7172 (0.0007) -[2023-10-15 02:30:54,052][88300] Updated weights for policy 1, policy_version 7182 (0.0009) -[2023-10-15 02:30:54,380][88298] Updated weights for policy 0, policy_version 7140 (0.0008) -[2023-10-15 02:30:54,417][88300] Updated weights for policy 1, policy_version 7192 (0.0008) -[2023-10-15 02:30:54,747][88298] Updated weights for policy 0, policy_version 7150 (0.0007) -[2023-10-15 02:30:55,119][88298] Updated weights for policy 0, policy_version 7160 (0.0007) -[2023-10-15 02:30:58,220][88300] Updated weights for policy 1, policy_version 7202 (0.0007) -[2023-10-15 02:30:58,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 14712832. Throughput: 0: 1734.3, 1: 1771.2. Samples: 3693692. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:30:58,534][87330] Avg episode reward: [(0, '21.230'), (1, '19.970')] -[2023-10-15 02:30:58,544][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000007168_7340032.pth... -[2023-10-15 02:30:58,579][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000005568_5701632.pth -[2023-10-15 02:30:58,596][88300] Updated weights for policy 1, policy_version 7212 (0.0009) -[2023-10-15 02:30:58,886][88298] Updated weights for policy 0, policy_version 7170 (0.0007) -[2023-10-15 02:30:58,968][88300] Updated weights for policy 1, policy_version 7222 (0.0007) -[2023-10-15 02:30:59,255][88298] Updated weights for policy 0, policy_version 7180 (0.0008) -[2023-10-15 02:30:59,340][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000007232_7405568.pth... -[2023-10-15 02:30:59,341][88300] Updated weights for policy 1, policy_version 7232 (0.0007) -[2023-10-15 02:30:59,377][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000005600_5734400.pth -[2023-10-15 02:30:59,625][88298] Updated weights for policy 0, policy_version 7190 (0.0011) -[2023-10-15 02:30:59,996][88298] Updated weights for policy 0, policy_version 7200 (0.0008) -[2023-10-15 02:31:03,251][88300] Updated weights for policy 1, policy_version 7242 (0.0008) -[2023-10-15 02:31:03,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 14778368. Throughput: 0: 1709.2, 1: 1741.8. Samples: 3703366. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:31:03,534][87330] Avg episode reward: [(0, '21.240'), (1, '20.250')] -[2023-10-15 02:31:03,616][88300] Updated weights for policy 1, policy_version 7252 (0.0010) -[2023-10-15 02:31:03,970][88298] Updated weights for policy 0, policy_version 7210 (0.0008) -[2023-10-15 02:31:03,986][88300] Updated weights for policy 1, policy_version 7262 (0.0007) -[2023-10-15 02:31:04,349][88298] Updated weights for policy 0, policy_version 7220 (0.0008) -[2023-10-15 02:31:04,723][88298] Updated weights for policy 0, policy_version 7230 (0.0010) -[2023-10-15 02:31:08,048][88300] Updated weights for policy 1, policy_version 7272 (0.0009) -[2023-10-15 02:31:08,429][88300] Updated weights for policy 1, policy_version 7282 (0.0008) -[2023-10-15 02:31:08,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13107.3, 300 sec: 13773.7). Total num frames: 14843904. Throughput: 0: 1727.7, 1: 1768.3. Samples: 3724700. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-15 02:31:08,534][87330] Avg episode reward: [(0, '21.140'), (1, '20.360')] -[2023-10-15 02:31:08,734][88298] Updated weights for policy 0, policy_version 7240 (0.0008) -[2023-10-15 02:31:08,805][88300] Updated weights for policy 1, policy_version 7292 (0.0008) -[2023-10-15 02:31:09,113][88298] Updated weights for policy 0, policy_version 7250 (0.0008) -[2023-10-15 02:31:09,483][88298] Updated weights for policy 0, policy_version 7260 (0.0009) -[2023-10-15 02:31:12,442][88300] Updated weights for policy 1, policy_version 7302 (0.0008) -[2023-10-15 02:31:12,802][88300] Updated weights for policy 1, policy_version 7312 (0.0009) -[2023-10-15 02:31:13,177][88300] Updated weights for policy 1, policy_version 7322 (0.0007) -[2023-10-15 02:31:13,451][88298] Updated weights for policy 0, policy_version 7270 (0.0009) -[2023-10-15 02:31:13,534][87330] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 14942208. Throughput: 0: 1738.1, 1: 1745.1. Samples: 3745094. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-15 02:31:13,534][87330] Avg episode reward: [(0, '21.180'), (1, '20.330')] -[2023-10-15 02:31:13,823][88298] Updated weights for policy 0, policy_version 7280 (0.0009) -[2023-10-15 02:31:14,196][88298] Updated weights for policy 0, policy_version 7290 (0.0008) -[2023-10-15 02:31:17,127][88300] Updated weights for policy 1, policy_version 7332 (0.0010) -[2023-10-15 02:31:17,500][88300] Updated weights for policy 1, policy_version 7342 (0.0010) -[2023-10-15 02:31:17,866][88300] Updated weights for policy 1, policy_version 7352 (0.0010) -[2023-10-15 02:31:18,134][88298] Updated weights for policy 0, policy_version 7300 (0.0009) -[2023-10-15 02:31:18,501][88298] Updated weights for policy 0, policy_version 7310 (0.0010) -[2023-10-15 02:31:18,534][87330] Fps is (10 sec: 16383.7, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 15007744. Throughput: 0: 1713.1, 1: 1757.5. Samples: 3755662. Policy #0 lag: (min: 1.0, avg: 9.8, max: 33.0) -[2023-10-15 02:31:18,535][87330] Avg episode reward: [(0, '21.340'), (1, '20.410')] -[2023-10-15 02:31:18,878][88298] Updated weights for policy 0, policy_version 7320 (0.0009) -[2023-10-15 02:31:21,833][88300] Updated weights for policy 1, policy_version 7362 (0.0008) -[2023-10-15 02:31:22,192][88300] Updated weights for policy 1, policy_version 7372 (0.0008) -[2023-10-15 02:31:22,565][88300] Updated weights for policy 1, policy_version 7382 (0.0010) -[2023-10-15 02:31:22,703][88298] Updated weights for policy 0, policy_version 7330 (0.0008) -[2023-10-15 02:31:22,931][88300] Updated weights for policy 1, policy_version 7392 (0.0007) -[2023-10-15 02:31:23,070][88298] Updated weights for policy 0, policy_version 7340 (0.0007) -[2023-10-15 02:31:23,448][88298] Updated weights for policy 0, policy_version 7350 (0.0007) -[2023-10-15 02:31:23,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 15073280. Throughput: 0: 1745.4, 1: 1751.8. Samples: 3776930. Policy #0 lag: (min: 1.0, avg: 9.8, max: 33.0) -[2023-10-15 02:31:23,534][87330] Avg episode reward: [(0, '21.290'), (1, '20.510')] -[2023-10-15 02:31:23,818][88298] Updated weights for policy 0, policy_version 7360 (0.0007) -[2023-10-15 02:31:26,858][88300] Updated weights for policy 1, policy_version 7402 (0.0011) -[2023-10-15 02:31:27,228][88300] Updated weights for policy 1, policy_version 7412 (0.0011) -[2023-10-15 02:31:27,604][88300] Updated weights for policy 1, policy_version 7422 (0.0009) -[2023-10-15 02:31:27,879][88298] Updated weights for policy 0, policy_version 7370 (0.0007) -[2023-10-15 02:31:28,256][88298] Updated weights for policy 0, policy_version 7380 (0.0007) -[2023-10-15 02:31:28,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 15138816. Throughput: 0: 1736.8, 1: 1726.8. Samples: 3797236. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-15 02:31:28,534][87330] Avg episode reward: [(0, '21.270'), (1, '20.470')] -[2023-10-15 02:31:28,632][88298] Updated weights for policy 0, policy_version 7390 (0.0008) -[2023-10-15 02:31:31,561][88300] Updated weights for policy 1, policy_version 7432 (0.0007) -[2023-10-15 02:31:31,930][88300] Updated weights for policy 1, policy_version 7442 (0.0007) -[2023-10-15 02:31:32,298][88300] Updated weights for policy 1, policy_version 7452 (0.0007) -[2023-10-15 02:31:32,547][88298] Updated weights for policy 0, policy_version 7400 (0.0008) -[2023-10-15 02:31:32,914][88298] Updated weights for policy 0, policy_version 7410 (0.0011) -[2023-10-15 02:31:33,284][88298] Updated weights for policy 0, policy_version 7420 (0.0010) -[2023-10-15 02:31:33,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 15237120. Throughput: 0: 1740.4, 1: 1758.7. Samples: 3808324. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:31:33,534][87330] Avg episode reward: [(0, '21.250'), (1, '20.380')] -[2023-10-15 02:31:36,092][88300] Updated weights for policy 1, policy_version 7462 (0.0010) -[2023-10-15 02:31:36,458][88300] Updated weights for policy 1, policy_version 7472 (0.0008) -[2023-10-15 02:31:36,822][88300] Updated weights for policy 1, policy_version 7482 (0.0008) -[2023-10-15 02:31:37,405][88298] Updated weights for policy 0, policy_version 7430 (0.0008) -[2023-10-15 02:31:37,775][88298] Updated weights for policy 0, policy_version 7440 (0.0007) -[2023-10-15 02:31:38,151][88298] Updated weights for policy 0, policy_version 7450 (0.0010) -[2023-10-15 02:31:38,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 15302656. Throughput: 0: 1745.7, 1: 1733.8. Samples: 3828446. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:31:38,534][87330] Avg episode reward: [(0, '21.380'), (1, '20.330')] -[2023-10-15 02:31:38,535][87905] Saving new best policy, reward=21.380! -[2023-10-15 02:31:40,816][88300] Updated weights for policy 1, policy_version 7492 (0.0008) -[2023-10-15 02:31:41,183][88300] Updated weights for policy 1, policy_version 7502 (0.0009) -[2023-10-15 02:31:41,560][88300] Updated weights for policy 1, policy_version 7512 (0.0009) -[2023-10-15 02:31:41,805][88298] Updated weights for policy 0, policy_version 7460 (0.0008) -[2023-10-15 02:31:42,176][88298] Updated weights for policy 0, policy_version 7470 (0.0009) -[2023-10-15 02:31:42,568][88298] Updated weights for policy 0, policy_version 7480 (0.0011) -[2023-10-15 02:31:43,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 15368192. Throughput: 0: 1716.9, 1: 1729.8. Samples: 3848794. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-15 02:31:43,534][87330] Avg episode reward: [(0, '21.330'), (1, '20.400')] -[2023-10-15 02:31:45,487][88300] Updated weights for policy 1, policy_version 7522 (0.0008) -[2023-10-15 02:31:45,863][88300] Updated weights for policy 1, policy_version 7532 (0.0007) -[2023-10-15 02:31:46,229][88300] Updated weights for policy 1, policy_version 7542 (0.0009) -[2023-10-15 02:31:46,480][88298] Updated weights for policy 0, policy_version 7490 (0.0009) -[2023-10-15 02:31:46,599][88300] Updated weights for policy 1, policy_version 7552 (0.0008) -[2023-10-15 02:31:46,848][88298] Updated weights for policy 0, policy_version 7500 (0.0007) -[2023-10-15 02:31:47,221][88298] Updated weights for policy 0, policy_version 7510 (0.0007) -[2023-10-15 02:31:47,596][88298] Updated weights for policy 0, policy_version 7520 (0.0007) -[2023-10-15 02:31:48,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 15433728. Throughput: 0: 1742.6, 1: 1737.8. Samples: 3859982. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-15 02:31:48,534][87330] Avg episode reward: [(0, '21.380'), (1, '20.460')] -[2023-10-15 02:31:50,487][88300] Updated weights for policy 1, policy_version 7562 (0.0009) -[2023-10-15 02:31:50,862][88300] Updated weights for policy 1, policy_version 7572 (0.0008) -[2023-10-15 02:31:51,225][88300] Updated weights for policy 1, policy_version 7582 (0.0007) -[2023-10-15 02:31:51,354][88298] Updated weights for policy 0, policy_version 7530 (0.0009) -[2023-10-15 02:31:51,727][88298] Updated weights for policy 0, policy_version 7540 (0.0008) -[2023-10-15 02:31:52,094][88298] Updated weights for policy 0, policy_version 7550 (0.0008) -[2023-10-15 02:31:53,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 15499264. Throughput: 0: 1724.0, 1: 1728.7. Samples: 3880070. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:31:53,535][87330] Avg episode reward: [(0, '21.380'), (1, '20.760')] -[2023-10-15 02:31:53,536][88033] Saving new best policy, reward=20.760! -[2023-10-15 02:31:55,140][88300] Updated weights for policy 1, policy_version 7592 (0.0010) -[2023-10-15 02:31:55,507][88300] Updated weights for policy 1, policy_version 7602 (0.0009) -[2023-10-15 02:31:55,877][88300] Updated weights for policy 1, policy_version 7612 (0.0008) -[2023-10-15 02:31:56,046][88298] Updated weights for policy 0, policy_version 7560 (0.0008) -[2023-10-15 02:31:56,419][88298] Updated weights for policy 0, policy_version 7570 (0.0010) -[2023-10-15 02:31:56,785][88298] Updated weights for policy 0, policy_version 7580 (0.0009) -[2023-10-15 02:31:58,534][87330] Fps is (10 sec: 13106.6, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 15564800. Throughput: 0: 1719.5, 1: 1756.2. Samples: 3901498. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:31:58,535][87330] Avg episode reward: [(0, '21.490'), (1, '20.980')] -[2023-10-15 02:31:58,544][87905] Saving new best policy, reward=21.490! -[2023-10-15 02:31:58,545][88033] Saving new best policy, reward=20.980! -[2023-10-15 02:31:59,576][88300] Updated weights for policy 1, policy_version 7622 (0.0009) -[2023-10-15 02:31:59,944][88300] Updated weights for policy 1, policy_version 7632 (0.0009) -[2023-10-15 02:32:00,308][88300] Updated weights for policy 1, policy_version 7642 (0.0009) -[2023-10-15 02:32:00,621][88298] Updated weights for policy 0, policy_version 7590 (0.0007) -[2023-10-15 02:32:00,984][88298] Updated weights for policy 0, policy_version 7600 (0.0007) -[2023-10-15 02:32:01,350][88298] Updated weights for policy 0, policy_version 7610 (0.0008) -[2023-10-15 02:32:03,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 15630336. Throughput: 0: 1747.3, 1: 1730.8. Samples: 3912180. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-15 02:32:03,535][87330] Avg episode reward: [(0, '21.480'), (1, '20.940')] -[2023-10-15 02:32:04,367][88300] Updated weights for policy 1, policy_version 7652 (0.0008) -[2023-10-15 02:32:04,738][88300] Updated weights for policy 1, policy_version 7662 (0.0010) -[2023-10-15 02:32:05,107][88300] Updated weights for policy 1, policy_version 7672 (0.0007) -[2023-10-15 02:32:05,296][88298] Updated weights for policy 0, policy_version 7620 (0.0008) -[2023-10-15 02:32:05,673][88298] Updated weights for policy 0, policy_version 7630 (0.0008) -[2023-10-15 02:32:06,047][88298] Updated weights for policy 0, policy_version 7640 (0.0008) -[2023-10-15 02:32:08,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 15695872. Throughput: 0: 1718.7, 1: 1747.3. Samples: 3932898. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-15 02:32:08,535][87330] Avg episode reward: [(0, '21.590'), (1, '20.940')] -[2023-10-15 02:32:08,536][87905] Saving new best policy, reward=21.590! -[2023-10-15 02:32:08,702][88300] Updated weights for policy 1, policy_version 7682 (0.0008) -[2023-10-15 02:32:09,071][88300] Updated weights for policy 1, policy_version 7692 (0.0008) -[2023-10-15 02:32:09,448][88300] Updated weights for policy 1, policy_version 7702 (0.0009) -[2023-10-15 02:32:09,813][88300] Updated weights for policy 1, policy_version 7712 (0.0010) -[2023-10-15 02:32:10,049][88298] Updated weights for policy 0, policy_version 7650 (0.0011) -[2023-10-15 02:32:10,424][88298] Updated weights for policy 0, policy_version 7660 (0.0008) -[2023-10-15 02:32:10,791][88298] Updated weights for policy 0, policy_version 7670 (0.0008) -[2023-10-15 02:32:11,168][88298] Updated weights for policy 0, policy_version 7680 (0.0009) -[2023-10-15 02:32:13,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 15761408. Throughput: 0: 1724.0, 1: 1768.0. Samples: 3954376. Policy #0 lag: (min: 25.0, avg: 30.6, max: 57.0) -[2023-10-15 02:32:13,534][87330] Avg episode reward: [(0, '21.570'), (1, '20.820')] -[2023-10-15 02:32:13,851][88300] Updated weights for policy 1, policy_version 7722 (0.0010) -[2023-10-15 02:32:14,225][88300] Updated weights for policy 1, policy_version 7732 (0.0010) -[2023-10-15 02:32:14,594][88300] Updated weights for policy 1, policy_version 7742 (0.0008) -[2023-10-15 02:32:14,929][88298] Updated weights for policy 0, policy_version 7690 (0.0010) -[2023-10-15 02:32:15,304][88298] Updated weights for policy 0, policy_version 7700 (0.0007) -[2023-10-15 02:32:15,677][88298] Updated weights for policy 0, policy_version 7710 (0.0008) -[2023-10-15 02:32:18,518][88300] Updated weights for policy 1, policy_version 7752 (0.0010) -[2023-10-15 02:32:18,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 15826944. Throughput: 0: 1722.1, 1: 1732.0. Samples: 3963758. Policy #0 lag: (min: 25.0, avg: 30.6, max: 57.0) -[2023-10-15 02:32:18,534][87330] Avg episode reward: [(0, '21.550'), (1, '20.840')] -[2023-10-15 02:32:18,887][88300] Updated weights for policy 1, policy_version 7762 (0.0007) -[2023-10-15 02:32:19,255][88300] Updated weights for policy 1, policy_version 7772 (0.0007) -[2023-10-15 02:32:19,650][88298] Updated weights for policy 0, policy_version 7720 (0.0009) -[2023-10-15 02:32:20,029][88298] Updated weights for policy 0, policy_version 7730 (0.0010) -[2023-10-15 02:32:20,407][88298] Updated weights for policy 0, policy_version 7740 (0.0008) -[2023-10-15 02:32:23,096][88300] Updated weights for policy 1, policy_version 7782 (0.0007) -[2023-10-15 02:32:23,464][88300] Updated weights for policy 1, policy_version 7792 (0.0009) -[2023-10-15 02:32:23,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 15892480. Throughput: 0: 1719.7, 1: 1760.4. Samples: 3985048. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:32:23,534][87330] Avg episode reward: [(0, '21.580'), (1, '20.880')] -[2023-10-15 02:32:23,828][88300] Updated weights for policy 1, policy_version 7802 (0.0008) -[2023-10-15 02:32:24,449][88298] Updated weights for policy 0, policy_version 7750 (0.0009) -[2023-10-15 02:32:24,822][88298] Updated weights for policy 0, policy_version 7760 (0.0007) -[2023-10-15 02:32:25,199][88298] Updated weights for policy 0, policy_version 7770 (0.0007) -[2023-10-15 02:32:27,770][88300] Updated weights for policy 1, policy_version 7812 (0.0008) -[2023-10-15 02:32:28,131][88300] Updated weights for policy 1, policy_version 7822 (0.0008) -[2023-10-15 02:32:28,490][88300] Updated weights for policy 1, policy_version 7832 (0.0009) -[2023-10-15 02:32:28,533][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 15958016. Throughput: 0: 1747.9, 1: 1749.2. Samples: 4006166. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:32:28,534][87330] Avg episode reward: [(0, '21.620'), (1, '20.670')] -[2023-10-15 02:32:28,541][87905] Saving new best policy, reward=21.620! -[2023-10-15 02:32:29,044][88298] Updated weights for policy 0, policy_version 7780 (0.0008) -[2023-10-15 02:32:29,429][88298] Updated weights for policy 0, policy_version 7790 (0.0010) -[2023-10-15 02:32:29,805][88298] Updated weights for policy 0, policy_version 7800 (0.0011) -[2023-10-15 02:32:32,380][88300] Updated weights for policy 1, policy_version 7842 (0.0007) -[2023-10-15 02:32:32,756][88300] Updated weights for policy 1, policy_version 7852 (0.0009) -[2023-10-15 02:32:33,127][88300] Updated weights for policy 1, policy_version 7862 (0.0007) -[2023-10-15 02:32:33,490][88300] Updated weights for policy 1, policy_version 7872 (0.0008) -[2023-10-15 02:32:33,534][87330] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 16056320. Throughput: 0: 1717.2, 1: 1755.4. Samples: 4016250. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:32:33,534][87330] Avg episode reward: [(0, '21.630'), (1, '20.490')] -[2023-10-15 02:32:33,619][88298] Updated weights for policy 0, policy_version 7810 (0.0010) -[2023-10-15 02:32:33,990][88298] Updated weights for policy 0, policy_version 7820 (0.0008) -[2023-10-15 02:32:34,364][88298] Updated weights for policy 0, policy_version 7830 (0.0008) -[2023-10-15 02:32:34,726][87905] Saving new best policy, reward=21.630! -[2023-10-15 02:32:34,727][88298] Updated weights for policy 0, policy_version 7840 (0.0008) -[2023-10-15 02:32:37,415][88300] Updated weights for policy 1, policy_version 7882 (0.0010) -[2023-10-15 02:32:37,787][88300] Updated weights for policy 1, policy_version 7892 (0.0008) -[2023-10-15 02:32:38,160][88300] Updated weights for policy 1, policy_version 7902 (0.0007) -[2023-10-15 02:32:38,534][87330] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 16121856. Throughput: 0: 1735.3, 1: 1758.3. Samples: 4037282. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:32:38,534][87330] Avg episode reward: [(0, '21.660'), (1, '20.820')] -[2023-10-15 02:32:38,800][88298] Updated weights for policy 0, policy_version 7850 (0.0008) -[2023-10-15 02:32:39,171][88298] Updated weights for policy 0, policy_version 7860 (0.0008) -[2023-10-15 02:32:39,549][88298] Updated weights for policy 0, policy_version 7870 (0.0008) -[2023-10-15 02:32:39,617][87905] Saving new best policy, reward=21.660! -[2023-10-15 02:32:42,102][88300] Updated weights for policy 1, policy_version 7912 (0.0007) -[2023-10-15 02:32:42,476][88300] Updated weights for policy 1, policy_version 7922 (0.0007) -[2023-10-15 02:32:42,842][88300] Updated weights for policy 1, policy_version 7932 (0.0007) -[2023-10-15 02:32:43,394][88298] Updated weights for policy 0, policy_version 7880 (0.0008) -[2023-10-15 02:32:43,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 16187392. Throughput: 0: 1746.7, 1: 1721.6. Samples: 4057568. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:32:43,535][87330] Avg episode reward: [(0, '21.700'), (1, '20.830')] -[2023-10-15 02:32:43,766][88298] Updated weights for policy 0, policy_version 7890 (0.0007) -[2023-10-15 02:32:44,133][88298] Updated weights for policy 0, policy_version 7900 (0.0007) -[2023-10-15 02:32:44,280][87905] Saving new best policy, reward=21.700! -[2023-10-15 02:32:46,781][88300] Updated weights for policy 1, policy_version 7942 (0.0009) -[2023-10-15 02:32:47,155][88300] Updated weights for policy 1, policy_version 7952 (0.0010) -[2023-10-15 02:32:47,523][88300] Updated weights for policy 1, policy_version 7962 (0.0008) -[2023-10-15 02:32:48,181][88298] Updated weights for policy 0, policy_version 7910 (0.0009) -[2023-10-15 02:32:48,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 16252928. Throughput: 0: 1717.8, 1: 1750.3. Samples: 4068244. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:32:48,534][87330] Avg episode reward: [(0, '21.770'), (1, '20.980')] -[2023-10-15 02:32:48,552][88298] Updated weights for policy 0, policy_version 7920 (0.0010) -[2023-10-15 02:32:48,922][88298] Updated weights for policy 0, policy_version 7930 (0.0010) -[2023-10-15 02:32:49,152][87905] Saving new best policy, reward=21.770! -[2023-10-15 02:32:51,544][88300] Updated weights for policy 1, policy_version 7972 (0.0009) -[2023-10-15 02:32:51,908][88300] Updated weights for policy 1, policy_version 7982 (0.0010) -[2023-10-15 02:32:52,274][88300] Updated weights for policy 1, policy_version 7992 (0.0008) -[2023-10-15 02:32:53,075][88298] Updated weights for policy 0, policy_version 7940 (0.0008) -[2023-10-15 02:32:53,450][88298] Updated weights for policy 0, policy_version 7950 (0.0008) -[2023-10-15 02:32:53,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 16318464. Throughput: 0: 1738.4, 1: 1726.6. Samples: 4088820. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-15 02:32:53,534][87330] Avg episode reward: [(0, '21.640'), (1, '20.990')] -[2023-10-15 02:32:53,535][88033] Saving new best policy, reward=20.990! -[2023-10-15 02:32:53,823][88298] Updated weights for policy 0, policy_version 7960 (0.0008) -[2023-10-15 02:32:56,114][88300] Updated weights for policy 1, policy_version 8002 (0.0007) -[2023-10-15 02:32:56,476][88300] Updated weights for policy 1, policy_version 8012 (0.0007) -[2023-10-15 02:32:56,846][88300] Updated weights for policy 1, policy_version 8022 (0.0008) -[2023-10-15 02:32:57,212][88300] Updated weights for policy 1, policy_version 8032 (0.0009) -[2023-10-15 02:32:57,670][88298] Updated weights for policy 0, policy_version 7970 (0.0008) -[2023-10-15 02:32:58,042][88298] Updated weights for policy 0, policy_version 7980 (0.0007) -[2023-10-15 02:32:58,414][88298] Updated weights for policy 0, policy_version 7990 (0.0009) -[2023-10-15 02:32:58,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 16384000. Throughput: 0: 1733.7, 1: 1718.2. Samples: 4109714. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-15 02:32:58,535][87330] Avg episode reward: [(0, '21.610'), (1, '21.010')] -[2023-10-15 02:32:58,543][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000008032_8224768.pth... -[2023-10-15 02:32:58,578][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000006400_6553600.pth -[2023-10-15 02:32:58,581][88033] Saving new best policy, reward=21.010! -[2023-10-15 02:32:58,619][88033] Saving a milestone ./train_atari/atari_seaquest_APPO/checkpoint_p1/milestones/checkpoint_000008032_8224768.pth -[2023-10-15 02:32:58,776][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000008000_8192000.pth... -[2023-10-15 02:32:58,779][88298] Updated weights for policy 0, policy_version 8000 (0.0007) -[2023-10-15 02:32:58,816][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000006368_6520832.pth -[2023-10-15 02:32:58,820][87905] Saving a milestone ./train_atari/atari_seaquest_APPO/checkpoint_p0/milestones/checkpoint_000008000_8192000.pth -[2023-10-15 02:33:01,068][88300] Updated weights for policy 1, policy_version 8042 (0.0010) -[2023-10-15 02:33:01,444][88300] Updated weights for policy 1, policy_version 8052 (0.0009) -[2023-10-15 02:33:01,812][88300] Updated weights for policy 1, policy_version 8062 (0.0007) -[2023-10-15 02:33:02,692][88298] Updated weights for policy 0, policy_version 8010 (0.0008) -[2023-10-15 02:33:03,055][88298] Updated weights for policy 0, policy_version 8020 (0.0008) -[2023-10-15 02:33:03,434][88298] Updated weights for policy 0, policy_version 8030 (0.0010) -[2023-10-15 02:33:03,534][87330] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 16482304. Throughput: 0: 1733.7, 1: 1743.1. Samples: 4120214. Policy #0 lag: (min: 1.0, avg: 11.3, max: 33.0) -[2023-10-15 02:33:03,535][87330] Avg episode reward: [(0, '21.520'), (1, '21.210')] -[2023-10-15 02:33:03,537][88033] Saving new best policy, reward=21.210! -[2023-10-15 02:33:05,639][88300] Updated weights for policy 1, policy_version 8072 (0.0009) -[2023-10-15 02:33:06,006][88300] Updated weights for policy 1, policy_version 8082 (0.0007) -[2023-10-15 02:33:06,368][88300] Updated weights for policy 1, policy_version 8092 (0.0007) -[2023-10-15 02:33:07,286][88298] Updated weights for policy 0, policy_version 8040 (0.0009) -[2023-10-15 02:33:07,650][88298] Updated weights for policy 0, policy_version 8050 (0.0008) -[2023-10-15 02:33:08,031][88298] Updated weights for policy 0, policy_version 8060 (0.0009) -[2023-10-15 02:33:08,534][87330] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 16547840. Throughput: 0: 1741.0, 1: 1726.4. Samples: 4141078. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-15 02:33:08,534][87330] Avg episode reward: [(0, '21.500'), (1, '21.290')] -[2023-10-15 02:33:08,535][88033] Saving new best policy, reward=21.290! -[2023-10-15 02:33:10,289][88300] Updated weights for policy 1, policy_version 8102 (0.0008) -[2023-10-15 02:33:10,653][88300] Updated weights for policy 1, policy_version 8112 (0.0009) -[2023-10-15 02:33:11,022][88300] Updated weights for policy 1, policy_version 8122 (0.0009) -[2023-10-15 02:33:12,098][88298] Updated weights for policy 0, policy_version 8070 (0.0009) -[2023-10-15 02:33:12,487][88298] Updated weights for policy 0, policy_version 8080 (0.0007) -[2023-10-15 02:33:12,867][88298] Updated weights for policy 0, policy_version 8090 (0.0008) -[2023-10-15 02:33:13,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 16613376. Throughput: 0: 1713.5, 1: 1740.0. Samples: 4161572. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-15 02:33:13,534][87330] Avg episode reward: [(0, '21.540'), (1, '21.310')] -[2023-10-15 02:33:13,543][88033] Saving new best policy, reward=21.310! -[2023-10-15 02:33:14,805][88300] Updated weights for policy 1, policy_version 8132 (0.0009) -[2023-10-15 02:33:15,181][88300] Updated weights for policy 1, policy_version 8142 (0.0009) -[2023-10-15 02:33:15,552][88300] Updated weights for policy 1, policy_version 8152 (0.0008) -[2023-10-15 02:33:16,685][88298] Updated weights for policy 0, policy_version 8100 (0.0008) -[2023-10-15 02:33:17,061][88298] Updated weights for policy 0, policy_version 8110 (0.0007) -[2023-10-15 02:33:17,432][88298] Updated weights for policy 0, policy_version 8120 (0.0007) -[2023-10-15 02:33:18,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 16678912. Throughput: 0: 1736.8, 1: 1722.7. Samples: 4171928. Policy #0 lag: (min: 2.0, avg: 3.6, max: 27.0) -[2023-10-15 02:33:18,534][87330] Avg episode reward: [(0, '21.510'), (1, '21.250')] -[2023-10-15 02:33:19,631][88300] Updated weights for policy 1, policy_version 8162 (0.0008) -[2023-10-15 02:33:20,005][88300] Updated weights for policy 1, policy_version 8172 (0.0009) -[2023-10-15 02:33:20,378][88300] Updated weights for policy 1, policy_version 8182 (0.0007) -[2023-10-15 02:33:20,739][88300] Updated weights for policy 1, policy_version 8192 (0.0007) -[2023-10-15 02:33:21,253][88298] Updated weights for policy 0, policy_version 8130 (0.0009) -[2023-10-15 02:33:21,628][88298] Updated weights for policy 0, policy_version 8140 (0.0007) -[2023-10-15 02:33:22,001][88298] Updated weights for policy 0, policy_version 8150 (0.0008) -[2023-10-15 02:33:22,373][88298] Updated weights for policy 0, policy_version 8160 (0.0009) -[2023-10-15 02:33:23,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13884.8). Total num frames: 16744448. Throughput: 0: 1722.6, 1: 1730.1. Samples: 4192652. Policy #0 lag: (min: 2.0, avg: 3.6, max: 27.0) -[2023-10-15 02:33:23,535][87330] Avg episode reward: [(0, '21.450'), (1, '21.020')] -[2023-10-15 02:33:24,493][88300] Updated weights for policy 1, policy_version 8202 (0.0011) -[2023-10-15 02:33:24,863][88300] Updated weights for policy 1, policy_version 8212 (0.0011) -[2023-10-15 02:33:25,228][88300] Updated weights for policy 1, policy_version 8222 (0.0011) -[2023-10-15 02:33:26,366][88298] Updated weights for policy 0, policy_version 8170 (0.0008) -[2023-10-15 02:33:26,731][88298] Updated weights for policy 0, policy_version 8180 (0.0008) -[2023-10-15 02:33:27,102][88298] Updated weights for policy 0, policy_version 8190 (0.0008) -[2023-10-15 02:33:28,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 16809984. Throughput: 0: 1705.4, 1: 1763.4. Samples: 4213664. Policy #0 lag: (min: 15.0, avg: 22.6, max: 47.0) -[2023-10-15 02:33:28,534][87330] Avg episode reward: [(0, '21.610'), (1, '21.000')] -[2023-10-15 02:33:29,156][88300] Updated weights for policy 1, policy_version 8232 (0.0008) -[2023-10-15 02:33:29,527][88300] Updated weights for policy 1, policy_version 8242 (0.0008) -[2023-10-15 02:33:29,891][88300] Updated weights for policy 1, policy_version 8252 (0.0007) -[2023-10-15 02:33:31,084][88298] Updated weights for policy 0, policy_version 8200 (0.0007) -[2023-10-15 02:33:31,459][88298] Updated weights for policy 0, policy_version 8210 (0.0007) -[2023-10-15 02:33:31,828][88298] Updated weights for policy 0, policy_version 8220 (0.0009) -[2023-10-15 02:33:33,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 16875520. Throughput: 0: 1735.8, 1: 1733.7. Samples: 4224372. Policy #0 lag: (min: 15.0, avg: 22.6, max: 47.0) -[2023-10-15 02:33:33,534][87330] Avg episode reward: [(0, '21.590'), (1, '21.050')] -[2023-10-15 02:33:33,796][88300] Updated weights for policy 1, policy_version 8262 (0.0009) -[2023-10-15 02:33:34,163][88300] Updated weights for policy 1, policy_version 8272 (0.0010) -[2023-10-15 02:33:34,537][88300] Updated weights for policy 1, policy_version 8282 (0.0009) -[2023-10-15 02:33:35,840][88298] Updated weights for policy 0, policy_version 8230 (0.0008) -[2023-10-15 02:33:36,218][88298] Updated weights for policy 0, policy_version 8240 (0.0008) -[2023-10-15 02:33:36,588][88298] Updated weights for policy 0, policy_version 8250 (0.0008) -[2023-10-15 02:33:38,279][88300] Updated weights for policy 1, policy_version 8292 (0.0008) -[2023-10-15 02:33:38,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 16941056. Throughput: 0: 1709.0, 1: 1760.1. Samples: 4244930. Policy #0 lag: (min: 30.0, avg: 36.5, max: 62.0) -[2023-10-15 02:33:38,534][87330] Avg episode reward: [(0, '21.660'), (1, '21.060')] -[2023-10-15 02:33:38,638][88300] Updated weights for policy 1, policy_version 8302 (0.0007) -[2023-10-15 02:33:39,000][88300] Updated weights for policy 1, policy_version 8312 (0.0008) -[2023-10-15 02:33:40,468][88298] Updated weights for policy 0, policy_version 8260 (0.0009) -[2023-10-15 02:33:40,828][88298] Updated weights for policy 0, policy_version 8270 (0.0008) -[2023-10-15 02:33:41,201][88298] Updated weights for policy 0, policy_version 8280 (0.0008) -[2023-10-15 02:33:42,901][88300] Updated weights for policy 1, policy_version 8322 (0.0008) -[2023-10-15 02:33:43,278][88300] Updated weights for policy 1, policy_version 8332 (0.0008) -[2023-10-15 02:33:43,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 17006592. Throughput: 0: 1715.6, 1: 1759.9. Samples: 4266114. Policy #0 lag: (min: 30.0, avg: 36.5, max: 62.0) -[2023-10-15 02:33:43,534][87330] Avg episode reward: [(0, '21.680'), (1, '21.010')] -[2023-10-15 02:33:43,654][88300] Updated weights for policy 1, policy_version 8342 (0.0008) -[2023-10-15 02:33:44,025][88300] Updated weights for policy 1, policy_version 8352 (0.0009) -[2023-10-15 02:33:44,990][88298] Updated weights for policy 0, policy_version 8290 (0.0009) -[2023-10-15 02:33:45,370][88298] Updated weights for policy 0, policy_version 8300 (0.0010) -[2023-10-15 02:33:45,745][88298] Updated weights for policy 0, policy_version 8310 (0.0009) -[2023-10-15 02:33:46,119][88298] Updated weights for policy 0, policy_version 8320 (0.0009) -[2023-10-15 02:33:48,051][88300] Updated weights for policy 1, policy_version 8362 (0.0008) -[2023-10-15 02:33:48,424][88300] Updated weights for policy 1, policy_version 8372 (0.0008) -[2023-10-15 02:33:48,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 17072128. Throughput: 0: 1723.6, 1: 1751.6. Samples: 4276596. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:33:48,535][87330] Avg episode reward: [(0, '21.740'), (1, '21.120')] -[2023-10-15 02:33:48,793][88300] Updated weights for policy 1, policy_version 8382 (0.0007) -[2023-10-15 02:33:49,932][88298] Updated weights for policy 0, policy_version 8330 (0.0007) -[2023-10-15 02:33:50,299][88298] Updated weights for policy 0, policy_version 8340 (0.0009) -[2023-10-15 02:33:50,676][88298] Updated weights for policy 0, policy_version 8350 (0.0008) -[2023-10-15 02:33:52,505][88300] Updated weights for policy 1, policy_version 8392 (0.0008) -[2023-10-15 02:33:52,864][88300] Updated weights for policy 1, policy_version 8402 (0.0007) -[2023-10-15 02:33:53,229][88300] Updated weights for policy 1, policy_version 8412 (0.0008) -[2023-10-15 02:33:53,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 17170432. Throughput: 0: 1709.8, 1: 1765.0. Samples: 4297444. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:33:53,534][87330] Avg episode reward: [(0, '21.650'), (1, '21.040')] -[2023-10-15 02:33:54,691][88298] Updated weights for policy 0, policy_version 8360 (0.0009) -[2023-10-15 02:33:55,066][88298] Updated weights for policy 0, policy_version 8370 (0.0009) -[2023-10-15 02:33:55,442][88298] Updated weights for policy 0, policy_version 8380 (0.0008) -[2023-10-15 02:33:57,172][88300] Updated weights for policy 1, policy_version 8422 (0.0009) -[2023-10-15 02:33:57,540][88300] Updated weights for policy 1, policy_version 8432 (0.0008) -[2023-10-15 02:33:57,910][88300] Updated weights for policy 1, policy_version 8442 (0.0009) -[2023-10-15 02:33:58,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 17235968. Throughput: 0: 1737.7, 1: 1731.5. Samples: 4317686. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-10-15 02:33:58,534][87330] Avg episode reward: [(0, '21.560'), (1, '21.250')] -[2023-10-15 02:33:59,420][88298] Updated weights for policy 0, policy_version 8390 (0.0008) -[2023-10-15 02:33:59,791][88298] Updated weights for policy 0, policy_version 8400 (0.0009) -[2023-10-15 02:34:00,164][88298] Updated weights for policy 0, policy_version 8410 (0.0007) -[2023-10-15 02:34:01,607][88300] Updated weights for policy 1, policy_version 8452 (0.0008) -[2023-10-15 02:34:01,971][88300] Updated weights for policy 1, policy_version 8462 (0.0007) -[2023-10-15 02:34:02,345][88300] Updated weights for policy 1, policy_version 8472 (0.0007) -[2023-10-15 02:34:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 17301504. Throughput: 0: 1714.7, 1: 1764.9. Samples: 4328510. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-10-15 02:34:03,534][87330] Avg episode reward: [(0, '21.740'), (1, '21.200')] -[2023-10-15 02:34:04,130][88298] Updated weights for policy 0, policy_version 8420 (0.0010) -[2023-10-15 02:34:04,506][88298] Updated weights for policy 0, policy_version 8430 (0.0011) -[2023-10-15 02:34:04,887][88298] Updated weights for policy 0, policy_version 8440 (0.0007) -[2023-10-15 02:34:06,249][88300] Updated weights for policy 1, policy_version 8482 (0.0008) -[2023-10-15 02:34:06,618][88300] Updated weights for policy 1, policy_version 8492 (0.0008) -[2023-10-15 02:34:06,984][88300] Updated weights for policy 1, policy_version 8502 (0.0009) -[2023-10-15 02:34:07,357][88300] Updated weights for policy 1, policy_version 8512 (0.0008) -[2023-10-15 02:34:08,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 17367040. Throughput: 0: 1729.0, 1: 1743.5. Samples: 4348912. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-15 02:34:08,535][87330] Avg episode reward: [(0, '21.710'), (1, '20.960')] -[2023-10-15 02:34:08,781][88298] Updated weights for policy 0, policy_version 8450 (0.0008) -[2023-10-15 02:34:09,158][88298] Updated weights for policy 0, policy_version 8460 (0.0009) -[2023-10-15 02:34:09,519][88298] Updated weights for policy 0, policy_version 8470 (0.0007) -[2023-10-15 02:34:09,891][88298] Updated weights for policy 0, policy_version 8480 (0.0009) -[2023-10-15 02:34:11,329][88300] Updated weights for policy 1, policy_version 8522 (0.0008) -[2023-10-15 02:34:11,699][88300] Updated weights for policy 1, policy_version 8532 (0.0007) -[2023-10-15 02:34:12,062][88300] Updated weights for policy 1, policy_version 8542 (0.0007) -[2023-10-15 02:34:13,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 17432576. Throughput: 0: 1746.5, 1: 1736.8. Samples: 4370410. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-15 02:34:13,535][87330] Avg episode reward: [(0, '21.680'), (1, '21.170')] -[2023-10-15 02:34:13,681][88298] Updated weights for policy 0, policy_version 8490 (0.0008) -[2023-10-15 02:34:14,050][88298] Updated weights for policy 0, policy_version 8500 (0.0007) -[2023-10-15 02:34:14,417][88298] Updated weights for policy 0, policy_version 8510 (0.0011) -[2023-10-15 02:34:15,870][88300] Updated weights for policy 1, policy_version 8552 (0.0007) -[2023-10-15 02:34:16,235][88300] Updated weights for policy 1, policy_version 8562 (0.0010) -[2023-10-15 02:34:16,592][88300] Updated weights for policy 1, policy_version 8572 (0.0008) -[2023-10-15 02:34:18,369][88298] Updated weights for policy 0, policy_version 8520 (0.0007) -[2023-10-15 02:34:18,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 17498112. Throughput: 0: 1717.0, 1: 1753.1. Samples: 4380524. Policy #0 lag: (min: 26.0, avg: 28.0, max: 54.0) -[2023-10-15 02:34:18,534][87330] Avg episode reward: [(0, '21.680'), (1, '21.200')] -[2023-10-15 02:34:18,745][88298] Updated weights for policy 0, policy_version 8530 (0.0009) -[2023-10-15 02:34:19,119][88298] Updated weights for policy 0, policy_version 8540 (0.0007) -[2023-10-15 02:34:20,516][88300] Updated weights for policy 1, policy_version 8582 (0.0010) -[2023-10-15 02:34:20,888][88300] Updated weights for policy 1, policy_version 8592 (0.0009) -[2023-10-15 02:34:21,247][88300] Updated weights for policy 1, policy_version 8602 (0.0008) -[2023-10-15 02:34:22,860][88298] Updated weights for policy 0, policy_version 8550 (0.0007) -[2023-10-15 02:34:23,226][88298] Updated weights for policy 0, policy_version 8560 (0.0007) -[2023-10-15 02:34:23,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 17563648. Throughput: 0: 1744.2, 1: 1733.1. Samples: 4401406. Policy #0 lag: (min: 26.0, avg: 28.0, max: 54.0) -[2023-10-15 02:34:23,534][87330] Avg episode reward: [(0, '21.160'), (1, '21.310')] -[2023-10-15 02:34:23,596][88298] Updated weights for policy 0, policy_version 8570 (0.0008) -[2023-10-15 02:34:25,160][88300] Updated weights for policy 1, policy_version 8612 (0.0009) -[2023-10-15 02:34:25,527][88300] Updated weights for policy 1, policy_version 8622 (0.0007) -[2023-10-15 02:34:25,886][88300] Updated weights for policy 1, policy_version 8632 (0.0007) -[2023-10-15 02:34:27,604][88298] Updated weights for policy 0, policy_version 8580 (0.0008) -[2023-10-15 02:34:27,972][88298] Updated weights for policy 0, policy_version 8590 (0.0008) -[2023-10-15 02:34:28,352][88298] Updated weights for policy 0, policy_version 8600 (0.0008) -[2023-10-15 02:34:28,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 17629184. Throughput: 0: 1742.3, 1: 1744.1. Samples: 4423006. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) -[2023-10-15 02:34:28,535][87330] Avg episode reward: [(0, '21.340'), (1, '21.300')] -[2023-10-15 02:34:29,706][88300] Updated weights for policy 1, policy_version 8642 (0.0009) -[2023-10-15 02:34:30,074][88300] Updated weights for policy 1, policy_version 8652 (0.0007) -[2023-10-15 02:34:30,443][88300] Updated weights for policy 1, policy_version 8662 (0.0008) -[2023-10-15 02:34:30,822][88300] Updated weights for policy 1, policy_version 8672 (0.0007) -[2023-10-15 02:34:32,354][88298] Updated weights for policy 0, policy_version 8610 (0.0007) -[2023-10-15 02:34:32,734][88298] Updated weights for policy 0, policy_version 8620 (0.0009) -[2023-10-15 02:34:33,106][88298] Updated weights for policy 0, policy_version 8630 (0.0007) -[2023-10-15 02:34:33,481][88298] Updated weights for policy 0, policy_version 8640 (0.0008) -[2023-10-15 02:34:33,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 17727488. Throughput: 0: 1737.2, 1: 1735.9. Samples: 4432884. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:34:33,534][87330] Avg episode reward: [(0, '21.300'), (1, '21.280')] -[2023-10-15 02:34:34,734][88300] Updated weights for policy 1, policy_version 8682 (0.0009) -[2023-10-15 02:34:35,099][88300] Updated weights for policy 1, policy_version 8692 (0.0009) -[2023-10-15 02:34:35,470][88300] Updated weights for policy 1, policy_version 8702 (0.0008) -[2023-10-15 02:34:37,502][88298] Updated weights for policy 0, policy_version 8650 (0.0009) -[2023-10-15 02:34:37,872][88298] Updated weights for policy 0, policy_version 8660 (0.0007) -[2023-10-15 02:34:38,240][88298] Updated weights for policy 0, policy_version 8670 (0.0007) -[2023-10-15 02:34:38,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 17793024. Throughput: 0: 1747.2, 1: 1739.8. Samples: 4454362. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:34:38,535][87330] Avg episode reward: [(0, '21.320'), (1, '21.670')] -[2023-10-15 02:34:38,536][88033] Saving new best policy, reward=21.670! -[2023-10-15 02:34:39,452][88300] Updated weights for policy 1, policy_version 8712 (0.0007) -[2023-10-15 02:34:39,819][88300] Updated weights for policy 1, policy_version 8722 (0.0010) -[2023-10-15 02:34:40,184][88300] Updated weights for policy 1, policy_version 8732 (0.0010) -[2023-10-15 02:34:42,190][88298] Updated weights for policy 0, policy_version 8680 (0.0007) -[2023-10-15 02:34:42,559][88298] Updated weights for policy 0, policy_version 8690 (0.0009) -[2023-10-15 02:34:42,941][88298] Updated weights for policy 0, policy_version 8700 (0.0008) -[2023-10-15 02:34:43,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 17858560. Throughput: 0: 1729.8, 1: 1768.1. Samples: 4475090. Policy #0 lag: (min: 15.0, avg: 23.5, max: 47.0) -[2023-10-15 02:34:43,534][87330] Avg episode reward: [(0, '21.350'), (1, '21.660')] -[2023-10-15 02:34:43,994][88300] Updated weights for policy 1, policy_version 8742 (0.0010) -[2023-10-15 02:34:44,369][88300] Updated weights for policy 1, policy_version 8752 (0.0010) -[2023-10-15 02:34:44,724][88300] Updated weights for policy 1, policy_version 8762 (0.0010) -[2023-10-15 02:34:46,673][88298] Updated weights for policy 0, policy_version 8710 (0.0008) -[2023-10-15 02:34:47,064][88298] Updated weights for policy 0, policy_version 8720 (0.0007) -[2023-10-15 02:34:47,436][88298] Updated weights for policy 0, policy_version 8730 (0.0007) -[2023-10-15 02:34:48,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 17924096. Throughput: 0: 1749.2, 1: 1737.4. Samples: 4485406. Policy #0 lag: (min: 15.0, avg: 23.5, max: 47.0) -[2023-10-15 02:34:48,534][87330] Avg episode reward: [(0, '21.290'), (1, '21.490')] -[2023-10-15 02:34:48,700][88300] Updated weights for policy 1, policy_version 8772 (0.0009) -[2023-10-15 02:34:49,071][88300] Updated weights for policy 1, policy_version 8782 (0.0009) -[2023-10-15 02:34:49,443][88300] Updated weights for policy 1, policy_version 8792 (0.0009) -[2023-10-15 02:34:51,348][88298] Updated weights for policy 0, policy_version 8740 (0.0008) -[2023-10-15 02:34:51,727][88298] Updated weights for policy 0, policy_version 8750 (0.0007) -[2023-10-15 02:34:52,108][88298] Updated weights for policy 0, policy_version 8760 (0.0008) -[2023-10-15 02:34:53,236][88300] Updated weights for policy 1, policy_version 8802 (0.0009) -[2023-10-15 02:34:53,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 17989632. Throughput: 0: 1729.7, 1: 1762.3. Samples: 4506050. Policy #0 lag: (min: 9.0, avg: 16.6, max: 41.0) -[2023-10-15 02:34:53,535][87330] Avg episode reward: [(0, '21.420'), (1, '21.480')] -[2023-10-15 02:34:53,590][88300] Updated weights for policy 1, policy_version 8812 (0.0008) -[2023-10-15 02:34:53,957][88300] Updated weights for policy 1, policy_version 8822 (0.0008) -[2023-10-15 02:34:54,325][88300] Updated weights for policy 1, policy_version 8832 (0.0007) -[2023-10-15 02:34:55,897][88298] Updated weights for policy 0, policy_version 8770 (0.0008) -[2023-10-15 02:34:56,264][88298] Updated weights for policy 0, policy_version 8780 (0.0008) -[2023-10-15 02:34:56,638][88298] Updated weights for policy 0, policy_version 8790 (0.0007) -[2023-10-15 02:34:57,013][88298] Updated weights for policy 0, policy_version 8800 (0.0008) -[2023-10-15 02:34:58,170][88300] Updated weights for policy 1, policy_version 8842 (0.0009) -[2023-10-15 02:34:58,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 18055168. Throughput: 0: 1717.2, 1: 1758.3. Samples: 4526804. Policy #0 lag: (min: 9.0, avg: 16.6, max: 41.0) -[2023-10-15 02:34:58,534][87330] Avg episode reward: [(0, '21.620'), (1, '21.440')] -[2023-10-15 02:34:58,544][88300] Updated weights for policy 1, policy_version 8852 (0.0009) -[2023-10-15 02:34:58,548][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000008800_9011200.pth... -[2023-10-15 02:34:58,582][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000007168_7340032.pth -[2023-10-15 02:34:58,913][88300] Updated weights for policy 1, policy_version 8862 (0.0007) -[2023-10-15 02:34:58,978][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000008864_9076736.pth... -[2023-10-15 02:34:59,007][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000007232_7405568.pth -[2023-10-15 02:35:00,983][88298] Updated weights for policy 0, policy_version 8810 (0.0009) -[2023-10-15 02:35:01,359][88298] Updated weights for policy 0, policy_version 8820 (0.0010) -[2023-10-15 02:35:01,732][88298] Updated weights for policy 0, policy_version 8830 (0.0008) -[2023-10-15 02:35:02,790][88300] Updated weights for policy 1, policy_version 8872 (0.0008) -[2023-10-15 02:35:03,159][88300] Updated weights for policy 1, policy_version 8882 (0.0009) -[2023-10-15 02:35:03,526][88300] Updated weights for policy 1, policy_version 8892 (0.0007) -[2023-10-15 02:35:03,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 18120704. Throughput: 0: 1745.3, 1: 1752.6. Samples: 4537928. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:35:03,534][87330] Avg episode reward: [(0, '21.700'), (1, '21.420')] -[2023-10-15 02:35:05,546][88298] Updated weights for policy 0, policy_version 8840 (0.0009) -[2023-10-15 02:35:05,919][88298] Updated weights for policy 0, policy_version 8850 (0.0007) -[2023-10-15 02:35:06,289][88298] Updated weights for policy 0, policy_version 8860 (0.0009) -[2023-10-15 02:35:07,388][88300] Updated weights for policy 1, policy_version 8902 (0.0008) -[2023-10-15 02:35:07,758][88300] Updated weights for policy 1, policy_version 8912 (0.0009) -[2023-10-15 02:35:08,120][88300] Updated weights for policy 1, policy_version 8922 (0.0010) -[2023-10-15 02:35:08,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 18219008. Throughput: 0: 1723.6, 1: 1770.3. Samples: 4558630. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:35:08,534][87330] Avg episode reward: [(0, '21.670'), (1, '21.320')] -[2023-10-15 02:35:10,062][88298] Updated weights for policy 0, policy_version 8870 (0.0008) -[2023-10-15 02:35:10,434][88298] Updated weights for policy 0, policy_version 8880 (0.0008) -[2023-10-15 02:35:10,798][88298] Updated weights for policy 0, policy_version 8890 (0.0008) -[2023-10-15 02:35:11,996][88300] Updated weights for policy 1, policy_version 8932 (0.0009) -[2023-10-15 02:35:12,366][88300] Updated weights for policy 1, policy_version 8942 (0.0007) -[2023-10-15 02:35:12,732][88300] Updated weights for policy 1, policy_version 8952 (0.0007) -[2023-10-15 02:35:13,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 18284544. Throughput: 0: 1727.5, 1: 1739.6. Samples: 4579024. Policy #0 lag: (min: 17.0, avg: 22.0, max: 48.0) -[2023-10-15 02:35:13,534][87330] Avg episode reward: [(0, '21.370'), (1, '21.320')] -[2023-10-15 02:35:14,909][88298] Updated weights for policy 0, policy_version 8900 (0.0009) -[2023-10-15 02:35:15,277][88298] Updated weights for policy 0, policy_version 8910 (0.0009) -[2023-10-15 02:35:15,658][88298] Updated weights for policy 0, policy_version 8920 (0.0009) -[2023-10-15 02:35:16,594][88300] Updated weights for policy 1, policy_version 8962 (0.0009) -[2023-10-15 02:35:16,967][88300] Updated weights for policy 1, policy_version 8972 (0.0008) -[2023-10-15 02:35:17,333][88300] Updated weights for policy 1, policy_version 8982 (0.0008) -[2023-10-15 02:35:17,692][88300] Updated weights for policy 1, policy_version 8992 (0.0007) -[2023-10-15 02:35:18,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 18350080. Throughput: 0: 1725.8, 1: 1765.3. Samples: 4589984. Policy #0 lag: (min: 17.0, avg: 22.0, max: 48.0) -[2023-10-15 02:35:18,534][87330] Avg episode reward: [(0, '21.430'), (1, '21.330')] -[2023-10-15 02:35:19,588][88298] Updated weights for policy 0, policy_version 8930 (0.0009) -[2023-10-15 02:35:19,952][88298] Updated weights for policy 0, policy_version 8940 (0.0007) -[2023-10-15 02:35:20,331][88298] Updated weights for policy 0, policy_version 8950 (0.0010) -[2023-10-15 02:35:20,694][88298] Updated weights for policy 0, policy_version 8960 (0.0009) -[2023-10-15 02:35:21,570][88300] Updated weights for policy 1, policy_version 9002 (0.0007) -[2023-10-15 02:35:21,941][88300] Updated weights for policy 1, policy_version 9012 (0.0007) -[2023-10-15 02:35:22,304][88300] Updated weights for policy 1, policy_version 9022 (0.0009) -[2023-10-15 02:35:23,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13884.8). Total num frames: 18415616. Throughput: 0: 1721.6, 1: 1741.0. Samples: 4610176. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:35:23,535][87330] Avg episode reward: [(0, '21.510'), (1, '21.340')] -[2023-10-15 02:35:24,481][88298] Updated weights for policy 0, policy_version 8970 (0.0009) -[2023-10-15 02:35:24,849][88298] Updated weights for policy 0, policy_version 8980 (0.0010) -[2023-10-15 02:35:25,216][88298] Updated weights for policy 0, policy_version 8990 (0.0011) -[2023-10-15 02:35:26,287][88300] Updated weights for policy 1, policy_version 9032 (0.0007) -[2023-10-15 02:35:26,661][88300] Updated weights for policy 1, policy_version 9042 (0.0009) -[2023-10-15 02:35:27,027][88300] Updated weights for policy 1, policy_version 9052 (0.0010) -[2023-10-15 02:35:28,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 18481152. Throughput: 0: 1740.8, 1: 1729.5. Samples: 4631254. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:35:28,534][87330] Avg episode reward: [(0, '21.610'), (1, '21.400')] -[2023-10-15 02:35:29,271][88298] Updated weights for policy 0, policy_version 9000 (0.0009) -[2023-10-15 02:35:29,646][88298] Updated weights for policy 0, policy_version 9010 (0.0009) -[2023-10-15 02:35:30,019][88298] Updated weights for policy 0, policy_version 9020 (0.0009) -[2023-10-15 02:35:30,866][88300] Updated weights for policy 1, policy_version 9062 (0.0009) -[2023-10-15 02:35:31,234][88300] Updated weights for policy 1, policy_version 9072 (0.0009) -[2023-10-15 02:35:31,601][88300] Updated weights for policy 1, policy_version 9082 (0.0008) -[2023-10-15 02:35:33,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 18546688. Throughput: 0: 1719.1, 1: 1749.0. Samples: 4641472. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:35:33,534][87330] Avg episode reward: [(0, '21.400'), (1, '21.390')] -[2023-10-15 02:35:34,075][88298] Updated weights for policy 0, policy_version 9030 (0.0008) -[2023-10-15 02:35:34,446][88298] Updated weights for policy 0, policy_version 9040 (0.0010) -[2023-10-15 02:35:34,817][88298] Updated weights for policy 0, policy_version 9050 (0.0010) -[2023-10-15 02:35:35,444][88300] Updated weights for policy 1, policy_version 9092 (0.0007) -[2023-10-15 02:35:35,821][88300] Updated weights for policy 1, policy_version 9102 (0.0011) -[2023-10-15 02:35:36,188][88300] Updated weights for policy 1, policy_version 9112 (0.0011) -[2023-10-15 02:35:38,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 18612224. Throughput: 0: 1738.1, 1: 1726.6. Samples: 4661962. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:35:38,534][87330] Avg episode reward: [(0, '21.410'), (1, '21.540')] -[2023-10-15 02:35:38,739][88298] Updated weights for policy 0, policy_version 9060 (0.0011) -[2023-10-15 02:35:39,116][88298] Updated weights for policy 0, policy_version 9070 (0.0010) -[2023-10-15 02:35:39,493][88298] Updated weights for policy 0, policy_version 9080 (0.0008) -[2023-10-15 02:35:40,177][88300] Updated weights for policy 1, policy_version 9122 (0.0011) -[2023-10-15 02:35:40,543][88300] Updated weights for policy 1, policy_version 9132 (0.0007) -[2023-10-15 02:35:40,909][88300] Updated weights for policy 1, policy_version 9142 (0.0007) -[2023-10-15 02:35:41,281][88300] Updated weights for policy 1, policy_version 9152 (0.0007) -[2023-10-15 02:35:43,489][88298] Updated weights for policy 0, policy_version 9090 (0.0008) -[2023-10-15 02:35:43,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 18677760. Throughput: 0: 1749.6, 1: 1738.1. Samples: 4683750. Policy #0 lag: (min: 26.0, avg: 33.7, max: 58.0) -[2023-10-15 02:35:43,534][87330] Avg episode reward: [(0, '21.740'), (1, '21.550')] -[2023-10-15 02:35:43,851][88298] Updated weights for policy 0, policy_version 9100 (0.0011) -[2023-10-15 02:35:44,228][88298] Updated weights for policy 0, policy_version 9110 (0.0008) -[2023-10-15 02:35:44,593][88298] Updated weights for policy 0, policy_version 9120 (0.0007) -[2023-10-15 02:35:45,103][88300] Updated weights for policy 1, policy_version 9162 (0.0009) -[2023-10-15 02:35:45,466][88300] Updated weights for policy 1, policy_version 9172 (0.0011) -[2023-10-15 02:35:45,837][88300] Updated weights for policy 1, policy_version 9182 (0.0009) -[2023-10-15 02:35:48,507][88298] Updated weights for policy 0, policy_version 9130 (0.0008) -[2023-10-15 02:35:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 18743296. Throughput: 0: 1721.4, 1: 1730.9. Samples: 4693282. Policy #0 lag: (min: 26.0, avg: 33.7, max: 58.0) -[2023-10-15 02:35:48,534][87330] Avg episode reward: [(0, '21.740'), (1, '21.710')] -[2023-10-15 02:35:48,535][88033] Saving new best policy, reward=21.710! -[2023-10-15 02:35:48,881][88298] Updated weights for policy 0, policy_version 9140 (0.0007) -[2023-10-15 02:35:49,245][88298] Updated weights for policy 0, policy_version 9150 (0.0007) -[2023-10-15 02:35:49,789][88300] Updated weights for policy 1, policy_version 9192 (0.0008) -[2023-10-15 02:35:50,154][88300] Updated weights for policy 1, policy_version 9202 (0.0007) -[2023-10-15 02:35:50,522][88300] Updated weights for policy 1, policy_version 9212 (0.0007) -[2023-10-15 02:35:53,332][88298] Updated weights for policy 0, policy_version 9160 (0.0007) -[2023-10-15 02:35:53,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 18808832. Throughput: 0: 1737.7, 1: 1727.2. Samples: 4714550. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) -[2023-10-15 02:35:53,534][87330] Avg episode reward: [(0, '21.710'), (1, '21.790')] -[2023-10-15 02:35:53,535][88033] Saving new best policy, reward=21.790! -[2023-10-15 02:35:53,698][88298] Updated weights for policy 0, policy_version 9170 (0.0007) -[2023-10-15 02:35:54,074][88298] Updated weights for policy 0, policy_version 9180 (0.0008) -[2023-10-15 02:35:54,355][88300] Updated weights for policy 1, policy_version 9222 (0.0008) -[2023-10-15 02:35:54,725][88300] Updated weights for policy 1, policy_version 9232 (0.0010) -[2023-10-15 02:35:55,101][88300] Updated weights for policy 1, policy_version 9242 (0.0010) -[2023-10-15 02:35:57,671][88298] Updated weights for policy 0, policy_version 9190 (0.0009) -[2023-10-15 02:35:58,044][88298] Updated weights for policy 0, policy_version 9200 (0.0008) -[2023-10-15 02:35:58,413][88298] Updated weights for policy 0, policy_version 9210 (0.0011) -[2023-10-15 02:35:58,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 18874368. Throughput: 0: 1731.6, 1: 1755.6. Samples: 4735950. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) -[2023-10-15 02:35:58,535][87330] Avg episode reward: [(0, '21.770'), (1, '21.730')] -[2023-10-15 02:35:58,987][88300] Updated weights for policy 1, policy_version 9252 (0.0007) -[2023-10-15 02:35:59,349][88300] Updated weights for policy 1, policy_version 9262 (0.0007) -[2023-10-15 02:35:59,703][88300] Updated weights for policy 1, policy_version 9272 (0.0009) -[2023-10-15 02:36:02,418][88298] Updated weights for policy 0, policy_version 9220 (0.0008) -[2023-10-15 02:36:02,787][88298] Updated weights for policy 0, policy_version 9230 (0.0007) -[2023-10-15 02:36:03,156][88298] Updated weights for policy 0, policy_version 9240 (0.0007) -[2023-10-15 02:36:03,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 18972672. Throughput: 0: 1735.8, 1: 1726.9. Samples: 4745808. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:36:03,535][87330] Avg episode reward: [(0, '21.680'), (1, '21.280')] -[2023-10-15 02:36:03,642][88300] Updated weights for policy 1, policy_version 9282 (0.0009) -[2023-10-15 02:36:04,008][88300] Updated weights for policy 1, policy_version 9292 (0.0007) -[2023-10-15 02:36:04,386][88300] Updated weights for policy 1, policy_version 9302 (0.0009) -[2023-10-15 02:36:04,756][88300] Updated weights for policy 1, policy_version 9312 (0.0009) -[2023-10-15 02:36:07,176][88298] Updated weights for policy 0, policy_version 9250 (0.0008) -[2023-10-15 02:36:07,550][88298] Updated weights for policy 0, policy_version 9260 (0.0007) -[2023-10-15 02:36:07,918][88298] Updated weights for policy 0, policy_version 9270 (0.0009) -[2023-10-15 02:36:08,289][88298] Updated weights for policy 0, policy_version 9280 (0.0009) -[2023-10-15 02:36:08,534][87330] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 19038208. Throughput: 0: 1739.9, 1: 1752.2. Samples: 4767322. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-10-15 02:36:08,535][87330] Avg episode reward: [(0, '21.800'), (1, '21.220')] -[2023-10-15 02:36:08,536][87905] Saving new best policy, reward=21.800! -[2023-10-15 02:36:08,569][88300] Updated weights for policy 1, policy_version 9322 (0.0007) -[2023-10-15 02:36:08,945][88300] Updated weights for policy 1, policy_version 9332 (0.0008) -[2023-10-15 02:36:09,320][88300] Updated weights for policy 1, policy_version 9342 (0.0007) -[2023-10-15 02:36:12,190][88298] Updated weights for policy 0, policy_version 9290 (0.0007) -[2023-10-15 02:36:12,579][88298] Updated weights for policy 0, policy_version 9300 (0.0010) -[2023-10-15 02:36:12,943][88298] Updated weights for policy 0, policy_version 9310 (0.0010) -[2023-10-15 02:36:13,219][88300] Updated weights for policy 1, policy_version 9352 (0.0007) -[2023-10-15 02:36:13,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 19103744. Throughput: 0: 1711.2, 1: 1758.0. Samples: 4787366. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-10-15 02:36:13,534][87330] Avg episode reward: [(0, '21.800'), (1, '21.250')] -[2023-10-15 02:36:13,599][88300] Updated weights for policy 1, policy_version 9362 (0.0007) -[2023-10-15 02:36:13,975][88300] Updated weights for policy 1, policy_version 9372 (0.0009) -[2023-10-15 02:36:16,691][88298] Updated weights for policy 0, policy_version 9320 (0.0007) -[2023-10-15 02:36:17,066][88298] Updated weights for policy 0, policy_version 9330 (0.0008) -[2023-10-15 02:36:17,428][88298] Updated weights for policy 0, policy_version 9340 (0.0007) -[2023-10-15 02:36:17,904][88300] Updated weights for policy 1, policy_version 9382 (0.0009) -[2023-10-15 02:36:18,267][88300] Updated weights for policy 1, policy_version 9392 (0.0007) -[2023-10-15 02:36:18,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 19169280. Throughput: 0: 1738.7, 1: 1743.2. Samples: 4798156. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:36:18,534][87330] Avg episode reward: [(0, '21.820'), (1, '21.260')] -[2023-10-15 02:36:18,535][87905] Saving new best policy, reward=21.820! -[2023-10-15 02:36:18,639][88300] Updated weights for policy 1, policy_version 9402 (0.0007) -[2023-10-15 02:36:21,423][88298] Updated weights for policy 0, policy_version 9350 (0.0007) -[2023-10-15 02:36:21,794][88298] Updated weights for policy 0, policy_version 9360 (0.0010) -[2023-10-15 02:36:22,178][88298] Updated weights for policy 0, policy_version 9370 (0.0009) -[2023-10-15 02:36:22,524][88300] Updated weights for policy 1, policy_version 9412 (0.0008) -[2023-10-15 02:36:22,890][88300] Updated weights for policy 1, policy_version 9422 (0.0010) -[2023-10-15 02:36:23,267][88300] Updated weights for policy 1, policy_version 9432 (0.0009) -[2023-10-15 02:36:23,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 19234816. Throughput: 0: 1725.5, 1: 1769.8. Samples: 4819248. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:36:23,534][87330] Avg episode reward: [(0, '21.700'), (1, '21.210')] -[2023-10-15 02:36:25,969][88298] Updated weights for policy 0, policy_version 9380 (0.0008) -[2023-10-15 02:36:26,348][88298] Updated weights for policy 0, policy_version 9390 (0.0008) -[2023-10-15 02:36:26,714][88298] Updated weights for policy 0, policy_version 9400 (0.0007) -[2023-10-15 02:36:27,167][88300] Updated weights for policy 1, policy_version 9442 (0.0010) -[2023-10-15 02:36:27,534][88300] Updated weights for policy 1, policy_version 9452 (0.0009) -[2023-10-15 02:36:27,899][88300] Updated weights for policy 1, policy_version 9462 (0.0011) -[2023-10-15 02:36:28,264][88300] Updated weights for policy 1, policy_version 9472 (0.0010) -[2023-10-15 02:36:28,534][87330] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 19333120. Throughput: 0: 1707.3, 1: 1734.2. Samples: 4838618. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-15 02:36:28,535][87330] Avg episode reward: [(0, '21.690'), (1, '21.250')] -[2023-10-15 02:36:30,513][88298] Updated weights for policy 0, policy_version 9410 (0.0008) -[2023-10-15 02:36:30,882][88298] Updated weights for policy 0, policy_version 9420 (0.0008) -[2023-10-15 02:36:31,249][88298] Updated weights for policy 0, policy_version 9430 (0.0008) -[2023-10-15 02:36:31,623][88298] Updated weights for policy 0, policy_version 9440 (0.0008) -[2023-10-15 02:36:32,188][88300] Updated weights for policy 1, policy_version 9482 (0.0009) -[2023-10-15 02:36:32,559][88300] Updated weights for policy 1, policy_version 9492 (0.0009) -[2023-10-15 02:36:32,932][88300] Updated weights for policy 1, policy_version 9502 (0.0007) -[2023-10-15 02:36:33,534][87330] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 19398656. Throughput: 0: 1736.4, 1: 1757.1. Samples: 4850492. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-15 02:36:33,535][87330] Avg episode reward: [(0, '21.740'), (1, '21.550')] -[2023-10-15 02:36:35,524][88298] Updated weights for policy 0, policy_version 9450 (0.0009) -[2023-10-15 02:36:35,891][88298] Updated weights for policy 0, policy_version 9460 (0.0007) -[2023-10-15 02:36:36,261][88298] Updated weights for policy 0, policy_version 9470 (0.0010) -[2023-10-15 02:36:36,947][88300] Updated weights for policy 1, policy_version 9512 (0.0009) -[2023-10-15 02:36:37,307][88300] Updated weights for policy 1, policy_version 9522 (0.0007) -[2023-10-15 02:36:37,673][88300] Updated weights for policy 1, policy_version 9532 (0.0008) -[2023-10-15 02:36:38,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 19464192. Throughput: 0: 1723.0, 1: 1742.6. Samples: 4870502. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:36:38,534][87330] Avg episode reward: [(0, '21.840'), (1, '21.770')] -[2023-10-15 02:36:38,535][87905] Saving new best policy, reward=21.840! -[2023-10-15 02:36:40,243][88298] Updated weights for policy 0, policy_version 9480 (0.0008) -[2023-10-15 02:36:40,618][88298] Updated weights for policy 0, policy_version 9490 (0.0008) -[2023-10-15 02:36:41,004][88298] Updated weights for policy 0, policy_version 9500 (0.0008) -[2023-10-15 02:36:41,483][88300] Updated weights for policy 1, policy_version 9542 (0.0008) -[2023-10-15 02:36:41,850][88300] Updated weights for policy 1, policy_version 9552 (0.0007) -[2023-10-15 02:36:42,219][88300] Updated weights for policy 1, policy_version 9562 (0.0007) -[2023-10-15 02:36:43,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 19529728. Throughput: 0: 1729.1, 1: 1724.3. Samples: 4891350. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:36:43,535][87330] Avg episode reward: [(0, '21.700'), (1, '21.750')] -[2023-10-15 02:36:44,967][88298] Updated weights for policy 0, policy_version 9510 (0.0009) -[2023-10-15 02:36:45,346][88298] Updated weights for policy 0, policy_version 9520 (0.0010) -[2023-10-15 02:36:45,720][88298] Updated weights for policy 0, policy_version 9530 (0.0009) -[2023-10-15 02:36:46,080][88300] Updated weights for policy 1, policy_version 9572 (0.0008) -[2023-10-15 02:36:46,448][88300] Updated weights for policy 1, policy_version 9582 (0.0009) -[2023-10-15 02:36:46,822][88300] Updated weights for policy 1, policy_version 9592 (0.0007) -[2023-10-15 02:36:48,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 19595264. Throughput: 0: 1726.5, 1: 1749.1. Samples: 4902208. Policy #0 lag: (min: 9.0, avg: 20.0, max: 41.0) -[2023-10-15 02:36:48,534][87330] Avg episode reward: [(0, '21.630'), (1, '21.360')] -[2023-10-15 02:36:49,533][88298] Updated weights for policy 0, policy_version 9540 (0.0010) -[2023-10-15 02:36:49,902][88298] Updated weights for policy 0, policy_version 9550 (0.0007) -[2023-10-15 02:36:50,275][88298] Updated weights for policy 0, policy_version 9560 (0.0009) -[2023-10-15 02:36:50,770][88300] Updated weights for policy 1, policy_version 9602 (0.0008) -[2023-10-15 02:36:51,140][88300] Updated weights for policy 1, policy_version 9612 (0.0010) -[2023-10-15 02:36:51,510][88300] Updated weights for policy 1, policy_version 9622 (0.0010) -[2023-10-15 02:36:51,875][88300] Updated weights for policy 1, policy_version 9632 (0.0008) -[2023-10-15 02:36:53,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 19660800. Throughput: 0: 1725.0, 1: 1721.7. Samples: 4922424. Policy #0 lag: (min: 9.0, avg: 20.0, max: 41.0) -[2023-10-15 02:36:53,534][87330] Avg episode reward: [(0, '21.790'), (1, '20.930')] -[2023-10-15 02:36:54,347][88298] Updated weights for policy 0, policy_version 9570 (0.0011) -[2023-10-15 02:36:54,723][88298] Updated weights for policy 0, policy_version 9580 (0.0009) -[2023-10-15 02:36:55,087][88298] Updated weights for policy 0, policy_version 9590 (0.0007) -[2023-10-15 02:36:55,457][88298] Updated weights for policy 0, policy_version 9600 (0.0008) -[2023-10-15 02:36:55,812][88300] Updated weights for policy 1, policy_version 9642 (0.0008) -[2023-10-15 02:36:56,182][88300] Updated weights for policy 1, policy_version 9652 (0.0011) -[2023-10-15 02:36:56,560][88300] Updated weights for policy 1, policy_version 9662 (0.0008) -[2023-10-15 02:36:58,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 19726336. Throughput: 0: 1754.5, 1: 1726.7. Samples: 4944018. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 02:36:58,535][87330] Avg episode reward: [(0, '21.710'), (1, '20.780')] -[2023-10-15 02:36:58,544][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000009600_9830400.pth... -[2023-10-15 02:36:58,545][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000009664_9895936.pth... -[2023-10-15 02:36:58,579][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000008000_8192000.pth -[2023-10-15 02:36:58,584][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000008032_8224768.pth -[2023-10-15 02:36:59,365][88298] Updated weights for policy 0, policy_version 9610 (0.0007) -[2023-10-15 02:36:59,743][88298] Updated weights for policy 0, policy_version 9620 (0.0008) -[2023-10-15 02:37:00,111][88298] Updated weights for policy 0, policy_version 9630 (0.0008) -[2023-10-15 02:37:00,404][88300] Updated weights for policy 1, policy_version 9672 (0.0007) -[2023-10-15 02:37:00,767][88300] Updated weights for policy 1, policy_version 9682 (0.0008) -[2023-10-15 02:37:01,130][88300] Updated weights for policy 1, policy_version 9692 (0.0008) -[2023-10-15 02:37:03,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 19791872. Throughput: 0: 1728.3, 1: 1728.4. Samples: 4953704. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 02:37:03,534][87330] Avg episode reward: [(0, '21.730'), (1, '20.690')] -[2023-10-15 02:37:03,891][88298] Updated weights for policy 0, policy_version 9640 (0.0009) -[2023-10-15 02:37:04,271][88298] Updated weights for policy 0, policy_version 9650 (0.0012) -[2023-10-15 02:37:04,655][88298] Updated weights for policy 0, policy_version 9660 (0.0010) -[2023-10-15 02:37:05,081][88300] Updated weights for policy 1, policy_version 9702 (0.0008) -[2023-10-15 02:37:05,452][88300] Updated weights for policy 1, policy_version 9712 (0.0007) -[2023-10-15 02:37:05,819][88300] Updated weights for policy 1, policy_version 9722 (0.0007) -[2023-10-15 02:37:08,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 19857408. Throughput: 0: 1744.0, 1: 1721.3. Samples: 4975186. Policy #0 lag: (min: 25.0, avg: 41.5, max: 57.0) -[2023-10-15 02:37:08,535][87330] Avg episode reward: [(0, '21.710'), (1, '20.450')] -[2023-10-15 02:37:08,586][88298] Updated weights for policy 0, policy_version 9670 (0.0010) -[2023-10-15 02:37:08,959][88298] Updated weights for policy 0, policy_version 9680 (0.0010) -[2023-10-15 02:37:09,336][88298] Updated weights for policy 0, policy_version 9690 (0.0010) -[2023-10-15 02:37:09,611][88300] Updated weights for policy 1, policy_version 9732 (0.0008) -[2023-10-15 02:37:09,977][88300] Updated weights for policy 1, policy_version 9742 (0.0008) -[2023-10-15 02:37:10,343][88300] Updated weights for policy 1, policy_version 9752 (0.0008) -[2023-10-15 02:37:13,208][88298] Updated weights for policy 0, policy_version 9700 (0.0008) -[2023-10-15 02:37:13,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 19922944. Throughput: 0: 1761.6, 1: 1753.5. Samples: 4996800. Policy #0 lag: (min: 25.0, avg: 41.5, max: 57.0) -[2023-10-15 02:37:13,535][87330] Avg episode reward: [(0, '21.920'), (1, '20.450')] -[2023-10-15 02:37:13,580][88298] Updated weights for policy 0, policy_version 9710 (0.0007) -[2023-10-15 02:37:13,948][88298] Updated weights for policy 0, policy_version 9720 (0.0007) -[2023-10-15 02:37:14,240][87905] Saving new best policy, reward=21.920! -[2023-10-15 02:37:14,290][88300] Updated weights for policy 1, policy_version 9762 (0.0009) -[2023-10-15 02:37:14,656][88300] Updated weights for policy 1, policy_version 9772 (0.0009) -[2023-10-15 02:37:15,016][88300] Updated weights for policy 1, policy_version 9782 (0.0008) -[2023-10-15 02:37:15,381][88300] Updated weights for policy 1, policy_version 9792 (0.0007) -[2023-10-15 02:37:17,678][88298] Updated weights for policy 0, policy_version 9730 (0.0007) -[2023-10-15 02:37:18,046][88298] Updated weights for policy 0, policy_version 9740 (0.0007) -[2023-10-15 02:37:18,415][88298] Updated weights for policy 0, policy_version 9750 (0.0008) -[2023-10-15 02:37:18,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 19988480. Throughput: 0: 1736.0, 1: 1728.6. Samples: 5006398. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 02:37:18,535][87330] Avg episode reward: [(0, '21.920'), (1, '20.820')] -[2023-10-15 02:37:18,787][88298] Updated weights for policy 0, policy_version 9760 (0.0010) -[2023-10-15 02:37:19,143][88300] Updated weights for policy 1, policy_version 9802 (0.0007) -[2023-10-15 02:37:19,519][88300] Updated weights for policy 1, policy_version 9812 (0.0009) -[2023-10-15 02:37:19,889][88300] Updated weights for policy 1, policy_version 9822 (0.0008) -[2023-10-15 02:37:22,733][88298] Updated weights for policy 0, policy_version 9770 (0.0010) -[2023-10-15 02:37:23,104][88298] Updated weights for policy 0, policy_version 9780 (0.0010) -[2023-10-15 02:37:23,484][88298] Updated weights for policy 0, policy_version 9790 (0.0009) -[2023-10-15 02:37:23,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 20054016. Throughput: 0: 1754.9, 1: 1745.3. Samples: 5028010. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 02:37:23,534][87330] Avg episode reward: [(0, '21.950'), (1, '21.110')] -[2023-10-15 02:37:23,551][87905] Saving new best policy, reward=21.950! -[2023-10-15 02:37:23,770][88300] Updated weights for policy 1, policy_version 9832 (0.0010) -[2023-10-15 02:37:24,137][88300] Updated weights for policy 1, policy_version 9842 (0.0010) -[2023-10-15 02:37:24,515][88300] Updated weights for policy 1, policy_version 9852 (0.0008) -[2023-10-15 02:37:27,539][88298] Updated weights for policy 0, policy_version 9800 (0.0007) -[2023-10-15 02:37:27,915][88298] Updated weights for policy 0, policy_version 9810 (0.0007) -[2023-10-15 02:37:28,284][88298] Updated weights for policy 0, policy_version 9820 (0.0008) -[2023-10-15 02:37:28,430][88300] Updated weights for policy 1, policy_version 9862 (0.0007) -[2023-10-15 02:37:28,534][87330] Fps is (10 sec: 16384.2, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 20152320. Throughput: 0: 1732.7, 1: 1762.9. Samples: 5048652. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:37:28,535][87330] Avg episode reward: [(0, '21.990'), (1, '21.190')] -[2023-10-15 02:37:28,544][87905] Saving new best policy, reward=21.990! -[2023-10-15 02:37:28,794][88300] Updated weights for policy 1, policy_version 9872 (0.0007) -[2023-10-15 02:37:29,160][88300] Updated weights for policy 1, policy_version 9882 (0.0007) -[2023-10-15 02:37:32,232][88298] Updated weights for policy 0, policy_version 9830 (0.0009) -[2023-10-15 02:37:32,609][88298] Updated weights for policy 0, policy_version 9840 (0.0008) -[2023-10-15 02:37:32,970][88298] Updated weights for policy 0, policy_version 9850 (0.0009) -[2023-10-15 02:37:33,067][88300] Updated weights for policy 1, policy_version 9892 (0.0009) -[2023-10-15 02:37:33,431][88300] Updated weights for policy 1, policy_version 9902 (0.0007) -[2023-10-15 02:37:33,534][87330] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 20217856. Throughput: 0: 1738.0, 1: 1739.9. Samples: 5058712. Policy #0 lag: (min: 3.0, avg: 5.2, max: 33.0) -[2023-10-15 02:37:33,534][87330] Avg episode reward: [(0, '22.080'), (1, '21.390')] -[2023-10-15 02:37:33,535][87905] Saving new best policy, reward=22.080! -[2023-10-15 02:37:33,796][88300] Updated weights for policy 1, policy_version 9912 (0.0007) -[2023-10-15 02:37:36,962][88298] Updated weights for policy 0, policy_version 9860 (0.0008) -[2023-10-15 02:37:37,337][88298] Updated weights for policy 0, policy_version 9870 (0.0007) -[2023-10-15 02:37:37,710][88298] Updated weights for policy 0, policy_version 9880 (0.0008) -[2023-10-15 02:37:37,732][88300] Updated weights for policy 1, policy_version 9922 (0.0008) -[2023-10-15 02:37:38,109][88300] Updated weights for policy 1, policy_version 9932 (0.0009) -[2023-10-15 02:37:38,485][88300] Updated weights for policy 1, policy_version 9942 (0.0008) -[2023-10-15 02:37:38,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 20283392. Throughput: 0: 1740.2, 1: 1761.4. Samples: 5079994. Policy #0 lag: (min: 3.0, avg: 5.2, max: 33.0) -[2023-10-15 02:37:38,535][87330] Avg episode reward: [(0, '22.080'), (1, '21.400')] -[2023-10-15 02:37:38,843][88300] Updated weights for policy 1, policy_version 9952 (0.0007) -[2023-10-15 02:37:41,486][88298] Updated weights for policy 0, policy_version 9890 (0.0009) -[2023-10-15 02:37:41,863][88298] Updated weights for policy 0, policy_version 9900 (0.0007) -[2023-10-15 02:37:42,239][88298] Updated weights for policy 0, policy_version 9910 (0.0010) -[2023-10-15 02:37:42,604][88298] Updated weights for policy 0, policy_version 9920 (0.0009) -[2023-10-15 02:37:42,783][88300] Updated weights for policy 1, policy_version 9962 (0.0010) -[2023-10-15 02:37:43,158][88300] Updated weights for policy 1, policy_version 9972 (0.0009) -[2023-10-15 02:37:43,530][88300] Updated weights for policy 1, policy_version 9982 (0.0008) -[2023-10-15 02:37:43,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 20348928. Throughput: 0: 1707.5, 1: 1745.5. Samples: 5099402. Policy #0 lag: (min: 24.0, avg: 52.7, max: 56.0) -[2023-10-15 02:37:43,534][87330] Avg episode reward: [(0, '22.040'), (1, '21.660')] -[2023-10-15 02:37:46,554][88298] Updated weights for policy 0, policy_version 9930 (0.0011) -[2023-10-15 02:37:46,931][88298] Updated weights for policy 0, policy_version 9940 (0.0010) -[2023-10-15 02:37:47,298][88298] Updated weights for policy 0, policy_version 9950 (0.0008) -[2023-10-15 02:37:47,549][88300] Updated weights for policy 1, policy_version 9992 (0.0008) -[2023-10-15 02:37:47,921][88300] Updated weights for policy 1, policy_version 10002 (0.0009) -[2023-10-15 02:37:48,293][88300] Updated weights for policy 1, policy_version 10012 (0.0007) -[2023-10-15 02:37:48,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 20447232. Throughput: 0: 1740.1, 1: 1754.5. Samples: 5110960. Policy #0 lag: (min: 24.0, avg: 52.7, max: 56.0) -[2023-10-15 02:37:48,534][87330] Avg episode reward: [(0, '22.060'), (1, '21.740')] -[2023-10-15 02:37:51,176][88298] Updated weights for policy 0, policy_version 9960 (0.0010) -[2023-10-15 02:37:51,552][88298] Updated weights for policy 0, policy_version 9970 (0.0008) -[2023-10-15 02:37:51,919][88298] Updated weights for policy 0, policy_version 9980 (0.0008) -[2023-10-15 02:37:52,011][88300] Updated weights for policy 1, policy_version 10022 (0.0008) -[2023-10-15 02:37:52,378][88300] Updated weights for policy 1, policy_version 10032 (0.0007) -[2023-10-15 02:37:52,742][88300] Updated weights for policy 1, policy_version 10042 (0.0007) -[2023-10-15 02:37:53,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 20512768. Throughput: 0: 1717.5, 1: 1747.3. Samples: 5131102. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:37:53,534][87330] Avg episode reward: [(0, '22.080'), (1, '21.810')] -[2023-10-15 02:37:53,535][88033] Saving new best policy, reward=21.810! -[2023-10-15 02:37:56,042][88298] Updated weights for policy 0, policy_version 9990 (0.0010) -[2023-10-15 02:37:56,434][88298] Updated weights for policy 0, policy_version 10000 (0.0009) -[2023-10-15 02:37:56,806][88298] Updated weights for policy 0, policy_version 10010 (0.0009) -[2023-10-15 02:37:56,841][88300] Updated weights for policy 1, policy_version 10052 (0.0010) -[2023-10-15 02:37:57,214][88300] Updated weights for policy 1, policy_version 10062 (0.0008) -[2023-10-15 02:37:57,579][88300] Updated weights for policy 1, policy_version 10072 (0.0008) -[2023-10-15 02:37:58,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 20578304. Throughput: 0: 1708.5, 1: 1724.2. Samples: 5151270. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:37:58,534][87330] Avg episode reward: [(0, '22.110'), (1, '21.820')] -[2023-10-15 02:37:58,540][87905] Saving new best policy, reward=22.110! -[2023-10-15 02:37:58,540][88033] Saving new best policy, reward=21.820! -[2023-10-15 02:38:00,613][88298] Updated weights for policy 0, policy_version 10020 (0.0009) -[2023-10-15 02:38:00,997][88298] Updated weights for policy 0, policy_version 10030 (0.0009) -[2023-10-15 02:38:01,356][88298] Updated weights for policy 0, policy_version 10040 (0.0009) -[2023-10-15 02:38:01,376][88300] Updated weights for policy 1, policy_version 10082 (0.0008) -[2023-10-15 02:38:01,737][88300] Updated weights for policy 1, policy_version 10092 (0.0009) -[2023-10-15 02:38:02,103][88300] Updated weights for policy 1, policy_version 10102 (0.0009) -[2023-10-15 02:38:02,472][88300] Updated weights for policy 1, policy_version 10112 (0.0008) -[2023-10-15 02:38:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 20643840. Throughput: 0: 1730.1, 1: 1757.7. Samples: 5163348. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:38:03,534][87330] Avg episode reward: [(0, '22.100'), (1, '21.850')] -[2023-10-15 02:38:03,535][88033] Saving new best policy, reward=21.850! -[2023-10-15 02:38:05,219][88298] Updated weights for policy 0, policy_version 10050 (0.0008) -[2023-10-15 02:38:05,600][88298] Updated weights for policy 0, policy_version 10060 (0.0008) -[2023-10-15 02:38:05,966][88298] Updated weights for policy 0, policy_version 10070 (0.0008) -[2023-10-15 02:38:06,342][88298] Updated weights for policy 0, policy_version 10080 (0.0008) -[2023-10-15 02:38:06,425][88300] Updated weights for policy 1, policy_version 10122 (0.0010) -[2023-10-15 02:38:06,792][88300] Updated weights for policy 1, policy_version 10132 (0.0010) -[2023-10-15 02:38:07,156][88300] Updated weights for policy 1, policy_version 10142 (0.0009) -[2023-10-15 02:38:08,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 20709376. Throughput: 0: 1712.7, 1: 1729.1. Samples: 5182890. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:38:08,534][87330] Avg episode reward: [(0, '22.110'), (1, '21.760')] -[2023-10-15 02:38:10,151][88298] Updated weights for policy 0, policy_version 10090 (0.0008) -[2023-10-15 02:38:10,527][88298] Updated weights for policy 0, policy_version 10100 (0.0008) -[2023-10-15 02:38:10,895][88298] Updated weights for policy 0, policy_version 10110 (0.0008) -[2023-10-15 02:38:11,032][88300] Updated weights for policy 1, policy_version 10152 (0.0008) -[2023-10-15 02:38:11,401][88300] Updated weights for policy 1, policy_version 10162 (0.0009) -[2023-10-15 02:38:11,763][88300] Updated weights for policy 1, policy_version 10172 (0.0009) -[2023-10-15 02:38:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 20774912. Throughput: 0: 1739.1, 1: 1724.7. Samples: 5204520. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:38:13,534][87330] Avg episode reward: [(0, '22.190'), (1, '21.710')] -[2023-10-15 02:38:13,543][87905] Saving new best policy, reward=22.190! -[2023-10-15 02:38:14,662][88298] Updated weights for policy 0, policy_version 10120 (0.0009) -[2023-10-15 02:38:15,031][88298] Updated weights for policy 0, policy_version 10130 (0.0011) -[2023-10-15 02:38:15,405][88298] Updated weights for policy 0, policy_version 10140 (0.0008) -[2023-10-15 02:38:15,653][88300] Updated weights for policy 1, policy_version 10182 (0.0008) -[2023-10-15 02:38:16,014][88300] Updated weights for policy 1, policy_version 10192 (0.0008) -[2023-10-15 02:38:16,382][88300] Updated weights for policy 1, policy_version 10202 (0.0009) -[2023-10-15 02:38:18,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 20840448. Throughput: 0: 1727.5, 1: 1733.4. Samples: 5214452. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:38:18,534][87330] Avg episode reward: [(0, '22.180'), (1, '21.740')] -[2023-10-15 02:38:19,419][88298] Updated weights for policy 0, policy_version 10150 (0.0008) -[2023-10-15 02:38:19,786][88298] Updated weights for policy 0, policy_version 10160 (0.0008) -[2023-10-15 02:38:20,154][88298] Updated weights for policy 0, policy_version 10170 (0.0009) -[2023-10-15 02:38:20,198][88300] Updated weights for policy 1, policy_version 10212 (0.0008) -[2023-10-15 02:38:20,576][88300] Updated weights for policy 1, policy_version 10222 (0.0009) -[2023-10-15 02:38:20,928][88300] Updated weights for policy 1, policy_version 10232 (0.0009) -[2023-10-15 02:38:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 20905984. Throughput: 0: 1730.4, 1: 1726.2. Samples: 5235542. Policy #0 lag: (min: 31.0, avg: 32.6, max: 58.0) -[2023-10-15 02:38:23,534][87330] Avg episode reward: [(0, '22.100'), (1, '21.690')] -[2023-10-15 02:38:24,005][88298] Updated weights for policy 0, policy_version 10180 (0.0008) -[2023-10-15 02:38:24,370][88298] Updated weights for policy 0, policy_version 10190 (0.0008) -[2023-10-15 02:38:24,741][88298] Updated weights for policy 0, policy_version 10200 (0.0010) -[2023-10-15 02:38:24,911][88300] Updated weights for policy 1, policy_version 10242 (0.0010) -[2023-10-15 02:38:25,284][88300] Updated weights for policy 1, policy_version 10252 (0.0009) -[2023-10-15 02:38:25,655][88300] Updated weights for policy 1, policy_version 10262 (0.0008) -[2023-10-15 02:38:26,025][88300] Updated weights for policy 1, policy_version 10272 (0.0007) -[2023-10-15 02:38:28,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 20971520. Throughput: 0: 1759.6, 1: 1744.0. Samples: 5257066. Policy #0 lag: (min: 31.0, avg: 32.6, max: 58.0) -[2023-10-15 02:38:28,534][87330] Avg episode reward: [(0, '22.000'), (1, '21.700')] -[2023-10-15 02:38:28,565][88298] Updated weights for policy 0, policy_version 10210 (0.0008) -[2023-10-15 02:38:28,939][88298] Updated weights for policy 0, policy_version 10220 (0.0010) -[2023-10-15 02:38:29,316][88298] Updated weights for policy 0, policy_version 10230 (0.0009) -[2023-10-15 02:38:29,696][88298] Updated weights for policy 0, policy_version 10240 (0.0010) -[2023-10-15 02:38:29,939][88300] Updated weights for policy 1, policy_version 10282 (0.0009) -[2023-10-15 02:38:30,321][88300] Updated weights for policy 1, policy_version 10292 (0.0007) -[2023-10-15 02:38:30,684][88300] Updated weights for policy 1, policy_version 10302 (0.0007) -[2023-10-15 02:38:33,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 21037056. Throughput: 0: 1727.9, 1: 1730.1. Samples: 5266570. Policy #0 lag: (min: 5.0, avg: 9.3, max: 37.0) -[2023-10-15 02:38:33,534][87330] Avg episode reward: [(0, '22.030'), (1, '21.750')] -[2023-10-15 02:38:33,842][88298] Updated weights for policy 0, policy_version 10250 (0.0008) -[2023-10-15 02:38:34,215][88298] Updated weights for policy 0, policy_version 10260 (0.0008) -[2023-10-15 02:38:34,582][88298] Updated weights for policy 0, policy_version 10270 (0.0008) -[2023-10-15 02:38:34,586][88300] Updated weights for policy 1, policy_version 10312 (0.0008) -[2023-10-15 02:38:34,943][88300] Updated weights for policy 1, policy_version 10322 (0.0009) -[2023-10-15 02:38:35,310][88300] Updated weights for policy 1, policy_version 10332 (0.0009) -[2023-10-15 02:38:38,520][88298] Updated weights for policy 0, policy_version 10280 (0.0009) -[2023-10-15 02:38:38,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 21102592. Throughput: 0: 1748.8, 1: 1736.7. Samples: 5287952. Policy #0 lag: (min: 5.0, avg: 9.3, max: 37.0) -[2023-10-15 02:38:38,535][87330] Avg episode reward: [(0, '22.030'), (1, '21.890')] -[2023-10-15 02:38:38,537][88033] Saving new best policy, reward=21.890! -[2023-10-15 02:38:38,892][88298] Updated weights for policy 0, policy_version 10290 (0.0007) -[2023-10-15 02:38:39,225][88300] Updated weights for policy 1, policy_version 10342 (0.0008) -[2023-10-15 02:38:39,269][88298] Updated weights for policy 0, policy_version 10300 (0.0008) -[2023-10-15 02:38:39,605][88300] Updated weights for policy 1, policy_version 10352 (0.0008) -[2023-10-15 02:38:39,978][88300] Updated weights for policy 1, policy_version 10362 (0.0007) -[2023-10-15 02:38:43,226][88298] Updated weights for policy 0, policy_version 10310 (0.0009) -[2023-10-15 02:38:43,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 21168128. Throughput: 0: 1760.9, 1: 1760.0. Samples: 5309714. Policy #0 lag: (min: 19.0, avg: 20.6, max: 47.0) -[2023-10-15 02:38:43,535][87330] Avg episode reward: [(0, '21.860'), (1, '21.910')] -[2023-10-15 02:38:43,602][88298] Updated weights for policy 0, policy_version 10320 (0.0007) -[2023-10-15 02:38:43,747][88300] Updated weights for policy 1, policy_version 10372 (0.0008) -[2023-10-15 02:38:43,978][88298] Updated weights for policy 0, policy_version 10330 (0.0008) -[2023-10-15 02:38:44,121][88300] Updated weights for policy 1, policy_version 10382 (0.0009) -[2023-10-15 02:38:44,493][88300] Updated weights for policy 1, policy_version 10392 (0.0009) -[2023-10-15 02:38:44,782][88033] Saving new best policy, reward=21.910! -[2023-10-15 02:38:47,652][88298] Updated weights for policy 0, policy_version 10340 (0.0010) -[2023-10-15 02:38:48,008][88298] Updated weights for policy 0, policy_version 10350 (0.0010) -[2023-10-15 02:38:48,389][88298] Updated weights for policy 0, policy_version 10360 (0.0010) -[2023-10-15 02:38:48,534][87330] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 21233664. Throughput: 0: 1732.7, 1: 1724.6. Samples: 5318926. Policy #0 lag: (min: 19.0, avg: 20.6, max: 47.0) -[2023-10-15 02:38:48,534][87330] Avg episode reward: [(0, '21.770'), (1, '21.940')] -[2023-10-15 02:38:48,561][88300] Updated weights for policy 1, policy_version 10402 (0.0009) -[2023-10-15 02:38:48,919][88300] Updated weights for policy 1, policy_version 10412 (0.0009) -[2023-10-15 02:38:49,281][88300] Updated weights for policy 1, policy_version 10422 (0.0010) -[2023-10-15 02:38:49,651][88033] Saving new best policy, reward=21.940! -[2023-10-15 02:38:49,655][88300] Updated weights for policy 1, policy_version 10432 (0.0011) -[2023-10-15 02:38:52,077][88298] Updated weights for policy 0, policy_version 10370 (0.0008) -[2023-10-15 02:38:52,446][88298] Updated weights for policy 0, policy_version 10380 (0.0008) -[2023-10-15 02:38:52,833][88298] Updated weights for policy 0, policy_version 10390 (0.0010) -[2023-10-15 02:38:53,207][88298] Updated weights for policy 0, policy_version 10400 (0.0007) -[2023-10-15 02:38:53,534][87330] Fps is (10 sec: 16384.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 21331968. Throughput: 0: 1753.8, 1: 1750.0. Samples: 5340560. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) -[2023-10-15 02:38:53,535][87330] Avg episode reward: [(0, '21.580'), (1, '21.770')] -[2023-10-15 02:38:53,562][88300] Updated weights for policy 1, policy_version 10442 (0.0008) -[2023-10-15 02:38:53,924][88300] Updated weights for policy 1, policy_version 10452 (0.0008) -[2023-10-15 02:38:54,297][88300] Updated weights for policy 1, policy_version 10462 (0.0007) -[2023-10-15 02:38:57,172][88298] Updated weights for policy 0, policy_version 10410 (0.0007) -[2023-10-15 02:38:57,535][88298] Updated weights for policy 0, policy_version 10420 (0.0009) -[2023-10-15 02:38:57,918][88298] Updated weights for policy 0, policy_version 10430 (0.0008) -[2023-10-15 02:38:58,234][88300] Updated weights for policy 1, policy_version 10472 (0.0009) -[2023-10-15 02:38:58,534][87330] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 21397504. Throughput: 0: 1721.8, 1: 1749.0. Samples: 5360706. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) -[2023-10-15 02:38:58,534][87330] Avg episode reward: [(0, '21.450'), (1, '21.770')] -[2023-10-15 02:38:58,543][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000010432_10682368.pth... -[2023-10-15 02:38:58,577][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000008800_9011200.pth -[2023-10-15 02:38:58,604][88300] Updated weights for policy 1, policy_version 10482 (0.0008) -[2023-10-15 02:38:58,974][88300] Updated weights for policy 1, policy_version 10492 (0.0010) -[2023-10-15 02:38:59,117][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000010496_10747904.pth... -[2023-10-15 02:38:59,146][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000008864_9076736.pth -[2023-10-15 02:39:01,885][88298] Updated weights for policy 0, policy_version 10440 (0.0007) -[2023-10-15 02:39:02,259][88298] Updated weights for policy 0, policy_version 10450 (0.0008) -[2023-10-15 02:39:02,638][88298] Updated weights for policy 0, policy_version 10460 (0.0009) -[2023-10-15 02:39:02,800][88300] Updated weights for policy 1, policy_version 10502 (0.0008) -[2023-10-15 02:39:03,177][88300] Updated weights for policy 1, policy_version 10512 (0.0008) -[2023-10-15 02:39:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 21463040. Throughput: 0: 1749.5, 1: 1741.9. Samples: 5371568. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) -[2023-10-15 02:39:03,535][87330] Avg episode reward: [(0, '21.350'), (1, '21.680')] -[2023-10-15 02:39:03,547][88300] Updated weights for policy 1, policy_version 10522 (0.0008) -[2023-10-15 02:39:06,678][88298] Updated weights for policy 0, policy_version 10470 (0.0008) -[2023-10-15 02:39:07,053][88298] Updated weights for policy 0, policy_version 10480 (0.0008) -[2023-10-15 02:39:07,382][88300] Updated weights for policy 1, policy_version 10532 (0.0009) -[2023-10-15 02:39:07,427][88298] Updated weights for policy 0, policy_version 10490 (0.0010) -[2023-10-15 02:39:07,740][88300] Updated weights for policy 1, policy_version 10542 (0.0009) -[2023-10-15 02:39:08,115][88300] Updated weights for policy 1, policy_version 10552 (0.0009) -[2023-10-15 02:39:08,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 21561344. Throughput: 0: 1739.9, 1: 1755.7. Samples: 5392842. Policy #0 lag: (min: 28.0, avg: 28.5, max: 45.0) -[2023-10-15 02:39:08,534][87330] Avg episode reward: [(0, '21.340'), (1, '21.640')] -[2023-10-15 02:39:11,373][88298] Updated weights for policy 0, policy_version 10500 (0.0009) -[2023-10-15 02:39:11,749][88298] Updated weights for policy 0, policy_version 10510 (0.0008) -[2023-10-15 02:39:12,097][88300] Updated weights for policy 1, policy_version 10562 (0.0008) -[2023-10-15 02:39:12,124][88298] Updated weights for policy 0, policy_version 10520 (0.0009) -[2023-10-15 02:39:12,458][88300] Updated weights for policy 1, policy_version 10572 (0.0007) -[2023-10-15 02:39:12,825][88300] Updated weights for policy 1, policy_version 10582 (0.0008) -[2023-10-15 02:39:13,188][88300] Updated weights for policy 1, policy_version 10592 (0.0008) -[2023-10-15 02:39:13,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 21626880. Throughput: 0: 1720.8, 1: 1727.1. Samples: 5412222. Policy #0 lag: (min: 28.0, avg: 28.5, max: 45.0) -[2023-10-15 02:39:13,535][87330] Avg episode reward: [(0, '21.520'), (1, '21.640')] -[2023-10-15 02:39:16,038][88298] Updated weights for policy 0, policy_version 10530 (0.0008) -[2023-10-15 02:39:16,413][88298] Updated weights for policy 0, policy_version 10540 (0.0010) -[2023-10-15 02:39:16,771][88298] Updated weights for policy 0, policy_version 10550 (0.0008) -[2023-10-15 02:39:17,019][88300] Updated weights for policy 1, policy_version 10602 (0.0008) -[2023-10-15 02:39:17,142][88298] Updated weights for policy 0, policy_version 10560 (0.0008) -[2023-10-15 02:39:17,394][88300] Updated weights for policy 1, policy_version 10612 (0.0008) -[2023-10-15 02:39:17,768][88300] Updated weights for policy 1, policy_version 10622 (0.0008) -[2023-10-15 02:39:18,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 21692416. Throughput: 0: 1751.2, 1: 1754.8. Samples: 5424340. Policy #0 lag: (min: 25.0, avg: 46.2, max: 57.0) -[2023-10-15 02:39:18,534][87330] Avg episode reward: [(0, '21.490'), (1, '21.690')] -[2023-10-15 02:39:21,085][88298] Updated weights for policy 0, policy_version 10570 (0.0007) -[2023-10-15 02:39:21,458][88298] Updated weights for policy 0, policy_version 10580 (0.0009) -[2023-10-15 02:39:21,723][88300] Updated weights for policy 1, policy_version 10632 (0.0009) -[2023-10-15 02:39:21,833][88298] Updated weights for policy 0, policy_version 10590 (0.0008) -[2023-10-15 02:39:22,101][88300] Updated weights for policy 1, policy_version 10642 (0.0009) -[2023-10-15 02:39:22,466][88300] Updated weights for policy 1, policy_version 10652 (0.0009) -[2023-10-15 02:39:23,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 21757952. Throughput: 0: 1723.7, 1: 1737.3. Samples: 5443696. Policy #0 lag: (min: 25.0, avg: 46.2, max: 57.0) -[2023-10-15 02:39:23,534][87330] Avg episode reward: [(0, '21.410'), (1, '21.740')] -[2023-10-15 02:39:25,862][88298] Updated weights for policy 0, policy_version 10600 (0.0010) -[2023-10-15 02:39:26,241][88298] Updated weights for policy 0, policy_version 10610 (0.0008) -[2023-10-15 02:39:26,420][88300] Updated weights for policy 1, policy_version 10662 (0.0009) -[2023-10-15 02:39:26,617][88298] Updated weights for policy 0, policy_version 10620 (0.0008) -[2023-10-15 02:39:26,820][88300] Updated weights for policy 1, policy_version 10672 (0.0008) -[2023-10-15 02:39:27,183][88300] Updated weights for policy 1, policy_version 10682 (0.0008) -[2023-10-15 02:39:28,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 21823488. Throughput: 0: 1710.9, 1: 1721.9. Samples: 5464192. Policy #0 lag: (min: 30.0, avg: 32.9, max: 62.0) -[2023-10-15 02:39:28,534][87330] Avg episode reward: [(0, '21.870'), (1, '21.770')] -[2023-10-15 02:39:30,342][88298] Updated weights for policy 0, policy_version 10630 (0.0008) -[2023-10-15 02:39:30,711][88298] Updated weights for policy 0, policy_version 10640 (0.0008) -[2023-10-15 02:39:30,920][88300] Updated weights for policy 1, policy_version 10692 (0.0007) -[2023-10-15 02:39:31,082][88298] Updated weights for policy 0, policy_version 10650 (0.0008) -[2023-10-15 02:39:31,292][88300] Updated weights for policy 1, policy_version 10702 (0.0008) -[2023-10-15 02:39:31,658][88300] Updated weights for policy 1, policy_version 10712 (0.0007) -[2023-10-15 02:39:33,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 21889024. Throughput: 0: 1732.4, 1: 1742.1. Samples: 5475278. Policy #0 lag: (min: 30.0, avg: 32.9, max: 62.0) -[2023-10-15 02:39:33,535][87330] Avg episode reward: [(0, '21.900'), (1, '21.850')] -[2023-10-15 02:39:34,976][88298] Updated weights for policy 0, policy_version 10660 (0.0009) -[2023-10-15 02:39:35,342][88298] Updated weights for policy 0, policy_version 10670 (0.0009) -[2023-10-15 02:39:35,646][88300] Updated weights for policy 1, policy_version 10722 (0.0007) -[2023-10-15 02:39:35,716][88298] Updated weights for policy 0, policy_version 10680 (0.0010) -[2023-10-15 02:39:36,013][88300] Updated weights for policy 1, policy_version 10732 (0.0008) -[2023-10-15 02:39:36,389][88300] Updated weights for policy 1, policy_version 10742 (0.0008) -[2023-10-15 02:39:36,755][88300] Updated weights for policy 1, policy_version 10752 (0.0007) -[2023-10-15 02:39:38,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 21954560. Throughput: 0: 1716.8, 1: 1721.6. Samples: 5495288. Policy #0 lag: (min: 30.0, avg: 32.9, max: 62.0) -[2023-10-15 02:39:38,534][87330] Avg episode reward: [(0, '21.850'), (1, '21.740')] -[2023-10-15 02:39:39,581][88298] Updated weights for policy 0, policy_version 10690 (0.0009) -[2023-10-15 02:39:39,945][88298] Updated weights for policy 0, policy_version 10700 (0.0009) -[2023-10-15 02:39:40,319][88298] Updated weights for policy 0, policy_version 10710 (0.0009) -[2023-10-15 02:39:40,596][88300] Updated weights for policy 1, policy_version 10762 (0.0007) -[2023-10-15 02:39:40,690][88298] Updated weights for policy 0, policy_version 10720 (0.0008) -[2023-10-15 02:39:40,964][88300] Updated weights for policy 1, policy_version 10772 (0.0008) -[2023-10-15 02:39:41,329][88300] Updated weights for policy 1, policy_version 10782 (0.0008) -[2023-10-15 02:39:43,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 22020096. Throughput: 0: 1749.9, 1: 1730.9. Samples: 5517342. Policy #0 lag: (min: 18.0, avg: 45.2, max: 48.0) -[2023-10-15 02:39:43,535][87330] Avg episode reward: [(0, '21.840'), (1, '21.770')] -[2023-10-15 02:39:44,384][88298] Updated weights for policy 0, policy_version 10730 (0.0010) -[2023-10-15 02:39:44,760][88298] Updated weights for policy 0, policy_version 10740 (0.0010) -[2023-10-15 02:39:45,134][88298] Updated weights for policy 0, policy_version 10750 (0.0008) -[2023-10-15 02:39:45,287][88300] Updated weights for policy 1, policy_version 10792 (0.0008) -[2023-10-15 02:39:45,664][88300] Updated weights for policy 1, policy_version 10802 (0.0008) -[2023-10-15 02:39:46,036][88300] Updated weights for policy 1, policy_version 10812 (0.0009) -[2023-10-15 02:39:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 22085632. Throughput: 0: 1723.9, 1: 1727.4. Samples: 5526874. Policy #0 lag: (min: 18.0, avg: 45.2, max: 48.0) -[2023-10-15 02:39:48,534][87330] Avg episode reward: [(0, '21.860'), (1, '21.680')] -[2023-10-15 02:39:49,008][88298] Updated weights for policy 0, policy_version 10760 (0.0008) -[2023-10-15 02:39:49,381][88298] Updated weights for policy 0, policy_version 10770 (0.0008) -[2023-10-15 02:39:49,756][88298] Updated weights for policy 0, policy_version 10780 (0.0008) -[2023-10-15 02:39:49,987][88300] Updated weights for policy 1, policy_version 10822 (0.0008) -[2023-10-15 02:39:50,362][88300] Updated weights for policy 1, policy_version 10832 (0.0007) -[2023-10-15 02:39:50,727][88300] Updated weights for policy 1, policy_version 10842 (0.0008) -[2023-10-15 02:39:53,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 22151168. Throughput: 0: 1729.6, 1: 1720.4. Samples: 5548092. Policy #0 lag: (min: 5.0, avg: 11.7, max: 37.0) -[2023-10-15 02:39:53,534][87330] Avg episode reward: [(0, '22.050'), (1, '21.730')] -[2023-10-15 02:39:53,863][88298] Updated weights for policy 0, policy_version 10790 (0.0008) -[2023-10-15 02:39:54,240][88298] Updated weights for policy 0, policy_version 10800 (0.0009) -[2023-10-15 02:39:54,444][88300] Updated weights for policy 1, policy_version 10852 (0.0008) -[2023-10-15 02:39:54,605][88298] Updated weights for policy 0, policy_version 10810 (0.0009) -[2023-10-15 02:39:54,811][88300] Updated weights for policy 1, policy_version 10862 (0.0008) -[2023-10-15 02:39:55,175][88300] Updated weights for policy 1, policy_version 10872 (0.0007) -[2023-10-15 02:39:58,511][88298] Updated weights for policy 0, policy_version 10820 (0.0007) -[2023-10-15 02:39:58,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 22216704. Throughput: 0: 1747.7, 1: 1748.9. Samples: 5569568. Policy #0 lag: (min: 5.0, avg: 11.7, max: 37.0) -[2023-10-15 02:39:58,534][87330] Avg episode reward: [(0, '21.940'), (1, '21.530')] -[2023-10-15 02:39:58,884][88298] Updated weights for policy 0, policy_version 10830 (0.0007) -[2023-10-15 02:39:59,180][88300] Updated weights for policy 1, policy_version 10882 (0.0008) -[2023-10-15 02:39:59,263][88298] Updated weights for policy 0, policy_version 10840 (0.0009) -[2023-10-15 02:39:59,539][88300] Updated weights for policy 1, policy_version 10892 (0.0007) -[2023-10-15 02:39:59,910][88300] Updated weights for policy 1, policy_version 10902 (0.0011) -[2023-10-15 02:40:00,280][88300] Updated weights for policy 1, policy_version 10912 (0.0011) -[2023-10-15 02:40:03,158][88298] Updated weights for policy 0, policy_version 10850 (0.0007) -[2023-10-15 02:40:03,517][88298] Updated weights for policy 0, policy_version 10860 (0.0007) -[2023-10-15 02:40:03,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 22282240. Throughput: 0: 1720.4, 1: 1719.5. Samples: 5579136. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:40:03,534][87330] Avg episode reward: [(0, '21.940'), (1, '21.540')] -[2023-10-15 02:40:03,890][88298] Updated weights for policy 0, policy_version 10870 (0.0009) -[2023-10-15 02:40:04,156][88300] Updated weights for policy 1, policy_version 10922 (0.0007) -[2023-10-15 02:40:04,257][88298] Updated weights for policy 0, policy_version 10880 (0.0009) -[2023-10-15 02:40:04,523][88300] Updated weights for policy 1, policy_version 10932 (0.0010) -[2023-10-15 02:40:04,895][88300] Updated weights for policy 1, policy_version 10942 (0.0009) -[2023-10-15 02:40:08,287][88298] Updated weights for policy 0, policy_version 10890 (0.0008) -[2023-10-15 02:40:08,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 22347776. Throughput: 0: 1750.4, 1: 1737.1. Samples: 5600632. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:40:08,534][87330] Avg episode reward: [(0, '21.980'), (1, '21.390')] -[2023-10-15 02:40:08,656][88298] Updated weights for policy 0, policy_version 10900 (0.0008) -[2023-10-15 02:40:08,877][88300] Updated weights for policy 1, policy_version 10952 (0.0007) -[2023-10-15 02:40:09,029][88298] Updated weights for policy 0, policy_version 10910 (0.0008) -[2023-10-15 02:40:09,253][88300] Updated weights for policy 1, policy_version 10962 (0.0009) -[2023-10-15 02:40:09,626][88300] Updated weights for policy 1, policy_version 10972 (0.0008) -[2023-10-15 02:40:12,837][88298] Updated weights for policy 0, policy_version 10920 (0.0009) -[2023-10-15 02:40:13,207][88298] Updated weights for policy 0, policy_version 10930 (0.0008) -[2023-10-15 02:40:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 22413312. Throughput: 0: 1752.0, 1: 1755.3. Samples: 5622020. Policy #0 lag: (min: 2.0, avg: 7.1, max: 34.0) -[2023-10-15 02:40:13,534][87330] Avg episode reward: [(0, '21.760'), (1, '21.430')] -[2023-10-15 02:40:13,580][88298] Updated weights for policy 0, policy_version 10940 (0.0010) -[2023-10-15 02:40:13,644][88300] Updated weights for policy 1, policy_version 10982 (0.0007) -[2023-10-15 02:40:14,021][88300] Updated weights for policy 1, policy_version 10992 (0.0010) -[2023-10-15 02:40:14,384][88300] Updated weights for policy 1, policy_version 11002 (0.0009) -[2023-10-15 02:40:17,452][88298] Updated weights for policy 0, policy_version 10950 (0.0009) -[2023-10-15 02:40:17,827][88298] Updated weights for policy 0, policy_version 10960 (0.0010) -[2023-10-15 02:40:18,199][88298] Updated weights for policy 0, policy_version 10970 (0.0010) -[2023-10-15 02:40:18,214][88300] Updated weights for policy 1, policy_version 11012 (0.0007) -[2023-10-15 02:40:18,534][87330] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 22511616. Throughput: 0: 1740.8, 1: 1734.4. Samples: 5631658. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:40:18,534][87330] Avg episode reward: [(0, '21.720'), (1, '21.520')] -[2023-10-15 02:40:18,578][88300] Updated weights for policy 1, policy_version 11022 (0.0009) -[2023-10-15 02:40:18,954][88300] Updated weights for policy 1, policy_version 11032 (0.0008) -[2023-10-15 02:40:22,010][88298] Updated weights for policy 0, policy_version 10980 (0.0007) -[2023-10-15 02:40:22,376][88298] Updated weights for policy 0, policy_version 10990 (0.0009) -[2023-10-15 02:40:22,744][88298] Updated weights for policy 0, policy_version 11000 (0.0010) -[2023-10-15 02:40:22,926][88300] Updated weights for policy 1, policy_version 11042 (0.0010) -[2023-10-15 02:40:23,290][88300] Updated weights for policy 1, policy_version 11052 (0.0007) -[2023-10-15 02:40:23,534][87330] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 22577152. Throughput: 0: 1753.8, 1: 1750.9. Samples: 5653000. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:40:23,534][87330] Avg episode reward: [(0, '21.740'), (1, '21.410')] -[2023-10-15 02:40:23,658][88300] Updated weights for policy 1, policy_version 11062 (0.0009) -[2023-10-15 02:40:24,020][88300] Updated weights for policy 1, policy_version 11072 (0.0007) -[2023-10-15 02:40:26,608][88298] Updated weights for policy 0, policy_version 11010 (0.0009) -[2023-10-15 02:40:26,972][88298] Updated weights for policy 0, policy_version 11020 (0.0010) -[2023-10-15 02:40:27,345][88298] Updated weights for policy 0, policy_version 11030 (0.0009) -[2023-10-15 02:40:27,722][88298] Updated weights for policy 0, policy_version 11040 (0.0009) -[2023-10-15 02:40:27,775][88300] Updated weights for policy 1, policy_version 11082 (0.0010) -[2023-10-15 02:40:28,148][88300] Updated weights for policy 1, policy_version 11092 (0.0007) -[2023-10-15 02:40:28,522][88300] Updated weights for policy 1, policy_version 11102 (0.0007) -[2023-10-15 02:40:28,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 22642688. Throughput: 0: 1718.6, 1: 1733.1. Samples: 5672668. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:40:28,534][87330] Avg episode reward: [(0, '21.770'), (1, '21.620')] -[2023-10-15 02:40:31,569][88298] Updated weights for policy 0, policy_version 11050 (0.0009) -[2023-10-15 02:40:31,936][88298] Updated weights for policy 0, policy_version 11060 (0.0010) -[2023-10-15 02:40:32,314][88298] Updated weights for policy 0, policy_version 11070 (0.0009) -[2023-10-15 02:40:32,378][88300] Updated weights for policy 1, policy_version 11112 (0.0008) -[2023-10-15 02:40:32,748][88300] Updated weights for policy 1, policy_version 11122 (0.0007) -[2023-10-15 02:40:33,112][88300] Updated weights for policy 1, policy_version 11132 (0.0007) -[2023-10-15 02:40:33,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 22740992. Throughput: 0: 1750.8, 1: 1751.1. Samples: 5684458. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:40:33,534][87330] Avg episode reward: [(0, '21.870'), (1, '21.430')] -[2023-10-15 02:40:36,183][88298] Updated weights for policy 0, policy_version 11080 (0.0008) -[2023-10-15 02:40:36,552][88298] Updated weights for policy 0, policy_version 11090 (0.0011) -[2023-10-15 02:40:36,930][88298] Updated weights for policy 0, policy_version 11100 (0.0008) -[2023-10-15 02:40:37,060][88300] Updated weights for policy 1, policy_version 11142 (0.0007) -[2023-10-15 02:40:37,419][88300] Updated weights for policy 1, policy_version 11152 (0.0010) -[2023-10-15 02:40:37,798][88300] Updated weights for policy 1, policy_version 11162 (0.0010) -[2023-10-15 02:40:38,534][87330] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 22806528. Throughput: 0: 1733.5, 1: 1744.8. Samples: 5704616. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:40:38,535][87330] Avg episode reward: [(0, '21.990'), (1, '21.670')] -[2023-10-15 02:40:40,830][88298] Updated weights for policy 0, policy_version 11110 (0.0008) -[2023-10-15 02:40:41,196][88298] Updated weights for policy 0, policy_version 11120 (0.0011) -[2023-10-15 02:40:41,578][88298] Updated weights for policy 0, policy_version 11130 (0.0010) -[2023-10-15 02:40:41,953][88300] Updated weights for policy 1, policy_version 11172 (0.0008) -[2023-10-15 02:40:42,322][88300] Updated weights for policy 1, policy_version 11182 (0.0007) -[2023-10-15 02:40:42,693][88300] Updated weights for policy 1, policy_version 11192 (0.0009) -[2023-10-15 02:40:43,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 22872064. Throughput: 0: 1727.8, 1: 1717.4. Samples: 5724604. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:40:43,535][87330] Avg episode reward: [(0, '22.010'), (1, '21.680')] -[2023-10-15 02:40:45,497][88298] Updated weights for policy 0, policy_version 11140 (0.0008) -[2023-10-15 02:40:45,869][88298] Updated weights for policy 0, policy_version 11150 (0.0007) -[2023-10-15 02:40:46,250][88298] Updated weights for policy 0, policy_version 11160 (0.0009) -[2023-10-15 02:40:46,729][88300] Updated weights for policy 1, policy_version 11202 (0.0009) -[2023-10-15 02:40:47,088][88300] Updated weights for policy 1, policy_version 11212 (0.0010) -[2023-10-15 02:40:47,451][88300] Updated weights for policy 1, policy_version 11222 (0.0008) -[2023-10-15 02:40:47,821][88300] Updated weights for policy 1, policy_version 11232 (0.0009) -[2023-10-15 02:40:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 22937600. Throughput: 0: 1746.8, 1: 1746.8. Samples: 5736344. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-15 02:40:48,535][87330] Avg episode reward: [(0, '22.240'), (1, '21.670')] -[2023-10-15 02:40:48,536][87905] Saving new best policy, reward=22.240! -[2023-10-15 02:40:50,249][88298] Updated weights for policy 0, policy_version 11170 (0.0007) -[2023-10-15 02:40:50,628][88298] Updated weights for policy 0, policy_version 11180 (0.0008) -[2023-10-15 02:40:51,003][88298] Updated weights for policy 0, policy_version 11190 (0.0009) -[2023-10-15 02:40:51,379][88298] Updated weights for policy 0, policy_version 11200 (0.0010) -[2023-10-15 02:40:51,706][88300] Updated weights for policy 1, policy_version 11242 (0.0010) -[2023-10-15 02:40:52,072][88300] Updated weights for policy 1, policy_version 11252 (0.0010) -[2023-10-15 02:40:52,447][88300] Updated weights for policy 1, policy_version 11262 (0.0007) -[2023-10-15 02:40:53,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 23003136. Throughput: 0: 1725.0, 1: 1727.9. Samples: 5756012. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-15 02:40:53,536][87330] Avg episode reward: [(0, '22.250'), (1, '21.790')] -[2023-10-15 02:40:53,537][87905] Saving new best policy, reward=22.250! -[2023-10-15 02:40:55,442][88298] Updated weights for policy 0, policy_version 11210 (0.0007) -[2023-10-15 02:40:55,822][88298] Updated weights for policy 0, policy_version 11220 (0.0008) -[2023-10-15 02:40:56,194][88298] Updated weights for policy 0, policy_version 11230 (0.0009) -[2023-10-15 02:40:56,412][88300] Updated weights for policy 1, policy_version 11272 (0.0009) -[2023-10-15 02:40:56,776][88300] Updated weights for policy 1, policy_version 11282 (0.0008) -[2023-10-15 02:40:57,146][88300] Updated weights for policy 1, policy_version 11292 (0.0009) -[2023-10-15 02:40:58,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 23068672. Throughput: 0: 1734.0, 1: 1712.8. Samples: 5777126. Policy #0 lag: (min: 17.0, avg: 26.1, max: 49.0) -[2023-10-15 02:40:58,535][87330] Avg episode reward: [(0, '22.130'), (1, '21.760')] -[2023-10-15 02:40:58,548][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000011296_11567104.pth... -[2023-10-15 02:40:58,548][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000011232_11501568.pth... -[2023-10-15 02:40:58,584][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000009600_9830400.pth -[2023-10-15 02:40:58,586][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000009664_9895936.pth -[2023-10-15 02:41:00,105][88298] Updated weights for policy 0, policy_version 11240 (0.0007) -[2023-10-15 02:41:00,477][88298] Updated weights for policy 0, policy_version 11250 (0.0007) -[2023-10-15 02:41:00,848][88298] Updated weights for policy 0, policy_version 11260 (0.0007) -[2023-10-15 02:41:01,067][88300] Updated weights for policy 1, policy_version 11302 (0.0008) -[2023-10-15 02:41:01,454][88300] Updated weights for policy 1, policy_version 11312 (0.0008) -[2023-10-15 02:41:01,822][88300] Updated weights for policy 1, policy_version 11322 (0.0010) -[2023-10-15 02:41:03,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 23134208. Throughput: 0: 1732.3, 1: 1737.4. Samples: 5787792. Policy #0 lag: (min: 17.0, avg: 26.1, max: 49.0) -[2023-10-15 02:41:03,535][87330] Avg episode reward: [(0, '22.100'), (1, '21.930')] -[2023-10-15 02:41:04,637][88298] Updated weights for policy 0, policy_version 11270 (0.0008) -[2023-10-15 02:41:05,018][88298] Updated weights for policy 0, policy_version 11280 (0.0009) -[2023-10-15 02:41:05,381][88298] Updated weights for policy 0, policy_version 11290 (0.0007) -[2023-10-15 02:41:05,557][88300] Updated weights for policy 1, policy_version 11332 (0.0007) -[2023-10-15 02:41:05,924][88300] Updated weights for policy 1, policy_version 11342 (0.0008) -[2023-10-15 02:41:06,293][88300] Updated weights for policy 1, policy_version 11352 (0.0008) -[2023-10-15 02:41:08,534][87330] Fps is (10 sec: 13107.6, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 23199744. Throughput: 0: 1725.9, 1: 1720.7. Samples: 5808098. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:41:08,534][87330] Avg episode reward: [(0, '22.140'), (1, '21.990')] -[2023-10-15 02:41:08,535][88033] Saving new best policy, reward=21.990! -[2023-10-15 02:41:09,241][88298] Updated weights for policy 0, policy_version 11300 (0.0007) -[2023-10-15 02:41:09,645][88298] Updated weights for policy 0, policy_version 11310 (0.0009) -[2023-10-15 02:41:10,007][88298] Updated weights for policy 0, policy_version 11320 (0.0008) -[2023-10-15 02:41:10,048][88300] Updated weights for policy 1, policy_version 11362 (0.0009) -[2023-10-15 02:41:10,431][88300] Updated weights for policy 1, policy_version 11372 (0.0007) -[2023-10-15 02:41:10,793][88300] Updated weights for policy 1, policy_version 11382 (0.0008) -[2023-10-15 02:41:11,154][88300] Updated weights for policy 1, policy_version 11392 (0.0008) -[2023-10-15 02:41:13,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 23265280. Throughput: 0: 1753.9, 1: 1735.2. Samples: 5829680. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:41:13,535][87330] Avg episode reward: [(0, '22.110'), (1, '21.980')] -[2023-10-15 02:41:13,832][88298] Updated weights for policy 0, policy_version 11330 (0.0009) -[2023-10-15 02:41:14,198][88298] Updated weights for policy 0, policy_version 11340 (0.0007) -[2023-10-15 02:41:14,582][88298] Updated weights for policy 0, policy_version 11350 (0.0009) -[2023-10-15 02:41:14,949][88298] Updated weights for policy 0, policy_version 11360 (0.0009) -[2023-10-15 02:41:15,109][88300] Updated weights for policy 1, policy_version 11402 (0.0008) -[2023-10-15 02:41:15,477][88300] Updated weights for policy 1, policy_version 11412 (0.0009) -[2023-10-15 02:41:15,851][88300] Updated weights for policy 1, policy_version 11422 (0.0011) -[2023-10-15 02:41:18,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 23330816. Throughput: 0: 1723.8, 1: 1714.4. Samples: 5839176. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:41:18,534][87330] Avg episode reward: [(0, '21.960'), (1, '21.530')] -[2023-10-15 02:41:18,801][88298] Updated weights for policy 0, policy_version 11370 (0.0009) -[2023-10-15 02:41:19,167][88298] Updated weights for policy 0, policy_version 11380 (0.0008) -[2023-10-15 02:41:19,544][88298] Updated weights for policy 0, policy_version 11390 (0.0007) -[2023-10-15 02:41:19,788][88300] Updated weights for policy 1, policy_version 11432 (0.0010) -[2023-10-15 02:41:20,167][88300] Updated weights for policy 1, policy_version 11442 (0.0008) -[2023-10-15 02:41:20,542][88300] Updated weights for policy 1, policy_version 11452 (0.0008) -[2023-10-15 02:41:23,512][88298] Updated weights for policy 0, policy_version 11400 (0.0007) -[2023-10-15 02:41:23,534][87330] Fps is (10 sec: 13107.8, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 23396352. Throughput: 0: 1745.0, 1: 1725.3. Samples: 5860782. Policy #0 lag: (min: 31.0, avg: 32.6, max: 58.0) -[2023-10-15 02:41:23,534][87330] Avg episode reward: [(0, '21.990'), (1, '21.590')] -[2023-10-15 02:41:23,880][88298] Updated weights for policy 0, policy_version 11410 (0.0008) -[2023-10-15 02:41:24,246][88298] Updated weights for policy 0, policy_version 11420 (0.0008) -[2023-10-15 02:41:24,541][88300] Updated weights for policy 1, policy_version 11462 (0.0009) -[2023-10-15 02:41:24,910][88300] Updated weights for policy 1, policy_version 11472 (0.0009) -[2023-10-15 02:41:25,282][88300] Updated weights for policy 1, policy_version 11482 (0.0009) -[2023-10-15 02:41:28,167][88298] Updated weights for policy 0, policy_version 11430 (0.0007) -[2023-10-15 02:41:28,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 23461888. Throughput: 0: 1750.6, 1: 1755.5. Samples: 5882378. Policy #0 lag: (min: 31.0, avg: 32.6, max: 58.0) -[2023-10-15 02:41:28,534][87330] Avg episode reward: [(0, '21.870'), (1, '21.580')] -[2023-10-15 02:41:28,536][88298] Updated weights for policy 0, policy_version 11440 (0.0011) -[2023-10-15 02:41:28,906][88298] Updated weights for policy 0, policy_version 11450 (0.0009) -[2023-10-15 02:41:29,013][88300] Updated weights for policy 1, policy_version 11492 (0.0008) -[2023-10-15 02:41:29,393][88300] Updated weights for policy 1, policy_version 11502 (0.0009) -[2023-10-15 02:41:29,748][88300] Updated weights for policy 1, policy_version 11512 (0.0010) -[2023-10-15 02:41:32,754][88298] Updated weights for policy 0, policy_version 11460 (0.0008) -[2023-10-15 02:41:33,125][88298] Updated weights for policy 0, policy_version 11470 (0.0007) -[2023-10-15 02:41:33,500][88298] Updated weights for policy 0, policy_version 11480 (0.0008) -[2023-10-15 02:41:33,533][88300] Updated weights for policy 1, policy_version 11522 (0.0010) -[2023-10-15 02:41:33,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 23527424. Throughput: 0: 1728.2, 1: 1725.1. Samples: 5891740. Policy #0 lag: (min: 31.0, avg: 32.6, max: 58.0) -[2023-10-15 02:41:33,534][87330] Avg episode reward: [(0, '21.670'), (1, '21.530')] -[2023-10-15 02:41:33,901][88300] Updated weights for policy 1, policy_version 11532 (0.0008) -[2023-10-15 02:41:34,275][88300] Updated weights for policy 1, policy_version 11542 (0.0008) -[2023-10-15 02:41:34,638][88300] Updated weights for policy 1, policy_version 11552 (0.0008) -[2023-10-15 02:41:37,371][88298] Updated weights for policy 0, policy_version 11490 (0.0008) -[2023-10-15 02:41:37,753][88298] Updated weights for policy 0, policy_version 11500 (0.0008) -[2023-10-15 02:41:38,124][88298] Updated weights for policy 0, policy_version 11510 (0.0009) -[2023-10-15 02:41:38,485][88300] Updated weights for policy 1, policy_version 11562 (0.0009) -[2023-10-15 02:41:38,486][88298] Updated weights for policy 0, policy_version 11520 (0.0008) -[2023-10-15 02:41:38,534][87330] Fps is (10 sec: 16383.6, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 23625728. Throughput: 0: 1752.9, 1: 1748.2. Samples: 5913562. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:41:38,535][87330] Avg episode reward: [(0, '21.600'), (1, '21.560')] -[2023-10-15 02:41:38,851][88300] Updated weights for policy 1, policy_version 11572 (0.0010) -[2023-10-15 02:41:39,215][88300] Updated weights for policy 1, policy_version 11582 (0.0011) -[2023-10-15 02:41:42,430][88298] Updated weights for policy 0, policy_version 11530 (0.0007) -[2023-10-15 02:41:42,801][88298] Updated weights for policy 0, policy_version 11540 (0.0008) -[2023-10-15 02:41:43,181][88298] Updated weights for policy 0, policy_version 11550 (0.0008) -[2023-10-15 02:41:43,215][88300] Updated weights for policy 1, policy_version 11592 (0.0009) -[2023-10-15 02:41:43,534][87330] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 23691264. Throughput: 0: 1728.0, 1: 1750.9. Samples: 5933676. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:41:43,535][87330] Avg episode reward: [(0, '21.620'), (1, '21.500')] -[2023-10-15 02:41:43,583][88300] Updated weights for policy 1, policy_version 11602 (0.0010) -[2023-10-15 02:41:43,949][88300] Updated weights for policy 1, policy_version 11612 (0.0008) -[2023-10-15 02:41:47,246][88298] Updated weights for policy 0, policy_version 11560 (0.0010) -[2023-10-15 02:41:47,619][88298] Updated weights for policy 0, policy_version 11570 (0.0010) -[2023-10-15 02:41:47,982][88298] Updated weights for policy 0, policy_version 11580 (0.0011) -[2023-10-15 02:41:48,027][88300] Updated weights for policy 1, policy_version 11622 (0.0008) -[2023-10-15 02:41:48,427][88300] Updated weights for policy 1, policy_version 11632 (0.0010) -[2023-10-15 02:41:48,534][87330] Fps is (10 sec: 13107.7, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 23756800. Throughput: 0: 1738.1, 1: 1734.7. Samples: 5944070. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:41:48,534][87330] Avg episode reward: [(0, '21.570'), (1, '21.850')] -[2023-10-15 02:41:48,795][88300] Updated weights for policy 1, policy_version 11642 (0.0008) -[2023-10-15 02:41:51,788][88298] Updated weights for policy 0, policy_version 11590 (0.0008) -[2023-10-15 02:41:52,165][88298] Updated weights for policy 0, policy_version 11600 (0.0007) -[2023-10-15 02:41:52,540][88298] Updated weights for policy 0, policy_version 11610 (0.0007) -[2023-10-15 02:41:52,636][88300] Updated weights for policy 1, policy_version 11652 (0.0009) -[2023-10-15 02:41:53,000][88300] Updated weights for policy 1, policy_version 11662 (0.0008) -[2023-10-15 02:41:53,372][88300] Updated weights for policy 1, policy_version 11672 (0.0007) -[2023-10-15 02:41:53,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 23822336. Throughput: 0: 1736.1, 1: 1754.1. Samples: 5965156. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:41:53,534][87330] Avg episode reward: [(0, '21.790'), (1, '21.930')] -[2023-10-15 02:41:56,400][88298] Updated weights for policy 0, policy_version 11620 (0.0008) -[2023-10-15 02:41:56,773][88298] Updated weights for policy 0, policy_version 11630 (0.0010) -[2023-10-15 02:41:57,138][88298] Updated weights for policy 0, policy_version 11640 (0.0009) -[2023-10-15 02:41:57,202][88300] Updated weights for policy 1, policy_version 11682 (0.0007) -[2023-10-15 02:41:57,565][88300] Updated weights for policy 1, policy_version 11692 (0.0009) -[2023-10-15 02:41:57,940][88300] Updated weights for policy 1, policy_version 11702 (0.0009) -[2023-10-15 02:41:58,304][88300] Updated weights for policy 1, policy_version 11712 (0.0009) -[2023-10-15 02:41:58,534][87330] Fps is (10 sec: 16383.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 23920640. Throughput: 0: 1715.8, 1: 1727.0. Samples: 5984608. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:41:58,535][87330] Avg episode reward: [(0, '21.760'), (1, '21.960')] -[2023-10-15 02:42:01,184][88298] Updated weights for policy 0, policy_version 11650 (0.0009) -[2023-10-15 02:42:01,552][88298] Updated weights for policy 0, policy_version 11660 (0.0010) -[2023-10-15 02:42:01,923][88298] Updated weights for policy 0, policy_version 11670 (0.0010) -[2023-10-15 02:42:02,226][88300] Updated weights for policy 1, policy_version 11722 (0.0008) -[2023-10-15 02:42:02,297][88298] Updated weights for policy 0, policy_version 11680 (0.0007) -[2023-10-15 02:42:02,585][88300] Updated weights for policy 1, policy_version 11732 (0.0010) -[2023-10-15 02:42:02,957][88300] Updated weights for policy 1, policy_version 11742 (0.0009) -[2023-10-15 02:42:03,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 23986176. Throughput: 0: 1746.6, 1: 1753.5. Samples: 5996680. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:42:03,534][87330] Avg episode reward: [(0, '22.130'), (1, '21.960')] -[2023-10-15 02:42:06,107][88298] Updated weights for policy 0, policy_version 11690 (0.0008) -[2023-10-15 02:42:06,476][88298] Updated weights for policy 0, policy_version 11700 (0.0007) -[2023-10-15 02:42:06,851][88298] Updated weights for policy 0, policy_version 11710 (0.0010) -[2023-10-15 02:42:06,947][88300] Updated weights for policy 1, policy_version 11752 (0.0009) -[2023-10-15 02:42:07,317][88300] Updated weights for policy 1, policy_version 11762 (0.0007) -[2023-10-15 02:42:07,684][88300] Updated weights for policy 1, policy_version 11772 (0.0007) -[2023-10-15 02:42:08,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 24051712. Throughput: 0: 1722.3, 1: 1737.5. Samples: 6016470. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:42:08,535][87330] Avg episode reward: [(0, '22.100'), (1, '21.950')] -[2023-10-15 02:42:10,832][88298] Updated weights for policy 0, policy_version 11720 (0.0010) -[2023-10-15 02:42:11,204][88298] Updated weights for policy 0, policy_version 11730 (0.0009) -[2023-10-15 02:42:11,496][88300] Updated weights for policy 1, policy_version 11782 (0.0007) -[2023-10-15 02:42:11,569][88298] Updated weights for policy 0, policy_version 11740 (0.0008) -[2023-10-15 02:42:11,870][88300] Updated weights for policy 1, policy_version 11792 (0.0007) -[2023-10-15 02:42:12,234][88300] Updated weights for policy 1, policy_version 11802 (0.0009) -[2023-10-15 02:42:13,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 24117248. Throughput: 0: 1719.6, 1: 1718.0. Samples: 6037072. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:42:13,535][87330] Avg episode reward: [(0, '22.070'), (1, '21.880')] -[2023-10-15 02:42:15,414][88298] Updated weights for policy 0, policy_version 11750 (0.0009) -[2023-10-15 02:42:15,789][88298] Updated weights for policy 0, policy_version 11760 (0.0009) -[2023-10-15 02:42:16,098][88300] Updated weights for policy 1, policy_version 11812 (0.0007) -[2023-10-15 02:42:16,158][88298] Updated weights for policy 0, policy_version 11770 (0.0009) -[2023-10-15 02:42:16,460][88300] Updated weights for policy 1, policy_version 11822 (0.0007) -[2023-10-15 02:42:16,826][88300] Updated weights for policy 1, policy_version 11832 (0.0008) -[2023-10-15 02:42:18,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 24182784. Throughput: 0: 1735.0, 1: 1745.1. Samples: 6048346. Policy #0 lag: (min: 9.0, avg: 23.0, max: 41.0) -[2023-10-15 02:42:18,534][87330] Avg episode reward: [(0, '22.030'), (1, '21.930')] -[2023-10-15 02:42:20,095][88298] Updated weights for policy 0, policy_version 11780 (0.0009) -[2023-10-15 02:42:20,476][88298] Updated weights for policy 0, policy_version 11790 (0.0008) -[2023-10-15 02:42:20,711][88300] Updated weights for policy 1, policy_version 11842 (0.0008) -[2023-10-15 02:42:20,844][88298] Updated weights for policy 0, policy_version 11800 (0.0007) -[2023-10-15 02:42:21,073][88300] Updated weights for policy 1, policy_version 11852 (0.0008) -[2023-10-15 02:42:21,439][88300] Updated weights for policy 1, policy_version 11862 (0.0009) -[2023-10-15 02:42:21,807][88300] Updated weights for policy 1, policy_version 11872 (0.0007) -[2023-10-15 02:42:23,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 24248320. Throughput: 0: 1715.5, 1: 1720.1. Samples: 6068166. Policy #0 lag: (min: 9.0, avg: 23.0, max: 41.0) -[2023-10-15 02:42:23,535][87330] Avg episode reward: [(0, '22.010'), (1, '21.970')] -[2023-10-15 02:42:24,666][88298] Updated weights for policy 0, policy_version 11810 (0.0008) -[2023-10-15 02:42:25,040][88298] Updated weights for policy 0, policy_version 11820 (0.0009) -[2023-10-15 02:42:25,413][88298] Updated weights for policy 0, policy_version 11830 (0.0010) -[2023-10-15 02:42:25,669][88300] Updated weights for policy 1, policy_version 11882 (0.0007) -[2023-10-15 02:42:25,791][88298] Updated weights for policy 0, policy_version 11840 (0.0009) -[2023-10-15 02:42:26,036][88300] Updated weights for policy 1, policy_version 11892 (0.0009) -[2023-10-15 02:42:26,408][88300] Updated weights for policy 1, policy_version 11902 (0.0007) -[2023-10-15 02:42:28,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 24313856. Throughput: 0: 1743.7, 1: 1727.6. Samples: 6089884. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:42:28,534][87330] Avg episode reward: [(0, '22.050'), (1, '21.960')] -[2023-10-15 02:42:29,549][88298] Updated weights for policy 0, policy_version 11850 (0.0009) -[2023-10-15 02:42:29,907][88298] Updated weights for policy 0, policy_version 11860 (0.0010) -[2023-10-15 02:42:30,237][88300] Updated weights for policy 1, policy_version 11912 (0.0009) -[2023-10-15 02:42:30,272][88298] Updated weights for policy 0, policy_version 11870 (0.0009) -[2023-10-15 02:42:30,614][88300] Updated weights for policy 1, policy_version 11922 (0.0010) -[2023-10-15 02:42:30,972][88300] Updated weights for policy 1, policy_version 11932 (0.0007) -[2023-10-15 02:42:33,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 24379392. Throughput: 0: 1729.7, 1: 1724.0. Samples: 6099488. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:42:33,534][87330] Avg episode reward: [(0, '22.060'), (1, '21.930')] -[2023-10-15 02:42:34,309][88298] Updated weights for policy 0, policy_version 11880 (0.0008) -[2023-10-15 02:42:34,689][88298] Updated weights for policy 0, policy_version 11890 (0.0008) -[2023-10-15 02:42:35,027][88300] Updated weights for policy 1, policy_version 11942 (0.0007) -[2023-10-15 02:42:35,057][88298] Updated weights for policy 0, policy_version 11900 (0.0008) -[2023-10-15 02:42:35,395][88300] Updated weights for policy 1, policy_version 11952 (0.0010) -[2023-10-15 02:42:35,763][88300] Updated weights for policy 1, policy_version 11962 (0.0008) -[2023-10-15 02:42:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 24444928. Throughput: 0: 1732.5, 1: 1725.7. Samples: 6120776. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:42:38,534][87330] Avg episode reward: [(0, '22.140'), (1, '21.950')] -[2023-10-15 02:42:39,094][88298] Updated weights for policy 0, policy_version 11910 (0.0008) -[2023-10-15 02:42:39,459][88298] Updated weights for policy 0, policy_version 11920 (0.0007) -[2023-10-15 02:42:39,758][88300] Updated weights for policy 1, policy_version 11972 (0.0007) -[2023-10-15 02:42:39,819][88298] Updated weights for policy 0, policy_version 11930 (0.0008) -[2023-10-15 02:42:40,122][88300] Updated weights for policy 1, policy_version 11982 (0.0008) -[2023-10-15 02:42:40,495][88300] Updated weights for policy 1, policy_version 11992 (0.0008) -[2023-10-15 02:42:43,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 24510464. Throughput: 0: 1753.0, 1: 1744.4. Samples: 6141988. Policy #0 lag: (min: 1.0, avg: 13.3, max: 33.0) -[2023-10-15 02:42:43,534][87330] Avg episode reward: [(0, '22.290'), (1, '22.050')] -[2023-10-15 02:42:43,543][88033] Saving new best policy, reward=22.050! -[2023-10-15 02:42:43,649][88298] Updated weights for policy 0, policy_version 11940 (0.0007) -[2023-10-15 02:42:44,032][88298] Updated weights for policy 0, policy_version 11950 (0.0007) -[2023-10-15 02:42:44,406][88298] Updated weights for policy 0, policy_version 11960 (0.0007) -[2023-10-15 02:42:44,430][88300] Updated weights for policy 1, policy_version 12002 (0.0009) -[2023-10-15 02:42:44,699][87905] Saving new best policy, reward=22.290! -[2023-10-15 02:42:44,799][88300] Updated weights for policy 1, policy_version 12012 (0.0008) -[2023-10-15 02:42:45,163][88300] Updated weights for policy 1, policy_version 12022 (0.0007) -[2023-10-15 02:42:45,526][88300] Updated weights for policy 1, policy_version 12032 (0.0007) -[2023-10-15 02:42:48,334][88298] Updated weights for policy 0, policy_version 11970 (0.0008) -[2023-10-15 02:42:48,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 24576000. Throughput: 0: 1716.6, 1: 1723.2. Samples: 6151468. Policy #0 lag: (min: 1.0, avg: 13.3, max: 33.0) -[2023-10-15 02:42:48,535][87330] Avg episode reward: [(0, '22.280'), (1, '22.030')] -[2023-10-15 02:42:48,706][88298] Updated weights for policy 0, policy_version 11980 (0.0009) -[2023-10-15 02:42:49,081][88298] Updated weights for policy 0, policy_version 11990 (0.0009) -[2023-10-15 02:42:49,376][88300] Updated weights for policy 1, policy_version 12042 (0.0007) -[2023-10-15 02:42:49,452][88298] Updated weights for policy 0, policy_version 12000 (0.0008) -[2023-10-15 02:42:49,736][88300] Updated weights for policy 1, policy_version 12052 (0.0010) -[2023-10-15 02:42:50,100][88300] Updated weights for policy 1, policy_version 12062 (0.0008) -[2023-10-15 02:42:53,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 24641536. Throughput: 0: 1738.9, 1: 1740.6. Samples: 6173048. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:42:53,534][87330] Avg episode reward: [(0, '22.310'), (1, '22.050')] -[2023-10-15 02:42:53,552][88298] Updated weights for policy 0, policy_version 12010 (0.0008) -[2023-10-15 02:42:53,921][88298] Updated weights for policy 0, policy_version 12020 (0.0008) -[2023-10-15 02:42:54,098][88300] Updated weights for policy 1, policy_version 12072 (0.0007) -[2023-10-15 02:42:54,284][88298] Updated weights for policy 0, policy_version 12030 (0.0008) -[2023-10-15 02:42:54,355][87905] Saving new best policy, reward=22.310! -[2023-10-15 02:42:54,474][88300] Updated weights for policy 1, policy_version 12082 (0.0010) -[2023-10-15 02:42:54,847][88300] Updated weights for policy 1, policy_version 12092 (0.0010) -[2023-10-15 02:42:58,227][88298] Updated weights for policy 0, policy_version 12040 (0.0007) -[2023-10-15 02:42:58,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 24707072. Throughput: 0: 1740.0, 1: 1759.2. Samples: 6194534. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:42:58,534][87330] Avg episode reward: [(0, '22.330'), (1, '22.030')] -[2023-10-15 02:42:58,587][88300] Updated weights for policy 1, policy_version 12102 (0.0010) -[2023-10-15 02:42:58,602][88298] Updated weights for policy 0, policy_version 12050 (0.0010) -[2023-10-15 02:42:58,952][88300] Updated weights for policy 1, policy_version 12112 (0.0007) -[2023-10-15 02:42:58,980][88298] Updated weights for policy 0, policy_version 12060 (0.0007) -[2023-10-15 02:42:59,119][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000012064_12353536.pth... -[2023-10-15 02:42:59,147][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000010432_10682368.pth -[2023-10-15 02:42:59,150][87905] Saving new best policy, reward=22.330! -[2023-10-15 02:42:59,316][88300] Updated weights for policy 1, policy_version 12122 (0.0009) -[2023-10-15 02:42:59,536][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000012128_12419072.pth... -[2023-10-15 02:42:59,575][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000010496_10747904.pth -[2023-10-15 02:43:02,979][88298] Updated weights for policy 0, policy_version 12070 (0.0008) -[2023-10-15 02:43:03,206][88300] Updated weights for policy 1, policy_version 12132 (0.0009) -[2023-10-15 02:43:03,346][88298] Updated weights for policy 0, policy_version 12080 (0.0007) -[2023-10-15 02:43:03,534][87330] Fps is (10 sec: 13106.6, 60 sec: 13107.1, 300 sec: 13773.7). Total num frames: 24772608. Throughput: 0: 1726.1, 1: 1731.9. Samples: 6203954. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:43:03,535][87330] Avg episode reward: [(0, '22.310'), (1, '21.920')] -[2023-10-15 02:43:03,570][88300] Updated weights for policy 1, policy_version 12142 (0.0007) -[2023-10-15 02:43:03,714][88298] Updated weights for policy 0, policy_version 12090 (0.0007) -[2023-10-15 02:43:03,940][88300] Updated weights for policy 1, policy_version 12152 (0.0008) -[2023-10-15 02:43:07,691][88298] Updated weights for policy 0, policy_version 12100 (0.0008) -[2023-10-15 02:43:07,899][88300] Updated weights for policy 1, policy_version 12162 (0.0010) -[2023-10-15 02:43:08,068][88298] Updated weights for policy 0, policy_version 12110 (0.0007) -[2023-10-15 02:43:08,261][88300] Updated weights for policy 1, policy_version 12172 (0.0008) -[2023-10-15 02:43:08,445][88298] Updated weights for policy 0, policy_version 12120 (0.0008) -[2023-10-15 02:43:08,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 24838144. Throughput: 0: 1737.2, 1: 1753.2. Samples: 6225234. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-15 02:43:08,534][87330] Avg episode reward: [(0, '22.310'), (1, '21.930')] -[2023-10-15 02:43:08,627][88300] Updated weights for policy 1, policy_version 12182 (0.0008) -[2023-10-15 02:43:08,996][88300] Updated weights for policy 1, policy_version 12192 (0.0008) -[2023-10-15 02:43:12,463][88298] Updated weights for policy 0, policy_version 12130 (0.0008) -[2023-10-15 02:43:12,831][88298] Updated weights for policy 0, policy_version 12140 (0.0007) -[2023-10-15 02:43:12,922][88300] Updated weights for policy 1, policy_version 12202 (0.0007) -[2023-10-15 02:43:13,195][88298] Updated weights for policy 0, policy_version 12150 (0.0009) -[2023-10-15 02:43:13,286][88300] Updated weights for policy 1, policy_version 12212 (0.0007) -[2023-10-15 02:43:13,534][87330] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 24903680. Throughput: 0: 1720.7, 1: 1740.8. Samples: 6245654. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-15 02:43:13,534][87330] Avg episode reward: [(0, '22.300'), (1, '21.910')] -[2023-10-15 02:43:13,572][88298] Updated weights for policy 0, policy_version 12160 (0.0009) -[2023-10-15 02:43:13,656][88300] Updated weights for policy 1, policy_version 12222 (0.0008) -[2023-10-15 02:43:17,380][88300] Updated weights for policy 1, policy_version 12232 (0.0008) -[2023-10-15 02:43:17,540][88298] Updated weights for policy 0, policy_version 12170 (0.0008) -[2023-10-15 02:43:17,736][88300] Updated weights for policy 1, policy_version 12242 (0.0008) -[2023-10-15 02:43:17,922][88298] Updated weights for policy 0, policy_version 12180 (0.0008) -[2023-10-15 02:43:18,107][88300] Updated weights for policy 1, policy_version 12252 (0.0010) -[2023-10-15 02:43:18,294][88298] Updated weights for policy 0, policy_version 12190 (0.0008) -[2023-10-15 02:43:18,534][87330] Fps is (10 sec: 19660.4, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 25034752. Throughput: 0: 1725.8, 1: 1756.2. Samples: 6256178. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:43:18,535][87330] Avg episode reward: [(0, '22.280'), (1, '21.930')] -[2023-10-15 02:43:22,063][88300] Updated weights for policy 1, policy_version 12262 (0.0008) -[2023-10-15 02:43:22,196][88298] Updated weights for policy 0, policy_version 12200 (0.0008) -[2023-10-15 02:43:22,431][88300] Updated weights for policy 1, policy_version 12272 (0.0007) -[2023-10-15 02:43:22,569][88298] Updated weights for policy 0, policy_version 12210 (0.0008) -[2023-10-15 02:43:22,794][88300] Updated weights for policy 1, policy_version 12282 (0.0009) -[2023-10-15 02:43:22,934][88298] Updated weights for policy 0, policy_version 12220 (0.0007) -[2023-10-15 02:43:23,534][87330] Fps is (10 sec: 19661.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 25100288. Throughput: 0: 1724.8, 1: 1750.2. Samples: 6277150. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:43:23,534][87330] Avg episode reward: [(0, '22.360'), (1, '21.950')] -[2023-10-15 02:43:23,535][87905] Saving new best policy, reward=22.360! -[2023-10-15 02:43:26,896][88298] Updated weights for policy 0, policy_version 12230 (0.0008) -[2023-10-15 02:43:26,982][88300] Updated weights for policy 1, policy_version 12292 (0.0008) -[2023-10-15 02:43:27,271][88298] Updated weights for policy 0, policy_version 12240 (0.0007) -[2023-10-15 02:43:27,382][88300] Updated weights for policy 1, policy_version 12302 (0.0009) -[2023-10-15 02:43:27,641][88298] Updated weights for policy 0, policy_version 12250 (0.0008) -[2023-10-15 02:43:27,743][88300] Updated weights for policy 1, policy_version 12312 (0.0009) -[2023-10-15 02:43:28,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 25165824. Throughput: 0: 1696.3, 1: 1732.3. Samples: 6296274. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:43:28,535][87330] Avg episode reward: [(0, '22.340'), (1, '21.970')] -[2023-10-15 02:43:31,470][88300] Updated weights for policy 1, policy_version 12322 (0.0008) -[2023-10-15 02:43:31,566][88298] Updated weights for policy 0, policy_version 12260 (0.0008) -[2023-10-15 02:43:31,834][88300] Updated weights for policy 1, policy_version 12332 (0.0009) -[2023-10-15 02:43:31,923][88298] Updated weights for policy 0, policy_version 12270 (0.0010) -[2023-10-15 02:43:32,205][88300] Updated weights for policy 1, policy_version 12342 (0.0009) -[2023-10-15 02:43:32,294][88298] Updated weights for policy 0, policy_version 12280 (0.0007) -[2023-10-15 02:43:32,562][88300] Updated weights for policy 1, policy_version 12352 (0.0009) -[2023-10-15 02:43:33,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 25231360. Throughput: 0: 1727.9, 1: 1760.0. Samples: 6308424. Policy #0 lag: (min: 31.0, avg: 39.9, max: 63.0) -[2023-10-15 02:43:33,534][87330] Avg episode reward: [(0, '22.300'), (1, '21.950')] -[2023-10-15 02:43:36,251][88298] Updated weights for policy 0, policy_version 12290 (0.0008) -[2023-10-15 02:43:36,599][88300] Updated weights for policy 1, policy_version 12362 (0.0008) -[2023-10-15 02:43:36,617][88298] Updated weights for policy 0, policy_version 12300 (0.0009) -[2023-10-15 02:43:36,958][88300] Updated weights for policy 1, policy_version 12372 (0.0007) -[2023-10-15 02:43:36,994][88298] Updated weights for policy 0, policy_version 12310 (0.0008) -[2023-10-15 02:43:37,325][88300] Updated weights for policy 1, policy_version 12382 (0.0007) -[2023-10-15 02:43:37,362][88298] Updated weights for policy 0, policy_version 12320 (0.0008) -[2023-10-15 02:43:38,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 25296896. Throughput: 0: 1713.5, 1: 1732.7. Samples: 6328126. Policy #0 lag: (min: 31.0, avg: 39.9, max: 63.0) -[2023-10-15 02:43:38,535][87330] Avg episode reward: [(0, '22.350'), (1, '22.090')] -[2023-10-15 02:43:38,536][88033] Saving new best policy, reward=22.090! -[2023-10-15 02:43:41,087][88298] Updated weights for policy 0, policy_version 12330 (0.0007) -[2023-10-15 02:43:41,187][88300] Updated weights for policy 1, policy_version 12392 (0.0008) -[2023-10-15 02:43:41,450][88298] Updated weights for policy 0, policy_version 12340 (0.0008) -[2023-10-15 02:43:41,552][88300] Updated weights for policy 1, policy_version 12402 (0.0008) -[2023-10-15 02:43:41,821][88298] Updated weights for policy 0, policy_version 12350 (0.0009) -[2023-10-15 02:43:41,917][88300] Updated weights for policy 1, policy_version 12412 (0.0008) -[2023-10-15 02:43:43,534][87330] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 25362432. Throughput: 0: 1701.2, 1: 1722.8. Samples: 6348614. Policy #0 lag: (min: 31.0, avg: 39.9, max: 63.0) -[2023-10-15 02:43:43,535][87330] Avg episode reward: [(0, '22.370'), (1, '22.080')] -[2023-10-15 02:43:43,545][87905] Saving new best policy, reward=22.370! -[2023-10-15 02:43:45,807][88298] Updated weights for policy 0, policy_version 12360 (0.0009) -[2023-10-15 02:43:45,913][88300] Updated weights for policy 1, policy_version 12422 (0.0009) -[2023-10-15 02:43:46,184][88298] Updated weights for policy 0, policy_version 12370 (0.0009) -[2023-10-15 02:43:46,283][88300] Updated weights for policy 1, policy_version 12432 (0.0008) -[2023-10-15 02:43:46,542][88298] Updated weights for policy 0, policy_version 12380 (0.0008) -[2023-10-15 02:43:46,642][88300] Updated weights for policy 1, policy_version 12442 (0.0008) -[2023-10-15 02:43:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 25427968. Throughput: 0: 1721.3, 1: 1738.6. Samples: 6359652. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-15 02:43:48,534][87330] Avg episode reward: [(0, '22.000'), (1, '22.120')] -[2023-10-15 02:43:48,535][88033] Saving new best policy, reward=22.120! -[2023-10-15 02:43:50,416][88298] Updated weights for policy 0, policy_version 12390 (0.0008) -[2023-10-15 02:43:50,673][88300] Updated weights for policy 1, policy_version 12452 (0.0009) -[2023-10-15 02:43:50,787][88298] Updated weights for policy 0, policy_version 12400 (0.0008) -[2023-10-15 02:43:51,037][88300] Updated weights for policy 1, policy_version 12462 (0.0007) -[2023-10-15 02:43:51,157][88298] Updated weights for policy 0, policy_version 12410 (0.0008) -[2023-10-15 02:43:51,404][88300] Updated weights for policy 1, policy_version 12472 (0.0008) -[2023-10-15 02:43:53,534][87330] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 25493504. Throughput: 0: 1705.8, 1: 1720.4. Samples: 6379414. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-15 02:43:53,534][87330] Avg episode reward: [(0, '22.030'), (1, '21.980')] -[2023-10-15 02:43:55,081][88298] Updated weights for policy 0, policy_version 12420 (0.0008) -[2023-10-15 02:43:55,297][88300] Updated weights for policy 1, policy_version 12482 (0.0010) -[2023-10-15 02:43:55,449][88298] Updated weights for policy 0, policy_version 12430 (0.0007) -[2023-10-15 02:43:55,665][88300] Updated weights for policy 1, policy_version 12492 (0.0009) -[2023-10-15 02:43:55,821][88298] Updated weights for policy 0, policy_version 12440 (0.0008) -[2023-10-15 02:43:56,029][88300] Updated weights for policy 1, policy_version 12502 (0.0008) -[2023-10-15 02:43:56,391][88300] Updated weights for policy 1, policy_version 12512 (0.0008) -[2023-10-15 02:43:58,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 25559040. Throughput: 0: 1715.0, 1: 1738.6. Samples: 6401066. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-15 02:43:58,535][87330] Avg episode reward: [(0, '21.900'), (1, '22.060')] -[2023-10-15 02:43:59,722][88298] Updated weights for policy 0, policy_version 12450 (0.0010) -[2023-10-15 02:44:00,010][88300] Updated weights for policy 1, policy_version 12522 (0.0010) -[2023-10-15 02:44:00,099][88298] Updated weights for policy 0, policy_version 12460 (0.0008) -[2023-10-15 02:44:00,371][88300] Updated weights for policy 1, policy_version 12532 (0.0008) -[2023-10-15 02:44:00,464][88298] Updated weights for policy 0, policy_version 12470 (0.0008) -[2023-10-15 02:44:00,734][88300] Updated weights for policy 1, policy_version 12542 (0.0009) -[2023-10-15 02:44:00,831][88298] Updated weights for policy 0, policy_version 12480 (0.0007) -[2023-10-15 02:44:03,534][87330] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 25624576. Throughput: 0: 1711.9, 1: 1722.7. Samples: 6410734. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:44:03,535][87330] Avg episode reward: [(0, '21.840'), (1, '21.810')] -[2023-10-15 02:44:04,735][88300] Updated weights for policy 1, policy_version 12552 (0.0008) -[2023-10-15 02:44:04,790][88298] Updated weights for policy 0, policy_version 12490 (0.0010) -[2023-10-15 02:44:05,103][88300] Updated weights for policy 1, policy_version 12562 (0.0008) -[2023-10-15 02:44:05,174][88298] Updated weights for policy 0, policy_version 12500 (0.0008) -[2023-10-15 02:44:05,468][88300] Updated weights for policy 1, policy_version 12572 (0.0009) -[2023-10-15 02:44:05,540][88298] Updated weights for policy 0, policy_version 12510 (0.0008) -[2023-10-15 02:44:08,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 25690112. Throughput: 0: 1709.7, 1: 1728.1. Samples: 6431850. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:44:08,535][87330] Avg episode reward: [(0, '21.800'), (1, '21.610')] -[2023-10-15 02:44:09,432][88300] Updated weights for policy 1, policy_version 12582 (0.0008) -[2023-10-15 02:44:09,569][88298] Updated weights for policy 0, policy_version 12520 (0.0008) -[2023-10-15 02:44:09,798][88300] Updated weights for policy 1, policy_version 12592 (0.0009) -[2023-10-15 02:44:09,941][88298] Updated weights for policy 0, policy_version 12530 (0.0007) -[2023-10-15 02:44:10,163][88300] Updated weights for policy 1, policy_version 12602 (0.0009) -[2023-10-15 02:44:10,318][88298] Updated weights for policy 0, policy_version 12540 (0.0007) -[2023-10-15 02:44:13,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 25755648. Throughput: 0: 1736.1, 1: 1752.3. Samples: 6453248. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:44:13,534][87330] Avg episode reward: [(0, '21.710'), (1, '21.620')] -[2023-10-15 02:44:14,002][88300] Updated weights for policy 1, policy_version 12612 (0.0008) -[2023-10-15 02:44:14,163][88298] Updated weights for policy 0, policy_version 12550 (0.0008) -[2023-10-15 02:44:14,385][88300] Updated weights for policy 1, policy_version 12622 (0.0009) -[2023-10-15 02:44:14,533][88298] Updated weights for policy 0, policy_version 12560 (0.0007) -[2023-10-15 02:44:14,751][88300] Updated weights for policy 1, policy_version 12632 (0.0007) -[2023-10-15 02:44:14,902][88298] Updated weights for policy 0, policy_version 12570 (0.0007) -[2023-10-15 02:44:18,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 25821184. Throughput: 0: 1704.9, 1: 1720.9. Samples: 6462586. Policy #0 lag: (min: 12.0, avg: 15.0, max: 44.0) -[2023-10-15 02:44:18,534][87330] Avg episode reward: [(0, '21.870'), (1, '21.580')] -[2023-10-15 02:44:18,617][88300] Updated weights for policy 1, policy_version 12642 (0.0009) -[2023-10-15 02:44:18,982][88300] Updated weights for policy 1, policy_version 12652 (0.0007) -[2023-10-15 02:44:19,040][88298] Updated weights for policy 0, policy_version 12580 (0.0008) -[2023-10-15 02:44:19,343][88300] Updated weights for policy 1, policy_version 12662 (0.0007) -[2023-10-15 02:44:19,439][88298] Updated weights for policy 0, policy_version 12590 (0.0008) -[2023-10-15 02:44:19,710][88300] Updated weights for policy 1, policy_version 12672 (0.0010) -[2023-10-15 02:44:19,811][88298] Updated weights for policy 0, policy_version 12600 (0.0007) -[2023-10-15 02:44:23,436][88300] Updated weights for policy 1, policy_version 12682 (0.0007) -[2023-10-15 02:44:23,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 25886720. Throughput: 0: 1716.6, 1: 1750.2. Samples: 6484130. Policy #0 lag: (min: 12.0, avg: 15.0, max: 44.0) -[2023-10-15 02:44:23,534][87330] Avg episode reward: [(0, '21.990'), (1, '21.600')] -[2023-10-15 02:44:23,664][88298] Updated weights for policy 0, policy_version 12610 (0.0007) -[2023-10-15 02:44:23,799][88300] Updated weights for policy 1, policy_version 12692 (0.0007) -[2023-10-15 02:44:24,039][88298] Updated weights for policy 0, policy_version 12620 (0.0008) -[2023-10-15 02:44:24,161][88300] Updated weights for policy 1, policy_version 12702 (0.0009) -[2023-10-15 02:44:24,409][88298] Updated weights for policy 0, policy_version 12630 (0.0008) -[2023-10-15 02:44:24,785][88298] Updated weights for policy 0, policy_version 12640 (0.0008) -[2023-10-15 02:44:28,020][88300] Updated weights for policy 1, policy_version 12712 (0.0008) -[2023-10-15 02:44:28,394][88300] Updated weights for policy 1, policy_version 12722 (0.0009) -[2023-10-15 02:44:28,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 25952256. Throughput: 0: 1736.0, 1: 1750.9. Samples: 6505524. Policy #0 lag: (min: 12.0, avg: 15.0, max: 44.0) -[2023-10-15 02:44:28,534][87330] Avg episode reward: [(0, '22.040'), (1, '21.660')] -[2023-10-15 02:44:28,721][88298] Updated weights for policy 0, policy_version 12650 (0.0007) -[2023-10-15 02:44:28,755][88300] Updated weights for policy 1, policy_version 12732 (0.0007) -[2023-10-15 02:44:29,098][88298] Updated weights for policy 0, policy_version 12660 (0.0007) -[2023-10-15 02:44:29,459][88298] Updated weights for policy 0, policy_version 12670 (0.0007) -[2023-10-15 02:44:32,674][88300] Updated weights for policy 1, policy_version 12742 (0.0007) -[2023-10-15 02:44:33,039][88300] Updated weights for policy 1, policy_version 12752 (0.0010) -[2023-10-15 02:44:33,401][88300] Updated weights for policy 1, policy_version 12762 (0.0009) -[2023-10-15 02:44:33,470][88298] Updated weights for policy 0, policy_version 12680 (0.0009) -[2023-10-15 02:44:33,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 26017792. Throughput: 0: 1714.9, 1: 1748.0. Samples: 6515484. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:44:33,534][87330] Avg episode reward: [(0, '22.090'), (1, '21.640')] -[2023-10-15 02:44:33,830][88298] Updated weights for policy 0, policy_version 12690 (0.0008) -[2023-10-15 02:44:34,205][88298] Updated weights for policy 0, policy_version 12700 (0.0009) -[2023-10-15 02:44:37,306][88300] Updated weights for policy 1, policy_version 12772 (0.0008) -[2023-10-15 02:44:37,675][88300] Updated weights for policy 1, policy_version 12782 (0.0008) -[2023-10-15 02:44:37,968][88298] Updated weights for policy 0, policy_version 12710 (0.0007) -[2023-10-15 02:44:38,039][88300] Updated weights for policy 1, policy_version 12792 (0.0008) -[2023-10-15 02:44:38,333][88298] Updated weights for policy 0, policy_version 12720 (0.0008) -[2023-10-15 02:44:38,534][87330] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 26116096. Throughput: 0: 1739.2, 1: 1766.4. Samples: 6537168. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:44:38,534][87330] Avg episode reward: [(0, '22.070'), (1, '21.820')] -[2023-10-15 02:44:38,701][88298] Updated weights for policy 0, policy_version 12730 (0.0009) -[2023-10-15 02:44:41,995][88300] Updated weights for policy 1, policy_version 12802 (0.0008) -[2023-10-15 02:44:42,375][88300] Updated weights for policy 1, policy_version 12812 (0.0009) -[2023-10-15 02:44:42,664][88298] Updated weights for policy 0, policy_version 12740 (0.0008) -[2023-10-15 02:44:42,738][88300] Updated weights for policy 1, policy_version 12822 (0.0007) -[2023-10-15 02:44:43,031][88298] Updated weights for policy 0, policy_version 12750 (0.0009) -[2023-10-15 02:44:43,103][88300] Updated weights for policy 1, policy_version 12832 (0.0007) -[2023-10-15 02:44:43,410][88298] Updated weights for policy 0, policy_version 12760 (0.0009) -[2023-10-15 02:44:43,534][87330] Fps is (10 sec: 16383.7, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 26181632. Throughput: 0: 1735.2, 1: 1734.8. Samples: 6557216. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:44:43,535][87330] Avg episode reward: [(0, '22.030'), (1, '21.790')] -[2023-10-15 02:44:47,069][88300] Updated weights for policy 1, policy_version 12842 (0.0008) -[2023-10-15 02:44:47,437][88300] Updated weights for policy 1, policy_version 12852 (0.0008) -[2023-10-15 02:44:47,459][88298] Updated weights for policy 0, policy_version 12770 (0.0008) -[2023-10-15 02:44:47,810][88300] Updated weights for policy 1, policy_version 12862 (0.0007) -[2023-10-15 02:44:47,825][88298] Updated weights for policy 0, policy_version 12780 (0.0008) -[2023-10-15 02:44:48,194][88298] Updated weights for policy 0, policy_version 12790 (0.0010) -[2023-10-15 02:44:48,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 26247168. Throughput: 0: 1736.5, 1: 1760.9. Samples: 6568118. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:44:48,534][87330] Avg episode reward: [(0, '22.100'), (1, '21.760')] -[2023-10-15 02:44:48,560][88298] Updated weights for policy 0, policy_version 12800 (0.0010) -[2023-10-15 02:44:51,991][88300] Updated weights for policy 1, policy_version 12872 (0.0009) -[2023-10-15 02:44:52,366][88300] Updated weights for policy 1, policy_version 12882 (0.0008) -[2023-10-15 02:44:52,502][88298] Updated weights for policy 0, policy_version 12810 (0.0007) -[2023-10-15 02:44:52,732][88300] Updated weights for policy 1, policy_version 12892 (0.0008) -[2023-10-15 02:44:52,864][88298] Updated weights for policy 0, policy_version 12820 (0.0008) -[2023-10-15 02:44:53,240][88298] Updated weights for policy 0, policy_version 12830 (0.0010) -[2023-10-15 02:44:53,534][87330] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 26345472. Throughput: 0: 1744.9, 1: 1743.1. Samples: 6588806. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:44:53,534][87330] Avg episode reward: [(0, '22.120'), (1, '21.740')] -[2023-10-15 02:44:56,447][88300] Updated weights for policy 1, policy_version 12902 (0.0009) -[2023-10-15 02:44:56,808][88300] Updated weights for policy 1, policy_version 12912 (0.0008) -[2023-10-15 02:44:57,166][88300] Updated weights for policy 1, policy_version 12922 (0.0008) -[2023-10-15 02:44:57,184][88298] Updated weights for policy 0, policy_version 12840 (0.0008) -[2023-10-15 02:44:57,547][88298] Updated weights for policy 0, policy_version 12850 (0.0010) -[2023-10-15 02:44:57,932][88298] Updated weights for policy 0, policy_version 12860 (0.0009) -[2023-10-15 02:44:58,534][87330] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 26411008. Throughput: 0: 1724.4, 1: 1725.9. Samples: 6608510. Policy #0 lag: (min: 48.0, avg: 55.8, max: 56.0) -[2023-10-15 02:44:58,535][87330] Avg episode reward: [(0, '22.120'), (1, '21.780')] -[2023-10-15 02:44:58,547][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000012864_13172736.pth... -[2023-10-15 02:44:58,547][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000012928_13238272.pth... -[2023-10-15 02:44:58,583][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000011232_11501568.pth -[2023-10-15 02:44:58,584][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000011296_11567104.pth -[2023-10-15 02:45:01,117][88300] Updated weights for policy 1, policy_version 12932 (0.0007) -[2023-10-15 02:45:01,529][88300] Updated weights for policy 1, policy_version 12942 (0.0008) -[2023-10-15 02:45:01,772][88298] Updated weights for policy 0, policy_version 12870 (0.0008) -[2023-10-15 02:45:01,881][88300] Updated weights for policy 1, policy_version 12952 (0.0009) -[2023-10-15 02:45:02,148][88298] Updated weights for policy 0, policy_version 12880 (0.0007) -[2023-10-15 02:45:02,523][88298] Updated weights for policy 0, policy_version 12890 (0.0007) -[2023-10-15 02:45:03,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 26476544. Throughput: 0: 1748.4, 1: 1749.6. Samples: 6619998. Policy #0 lag: (min: 48.0, avg: 55.8, max: 56.0) -[2023-10-15 02:45:03,535][87330] Avg episode reward: [(0, '22.170'), (1, '21.710')] -[2023-10-15 02:45:05,872][88300] Updated weights for policy 1, policy_version 12962 (0.0008) -[2023-10-15 02:45:06,251][88300] Updated weights for policy 1, policy_version 12972 (0.0009) -[2023-10-15 02:45:06,613][88300] Updated weights for policy 1, policy_version 12982 (0.0009) -[2023-10-15 02:45:06,622][88298] Updated weights for policy 0, policy_version 12900 (0.0008) -[2023-10-15 02:45:06,993][88300] Updated weights for policy 1, policy_version 12992 (0.0009) -[2023-10-15 02:45:07,013][88298] Updated weights for policy 0, policy_version 12910 (0.0008) -[2023-10-15 02:45:07,376][88298] Updated weights for policy 0, policy_version 12920 (0.0007) -[2023-10-15 02:45:08,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 26542080. Throughput: 0: 1736.8, 1: 1715.8. Samples: 6639496. Policy #0 lag: (min: 48.0, avg: 55.8, max: 56.0) -[2023-10-15 02:45:08,535][87330] Avg episode reward: [(0, '22.020'), (1, '21.680')] -[2023-10-15 02:45:10,964][88300] Updated weights for policy 1, policy_version 13002 (0.0009) -[2023-10-15 02:45:11,286][88298] Updated weights for policy 0, policy_version 12930 (0.0008) -[2023-10-15 02:45:11,332][88300] Updated weights for policy 1, policy_version 13012 (0.0009) -[2023-10-15 02:45:11,657][88298] Updated weights for policy 0, policy_version 12940 (0.0007) -[2023-10-15 02:45:11,702][88300] Updated weights for policy 1, policy_version 13022 (0.0007) -[2023-10-15 02:45:12,023][88298] Updated weights for policy 0, policy_version 12950 (0.0010) -[2023-10-15 02:45:12,400][88298] Updated weights for policy 0, policy_version 12960 (0.0008) -[2023-10-15 02:45:13,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 26607616. Throughput: 0: 1707.9, 1: 1724.9. Samples: 6660000. Policy #0 lag: (min: 1.0, avg: 14.5, max: 33.0) -[2023-10-15 02:45:13,535][87330] Avg episode reward: [(0, '22.140'), (1, '21.700')] -[2023-10-15 02:45:15,376][88300] Updated weights for policy 1, policy_version 13032 (0.0007) -[2023-10-15 02:45:15,746][88300] Updated weights for policy 1, policy_version 13042 (0.0007) -[2023-10-15 02:45:16,106][88300] Updated weights for policy 1, policy_version 13052 (0.0008) -[2023-10-15 02:45:16,279][88298] Updated weights for policy 0, policy_version 12970 (0.0009) -[2023-10-15 02:45:16,643][88298] Updated weights for policy 0, policy_version 12980 (0.0008) -[2023-10-15 02:45:17,027][88298] Updated weights for policy 0, policy_version 12990 (0.0011) -[2023-10-15 02:45:18,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 26673152. Throughput: 0: 1740.1, 1: 1713.7. Samples: 6670904. Policy #0 lag: (min: 1.0, avg: 14.5, max: 33.0) -[2023-10-15 02:45:18,535][87330] Avg episode reward: [(0, '22.150'), (1, '21.980')] -[2023-10-15 02:45:19,891][88300] Updated weights for policy 1, policy_version 13062 (0.0009) -[2023-10-15 02:45:20,270][88300] Updated weights for policy 1, policy_version 13072 (0.0010) -[2023-10-15 02:45:20,646][88300] Updated weights for policy 1, policy_version 13082 (0.0008) -[2023-10-15 02:45:20,903][88298] Updated weights for policy 0, policy_version 13000 (0.0009) -[2023-10-15 02:45:21,284][88298] Updated weights for policy 0, policy_version 13010 (0.0009) -[2023-10-15 02:45:21,653][88298] Updated weights for policy 0, policy_version 13020 (0.0008) -[2023-10-15 02:45:23,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 26738688. Throughput: 0: 1708.7, 1: 1714.0. Samples: 6691192. Policy #0 lag: (min: 1.0, avg: 14.5, max: 33.0) -[2023-10-15 02:45:23,535][87330] Avg episode reward: [(0, '22.160'), (1, '21.970')] -[2023-10-15 02:45:24,743][88300] Updated weights for policy 1, policy_version 13092 (0.0008) -[2023-10-15 02:45:25,114][88300] Updated weights for policy 1, policy_version 13102 (0.0009) -[2023-10-15 02:45:25,492][88300] Updated weights for policy 1, policy_version 13112 (0.0008) -[2023-10-15 02:45:25,585][88298] Updated weights for policy 0, policy_version 13030 (0.0008) -[2023-10-15 02:45:25,962][88298] Updated weights for policy 0, policy_version 13040 (0.0009) -[2023-10-15 02:45:26,333][88298] Updated weights for policy 0, policy_version 13050 (0.0011) -[2023-10-15 02:45:28,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 26804224. Throughput: 0: 1709.1, 1: 1738.3. Samples: 6712350. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) -[2023-10-15 02:45:28,534][87330] Avg episode reward: [(0, '22.110'), (1, '21.790')] -[2023-10-15 02:45:29,299][88300] Updated weights for policy 1, policy_version 13122 (0.0008) -[2023-10-15 02:45:29,673][88300] Updated weights for policy 1, policy_version 13132 (0.0011) -[2023-10-15 02:45:30,041][88300] Updated weights for policy 1, policy_version 13142 (0.0010) -[2023-10-15 02:45:30,261][88298] Updated weights for policy 0, policy_version 13060 (0.0009) -[2023-10-15 02:45:30,413][88300] Updated weights for policy 1, policy_version 13152 (0.0008) -[2023-10-15 02:45:30,640][88298] Updated weights for policy 0, policy_version 13070 (0.0008) -[2023-10-15 02:45:31,020][88298] Updated weights for policy 0, policy_version 13080 (0.0009) -[2023-10-15 02:45:33,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 26869760. Throughput: 0: 1719.5, 1: 1713.1. Samples: 6722582. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) -[2023-10-15 02:45:33,534][87330] Avg episode reward: [(0, '22.160'), (1, '21.680')] -[2023-10-15 02:45:34,208][88300] Updated weights for policy 1, policy_version 13162 (0.0009) -[2023-10-15 02:45:34,584][88300] Updated weights for policy 1, policy_version 13172 (0.0008) -[2023-10-15 02:45:34,827][88298] Updated weights for policy 0, policy_version 13090 (0.0009) -[2023-10-15 02:45:34,948][88300] Updated weights for policy 1, policy_version 13182 (0.0007) -[2023-10-15 02:45:35,204][88298] Updated weights for policy 0, policy_version 13100 (0.0010) -[2023-10-15 02:45:35,578][88298] Updated weights for policy 0, policy_version 13110 (0.0008) -[2023-10-15 02:45:35,955][88298] Updated weights for policy 0, policy_version 13120 (0.0007) -[2023-10-15 02:45:38,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 26935296. Throughput: 0: 1704.5, 1: 1734.1. Samples: 6743544. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) -[2023-10-15 02:45:38,534][87330] Avg episode reward: [(0, '22.380'), (1, '21.820')] -[2023-10-15 02:45:38,535][87905] Saving new best policy, reward=22.380! -[2023-10-15 02:45:38,829][88300] Updated weights for policy 1, policy_version 13192 (0.0007) -[2023-10-15 02:45:39,195][88300] Updated weights for policy 1, policy_version 13202 (0.0010) -[2023-10-15 02:45:39,569][88300] Updated weights for policy 1, policy_version 13212 (0.0010) -[2023-10-15 02:45:40,000][88298] Updated weights for policy 0, policy_version 13130 (0.0009) -[2023-10-15 02:45:40,384][88298] Updated weights for policy 0, policy_version 13140 (0.0008) -[2023-10-15 02:45:40,754][88298] Updated weights for policy 0, policy_version 13150 (0.0007) -[2023-10-15 02:45:43,534][87330] Fps is (10 sec: 13106.6, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 27000832. Throughput: 0: 1729.5, 1: 1756.8. Samples: 6765394. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-15 02:45:43,535][87330] Avg episode reward: [(0, '22.350'), (1, '21.890')] -[2023-10-15 02:45:43,571][88300] Updated weights for policy 1, policy_version 13222 (0.0008) -[2023-10-15 02:45:43,941][88300] Updated weights for policy 1, policy_version 13232 (0.0010) -[2023-10-15 02:45:44,306][88300] Updated weights for policy 1, policy_version 13242 (0.0009) -[2023-10-15 02:45:44,450][88298] Updated weights for policy 0, policy_version 13160 (0.0008) -[2023-10-15 02:45:44,823][88298] Updated weights for policy 0, policy_version 13170 (0.0009) -[2023-10-15 02:45:45,202][88298] Updated weights for policy 0, policy_version 13180 (0.0008) -[2023-10-15 02:45:48,244][88300] Updated weights for policy 1, policy_version 13252 (0.0008) -[2023-10-15 02:45:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 27066368. Throughput: 0: 1710.8, 1: 1733.3. Samples: 6774982. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-15 02:45:48,534][87330] Avg episode reward: [(0, '22.420'), (1, '21.850')] -[2023-10-15 02:45:48,535][87905] Saving new best policy, reward=22.420! -[2023-10-15 02:45:48,606][88300] Updated weights for policy 1, policy_version 13262 (0.0009) -[2023-10-15 02:45:48,973][88300] Updated weights for policy 1, policy_version 13272 (0.0007) -[2023-10-15 02:45:49,120][88298] Updated weights for policy 0, policy_version 13190 (0.0010) -[2023-10-15 02:45:49,504][88298] Updated weights for policy 0, policy_version 13200 (0.0009) -[2023-10-15 02:45:49,869][88298] Updated weights for policy 0, policy_version 13210 (0.0008) -[2023-10-15 02:45:52,977][88300] Updated weights for policy 1, policy_version 13282 (0.0009) -[2023-10-15 02:45:53,354][88300] Updated weights for policy 1, policy_version 13292 (0.0009) -[2023-10-15 02:45:53,534][87330] Fps is (10 sec: 13107.7, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 27131904. Throughput: 0: 1728.4, 1: 1759.8. Samples: 6796466. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-15 02:45:53,534][87330] Avg episode reward: [(0, '22.340'), (1, '21.810')] -[2023-10-15 02:45:53,721][88300] Updated weights for policy 1, policy_version 13302 (0.0008) -[2023-10-15 02:45:53,839][88298] Updated weights for policy 0, policy_version 13220 (0.0009) -[2023-10-15 02:45:54,090][88300] Updated weights for policy 1, policy_version 13312 (0.0007) -[2023-10-15 02:45:54,237][88298] Updated weights for policy 0, policy_version 13230 (0.0008) -[2023-10-15 02:45:54,609][88298] Updated weights for policy 0, policy_version 13240 (0.0007) -[2023-10-15 02:45:57,985][88300] Updated weights for policy 1, policy_version 13322 (0.0007) -[2023-10-15 02:45:58,354][88300] Updated weights for policy 1, policy_version 13332 (0.0007) -[2023-10-15 02:45:58,358][88298] Updated weights for policy 0, policy_version 13250 (0.0009) -[2023-10-15 02:45:58,534][87330] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 27197440. Throughput: 0: 1749.7, 1: 1747.4. Samples: 6817368. Policy #0 lag: (min: 8.0, avg: 30.9, max: 40.0) -[2023-10-15 02:45:58,535][87330] Avg episode reward: [(0, '22.420'), (1, '22.070')] -[2023-10-15 02:45:58,727][88300] Updated weights for policy 1, policy_version 13342 (0.0008) -[2023-10-15 02:45:58,732][88298] Updated weights for policy 0, policy_version 13260 (0.0008) -[2023-10-15 02:45:59,101][88298] Updated weights for policy 0, policy_version 13270 (0.0008) -[2023-10-15 02:45:59,487][88298] Updated weights for policy 0, policy_version 13280 (0.0008) -[2023-10-15 02:46:02,616][88300] Updated weights for policy 1, policy_version 13352 (0.0009) -[2023-10-15 02:46:02,988][88300] Updated weights for policy 1, policy_version 13362 (0.0008) -[2023-10-15 02:46:03,355][88300] Updated weights for policy 1, policy_version 13372 (0.0008) -[2023-10-15 02:46:03,375][88298] Updated weights for policy 0, policy_version 13290 (0.0008) -[2023-10-15 02:46:03,534][87330] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 27295744. Throughput: 0: 1715.6, 1: 1766.3. Samples: 6827592. Policy #0 lag: (min: 8.0, avg: 30.9, max: 40.0) -[2023-10-15 02:46:03,534][87330] Avg episode reward: [(0, '22.430'), (1, '22.040')] -[2023-10-15 02:46:03,748][88298] Updated weights for policy 0, policy_version 13300 (0.0009) -[2023-10-15 02:46:04,114][88298] Updated weights for policy 0, policy_version 13310 (0.0010) -[2023-10-15 02:46:04,187][87905] Saving new best policy, reward=22.430! -[2023-10-15 02:46:07,297][88300] Updated weights for policy 1, policy_version 13382 (0.0009) -[2023-10-15 02:46:07,661][88300] Updated weights for policy 1, policy_version 13392 (0.0009) -[2023-10-15 02:46:08,035][88300] Updated weights for policy 1, policy_version 13402 (0.0007) -[2023-10-15 02:46:08,095][88298] Updated weights for policy 0, policy_version 13320 (0.0007) -[2023-10-15 02:46:08,464][88298] Updated weights for policy 0, policy_version 13330 (0.0007) -[2023-10-15 02:46:08,534][87330] Fps is (10 sec: 16384.4, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 27361280. Throughput: 0: 1738.9, 1: 1759.3. Samples: 6848610. Policy #0 lag: (min: 8.0, avg: 30.9, max: 40.0) -[2023-10-15 02:46:08,534][87330] Avg episode reward: [(0, '22.400'), (1, '22.190')] -[2023-10-15 02:46:08,535][88033] Saving new best policy, reward=22.190! -[2023-10-15 02:46:08,837][88298] Updated weights for policy 0, policy_version 13340 (0.0007) -[2023-10-15 02:46:11,854][88300] Updated weights for policy 1, policy_version 13412 (0.0008) -[2023-10-15 02:46:12,212][88300] Updated weights for policy 1, policy_version 13422 (0.0010) -[2023-10-15 02:46:12,591][88300] Updated weights for policy 1, policy_version 13432 (0.0008) -[2023-10-15 02:46:12,744][88298] Updated weights for policy 0, policy_version 13350 (0.0008) -[2023-10-15 02:46:13,111][88298] Updated weights for policy 0, policy_version 13360 (0.0010) -[2023-10-15 02:46:13,488][88298] Updated weights for policy 0, policy_version 13370 (0.0008) -[2023-10-15 02:46:13,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 27426816. Throughput: 0: 1742.0, 1: 1734.7. Samples: 6868802. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-15 02:46:13,535][87330] Avg episode reward: [(0, '22.400'), (1, '22.230')] -[2023-10-15 02:46:13,547][88033] Saving new best policy, reward=22.230! -[2023-10-15 02:46:16,440][88300] Updated weights for policy 1, policy_version 13442 (0.0008) -[2023-10-15 02:46:16,808][88300] Updated weights for policy 1, policy_version 13452 (0.0008) -[2023-10-15 02:46:17,177][88300] Updated weights for policy 1, policy_version 13462 (0.0008) -[2023-10-15 02:46:17,433][88298] Updated weights for policy 0, policy_version 13380 (0.0008) -[2023-10-15 02:46:17,540][88300] Updated weights for policy 1, policy_version 13472 (0.0009) -[2023-10-15 02:46:17,806][88298] Updated weights for policy 0, policy_version 13390 (0.0009) -[2023-10-15 02:46:18,180][88298] Updated weights for policy 0, policy_version 13400 (0.0009) -[2023-10-15 02:46:18,534][87330] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 27525120. Throughput: 0: 1735.9, 1: 1763.2. Samples: 6880044. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-15 02:46:18,535][87330] Avg episode reward: [(0, '22.300'), (1, '22.110')] -[2023-10-15 02:46:21,505][88300] Updated weights for policy 1, policy_version 13482 (0.0008) -[2023-10-15 02:46:21,880][88300] Updated weights for policy 1, policy_version 13492 (0.0009) -[2023-10-15 02:46:22,128][88298] Updated weights for policy 0, policy_version 13410 (0.0007) -[2023-10-15 02:46:22,237][88300] Updated weights for policy 1, policy_version 13502 (0.0008) -[2023-10-15 02:46:22,501][88298] Updated weights for policy 0, policy_version 13420 (0.0008) -[2023-10-15 02:46:22,871][88298] Updated weights for policy 0, policy_version 13430 (0.0008) -[2023-10-15 02:46:23,251][88298] Updated weights for policy 0, policy_version 13440 (0.0010) -[2023-10-15 02:46:23,534][87330] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 27590656. Throughput: 0: 1751.4, 1: 1736.6. Samples: 6900506. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-15 02:46:23,535][87330] Avg episode reward: [(0, '22.320'), (1, '22.170')] -[2023-10-15 02:46:25,932][88300] Updated weights for policy 1, policy_version 13512 (0.0007) -[2023-10-15 02:46:26,299][88300] Updated weights for policy 1, policy_version 13522 (0.0007) -[2023-10-15 02:46:26,670][88300] Updated weights for policy 1, policy_version 13532 (0.0007) -[2023-10-15 02:46:27,246][88298] Updated weights for policy 0, policy_version 13450 (0.0008) -[2023-10-15 02:46:27,617][88298] Updated weights for policy 0, policy_version 13460 (0.0007) -[2023-10-15 02:46:27,990][88298] Updated weights for policy 0, policy_version 13470 (0.0008) -[2023-10-15 02:46:28,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 27656192. Throughput: 0: 1725.3, 1: 1731.2. Samples: 6920938. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-15 02:46:28,535][87330] Avg episode reward: [(0, '22.340'), (1, '22.130')] -[2023-10-15 02:46:30,561][88300] Updated weights for policy 1, policy_version 13542 (0.0008) -[2023-10-15 02:46:30,933][88300] Updated weights for policy 1, policy_version 13552 (0.0007) -[2023-10-15 02:46:31,301][88300] Updated weights for policy 1, policy_version 13562 (0.0008) -[2023-10-15 02:46:31,763][88298] Updated weights for policy 0, policy_version 13480 (0.0010) -[2023-10-15 02:46:32,136][88298] Updated weights for policy 0, policy_version 13490 (0.0010) -[2023-10-15 02:46:32,508][88298] Updated weights for policy 0, policy_version 13500 (0.0009) -[2023-10-15 02:46:33,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13884.8). Total num frames: 27721728. Throughput: 0: 1744.7, 1: 1739.6. Samples: 6931776. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-15 02:46:33,535][87330] Avg episode reward: [(0, '22.320'), (1, '22.140')] -[2023-10-15 02:46:35,161][88300] Updated weights for policy 1, policy_version 13572 (0.0010) -[2023-10-15 02:46:35,539][88300] Updated weights for policy 1, policy_version 13582 (0.0010) -[2023-10-15 02:46:35,907][88300] Updated weights for policy 1, policy_version 13592 (0.0010) -[2023-10-15 02:46:36,534][88298] Updated weights for policy 0, policy_version 13510 (0.0008) -[2023-10-15 02:46:36,905][88298] Updated weights for policy 0, policy_version 13520 (0.0009) -[2023-10-15 02:46:37,277][88298] Updated weights for policy 0, policy_version 13530 (0.0010) -[2023-10-15 02:46:38,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 27787264. Throughput: 0: 1731.0, 1: 1732.4. Samples: 6952318. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-15 02:46:38,534][87330] Avg episode reward: [(0, '22.330'), (1, '22.070')] -[2023-10-15 02:46:39,869][88300] Updated weights for policy 1, policy_version 13602 (0.0008) -[2023-10-15 02:46:40,274][88300] Updated weights for policy 1, policy_version 13612 (0.0007) -[2023-10-15 02:46:40,637][88300] Updated weights for policy 1, policy_version 13622 (0.0008) -[2023-10-15 02:46:41,000][88300] Updated weights for policy 1, policy_version 13632 (0.0009) -[2023-10-15 02:46:41,139][88298] Updated weights for policy 0, policy_version 13540 (0.0009) -[2023-10-15 02:46:41,534][88298] Updated weights for policy 0, policy_version 13550 (0.0009) -[2023-10-15 02:46:41,904][88298] Updated weights for policy 0, policy_version 13560 (0.0009) -[2023-10-15 02:46:43,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 27852800. Throughput: 0: 1719.1, 1: 1740.7. Samples: 6973060. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-15 02:46:43,535][87330] Avg episode reward: [(0, '22.350'), (1, '21.880')] -[2023-10-15 02:46:44,780][88300] Updated weights for policy 1, policy_version 13642 (0.0009) -[2023-10-15 02:46:45,150][88300] Updated weights for policy 1, policy_version 13652 (0.0009) -[2023-10-15 02:46:45,525][88300] Updated weights for policy 1, policy_version 13662 (0.0011) -[2023-10-15 02:46:45,832][88298] Updated weights for policy 0, policy_version 13570 (0.0009) -[2023-10-15 02:46:46,192][88298] Updated weights for policy 0, policy_version 13580 (0.0009) -[2023-10-15 02:46:46,569][88298] Updated weights for policy 0, policy_version 13590 (0.0009) -[2023-10-15 02:46:46,946][88298] Updated weights for policy 0, policy_version 13600 (0.0009) -[2023-10-15 02:46:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 27918336. Throughput: 0: 1746.5, 1: 1721.3. Samples: 6983644. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-15 02:46:48,534][87330] Avg episode reward: [(0, '22.350'), (1, '22.000')] -[2023-10-15 02:46:49,487][88300] Updated weights for policy 1, policy_version 13672 (0.0008) -[2023-10-15 02:46:49,855][88300] Updated weights for policy 1, policy_version 13682 (0.0009) -[2023-10-15 02:46:50,223][88300] Updated weights for policy 1, policy_version 13692 (0.0007) -[2023-10-15 02:46:50,866][88298] Updated weights for policy 0, policy_version 13610 (0.0008) -[2023-10-15 02:46:51,239][88298] Updated weights for policy 0, policy_version 13620 (0.0008) -[2023-10-15 02:46:51,612][88298] Updated weights for policy 0, policy_version 13630 (0.0008) -[2023-10-15 02:46:53,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 27983872. Throughput: 0: 1719.1, 1: 1725.6. Samples: 7003620. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-15 02:46:53,535][87330] Avg episode reward: [(0, '22.400'), (1, '21.830')] -[2023-10-15 02:46:54,339][88300] Updated weights for policy 1, policy_version 13702 (0.0007) -[2023-10-15 02:46:54,702][88300] Updated weights for policy 1, policy_version 13712 (0.0008) -[2023-10-15 02:46:55,073][88300] Updated weights for policy 1, policy_version 13722 (0.0007) -[2023-10-15 02:46:55,646][88298] Updated weights for policy 0, policy_version 13640 (0.0009) -[2023-10-15 02:46:56,030][88298] Updated weights for policy 0, policy_version 13650 (0.0009) -[2023-10-15 02:46:56,389][88298] Updated weights for policy 0, policy_version 13660 (0.0009) -[2023-10-15 02:46:58,534][87330] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 28049408. Throughput: 0: 1720.6, 1: 1754.7. Samples: 7025190. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-15 02:46:58,535][87330] Avg episode reward: [(0, '22.430'), (1, '21.800')] -[2023-10-15 02:46:58,546][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000013664_13991936.pth... -[2023-10-15 02:46:58,546][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000013728_14057472.pth... -[2023-10-15 02:46:58,577][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000012064_12353536.pth -[2023-10-15 02:46:58,577][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000012128_12419072.pth -[2023-10-15 02:46:58,932][88300] Updated weights for policy 1, policy_version 13732 (0.0008) -[2023-10-15 02:46:59,307][88300] Updated weights for policy 1, policy_version 13742 (0.0009) -[2023-10-15 02:46:59,682][88300] Updated weights for policy 1, policy_version 13752 (0.0009) -[2023-10-15 02:47:00,181][88298] Updated weights for policy 0, policy_version 13670 (0.0009) -[2023-10-15 02:47:00,556][88298] Updated weights for policy 0, policy_version 13680 (0.0007) -[2023-10-15 02:47:00,926][88298] Updated weights for policy 0, policy_version 13690 (0.0009) -[2023-10-15 02:47:03,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 28114944. Throughput: 0: 1727.6, 1: 1724.9. Samples: 7035406. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-15 02:47:03,535][87330] Avg episode reward: [(0, '22.440'), (1, '21.780')] -[2023-10-15 02:47:03,536][87905] Saving new best policy, reward=22.440! -[2023-10-15 02:47:03,644][88300] Updated weights for policy 1, policy_version 13762 (0.0009) -[2023-10-15 02:47:04,012][88300] Updated weights for policy 1, policy_version 13772 (0.0007) -[2023-10-15 02:47:04,384][88300] Updated weights for policy 1, policy_version 13782 (0.0008) -[2023-10-15 02:47:04,745][88300] Updated weights for policy 1, policy_version 13792 (0.0007) -[2023-10-15 02:47:04,829][88298] Updated weights for policy 0, policy_version 13700 (0.0011) -[2023-10-15 02:47:05,208][88298] Updated weights for policy 0, policy_version 13710 (0.0010) -[2023-10-15 02:47:05,578][88298] Updated weights for policy 0, policy_version 13720 (0.0007) -[2023-10-15 02:47:08,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 28180480. Throughput: 0: 1717.5, 1: 1750.2. Samples: 7056552. Policy #0 lag: (min: 2.0, avg: 11.1, max: 34.0) -[2023-10-15 02:47:08,535][87330] Avg episode reward: [(0, '22.460'), (1, '21.800')] -[2023-10-15 02:47:08,536][87905] Saving new best policy, reward=22.460! -[2023-10-15 02:47:08,639][88300] Updated weights for policy 1, policy_version 13802 (0.0007) -[2023-10-15 02:47:09,009][88300] Updated weights for policy 1, policy_version 13812 (0.0009) -[2023-10-15 02:47:09,343][88298] Updated weights for policy 0, policy_version 13730 (0.0009) -[2023-10-15 02:47:09,375][88300] Updated weights for policy 1, policy_version 13822 (0.0008) -[2023-10-15 02:47:09,715][88298] Updated weights for policy 0, policy_version 13740 (0.0008) -[2023-10-15 02:47:10,091][88298] Updated weights for policy 0, policy_version 13750 (0.0007) -[2023-10-15 02:47:10,463][88298] Updated weights for policy 0, policy_version 13760 (0.0007) -[2023-10-15 02:47:13,179][88300] Updated weights for policy 1, policy_version 13832 (0.0010) -[2023-10-15 02:47:13,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 28246016. Throughput: 0: 1742.5, 1: 1744.5. Samples: 7077850. Policy #0 lag: (min: 2.0, avg: 11.1, max: 34.0) -[2023-10-15 02:47:13,534][87330] Avg episode reward: [(0, '22.290'), (1, '22.040')] -[2023-10-15 02:47:13,553][88300] Updated weights for policy 1, policy_version 13842 (0.0008) -[2023-10-15 02:47:13,925][88300] Updated weights for policy 1, policy_version 13852 (0.0010) -[2023-10-15 02:47:14,350][88298] Updated weights for policy 0, policy_version 13770 (0.0010) -[2023-10-15 02:47:14,727][88298] Updated weights for policy 0, policy_version 13780 (0.0011) -[2023-10-15 02:47:15,095][88298] Updated weights for policy 0, policy_version 13790 (0.0008) -[2023-10-15 02:47:17,857][88300] Updated weights for policy 1, policy_version 13862 (0.0008) -[2023-10-15 02:47:18,226][88300] Updated weights for policy 1, policy_version 13872 (0.0007) -[2023-10-15 02:47:18,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 28311552. Throughput: 0: 1722.1, 1: 1744.8. Samples: 7087788. Policy #0 lag: (min: 2.0, avg: 11.1, max: 34.0) -[2023-10-15 02:47:18,535][87330] Avg episode reward: [(0, '22.200'), (1, '22.040')] -[2023-10-15 02:47:18,599][88300] Updated weights for policy 1, policy_version 13882 (0.0009) -[2023-10-15 02:47:18,998][88298] Updated weights for policy 0, policy_version 13800 (0.0007) -[2023-10-15 02:47:19,364][88298] Updated weights for policy 0, policy_version 13810 (0.0007) -[2023-10-15 02:47:19,732][88298] Updated weights for policy 0, policy_version 13820 (0.0008) -[2023-10-15 02:47:22,398][88300] Updated weights for policy 1, policy_version 13892 (0.0008) -[2023-10-15 02:47:22,765][88300] Updated weights for policy 1, policy_version 13902 (0.0011) -[2023-10-15 02:47:23,140][88300] Updated weights for policy 1, policy_version 13912 (0.0009) -[2023-10-15 02:47:23,423][88298] Updated weights for policy 0, policy_version 13830 (0.0008) -[2023-10-15 02:47:23,534][87330] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 28409856. Throughput: 0: 1734.9, 1: 1757.1. Samples: 7109460. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-15 02:47:23,534][87330] Avg episode reward: [(0, '22.120'), (1, '21.790')] -[2023-10-15 02:47:23,794][88298] Updated weights for policy 0, policy_version 13840 (0.0010) -[2023-10-15 02:47:24,162][88298] Updated weights for policy 0, policy_version 13850 (0.0009) -[2023-10-15 02:47:27,050][88300] Updated weights for policy 1, policy_version 13922 (0.0007) -[2023-10-15 02:47:27,466][88300] Updated weights for policy 1, policy_version 13932 (0.0008) -[2023-10-15 02:47:27,831][88300] Updated weights for policy 1, policy_version 13942 (0.0010) -[2023-10-15 02:47:28,151][88298] Updated weights for policy 0, policy_version 13860 (0.0007) -[2023-10-15 02:47:28,188][88300] Updated weights for policy 1, policy_version 13952 (0.0009) -[2023-10-15 02:47:28,534][87330] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 28475392. Throughput: 0: 1753.7, 1: 1727.4. Samples: 7129712. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-15 02:47:28,535][87330] Avg episode reward: [(0, '22.050'), (1, '21.810')] -[2023-10-15 02:47:28,537][88298] Updated weights for policy 0, policy_version 13870 (0.0008) -[2023-10-15 02:47:28,911][88298] Updated weights for policy 0, policy_version 13880 (0.0008) -[2023-10-15 02:47:32,029][88300] Updated weights for policy 1, policy_version 13962 (0.0008) -[2023-10-15 02:47:32,396][88300] Updated weights for policy 1, policy_version 13972 (0.0007) -[2023-10-15 02:47:32,696][88298] Updated weights for policy 0, policy_version 13890 (0.0009) -[2023-10-15 02:47:32,767][88300] Updated weights for policy 1, policy_version 13982 (0.0007) -[2023-10-15 02:47:33,059][88298] Updated weights for policy 0, policy_version 13900 (0.0009) -[2023-10-15 02:47:33,443][88298] Updated weights for policy 0, policy_version 13910 (0.0008) -[2023-10-15 02:47:33,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 28540928. Throughput: 0: 1730.2, 1: 1759.4. Samples: 7140674. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-15 02:47:33,534][87330] Avg episode reward: [(0, '21.920'), (1, '21.820')] -[2023-10-15 02:47:33,813][88298] Updated weights for policy 0, policy_version 13920 (0.0010) -[2023-10-15 02:47:36,736][88300] Updated weights for policy 1, policy_version 13992 (0.0008) -[2023-10-15 02:47:37,106][88300] Updated weights for policy 1, policy_version 14002 (0.0007) -[2023-10-15 02:47:37,470][88300] Updated weights for policy 1, policy_version 14012 (0.0010) -[2023-10-15 02:47:37,790][88298] Updated weights for policy 0, policy_version 13930 (0.0008) -[2023-10-15 02:47:38,171][88298] Updated weights for policy 0, policy_version 13940 (0.0009) -[2023-10-15 02:47:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 28606464. Throughput: 0: 1764.7, 1: 1741.0. Samples: 7161376. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-10-15 02:47:38,535][87330] Avg episode reward: [(0, '21.920'), (1, '21.800')] -[2023-10-15 02:47:38,546][88298] Updated weights for policy 0, policy_version 13950 (0.0008) -[2023-10-15 02:47:41,170][88300] Updated weights for policy 1, policy_version 14022 (0.0010) -[2023-10-15 02:47:41,535][88300] Updated weights for policy 1, policy_version 14032 (0.0007) -[2023-10-15 02:47:41,900][88300] Updated weights for policy 1, policy_version 14042 (0.0008) -[2023-10-15 02:47:42,468][88298] Updated weights for policy 0, policy_version 13960 (0.0007) -[2023-10-15 02:47:42,839][88298] Updated weights for policy 0, policy_version 13970 (0.0010) -[2023-10-15 02:47:43,218][88298] Updated weights for policy 0, policy_version 13980 (0.0007) -[2023-10-15 02:47:43,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 28704768. Throughput: 0: 1754.1, 1: 1729.5. Samples: 7181950. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-10-15 02:47:43,535][87330] Avg episode reward: [(0, '22.090'), (1, '21.650')] -[2023-10-15 02:47:45,918][88300] Updated weights for policy 1, policy_version 14052 (0.0008) -[2023-10-15 02:47:46,284][88300] Updated weights for policy 1, policy_version 14062 (0.0008) -[2023-10-15 02:47:46,656][88300] Updated weights for policy 1, policy_version 14072 (0.0008) -[2023-10-15 02:47:47,044][88298] Updated weights for policy 0, policy_version 13990 (0.0007) -[2023-10-15 02:47:47,419][88298] Updated weights for policy 0, policy_version 14000 (0.0007) -[2023-10-15 02:47:47,795][88298] Updated weights for policy 0, policy_version 14010 (0.0010) -[2023-10-15 02:47:48,534][87330] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 28770304. Throughput: 0: 1754.2, 1: 1746.5. Samples: 7192936. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-15 02:47:48,534][87330] Avg episode reward: [(0, '22.080'), (1, '21.330')] -[2023-10-15 02:47:50,568][88300] Updated weights for policy 1, policy_version 14082 (0.0009) -[2023-10-15 02:47:50,936][88300] Updated weights for policy 1, policy_version 14092 (0.0008) -[2023-10-15 02:47:51,307][88300] Updated weights for policy 1, policy_version 14102 (0.0008) -[2023-10-15 02:47:51,674][88300] Updated weights for policy 1, policy_version 14112 (0.0009) -[2023-10-15 02:47:51,690][88298] Updated weights for policy 0, policy_version 14020 (0.0010) -[2023-10-15 02:47:52,069][88298] Updated weights for policy 0, policy_version 14030 (0.0010) -[2023-10-15 02:47:52,440][88298] Updated weights for policy 0, policy_version 14040 (0.0007) -[2023-10-15 02:47:53,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 28835840. Throughput: 0: 1760.4, 1: 1723.2. Samples: 7213310. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-15 02:47:53,534][87330] Avg episode reward: [(0, '22.260'), (1, '21.380')] -[2023-10-15 02:47:55,663][88300] Updated weights for policy 1, policy_version 14122 (0.0007) -[2023-10-15 02:47:56,021][88300] Updated weights for policy 1, policy_version 14132 (0.0009) -[2023-10-15 02:47:56,336][88298] Updated weights for policy 0, policy_version 14050 (0.0008) -[2023-10-15 02:47:56,388][88300] Updated weights for policy 1, policy_version 14142 (0.0009) -[2023-10-15 02:47:56,707][88298] Updated weights for policy 0, policy_version 14060 (0.0009) -[2023-10-15 02:47:57,084][88298] Updated weights for policy 0, policy_version 14070 (0.0008) -[2023-10-15 02:47:57,443][88298] Updated weights for policy 0, policy_version 14080 (0.0009) -[2023-10-15 02:47:58,534][87330] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 28901376. Throughput: 0: 1734.7, 1: 1726.1. Samples: 7233586. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-15 02:47:58,535][87330] Avg episode reward: [(0, '22.270'), (1, '21.370')] -[2023-10-15 02:48:00,357][88300] Updated weights for policy 1, policy_version 14152 (0.0010) -[2023-10-15 02:48:00,732][88300] Updated weights for policy 1, policy_version 14162 (0.0009) -[2023-10-15 02:48:01,092][88300] Updated weights for policy 1, policy_version 14172 (0.0008) -[2023-10-15 02:48:01,263][88298] Updated weights for policy 0, policy_version 14090 (0.0008) -[2023-10-15 02:48:01,638][88298] Updated weights for policy 0, policy_version 14100 (0.0010) -[2023-10-15 02:48:02,007][88298] Updated weights for policy 0, policy_version 14110 (0.0009) -[2023-10-15 02:48:03,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 28966912. Throughput: 0: 1765.7, 1: 1720.2. Samples: 7244652. Policy #0 lag: (min: 17.0, avg: 26.6, max: 49.0) -[2023-10-15 02:48:03,535][87330] Avg episode reward: [(0, '22.370'), (1, '21.600')] -[2023-10-15 02:48:04,920][88300] Updated weights for policy 1, policy_version 14182 (0.0011) -[2023-10-15 02:48:05,301][88300] Updated weights for policy 1, policy_version 14192 (0.0010) -[2023-10-15 02:48:05,662][88300] Updated weights for policy 1, policy_version 14202 (0.0010) -[2023-10-15 02:48:05,916][88298] Updated weights for policy 0, policy_version 14120 (0.0008) -[2023-10-15 02:48:06,289][88298] Updated weights for policy 0, policy_version 14130 (0.0009) -[2023-10-15 02:48:06,667][88298] Updated weights for policy 0, policy_version 14140 (0.0009) -[2023-10-15 02:48:08,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 29032448. Throughput: 0: 1735.8, 1: 1716.4. Samples: 7264812. Policy #0 lag: (min: 17.0, avg: 26.6, max: 49.0) -[2023-10-15 02:48:08,534][87330] Avg episode reward: [(0, '22.060'), (1, '21.480')] -[2023-10-15 02:48:09,701][88300] Updated weights for policy 1, policy_version 14212 (0.0008) -[2023-10-15 02:48:10,080][88300] Updated weights for policy 1, policy_version 14222 (0.0008) -[2023-10-15 02:48:10,444][88300] Updated weights for policy 1, policy_version 14232 (0.0009) -[2023-10-15 02:48:10,549][88298] Updated weights for policy 0, policy_version 14150 (0.0008) -[2023-10-15 02:48:10,918][88298] Updated weights for policy 0, policy_version 14160 (0.0007) -[2023-10-15 02:48:11,287][88298] Updated weights for policy 0, policy_version 14170 (0.0009) -[2023-10-15 02:48:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 29097984. Throughput: 0: 1731.9, 1: 1748.7. Samples: 7286340. Policy #0 lag: (min: 17.0, avg: 26.6, max: 49.0) -[2023-10-15 02:48:13,535][87330] Avg episode reward: [(0, '22.070'), (1, '21.660')] -[2023-10-15 02:48:14,458][88300] Updated weights for policy 1, policy_version 14242 (0.0010) -[2023-10-15 02:48:14,859][88300] Updated weights for policy 1, policy_version 14252 (0.0007) -[2023-10-15 02:48:15,219][88300] Updated weights for policy 1, policy_version 14262 (0.0007) -[2023-10-15 02:48:15,284][88298] Updated weights for policy 0, policy_version 14180 (0.0010) -[2023-10-15 02:48:15,592][88300] Updated weights for policy 1, policy_version 14272 (0.0007) -[2023-10-15 02:48:15,673][88298] Updated weights for policy 0, policy_version 14190 (0.0008) -[2023-10-15 02:48:16,047][88298] Updated weights for policy 0, policy_version 14200 (0.0008) -[2023-10-15 02:48:18,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 29163520. Throughput: 0: 1743.3, 1: 1710.0. Samples: 7296072. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-15 02:48:18,535][87330] Avg episode reward: [(0, '22.050'), (1, '21.850')] -[2023-10-15 02:48:19,366][88300] Updated weights for policy 1, policy_version 14282 (0.0009) -[2023-10-15 02:48:19,735][88300] Updated weights for policy 1, policy_version 14292 (0.0010) -[2023-10-15 02:48:19,858][88298] Updated weights for policy 0, policy_version 14210 (0.0010) -[2023-10-15 02:48:20,108][88300] Updated weights for policy 1, policy_version 14302 (0.0007) -[2023-10-15 02:48:20,226][88298] Updated weights for policy 0, policy_version 14220 (0.0007) -[2023-10-15 02:48:20,613][88298] Updated weights for policy 0, policy_version 14230 (0.0009) -[2023-10-15 02:48:20,981][88298] Updated weights for policy 0, policy_version 14240 (0.0011) -[2023-10-15 02:48:23,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 29229056. Throughput: 0: 1726.7, 1: 1736.4. Samples: 7317218. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-15 02:48:23,534][87330] Avg episode reward: [(0, '22.030'), (1, '22.270')] -[2023-10-15 02:48:23,536][88033] Saving new best policy, reward=22.270! -[2023-10-15 02:48:24,078][88300] Updated weights for policy 1, policy_version 14312 (0.0008) -[2023-10-15 02:48:24,439][88300] Updated weights for policy 1, policy_version 14322 (0.0008) -[2023-10-15 02:48:24,812][88300] Updated weights for policy 1, policy_version 14332 (0.0008) -[2023-10-15 02:48:24,830][88298] Updated weights for policy 0, policy_version 14250 (0.0007) -[2023-10-15 02:48:25,196][88298] Updated weights for policy 0, policy_version 14260 (0.0008) -[2023-10-15 02:48:25,574][88298] Updated weights for policy 0, policy_version 14270 (0.0009) -[2023-10-15 02:48:28,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 29294592. Throughput: 0: 1741.4, 1: 1747.0. Samples: 7338928. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-15 02:48:28,534][87330] Avg episode reward: [(0, '22.030'), (1, '22.120')] -[2023-10-15 02:48:28,596][88300] Updated weights for policy 1, policy_version 14342 (0.0007) -[2023-10-15 02:48:28,962][88300] Updated weights for policy 1, policy_version 14352 (0.0009) -[2023-10-15 02:48:29,343][88300] Updated weights for policy 1, policy_version 14362 (0.0008) -[2023-10-15 02:48:29,455][88298] Updated weights for policy 0, policy_version 14280 (0.0007) -[2023-10-15 02:48:29,821][88298] Updated weights for policy 0, policy_version 14290 (0.0008) -[2023-10-15 02:48:30,193][88298] Updated weights for policy 0, policy_version 14300 (0.0007) -[2023-10-15 02:48:33,215][88300] Updated weights for policy 1, policy_version 14372 (0.0008) -[2023-10-15 02:48:33,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 29360128. Throughput: 0: 1727.0, 1: 1730.8. Samples: 7348534. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:48:33,534][87330] Avg episode reward: [(0, '22.040'), (1, '21.920')] -[2023-10-15 02:48:33,583][88300] Updated weights for policy 1, policy_version 14382 (0.0009) -[2023-10-15 02:48:33,941][88300] Updated weights for policy 1, policy_version 14392 (0.0008) -[2023-10-15 02:48:33,984][88298] Updated weights for policy 0, policy_version 14310 (0.0008) -[2023-10-15 02:48:34,366][88298] Updated weights for policy 0, policy_version 14320 (0.0008) -[2023-10-15 02:48:34,739][88298] Updated weights for policy 0, policy_version 14330 (0.0009) -[2023-10-15 02:48:37,804][88300] Updated weights for policy 1, policy_version 14402 (0.0008) -[2023-10-15 02:48:38,168][88300] Updated weights for policy 1, policy_version 14412 (0.0010) -[2023-10-15 02:48:38,534][88300] Updated weights for policy 1, policy_version 14422 (0.0009) -[2023-10-15 02:48:38,534][87330] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 29425664. Throughput: 0: 1730.3, 1: 1752.7. Samples: 7370046. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:48:38,535][87330] Avg episode reward: [(0, '22.160'), (1, '21.810')] -[2023-10-15 02:48:38,579][88298] Updated weights for policy 0, policy_version 14340 (0.0009) -[2023-10-15 02:48:38,905][88300] Updated weights for policy 1, policy_version 14432 (0.0007) -[2023-10-15 02:48:38,956][88298] Updated weights for policy 0, policy_version 14350 (0.0008) -[2023-10-15 02:48:39,330][88298] Updated weights for policy 0, policy_version 14360 (0.0007) -[2023-10-15 02:48:42,845][88300] Updated weights for policy 1, policy_version 14442 (0.0009) -[2023-10-15 02:48:43,215][88300] Updated weights for policy 1, policy_version 14452 (0.0007) -[2023-10-15 02:48:43,446][88298] Updated weights for policy 0, policy_version 14370 (0.0009) -[2023-10-15 02:48:43,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 29491200. Throughput: 0: 1751.7, 1: 1737.8. Samples: 7390614. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:48:43,535][87330] Avg episode reward: [(0, '22.230'), (1, '21.880')] -[2023-10-15 02:48:43,582][88300] Updated weights for policy 1, policy_version 14462 (0.0007) -[2023-10-15 02:48:43,818][88298] Updated weights for policy 0, policy_version 14380 (0.0007) -[2023-10-15 02:48:44,185][88298] Updated weights for policy 0, policy_version 14390 (0.0008) -[2023-10-15 02:48:44,554][88298] Updated weights for policy 0, policy_version 14400 (0.0010) -[2023-10-15 02:48:47,430][88300] Updated weights for policy 1, policy_version 14472 (0.0008) -[2023-10-15 02:48:47,795][88300] Updated weights for policy 1, policy_version 14482 (0.0008) -[2023-10-15 02:48:48,163][88300] Updated weights for policy 1, policy_version 14492 (0.0009) -[2023-10-15 02:48:48,527][88298] Updated weights for policy 0, policy_version 14410 (0.0009) -[2023-10-15 02:48:48,534][87330] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 29589504. Throughput: 0: 1718.3, 1: 1753.6. Samples: 7400888. Policy #0 lag: (min: 8.0, avg: 26.7, max: 40.0) -[2023-10-15 02:48:48,535][87330] Avg episode reward: [(0, '22.150'), (1, '21.660')] -[2023-10-15 02:48:48,910][88298] Updated weights for policy 0, policy_version 14420 (0.0011) -[2023-10-15 02:48:49,278][88298] Updated weights for policy 0, policy_version 14430 (0.0010) -[2023-10-15 02:48:52,124][88300] Updated weights for policy 1, policy_version 14502 (0.0008) -[2023-10-15 02:48:52,496][88300] Updated weights for policy 1, policy_version 14512 (0.0010) -[2023-10-15 02:48:52,872][88300] Updated weights for policy 1, policy_version 14522 (0.0008) -[2023-10-15 02:48:53,185][88298] Updated weights for policy 0, policy_version 14440 (0.0008) -[2023-10-15 02:48:53,534][87330] Fps is (10 sec: 16384.3, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 29655040. Throughput: 0: 1743.5, 1: 1749.7. Samples: 7422006. Policy #0 lag: (min: 8.0, avg: 26.7, max: 40.0) -[2023-10-15 02:48:53,534][87330] Avg episode reward: [(0, '22.220'), (1, '21.610')] -[2023-10-15 02:48:53,551][88298] Updated weights for policy 0, policy_version 14450 (0.0008) -[2023-10-15 02:48:53,922][88298] Updated weights for policy 0, policy_version 14460 (0.0010) -[2023-10-15 02:48:56,783][88300] Updated weights for policy 1, policy_version 14532 (0.0009) -[2023-10-15 02:48:57,145][88300] Updated weights for policy 1, policy_version 14542 (0.0009) -[2023-10-15 02:48:57,516][88300] Updated weights for policy 1, policy_version 14552 (0.0009) -[2023-10-15 02:48:57,741][88298] Updated weights for policy 0, policy_version 14470 (0.0007) -[2023-10-15 02:48:58,114][88298] Updated weights for policy 0, policy_version 14480 (0.0007) -[2023-10-15 02:48:58,481][88298] Updated weights for policy 0, policy_version 14490 (0.0009) -[2023-10-15 02:48:58,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 29720576. Throughput: 0: 1742.3, 1: 1731.5. Samples: 7442658. Policy #0 lag: (min: 8.0, avg: 26.7, max: 40.0) -[2023-10-15 02:48:58,534][87330] Avg episode reward: [(0, '22.190'), (1, '21.530')] -[2023-10-15 02:48:58,546][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000014560_14909440.pth... -[2023-10-15 02:48:58,581][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000012928_13238272.pth -[2023-10-15 02:48:58,702][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000014496_14843904.pth... -[2023-10-15 02:48:58,731][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000012864_13172736.pth -[2023-10-15 02:49:01,346][88300] Updated weights for policy 1, policy_version 14562 (0.0009) -[2023-10-15 02:49:01,743][88300] Updated weights for policy 1, policy_version 14572 (0.0010) -[2023-10-15 02:49:02,127][88300] Updated weights for policy 1, policy_version 14582 (0.0010) -[2023-10-15 02:49:02,388][88298] Updated weights for policy 0, policy_version 14500 (0.0009) -[2023-10-15 02:49:02,494][88300] Updated weights for policy 1, policy_version 14592 (0.0007) -[2023-10-15 02:49:02,759][88298] Updated weights for policy 0, policy_version 14510 (0.0009) -[2023-10-15 02:49:03,122][88298] Updated weights for policy 0, policy_version 14520 (0.0008) -[2023-10-15 02:49:03,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 29818880. Throughput: 0: 1736.8, 1: 1770.2. Samples: 7453886. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:49:03,534][87330] Avg episode reward: [(0, '22.220'), (1, '21.700')] -[2023-10-15 02:49:06,157][88300] Updated weights for policy 1, policy_version 14602 (0.0009) -[2023-10-15 02:49:06,521][88300] Updated weights for policy 1, policy_version 14612 (0.0009) -[2023-10-15 02:49:06,894][88300] Updated weights for policy 1, policy_version 14622 (0.0008) -[2023-10-15 02:49:07,046][88298] Updated weights for policy 0, policy_version 14530 (0.0009) -[2023-10-15 02:49:07,425][88298] Updated weights for policy 0, policy_version 14540 (0.0009) -[2023-10-15 02:49:07,798][88298] Updated weights for policy 0, policy_version 14550 (0.0008) -[2023-10-15 02:49:08,164][88298] Updated weights for policy 0, policy_version 14560 (0.0007) -[2023-10-15 02:49:08,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 29884416. Throughput: 0: 1750.4, 1: 1734.0. Samples: 7474018. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:49:08,534][87330] Avg episode reward: [(0, '22.010'), (1, '21.910')] -[2023-10-15 02:49:10,712][88300] Updated weights for policy 1, policy_version 14632 (0.0007) -[2023-10-15 02:49:11,085][88300] Updated weights for policy 1, policy_version 14642 (0.0007) -[2023-10-15 02:49:11,453][88300] Updated weights for policy 1, policy_version 14652 (0.0008) -[2023-10-15 02:49:11,929][88298] Updated weights for policy 0, policy_version 14570 (0.0009) -[2023-10-15 02:49:12,301][88298] Updated weights for policy 0, policy_version 14580 (0.0007) -[2023-10-15 02:49:12,673][88298] Updated weights for policy 0, policy_version 14590 (0.0009) -[2023-10-15 02:49:13,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 29949952. Throughput: 0: 1715.9, 1: 1738.8. Samples: 7494388. Policy #0 lag: (min: 23.0, avg: 30.0, max: 55.0) -[2023-10-15 02:49:13,535][87330] Avg episode reward: [(0, '22.120'), (1, '22.000')] -[2023-10-15 02:49:15,310][88300] Updated weights for policy 1, policy_version 14662 (0.0008) -[2023-10-15 02:49:15,674][88300] Updated weights for policy 1, policy_version 14672 (0.0007) -[2023-10-15 02:49:16,048][88300] Updated weights for policy 1, policy_version 14682 (0.0008) -[2023-10-15 02:49:16,540][88298] Updated weights for policy 0, policy_version 14600 (0.0008) -[2023-10-15 02:49:16,914][88298] Updated weights for policy 0, policy_version 14610 (0.0009) -[2023-10-15 02:49:17,291][88298] Updated weights for policy 0, policy_version 14620 (0.0008) -[2023-10-15 02:49:18,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 30015488. Throughput: 0: 1744.6, 1: 1736.3. Samples: 7505176. Policy #0 lag: (min: 23.0, avg: 30.0, max: 55.0) -[2023-10-15 02:49:18,534][87330] Avg episode reward: [(0, '22.120'), (1, '22.010')] -[2023-10-15 02:49:19,844][88300] Updated weights for policy 1, policy_version 14692 (0.0008) -[2023-10-15 02:49:20,219][88300] Updated weights for policy 1, policy_version 14702 (0.0009) -[2023-10-15 02:49:20,577][88300] Updated weights for policy 1, policy_version 14712 (0.0010) -[2023-10-15 02:49:21,166][88298] Updated weights for policy 0, policy_version 14630 (0.0010) -[2023-10-15 02:49:21,531][88298] Updated weights for policy 0, policy_version 14640 (0.0010) -[2023-10-15 02:49:21,906][88298] Updated weights for policy 0, policy_version 14650 (0.0008) -[2023-10-15 02:49:23,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 30081024. Throughput: 0: 1725.4, 1: 1739.3. Samples: 7525956. Policy #0 lag: (min: 23.0, avg: 30.0, max: 55.0) -[2023-10-15 02:49:23,534][87330] Avg episode reward: [(0, '22.100'), (1, '22.260')] -[2023-10-15 02:49:24,492][88300] Updated weights for policy 1, policy_version 14722 (0.0009) -[2023-10-15 02:49:24,870][88300] Updated weights for policy 1, policy_version 14732 (0.0007) -[2023-10-15 02:49:25,238][88300] Updated weights for policy 1, policy_version 14742 (0.0007) -[2023-10-15 02:49:25,615][88300] Updated weights for policy 1, policy_version 14752 (0.0008) -[2023-10-15 02:49:25,865][88298] Updated weights for policy 0, policy_version 14660 (0.0008) -[2023-10-15 02:49:26,228][88298] Updated weights for policy 0, policy_version 14670 (0.0010) -[2023-10-15 02:49:26,592][88298] Updated weights for policy 0, policy_version 14680 (0.0010) -[2023-10-15 02:49:28,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 30146560. Throughput: 0: 1719.0, 1: 1756.8. Samples: 7547026. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:49:28,535][87330] Avg episode reward: [(0, '22.100'), (1, '22.120')] -[2023-10-15 02:49:29,571][88300] Updated weights for policy 1, policy_version 14762 (0.0008) -[2023-10-15 02:49:29,943][88300] Updated weights for policy 1, policy_version 14772 (0.0007) -[2023-10-15 02:49:30,307][88300] Updated weights for policy 1, policy_version 14782 (0.0010) -[2023-10-15 02:49:30,529][88298] Updated weights for policy 0, policy_version 14690 (0.0008) -[2023-10-15 02:49:30,903][88298] Updated weights for policy 0, policy_version 14700 (0.0008) -[2023-10-15 02:49:31,272][88298] Updated weights for policy 0, policy_version 14710 (0.0009) -[2023-10-15 02:49:31,643][88298] Updated weights for policy 0, policy_version 14720 (0.0009) -[2023-10-15 02:49:33,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 30212096. Throughput: 0: 1742.9, 1: 1739.8. Samples: 7557610. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:49:33,534][87330] Avg episode reward: [(0, '21.750'), (1, '22.130')] -[2023-10-15 02:49:34,162][88300] Updated weights for policy 1, policy_version 14792 (0.0008) -[2023-10-15 02:49:34,530][88300] Updated weights for policy 1, policy_version 14802 (0.0009) -[2023-10-15 02:49:34,888][88300] Updated weights for policy 1, policy_version 14812 (0.0010) -[2023-10-15 02:49:35,532][88298] Updated weights for policy 0, policy_version 14730 (0.0008) -[2023-10-15 02:49:35,906][88298] Updated weights for policy 0, policy_version 14740 (0.0007) -[2023-10-15 02:49:36,270][88298] Updated weights for policy 0, policy_version 14750 (0.0010) -[2023-10-15 02:49:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 30277632. Throughput: 0: 1726.8, 1: 1747.3. Samples: 7578342. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:49:38,535][87330] Avg episode reward: [(0, '21.950'), (1, '22.090')] -[2023-10-15 02:49:38,782][88300] Updated weights for policy 1, policy_version 14822 (0.0008) -[2023-10-15 02:49:39,148][88300] Updated weights for policy 1, policy_version 14832 (0.0009) -[2023-10-15 02:49:39,517][88300] Updated weights for policy 1, policy_version 14842 (0.0008) -[2023-10-15 02:49:40,207][88298] Updated weights for policy 0, policy_version 14760 (0.0007) -[2023-10-15 02:49:40,578][88298] Updated weights for policy 0, policy_version 14770 (0.0009) -[2023-10-15 02:49:40,958][88298] Updated weights for policy 0, policy_version 14780 (0.0008) -[2023-10-15 02:49:43,455][88300] Updated weights for policy 1, policy_version 14852 (0.0009) -[2023-10-15 02:49:43,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 30343168. Throughput: 0: 1728.7, 1: 1765.6. Samples: 7599900. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-15 02:49:43,535][87330] Avg episode reward: [(0, '21.760'), (1, '22.130')] -[2023-10-15 02:49:43,817][88300] Updated weights for policy 1, policy_version 14862 (0.0007) -[2023-10-15 02:49:44,190][88300] Updated weights for policy 1, policy_version 14872 (0.0007) -[2023-10-15 02:49:44,964][88298] Updated weights for policy 0, policy_version 14790 (0.0010) -[2023-10-15 02:49:45,336][88298] Updated weights for policy 0, policy_version 14800 (0.0010) -[2023-10-15 02:49:45,710][88298] Updated weights for policy 0, policy_version 14810 (0.0008) -[2023-10-15 02:49:48,285][88300] Updated weights for policy 1, policy_version 14882 (0.0008) -[2023-10-15 02:49:48,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 30408704. Throughput: 0: 1727.2, 1: 1731.6. Samples: 7609530. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-15 02:49:48,534][87330] Avg episode reward: [(0, '21.740'), (1, '22.130')] -[2023-10-15 02:49:48,712][88300] Updated weights for policy 1, policy_version 14892 (0.0009) -[2023-10-15 02:49:49,085][88300] Updated weights for policy 1, policy_version 14902 (0.0007) -[2023-10-15 02:49:49,447][88300] Updated weights for policy 1, policy_version 14912 (0.0007) -[2023-10-15 02:49:49,727][88298] Updated weights for policy 0, policy_version 14820 (0.0008) -[2023-10-15 02:49:50,126][88298] Updated weights for policy 0, policy_version 14830 (0.0007) -[2023-10-15 02:49:50,497][88298] Updated weights for policy 0, policy_version 14840 (0.0007) -[2023-10-15 02:49:53,337][88300] Updated weights for policy 1, policy_version 14922 (0.0009) -[2023-10-15 02:49:53,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 30474240. Throughput: 0: 1718.4, 1: 1756.2. Samples: 7630372. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-15 02:49:53,534][87330] Avg episode reward: [(0, '21.860'), (1, '22.000')] -[2023-10-15 02:49:53,696][88300] Updated weights for policy 1, policy_version 14932 (0.0008) -[2023-10-15 02:49:54,068][88300] Updated weights for policy 1, policy_version 14942 (0.0008) -[2023-10-15 02:49:54,576][88298] Updated weights for policy 0, policy_version 14850 (0.0008) -[2023-10-15 02:49:54,947][88298] Updated weights for policy 0, policy_version 14860 (0.0011) -[2023-10-15 02:49:55,319][88298] Updated weights for policy 0, policy_version 14870 (0.0010) -[2023-10-15 02:49:55,689][88298] Updated weights for policy 0, policy_version 14880 (0.0010) -[2023-10-15 02:49:57,870][88300] Updated weights for policy 1, policy_version 14952 (0.0007) -[2023-10-15 02:49:58,240][88300] Updated weights for policy 1, policy_version 14962 (0.0007) -[2023-10-15 02:49:58,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 30539776. Throughput: 0: 1745.8, 1: 1738.2. Samples: 7651170. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:49:58,534][87330] Avg episode reward: [(0, '21.820'), (1, '22.050')] -[2023-10-15 02:49:58,611][88300] Updated weights for policy 1, policy_version 14972 (0.0007) -[2023-10-15 02:49:59,628][88298] Updated weights for policy 0, policy_version 14890 (0.0008) -[2023-10-15 02:50:00,007][88298] Updated weights for policy 0, policy_version 14900 (0.0007) -[2023-10-15 02:50:00,384][88298] Updated weights for policy 0, policy_version 14910 (0.0008) -[2023-10-15 02:50:02,553][88300] Updated weights for policy 1, policy_version 14982 (0.0007) -[2023-10-15 02:50:02,917][88300] Updated weights for policy 1, policy_version 14992 (0.0007) -[2023-10-15 02:50:03,288][88300] Updated weights for policy 1, policy_version 15002 (0.0007) -[2023-10-15 02:50:03,534][87330] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 30638080. Throughput: 0: 1716.3, 1: 1752.8. Samples: 7661286. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:50:03,534][87330] Avg episode reward: [(0, '22.050'), (1, '22.290')] -[2023-10-15 02:50:03,535][88033] Saving new best policy, reward=22.290! -[2023-10-15 02:50:04,125][88298] Updated weights for policy 0, policy_version 14920 (0.0008) -[2023-10-15 02:50:04,486][88298] Updated weights for policy 0, policy_version 14930 (0.0007) -[2023-10-15 02:50:04,853][88298] Updated weights for policy 0, policy_version 14940 (0.0008) -[2023-10-15 02:50:07,251][88300] Updated weights for policy 1, policy_version 15012 (0.0007) -[2023-10-15 02:50:07,617][88300] Updated weights for policy 1, policy_version 15022 (0.0010) -[2023-10-15 02:50:07,985][88300] Updated weights for policy 1, policy_version 15032 (0.0010) -[2023-10-15 02:50:08,534][87330] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 30703616. Throughput: 0: 1736.9, 1: 1748.1. Samples: 7682780. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:50:08,535][87330] Avg episode reward: [(0, '22.210'), (1, '22.320')] -[2023-10-15 02:50:08,536][88033] Saving new best policy, reward=22.320! -[2023-10-15 02:50:08,727][88298] Updated weights for policy 0, policy_version 14950 (0.0008) -[2023-10-15 02:50:09,095][88298] Updated weights for policy 0, policy_version 14960 (0.0007) -[2023-10-15 02:50:09,472][88298] Updated weights for policy 0, policy_version 14970 (0.0009) -[2023-10-15 02:50:11,835][88300] Updated weights for policy 1, policy_version 15042 (0.0010) -[2023-10-15 02:50:12,208][88300] Updated weights for policy 1, policy_version 15052 (0.0007) -[2023-10-15 02:50:12,566][88300] Updated weights for policy 1, policy_version 15062 (0.0010) -[2023-10-15 02:50:12,930][88300] Updated weights for policy 1, policy_version 15072 (0.0007) -[2023-10-15 02:50:13,352][88298] Updated weights for policy 0, policy_version 14980 (0.0008) -[2023-10-15 02:50:13,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 30769152. Throughput: 0: 1747.8, 1: 1724.4. Samples: 7703278. Policy #0 lag: (min: 5.0, avg: 12.9, max: 37.0) -[2023-10-15 02:50:13,535][87330] Avg episode reward: [(0, '22.050'), (1, '22.170')] -[2023-10-15 02:50:13,719][88298] Updated weights for policy 0, policy_version 14990 (0.0008) -[2023-10-15 02:50:14,095][88298] Updated weights for policy 0, policy_version 15000 (0.0007) -[2023-10-15 02:50:16,845][88300] Updated weights for policy 1, policy_version 15082 (0.0009) -[2023-10-15 02:50:17,217][88300] Updated weights for policy 1, policy_version 15092 (0.0008) -[2023-10-15 02:50:17,577][88300] Updated weights for policy 1, policy_version 15102 (0.0008) -[2023-10-15 02:50:17,954][88298] Updated weights for policy 0, policy_version 15010 (0.0007) -[2023-10-15 02:50:18,329][88298] Updated weights for policy 0, policy_version 15020 (0.0008) -[2023-10-15 02:50:18,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 30834688. Throughput: 0: 1724.3, 1: 1754.9. Samples: 7714178. Policy #0 lag: (min: 5.0, avg: 12.9, max: 37.0) -[2023-10-15 02:50:18,534][87330] Avg episode reward: [(0, '22.280'), (1, '22.000')] -[2023-10-15 02:50:18,703][88298] Updated weights for policy 0, policy_version 15030 (0.0008) -[2023-10-15 02:50:19,069][88298] Updated weights for policy 0, policy_version 15040 (0.0009) -[2023-10-15 02:50:21,331][88300] Updated weights for policy 1, policy_version 15112 (0.0009) -[2023-10-15 02:50:21,701][88300] Updated weights for policy 1, policy_version 15122 (0.0008) -[2023-10-15 02:50:22,064][88300] Updated weights for policy 1, policy_version 15132 (0.0010) -[2023-10-15 02:50:23,018][88298] Updated weights for policy 0, policy_version 15050 (0.0011) -[2023-10-15 02:50:23,395][88298] Updated weights for policy 0, policy_version 15060 (0.0010) -[2023-10-15 02:50:23,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 30900224. Throughput: 0: 1746.1, 1: 1723.5. Samples: 7734472. Policy #0 lag: (min: 5.0, avg: 12.9, max: 37.0) -[2023-10-15 02:50:23,535][87330] Avg episode reward: [(0, '22.220'), (1, '22.160')] -[2023-10-15 02:50:23,760][88298] Updated weights for policy 0, policy_version 15070 (0.0010) -[2023-10-15 02:50:25,818][88300] Updated weights for policy 1, policy_version 15142 (0.0008) -[2023-10-15 02:50:26,193][88300] Updated weights for policy 1, policy_version 15152 (0.0008) -[2023-10-15 02:50:26,556][88300] Updated weights for policy 1, policy_version 15162 (0.0009) -[2023-10-15 02:50:27,628][88298] Updated weights for policy 0, policy_version 15080 (0.0008) -[2023-10-15 02:50:27,995][88298] Updated weights for policy 0, policy_version 15090 (0.0009) -[2023-10-15 02:50:28,369][88298] Updated weights for policy 0, policy_version 15100 (0.0009) -[2023-10-15 02:50:28,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 30998528. Throughput: 0: 1737.5, 1: 1724.9. Samples: 7755710. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-15 02:50:28,534][87330] Avg episode reward: [(0, '22.180'), (1, '22.180')] -[2023-10-15 02:50:30,536][88300] Updated weights for policy 1, policy_version 15172 (0.0008) -[2023-10-15 02:50:30,902][88300] Updated weights for policy 1, policy_version 15182 (0.0008) -[2023-10-15 02:50:31,274][88300] Updated weights for policy 1, policy_version 15192 (0.0009) -[2023-10-15 02:50:32,402][88298] Updated weights for policy 0, policy_version 15110 (0.0010) -[2023-10-15 02:50:32,778][88298] Updated weights for policy 0, policy_version 15120 (0.0008) -[2023-10-15 02:50:33,152][88298] Updated weights for policy 0, policy_version 15130 (0.0009) -[2023-10-15 02:50:33,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 31064064. Throughput: 0: 1741.0, 1: 1738.8. Samples: 7766124. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-15 02:50:33,535][87330] Avg episode reward: [(0, '21.910'), (1, '21.990')] -[2023-10-15 02:50:35,236][88300] Updated weights for policy 1, policy_version 15202 (0.0008) -[2023-10-15 02:50:35,600][88300] Updated weights for policy 1, policy_version 15212 (0.0008) -[2023-10-15 02:50:35,973][88300] Updated weights for policy 1, policy_version 15222 (0.0007) -[2023-10-15 02:50:36,347][88300] Updated weights for policy 1, policy_version 15232 (0.0010) -[2023-10-15 02:50:37,172][88298] Updated weights for policy 0, policy_version 15140 (0.0007) -[2023-10-15 02:50:37,561][88298] Updated weights for policy 0, policy_version 15150 (0.0009) -[2023-10-15 02:50:37,931][88298] Updated weights for policy 0, policy_version 15160 (0.0009) -[2023-10-15 02:50:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 31129600. Throughput: 0: 1748.0, 1: 1736.2. Samples: 7787164. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:50:38,534][87330] Avg episode reward: [(0, '21.900'), (1, '21.980')] -[2023-10-15 02:50:40,209][88300] Updated weights for policy 1, policy_version 15242 (0.0009) -[2023-10-15 02:50:40,579][88300] Updated weights for policy 1, policy_version 15252 (0.0009) -[2023-10-15 02:50:40,954][88300] Updated weights for policy 1, policy_version 15262 (0.0009) -[2023-10-15 02:50:41,667][88298] Updated weights for policy 0, policy_version 15170 (0.0007) -[2023-10-15 02:50:42,041][88298] Updated weights for policy 0, policy_version 15180 (0.0008) -[2023-10-15 02:50:42,412][88298] Updated weights for policy 0, policy_version 15190 (0.0008) -[2023-10-15 02:50:42,786][88298] Updated weights for policy 0, policy_version 15200 (0.0010) -[2023-10-15 02:50:43,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 31195136. Throughput: 0: 1724.1, 1: 1746.0. Samples: 7807326. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:50:43,534][87330] Avg episode reward: [(0, '21.880'), (1, '22.170')] -[2023-10-15 02:50:44,938][88300] Updated weights for policy 1, policy_version 15272 (0.0007) -[2023-10-15 02:50:45,297][88300] Updated weights for policy 1, policy_version 15282 (0.0007) -[2023-10-15 02:50:45,672][88300] Updated weights for policy 1, policy_version 15292 (0.0009) -[2023-10-15 02:50:46,641][88298] Updated weights for policy 0, policy_version 15210 (0.0008) -[2023-10-15 02:50:47,007][88298] Updated weights for policy 0, policy_version 15220 (0.0010) -[2023-10-15 02:50:47,381][88298] Updated weights for policy 0, policy_version 15230 (0.0007) -[2023-10-15 02:50:48,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 31260672. Throughput: 0: 1756.3, 1: 1729.1. Samples: 7818128. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:50:48,534][87330] Avg episode reward: [(0, '22.060'), (1, '22.030')] -[2023-10-15 02:50:49,535][88300] Updated weights for policy 1, policy_version 15302 (0.0009) -[2023-10-15 02:50:49,905][88300] Updated weights for policy 1, policy_version 15312 (0.0009) -[2023-10-15 02:50:50,270][88300] Updated weights for policy 1, policy_version 15322 (0.0007) -[2023-10-15 02:50:51,333][88298] Updated weights for policy 0, policy_version 15240 (0.0007) -[2023-10-15 02:50:51,702][88298] Updated weights for policy 0, policy_version 15250 (0.0008) -[2023-10-15 02:50:52,069][88298] Updated weights for policy 0, policy_version 15260 (0.0007) -[2023-10-15 02:50:53,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 31326208. Throughput: 0: 1735.2, 1: 1736.6. Samples: 7839010. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-15 02:50:53,535][87330] Avg episode reward: [(0, '22.020'), (1, '21.970')] -[2023-10-15 02:50:54,073][88300] Updated weights for policy 1, policy_version 15332 (0.0008) -[2023-10-15 02:50:54,448][88300] Updated weights for policy 1, policy_version 15342 (0.0009) -[2023-10-15 02:50:54,818][88300] Updated weights for policy 1, policy_version 15352 (0.0010) -[2023-10-15 02:50:55,978][88298] Updated weights for policy 0, policy_version 15270 (0.0007) -[2023-10-15 02:50:56,346][88298] Updated weights for policy 0, policy_version 15280 (0.0009) -[2023-10-15 02:50:56,711][88298] Updated weights for policy 0, policy_version 15290 (0.0011) -[2023-10-15 02:50:58,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 31391744. Throughput: 0: 1721.3, 1: 1760.8. Samples: 7859976. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-15 02:50:58,534][87330] Avg episode reward: [(0, '22.080'), (1, '21.790')] -[2023-10-15 02:50:58,542][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000015296_15663104.pth... -[2023-10-15 02:50:58,578][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000013664_13991936.pth -[2023-10-15 02:50:58,686][88300] Updated weights for policy 1, policy_version 15362 (0.0011) -[2023-10-15 02:50:59,054][88300] Updated weights for policy 1, policy_version 15372 (0.0007) -[2023-10-15 02:50:59,422][88300] Updated weights for policy 1, policy_version 15382 (0.0010) -[2023-10-15 02:50:59,788][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000015392_15761408.pth... -[2023-10-15 02:50:59,792][88300] Updated weights for policy 1, policy_version 15392 (0.0009) -[2023-10-15 02:50:59,827][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000013728_14057472.pth -[2023-10-15 02:51:00,347][88298] Updated weights for policy 0, policy_version 15300 (0.0010) -[2023-10-15 02:51:00,715][88298] Updated weights for policy 0, policy_version 15310 (0.0008) -[2023-10-15 02:51:01,095][88298] Updated weights for policy 0, policy_version 15320 (0.0007) -[2023-10-15 02:51:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 31457280. Throughput: 0: 1741.3, 1: 1731.4. Samples: 7870448. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-15 02:51:03,535][87330] Avg episode reward: [(0, '22.280'), (1, '21.680')] -[2023-10-15 02:51:03,927][88300] Updated weights for policy 1, policy_version 15402 (0.0011) -[2023-10-15 02:51:04,290][88300] Updated weights for policy 1, policy_version 15412 (0.0010) -[2023-10-15 02:51:04,653][88300] Updated weights for policy 1, policy_version 15422 (0.0009) -[2023-10-15 02:51:05,099][88298] Updated weights for policy 0, policy_version 15330 (0.0010) -[2023-10-15 02:51:05,467][88298] Updated weights for policy 0, policy_version 15340 (0.0009) -[2023-10-15 02:51:05,836][88298] Updated weights for policy 0, policy_version 15350 (0.0011) -[2023-10-15 02:51:06,212][88298] Updated weights for policy 0, policy_version 15360 (0.0011) -[2023-10-15 02:51:08,511][88300] Updated weights for policy 1, policy_version 15432 (0.0007) -[2023-10-15 02:51:08,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 31522816. Throughput: 0: 1722.4, 1: 1758.2. Samples: 7891100. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:51:08,534][87330] Avg episode reward: [(0, '22.290'), (1, '21.650')] -[2023-10-15 02:51:08,876][88300] Updated weights for policy 1, policy_version 15442 (0.0007) -[2023-10-15 02:51:09,243][88300] Updated weights for policy 1, policy_version 15452 (0.0008) -[2023-10-15 02:51:10,153][88298] Updated weights for policy 0, policy_version 15370 (0.0007) -[2023-10-15 02:51:10,522][88298] Updated weights for policy 0, policy_version 15380 (0.0007) -[2023-10-15 02:51:10,894][88298] Updated weights for policy 0, policy_version 15390 (0.0007) -[2023-10-15 02:51:13,055][88300] Updated weights for policy 1, policy_version 15462 (0.0010) -[2023-10-15 02:51:13,425][88300] Updated weights for policy 1, policy_version 15472 (0.0009) -[2023-10-15 02:51:13,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 31588352. Throughput: 0: 1729.6, 1: 1750.0. Samples: 7912292. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:51:13,535][87330] Avg episode reward: [(0, '22.160'), (1, '21.400')] -[2023-10-15 02:51:13,789][88300] Updated weights for policy 1, policy_version 15482 (0.0008) -[2023-10-15 02:51:14,877][88298] Updated weights for policy 0, policy_version 15400 (0.0007) -[2023-10-15 02:51:15,245][88298] Updated weights for policy 0, policy_version 15410 (0.0008) -[2023-10-15 02:51:15,621][88298] Updated weights for policy 0, policy_version 15420 (0.0007) -[2023-10-15 02:51:17,513][88300] Updated weights for policy 1, policy_version 15492 (0.0008) -[2023-10-15 02:51:17,877][88300] Updated weights for policy 1, policy_version 15502 (0.0011) -[2023-10-15 02:51:18,247][88300] Updated weights for policy 1, policy_version 15512 (0.0010) -[2023-10-15 02:51:18,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 31653888. Throughput: 0: 1721.0, 1: 1749.3. Samples: 7922286. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:51:18,534][87330] Avg episode reward: [(0, '22.170'), (1, '21.720')] -[2023-10-15 02:51:19,437][88298] Updated weights for policy 0, policy_version 15430 (0.0009) -[2023-10-15 02:51:19,810][88298] Updated weights for policy 0, policy_version 15440 (0.0010) -[2023-10-15 02:51:20,179][88298] Updated weights for policy 0, policy_version 15450 (0.0010) -[2023-10-15 02:51:22,079][88300] Updated weights for policy 1, policy_version 15522 (0.0009) -[2023-10-15 02:51:22,458][88300] Updated weights for policy 1, policy_version 15532 (0.0008) -[2023-10-15 02:51:22,820][88300] Updated weights for policy 1, policy_version 15542 (0.0007) -[2023-10-15 02:51:23,190][88300] Updated weights for policy 1, policy_version 15552 (0.0007) -[2023-10-15 02:51:23,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 31752192. Throughput: 0: 1720.3, 1: 1758.8. Samples: 7943724. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-15 02:51:23,534][87330] Avg episode reward: [(0, '22.330'), (1, '21.750')] -[2023-10-15 02:51:24,285][88298] Updated weights for policy 0, policy_version 15460 (0.0008) -[2023-10-15 02:51:24,676][88298] Updated weights for policy 0, policy_version 15470 (0.0007) -[2023-10-15 02:51:25,044][88298] Updated weights for policy 0, policy_version 15480 (0.0008) -[2023-10-15 02:51:27,181][88300] Updated weights for policy 1, policy_version 15562 (0.0009) -[2023-10-15 02:51:27,550][88300] Updated weights for policy 1, policy_version 15572 (0.0010) -[2023-10-15 02:51:27,915][88300] Updated weights for policy 1, policy_version 15582 (0.0007) -[2023-10-15 02:51:28,534][87330] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 31817728. Throughput: 0: 1748.5, 1: 1734.7. Samples: 7964070. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-15 02:51:28,534][87330] Avg episode reward: [(0, '22.280'), (1, '21.950')] -[2023-10-15 02:51:28,947][88298] Updated weights for policy 0, policy_version 15490 (0.0010) -[2023-10-15 02:51:29,329][88298] Updated weights for policy 0, policy_version 15500 (0.0008) -[2023-10-15 02:51:29,701][88298] Updated weights for policy 0, policy_version 15510 (0.0009) -[2023-10-15 02:51:30,071][88298] Updated weights for policy 0, policy_version 15520 (0.0008) -[2023-10-15 02:51:31,848][88300] Updated weights for policy 1, policy_version 15592 (0.0009) -[2023-10-15 02:51:32,217][88300] Updated weights for policy 1, policy_version 15602 (0.0008) -[2023-10-15 02:51:32,591][88300] Updated weights for policy 1, policy_version 15612 (0.0009) -[2023-10-15 02:51:33,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 31883264. Throughput: 0: 1717.6, 1: 1767.6. Samples: 7974966. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-15 02:51:33,534][87330] Avg episode reward: [(0, '22.250'), (1, '22.160')] -[2023-10-15 02:51:33,936][88298] Updated weights for policy 0, policy_version 15530 (0.0007) -[2023-10-15 02:51:34,310][88298] Updated weights for policy 0, policy_version 15540 (0.0008) -[2023-10-15 02:51:34,680][88298] Updated weights for policy 0, policy_version 15550 (0.0008) -[2023-10-15 02:51:36,511][88300] Updated weights for policy 1, policy_version 15622 (0.0009) -[2023-10-15 02:51:36,885][88300] Updated weights for policy 1, policy_version 15632 (0.0009) -[2023-10-15 02:51:37,241][88300] Updated weights for policy 1, policy_version 15642 (0.0008) -[2023-10-15 02:51:38,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 31948800. Throughput: 0: 1739.5, 1: 1739.3. Samples: 7995554. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 02:51:38,535][87330] Avg episode reward: [(0, '22.220'), (1, '22.220')] -[2023-10-15 02:51:38,636][88298] Updated weights for policy 0, policy_version 15560 (0.0007) -[2023-10-15 02:51:39,017][88298] Updated weights for policy 0, policy_version 15570 (0.0007) -[2023-10-15 02:51:39,385][88298] Updated weights for policy 0, policy_version 15580 (0.0008) -[2023-10-15 02:51:41,256][88300] Updated weights for policy 1, policy_version 15652 (0.0009) -[2023-10-15 02:51:41,623][88300] Updated weights for policy 1, policy_version 15662 (0.0010) -[2023-10-15 02:51:41,990][88300] Updated weights for policy 1, policy_version 15672 (0.0011) -[2023-10-15 02:51:43,018][88298] Updated weights for policy 0, policy_version 15590 (0.0007) -[2023-10-15 02:51:43,397][88298] Updated weights for policy 0, policy_version 15600 (0.0008) -[2023-10-15 02:51:43,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 32014336. Throughput: 0: 1754.4, 1: 1729.2. Samples: 8016736. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 02:51:43,535][87330] Avg episode reward: [(0, '22.260'), (1, '22.240')] -[2023-10-15 02:51:43,769][88298] Updated weights for policy 0, policy_version 15610 (0.0007) -[2023-10-15 02:51:45,937][88300] Updated weights for policy 1, policy_version 15682 (0.0007) -[2023-10-15 02:51:46,306][88300] Updated weights for policy 1, policy_version 15692 (0.0008) -[2023-10-15 02:51:46,676][88300] Updated weights for policy 1, policy_version 15702 (0.0009) -[2023-10-15 02:51:47,036][88300] Updated weights for policy 1, policy_version 15712 (0.0009) -[2023-10-15 02:51:47,669][88298] Updated weights for policy 0, policy_version 15620 (0.0007) -[2023-10-15 02:51:48,037][88298] Updated weights for policy 0, policy_version 15630 (0.0008) -[2023-10-15 02:51:48,421][88298] Updated weights for policy 0, policy_version 15640 (0.0008) -[2023-10-15 02:51:48,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 32079872. Throughput: 0: 1733.2, 1: 1746.2. Samples: 8027022. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 02:51:48,534][87330] Avg episode reward: [(0, '22.370'), (1, '22.420')] -[2023-10-15 02:51:48,535][88033] Saving new best policy, reward=22.420! -[2023-10-15 02:51:50,929][88300] Updated weights for policy 1, policy_version 15722 (0.0007) -[2023-10-15 02:51:51,303][88300] Updated weights for policy 1, policy_version 15732 (0.0009) -[2023-10-15 02:51:51,658][88300] Updated weights for policy 1, policy_version 15742 (0.0009) -[2023-10-15 02:51:52,409][88298] Updated weights for policy 0, policy_version 15650 (0.0011) -[2023-10-15 02:51:52,775][88298] Updated weights for policy 0, policy_version 15660 (0.0009) -[2023-10-15 02:51:53,144][88298] Updated weights for policy 0, policy_version 15670 (0.0007) -[2023-10-15 02:51:53,514][88298] Updated weights for policy 0, policy_version 15680 (0.0009) -[2023-10-15 02:51:53,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 32178176. Throughput: 0: 1754.6, 1: 1729.3. Samples: 8047876. Policy #0 lag: (min: 15.0, avg: 22.6, max: 47.0) -[2023-10-15 02:51:53,535][87330] Avg episode reward: [(0, '22.180'), (1, '22.130')] -[2023-10-15 02:51:55,424][88300] Updated weights for policy 1, policy_version 15752 (0.0010) -[2023-10-15 02:51:55,800][88300] Updated weights for policy 1, policy_version 15762 (0.0008) -[2023-10-15 02:51:56,175][88300] Updated weights for policy 1, policy_version 15772 (0.0007) -[2023-10-15 02:51:57,570][88298] Updated weights for policy 0, policy_version 15690 (0.0008) -[2023-10-15 02:51:57,948][88298] Updated weights for policy 0, policy_version 15700 (0.0009) -[2023-10-15 02:51:58,330][88298] Updated weights for policy 0, policy_version 15710 (0.0008) -[2023-10-15 02:51:58,534][87330] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 32243712. Throughput: 0: 1738.2, 1: 1737.8. Samples: 8068712. Policy #0 lag: (min: 15.0, avg: 22.6, max: 47.0) -[2023-10-15 02:51:58,535][87330] Avg episode reward: [(0, '22.120'), (1, '22.140')] -[2023-10-15 02:52:00,180][88300] Updated weights for policy 1, policy_version 15782 (0.0010) -[2023-10-15 02:52:00,535][88300] Updated weights for policy 1, policy_version 15792 (0.0008) -[2023-10-15 02:52:00,911][88300] Updated weights for policy 1, policy_version 15802 (0.0010) -[2023-10-15 02:52:02,175][88298] Updated weights for policy 0, policy_version 15720 (0.0010) -[2023-10-15 02:52:02,539][88298] Updated weights for policy 0, policy_version 15730 (0.0010) -[2023-10-15 02:52:02,902][88298] Updated weights for policy 0, policy_version 15740 (0.0010) -[2023-10-15 02:52:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 32309248. Throughput: 0: 1749.3, 1: 1725.4. Samples: 8078646. Policy #0 lag: (min: 31.0, avg: 43.2, max: 63.0) -[2023-10-15 02:52:03,535][87330] Avg episode reward: [(0, '22.180'), (1, '22.170')] -[2023-10-15 02:52:04,887][88300] Updated weights for policy 1, policy_version 15812 (0.0009) -[2023-10-15 02:52:05,254][88300] Updated weights for policy 1, policy_version 15822 (0.0009) -[2023-10-15 02:52:05,626][88300] Updated weights for policy 1, policy_version 15832 (0.0007) -[2023-10-15 02:52:06,981][88298] Updated weights for policy 0, policy_version 15750 (0.0009) -[2023-10-15 02:52:07,357][88298] Updated weights for policy 0, policy_version 15760 (0.0008) -[2023-10-15 02:52:07,732][88298] Updated weights for policy 0, policy_version 15770 (0.0008) -[2023-10-15 02:52:08,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 32374784. Throughput: 0: 1748.2, 1: 1724.2. Samples: 8099980. Policy #0 lag: (min: 31.0, avg: 43.2, max: 63.0) -[2023-10-15 02:52:08,535][87330] Avg episode reward: [(0, '22.230'), (1, '22.180')] -[2023-10-15 02:52:09,401][88300] Updated weights for policy 1, policy_version 15842 (0.0008) -[2023-10-15 02:52:09,762][88300] Updated weights for policy 1, policy_version 15852 (0.0007) -[2023-10-15 02:52:10,125][88300] Updated weights for policy 1, policy_version 15862 (0.0007) -[2023-10-15 02:52:10,499][88300] Updated weights for policy 1, policy_version 15872 (0.0008) -[2023-10-15 02:52:11,586][88298] Updated weights for policy 0, policy_version 15780 (0.0008) -[2023-10-15 02:52:11,965][88298] Updated weights for policy 0, policy_version 15790 (0.0008) -[2023-10-15 02:52:12,340][88298] Updated weights for policy 0, policy_version 15800 (0.0007) -[2023-10-15 02:52:13,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 32440320. Throughput: 0: 1716.6, 1: 1757.4. Samples: 8120402. Policy #0 lag: (min: 31.0, avg: 43.2, max: 63.0) -[2023-10-15 02:52:13,534][87330] Avg episode reward: [(0, '22.300'), (1, '22.150')] -[2023-10-15 02:52:14,374][88300] Updated weights for policy 1, policy_version 15882 (0.0010) -[2023-10-15 02:52:14,754][88300] Updated weights for policy 1, policy_version 15892 (0.0009) -[2023-10-15 02:52:15,125][88300] Updated weights for policy 1, policy_version 15902 (0.0011) -[2023-10-15 02:52:16,264][88298] Updated weights for policy 0, policy_version 15810 (0.0007) -[2023-10-15 02:52:16,633][88298] Updated weights for policy 0, policy_version 15820 (0.0007) -[2023-10-15 02:52:17,004][88298] Updated weights for policy 0, policy_version 15830 (0.0008) -[2023-10-15 02:52:17,372][88298] Updated weights for policy 0, policy_version 15840 (0.0007) -[2023-10-15 02:52:18,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 32505856. Throughput: 0: 1745.1, 1: 1719.7. Samples: 8130882. Policy #0 lag: (min: 31.0, avg: 31.9, max: 51.0) -[2023-10-15 02:52:18,534][87330] Avg episode reward: [(0, '22.330'), (1, '22.080')] -[2023-10-15 02:52:19,188][88300] Updated weights for policy 1, policy_version 15912 (0.0008) -[2023-10-15 02:52:19,556][88300] Updated weights for policy 1, policy_version 15922 (0.0010) -[2023-10-15 02:52:19,921][88300] Updated weights for policy 1, policy_version 15932 (0.0008) -[2023-10-15 02:52:21,091][88298] Updated weights for policy 0, policy_version 15850 (0.0007) -[2023-10-15 02:52:21,462][88298] Updated weights for policy 0, policy_version 15860 (0.0009) -[2023-10-15 02:52:21,839][88298] Updated weights for policy 0, policy_version 15870 (0.0007) -[2023-10-15 02:52:23,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 32571392. Throughput: 0: 1719.2, 1: 1744.0. Samples: 8151396. Policy #0 lag: (min: 31.0, avg: 31.9, max: 51.0) -[2023-10-15 02:52:23,534][87330] Avg episode reward: [(0, '22.460'), (1, '21.980')] -[2023-10-15 02:52:23,696][88300] Updated weights for policy 1, policy_version 15942 (0.0008) -[2023-10-15 02:52:24,062][88300] Updated weights for policy 1, policy_version 15952 (0.0008) -[2023-10-15 02:52:24,437][88300] Updated weights for policy 1, policy_version 15962 (0.0009) -[2023-10-15 02:52:25,594][88298] Updated weights for policy 0, policy_version 15880 (0.0007) -[2023-10-15 02:52:25,959][88298] Updated weights for policy 0, policy_version 15890 (0.0009) -[2023-10-15 02:52:26,339][88298] Updated weights for policy 0, policy_version 15900 (0.0008) -[2023-10-15 02:52:28,382][88300] Updated weights for policy 1, policy_version 15972 (0.0009) -[2023-10-15 02:52:28,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 32636928. Throughput: 0: 1719.2, 1: 1754.0. Samples: 8173030. Policy #0 lag: (min: 31.0, avg: 31.9, max: 51.0) -[2023-10-15 02:52:28,535][87330] Avg episode reward: [(0, '22.510'), (1, '22.210')] -[2023-10-15 02:52:28,545][87905] Saving new best policy, reward=22.510! -[2023-10-15 02:52:28,751][88300] Updated weights for policy 1, policy_version 15982 (0.0008) -[2023-10-15 02:52:29,128][88300] Updated weights for policy 1, policy_version 15992 (0.0009) -[2023-10-15 02:52:30,135][88298] Updated weights for policy 0, policy_version 15910 (0.0008) -[2023-10-15 02:52:30,507][88298] Updated weights for policy 0, policy_version 15920 (0.0008) -[2023-10-15 02:52:30,871][88298] Updated weights for policy 0, policy_version 15930 (0.0008) -[2023-10-15 02:52:32,964][88300] Updated weights for policy 1, policy_version 16002 (0.0008) -[2023-10-15 02:52:33,339][88300] Updated weights for policy 1, policy_version 16012 (0.0007) -[2023-10-15 02:52:33,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 32702464. Throughput: 0: 1728.9, 1: 1734.2. Samples: 8182862. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:52:33,534][87330] Avg episode reward: [(0, '22.530'), (1, '22.180')] -[2023-10-15 02:52:33,535][87905] Saving new best policy, reward=22.530! -[2023-10-15 02:52:33,710][88300] Updated weights for policy 1, policy_version 16022 (0.0010) -[2023-10-15 02:52:34,075][88300] Updated weights for policy 1, policy_version 16032 (0.0008) -[2023-10-15 02:52:34,776][88298] Updated weights for policy 0, policy_version 15940 (0.0009) -[2023-10-15 02:52:35,162][88298] Updated weights for policy 0, policy_version 15950 (0.0008) -[2023-10-15 02:52:35,524][88298] Updated weights for policy 0, policy_version 15960 (0.0007) -[2023-10-15 02:52:37,842][88300] Updated weights for policy 1, policy_version 16042 (0.0010) -[2023-10-15 02:52:38,220][88300] Updated weights for policy 1, policy_version 16052 (0.0008) -[2023-10-15 02:52:38,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 32768000. Throughput: 0: 1715.0, 1: 1760.3. Samples: 8204264. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:52:38,535][87330] Avg episode reward: [(0, '22.560'), (1, '22.190')] -[2023-10-15 02:52:38,536][87905] Saving new best policy, reward=22.560! -[2023-10-15 02:52:38,591][88300] Updated weights for policy 1, policy_version 16062 (0.0008) -[2023-10-15 02:52:39,522][88298] Updated weights for policy 0, policy_version 15970 (0.0008) -[2023-10-15 02:52:39,891][88298] Updated weights for policy 0, policy_version 15980 (0.0010) -[2023-10-15 02:52:40,257][88298] Updated weights for policy 0, policy_version 15990 (0.0011) -[2023-10-15 02:52:40,629][88298] Updated weights for policy 0, policy_version 16000 (0.0008) -[2023-10-15 02:52:42,477][88300] Updated weights for policy 1, policy_version 16072 (0.0008) -[2023-10-15 02:52:42,846][88300] Updated weights for policy 1, policy_version 16082 (0.0008) -[2023-10-15 02:52:43,210][88300] Updated weights for policy 1, policy_version 16092 (0.0007) -[2023-10-15 02:52:43,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 32866304. Throughput: 0: 1733.4, 1: 1735.0. Samples: 8224792. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:52:43,535][87330] Avg episode reward: [(0, '22.320'), (1, '22.290')] -[2023-10-15 02:52:44,583][88298] Updated weights for policy 0, policy_version 16010 (0.0007) -[2023-10-15 02:52:44,956][88298] Updated weights for policy 0, policy_version 16020 (0.0007) -[2023-10-15 02:52:45,325][88298] Updated weights for policy 0, policy_version 16030 (0.0008) -[2023-10-15 02:52:47,266][88300] Updated weights for policy 1, policy_version 16102 (0.0008) -[2023-10-15 02:52:47,635][88300] Updated weights for policy 1, policy_version 16112 (0.0008) -[2023-10-15 02:52:48,002][88300] Updated weights for policy 1, policy_version 16122 (0.0009) -[2023-10-15 02:52:48,534][87330] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 32931840. Throughput: 0: 1720.4, 1: 1759.1. Samples: 8235226. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-15 02:52:48,534][87330] Avg episode reward: [(0, '22.270'), (1, '22.340')] -[2023-10-15 02:52:49,400][88298] Updated weights for policy 0, policy_version 16040 (0.0010) -[2023-10-15 02:52:49,768][88298] Updated weights for policy 0, policy_version 16050 (0.0011) -[2023-10-15 02:52:50,142][88298] Updated weights for policy 0, policy_version 16060 (0.0010) -[2023-10-15 02:52:52,025][88300] Updated weights for policy 1, policy_version 16132 (0.0010) -[2023-10-15 02:52:52,387][88300] Updated weights for policy 1, policy_version 16142 (0.0008) -[2023-10-15 02:52:52,760][88300] Updated weights for policy 1, policy_version 16152 (0.0010) -[2023-10-15 02:52:53,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 32997376. Throughput: 0: 1720.8, 1: 1749.7. Samples: 8256152. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-15 02:52:53,535][87330] Avg episode reward: [(0, '22.340'), (1, '22.390')] -[2023-10-15 02:52:54,013][88298] Updated weights for policy 0, policy_version 16070 (0.0010) -[2023-10-15 02:52:54,388][88298] Updated weights for policy 0, policy_version 16080 (0.0008) -[2023-10-15 02:52:54,759][88298] Updated weights for policy 0, policy_version 16090 (0.0007) -[2023-10-15 02:52:56,419][88300] Updated weights for policy 1, policy_version 16162 (0.0007) -[2023-10-15 02:52:56,782][88300] Updated weights for policy 1, policy_version 16172 (0.0008) -[2023-10-15 02:52:57,152][88300] Updated weights for policy 1, policy_version 16182 (0.0008) -[2023-10-15 02:52:57,517][88300] Updated weights for policy 1, policy_version 16192 (0.0008) -[2023-10-15 02:52:58,534][87330] Fps is (10 sec: 13106.7, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 33062912. Throughput: 0: 1753.9, 1: 1725.5. Samples: 8276980. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-15 02:52:58,535][87330] Avg episode reward: [(0, '22.370'), (1, '22.370')] -[2023-10-15 02:52:58,547][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000016096_16482304.pth... -[2023-10-15 02:52:58,547][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000016192_16580608.pth... -[2023-10-15 02:52:58,582][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000014496_14843904.pth -[2023-10-15 02:52:58,583][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000014560_14909440.pth -[2023-10-15 02:52:58,587][87905] Saving a milestone ./train_atari/atari_seaquest_APPO/checkpoint_p0/milestones/checkpoint_000016096_16482304.pth -[2023-10-15 02:52:58,587][88033] Saving a milestone ./train_atari/atari_seaquest_APPO/checkpoint_p1/milestones/checkpoint_000016192_16580608.pth -[2023-10-15 02:52:58,944][88298] Updated weights for policy 0, policy_version 16100 (0.0011) -[2023-10-15 02:52:59,329][88298] Updated weights for policy 0, policy_version 16110 (0.0007) -[2023-10-15 02:52:59,702][88298] Updated weights for policy 0, policy_version 16120 (0.0008) -[2023-10-15 02:53:01,387][88300] Updated weights for policy 1, policy_version 16202 (0.0010) -[2023-10-15 02:53:01,756][88300] Updated weights for policy 1, policy_version 16212 (0.0008) -[2023-10-15 02:53:02,116][88300] Updated weights for policy 1, policy_version 16222 (0.0007) -[2023-10-15 02:53:03,478][88298] Updated weights for policy 0, policy_version 16130 (0.0008) -[2023-10-15 02:53:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 33128448. Throughput: 0: 1719.1, 1: 1755.9. Samples: 8287260. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:53:03,535][87330] Avg episode reward: [(0, '22.370'), (1, '22.360')] -[2023-10-15 02:53:03,851][88298] Updated weights for policy 0, policy_version 16140 (0.0009) -[2023-10-15 02:53:04,234][88298] Updated weights for policy 0, policy_version 16150 (0.0009) -[2023-10-15 02:53:04,605][88298] Updated weights for policy 0, policy_version 16160 (0.0010) -[2023-10-15 02:53:05,914][88300] Updated weights for policy 1, policy_version 16232 (0.0007) -[2023-10-15 02:53:06,282][88300] Updated weights for policy 1, policy_version 16242 (0.0008) -[2023-10-15 02:53:06,650][88300] Updated weights for policy 1, policy_version 16252 (0.0009) -[2023-10-15 02:53:08,505][88298] Updated weights for policy 0, policy_version 16170 (0.0009) -[2023-10-15 02:53:08,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 33193984. Throughput: 0: 1743.5, 1: 1730.5. Samples: 8307728. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:53:08,535][87330] Avg episode reward: [(0, '22.400'), (1, '22.370')] -[2023-10-15 02:53:08,879][88298] Updated weights for policy 0, policy_version 16180 (0.0007) -[2023-10-15 02:53:09,249][88298] Updated weights for policy 0, policy_version 16190 (0.0007) -[2023-10-15 02:53:10,672][88300] Updated weights for policy 1, policy_version 16262 (0.0008) -[2023-10-15 02:53:11,044][88300] Updated weights for policy 1, policy_version 16272 (0.0008) -[2023-10-15 02:53:11,405][88300] Updated weights for policy 1, policy_version 16282 (0.0010) -[2023-10-15 02:53:13,114][88298] Updated weights for policy 0, policy_version 16200 (0.0008) -[2023-10-15 02:53:13,474][88298] Updated weights for policy 0, policy_version 16210 (0.0007) -[2023-10-15 02:53:13,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 33259520. Throughput: 0: 1742.7, 1: 1729.9. Samples: 8329296. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:53:13,534][87330] Avg episode reward: [(0, '22.590'), (1, '22.340')] -[2023-10-15 02:53:13,849][88298] Updated weights for policy 0, policy_version 16220 (0.0010) -[2023-10-15 02:53:13,996][87905] Saving new best policy, reward=22.590! -[2023-10-15 02:53:15,241][88300] Updated weights for policy 1, policy_version 16292 (0.0007) -[2023-10-15 02:53:15,603][88300] Updated weights for policy 1, policy_version 16302 (0.0007) -[2023-10-15 02:53:15,976][88300] Updated weights for policy 1, policy_version 16312 (0.0010) -[2023-10-15 02:53:17,856][88298] Updated weights for policy 0, policy_version 16230 (0.0009) -[2023-10-15 02:53:18,224][88298] Updated weights for policy 0, policy_version 16240 (0.0007) -[2023-10-15 02:53:18,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 33325056. Throughput: 0: 1736.0, 1: 1736.2. Samples: 8339110. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:53:18,534][87330] Avg episode reward: [(0, '22.590'), (1, '22.140')] -[2023-10-15 02:53:18,597][88298] Updated weights for policy 0, policy_version 16250 (0.0008) -[2023-10-15 02:53:19,820][88300] Updated weights for policy 1, policy_version 16322 (0.0008) -[2023-10-15 02:53:20,191][88300] Updated weights for policy 1, policy_version 16332 (0.0008) -[2023-10-15 02:53:20,571][88300] Updated weights for policy 1, policy_version 16342 (0.0008) -[2023-10-15 02:53:20,937][88300] Updated weights for policy 1, policy_version 16352 (0.0008) -[2023-10-15 02:53:22,380][88298] Updated weights for policy 0, policy_version 16260 (0.0007) -[2023-10-15 02:53:22,749][88298] Updated weights for policy 0, policy_version 16270 (0.0007) -[2023-10-15 02:53:23,123][88298] Updated weights for policy 0, policy_version 16280 (0.0008) -[2023-10-15 02:53:23,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 33423360. Throughput: 0: 1747.3, 1: 1724.7. Samples: 8360502. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:53:23,534][87330] Avg episode reward: [(0, '22.510'), (1, '22.090')] -[2023-10-15 02:53:24,871][88300] Updated weights for policy 1, policy_version 16362 (0.0008) -[2023-10-15 02:53:25,224][88300] Updated weights for policy 1, policy_version 16372 (0.0008) -[2023-10-15 02:53:25,592][88300] Updated weights for policy 1, policy_version 16382 (0.0007) -[2023-10-15 02:53:26,865][88298] Updated weights for policy 0, policy_version 16290 (0.0009) -[2023-10-15 02:53:27,231][88298] Updated weights for policy 0, policy_version 16300 (0.0011) -[2023-10-15 02:53:27,606][88298] Updated weights for policy 0, policy_version 16310 (0.0010) -[2023-10-15 02:53:27,976][88298] Updated weights for policy 0, policy_version 16320 (0.0009) -[2023-10-15 02:53:28,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 33488896. Throughput: 0: 1724.3, 1: 1748.7. Samples: 8381076. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:53:28,535][87330] Avg episode reward: [(0, '22.390'), (1, '22.150')] -[2023-10-15 02:53:29,359][88300] Updated weights for policy 1, policy_version 16392 (0.0009) -[2023-10-15 02:53:29,734][88300] Updated weights for policy 1, policy_version 16402 (0.0009) -[2023-10-15 02:53:30,102][88300] Updated weights for policy 1, policy_version 16412 (0.0008) -[2023-10-15 02:53:31,930][88298] Updated weights for policy 0, policy_version 16330 (0.0007) -[2023-10-15 02:53:32,316][88298] Updated weights for policy 0, policy_version 16340 (0.0008) -[2023-10-15 02:53:32,688][88298] Updated weights for policy 0, policy_version 16350 (0.0009) -[2023-10-15 02:53:33,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 33554432. Throughput: 0: 1752.0, 1: 1726.5. Samples: 8391758. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:53:33,534][87330] Avg episode reward: [(0, '22.420'), (1, '22.160')] -[2023-10-15 02:53:34,040][88300] Updated weights for policy 1, policy_version 16422 (0.0007) -[2023-10-15 02:53:34,411][88300] Updated weights for policy 1, policy_version 16432 (0.0009) -[2023-10-15 02:53:34,782][88300] Updated weights for policy 1, policy_version 16442 (0.0009) -[2023-10-15 02:53:36,603][88298] Updated weights for policy 0, policy_version 16360 (0.0008) -[2023-10-15 02:53:36,972][88298] Updated weights for policy 0, policy_version 16370 (0.0008) -[2023-10-15 02:53:37,348][88298] Updated weights for policy 0, policy_version 16380 (0.0010) -[2023-10-15 02:53:38,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 33619968. Throughput: 0: 1739.6, 1: 1739.1. Samples: 8412694. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:53:38,535][87330] Avg episode reward: [(0, '22.400'), (1, '22.190')] -[2023-10-15 02:53:38,657][88300] Updated weights for policy 1, policy_version 16452 (0.0010) -[2023-10-15 02:53:39,020][88300] Updated weights for policy 1, policy_version 16462 (0.0007) -[2023-10-15 02:53:39,389][88300] Updated weights for policy 1, policy_version 16472 (0.0007) -[2023-10-15 02:53:41,160][88298] Updated weights for policy 0, policy_version 16390 (0.0009) -[2023-10-15 02:53:41,529][88298] Updated weights for policy 0, policy_version 16400 (0.0008) -[2023-10-15 02:53:41,906][88298] Updated weights for policy 0, policy_version 16410 (0.0007) -[2023-10-15 02:53:43,250][88300] Updated weights for policy 1, policy_version 16482 (0.0009) -[2023-10-15 02:53:43,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 33685504. Throughput: 0: 1717.9, 1: 1756.6. Samples: 8433332. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:53:43,534][87330] Avg episode reward: [(0, '22.380'), (1, '22.220')] -[2023-10-15 02:53:43,613][88300] Updated weights for policy 1, policy_version 16492 (0.0009) -[2023-10-15 02:53:43,979][88300] Updated weights for policy 1, policy_version 16502 (0.0009) -[2023-10-15 02:53:44,349][88300] Updated weights for policy 1, policy_version 16512 (0.0009) -[2023-10-15 02:53:45,920][88298] Updated weights for policy 0, policy_version 16420 (0.0007) -[2023-10-15 02:53:46,300][88298] Updated weights for policy 0, policy_version 16430 (0.0010) -[2023-10-15 02:53:46,672][88298] Updated weights for policy 0, policy_version 16440 (0.0008) -[2023-10-15 02:53:48,289][88300] Updated weights for policy 1, policy_version 16522 (0.0008) -[2023-10-15 02:53:48,534][87330] Fps is (10 sec: 13107.7, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 33751040. Throughput: 0: 1752.4, 1: 1732.7. Samples: 8444090. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:53:48,534][87330] Avg episode reward: [(0, '22.450'), (1, '22.190')] -[2023-10-15 02:53:48,654][88300] Updated weights for policy 1, policy_version 16532 (0.0010) -[2023-10-15 02:53:49,020][88300] Updated weights for policy 1, policy_version 16542 (0.0010) -[2023-10-15 02:53:50,643][88298] Updated weights for policy 0, policy_version 16450 (0.0009) -[2023-10-15 02:53:51,019][88298] Updated weights for policy 0, policy_version 16460 (0.0009) -[2023-10-15 02:53:51,386][88298] Updated weights for policy 0, policy_version 16470 (0.0008) -[2023-10-15 02:53:51,753][88298] Updated weights for policy 0, policy_version 16480 (0.0007) -[2023-10-15 02:53:52,859][88300] Updated weights for policy 1, policy_version 16552 (0.0007) -[2023-10-15 02:53:53,228][88300] Updated weights for policy 1, policy_version 16562 (0.0007) -[2023-10-15 02:53:53,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 33816576. Throughput: 0: 1720.9, 1: 1761.2. Samples: 8464420. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:53:53,534][87330] Avg episode reward: [(0, '22.340'), (1, '22.230')] -[2023-10-15 02:53:53,599][88300] Updated weights for policy 1, policy_version 16572 (0.0008) -[2023-10-15 02:53:55,638][88298] Updated weights for policy 0, policy_version 16490 (0.0010) -[2023-10-15 02:53:56,000][88298] Updated weights for policy 0, policy_version 16500 (0.0008) -[2023-10-15 02:53:56,364][88298] Updated weights for policy 0, policy_version 16510 (0.0009) -[2023-10-15 02:53:57,425][88300] Updated weights for policy 1, policy_version 16582 (0.0008) -[2023-10-15 02:53:57,791][88300] Updated weights for policy 1, policy_version 16592 (0.0008) -[2023-10-15 02:53:58,164][88300] Updated weights for policy 1, policy_version 16602 (0.0007) -[2023-10-15 02:53:58,534][87330] Fps is (10 sec: 16383.5, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 33914880. Throughput: 0: 1721.2, 1: 1738.5. Samples: 8484984. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:53:58,535][87330] Avg episode reward: [(0, '22.490'), (1, '22.240')] -[2023-10-15 02:54:00,246][88298] Updated weights for policy 0, policy_version 16520 (0.0007) -[2023-10-15 02:54:00,622][88298] Updated weights for policy 0, policy_version 16530 (0.0008) -[2023-10-15 02:54:00,994][88298] Updated weights for policy 0, policy_version 16540 (0.0007) -[2023-10-15 02:54:02,156][88300] Updated weights for policy 1, policy_version 16612 (0.0007) -[2023-10-15 02:54:02,523][88300] Updated weights for policy 1, policy_version 16622 (0.0010) -[2023-10-15 02:54:02,893][88300] Updated weights for policy 1, policy_version 16632 (0.0010) -[2023-10-15 02:54:03,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 33980416. Throughput: 0: 1731.4, 1: 1755.8. Samples: 8496036. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:54:03,534][87330] Avg episode reward: [(0, '22.480'), (1, '22.130')] -[2023-10-15 02:54:04,920][88298] Updated weights for policy 0, policy_version 16550 (0.0009) -[2023-10-15 02:54:05,288][88298] Updated weights for policy 0, policy_version 16560 (0.0009) -[2023-10-15 02:54:05,657][88298] Updated weights for policy 0, policy_version 16570 (0.0009) -[2023-10-15 02:54:06,784][88300] Updated weights for policy 1, policy_version 16642 (0.0011) -[2023-10-15 02:54:07,155][88300] Updated weights for policy 1, policy_version 16652 (0.0008) -[2023-10-15 02:54:07,521][88300] Updated weights for policy 1, policy_version 16662 (0.0008) -[2023-10-15 02:54:07,892][88300] Updated weights for policy 1, policy_version 16672 (0.0010) -[2023-10-15 02:54:08,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 34045952. Throughput: 0: 1715.0, 1: 1747.1. Samples: 8516294. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:54:08,535][87330] Avg episode reward: [(0, '22.390'), (1, '22.150')] -[2023-10-15 02:54:09,467][88298] Updated weights for policy 0, policy_version 16580 (0.0009) -[2023-10-15 02:54:09,830][88298] Updated weights for policy 0, policy_version 16590 (0.0009) -[2023-10-15 02:54:10,201][88298] Updated weights for policy 0, policy_version 16600 (0.0010) -[2023-10-15 02:54:11,883][88300] Updated weights for policy 1, policy_version 16682 (0.0009) -[2023-10-15 02:54:12,236][88300] Updated weights for policy 1, policy_version 16692 (0.0009) -[2023-10-15 02:54:12,602][88300] Updated weights for policy 1, policy_version 16702 (0.0009) -[2023-10-15 02:54:13,534][87330] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 34111488. Throughput: 0: 1746.5, 1: 1726.7. Samples: 8537368. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:54:13,535][87330] Avg episode reward: [(0, '22.350'), (1, '22.130')] -[2023-10-15 02:54:13,968][88298] Updated weights for policy 0, policy_version 16610 (0.0009) -[2023-10-15 02:54:14,346][88298] Updated weights for policy 0, policy_version 16620 (0.0007) -[2023-10-15 02:54:14,724][88298] Updated weights for policy 0, policy_version 16630 (0.0009) -[2023-10-15 02:54:15,078][88298] Updated weights for policy 0, policy_version 16640 (0.0007) -[2023-10-15 02:54:16,521][88300] Updated weights for policy 1, policy_version 16712 (0.0008) -[2023-10-15 02:54:16,879][88300] Updated weights for policy 1, policy_version 16722 (0.0011) -[2023-10-15 02:54:17,248][88300] Updated weights for policy 1, policy_version 16732 (0.0010) -[2023-10-15 02:54:18,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 34177024. Throughput: 0: 1717.5, 1: 1758.6. Samples: 8548180. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:54:18,535][87330] Avg episode reward: [(0, '22.350'), (1, '22.050')] -[2023-10-15 02:54:19,205][88298] Updated weights for policy 0, policy_version 16650 (0.0009) -[2023-10-15 02:54:19,583][88298] Updated weights for policy 0, policy_version 16660 (0.0008) -[2023-10-15 02:54:19,953][88298] Updated weights for policy 0, policy_version 16670 (0.0010) -[2023-10-15 02:54:21,214][88300] Updated weights for policy 1, policy_version 16742 (0.0007) -[2023-10-15 02:54:21,584][88300] Updated weights for policy 1, policy_version 16752 (0.0009) -[2023-10-15 02:54:21,955][88300] Updated weights for policy 1, policy_version 16762 (0.0011) -[2023-10-15 02:54:23,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 34242560. Throughput: 0: 1733.6, 1: 1724.1. Samples: 8568288. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:54:23,534][87330] Avg episode reward: [(0, '22.340'), (1, '22.270')] -[2023-10-15 02:54:23,877][88298] Updated weights for policy 0, policy_version 16680 (0.0009) -[2023-10-15 02:54:24,242][88298] Updated weights for policy 0, policy_version 16690 (0.0008) -[2023-10-15 02:54:24,619][88298] Updated weights for policy 0, policy_version 16700 (0.0009) -[2023-10-15 02:54:25,988][88300] Updated weights for policy 1, policy_version 16772 (0.0008) -[2023-10-15 02:54:26,358][88300] Updated weights for policy 1, policy_version 16782 (0.0009) -[2023-10-15 02:54:26,725][88300] Updated weights for policy 1, policy_version 16792 (0.0008) -[2023-10-15 02:54:28,494][88298] Updated weights for policy 0, policy_version 16710 (0.0009) -[2023-10-15 02:54:28,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 34308096. Throughput: 0: 1756.1, 1: 1723.2. Samples: 8589902. Policy #0 lag: (min: 22.0, avg: 29.0, max: 54.0) -[2023-10-15 02:54:28,534][87330] Avg episode reward: [(0, '22.470'), (1, '22.100')] -[2023-10-15 02:54:28,866][88298] Updated weights for policy 0, policy_version 16720 (0.0008) -[2023-10-15 02:54:29,233][88298] Updated weights for policy 0, policy_version 16730 (0.0008) -[2023-10-15 02:54:30,610][88300] Updated weights for policy 1, policy_version 16802 (0.0009) -[2023-10-15 02:54:30,967][88300] Updated weights for policy 1, policy_version 16812 (0.0008) -[2023-10-15 02:54:31,339][88300] Updated weights for policy 1, policy_version 16822 (0.0009) -[2023-10-15 02:54:31,695][88300] Updated weights for policy 1, policy_version 16832 (0.0009) -[2023-10-15 02:54:33,219][88298] Updated weights for policy 0, policy_version 16740 (0.0007) -[2023-10-15 02:54:33,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 34373632. Throughput: 0: 1722.3, 1: 1740.4. Samples: 8599914. Policy #0 lag: (min: 22.0, avg: 29.0, max: 54.0) -[2023-10-15 02:54:33,535][87330] Avg episode reward: [(0, '22.500'), (1, '22.000')] -[2023-10-15 02:54:33,607][88298] Updated weights for policy 0, policy_version 16750 (0.0009) -[2023-10-15 02:54:33,987][88298] Updated weights for policy 0, policy_version 16760 (0.0008) -[2023-10-15 02:54:35,539][88300] Updated weights for policy 1, policy_version 16842 (0.0011) -[2023-10-15 02:54:35,913][88300] Updated weights for policy 1, policy_version 16852 (0.0010) -[2023-10-15 02:54:36,283][88300] Updated weights for policy 1, policy_version 16862 (0.0008) -[2023-10-15 02:54:37,936][88298] Updated weights for policy 0, policy_version 16770 (0.0008) -[2023-10-15 02:54:38,309][88298] Updated weights for policy 0, policy_version 16780 (0.0010) -[2023-10-15 02:54:38,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 34439168. Throughput: 0: 1750.1, 1: 1722.2. Samples: 8620674. Policy #0 lag: (min: 22.0, avg: 29.0, max: 54.0) -[2023-10-15 02:54:38,535][87330] Avg episode reward: [(0, '22.580'), (1, '22.100')] -[2023-10-15 02:54:38,685][88298] Updated weights for policy 0, policy_version 16790 (0.0010) -[2023-10-15 02:54:39,065][88298] Updated weights for policy 0, policy_version 16800 (0.0010) -[2023-10-15 02:54:40,284][88300] Updated weights for policy 1, policy_version 16872 (0.0007) -[2023-10-15 02:54:40,657][88300] Updated weights for policy 1, policy_version 16882 (0.0008) -[2023-10-15 02:54:41,024][88300] Updated weights for policy 1, policy_version 16892 (0.0008) -[2023-10-15 02:54:42,972][88298] Updated weights for policy 0, policy_version 16810 (0.0007) -[2023-10-15 02:54:43,347][88298] Updated weights for policy 0, policy_version 16820 (0.0010) -[2023-10-15 02:54:43,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 34504704. Throughput: 0: 1739.0, 1: 1737.4. Samples: 8641420. Policy #0 lag: (min: 29.0, avg: 31.2, max: 60.0) -[2023-10-15 02:54:43,534][87330] Avg episode reward: [(0, '22.620'), (1, '22.100')] -[2023-10-15 02:54:43,717][88298] Updated weights for policy 0, policy_version 16830 (0.0010) -[2023-10-15 02:54:43,790][87905] Saving new best policy, reward=22.620! -[2023-10-15 02:54:45,033][88300] Updated weights for policy 1, policy_version 16902 (0.0009) -[2023-10-15 02:54:45,393][88300] Updated weights for policy 1, policy_version 16912 (0.0009) -[2023-10-15 02:54:45,766][88300] Updated weights for policy 1, policy_version 16922 (0.0008) -[2023-10-15 02:54:47,584][88298] Updated weights for policy 0, policy_version 16840 (0.0008) -[2023-10-15 02:54:47,952][88298] Updated weights for policy 0, policy_version 16850 (0.0007) -[2023-10-15 02:54:48,328][88298] Updated weights for policy 0, policy_version 16860 (0.0012) -[2023-10-15 02:54:48,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 34603008. Throughput: 0: 1732.1, 1: 1712.9. Samples: 8651060. Policy #0 lag: (min: 29.0, avg: 31.2, max: 60.0) -[2023-10-15 02:54:48,535][87330] Avg episode reward: [(0, '22.630'), (1, '22.160')] -[2023-10-15 02:54:48,535][87905] Saving new best policy, reward=22.630! -[2023-10-15 02:54:49,637][88300] Updated weights for policy 1, policy_version 16932 (0.0008) -[2023-10-15 02:54:50,003][88300] Updated weights for policy 1, policy_version 16942 (0.0009) -[2023-10-15 02:54:50,369][88300] Updated weights for policy 1, policy_version 16952 (0.0008) -[2023-10-15 02:54:52,206][88298] Updated weights for policy 0, policy_version 16870 (0.0011) -[2023-10-15 02:54:52,574][88298] Updated weights for policy 0, policy_version 16880 (0.0009) -[2023-10-15 02:54:52,955][88298] Updated weights for policy 0, policy_version 16890 (0.0008) -[2023-10-15 02:54:53,534][87330] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 34668544. Throughput: 0: 1747.8, 1: 1725.8. Samples: 8672604. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-15 02:54:53,535][87330] Avg episode reward: [(0, '22.460'), (1, '22.030')] -[2023-10-15 02:54:54,299][88300] Updated weights for policy 1, policy_version 16962 (0.0009) -[2023-10-15 02:54:54,675][88300] Updated weights for policy 1, policy_version 16972 (0.0008) -[2023-10-15 02:54:55,029][88300] Updated weights for policy 1, policy_version 16982 (0.0008) -[2023-10-15 02:54:55,401][88300] Updated weights for policy 1, policy_version 16992 (0.0008) -[2023-10-15 02:54:56,924][88298] Updated weights for policy 0, policy_version 16900 (0.0008) -[2023-10-15 02:54:57,298][88298] Updated weights for policy 0, policy_version 16910 (0.0007) -[2023-10-15 02:54:57,665][88298] Updated weights for policy 0, policy_version 16920 (0.0009) -[2023-10-15 02:54:58,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 34734080. Throughput: 0: 1716.2, 1: 1747.6. Samples: 8693236. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-15 02:54:58,535][87330] Avg episode reward: [(0, '22.420'), (1, '21.990')] -[2023-10-15 02:54:58,546][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000016992_17399808.pth... -[2023-10-15 02:54:58,546][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000016928_17334272.pth... -[2023-10-15 02:54:58,575][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000015392_15761408.pth -[2023-10-15 02:54:58,579][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000015296_15663104.pth -[2023-10-15 02:54:59,245][88300] Updated weights for policy 1, policy_version 17002 (0.0008) -[2023-10-15 02:54:59,610][88300] Updated weights for policy 1, policy_version 17012 (0.0009) -[2023-10-15 02:54:59,974][88300] Updated weights for policy 1, policy_version 17022 (0.0009) -[2023-10-15 02:55:01,648][88298] Updated weights for policy 0, policy_version 16930 (0.0008) -[2023-10-15 02:55:02,023][88298] Updated weights for policy 0, policy_version 16940 (0.0008) -[2023-10-15 02:55:02,389][88298] Updated weights for policy 0, policy_version 16950 (0.0007) -[2023-10-15 02:55:02,758][88298] Updated weights for policy 0, policy_version 16960 (0.0008) -[2023-10-15 02:55:03,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 34799616. Throughput: 0: 1742.9, 1: 1717.6. Samples: 8703902. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-15 02:55:03,535][87330] Avg episode reward: [(0, '22.390'), (1, '22.390')] -[2023-10-15 02:55:03,892][88300] Updated weights for policy 1, policy_version 17032 (0.0010) -[2023-10-15 02:55:04,267][88300] Updated weights for policy 1, policy_version 17042 (0.0011) -[2023-10-15 02:55:04,640][88300] Updated weights for policy 1, policy_version 17052 (0.0009) -[2023-10-15 02:55:06,639][88298] Updated weights for policy 0, policy_version 16970 (0.0008) -[2023-10-15 02:55:07,015][88298] Updated weights for policy 0, policy_version 16980 (0.0009) -[2023-10-15 02:55:07,385][88298] Updated weights for policy 0, policy_version 16990 (0.0009) -[2023-10-15 02:55:08,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 34865152. Throughput: 0: 1736.1, 1: 1752.4. Samples: 8725268. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-15 02:55:08,535][87330] Avg episode reward: [(0, '22.420'), (1, '22.320')] -[2023-10-15 02:55:08,550][88300] Updated weights for policy 1, policy_version 17062 (0.0007) -[2023-10-15 02:55:08,909][88300] Updated weights for policy 1, policy_version 17072 (0.0008) -[2023-10-15 02:55:09,279][88300] Updated weights for policy 1, policy_version 17082 (0.0008) -[2023-10-15 02:55:11,252][88298] Updated weights for policy 0, policy_version 17000 (0.0011) -[2023-10-15 02:55:11,622][88298] Updated weights for policy 0, policy_version 17010 (0.0009) -[2023-10-15 02:55:12,002][88298] Updated weights for policy 0, policy_version 17020 (0.0008) -[2023-10-15 02:55:13,272][88300] Updated weights for policy 1, policy_version 17092 (0.0008) -[2023-10-15 02:55:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 34930688. Throughput: 0: 1717.4, 1: 1750.5. Samples: 8745958. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-15 02:55:13,535][87330] Avg episode reward: [(0, '22.390'), (1, '22.230')] -[2023-10-15 02:55:13,639][88300] Updated weights for policy 1, policy_version 17102 (0.0009) -[2023-10-15 02:55:14,005][88300] Updated weights for policy 1, policy_version 17112 (0.0009) -[2023-10-15 02:55:15,912][88298] Updated weights for policy 0, policy_version 17030 (0.0008) -[2023-10-15 02:55:16,280][88298] Updated weights for policy 0, policy_version 17040 (0.0008) -[2023-10-15 02:55:16,653][88298] Updated weights for policy 0, policy_version 17050 (0.0007) -[2023-10-15 02:55:17,882][88300] Updated weights for policy 1, policy_version 17122 (0.0008) -[2023-10-15 02:55:18,250][88300] Updated weights for policy 1, policy_version 17132 (0.0009) -[2023-10-15 02:55:18,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 34996224. Throughput: 0: 1749.2, 1: 1736.5. Samples: 8756772. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-15 02:55:18,535][87330] Avg episode reward: [(0, '22.370'), (1, '21.960')] -[2023-10-15 02:55:18,623][88300] Updated weights for policy 1, policy_version 17142 (0.0007) -[2023-10-15 02:55:18,996][88300] Updated weights for policy 1, policy_version 17152 (0.0009) -[2023-10-15 02:55:20,485][88298] Updated weights for policy 0, policy_version 17060 (0.0008) -[2023-10-15 02:55:20,869][88298] Updated weights for policy 0, policy_version 17070 (0.0007) -[2023-10-15 02:55:21,242][88298] Updated weights for policy 0, policy_version 17080 (0.0007) -[2023-10-15 02:55:22,984][88300] Updated weights for policy 1, policy_version 17162 (0.0009) -[2023-10-15 02:55:23,351][88300] Updated weights for policy 1, policy_version 17172 (0.0007) -[2023-10-15 02:55:23,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 35061760. Throughput: 0: 1720.5, 1: 1751.1. Samples: 8776896. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 02:55:23,534][87330] Avg episode reward: [(0, '22.510'), (1, '22.140')] -[2023-10-15 02:55:23,724][88300] Updated weights for policy 1, policy_version 17182 (0.0010) -[2023-10-15 02:55:25,048][88298] Updated weights for policy 0, policy_version 17090 (0.0011) -[2023-10-15 02:55:25,424][88298] Updated weights for policy 0, policy_version 17100 (0.0010) -[2023-10-15 02:55:25,797][88298] Updated weights for policy 0, policy_version 17110 (0.0010) -[2023-10-15 02:55:26,158][88298] Updated weights for policy 0, policy_version 17120 (0.0008) -[2023-10-15 02:55:27,629][88300] Updated weights for policy 1, policy_version 17192 (0.0010) -[2023-10-15 02:55:27,999][88300] Updated weights for policy 1, policy_version 17202 (0.0010) -[2023-10-15 02:55:28,372][88300] Updated weights for policy 1, policy_version 17212 (0.0009) -[2023-10-15 02:55:28,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 35160064. Throughput: 0: 1730.5, 1: 1734.7. Samples: 8797356. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 02:55:28,534][87330] Avg episode reward: [(0, '22.480'), (1, '22.040')] -[2023-10-15 02:55:30,142][88298] Updated weights for policy 0, policy_version 17130 (0.0007) -[2023-10-15 02:55:30,523][88298] Updated weights for policy 0, policy_version 17140 (0.0007) -[2023-10-15 02:55:30,893][88298] Updated weights for policy 0, policy_version 17150 (0.0008) -[2023-10-15 02:55:32,205][88300] Updated weights for policy 1, policy_version 17222 (0.0008) -[2023-10-15 02:55:32,575][88300] Updated weights for policy 1, policy_version 17232 (0.0010) -[2023-10-15 02:55:32,952][88300] Updated weights for policy 1, policy_version 17242 (0.0009) -[2023-10-15 02:55:33,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 35225600. Throughput: 0: 1733.9, 1: 1756.0. Samples: 8808102. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 02:55:33,534][87330] Avg episode reward: [(0, '22.530'), (1, '21.970')] -[2023-10-15 02:55:34,747][88298] Updated weights for policy 0, policy_version 17160 (0.0009) -[2023-10-15 02:55:35,130][88298] Updated weights for policy 0, policy_version 17170 (0.0008) -[2023-10-15 02:55:35,496][88298] Updated weights for policy 0, policy_version 17180 (0.0007) -[2023-10-15 02:55:36,741][88300] Updated weights for policy 1, policy_version 17252 (0.0007) -[2023-10-15 02:55:37,095][88300] Updated weights for policy 1, policy_version 17262 (0.0008) -[2023-10-15 02:55:37,466][88300] Updated weights for policy 1, policy_version 17272 (0.0007) -[2023-10-15 02:55:38,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 35291136. Throughput: 0: 1722.5, 1: 1741.1. Samples: 8828464. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-15 02:55:38,535][87330] Avg episode reward: [(0, '22.380'), (1, '22.070')] -[2023-10-15 02:55:39,451][88298] Updated weights for policy 0, policy_version 17190 (0.0010) -[2023-10-15 02:55:39,823][88298] Updated weights for policy 0, policy_version 17200 (0.0008) -[2023-10-15 02:55:40,197][88298] Updated weights for policy 0, policy_version 17210 (0.0007) -[2023-10-15 02:55:41,349][88300] Updated weights for policy 1, policy_version 17282 (0.0009) -[2023-10-15 02:55:41,713][88300] Updated weights for policy 1, policy_version 17292 (0.0008) -[2023-10-15 02:55:42,082][88300] Updated weights for policy 1, policy_version 17302 (0.0010) -[2023-10-15 02:55:42,454][88300] Updated weights for policy 1, policy_version 17312 (0.0011) -[2023-10-15 02:55:43,534][87330] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 35356672. Throughput: 0: 1752.4, 1: 1723.7. Samples: 8849658. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-15 02:55:43,535][87330] Avg episode reward: [(0, '22.380'), (1, '22.030')] -[2023-10-15 02:55:44,013][88298] Updated weights for policy 0, policy_version 17220 (0.0008) -[2023-10-15 02:55:44,378][88298] Updated weights for policy 0, policy_version 17230 (0.0008) -[2023-10-15 02:55:44,752][88298] Updated weights for policy 0, policy_version 17240 (0.0008) -[2023-10-15 02:55:46,415][88300] Updated weights for policy 1, policy_version 17322 (0.0007) -[2023-10-15 02:55:46,788][88300] Updated weights for policy 1, policy_version 17332 (0.0009) -[2023-10-15 02:55:47,162][88300] Updated weights for policy 1, policy_version 17342 (0.0010) -[2023-10-15 02:55:48,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 35422208. Throughput: 0: 1726.9, 1: 1749.1. Samples: 8860322. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-15 02:55:48,534][87330] Avg episode reward: [(0, '22.440'), (1, '21.990')] -[2023-10-15 02:55:48,604][88298] Updated weights for policy 0, policy_version 17250 (0.0007) -[2023-10-15 02:55:48,980][88298] Updated weights for policy 0, policy_version 17260 (0.0008) -[2023-10-15 02:55:49,355][88298] Updated weights for policy 0, policy_version 17270 (0.0010) -[2023-10-15 02:55:49,727][88298] Updated weights for policy 0, policy_version 17280 (0.0009) -[2023-10-15 02:55:50,936][88300] Updated weights for policy 1, policy_version 17352 (0.0008) -[2023-10-15 02:55:51,297][88300] Updated weights for policy 1, policy_version 17362 (0.0009) -[2023-10-15 02:55:51,673][88300] Updated weights for policy 1, policy_version 17372 (0.0007) -[2023-10-15 02:55:53,534][87330] Fps is (10 sec: 13107.7, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 35487744. Throughput: 0: 1731.2, 1: 1721.0. Samples: 8880618. Policy #0 lag: (min: 31.0, avg: 43.5, max: 63.0) -[2023-10-15 02:55:53,534][87330] Avg episode reward: [(0, '22.510'), (1, '22.250')] -[2023-10-15 02:55:53,769][88298] Updated weights for policy 0, policy_version 17290 (0.0009) -[2023-10-15 02:55:54,135][88298] Updated weights for policy 0, policy_version 17300 (0.0008) -[2023-10-15 02:55:54,500][88298] Updated weights for policy 0, policy_version 17310 (0.0008) -[2023-10-15 02:55:55,500][88300] Updated weights for policy 1, policy_version 17382 (0.0008) -[2023-10-15 02:55:55,869][88300] Updated weights for policy 1, policy_version 17392 (0.0009) -[2023-10-15 02:55:56,244][88300] Updated weights for policy 1, policy_version 17402 (0.0008) -[2023-10-15 02:55:58,297][88298] Updated weights for policy 0, policy_version 17320 (0.0007) -[2023-10-15 02:55:58,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 35553280. Throughput: 0: 1750.0, 1: 1729.7. Samples: 8902544. Policy #0 lag: (min: 31.0, avg: 43.5, max: 63.0) -[2023-10-15 02:55:58,534][87330] Avg episode reward: [(0, '22.500'), (1, '22.260')] -[2023-10-15 02:55:58,678][88298] Updated weights for policy 0, policy_version 17330 (0.0007) -[2023-10-15 02:55:59,042][88298] Updated weights for policy 0, policy_version 17340 (0.0007) -[2023-10-15 02:56:00,036][88300] Updated weights for policy 1, policy_version 17412 (0.0009) -[2023-10-15 02:56:00,396][88300] Updated weights for policy 1, policy_version 17422 (0.0009) -[2023-10-15 02:56:00,763][88300] Updated weights for policy 1, policy_version 17432 (0.0007) -[2023-10-15 02:56:02,774][88298] Updated weights for policy 0, policy_version 17350 (0.0007) -[2023-10-15 02:56:03,143][88298] Updated weights for policy 0, policy_version 17360 (0.0008) -[2023-10-15 02:56:03,520][88298] Updated weights for policy 0, policy_version 17370 (0.0007) -[2023-10-15 02:56:03,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 35618816. Throughput: 0: 1724.8, 1: 1728.5. Samples: 8912172. Policy #0 lag: (min: 31.0, avg: 43.5, max: 63.0) -[2023-10-15 02:56:03,535][87330] Avg episode reward: [(0, '22.510'), (1, '22.270')] -[2023-10-15 02:56:04,722][88300] Updated weights for policy 1, policy_version 17442 (0.0007) -[2023-10-15 02:56:05,098][88300] Updated weights for policy 1, policy_version 17452 (0.0008) -[2023-10-15 02:56:05,467][88300] Updated weights for policy 1, policy_version 17462 (0.0007) -[2023-10-15 02:56:05,836][88300] Updated weights for policy 1, policy_version 17472 (0.0009) -[2023-10-15 02:56:07,452][88298] Updated weights for policy 0, policy_version 17380 (0.0010) -[2023-10-15 02:56:07,839][88298] Updated weights for policy 0, policy_version 17390 (0.0009) -[2023-10-15 02:56:08,208][88298] Updated weights for policy 0, policy_version 17400 (0.0008) -[2023-10-15 02:56:08,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 35717120. Throughput: 0: 1759.7, 1: 1727.8. Samples: 8933834. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-10-15 02:56:08,534][87330] Avg episode reward: [(0, '22.660'), (1, '22.260')] -[2023-10-15 02:56:08,535][87905] Saving new best policy, reward=22.660! -[2023-10-15 02:56:09,672][88300] Updated weights for policy 1, policy_version 17482 (0.0009) -[2023-10-15 02:56:10,045][88300] Updated weights for policy 1, policy_version 17492 (0.0011) -[2023-10-15 02:56:10,408][88300] Updated weights for policy 1, policy_version 17502 (0.0010) -[2023-10-15 02:56:12,260][88298] Updated weights for policy 0, policy_version 17410 (0.0007) -[2023-10-15 02:56:12,628][88298] Updated weights for policy 0, policy_version 17420 (0.0007) -[2023-10-15 02:56:13,000][88298] Updated weights for policy 0, policy_version 17430 (0.0008) -[2023-10-15 02:56:13,368][88298] Updated weights for policy 0, policy_version 17440 (0.0008) -[2023-10-15 02:56:13,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 35782656. Throughput: 0: 1746.0, 1: 1751.9. Samples: 8954760. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-10-15 02:56:13,534][87330] Avg episode reward: [(0, '22.670'), (1, '22.340')] -[2023-10-15 02:56:13,545][87905] Saving new best policy, reward=22.670! -[2023-10-15 02:56:14,426][88300] Updated weights for policy 1, policy_version 17512 (0.0010) -[2023-10-15 02:56:14,808][88300] Updated weights for policy 1, policy_version 17522 (0.0008) -[2023-10-15 02:56:15,175][88300] Updated weights for policy 1, policy_version 17532 (0.0008) -[2023-10-15 02:56:17,173][88298] Updated weights for policy 0, policy_version 17450 (0.0008) -[2023-10-15 02:56:17,552][88298] Updated weights for policy 0, policy_version 17460 (0.0009) -[2023-10-15 02:56:17,931][88298] Updated weights for policy 0, policy_version 17470 (0.0008) -[2023-10-15 02:56:18,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 35848192. Throughput: 0: 1751.5, 1: 1730.8. Samples: 8964804. Policy #0 lag: (min: 3.0, avg: 11.0, max: 35.0) -[2023-10-15 02:56:18,534][87330] Avg episode reward: [(0, '22.600'), (1, '22.250')] -[2023-10-15 02:56:19,047][88300] Updated weights for policy 1, policy_version 17542 (0.0008) -[2023-10-15 02:56:19,421][88300] Updated weights for policy 1, policy_version 17552 (0.0008) -[2023-10-15 02:56:19,787][88300] Updated weights for policy 1, policy_version 17562 (0.0009) -[2023-10-15 02:56:21,809][88298] Updated weights for policy 0, policy_version 17480 (0.0010) -[2023-10-15 02:56:22,185][88298] Updated weights for policy 0, policy_version 17490 (0.0009) -[2023-10-15 02:56:22,562][88298] Updated weights for policy 0, policy_version 17500 (0.0011) -[2023-10-15 02:56:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 35913728. Throughput: 0: 1753.3, 1: 1750.4. Samples: 8986130. Policy #0 lag: (min: 3.0, avg: 11.0, max: 35.0) -[2023-10-15 02:56:23,534][87330] Avg episode reward: [(0, '22.600'), (1, '22.180')] -[2023-10-15 02:56:23,542][88300] Updated weights for policy 1, policy_version 17572 (0.0008) -[2023-10-15 02:56:23,905][88300] Updated weights for policy 1, policy_version 17582 (0.0007) -[2023-10-15 02:56:24,276][88300] Updated weights for policy 1, policy_version 17592 (0.0007) -[2023-10-15 02:56:26,283][88298] Updated weights for policy 0, policy_version 17510 (0.0011) -[2023-10-15 02:56:26,653][88298] Updated weights for policy 0, policy_version 17520 (0.0008) -[2023-10-15 02:56:27,022][88298] Updated weights for policy 0, policy_version 17530 (0.0007) -[2023-10-15 02:56:28,153][88300] Updated weights for policy 1, policy_version 17602 (0.0007) -[2023-10-15 02:56:28,509][88300] Updated weights for policy 1, policy_version 17612 (0.0007) -[2023-10-15 02:56:28,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 35979264. Throughput: 0: 1727.8, 1: 1761.4. Samples: 9006670. Policy #0 lag: (min: 3.0, avg: 11.0, max: 35.0) -[2023-10-15 02:56:28,534][87330] Avg episode reward: [(0, '22.640'), (1, '22.040')] -[2023-10-15 02:56:28,878][88300] Updated weights for policy 1, policy_version 17622 (0.0007) -[2023-10-15 02:56:29,244][88300] Updated weights for policy 1, policy_version 17632 (0.0008) -[2023-10-15 02:56:30,853][88298] Updated weights for policy 0, policy_version 17540 (0.0009) -[2023-10-15 02:56:31,233][88298] Updated weights for policy 0, policy_version 17550 (0.0008) -[2023-10-15 02:56:31,596][88298] Updated weights for policy 0, policy_version 17560 (0.0010) -[2023-10-15 02:56:33,084][88300] Updated weights for policy 1, policy_version 17642 (0.0010) -[2023-10-15 02:56:33,452][88300] Updated weights for policy 1, policy_version 17652 (0.0009) -[2023-10-15 02:56:33,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 36044800. Throughput: 0: 1759.3, 1: 1738.9. Samples: 9017742. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-15 02:56:33,534][87330] Avg episode reward: [(0, '22.610'), (1, '21.880')] -[2023-10-15 02:56:33,820][88300] Updated weights for policy 1, policy_version 17662 (0.0009) -[2023-10-15 02:56:35,487][88298] Updated weights for policy 0, policy_version 17570 (0.0007) -[2023-10-15 02:56:35,854][88298] Updated weights for policy 0, policy_version 17580 (0.0010) -[2023-10-15 02:56:36,224][88298] Updated weights for policy 0, policy_version 17590 (0.0009) -[2023-10-15 02:56:36,594][88298] Updated weights for policy 0, policy_version 17600 (0.0009) -[2023-10-15 02:56:37,895][88300] Updated weights for policy 1, policy_version 17672 (0.0010) -[2023-10-15 02:56:38,271][88300] Updated weights for policy 1, policy_version 17682 (0.0008) -[2023-10-15 02:56:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 36110336. Throughput: 0: 1737.2, 1: 1761.7. Samples: 9038070. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-15 02:56:38,534][87330] Avg episode reward: [(0, '22.560'), (1, '21.790')] -[2023-10-15 02:56:38,632][88300] Updated weights for policy 1, policy_version 17692 (0.0009) -[2023-10-15 02:56:40,430][88298] Updated weights for policy 0, policy_version 17610 (0.0007) -[2023-10-15 02:56:40,804][88298] Updated weights for policy 0, policy_version 17620 (0.0007) -[2023-10-15 02:56:41,172][88298] Updated weights for policy 0, policy_version 17630 (0.0009) -[2023-10-15 02:56:42,455][88300] Updated weights for policy 1, policy_version 17702 (0.0009) -[2023-10-15 02:56:42,823][88300] Updated weights for policy 1, policy_version 17712 (0.0009) -[2023-10-15 02:56:43,193][88300] Updated weights for policy 1, policy_version 17722 (0.0007) -[2023-10-15 02:56:43,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 36208640. Throughput: 0: 1740.9, 1: 1735.6. Samples: 9058988. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-15 02:56:43,535][87330] Avg episode reward: [(0, '22.500'), (1, '21.720')] -[2023-10-15 02:56:45,204][88298] Updated weights for policy 0, policy_version 17640 (0.0007) -[2023-10-15 02:56:45,580][88298] Updated weights for policy 0, policy_version 17650 (0.0009) -[2023-10-15 02:56:45,954][88298] Updated weights for policy 0, policy_version 17660 (0.0009) -[2023-10-15 02:56:47,003][88300] Updated weights for policy 1, policy_version 17732 (0.0008) -[2023-10-15 02:56:47,369][88300] Updated weights for policy 1, policy_version 17742 (0.0007) -[2023-10-15 02:56:47,728][88300] Updated weights for policy 1, policy_version 17752 (0.0009) -[2023-10-15 02:56:48,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 36274176. Throughput: 0: 1747.4, 1: 1762.1. Samples: 9070100. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:56:48,534][87330] Avg episode reward: [(0, '22.530'), (1, '21.710')] -[2023-10-15 02:56:49,976][88298] Updated weights for policy 0, policy_version 17670 (0.0007) -[2023-10-15 02:56:50,341][88298] Updated weights for policy 0, policy_version 17680 (0.0008) -[2023-10-15 02:56:50,712][88298] Updated weights for policy 0, policy_version 17690 (0.0007) -[2023-10-15 02:56:51,635][88300] Updated weights for policy 1, policy_version 17762 (0.0011) -[2023-10-15 02:56:51,994][88300] Updated weights for policy 1, policy_version 17772 (0.0009) -[2023-10-15 02:56:52,358][88300] Updated weights for policy 1, policy_version 17782 (0.0009) -[2023-10-15 02:56:52,722][88300] Updated weights for policy 1, policy_version 17792 (0.0009) -[2023-10-15 02:56:53,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13884.8). Total num frames: 36339712. Throughput: 0: 1732.9, 1: 1750.0. Samples: 9090564. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:56:53,534][87330] Avg episode reward: [(0, '22.580'), (1, '21.900')] -[2023-10-15 02:56:54,648][88298] Updated weights for policy 0, policy_version 17700 (0.0009) -[2023-10-15 02:56:55,043][88298] Updated weights for policy 0, policy_version 17710 (0.0009) -[2023-10-15 02:56:55,421][88298] Updated weights for policy 0, policy_version 17720 (0.0008) -[2023-10-15 02:56:56,553][88300] Updated weights for policy 1, policy_version 17802 (0.0007) -[2023-10-15 02:56:56,911][88300] Updated weights for policy 1, policy_version 17812 (0.0008) -[2023-10-15 02:56:57,289][88300] Updated weights for policy 1, policy_version 17822 (0.0007) -[2023-10-15 02:56:58,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 36405248. Throughput: 0: 1746.5, 1: 1740.5. Samples: 9111676. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:56:58,535][87330] Avg episode reward: [(0, '22.490'), (1, '22.140')] -[2023-10-15 02:56:58,545][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000017824_18251776.pth... -[2023-10-15 02:56:58,545][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000017728_18153472.pth... -[2023-10-15 02:56:58,585][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000016192_16580608.pth -[2023-10-15 02:56:58,586][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000016096_16482304.pth -[2023-10-15 02:56:59,219][88298] Updated weights for policy 0, policy_version 17730 (0.0009) -[2023-10-15 02:56:59,585][88298] Updated weights for policy 0, policy_version 17740 (0.0007) -[2023-10-15 02:56:59,953][88298] Updated weights for policy 0, policy_version 17750 (0.0007) -[2023-10-15 02:57:00,328][88298] Updated weights for policy 0, policy_version 17760 (0.0008) -[2023-10-15 02:57:01,165][88300] Updated weights for policy 1, policy_version 17832 (0.0009) -[2023-10-15 02:57:01,548][88300] Updated weights for policy 1, policy_version 17842 (0.0009) -[2023-10-15 02:57:01,915][88300] Updated weights for policy 1, policy_version 17852 (0.0007) -[2023-10-15 02:57:03,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 36470784. Throughput: 0: 1732.9, 1: 1764.8. Samples: 9122200. Policy #0 lag: (min: 31.0, avg: 32.9, max: 60.0) -[2023-10-15 02:57:03,534][87330] Avg episode reward: [(0, '22.500'), (1, '22.030')] -[2023-10-15 02:57:04,254][88298] Updated weights for policy 0, policy_version 17770 (0.0009) -[2023-10-15 02:57:04,633][88298] Updated weights for policy 0, policy_version 17780 (0.0008) -[2023-10-15 02:57:04,995][88298] Updated weights for policy 0, policy_version 17790 (0.0008) -[2023-10-15 02:57:05,881][88300] Updated weights for policy 1, policy_version 17862 (0.0010) -[2023-10-15 02:57:06,246][88300] Updated weights for policy 1, policy_version 17872 (0.0008) -[2023-10-15 02:57:06,617][88300] Updated weights for policy 1, policy_version 17882 (0.0009) -[2023-10-15 02:57:08,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 36536320. Throughput: 0: 1744.1, 1: 1739.0. Samples: 9142870. Policy #0 lag: (min: 31.0, avg: 32.9, max: 60.0) -[2023-10-15 02:57:08,535][87330] Avg episode reward: [(0, '22.490'), (1, '22.240')] -[2023-10-15 02:57:08,724][88298] Updated weights for policy 0, policy_version 17800 (0.0009) -[2023-10-15 02:57:09,103][88298] Updated weights for policy 0, policy_version 17810 (0.0007) -[2023-10-15 02:57:09,473][88298] Updated weights for policy 0, policy_version 17820 (0.0007) -[2023-10-15 02:57:10,470][88300] Updated weights for policy 1, policy_version 17892 (0.0007) -[2023-10-15 02:57:10,842][88300] Updated weights for policy 1, policy_version 17902 (0.0007) -[2023-10-15 02:57:11,209][88300] Updated weights for policy 1, policy_version 17912 (0.0007) -[2023-10-15 02:57:13,154][88298] Updated weights for policy 0, policy_version 17830 (0.0009) -[2023-10-15 02:57:13,525][88298] Updated weights for policy 0, policy_version 17840 (0.0010) -[2023-10-15 02:57:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 36601856. Throughput: 0: 1772.3, 1: 1744.5. Samples: 9164926. Policy #0 lag: (min: 31.0, avg: 32.9, max: 60.0) -[2023-10-15 02:57:13,534][87330] Avg episode reward: [(0, '22.590'), (1, '22.080')] -[2023-10-15 02:57:13,897][88298] Updated weights for policy 0, policy_version 17850 (0.0008) -[2023-10-15 02:57:15,134][88300] Updated weights for policy 1, policy_version 17922 (0.0008) -[2023-10-15 02:57:15,499][88300] Updated weights for policy 1, policy_version 17932 (0.0010) -[2023-10-15 02:57:15,857][88300] Updated weights for policy 1, policy_version 17942 (0.0010) -[2023-10-15 02:57:16,234][88300] Updated weights for policy 1, policy_version 17952 (0.0009) -[2023-10-15 02:57:17,929][88298] Updated weights for policy 0, policy_version 17860 (0.0009) -[2023-10-15 02:57:18,292][88298] Updated weights for policy 0, policy_version 17870 (0.0008) -[2023-10-15 02:57:18,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 36667392. Throughput: 0: 1740.3, 1: 1740.6. Samples: 9174382. Policy #0 lag: (min: 1.0, avg: 12.8, max: 33.0) -[2023-10-15 02:57:18,534][87330] Avg episode reward: [(0, '22.350'), (1, '21.700')] -[2023-10-15 02:57:18,669][88298] Updated weights for policy 0, policy_version 17880 (0.0007) -[2023-10-15 02:57:20,146][88300] Updated weights for policy 1, policy_version 17962 (0.0008) -[2023-10-15 02:57:20,521][88300] Updated weights for policy 1, policy_version 17972 (0.0008) -[2023-10-15 02:57:20,899][88300] Updated weights for policy 1, policy_version 17982 (0.0011) -[2023-10-15 02:57:22,494][88298] Updated weights for policy 0, policy_version 17890 (0.0007) -[2023-10-15 02:57:22,864][88298] Updated weights for policy 0, policy_version 17900 (0.0007) -[2023-10-15 02:57:23,230][88298] Updated weights for policy 0, policy_version 17910 (0.0007) -[2023-10-15 02:57:23,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 36732928. Throughput: 0: 1762.7, 1: 1741.1. Samples: 9195740. Policy #0 lag: (min: 1.0, avg: 12.8, max: 33.0) -[2023-10-15 02:57:23,534][87330] Avg episode reward: [(0, '22.280'), (1, '21.660')] -[2023-10-15 02:57:23,608][88298] Updated weights for policy 0, policy_version 17920 (0.0008) -[2023-10-15 02:57:24,824][88300] Updated weights for policy 1, policy_version 17992 (0.0011) -[2023-10-15 02:57:25,199][88300] Updated weights for policy 1, policy_version 18002 (0.0011) -[2023-10-15 02:57:25,569][88300] Updated weights for policy 1, policy_version 18012 (0.0011) -[2023-10-15 02:57:27,503][88298] Updated weights for policy 0, policy_version 17930 (0.0008) -[2023-10-15 02:57:27,877][88298] Updated weights for policy 0, policy_version 17940 (0.0009) -[2023-10-15 02:57:28,242][88298] Updated weights for policy 0, policy_version 17950 (0.0007) -[2023-10-15 02:57:28,534][87330] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 36831232. Throughput: 0: 1743.8, 1: 1757.7. Samples: 9216556. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-15 02:57:28,535][87330] Avg episode reward: [(0, '22.170'), (1, '21.690')] -[2023-10-15 02:57:29,495][88300] Updated weights for policy 1, policy_version 18022 (0.0008) -[2023-10-15 02:57:29,866][88300] Updated weights for policy 1, policy_version 18032 (0.0008) -[2023-10-15 02:57:30,235][88300] Updated weights for policy 1, policy_version 18042 (0.0010) -[2023-10-15 02:57:32,127][88298] Updated weights for policy 0, policy_version 17960 (0.0010) -[2023-10-15 02:57:32,512][88298] Updated weights for policy 0, policy_version 17970 (0.0009) -[2023-10-15 02:57:32,886][88298] Updated weights for policy 0, policy_version 17980 (0.0008) -[2023-10-15 02:57:33,534][87330] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 36896768. Throughput: 0: 1748.7, 1: 1726.1. Samples: 9226466. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-15 02:57:33,535][87330] Avg episode reward: [(0, '22.230'), (1, '21.860')] -[2023-10-15 02:57:34,115][88300] Updated weights for policy 1, policy_version 18052 (0.0009) -[2023-10-15 02:57:34,479][88300] Updated weights for policy 1, policy_version 18062 (0.0008) -[2023-10-15 02:57:34,854][88300] Updated weights for policy 1, policy_version 18072 (0.0008) -[2023-10-15 02:57:36,730][88298] Updated weights for policy 0, policy_version 17990 (0.0010) -[2023-10-15 02:57:37,110][88298] Updated weights for policy 0, policy_version 18000 (0.0008) -[2023-10-15 02:57:37,483][88298] Updated weights for policy 0, policy_version 18010 (0.0009) -[2023-10-15 02:57:38,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 36962304. Throughput: 0: 1753.2, 1: 1745.7. Samples: 9248016. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-15 02:57:38,534][87330] Avg episode reward: [(0, '22.260'), (1, '21.640')] -[2023-10-15 02:57:38,599][88300] Updated weights for policy 1, policy_version 18082 (0.0008) -[2023-10-15 02:57:38,969][88300] Updated weights for policy 1, policy_version 18092 (0.0008) -[2023-10-15 02:57:39,338][88300] Updated weights for policy 1, policy_version 18102 (0.0007) -[2023-10-15 02:57:39,701][88300] Updated weights for policy 1, policy_version 18112 (0.0007) -[2023-10-15 02:57:41,401][88298] Updated weights for policy 0, policy_version 18020 (0.0010) -[2023-10-15 02:57:41,783][88298] Updated weights for policy 0, policy_version 18030 (0.0009) -[2023-10-15 02:57:42,145][88298] Updated weights for policy 0, policy_version 18040 (0.0007) -[2023-10-15 02:57:43,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 37027840. Throughput: 0: 1732.8, 1: 1759.0. Samples: 9268806. Policy #0 lag: (min: 9.0, avg: 21.3, max: 41.0) -[2023-10-15 02:57:43,534][87330] Avg episode reward: [(0, '22.310'), (1, '21.400')] -[2023-10-15 02:57:43,546][88300] Updated weights for policy 1, policy_version 18122 (0.0009) -[2023-10-15 02:57:43,914][88300] Updated weights for policy 1, policy_version 18132 (0.0008) -[2023-10-15 02:57:44,275][88300] Updated weights for policy 1, policy_version 18142 (0.0009) -[2023-10-15 02:57:45,995][88298] Updated weights for policy 0, policy_version 18050 (0.0008) -[2023-10-15 02:57:46,369][88298] Updated weights for policy 0, policy_version 18060 (0.0009) -[2023-10-15 02:57:46,743][88298] Updated weights for policy 0, policy_version 18070 (0.0011) -[2023-10-15 02:57:47,108][88298] Updated weights for policy 0, policy_version 18080 (0.0009) -[2023-10-15 02:57:48,426][88300] Updated weights for policy 1, policy_version 18152 (0.0010) -[2023-10-15 02:57:48,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 37093376. Throughput: 0: 1762.5, 1: 1735.1. Samples: 9279592. Policy #0 lag: (min: 9.0, avg: 21.3, max: 41.0) -[2023-10-15 02:57:48,534][87330] Avg episode reward: [(0, '22.390'), (1, '21.690')] -[2023-10-15 02:57:48,801][88300] Updated weights for policy 1, policy_version 18162 (0.0009) -[2023-10-15 02:57:49,160][88300] Updated weights for policy 1, policy_version 18172 (0.0008) -[2023-10-15 02:57:51,032][88298] Updated weights for policy 0, policy_version 18090 (0.0009) -[2023-10-15 02:57:51,402][88298] Updated weights for policy 0, policy_version 18100 (0.0011) -[2023-10-15 02:57:51,775][88298] Updated weights for policy 0, policy_version 18110 (0.0009) -[2023-10-15 02:57:52,870][88300] Updated weights for policy 1, policy_version 18182 (0.0007) -[2023-10-15 02:57:53,246][88300] Updated weights for policy 1, policy_version 18192 (0.0008) -[2023-10-15 02:57:53,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 37158912. Throughput: 0: 1730.9, 1: 1757.3. Samples: 9299838. Policy #0 lag: (min: 9.0, avg: 21.3, max: 41.0) -[2023-10-15 02:57:53,534][87330] Avg episode reward: [(0, '22.600'), (1, '22.080')] -[2023-10-15 02:57:53,605][88300] Updated weights for policy 1, policy_version 18202 (0.0007) -[2023-10-15 02:57:55,741][88298] Updated weights for policy 0, policy_version 18120 (0.0007) -[2023-10-15 02:57:56,112][88298] Updated weights for policy 0, policy_version 18130 (0.0007) -[2023-10-15 02:57:56,476][88298] Updated weights for policy 0, policy_version 18140 (0.0008) -[2023-10-15 02:57:57,662][88300] Updated weights for policy 1, policy_version 18212 (0.0009) -[2023-10-15 02:57:58,036][88300] Updated weights for policy 1, policy_version 18222 (0.0011) -[2023-10-15 02:57:58,405][88300] Updated weights for policy 1, policy_version 18232 (0.0009) -[2023-10-15 02:57:58,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 37224448. Throughput: 0: 1718.5, 1: 1734.6. Samples: 9320316. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:57:58,534][87330] Avg episode reward: [(0, '22.600'), (1, '22.060')] -[2023-10-15 02:58:00,539][88298] Updated weights for policy 0, policy_version 18150 (0.0009) -[2023-10-15 02:58:00,915][88298] Updated weights for policy 0, policy_version 18160 (0.0008) -[2023-10-15 02:58:01,292][88298] Updated weights for policy 0, policy_version 18170 (0.0008) -[2023-10-15 02:58:02,254][88300] Updated weights for policy 1, policy_version 18242 (0.0010) -[2023-10-15 02:58:02,619][88300] Updated weights for policy 1, policy_version 18252 (0.0010) -[2023-10-15 02:58:02,988][88300] Updated weights for policy 1, policy_version 18262 (0.0008) -[2023-10-15 02:58:03,360][88300] Updated weights for policy 1, policy_version 18272 (0.0009) -[2023-10-15 02:58:03,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 37322752. Throughput: 0: 1735.4, 1: 1748.2. Samples: 9331146. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:58:03,534][87330] Avg episode reward: [(0, '22.720'), (1, '22.080')] -[2023-10-15 02:58:03,535][87905] Saving new best policy, reward=22.720! -[2023-10-15 02:58:05,298][88298] Updated weights for policy 0, policy_version 18180 (0.0007) -[2023-10-15 02:58:05,671][88298] Updated weights for policy 0, policy_version 18190 (0.0008) -[2023-10-15 02:58:06,044][88298] Updated weights for policy 0, policy_version 18200 (0.0009) -[2023-10-15 02:58:07,319][88300] Updated weights for policy 1, policy_version 18282 (0.0008) -[2023-10-15 02:58:07,690][88300] Updated weights for policy 1, policy_version 18292 (0.0007) -[2023-10-15 02:58:08,048][88300] Updated weights for policy 1, policy_version 18302 (0.0008) -[2023-10-15 02:58:08,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 37388288. Throughput: 0: 1719.6, 1: 1746.0. Samples: 9351692. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:58:08,534][87330] Avg episode reward: [(0, '22.790'), (1, '22.190')] -[2023-10-15 02:58:08,535][87905] Saving new best policy, reward=22.790! -[2023-10-15 02:58:09,808][88298] Updated weights for policy 0, policy_version 18210 (0.0010) -[2023-10-15 02:58:10,178][88298] Updated weights for policy 0, policy_version 18220 (0.0011) -[2023-10-15 02:58:10,540][88298] Updated weights for policy 0, policy_version 18230 (0.0007) -[2023-10-15 02:58:10,911][88298] Updated weights for policy 0, policy_version 18240 (0.0007) -[2023-10-15 02:58:11,878][88300] Updated weights for policy 1, policy_version 18312 (0.0008) -[2023-10-15 02:58:12,254][88300] Updated weights for policy 1, policy_version 18322 (0.0007) -[2023-10-15 02:58:12,623][88300] Updated weights for policy 1, policy_version 18332 (0.0007) -[2023-10-15 02:58:13,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 37453824. Throughput: 0: 1736.5, 1: 1729.5. Samples: 9372528. Policy #0 lag: (min: 24.0, avg: 31.6, max: 32.0) -[2023-10-15 02:58:13,534][87330] Avg episode reward: [(0, '22.720'), (1, '22.540')] -[2023-10-15 02:58:13,543][88033] Saving new best policy, reward=22.540! -[2023-10-15 02:58:14,838][88298] Updated weights for policy 0, policy_version 18250 (0.0007) -[2023-10-15 02:58:15,206][88298] Updated weights for policy 0, policy_version 18260 (0.0007) -[2023-10-15 02:58:15,574][88298] Updated weights for policy 0, policy_version 18270 (0.0007) -[2023-10-15 02:58:16,405][88300] Updated weights for policy 1, policy_version 18342 (0.0009) -[2023-10-15 02:58:16,774][88300] Updated weights for policy 1, policy_version 18352 (0.0009) -[2023-10-15 02:58:17,136][88300] Updated weights for policy 1, policy_version 18362 (0.0007) -[2023-10-15 02:58:18,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 37519360. Throughput: 0: 1721.9, 1: 1763.3. Samples: 9383300. Policy #0 lag: (min: 24.0, avg: 31.6, max: 32.0) -[2023-10-15 02:58:18,535][87330] Avg episode reward: [(0, '22.680'), (1, '22.550')] -[2023-10-15 02:58:18,536][88033] Saving new best policy, reward=22.550! -[2023-10-15 02:58:19,375][88298] Updated weights for policy 0, policy_version 18280 (0.0009) -[2023-10-15 02:58:19,755][88298] Updated weights for policy 0, policy_version 18290 (0.0008) -[2023-10-15 02:58:20,138][88298] Updated weights for policy 0, policy_version 18300 (0.0009) -[2023-10-15 02:58:21,114][88300] Updated weights for policy 1, policy_version 18372 (0.0008) -[2023-10-15 02:58:21,482][88300] Updated weights for policy 1, policy_version 18382 (0.0009) -[2023-10-15 02:58:21,857][88300] Updated weights for policy 1, policy_version 18392 (0.0010) -[2023-10-15 02:58:23,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 37584896. Throughput: 0: 1728.3, 1: 1727.2. Samples: 9403512. Policy #0 lag: (min: 24.0, avg: 31.6, max: 32.0) -[2023-10-15 02:58:23,534][87330] Avg episode reward: [(0, '22.660'), (1, '22.590')] -[2023-10-15 02:58:23,536][88033] Saving new best policy, reward=22.590! -[2023-10-15 02:58:23,898][88298] Updated weights for policy 0, policy_version 18310 (0.0010) -[2023-10-15 02:58:24,278][88298] Updated weights for policy 0, policy_version 18320 (0.0007) -[2023-10-15 02:58:24,648][88298] Updated weights for policy 0, policy_version 18330 (0.0007) -[2023-10-15 02:58:25,697][88300] Updated weights for policy 1, policy_version 18402 (0.0009) -[2023-10-15 02:58:26,060][88300] Updated weights for policy 1, policy_version 18412 (0.0009) -[2023-10-15 02:58:26,437][88300] Updated weights for policy 1, policy_version 18422 (0.0008) -[2023-10-15 02:58:26,797][88300] Updated weights for policy 1, policy_version 18432 (0.0010) -[2023-10-15 02:58:28,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 37650432. Throughput: 0: 1754.2, 1: 1723.8. Samples: 9425316. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-10-15 02:58:28,534][87330] Avg episode reward: [(0, '22.480'), (1, '22.370')] -[2023-10-15 02:58:28,731][88298] Updated weights for policy 0, policy_version 18340 (0.0010) -[2023-10-15 02:58:29,128][88298] Updated weights for policy 0, policy_version 18350 (0.0009) -[2023-10-15 02:58:29,495][88298] Updated weights for policy 0, policy_version 18360 (0.0008) -[2023-10-15 02:58:30,782][88300] Updated weights for policy 1, policy_version 18442 (0.0009) -[2023-10-15 02:58:31,139][88300] Updated weights for policy 1, policy_version 18452 (0.0008) -[2023-10-15 02:58:31,502][88300] Updated weights for policy 1, policy_version 18462 (0.0008) -[2023-10-15 02:58:33,377][88298] Updated weights for policy 0, policy_version 18370 (0.0008) -[2023-10-15 02:58:33,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 37715968. Throughput: 0: 1719.8, 1: 1735.7. Samples: 9435090. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-10-15 02:58:33,534][87330] Avg episode reward: [(0, '22.450'), (1, '22.340')] -[2023-10-15 02:58:33,753][88298] Updated weights for policy 0, policy_version 18380 (0.0010) -[2023-10-15 02:58:34,130][88298] Updated weights for policy 0, policy_version 18390 (0.0010) -[2023-10-15 02:58:34,500][88298] Updated weights for policy 0, policy_version 18400 (0.0007) -[2023-10-15 02:58:35,507][88300] Updated weights for policy 1, policy_version 18472 (0.0008) -[2023-10-15 02:58:35,866][88300] Updated weights for policy 1, policy_version 18482 (0.0008) -[2023-10-15 02:58:36,235][88300] Updated weights for policy 1, policy_version 18492 (0.0008) -[2023-10-15 02:58:38,370][88298] Updated weights for policy 0, policy_version 18410 (0.0007) -[2023-10-15 02:58:38,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 37781504. Throughput: 0: 1746.8, 1: 1723.1. Samples: 9455984. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-10-15 02:58:38,535][87330] Avg episode reward: [(0, '22.390'), (1, '22.110')] -[2023-10-15 02:58:38,745][88298] Updated weights for policy 0, policy_version 18420 (0.0010) -[2023-10-15 02:58:39,129][88298] Updated weights for policy 0, policy_version 18430 (0.0008) -[2023-10-15 02:58:40,093][88300] Updated weights for policy 1, policy_version 18502 (0.0009) -[2023-10-15 02:58:40,463][88300] Updated weights for policy 1, policy_version 18512 (0.0009) -[2023-10-15 02:58:40,823][88300] Updated weights for policy 1, policy_version 18522 (0.0008) -[2023-10-15 02:58:42,922][88298] Updated weights for policy 0, policy_version 18440 (0.0008) -[2023-10-15 02:58:43,299][88298] Updated weights for policy 0, policy_version 18450 (0.0008) -[2023-10-15 02:58:43,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 37847040. Throughput: 0: 1742.9, 1: 1744.8. Samples: 9477262. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-15 02:58:43,534][87330] Avg episode reward: [(0, '22.350'), (1, '21.760')] -[2023-10-15 02:58:43,679][88298] Updated weights for policy 0, policy_version 18460 (0.0008) -[2023-10-15 02:58:44,691][88300] Updated weights for policy 1, policy_version 18532 (0.0009) -[2023-10-15 02:58:45,061][88300] Updated weights for policy 1, policy_version 18542 (0.0007) -[2023-10-15 02:58:45,427][88300] Updated weights for policy 1, policy_version 18552 (0.0009) -[2023-10-15 02:58:47,626][88298] Updated weights for policy 0, policy_version 18470 (0.0008) -[2023-10-15 02:58:47,986][88298] Updated weights for policy 0, policy_version 18480 (0.0009) -[2023-10-15 02:58:48,356][88298] Updated weights for policy 0, policy_version 18490 (0.0007) -[2023-10-15 02:58:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 37912576. Throughput: 0: 1728.2, 1: 1731.9. Samples: 9486852. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-15 02:58:48,534][87330] Avg episode reward: [(0, '22.360'), (1, '21.790')] -[2023-10-15 02:58:49,336][88300] Updated weights for policy 1, policy_version 18562 (0.0007) -[2023-10-15 02:58:49,705][88300] Updated weights for policy 1, policy_version 18572 (0.0008) -[2023-10-15 02:58:50,073][88300] Updated weights for policy 1, policy_version 18582 (0.0008) -[2023-10-15 02:58:50,443][88300] Updated weights for policy 1, policy_version 18592 (0.0008) -[2023-10-15 02:58:52,353][88298] Updated weights for policy 0, policy_version 18500 (0.0009) -[2023-10-15 02:58:52,723][88298] Updated weights for policy 0, policy_version 18510 (0.0008) -[2023-10-15 02:58:53,093][88298] Updated weights for policy 0, policy_version 18520 (0.0008) -[2023-10-15 02:58:53,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 38010880. Throughput: 0: 1746.0, 1: 1737.1. Samples: 9508430. Policy #0 lag: (min: 24.0, avg: 45.3, max: 56.0) -[2023-10-15 02:58:53,535][87330] Avg episode reward: [(0, '22.350'), (1, '21.600')] -[2023-10-15 02:58:54,295][88300] Updated weights for policy 1, policy_version 18602 (0.0009) -[2023-10-15 02:58:54,658][88300] Updated weights for policy 1, policy_version 18612 (0.0009) -[2023-10-15 02:58:55,023][88300] Updated weights for policy 1, policy_version 18622 (0.0007) -[2023-10-15 02:58:56,955][88298] Updated weights for policy 0, policy_version 18530 (0.0008) -[2023-10-15 02:58:57,323][88298] Updated weights for policy 0, policy_version 18540 (0.0007) -[2023-10-15 02:58:57,694][88298] Updated weights for policy 0, policy_version 18550 (0.0008) -[2023-10-15 02:58:58,065][88298] Updated weights for policy 0, policy_version 18560 (0.0008) -[2023-10-15 02:58:58,534][87330] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 38076416. Throughput: 0: 1721.8, 1: 1761.4. Samples: 9529270. Policy #0 lag: (min: 24.0, avg: 45.3, max: 56.0) -[2023-10-15 02:58:58,535][87330] Avg episode reward: [(0, '22.530'), (1, '21.810')] -[2023-10-15 02:58:58,545][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000018560_19005440.pth... -[2023-10-15 02:58:58,579][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000016928_17334272.pth -[2023-10-15 02:58:58,840][88300] Updated weights for policy 1, policy_version 18632 (0.0010) -[2023-10-15 02:58:59,209][88300] Updated weights for policy 1, policy_version 18642 (0.0011) -[2023-10-15 02:58:59,586][88300] Updated weights for policy 1, policy_version 18652 (0.0011) -[2023-10-15 02:58:59,728][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000018656_19103744.pth... -[2023-10-15 02:58:59,757][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000016992_17399808.pth -[2023-10-15 02:59:01,942][88298] Updated weights for policy 0, policy_version 18570 (0.0010) -[2023-10-15 02:59:02,320][88298] Updated weights for policy 0, policy_version 18580 (0.0008) -[2023-10-15 02:59:02,693][88298] Updated weights for policy 0, policy_version 18590 (0.0007) -[2023-10-15 02:59:03,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 38141952. Throughput: 0: 1748.9, 1: 1730.1. Samples: 9539850. Policy #0 lag: (min: 24.0, avg: 45.3, max: 56.0) -[2023-10-15 02:59:03,534][87330] Avg episode reward: [(0, '22.490'), (1, '21.810')] -[2023-10-15 02:59:03,612][88300] Updated weights for policy 1, policy_version 18662 (0.0009) -[2023-10-15 02:59:03,980][88300] Updated weights for policy 1, policy_version 18672 (0.0009) -[2023-10-15 02:59:04,350][88300] Updated weights for policy 1, policy_version 18682 (0.0009) -[2023-10-15 02:59:06,676][88298] Updated weights for policy 0, policy_version 18600 (0.0010) -[2023-10-15 02:59:07,056][88298] Updated weights for policy 0, policy_version 18610 (0.0008) -[2023-10-15 02:59:07,422][88298] Updated weights for policy 0, policy_version 18620 (0.0008) -[2023-10-15 02:59:08,229][88300] Updated weights for policy 1, policy_version 18692 (0.0009) -[2023-10-15 02:59:08,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 38207488. Throughput: 0: 1737.8, 1: 1756.9. Samples: 9560774. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:59:08,535][87330] Avg episode reward: [(0, '22.540'), (1, '22.060')] -[2023-10-15 02:59:08,608][88300] Updated weights for policy 1, policy_version 18702 (0.0010) -[2023-10-15 02:59:08,983][88300] Updated weights for policy 1, policy_version 18712 (0.0009) -[2023-10-15 02:59:11,301][88298] Updated weights for policy 0, policy_version 18630 (0.0009) -[2023-10-15 02:59:11,678][88298] Updated weights for policy 0, policy_version 18640 (0.0009) -[2023-10-15 02:59:12,055][88298] Updated weights for policy 0, policy_version 18650 (0.0009) -[2023-10-15 02:59:12,823][88300] Updated weights for policy 1, policy_version 18722 (0.0009) -[2023-10-15 02:59:13,183][88300] Updated weights for policy 1, policy_version 18732 (0.0011) -[2023-10-15 02:59:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 38273024. Throughput: 0: 1710.7, 1: 1748.4. Samples: 9580978. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:59:13,534][87330] Avg episode reward: [(0, '22.580'), (1, '22.440')] -[2023-10-15 02:59:13,550][88300] Updated weights for policy 1, policy_version 18742 (0.0010) -[2023-10-15 02:59:13,917][88300] Updated weights for policy 1, policy_version 18752 (0.0010) -[2023-10-15 02:59:16,087][88298] Updated weights for policy 0, policy_version 18660 (0.0009) -[2023-10-15 02:59:16,455][88298] Updated weights for policy 0, policy_version 18670 (0.0010) -[2023-10-15 02:59:16,833][88298] Updated weights for policy 0, policy_version 18680 (0.0010) -[2023-10-15 02:59:17,916][88300] Updated weights for policy 1, policy_version 18762 (0.0008) -[2023-10-15 02:59:18,287][88300] Updated weights for policy 1, policy_version 18772 (0.0010) -[2023-10-15 02:59:18,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 38338560. Throughput: 0: 1741.6, 1: 1748.5. Samples: 9592144. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:59:18,534][87330] Avg episode reward: [(0, '22.640'), (1, '22.370')] -[2023-10-15 02:59:18,662][88300] Updated weights for policy 1, policy_version 18782 (0.0009) -[2023-10-15 02:59:20,830][88298] Updated weights for policy 0, policy_version 18690 (0.0009) -[2023-10-15 02:59:21,208][88298] Updated weights for policy 0, policy_version 18700 (0.0009) -[2023-10-15 02:59:21,587][88298] Updated weights for policy 0, policy_version 18710 (0.0008) -[2023-10-15 02:59:21,956][88298] Updated weights for policy 0, policy_version 18720 (0.0008) -[2023-10-15 02:59:22,549][88300] Updated weights for policy 1, policy_version 18792 (0.0009) -[2023-10-15 02:59:22,912][88300] Updated weights for policy 1, policy_version 18802 (0.0009) -[2023-10-15 02:59:23,285][88300] Updated weights for policy 1, policy_version 18812 (0.0012) -[2023-10-15 02:59:23,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 38436864. Throughput: 0: 1712.3, 1: 1760.3. Samples: 9612250. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:59:23,534][87330] Avg episode reward: [(0, '22.660'), (1, '22.270')] -[2023-10-15 02:59:25,930][88298] Updated weights for policy 0, policy_version 18730 (0.0009) -[2023-10-15 02:59:26,299][88298] Updated weights for policy 0, policy_version 18740 (0.0008) -[2023-10-15 02:59:26,664][88298] Updated weights for policy 0, policy_version 18750 (0.0011) -[2023-10-15 02:59:27,235][88300] Updated weights for policy 1, policy_version 18822 (0.0009) -[2023-10-15 02:59:27,607][88300] Updated weights for policy 1, policy_version 18832 (0.0008) -[2023-10-15 02:59:27,967][88300] Updated weights for policy 1, policy_version 18842 (0.0008) -[2023-10-15 02:59:28,534][87330] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 38502400. Throughput: 0: 1713.4, 1: 1729.2. Samples: 9632180. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:59:28,535][87330] Avg episode reward: [(0, '22.730'), (1, '22.460')] -[2023-10-15 02:59:30,627][88298] Updated weights for policy 0, policy_version 18760 (0.0008) -[2023-10-15 02:59:31,006][88298] Updated weights for policy 0, policy_version 18770 (0.0007) -[2023-10-15 02:59:31,367][88298] Updated weights for policy 0, policy_version 18780 (0.0008) -[2023-10-15 02:59:31,796][88300] Updated weights for policy 1, policy_version 18852 (0.0008) -[2023-10-15 02:59:32,171][88300] Updated weights for policy 1, policy_version 18862 (0.0010) -[2023-10-15 02:59:32,534][88300] Updated weights for policy 1, policy_version 18872 (0.0007) -[2023-10-15 02:59:33,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 38567936. Throughput: 0: 1731.2, 1: 1756.6. Samples: 9643806. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:59:33,535][87330] Avg episode reward: [(0, '22.780'), (1, '22.340')] -[2023-10-15 02:59:35,303][88298] Updated weights for policy 0, policy_version 18790 (0.0007) -[2023-10-15 02:59:35,679][88298] Updated weights for policy 0, policy_version 18800 (0.0009) -[2023-10-15 02:59:36,050][88298] Updated weights for policy 0, policy_version 18810 (0.0009) -[2023-10-15 02:59:36,405][88300] Updated weights for policy 1, policy_version 18882 (0.0008) -[2023-10-15 02:59:36,769][88300] Updated weights for policy 1, policy_version 18892 (0.0010) -[2023-10-15 02:59:37,140][88300] Updated weights for policy 1, policy_version 18902 (0.0010) -[2023-10-15 02:59:37,510][88300] Updated weights for policy 1, policy_version 18912 (0.0008) -[2023-10-15 02:59:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 38633472. Throughput: 0: 1712.3, 1: 1737.7. Samples: 9663680. Policy #0 lag: (min: 28.0, avg: 28.0, max: 31.0) -[2023-10-15 02:59:38,535][87330] Avg episode reward: [(0, '22.800'), (1, '22.140')] -[2023-10-15 02:59:38,536][87905] Saving new best policy, reward=22.800! -[2023-10-15 02:59:39,998][88298] Updated weights for policy 0, policy_version 18820 (0.0009) -[2023-10-15 02:59:40,375][88298] Updated weights for policy 0, policy_version 18830 (0.0010) -[2023-10-15 02:59:40,734][88298] Updated weights for policy 0, policy_version 18840 (0.0008) -[2023-10-15 02:59:41,377][88300] Updated weights for policy 1, policy_version 18922 (0.0009) -[2023-10-15 02:59:41,745][88300] Updated weights for policy 1, policy_version 18932 (0.0008) -[2023-10-15 02:59:42,119][88300] Updated weights for policy 1, policy_version 18942 (0.0009) -[2023-10-15 02:59:43,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 38699008. Throughput: 0: 1730.5, 1: 1726.4. Samples: 9684830. Policy #0 lag: (min: 28.0, avg: 28.0, max: 31.0) -[2023-10-15 02:59:43,535][87330] Avg episode reward: [(0, '22.820'), (1, '22.070')] -[2023-10-15 02:59:43,545][87905] Saving new best policy, reward=22.820! -[2023-10-15 02:59:44,633][88298] Updated weights for policy 0, policy_version 18850 (0.0008) -[2023-10-15 02:59:45,012][88298] Updated weights for policy 0, policy_version 18860 (0.0010) -[2023-10-15 02:59:45,379][88298] Updated weights for policy 0, policy_version 18870 (0.0009) -[2023-10-15 02:59:45,757][88298] Updated weights for policy 0, policy_version 18880 (0.0009) -[2023-10-15 02:59:45,830][88300] Updated weights for policy 1, policy_version 18952 (0.0010) -[2023-10-15 02:59:46,202][88300] Updated weights for policy 1, policy_version 18962 (0.0008) -[2023-10-15 02:59:46,578][88300] Updated weights for policy 1, policy_version 18972 (0.0009) -[2023-10-15 02:59:48,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 38764544. Throughput: 0: 1702.0, 1: 1741.7. Samples: 9694816. Policy #0 lag: (min: 28.0, avg: 28.0, max: 31.0) -[2023-10-15 02:59:48,534][87330] Avg episode reward: [(0, '22.680'), (1, '22.120')] -[2023-10-15 02:59:49,663][88298] Updated weights for policy 0, policy_version 18890 (0.0007) -[2023-10-15 02:59:50,040][88298] Updated weights for policy 0, policy_version 18900 (0.0008) -[2023-10-15 02:59:50,401][88298] Updated weights for policy 0, policy_version 18910 (0.0007) -[2023-10-15 02:59:50,661][88300] Updated weights for policy 1, policy_version 18982 (0.0009) -[2023-10-15 02:59:51,029][88300] Updated weights for policy 1, policy_version 18992 (0.0010) -[2023-10-15 02:59:51,396][88300] Updated weights for policy 1, policy_version 19002 (0.0010) -[2023-10-15 02:59:53,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 38830080. Throughput: 0: 1712.7, 1: 1724.1. Samples: 9715430. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:59:53,535][87330] Avg episode reward: [(0, '22.650'), (1, '22.130')] -[2023-10-15 02:59:54,257][88298] Updated weights for policy 0, policy_version 18920 (0.0010) -[2023-10-15 02:59:54,633][88298] Updated weights for policy 0, policy_version 18930 (0.0008) -[2023-10-15 02:59:55,009][88298] Updated weights for policy 0, policy_version 18940 (0.0007) -[2023-10-15 02:59:55,345][88300] Updated weights for policy 1, policy_version 19012 (0.0008) -[2023-10-15 02:59:55,719][88300] Updated weights for policy 1, policy_version 19022 (0.0009) -[2023-10-15 02:59:56,088][88300] Updated weights for policy 1, policy_version 19032 (0.0009) -[2023-10-15 02:59:58,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 38895616. Throughput: 0: 1734.7, 1: 1733.3. Samples: 9737036. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 02:59:58,534][87330] Avg episode reward: [(0, '22.640'), (1, '22.180')] -[2023-10-15 02:59:58,967][88298] Updated weights for policy 0, policy_version 18950 (0.0007) -[2023-10-15 02:59:59,337][88298] Updated weights for policy 0, policy_version 18960 (0.0007) -[2023-10-15 02:59:59,715][88298] Updated weights for policy 0, policy_version 18970 (0.0008) -[2023-10-15 02:59:59,910][88300] Updated weights for policy 1, policy_version 19042 (0.0010) -[2023-10-15 03:00:00,283][88300] Updated weights for policy 1, policy_version 19052 (0.0010) -[2023-10-15 03:00:00,653][88300] Updated weights for policy 1, policy_version 19062 (0.0009) -[2023-10-15 03:00:01,024][88300] Updated weights for policy 1, policy_version 19072 (0.0009) -[2023-10-15 03:00:03,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 38961152. Throughput: 0: 1706.0, 1: 1725.6. Samples: 9746566. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:00:03,535][87330] Avg episode reward: [(0, '22.610'), (1, '22.250')] -[2023-10-15 03:00:03,766][88298] Updated weights for policy 0, policy_version 18980 (0.0007) -[2023-10-15 03:00:04,137][88298] Updated weights for policy 0, policy_version 18990 (0.0008) -[2023-10-15 03:00:04,521][88298] Updated weights for policy 0, policy_version 19000 (0.0009) -[2023-10-15 03:00:05,011][88300] Updated weights for policy 1, policy_version 19082 (0.0009) -[2023-10-15 03:00:05,388][88300] Updated weights for policy 1, policy_version 19092 (0.0007) -[2023-10-15 03:00:05,750][88300] Updated weights for policy 1, policy_version 19102 (0.0010) -[2023-10-15 03:00:08,317][88298] Updated weights for policy 0, policy_version 19010 (0.0009) -[2023-10-15 03:00:08,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 39026688. Throughput: 0: 1734.8, 1: 1726.8. Samples: 9768022. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-15 03:00:08,535][87330] Avg episode reward: [(0, '22.570'), (1, '22.510')] -[2023-10-15 03:00:08,686][88298] Updated weights for policy 0, policy_version 19020 (0.0010) -[2023-10-15 03:00:09,066][88298] Updated weights for policy 0, policy_version 19030 (0.0009) -[2023-10-15 03:00:09,430][88298] Updated weights for policy 0, policy_version 19040 (0.0008) -[2023-10-15 03:00:09,764][88300] Updated weights for policy 1, policy_version 19112 (0.0009) -[2023-10-15 03:00:10,127][88300] Updated weights for policy 1, policy_version 19122 (0.0011) -[2023-10-15 03:00:10,491][88300] Updated weights for policy 1, policy_version 19132 (0.0008) -[2023-10-15 03:00:13,250][88298] Updated weights for policy 0, policy_version 19050 (0.0007) -[2023-10-15 03:00:13,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 39092224. Throughput: 0: 1740.3, 1: 1759.4. Samples: 9789668. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-15 03:00:13,535][87330] Avg episode reward: [(0, '22.580'), (1, '22.540')] -[2023-10-15 03:00:13,619][88298] Updated weights for policy 0, policy_version 19060 (0.0009) -[2023-10-15 03:00:13,991][88298] Updated weights for policy 0, policy_version 19070 (0.0007) -[2023-10-15 03:00:14,169][88300] Updated weights for policy 1, policy_version 19142 (0.0009) -[2023-10-15 03:00:14,539][88300] Updated weights for policy 1, policy_version 19152 (0.0010) -[2023-10-15 03:00:14,900][88300] Updated weights for policy 1, policy_version 19162 (0.0010) -[2023-10-15 03:00:18,012][88298] Updated weights for policy 0, policy_version 19080 (0.0007) -[2023-10-15 03:00:18,387][88298] Updated weights for policy 0, policy_version 19090 (0.0007) -[2023-10-15 03:00:18,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 39157760. Throughput: 0: 1721.8, 1: 1730.4. Samples: 9799154. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-15 03:00:18,534][87330] Avg episode reward: [(0, '22.680'), (1, '22.600')] -[2023-10-15 03:00:18,675][88300] Updated weights for policy 1, policy_version 19172 (0.0008) -[2023-10-15 03:00:18,745][88298] Updated weights for policy 0, policy_version 19100 (0.0008) -[2023-10-15 03:00:19,047][88300] Updated weights for policy 1, policy_version 19182 (0.0008) -[2023-10-15 03:00:19,418][88300] Updated weights for policy 1, policy_version 19192 (0.0007) -[2023-10-15 03:00:19,712][88033] Saving new best policy, reward=22.600! -[2023-10-15 03:00:22,657][88298] Updated weights for policy 0, policy_version 19110 (0.0007) -[2023-10-15 03:00:23,026][88298] Updated weights for policy 0, policy_version 19120 (0.0007) -[2023-10-15 03:00:23,328][88300] Updated weights for policy 1, policy_version 19202 (0.0009) -[2023-10-15 03:00:23,397][88298] Updated weights for policy 0, policy_version 19130 (0.0007) -[2023-10-15 03:00:23,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 39223296. Throughput: 0: 1738.7, 1: 1747.2. Samples: 9820542. Policy #0 lag: (min: 26.0, avg: 33.0, max: 58.0) -[2023-10-15 03:00:23,534][87330] Avg episode reward: [(0, '22.550'), (1, '22.540')] -[2023-10-15 03:00:23,692][88300] Updated weights for policy 1, policy_version 19212 (0.0010) -[2023-10-15 03:00:24,067][88300] Updated weights for policy 1, policy_version 19222 (0.0010) -[2023-10-15 03:00:24,437][88300] Updated weights for policy 1, policy_version 19232 (0.0010) -[2023-10-15 03:00:27,166][88298] Updated weights for policy 0, policy_version 19140 (0.0008) -[2023-10-15 03:00:27,535][88298] Updated weights for policy 0, policy_version 19150 (0.0008) -[2023-10-15 03:00:27,910][88298] Updated weights for policy 0, policy_version 19160 (0.0010) -[2023-10-15 03:00:28,450][88300] Updated weights for policy 1, policy_version 19242 (0.0010) -[2023-10-15 03:00:28,534][87330] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 39321600. Throughput: 0: 1723.7, 1: 1749.9. Samples: 9841142. Policy #0 lag: (min: 26.0, avg: 33.0, max: 58.0) -[2023-10-15 03:00:28,534][87330] Avg episode reward: [(0, '22.570'), (1, '22.580')] -[2023-10-15 03:00:28,806][88300] Updated weights for policy 1, policy_version 19252 (0.0007) -[2023-10-15 03:00:29,177][88300] Updated weights for policy 1, policy_version 19262 (0.0007) -[2023-10-15 03:00:31,943][88298] Updated weights for policy 0, policy_version 19170 (0.0007) -[2023-10-15 03:00:32,323][88298] Updated weights for policy 0, policy_version 19180 (0.0010) -[2023-10-15 03:00:32,691][88298] Updated weights for policy 0, policy_version 19190 (0.0009) -[2023-10-15 03:00:32,954][88300] Updated weights for policy 1, policy_version 19272 (0.0008) -[2023-10-15 03:00:33,067][88298] Updated weights for policy 0, policy_version 19200 (0.0007) -[2023-10-15 03:00:33,319][88300] Updated weights for policy 1, policy_version 19282 (0.0007) -[2023-10-15 03:00:33,534][87330] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 39387136. Throughput: 0: 1744.6, 1: 1740.7. Samples: 9851652. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-15 03:00:33,535][87330] Avg episode reward: [(0, '22.630'), (1, '22.330')] -[2023-10-15 03:00:33,692][88300] Updated weights for policy 1, policy_version 19292 (0.0007) -[2023-10-15 03:00:36,894][88298] Updated weights for policy 0, policy_version 19210 (0.0009) -[2023-10-15 03:00:37,260][88298] Updated weights for policy 0, policy_version 19220 (0.0008) -[2023-10-15 03:00:37,638][88298] Updated weights for policy 0, policy_version 19230 (0.0008) -[2023-10-15 03:00:37,648][88300] Updated weights for policy 1, policy_version 19302 (0.0008) -[2023-10-15 03:00:38,005][88300] Updated weights for policy 1, policy_version 19312 (0.0007) -[2023-10-15 03:00:38,372][88300] Updated weights for policy 1, policy_version 19322 (0.0008) -[2023-10-15 03:00:38,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 39452672. Throughput: 0: 1735.8, 1: 1760.7. Samples: 9872770. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-15 03:00:38,535][87330] Avg episode reward: [(0, '22.600'), (1, '22.300')] -[2023-10-15 03:00:41,649][88298] Updated weights for policy 0, policy_version 19240 (0.0007) -[2023-10-15 03:00:42,021][88298] Updated weights for policy 0, policy_version 19250 (0.0007) -[2023-10-15 03:00:42,288][88300] Updated weights for policy 1, policy_version 19332 (0.0008) -[2023-10-15 03:00:42,398][88298] Updated weights for policy 0, policy_version 19260 (0.0007) -[2023-10-15 03:00:42,658][88300] Updated weights for policy 1, policy_version 19342 (0.0007) -[2023-10-15 03:00:43,025][88300] Updated weights for policy 1, policy_version 19352 (0.0010) -[2023-10-15 03:00:43,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 39550976. Throughput: 0: 1710.8, 1: 1734.7. Samples: 9892082. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-15 03:00:43,535][87330] Avg episode reward: [(0, '22.480'), (1, '22.270')] -[2023-10-15 03:00:46,218][88298] Updated weights for policy 0, policy_version 19270 (0.0009) -[2023-10-15 03:00:46,582][88298] Updated weights for policy 0, policy_version 19280 (0.0010) -[2023-10-15 03:00:46,952][88298] Updated weights for policy 0, policy_version 19290 (0.0009) -[2023-10-15 03:00:47,066][88300] Updated weights for policy 1, policy_version 19362 (0.0010) -[2023-10-15 03:00:47,433][88300] Updated weights for policy 1, policy_version 19372 (0.0008) -[2023-10-15 03:00:47,803][88300] Updated weights for policy 1, policy_version 19382 (0.0011) -[2023-10-15 03:00:48,169][88300] Updated weights for policy 1, policy_version 19392 (0.0008) -[2023-10-15 03:00:48,534][87330] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 39616512. Throughput: 0: 1749.1, 1: 1754.4. Samples: 9904224. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-15 03:00:48,534][87330] Avg episode reward: [(0, '22.490'), (1, '22.140')] -[2023-10-15 03:00:51,011][88298] Updated weights for policy 0, policy_version 19300 (0.0008) -[2023-10-15 03:00:51,411][88298] Updated weights for policy 0, policy_version 19310 (0.0011) -[2023-10-15 03:00:51,777][88298] Updated weights for policy 0, policy_version 19320 (0.0008) -[2023-10-15 03:00:52,199][88300] Updated weights for policy 1, policy_version 19402 (0.0008) -[2023-10-15 03:00:52,563][88300] Updated weights for policy 1, policy_version 19412 (0.0008) -[2023-10-15 03:00:52,932][88300] Updated weights for policy 1, policy_version 19422 (0.0008) -[2023-10-15 03:00:53,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 39682048. Throughput: 0: 1720.8, 1: 1740.0. Samples: 9923760. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-15 03:00:53,535][87330] Avg episode reward: [(0, '22.550'), (1, '22.000')] -[2023-10-15 03:00:55,647][88298] Updated weights for policy 0, policy_version 19330 (0.0007) -[2023-10-15 03:00:56,016][88298] Updated weights for policy 0, policy_version 19340 (0.0008) -[2023-10-15 03:00:56,388][88298] Updated weights for policy 0, policy_version 19350 (0.0009) -[2023-10-15 03:00:56,720][88300] Updated weights for policy 1, policy_version 19432 (0.0007) -[2023-10-15 03:00:56,760][88298] Updated weights for policy 0, policy_version 19360 (0.0008) -[2023-10-15 03:00:57,096][88300] Updated weights for policy 1, policy_version 19442 (0.0007) -[2023-10-15 03:00:57,466][88300] Updated weights for policy 1, policy_version 19452 (0.0010) -[2023-10-15 03:00:58,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 39747584. Throughput: 0: 1713.0, 1: 1717.2. Samples: 9944026. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-15 03:00:58,534][87330] Avg episode reward: [(0, '22.400'), (1, '21.930')] -[2023-10-15 03:00:58,545][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000019360_19824640.pth... -[2023-10-15 03:00:58,545][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000019456_19922944.pth... -[2023-10-15 03:00:58,574][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000017728_18153472.pth -[2023-10-15 03:00:58,579][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000017824_18251776.pth -[2023-10-15 03:01:00,746][88298] Updated weights for policy 0, policy_version 19370 (0.0007) -[2023-10-15 03:01:01,119][88298] Updated weights for policy 0, policy_version 19380 (0.0009) -[2023-10-15 03:01:01,421][88300] Updated weights for policy 1, policy_version 19462 (0.0009) -[2023-10-15 03:01:01,494][88298] Updated weights for policy 0, policy_version 19390 (0.0008) -[2023-10-15 03:01:01,784][88300] Updated weights for policy 1, policy_version 19472 (0.0009) -[2023-10-15 03:01:02,151][88300] Updated weights for policy 1, policy_version 19482 (0.0007) -[2023-10-15 03:01:03,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 39813120. Throughput: 0: 1731.1, 1: 1745.9. Samples: 9955616. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-15 03:01:03,534][87330] Avg episode reward: [(0, '22.380'), (1, '22.060')] -[2023-10-15 03:01:05,411][88298] Updated weights for policy 0, policy_version 19400 (0.0007) -[2023-10-15 03:01:05,781][88298] Updated weights for policy 0, policy_version 19410 (0.0008) -[2023-10-15 03:01:06,028][88300] Updated weights for policy 1, policy_version 19492 (0.0008) -[2023-10-15 03:01:06,153][88298] Updated weights for policy 0, policy_version 19420 (0.0008) -[2023-10-15 03:01:06,400][88300] Updated weights for policy 1, policy_version 19502 (0.0009) -[2023-10-15 03:01:06,761][88300] Updated weights for policy 1, policy_version 19512 (0.0007) -[2023-10-15 03:01:08,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 39878656. Throughput: 0: 1709.8, 1: 1722.5. Samples: 9974994. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:01:08,534][87330] Avg episode reward: [(0, '22.180'), (1, '22.100')] -[2023-10-15 03:01:10,118][88298] Updated weights for policy 0, policy_version 19430 (0.0008) -[2023-10-15 03:01:10,491][88298] Updated weights for policy 0, policy_version 19440 (0.0007) -[2023-10-15 03:01:10,653][88300] Updated weights for policy 1, policy_version 19522 (0.0010) -[2023-10-15 03:01:10,858][88298] Updated weights for policy 0, policy_version 19450 (0.0007) -[2023-10-15 03:01:11,021][88300] Updated weights for policy 1, policy_version 19532 (0.0007) -[2023-10-15 03:01:11,394][88300] Updated weights for policy 1, policy_version 19542 (0.0008) -[2023-10-15 03:01:11,760][88300] Updated weights for policy 1, policy_version 19552 (0.0009) -[2023-10-15 03:01:13,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 39944192. Throughput: 0: 1729.4, 1: 1728.9. Samples: 9996768. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:01:13,534][87330] Avg episode reward: [(0, '22.220'), (1, '22.160')] -[2023-10-15 03:01:14,922][88298] Updated weights for policy 0, policy_version 19460 (0.0009) -[2023-10-15 03:01:15,298][88298] Updated weights for policy 0, policy_version 19470 (0.0008) -[2023-10-15 03:01:15,439][88300] Updated weights for policy 1, policy_version 19562 (0.0009) -[2023-10-15 03:01:15,668][88298] Updated weights for policy 0, policy_version 19480 (0.0008) -[2023-10-15 03:01:15,806][88300] Updated weights for policy 1, policy_version 19572 (0.0009) -[2023-10-15 03:01:16,175][88300] Updated weights for policy 1, policy_version 19582 (0.0008) -[2023-10-15 03:01:18,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 40009728. Throughput: 0: 1713.4, 1: 1728.5. Samples: 10006536. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:01:18,535][87330] Avg episode reward: [(0, '22.330'), (1, '22.060')] -[2023-10-15 03:01:19,679][88298] Updated weights for policy 0, policy_version 19490 (0.0008) -[2023-10-15 03:01:20,049][88298] Updated weights for policy 0, policy_version 19500 (0.0009) -[2023-10-15 03:01:20,166][88300] Updated weights for policy 1, policy_version 19592 (0.0008) -[2023-10-15 03:01:20,421][88298] Updated weights for policy 0, policy_version 19510 (0.0007) -[2023-10-15 03:01:20,536][88300] Updated weights for policy 1, policy_version 19602 (0.0007) -[2023-10-15 03:01:20,793][88298] Updated weights for policy 0, policy_version 19520 (0.0008) -[2023-10-15 03:01:20,895][88300] Updated weights for policy 1, policy_version 19612 (0.0008) -[2023-10-15 03:01:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 40075264. Throughput: 0: 1705.4, 1: 1728.0. Samples: 10027272. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-15 03:01:23,534][87330] Avg episode reward: [(0, '22.240'), (1, '22.180')] -[2023-10-15 03:01:24,616][88300] Updated weights for policy 1, policy_version 19622 (0.0008) -[2023-10-15 03:01:24,818][88298] Updated weights for policy 0, policy_version 19530 (0.0007) -[2023-10-15 03:01:24,985][88300] Updated weights for policy 1, policy_version 19632 (0.0009) -[2023-10-15 03:01:25,188][88298] Updated weights for policy 0, policy_version 19540 (0.0007) -[2023-10-15 03:01:25,341][88300] Updated weights for policy 1, policy_version 19642 (0.0008) -[2023-10-15 03:01:25,560][88298] Updated weights for policy 0, policy_version 19550 (0.0009) -[2023-10-15 03:01:28,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 40140800. Throughput: 0: 1728.8, 1: 1756.4. Samples: 10048914. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-15 03:01:28,535][87330] Avg episode reward: [(0, '22.280'), (1, '22.130')] -[2023-10-15 03:01:29,192][88300] Updated weights for policy 1, policy_version 19652 (0.0008) -[2023-10-15 03:01:29,492][88298] Updated weights for policy 0, policy_version 19560 (0.0009) -[2023-10-15 03:01:29,551][88300] Updated weights for policy 1, policy_version 19662 (0.0010) -[2023-10-15 03:01:29,863][88298] Updated weights for policy 0, policy_version 19570 (0.0009) -[2023-10-15 03:01:29,924][88300] Updated weights for policy 1, policy_version 19672 (0.0010) -[2023-10-15 03:01:30,224][88298] Updated weights for policy 0, policy_version 19580 (0.0009) -[2023-10-15 03:01:33,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 40206336. Throughput: 0: 1691.3, 1: 1736.0. Samples: 10058450. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-15 03:01:33,535][87330] Avg episode reward: [(0, '22.410'), (1, '22.140')] -[2023-10-15 03:01:33,960][88300] Updated weights for policy 1, policy_version 19682 (0.0009) -[2023-10-15 03:01:34,174][88298] Updated weights for policy 0, policy_version 19590 (0.0010) -[2023-10-15 03:01:34,338][88300] Updated weights for policy 1, policy_version 19692 (0.0008) -[2023-10-15 03:01:34,536][88298] Updated weights for policy 0, policy_version 19600 (0.0008) -[2023-10-15 03:01:34,707][88300] Updated weights for policy 1, policy_version 19702 (0.0009) -[2023-10-15 03:01:34,909][88298] Updated weights for policy 0, policy_version 19610 (0.0008) -[2023-10-15 03:01:35,078][88300] Updated weights for policy 1, policy_version 19712 (0.0007) -[2023-10-15 03:01:38,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 40271872. Throughput: 0: 1719.6, 1: 1749.1. Samples: 10079850. Policy #0 lag: (min: 38.0, avg: 55.1, max: 56.0) -[2023-10-15 03:01:38,534][87330] Avg episode reward: [(0, '22.300'), (1, '22.180')] -[2023-10-15 03:01:38,946][88298] Updated weights for policy 0, policy_version 19620 (0.0008) -[2023-10-15 03:01:39,005][88300] Updated weights for policy 1, policy_version 19722 (0.0009) -[2023-10-15 03:01:39,333][88298] Updated weights for policy 0, policy_version 19630 (0.0007) -[2023-10-15 03:01:39,372][88300] Updated weights for policy 1, policy_version 19732 (0.0008) -[2023-10-15 03:01:39,701][88298] Updated weights for policy 0, policy_version 19640 (0.0008) -[2023-10-15 03:01:39,741][88300] Updated weights for policy 1, policy_version 19742 (0.0009) -[2023-10-15 03:01:43,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 40337408. Throughput: 0: 1724.2, 1: 1767.4. Samples: 10101148. Policy #0 lag: (min: 38.0, avg: 55.1, max: 56.0) -[2023-10-15 03:01:43,534][87330] Avg episode reward: [(0, '22.410'), (1, '22.110')] -[2023-10-15 03:01:43,569][88298] Updated weights for policy 0, policy_version 19650 (0.0010) -[2023-10-15 03:01:43,698][88300] Updated weights for policy 1, policy_version 19752 (0.0009) -[2023-10-15 03:01:43,928][88298] Updated weights for policy 0, policy_version 19660 (0.0008) -[2023-10-15 03:01:44,076][88300] Updated weights for policy 1, policy_version 19762 (0.0009) -[2023-10-15 03:01:44,297][88298] Updated weights for policy 0, policy_version 19670 (0.0007) -[2023-10-15 03:01:44,441][88300] Updated weights for policy 1, policy_version 19772 (0.0007) -[2023-10-15 03:01:44,667][88298] Updated weights for policy 0, policy_version 19680 (0.0007) -[2023-10-15 03:01:48,298][88300] Updated weights for policy 1, policy_version 19782 (0.0009) -[2023-10-15 03:01:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 40402944. Throughput: 0: 1704.3, 1: 1733.6. Samples: 10110318. Policy #0 lag: (min: 38.0, avg: 55.1, max: 56.0) -[2023-10-15 03:01:48,534][87330] Avg episode reward: [(0, '22.220'), (1, '22.290')] -[2023-10-15 03:01:48,650][88298] Updated weights for policy 0, policy_version 19690 (0.0008) -[2023-10-15 03:01:48,669][88300] Updated weights for policy 1, policy_version 19792 (0.0010) -[2023-10-15 03:01:49,021][88298] Updated weights for policy 0, policy_version 19700 (0.0007) -[2023-10-15 03:01:49,035][88300] Updated weights for policy 1, policy_version 19802 (0.0007) -[2023-10-15 03:01:49,397][88298] Updated weights for policy 0, policy_version 19710 (0.0008) -[2023-10-15 03:01:52,966][88300] Updated weights for policy 1, policy_version 19812 (0.0007) -[2023-10-15 03:01:53,334][88300] Updated weights for policy 1, policy_version 19822 (0.0008) -[2023-10-15 03:01:53,384][88298] Updated weights for policy 0, policy_version 19720 (0.0007) -[2023-10-15 03:01:53,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 40468480. Throughput: 0: 1726.8, 1: 1758.2. Samples: 10131820. Policy #0 lag: (min: 2.0, avg: 7.1, max: 34.0) -[2023-10-15 03:01:53,534][87330] Avg episode reward: [(0, '22.340'), (1, '22.350')] -[2023-10-15 03:01:53,710][88300] Updated weights for policy 1, policy_version 19832 (0.0009) -[2023-10-15 03:01:53,749][88298] Updated weights for policy 0, policy_version 19730 (0.0007) -[2023-10-15 03:01:54,131][88298] Updated weights for policy 0, policy_version 19740 (0.0010) -[2023-10-15 03:01:57,650][88300] Updated weights for policy 1, policy_version 19842 (0.0009) -[2023-10-15 03:01:58,016][88298] Updated weights for policy 0, policy_version 19750 (0.0009) -[2023-10-15 03:01:58,018][88300] Updated weights for policy 1, policy_version 19852 (0.0009) -[2023-10-15 03:01:58,381][88298] Updated weights for policy 0, policy_version 19760 (0.0009) -[2023-10-15 03:01:58,384][88300] Updated weights for policy 1, policy_version 19862 (0.0010) -[2023-10-15 03:01:58,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 40534016. Throughput: 0: 1724.3, 1: 1736.7. Samples: 10152510. Policy #0 lag: (min: 2.0, avg: 7.1, max: 34.0) -[2023-10-15 03:01:58,534][87330] Avg episode reward: [(0, '22.320'), (1, '22.260')] -[2023-10-15 03:01:58,745][88300] Updated weights for policy 1, policy_version 19872 (0.0009) -[2023-10-15 03:01:58,752][88298] Updated weights for policy 0, policy_version 19770 (0.0007) -[2023-10-15 03:02:02,726][88298] Updated weights for policy 0, policy_version 19780 (0.0007) -[2023-10-15 03:02:02,807][88300] Updated weights for policy 1, policy_version 19882 (0.0008) -[2023-10-15 03:02:03,113][88298] Updated weights for policy 0, policy_version 19790 (0.0008) -[2023-10-15 03:02:03,173][88300] Updated weights for policy 1, policy_version 19892 (0.0008) -[2023-10-15 03:02:03,474][88298] Updated weights for policy 0, policy_version 19800 (0.0008) -[2023-10-15 03:02:03,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 40599552. Throughput: 0: 1718.9, 1: 1741.5. Samples: 10162254. Policy #0 lag: (min: 2.0, avg: 7.1, max: 34.0) -[2023-10-15 03:02:03,535][87330] Avg episode reward: [(0, '22.290'), (1, '22.260')] -[2023-10-15 03:02:03,542][88300] Updated weights for policy 1, policy_version 19902 (0.0008) -[2023-10-15 03:02:07,238][88298] Updated weights for policy 0, policy_version 19810 (0.0007) -[2023-10-15 03:02:07,602][88298] Updated weights for policy 0, policy_version 19820 (0.0008) -[2023-10-15 03:02:07,664][88300] Updated weights for policy 1, policy_version 19912 (0.0008) -[2023-10-15 03:02:07,980][88298] Updated weights for policy 0, policy_version 19830 (0.0008) -[2023-10-15 03:02:08,038][88300] Updated weights for policy 1, policy_version 19922 (0.0007) -[2023-10-15 03:02:08,342][88298] Updated weights for policy 0, policy_version 19840 (0.0009) -[2023-10-15 03:02:08,404][88300] Updated weights for policy 1, policy_version 19932 (0.0007) -[2023-10-15 03:02:08,534][87330] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 40697856. Throughput: 0: 1734.8, 1: 1737.4. Samples: 10183522. Policy #0 lag: (min: 29.0, avg: 37.0, max: 61.0) -[2023-10-15 03:02:08,535][87330] Avg episode reward: [(0, '22.420'), (1, '22.220')] -[2023-10-15 03:02:12,297][88298] Updated weights for policy 0, policy_version 19850 (0.0007) -[2023-10-15 03:02:12,324][88300] Updated weights for policy 1, policy_version 19942 (0.0008) -[2023-10-15 03:02:12,661][88298] Updated weights for policy 0, policy_version 19860 (0.0007) -[2023-10-15 03:02:12,700][88300] Updated weights for policy 1, policy_version 19952 (0.0008) -[2023-10-15 03:02:13,028][88298] Updated weights for policy 0, policy_version 19870 (0.0007) -[2023-10-15 03:02:13,068][88300] Updated weights for policy 1, policy_version 19962 (0.0010) -[2023-10-15 03:02:13,534][87330] Fps is (10 sec: 19660.7, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 40796160. Throughput: 0: 1719.2, 1: 1704.9. Samples: 10202998. Policy #0 lag: (min: 29.0, avg: 37.0, max: 61.0) -[2023-10-15 03:02:13,535][87330] Avg episode reward: [(0, '22.400'), (1, '22.270')] -[2023-10-15 03:02:16,954][88298] Updated weights for policy 0, policy_version 19880 (0.0007) -[2023-10-15 03:02:17,046][88300] Updated weights for policy 1, policy_version 19972 (0.0008) -[2023-10-15 03:02:17,322][88298] Updated weights for policy 0, policy_version 19890 (0.0008) -[2023-10-15 03:02:17,413][88300] Updated weights for policy 1, policy_version 19982 (0.0008) -[2023-10-15 03:02:17,693][88298] Updated weights for policy 0, policy_version 19900 (0.0009) -[2023-10-15 03:02:17,767][88300] Updated weights for policy 1, policy_version 19992 (0.0008) -[2023-10-15 03:02:18,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 40861696. Throughput: 0: 1739.2, 1: 1726.0. Samples: 10214384. Policy #0 lag: (min: 29.0, avg: 37.0, max: 61.0) -[2023-10-15 03:02:18,535][87330] Avg episode reward: [(0, '22.460'), (1, '22.340')] -[2023-10-15 03:02:21,491][88298] Updated weights for policy 0, policy_version 19910 (0.0008) -[2023-10-15 03:02:21,609][88300] Updated weights for policy 1, policy_version 20002 (0.0009) -[2023-10-15 03:02:21,850][88298] Updated weights for policy 0, policy_version 19920 (0.0008) -[2023-10-15 03:02:21,978][88300] Updated weights for policy 1, policy_version 20012 (0.0008) -[2023-10-15 03:02:22,221][88298] Updated weights for policy 0, policy_version 19930 (0.0008) -[2023-10-15 03:02:22,343][88300] Updated weights for policy 1, policy_version 20022 (0.0008) -[2023-10-15 03:02:22,703][88300] Updated weights for policy 1, policy_version 20032 (0.0009) -[2023-10-15 03:02:23,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 40927232. Throughput: 0: 1733.7, 1: 1714.7. Samples: 10235030. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:02:23,535][87330] Avg episode reward: [(0, '22.630'), (1, '22.340')] -[2023-10-15 03:02:26,286][88298] Updated weights for policy 0, policy_version 19940 (0.0008) -[2023-10-15 03:02:26,465][88300] Updated weights for policy 1, policy_version 20042 (0.0010) -[2023-10-15 03:02:26,678][88298] Updated weights for policy 0, policy_version 19950 (0.0007) -[2023-10-15 03:02:26,827][88300] Updated weights for policy 1, policy_version 20052 (0.0010) -[2023-10-15 03:02:27,055][88298] Updated weights for policy 0, policy_version 19960 (0.0008) -[2023-10-15 03:02:27,199][88300] Updated weights for policy 1, policy_version 20062 (0.0009) -[2023-10-15 03:02:28,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 40992768. Throughput: 0: 1710.4, 1: 1707.6. Samples: 10254962. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:02:28,534][87330] Avg episode reward: [(0, '22.610'), (1, '22.320')] -[2023-10-15 03:02:31,020][88298] Updated weights for policy 0, policy_version 19970 (0.0008) -[2023-10-15 03:02:31,349][88300] Updated weights for policy 1, policy_version 20072 (0.0008) -[2023-10-15 03:02:31,387][88298] Updated weights for policy 0, policy_version 19980 (0.0008) -[2023-10-15 03:02:31,718][88300] Updated weights for policy 1, policy_version 20082 (0.0008) -[2023-10-15 03:02:31,761][88298] Updated weights for policy 0, policy_version 19990 (0.0009) -[2023-10-15 03:02:32,089][88300] Updated weights for policy 1, policy_version 20092 (0.0010) -[2023-10-15 03:02:32,128][88298] Updated weights for policy 0, policy_version 20000 (0.0008) -[2023-10-15 03:02:33,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 41058304. Throughput: 0: 1737.3, 1: 1734.8. Samples: 10266560. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:02:33,535][87330] Avg episode reward: [(0, '22.630'), (1, '22.580')] -[2023-10-15 03:02:35,845][88300] Updated weights for policy 1, policy_version 20102 (0.0008) -[2023-10-15 03:02:35,927][88298] Updated weights for policy 0, policy_version 20010 (0.0008) -[2023-10-15 03:02:36,203][88300] Updated weights for policy 1, policy_version 20112 (0.0008) -[2023-10-15 03:02:36,290][88298] Updated weights for policy 0, policy_version 20020 (0.0007) -[2023-10-15 03:02:36,580][88300] Updated weights for policy 1, policy_version 20122 (0.0008) -[2023-10-15 03:02:36,664][88298] Updated weights for policy 0, policy_version 20030 (0.0008) -[2023-10-15 03:02:38,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 41123840. Throughput: 0: 1708.2, 1: 1708.4. Samples: 10285568. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:02:38,535][87330] Avg episode reward: [(0, '22.670'), (1, '22.640')] -[2023-10-15 03:02:38,537][88033] Saving new best policy, reward=22.640! -[2023-10-15 03:02:40,342][88300] Updated weights for policy 1, policy_version 20132 (0.0008) -[2023-10-15 03:02:40,562][88298] Updated weights for policy 0, policy_version 20040 (0.0009) -[2023-10-15 03:02:40,701][88300] Updated weights for policy 1, policy_version 20142 (0.0007) -[2023-10-15 03:02:40,926][88298] Updated weights for policy 0, policy_version 20050 (0.0007) -[2023-10-15 03:02:41,071][88300] Updated weights for policy 1, policy_version 20152 (0.0009) -[2023-10-15 03:02:41,303][88298] Updated weights for policy 0, policy_version 20060 (0.0007) -[2023-10-15 03:02:43,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 41189376. Throughput: 0: 1711.7, 1: 1731.3. Samples: 10307444. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:02:43,535][87330] Avg episode reward: [(0, '22.720'), (1, '22.460')] -[2023-10-15 03:02:44,944][88300] Updated weights for policy 1, policy_version 20162 (0.0008) -[2023-10-15 03:02:45,181][88298] Updated weights for policy 0, policy_version 20070 (0.0009) -[2023-10-15 03:02:45,311][88300] Updated weights for policy 1, policy_version 20172 (0.0009) -[2023-10-15 03:02:45,550][88298] Updated weights for policy 0, policy_version 20080 (0.0009) -[2023-10-15 03:02:45,675][88300] Updated weights for policy 1, policy_version 20182 (0.0008) -[2023-10-15 03:02:45,925][88298] Updated weights for policy 0, policy_version 20090 (0.0008) -[2023-10-15 03:02:46,037][88300] Updated weights for policy 1, policy_version 20192 (0.0009) -[2023-10-15 03:02:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 41254912. Throughput: 0: 1725.0, 1: 1722.7. Samples: 10317398. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:02:48,535][87330] Avg episode reward: [(0, '22.720'), (1, '22.300')] -[2023-10-15 03:02:49,861][88298] Updated weights for policy 0, policy_version 20100 (0.0007) -[2023-10-15 03:02:50,138][88300] Updated weights for policy 1, policy_version 20202 (0.0008) -[2023-10-15 03:02:50,232][88298] Updated weights for policy 0, policy_version 20110 (0.0008) -[2023-10-15 03:02:50,508][88300] Updated weights for policy 1, policy_version 20212 (0.0009) -[2023-10-15 03:02:50,606][88298] Updated weights for policy 0, policy_version 20120 (0.0008) -[2023-10-15 03:02:50,882][88300] Updated weights for policy 1, policy_version 20222 (0.0008) -[2023-10-15 03:02:53,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 41320448. Throughput: 0: 1714.0, 1: 1719.2. Samples: 10338014. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:02:53,534][87330] Avg episode reward: [(0, '22.760'), (1, '22.270')] -[2023-10-15 03:02:54,591][88298] Updated weights for policy 0, policy_version 20130 (0.0009) -[2023-10-15 03:02:54,810][88300] Updated weights for policy 1, policy_version 20232 (0.0009) -[2023-10-15 03:02:54,959][88298] Updated weights for policy 0, policy_version 20140 (0.0007) -[2023-10-15 03:02:55,180][88300] Updated weights for policy 1, policy_version 20242 (0.0008) -[2023-10-15 03:02:55,326][88298] Updated weights for policy 0, policy_version 20150 (0.0009) -[2023-10-15 03:02:55,553][88300] Updated weights for policy 1, policy_version 20252 (0.0007) -[2023-10-15 03:02:55,693][88298] Updated weights for policy 0, policy_version 20160 (0.0007) -[2023-10-15 03:02:58,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 41385984. Throughput: 0: 1730.0, 1: 1745.8. Samples: 10359408. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:02:58,535][87330] Avg episode reward: [(0, '22.740'), (1, '22.210')] -[2023-10-15 03:02:58,545][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000020160_20643840.pth... -[2023-10-15 03:02:58,545][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000020256_20742144.pth... -[2023-10-15 03:02:58,591][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000018560_19005440.pth -[2023-10-15 03:02:58,591][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000018656_19103744.pth -[2023-10-15 03:02:59,484][88300] Updated weights for policy 1, policy_version 20262 (0.0009) -[2023-10-15 03:02:59,762][88298] Updated weights for policy 0, policy_version 20170 (0.0007) -[2023-10-15 03:02:59,859][88300] Updated weights for policy 1, policy_version 20272 (0.0008) -[2023-10-15 03:03:00,132][88298] Updated weights for policy 0, policy_version 20180 (0.0009) -[2023-10-15 03:03:00,233][88300] Updated weights for policy 1, policy_version 20282 (0.0010) -[2023-10-15 03:03:00,505][88298] Updated weights for policy 0, policy_version 20190 (0.0009) -[2023-10-15 03:03:03,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 41451520. Throughput: 0: 1708.7, 1: 1720.4. Samples: 10368690. Policy #0 lag: (min: 10.0, avg: 13.3, max: 42.0) -[2023-10-15 03:03:03,535][87330] Avg episode reward: [(0, '22.780'), (1, '22.030')] -[2023-10-15 03:03:04,234][88300] Updated weights for policy 1, policy_version 20292 (0.0008) -[2023-10-15 03:03:04,590][88298] Updated weights for policy 0, policy_version 20200 (0.0009) -[2023-10-15 03:03:04,602][88300] Updated weights for policy 1, policy_version 20302 (0.0011) -[2023-10-15 03:03:04,959][88298] Updated weights for policy 0, policy_version 20210 (0.0009) -[2023-10-15 03:03:04,979][88300] Updated weights for policy 1, policy_version 20312 (0.0008) -[2023-10-15 03:03:05,323][88298] Updated weights for policy 0, policy_version 20220 (0.0007) -[2023-10-15 03:03:08,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 41517056. Throughput: 0: 1713.6, 1: 1731.2. Samples: 10390050. Policy #0 lag: (min: 10.0, avg: 13.3, max: 42.0) -[2023-10-15 03:03:08,534][87330] Avg episode reward: [(0, '22.680'), (1, '22.050')] -[2023-10-15 03:03:08,825][88300] Updated weights for policy 1, policy_version 20322 (0.0007) -[2023-10-15 03:03:09,077][88298] Updated weights for policy 0, policy_version 20230 (0.0008) -[2023-10-15 03:03:09,198][88300] Updated weights for policy 1, policy_version 20332 (0.0009) -[2023-10-15 03:03:09,454][88298] Updated weights for policy 0, policy_version 20240 (0.0008) -[2023-10-15 03:03:09,567][88300] Updated weights for policy 1, policy_version 20342 (0.0007) -[2023-10-15 03:03:09,821][88298] Updated weights for policy 0, policy_version 20250 (0.0009) -[2023-10-15 03:03:09,937][88300] Updated weights for policy 1, policy_version 20352 (0.0008) -[2023-10-15 03:03:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 41582592. Throughput: 0: 1739.3, 1: 1742.1. Samples: 10411626. Policy #0 lag: (min: 10.0, avg: 13.3, max: 42.0) -[2023-10-15 03:03:13,535][87330] Avg episode reward: [(0, '22.600'), (1, '22.170')] -[2023-10-15 03:03:13,847][88298] Updated weights for policy 0, policy_version 20260 (0.0010) -[2023-10-15 03:03:14,015][88300] Updated weights for policy 1, policy_version 20362 (0.0008) -[2023-10-15 03:03:14,231][88298] Updated weights for policy 0, policy_version 20270 (0.0008) -[2023-10-15 03:03:14,375][88300] Updated weights for policy 1, policy_version 20372 (0.0008) -[2023-10-15 03:03:14,605][88298] Updated weights for policy 0, policy_version 20280 (0.0007) -[2023-10-15 03:03:14,741][88300] Updated weights for policy 1, policy_version 20382 (0.0008) -[2023-10-15 03:03:18,522][88300] Updated weights for policy 1, policy_version 20392 (0.0007) -[2023-10-15 03:03:18,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 13773.7). Total num frames: 41648128. Throughput: 0: 1710.4, 1: 1719.6. Samples: 10420906. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-15 03:03:18,534][87330] Avg episode reward: [(0, '22.520'), (1, '22.130')] -[2023-10-15 03:03:18,565][88298] Updated weights for policy 0, policy_version 20290 (0.0008) -[2023-10-15 03:03:18,896][88300] Updated weights for policy 1, policy_version 20402 (0.0007) -[2023-10-15 03:03:18,937][88298] Updated weights for policy 0, policy_version 20300 (0.0008) -[2023-10-15 03:03:19,261][88300] Updated weights for policy 1, policy_version 20412 (0.0009) -[2023-10-15 03:03:19,303][88298] Updated weights for policy 0, policy_version 20310 (0.0007) -[2023-10-15 03:03:19,673][88298] Updated weights for policy 0, policy_version 20320 (0.0008) -[2023-10-15 03:03:23,046][88300] Updated weights for policy 1, policy_version 20422 (0.0007) -[2023-10-15 03:03:23,423][88300] Updated weights for policy 1, policy_version 20432 (0.0008) -[2023-10-15 03:03:23,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 41713664. Throughput: 0: 1741.1, 1: 1746.9. Samples: 10442530. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-15 03:03:23,535][87330] Avg episode reward: [(0, '22.500'), (1, '22.270')] -[2023-10-15 03:03:23,579][88298] Updated weights for policy 0, policy_version 20330 (0.0008) -[2023-10-15 03:03:23,787][88300] Updated weights for policy 1, policy_version 20442 (0.0007) -[2023-10-15 03:03:23,957][88298] Updated weights for policy 0, policy_version 20340 (0.0009) -[2023-10-15 03:03:24,320][88298] Updated weights for policy 0, policy_version 20350 (0.0010) -[2023-10-15 03:03:27,803][88300] Updated weights for policy 1, policy_version 20452 (0.0009) -[2023-10-15 03:03:28,168][88298] Updated weights for policy 0, policy_version 20360 (0.0008) -[2023-10-15 03:03:28,177][88300] Updated weights for policy 1, policy_version 20462 (0.0008) -[2023-10-15 03:03:28,525][88298] Updated weights for policy 0, policy_version 20370 (0.0007) -[2023-10-15 03:03:28,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 41779200. Throughput: 0: 1737.9, 1: 1725.6. Samples: 10463298. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-15 03:03:28,534][87330] Avg episode reward: [(0, '22.490'), (1, '22.340')] -[2023-10-15 03:03:28,539][88300] Updated weights for policy 1, policy_version 20472 (0.0010) -[2023-10-15 03:03:28,897][88298] Updated weights for policy 0, policy_version 20380 (0.0007) -[2023-10-15 03:03:32,412][88300] Updated weights for policy 1, policy_version 20482 (0.0009) -[2023-10-15 03:03:32,708][88298] Updated weights for policy 0, policy_version 20390 (0.0007) -[2023-10-15 03:03:32,782][88300] Updated weights for policy 1, policy_version 20492 (0.0008) -[2023-10-15 03:03:33,082][88298] Updated weights for policy 0, policy_version 20400 (0.0007) -[2023-10-15 03:03:33,145][88300] Updated weights for policy 1, policy_version 20502 (0.0007) -[2023-10-15 03:03:33,453][88298] Updated weights for policy 0, policy_version 20410 (0.0007) -[2023-10-15 03:03:33,505][88300] Updated weights for policy 1, policy_version 20512 (0.0009) -[2023-10-15 03:03:33,534][87330] Fps is (10 sec: 16384.4, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 41877504. Throughput: 0: 1731.3, 1: 1738.6. Samples: 10473546. Policy #0 lag: (min: 18.0, avg: 18.0, max: 19.0) -[2023-10-15 03:03:33,534][87330] Avg episode reward: [(0, '22.480'), (1, '22.450')] -[2023-10-15 03:03:37,419][88298] Updated weights for policy 0, policy_version 20420 (0.0007) -[2023-10-15 03:03:37,491][88300] Updated weights for policy 1, policy_version 20522 (0.0007) -[2023-10-15 03:03:37,786][88298] Updated weights for policy 0, policy_version 20430 (0.0007) -[2023-10-15 03:03:37,860][88300] Updated weights for policy 1, policy_version 20532 (0.0007) -[2023-10-15 03:03:38,164][88298] Updated weights for policy 0, policy_version 20440 (0.0007) -[2023-10-15 03:03:38,215][88300] Updated weights for policy 1, policy_version 20542 (0.0007) -[2023-10-15 03:03:38,534][87330] Fps is (10 sec: 19660.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 41975808. Throughput: 0: 1742.8, 1: 1740.5. Samples: 10494762. Policy #0 lag: (min: 18.0, avg: 18.0, max: 19.0) -[2023-10-15 03:03:38,535][87330] Avg episode reward: [(0, '22.480'), (1, '22.450')] -[2023-10-15 03:03:42,098][88298] Updated weights for policy 0, policy_version 20450 (0.0010) -[2023-10-15 03:03:42,275][88300] Updated weights for policy 1, policy_version 20552 (0.0007) -[2023-10-15 03:03:42,472][88298] Updated weights for policy 0, policy_version 20460 (0.0008) -[2023-10-15 03:03:42,652][88300] Updated weights for policy 1, policy_version 20562 (0.0010) -[2023-10-15 03:03:42,840][88298] Updated weights for policy 0, policy_version 20470 (0.0009) -[2023-10-15 03:03:43,014][88300] Updated weights for policy 1, policy_version 20572 (0.0008) -[2023-10-15 03:03:43,204][88298] Updated weights for policy 0, policy_version 20480 (0.0007) -[2023-10-15 03:03:43,534][87330] Fps is (10 sec: 16383.2, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 42041344. Throughput: 0: 1726.5, 1: 1710.6. Samples: 10514080. Policy #0 lag: (min: 18.0, avg: 18.0, max: 19.0) -[2023-10-15 03:03:43,535][87330] Avg episode reward: [(0, '22.680'), (1, '22.390')] -[2023-10-15 03:03:46,929][88300] Updated weights for policy 1, policy_version 20582 (0.0008) -[2023-10-15 03:03:47,215][88298] Updated weights for policy 0, policy_version 20490 (0.0009) -[2023-10-15 03:03:47,296][88300] Updated weights for policy 1, policy_version 20592 (0.0008) -[2023-10-15 03:03:47,597][88298] Updated weights for policy 0, policy_version 20500 (0.0007) -[2023-10-15 03:03:47,660][88300] Updated weights for policy 1, policy_version 20602 (0.0008) -[2023-10-15 03:03:47,967][88298] Updated weights for policy 0, policy_version 20510 (0.0008) -[2023-10-15 03:03:48,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 42106880. Throughput: 0: 1741.5, 1: 1740.1. Samples: 10525364. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) -[2023-10-15 03:03:48,535][87330] Avg episode reward: [(0, '22.760'), (1, '22.360')] -[2023-10-15 03:03:51,690][88300] Updated weights for policy 1, policy_version 20612 (0.0008) -[2023-10-15 03:03:51,899][88298] Updated weights for policy 0, policy_version 20520 (0.0007) -[2023-10-15 03:03:52,059][88300] Updated weights for policy 1, policy_version 20622 (0.0008) -[2023-10-15 03:03:52,260][88298] Updated weights for policy 0, policy_version 20530 (0.0007) -[2023-10-15 03:03:52,423][88300] Updated weights for policy 1, policy_version 20632 (0.0008) -[2023-10-15 03:03:52,632][88298] Updated weights for policy 0, policy_version 20540 (0.0007) -[2023-10-15 03:03:53,534][87330] Fps is (10 sec: 13107.6, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 42172416. Throughput: 0: 1741.0, 1: 1721.0. Samples: 10545838. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) -[2023-10-15 03:03:53,535][87330] Avg episode reward: [(0, '22.800'), (1, '22.490')] -[2023-10-15 03:03:56,308][88300] Updated weights for policy 1, policy_version 20642 (0.0007) -[2023-10-15 03:03:56,429][88298] Updated weights for policy 0, policy_version 20550 (0.0007) -[2023-10-15 03:03:56,679][88300] Updated weights for policy 1, policy_version 20652 (0.0007) -[2023-10-15 03:03:56,801][88298] Updated weights for policy 0, policy_version 20560 (0.0010) -[2023-10-15 03:03:57,039][88300] Updated weights for policy 1, policy_version 20662 (0.0008) -[2023-10-15 03:03:57,168][88298] Updated weights for policy 0, policy_version 20570 (0.0007) -[2023-10-15 03:03:57,413][88300] Updated weights for policy 1, policy_version 20672 (0.0009) -[2023-10-15 03:03:58,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 42237952. Throughput: 0: 1714.7, 1: 1707.9. Samples: 10565644. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) -[2023-10-15 03:03:58,534][87330] Avg episode reward: [(0, '22.600'), (1, '22.370')] -[2023-10-15 03:04:01,107][88298] Updated weights for policy 0, policy_version 20580 (0.0008) -[2023-10-15 03:04:01,360][88300] Updated weights for policy 1, policy_version 20682 (0.0009) -[2023-10-15 03:04:01,483][88298] Updated weights for policy 0, policy_version 20590 (0.0008) -[2023-10-15 03:04:01,728][88300] Updated weights for policy 1, policy_version 20692 (0.0008) -[2023-10-15 03:04:01,848][88298] Updated weights for policy 0, policy_version 20600 (0.0007) -[2023-10-15 03:04:02,084][88300] Updated weights for policy 1, policy_version 20702 (0.0010) -[2023-10-15 03:04:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 42303488. Throughput: 0: 1752.2, 1: 1730.2. Samples: 10577614. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) -[2023-10-15 03:04:03,535][87330] Avg episode reward: [(0, '22.570'), (1, '22.350')] -[2023-10-15 03:04:05,626][88298] Updated weights for policy 0, policy_version 20610 (0.0008) -[2023-10-15 03:04:05,995][88300] Updated weights for policy 1, policy_version 20712 (0.0009) -[2023-10-15 03:04:06,002][88298] Updated weights for policy 0, policy_version 20620 (0.0009) -[2023-10-15 03:04:06,361][88300] Updated weights for policy 1, policy_version 20722 (0.0007) -[2023-10-15 03:04:06,380][88298] Updated weights for policy 0, policy_version 20630 (0.0009) -[2023-10-15 03:04:06,727][88300] Updated weights for policy 1, policy_version 20732 (0.0008) -[2023-10-15 03:04:06,745][88298] Updated weights for policy 0, policy_version 20640 (0.0010) -[2023-10-15 03:04:08,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 42369024. Throughput: 0: 1720.8, 1: 1702.6. Samples: 10596584. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-15 03:04:08,534][87330] Avg episode reward: [(0, '22.570'), (1, '22.360')] -[2023-10-15 03:04:10,673][88300] Updated weights for policy 1, policy_version 20742 (0.0007) -[2023-10-15 03:04:10,718][88298] Updated weights for policy 0, policy_version 20650 (0.0007) -[2023-10-15 03:04:11,042][88300] Updated weights for policy 1, policy_version 20752 (0.0009) -[2023-10-15 03:04:11,088][88298] Updated weights for policy 0, policy_version 20660 (0.0008) -[2023-10-15 03:04:11,416][88300] Updated weights for policy 1, policy_version 20762 (0.0009) -[2023-10-15 03:04:11,460][88298] Updated weights for policy 0, policy_version 20670 (0.0010) -[2023-10-15 03:04:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 42434560. Throughput: 0: 1718.5, 1: 1722.5. Samples: 10618144. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-15 03:04:13,535][87330] Avg episode reward: [(0, '22.510'), (1, '22.370')] -[2023-10-15 03:04:15,212][88300] Updated weights for policy 1, policy_version 20772 (0.0008) -[2023-10-15 03:04:15,451][88298] Updated weights for policy 0, policy_version 20680 (0.0008) -[2023-10-15 03:04:15,571][88300] Updated weights for policy 1, policy_version 20782 (0.0009) -[2023-10-15 03:04:15,819][88298] Updated weights for policy 0, policy_version 20690 (0.0007) -[2023-10-15 03:04:15,947][88300] Updated weights for policy 1, policy_version 20792 (0.0008) -[2023-10-15 03:04:16,196][88298] Updated weights for policy 0, policy_version 20700 (0.0007) -[2023-10-15 03:04:18,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 42500096. Throughput: 0: 1728.7, 1: 1713.1. Samples: 10628424. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-15 03:04:18,535][87330] Avg episode reward: [(0, '22.510'), (1, '22.490')] -[2023-10-15 03:04:19,834][88300] Updated weights for policy 1, policy_version 20802 (0.0010) -[2023-10-15 03:04:20,055][88298] Updated weights for policy 0, policy_version 20710 (0.0008) -[2023-10-15 03:04:20,199][88300] Updated weights for policy 1, policy_version 20812 (0.0007) -[2023-10-15 03:04:20,417][88298] Updated weights for policy 0, policy_version 20720 (0.0007) -[2023-10-15 03:04:20,571][88300] Updated weights for policy 1, policy_version 20822 (0.0009) -[2023-10-15 03:04:20,795][88298] Updated weights for policy 0, policy_version 20730 (0.0008) -[2023-10-15 03:04:20,930][88300] Updated weights for policy 1, policy_version 20832 (0.0008) -[2023-10-15 03:04:23,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 42565632. Throughput: 0: 1715.3, 1: 1717.6. Samples: 10649238. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-15 03:04:23,534][87330] Avg episode reward: [(0, '22.370'), (1, '22.550')] -[2023-10-15 03:04:24,713][88298] Updated weights for policy 0, policy_version 20740 (0.0008) -[2023-10-15 03:04:25,038][88300] Updated weights for policy 1, policy_version 20842 (0.0007) -[2023-10-15 03:04:25,084][88298] Updated weights for policy 0, policy_version 20750 (0.0007) -[2023-10-15 03:04:25,411][88300] Updated weights for policy 1, policy_version 20852 (0.0008) -[2023-10-15 03:04:25,456][88298] Updated weights for policy 0, policy_version 20760 (0.0007) -[2023-10-15 03:04:25,769][88300] Updated weights for policy 1, policy_version 20862 (0.0007) -[2023-10-15 03:04:28,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 42631168. Throughput: 0: 1731.4, 1: 1750.7. Samples: 10670776. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) -[2023-10-15 03:04:28,534][87330] Avg episode reward: [(0, '22.430'), (1, '22.600')] -[2023-10-15 03:04:29,272][88298] Updated weights for policy 0, policy_version 20770 (0.0007) -[2023-10-15 03:04:29,652][88298] Updated weights for policy 0, policy_version 20780 (0.0008) -[2023-10-15 03:04:29,689][88300] Updated weights for policy 1, policy_version 20872 (0.0007) -[2023-10-15 03:04:30,028][88298] Updated weights for policy 0, policy_version 20790 (0.0008) -[2023-10-15 03:04:30,071][88300] Updated weights for policy 1, policy_version 20882 (0.0008) -[2023-10-15 03:04:30,401][88298] Updated weights for policy 0, policy_version 20800 (0.0008) -[2023-10-15 03:04:30,446][88300] Updated weights for policy 1, policy_version 20892 (0.0009) -[2023-10-15 03:04:33,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 42696704. Throughput: 0: 1718.5, 1: 1719.3. Samples: 10680066. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) -[2023-10-15 03:04:33,534][87330] Avg episode reward: [(0, '22.390'), (1, '22.570')] -[2023-10-15 03:04:34,342][88298] Updated weights for policy 0, policy_version 20810 (0.0007) -[2023-10-15 03:04:34,445][88300] Updated weights for policy 1, policy_version 20902 (0.0009) -[2023-10-15 03:04:34,704][88298] Updated weights for policy 0, policy_version 20820 (0.0008) -[2023-10-15 03:04:34,814][88300] Updated weights for policy 1, policy_version 20912 (0.0009) -[2023-10-15 03:04:35,072][88298] Updated weights for policy 0, policy_version 20830 (0.0009) -[2023-10-15 03:04:35,177][88300] Updated weights for policy 1, policy_version 20922 (0.0008) -[2023-10-15 03:04:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 13773.7). Total num frames: 42762240. Throughput: 0: 1720.2, 1: 1738.9. Samples: 10701496. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) -[2023-10-15 03:04:38,534][87330] Avg episode reward: [(0, '22.350'), (1, '22.560')] -[2023-10-15 03:04:39,015][88300] Updated weights for policy 1, policy_version 20932 (0.0008) -[2023-10-15 03:04:39,041][88298] Updated weights for policy 0, policy_version 20840 (0.0008) -[2023-10-15 03:04:39,388][88300] Updated weights for policy 1, policy_version 20942 (0.0007) -[2023-10-15 03:04:39,396][88298] Updated weights for policy 0, policy_version 20850 (0.0008) -[2023-10-15 03:04:39,749][88300] Updated weights for policy 1, policy_version 20952 (0.0008) -[2023-10-15 03:04:39,763][88298] Updated weights for policy 0, policy_version 20860 (0.0008) -[2023-10-15 03:04:43,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13107.3, 300 sec: 13773.7). Total num frames: 42827776. Throughput: 0: 1748.3, 1: 1751.1. Samples: 10723116. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) -[2023-10-15 03:04:43,535][87330] Avg episode reward: [(0, '22.400'), (1, '22.200')] -[2023-10-15 03:04:43,674][88298] Updated weights for policy 0, policy_version 20870 (0.0009) -[2023-10-15 03:04:43,819][88300] Updated weights for policy 1, policy_version 20962 (0.0008) -[2023-10-15 03:04:44,041][88298] Updated weights for policy 0, policy_version 20880 (0.0010) -[2023-10-15 03:04:44,184][88300] Updated weights for policy 1, policy_version 20972 (0.0010) -[2023-10-15 03:04:44,408][88298] Updated weights for policy 0, policy_version 20890 (0.0007) -[2023-10-15 03:04:44,549][88300] Updated weights for policy 1, policy_version 20982 (0.0008) -[2023-10-15 03:04:44,922][88300] Updated weights for policy 1, policy_version 20992 (0.0010) -[2023-10-15 03:04:48,444][88298] Updated weights for policy 0, policy_version 20900 (0.0008) -[2023-10-15 03:04:48,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 42893312. Throughput: 0: 1711.1, 1: 1732.4. Samples: 10732572. Policy #0 lag: (min: 3.0, avg: 7.5, max: 35.0) -[2023-10-15 03:04:48,535][87330] Avg episode reward: [(0, '22.420'), (1, '22.200')] -[2023-10-15 03:04:48,693][88300] Updated weights for policy 1, policy_version 21002 (0.0008) -[2023-10-15 03:04:48,831][88298] Updated weights for policy 0, policy_version 20910 (0.0007) -[2023-10-15 03:04:49,065][88300] Updated weights for policy 1, policy_version 21012 (0.0008) -[2023-10-15 03:04:49,205][88298] Updated weights for policy 0, policy_version 20920 (0.0008) -[2023-10-15 03:04:49,430][88300] Updated weights for policy 1, policy_version 21022 (0.0008) -[2023-10-15 03:04:53,051][88298] Updated weights for policy 0, policy_version 20930 (0.0009) -[2023-10-15 03:04:53,422][88298] Updated weights for policy 0, policy_version 20940 (0.0007) -[2023-10-15 03:04:53,439][88300] Updated weights for policy 1, policy_version 21032 (0.0008) -[2023-10-15 03:04:53,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 42958848. Throughput: 0: 1740.0, 1: 1755.5. Samples: 10753882. Policy #0 lag: (min: 3.0, avg: 7.5, max: 35.0) -[2023-10-15 03:04:53,534][87330] Avg episode reward: [(0, '22.540'), (1, '22.190')] -[2023-10-15 03:04:53,793][88298] Updated weights for policy 0, policy_version 20950 (0.0008) -[2023-10-15 03:04:53,820][88300] Updated weights for policy 1, policy_version 21042 (0.0008) -[2023-10-15 03:04:54,158][88298] Updated weights for policy 0, policy_version 20960 (0.0007) -[2023-10-15 03:04:54,180][88300] Updated weights for policy 1, policy_version 21052 (0.0007) -[2023-10-15 03:04:58,111][88300] Updated weights for policy 1, policy_version 21062 (0.0009) -[2023-10-15 03:04:58,131][88298] Updated weights for policy 0, policy_version 20970 (0.0009) -[2023-10-15 03:04:58,485][88300] Updated weights for policy 1, policy_version 21072 (0.0009) -[2023-10-15 03:04:58,493][88298] Updated weights for policy 0, policy_version 20980 (0.0007) -[2023-10-15 03:04:58,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 43024384. Throughput: 0: 1745.5, 1: 1738.6. Samples: 10774928. Policy #0 lag: (min: 3.0, avg: 7.5, max: 35.0) -[2023-10-15 03:04:58,534][87330] Avg episode reward: [(0, '22.560'), (1, '22.140')] -[2023-10-15 03:04:58,844][88300] Updated weights for policy 1, policy_version 21082 (0.0008) -[2023-10-15 03:04:58,867][88298] Updated weights for policy 0, policy_version 20990 (0.0007) -[2023-10-15 03:04:58,937][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000020992_21495808.pth... -[2023-10-15 03:04:58,970][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000019360_19824640.pth -[2023-10-15 03:04:59,065][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000021088_21594112.pth... -[2023-10-15 03:04:59,104][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000019456_19922944.pth -[2023-10-15 03:05:02,760][88300] Updated weights for policy 1, policy_version 21092 (0.0008) -[2023-10-15 03:05:02,885][88298] Updated weights for policy 0, policy_version 21000 (0.0008) -[2023-10-15 03:05:03,125][88300] Updated weights for policy 1, policy_version 21102 (0.0008) -[2023-10-15 03:05:03,251][88298] Updated weights for policy 0, policy_version 21010 (0.0008) -[2023-10-15 03:05:03,491][88300] Updated weights for policy 1, policy_version 21112 (0.0008) -[2023-10-15 03:05:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 43089920. Throughput: 0: 1734.0, 1: 1742.5. Samples: 10784868. Policy #0 lag: (min: 1.0, avg: 9.2, max: 33.0) -[2023-10-15 03:05:03,534][87330] Avg episode reward: [(0, '22.590'), (1, '22.200')] -[2023-10-15 03:05:03,627][88298] Updated weights for policy 0, policy_version 21020 (0.0008) -[2023-10-15 03:05:07,445][88300] Updated weights for policy 1, policy_version 21122 (0.0008) -[2023-10-15 03:05:07,694][88298] Updated weights for policy 0, policy_version 21030 (0.0009) -[2023-10-15 03:05:07,818][88300] Updated weights for policy 1, policy_version 21132 (0.0009) -[2023-10-15 03:05:08,060][88298] Updated weights for policy 0, policy_version 21040 (0.0008) -[2023-10-15 03:05:08,179][88300] Updated weights for policy 1, policy_version 21142 (0.0008) -[2023-10-15 03:05:08,427][88298] Updated weights for policy 0, policy_version 21050 (0.0007) -[2023-10-15 03:05:08,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 43155456. Throughput: 0: 1742.0, 1: 1737.7. Samples: 10805826. Policy #0 lag: (min: 1.0, avg: 9.2, max: 33.0) -[2023-10-15 03:05:08,535][87330] Avg episode reward: [(0, '22.720'), (1, '22.170')] -[2023-10-15 03:05:08,547][88300] Updated weights for policy 1, policy_version 21152 (0.0008) -[2023-10-15 03:05:12,417][88298] Updated weights for policy 0, policy_version 21060 (0.0007) -[2023-10-15 03:05:12,491][88300] Updated weights for policy 1, policy_version 21162 (0.0007) -[2023-10-15 03:05:12,795][88298] Updated weights for policy 0, policy_version 21070 (0.0007) -[2023-10-15 03:05:12,860][88300] Updated weights for policy 1, policy_version 21172 (0.0007) -[2023-10-15 03:05:13,164][88298] Updated weights for policy 0, policy_version 21080 (0.0008) -[2023-10-15 03:05:13,228][88300] Updated weights for policy 1, policy_version 21182 (0.0008) -[2023-10-15 03:05:13,534][87330] Fps is (10 sec: 19660.7, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 43286528. Throughput: 0: 1729.6, 1: 1712.9. Samples: 10825688. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-15 03:05:13,534][87330] Avg episode reward: [(0, '22.680'), (1, '22.170')] -[2023-10-15 03:05:17,057][88300] Updated weights for policy 1, policy_version 21192 (0.0009) -[2023-10-15 03:05:17,190][88298] Updated weights for policy 0, policy_version 21090 (0.0009) -[2023-10-15 03:05:17,424][88300] Updated weights for policy 1, policy_version 21202 (0.0008) -[2023-10-15 03:05:17,557][88298] Updated weights for policy 0, policy_version 21100 (0.0009) -[2023-10-15 03:05:17,782][88300] Updated weights for policy 1, policy_version 21212 (0.0007) -[2023-10-15 03:05:17,923][88298] Updated weights for policy 0, policy_version 21110 (0.0007) -[2023-10-15 03:05:18,290][88298] Updated weights for policy 0, policy_version 21120 (0.0007) -[2023-10-15 03:05:18,534][87330] Fps is (10 sec: 19660.8, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 43352064. Throughput: 0: 1740.6, 1: 1741.3. Samples: 10836752. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-15 03:05:18,534][87330] Avg episode reward: [(0, '22.690'), (1, '22.430')] -[2023-10-15 03:05:21,721][88300] Updated weights for policy 1, policy_version 21222 (0.0007) -[2023-10-15 03:05:22,085][88300] Updated weights for policy 1, policy_version 21232 (0.0008) -[2023-10-15 03:05:22,216][88298] Updated weights for policy 0, policy_version 21130 (0.0008) -[2023-10-15 03:05:22,456][88300] Updated weights for policy 1, policy_version 21242 (0.0007) -[2023-10-15 03:05:22,591][88298] Updated weights for policy 0, policy_version 21140 (0.0008) -[2023-10-15 03:05:22,962][88298] Updated weights for policy 0, policy_version 21150 (0.0008) -[2023-10-15 03:05:23,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 43417600. Throughput: 0: 1739.5, 1: 1723.4. Samples: 10857328. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-15 03:05:23,535][87330] Avg episode reward: [(0, '22.680'), (1, '22.410')] -[2023-10-15 03:05:26,240][88300] Updated weights for policy 1, policy_version 21252 (0.0007) -[2023-10-15 03:05:26,607][88300] Updated weights for policy 1, policy_version 21262 (0.0009) -[2023-10-15 03:05:26,933][88298] Updated weights for policy 0, policy_version 21160 (0.0007) -[2023-10-15 03:05:26,977][88300] Updated weights for policy 1, policy_version 21272 (0.0008) -[2023-10-15 03:05:27,303][88298] Updated weights for policy 0, policy_version 21170 (0.0008) -[2023-10-15 03:05:27,676][88298] Updated weights for policy 0, policy_version 21180 (0.0010) -[2023-10-15 03:05:28,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 43483136. Throughput: 0: 1707.8, 1: 1713.1. Samples: 10877056. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-15 03:05:28,534][87330] Avg episode reward: [(0, '22.690'), (1, '22.360')] -[2023-10-15 03:05:30,778][88300] Updated weights for policy 1, policy_version 21282 (0.0008) -[2023-10-15 03:05:31,154][88300] Updated weights for policy 1, policy_version 21292 (0.0008) -[2023-10-15 03:05:31,336][88298] Updated weights for policy 0, policy_version 21190 (0.0008) -[2023-10-15 03:05:31,517][88300] Updated weights for policy 1, policy_version 21302 (0.0008) -[2023-10-15 03:05:31,701][88298] Updated weights for policy 0, policy_version 21200 (0.0008) -[2023-10-15 03:05:31,884][88300] Updated weights for policy 1, policy_version 21312 (0.0008) -[2023-10-15 03:05:32,070][88298] Updated weights for policy 0, policy_version 21210 (0.0008) -[2023-10-15 03:05:33,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 43548672. Throughput: 0: 1737.6, 1: 1727.2. Samples: 10888488. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-15 03:05:33,534][87330] Avg episode reward: [(0, '22.690'), (1, '22.280')] -[2023-10-15 03:05:35,882][88300] Updated weights for policy 1, policy_version 21322 (0.0010) -[2023-10-15 03:05:36,045][88298] Updated weights for policy 0, policy_version 21220 (0.0009) -[2023-10-15 03:05:36,240][88300] Updated weights for policy 1, policy_version 21332 (0.0007) -[2023-10-15 03:05:36,417][88298] Updated weights for policy 0, policy_version 21230 (0.0007) -[2023-10-15 03:05:36,613][88300] Updated weights for policy 1, policy_version 21342 (0.0008) -[2023-10-15 03:05:36,776][88298] Updated weights for policy 0, policy_version 21240 (0.0007) -[2023-10-15 03:05:38,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 43614208. Throughput: 0: 1712.0, 1: 1709.8. Samples: 10907864. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-15 03:05:38,535][87330] Avg episode reward: [(0, '22.690'), (1, '22.060')] -[2023-10-15 03:05:40,314][88300] Updated weights for policy 1, policy_version 21352 (0.0007) -[2023-10-15 03:05:40,680][88298] Updated weights for policy 0, policy_version 21250 (0.0009) -[2023-10-15 03:05:40,692][88300] Updated weights for policy 1, policy_version 21362 (0.0007) -[2023-10-15 03:05:41,055][88300] Updated weights for policy 1, policy_version 21372 (0.0009) -[2023-10-15 03:05:41,074][88298] Updated weights for policy 0, policy_version 21260 (0.0008) -[2023-10-15 03:05:41,448][88298] Updated weights for policy 0, policy_version 21270 (0.0009) -[2023-10-15 03:05:41,818][88298] Updated weights for policy 0, policy_version 21280 (0.0007) -[2023-10-15 03:05:43,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 43679744. Throughput: 0: 1698.7, 1: 1732.5. Samples: 10929328. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-15 03:05:43,534][87330] Avg episode reward: [(0, '22.810'), (1, '22.020')] -[2023-10-15 03:05:44,928][88300] Updated weights for policy 1, policy_version 21382 (0.0010) -[2023-10-15 03:05:45,290][88300] Updated weights for policy 1, policy_version 21392 (0.0010) -[2023-10-15 03:05:45,667][88300] Updated weights for policy 1, policy_version 21402 (0.0008) -[2023-10-15 03:05:45,884][88298] Updated weights for policy 0, policy_version 21290 (0.0009) -[2023-10-15 03:05:46,262][88298] Updated weights for policy 0, policy_version 21300 (0.0009) -[2023-10-15 03:05:46,630][88298] Updated weights for policy 0, policy_version 21310 (0.0010) -[2023-10-15 03:05:48,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 43745280. Throughput: 0: 1718.7, 1: 1722.9. Samples: 10939738. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-15 03:05:48,535][87330] Avg episode reward: [(0, '22.840'), (1, '22.120')] -[2023-10-15 03:05:48,536][87905] Saving new best policy, reward=22.840! -[2023-10-15 03:05:49,711][88300] Updated weights for policy 1, policy_version 21412 (0.0009) -[2023-10-15 03:05:50,080][88300] Updated weights for policy 1, policy_version 21422 (0.0011) -[2023-10-15 03:05:50,449][88300] Updated weights for policy 1, policy_version 21432 (0.0008) -[2023-10-15 03:05:50,510][88298] Updated weights for policy 0, policy_version 21320 (0.0008) -[2023-10-15 03:05:50,884][88298] Updated weights for policy 0, policy_version 21330 (0.0007) -[2023-10-15 03:05:51,255][88298] Updated weights for policy 0, policy_version 21340 (0.0008) -[2023-10-15 03:05:53,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 43810816. Throughput: 0: 1700.5, 1: 1730.3. Samples: 10960214. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-15 03:05:53,534][87330] Avg episode reward: [(0, '22.850'), (1, '22.160')] -[2023-10-15 03:05:53,535][87905] Saving new best policy, reward=22.850! -[2023-10-15 03:05:54,433][88300] Updated weights for policy 1, policy_version 21442 (0.0008) -[2023-10-15 03:05:54,809][88300] Updated weights for policy 1, policy_version 21452 (0.0009) -[2023-10-15 03:05:55,174][88300] Updated weights for policy 1, policy_version 21462 (0.0010) -[2023-10-15 03:05:55,262][88298] Updated weights for policy 0, policy_version 21350 (0.0008) -[2023-10-15 03:05:55,542][88300] Updated weights for policy 1, policy_version 21472 (0.0008) -[2023-10-15 03:05:55,635][88298] Updated weights for policy 0, policy_version 21360 (0.0008) -[2023-10-15 03:05:56,007][88298] Updated weights for policy 0, policy_version 21370 (0.0007) -[2023-10-15 03:05:58,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 43876352. Throughput: 0: 1712.6, 1: 1753.6. Samples: 10981668. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-15 03:05:58,535][87330] Avg episode reward: [(0, '22.850'), (1, '21.900')] -[2023-10-15 03:05:59,595][88300] Updated weights for policy 1, policy_version 21482 (0.0007) -[2023-10-15 03:05:59,930][88298] Updated weights for policy 0, policy_version 21380 (0.0008) -[2023-10-15 03:05:59,967][88300] Updated weights for policy 1, policy_version 21492 (0.0010) -[2023-10-15 03:06:00,300][88298] Updated weights for policy 0, policy_version 21390 (0.0008) -[2023-10-15 03:06:00,331][88300] Updated weights for policy 1, policy_version 21502 (0.0009) -[2023-10-15 03:06:00,669][88298] Updated weights for policy 0, policy_version 21400 (0.0009) -[2023-10-15 03:06:03,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 43941888. Throughput: 0: 1703.4, 1: 1734.1. Samples: 10991440. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-15 03:06:03,535][87330] Avg episode reward: [(0, '22.850'), (1, '21.740')] -[2023-10-15 03:06:04,159][88300] Updated weights for policy 1, policy_version 21512 (0.0007) -[2023-10-15 03:06:04,534][88300] Updated weights for policy 1, policy_version 21522 (0.0008) -[2023-10-15 03:06:04,555][88298] Updated weights for policy 0, policy_version 21410 (0.0009) -[2023-10-15 03:06:04,905][88300] Updated weights for policy 1, policy_version 21532 (0.0008) -[2023-10-15 03:06:04,929][88298] Updated weights for policy 0, policy_version 21420 (0.0009) -[2023-10-15 03:06:05,303][88298] Updated weights for policy 0, policy_version 21430 (0.0009) -[2023-10-15 03:06:05,675][88298] Updated weights for policy 0, policy_version 21440 (0.0008) -[2023-10-15 03:06:08,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 44007424. Throughput: 0: 1695.7, 1: 1753.7. Samples: 11012550. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-15 03:06:08,534][87330] Avg episode reward: [(0, '22.840'), (1, '21.960')] -[2023-10-15 03:06:08,696][88300] Updated weights for policy 1, policy_version 21542 (0.0009) -[2023-10-15 03:06:09,063][88300] Updated weights for policy 1, policy_version 21552 (0.0010) -[2023-10-15 03:06:09,437][88300] Updated weights for policy 1, policy_version 21562 (0.0007) -[2023-10-15 03:06:09,485][88298] Updated weights for policy 0, policy_version 21450 (0.0009) -[2023-10-15 03:06:09,858][88298] Updated weights for policy 0, policy_version 21460 (0.0008) -[2023-10-15 03:06:10,220][88298] Updated weights for policy 0, policy_version 21470 (0.0007) -[2023-10-15 03:06:13,273][88300] Updated weights for policy 1, policy_version 21572 (0.0008) -[2023-10-15 03:06:13,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 44072960. Throughput: 0: 1727.6, 1: 1764.8. Samples: 11034214. Policy #0 lag: (min: 17.0, avg: 24.7, max: 49.0) -[2023-10-15 03:06:13,534][87330] Avg episode reward: [(0, '22.810'), (1, '21.960')] -[2023-10-15 03:06:13,635][88300] Updated weights for policy 1, policy_version 21582 (0.0007) -[2023-10-15 03:06:14,008][88300] Updated weights for policy 1, policy_version 21592 (0.0007) -[2023-10-15 03:06:14,166][88298] Updated weights for policy 0, policy_version 21480 (0.0009) -[2023-10-15 03:06:14,533][88298] Updated weights for policy 0, policy_version 21490 (0.0010) -[2023-10-15 03:06:14,903][88298] Updated weights for policy 0, policy_version 21500 (0.0011) -[2023-10-15 03:06:17,808][88300] Updated weights for policy 1, policy_version 21602 (0.0008) -[2023-10-15 03:06:18,170][88300] Updated weights for policy 1, policy_version 21612 (0.0009) -[2023-10-15 03:06:18,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 44138496. Throughput: 0: 1701.6, 1: 1749.5. Samples: 11043788. Policy #0 lag: (min: 17.0, avg: 24.7, max: 49.0) -[2023-10-15 03:06:18,535][87330] Avg episode reward: [(0, '22.790'), (1, '21.950')] -[2023-10-15 03:06:18,544][88300] Updated weights for policy 1, policy_version 21622 (0.0009) -[2023-10-15 03:06:18,880][88298] Updated weights for policy 0, policy_version 21510 (0.0009) -[2023-10-15 03:06:18,912][88300] Updated weights for policy 1, policy_version 21632 (0.0008) -[2023-10-15 03:06:19,259][88298] Updated weights for policy 0, policy_version 21520 (0.0007) -[2023-10-15 03:06:19,632][88298] Updated weights for policy 0, policy_version 21530 (0.0008) -[2023-10-15 03:06:22,864][88300] Updated weights for policy 1, policy_version 21642 (0.0007) -[2023-10-15 03:06:23,228][88300] Updated weights for policy 1, policy_version 21652 (0.0009) -[2023-10-15 03:06:23,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 44204032. Throughput: 0: 1729.3, 1: 1767.5. Samples: 11065220. Policy #0 lag: (min: 17.0, avg: 24.7, max: 49.0) -[2023-10-15 03:06:23,534][87330] Avg episode reward: [(0, '22.810'), (1, '21.830')] -[2023-10-15 03:06:23,598][88300] Updated weights for policy 1, policy_version 21662 (0.0009) -[2023-10-15 03:06:23,610][88298] Updated weights for policy 0, policy_version 21540 (0.0010) -[2023-10-15 03:06:23,982][88298] Updated weights for policy 0, policy_version 21550 (0.0009) -[2023-10-15 03:06:24,355][88298] Updated weights for policy 0, policy_version 21560 (0.0008) -[2023-10-15 03:06:27,604][88300] Updated weights for policy 1, policy_version 21672 (0.0008) -[2023-10-15 03:06:27,981][88300] Updated weights for policy 1, policy_version 21682 (0.0008) -[2023-10-15 03:06:28,210][88298] Updated weights for policy 0, policy_version 21570 (0.0009) -[2023-10-15 03:06:28,342][88300] Updated weights for policy 1, policy_version 21692 (0.0009) -[2023-10-15 03:06:28,534][87330] Fps is (10 sec: 16384.4, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 44302336. Throughput: 0: 1744.0, 1: 1737.5. Samples: 11085994. Policy #0 lag: (min: 17.0, avg: 24.7, max: 49.0) -[2023-10-15 03:06:28,534][87330] Avg episode reward: [(0, '22.800'), (1, '22.010')] -[2023-10-15 03:06:28,613][88298] Updated weights for policy 0, policy_version 21580 (0.0008) -[2023-10-15 03:06:28,985][88298] Updated weights for policy 0, policy_version 21590 (0.0008) -[2023-10-15 03:06:29,358][88298] Updated weights for policy 0, policy_version 21600 (0.0011) -[2023-10-15 03:06:32,254][88300] Updated weights for policy 1, policy_version 21702 (0.0008) -[2023-10-15 03:06:32,616][88300] Updated weights for policy 1, policy_version 21712 (0.0007) -[2023-10-15 03:06:32,987][88300] Updated weights for policy 1, policy_version 21722 (0.0009) -[2023-10-15 03:06:33,281][88298] Updated weights for policy 0, policy_version 21610 (0.0007) -[2023-10-15 03:06:33,534][87330] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 44367872. Throughput: 0: 1717.7, 1: 1760.7. Samples: 11096264. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-10-15 03:06:33,534][87330] Avg episode reward: [(0, '22.800'), (1, '22.240')] -[2023-10-15 03:06:33,639][88298] Updated weights for policy 0, policy_version 21620 (0.0007) -[2023-10-15 03:06:34,015][88298] Updated weights for policy 0, policy_version 21630 (0.0008) -[2023-10-15 03:06:36,938][88300] Updated weights for policy 1, policy_version 21732 (0.0007) -[2023-10-15 03:06:37,299][88300] Updated weights for policy 1, policy_version 21742 (0.0009) -[2023-10-15 03:06:37,666][88300] Updated weights for policy 1, policy_version 21752 (0.0008) -[2023-10-15 03:06:37,872][88298] Updated weights for policy 0, policy_version 21640 (0.0008) -[2023-10-15 03:06:38,245][88298] Updated weights for policy 0, policy_version 21650 (0.0009) -[2023-10-15 03:06:38,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 44433408. Throughput: 0: 1749.1, 1: 1747.7. Samples: 11117572. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-10-15 03:06:38,535][87330] Avg episode reward: [(0, '22.770'), (1, '22.440')] -[2023-10-15 03:06:38,630][88298] Updated weights for policy 0, policy_version 21660 (0.0010) -[2023-10-15 03:06:41,503][88300] Updated weights for policy 1, policy_version 21762 (0.0008) -[2023-10-15 03:06:41,872][88300] Updated weights for policy 1, policy_version 21772 (0.0010) -[2023-10-15 03:06:42,246][88300] Updated weights for policy 1, policy_version 21782 (0.0007) -[2023-10-15 03:06:42,543][88298] Updated weights for policy 0, policy_version 21670 (0.0009) -[2023-10-15 03:06:42,615][88300] Updated weights for policy 1, policy_version 21792 (0.0007) -[2023-10-15 03:06:42,915][88298] Updated weights for policy 0, policy_version 21680 (0.0009) -[2023-10-15 03:06:43,297][88298] Updated weights for policy 0, policy_version 21690 (0.0008) -[2023-10-15 03:06:43,534][87330] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 44531712. Throughput: 0: 1735.6, 1: 1729.7. Samples: 11137606. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-10-15 03:06:43,535][87330] Avg episode reward: [(0, '22.800'), (1, '22.460')] -[2023-10-15 03:06:46,511][88300] Updated weights for policy 1, policy_version 21802 (0.0008) -[2023-10-15 03:06:46,869][88300] Updated weights for policy 1, policy_version 21812 (0.0010) -[2023-10-15 03:06:47,241][88300] Updated weights for policy 1, policy_version 21822 (0.0009) -[2023-10-15 03:06:47,308][88298] Updated weights for policy 0, policy_version 21700 (0.0009) -[2023-10-15 03:06:47,673][88298] Updated weights for policy 0, policy_version 21710 (0.0009) -[2023-10-15 03:06:48,046][88298] Updated weights for policy 0, policy_version 21720 (0.0008) -[2023-10-15 03:06:48,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 44597248. Throughput: 0: 1741.1, 1: 1751.6. Samples: 11148612. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-15 03:06:48,534][87330] Avg episode reward: [(0, '22.750'), (1, '22.460')] -[2023-10-15 03:06:51,055][88300] Updated weights for policy 1, policy_version 21832 (0.0009) -[2023-10-15 03:06:51,431][88300] Updated weights for policy 1, policy_version 21842 (0.0009) -[2023-10-15 03:06:51,795][88300] Updated weights for policy 1, policy_version 21852 (0.0007) -[2023-10-15 03:06:51,918][88298] Updated weights for policy 0, policy_version 21730 (0.0009) -[2023-10-15 03:06:52,297][88298] Updated weights for policy 0, policy_version 21740 (0.0007) -[2023-10-15 03:06:52,663][88298] Updated weights for policy 0, policy_version 21750 (0.0009) -[2023-10-15 03:06:53,037][88298] Updated weights for policy 0, policy_version 21760 (0.0009) -[2023-10-15 03:06:53,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 44662784. Throughput: 0: 1754.6, 1: 1726.0. Samples: 11169176. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-15 03:06:53,535][87330] Avg episode reward: [(0, '22.750'), (1, '22.420')] -[2023-10-15 03:06:55,655][88300] Updated weights for policy 1, policy_version 21862 (0.0009) -[2023-10-15 03:06:56,021][88300] Updated weights for policy 1, policy_version 21872 (0.0010) -[2023-10-15 03:06:56,385][88300] Updated weights for policy 1, policy_version 21882 (0.0009) -[2023-10-15 03:06:57,071][88298] Updated weights for policy 0, policy_version 21770 (0.0008) -[2023-10-15 03:06:57,444][88298] Updated weights for policy 0, policy_version 21780 (0.0007) -[2023-10-15 03:06:57,820][88298] Updated weights for policy 0, policy_version 21790 (0.0009) -[2023-10-15 03:06:58,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 44728320. Throughput: 0: 1727.4, 1: 1724.1. Samples: 11189532. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-15 03:06:58,535][87330] Avg episode reward: [(0, '22.720'), (1, '22.240')] -[2023-10-15 03:06:58,547][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000021792_22315008.pth... -[2023-10-15 03:06:58,548][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000021888_22413312.pth... -[2023-10-15 03:06:58,584][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000020256_20742144.pth -[2023-10-15 03:06:58,586][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000020160_20643840.pth -[2023-10-15 03:07:00,369][88300] Updated weights for policy 1, policy_version 21892 (0.0010) -[2023-10-15 03:07:00,736][88300] Updated weights for policy 1, policy_version 21902 (0.0010) -[2023-10-15 03:07:01,098][88300] Updated weights for policy 1, policy_version 21912 (0.0009) -[2023-10-15 03:07:01,729][88298] Updated weights for policy 0, policy_version 21800 (0.0007) -[2023-10-15 03:07:02,103][88298] Updated weights for policy 0, policy_version 21810 (0.0008) -[2023-10-15 03:07:02,479][88298] Updated weights for policy 0, policy_version 21820 (0.0008) -[2023-10-15 03:07:03,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 44793856. Throughput: 0: 1756.2, 1: 1725.5. Samples: 11200464. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-15 03:07:03,535][87330] Avg episode reward: [(0, '22.550'), (1, '22.300')] -[2023-10-15 03:07:05,044][88300] Updated weights for policy 1, policy_version 21922 (0.0008) -[2023-10-15 03:07:05,421][88300] Updated weights for policy 1, policy_version 21932 (0.0008) -[2023-10-15 03:07:05,791][88300] Updated weights for policy 1, policy_version 21942 (0.0010) -[2023-10-15 03:07:06,150][88300] Updated weights for policy 1, policy_version 21952 (0.0010) -[2023-10-15 03:07:06,220][88298] Updated weights for policy 0, policy_version 21830 (0.0008) -[2023-10-15 03:07:06,609][88298] Updated weights for policy 0, policy_version 21840 (0.0008) -[2023-10-15 03:07:06,986][88298] Updated weights for policy 0, policy_version 21850 (0.0008) -[2023-10-15 03:07:08,534][87330] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 44859392. Throughput: 0: 1736.6, 1: 1724.8. Samples: 11220982. Policy #0 lag: (min: 13.0, avg: 16.2, max: 45.0) -[2023-10-15 03:07:08,534][87330] Avg episode reward: [(0, '22.530'), (1, '22.290')] -[2023-10-15 03:07:10,034][88300] Updated weights for policy 1, policy_version 21962 (0.0010) -[2023-10-15 03:07:10,408][88300] Updated weights for policy 1, policy_version 21972 (0.0010) -[2023-10-15 03:07:10,782][88300] Updated weights for policy 1, policy_version 21982 (0.0010) -[2023-10-15 03:07:10,892][88298] Updated weights for policy 0, policy_version 21860 (0.0008) -[2023-10-15 03:07:11,263][88298] Updated weights for policy 0, policy_version 21870 (0.0008) -[2023-10-15 03:07:11,634][88298] Updated weights for policy 0, policy_version 21880 (0.0008) -[2023-10-15 03:07:13,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 44924928. Throughput: 0: 1714.4, 1: 1742.6. Samples: 11241562. Policy #0 lag: (min: 13.0, avg: 16.2, max: 45.0) -[2023-10-15 03:07:13,535][87330] Avg episode reward: [(0, '22.570'), (1, '22.310')] -[2023-10-15 03:07:14,859][88300] Updated weights for policy 1, policy_version 21992 (0.0008) -[2023-10-15 03:07:15,238][88300] Updated weights for policy 1, policy_version 22002 (0.0008) -[2023-10-15 03:07:15,522][88298] Updated weights for policy 0, policy_version 21890 (0.0007) -[2023-10-15 03:07:15,615][88300] Updated weights for policy 1, policy_version 22012 (0.0008) -[2023-10-15 03:07:15,933][88298] Updated weights for policy 0, policy_version 21900 (0.0008) -[2023-10-15 03:07:16,294][88298] Updated weights for policy 0, policy_version 21910 (0.0008) -[2023-10-15 03:07:16,670][88298] Updated weights for policy 0, policy_version 21920 (0.0007) -[2023-10-15 03:07:18,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 44990464. Throughput: 0: 1738.3, 1: 1718.8. Samples: 11251838. Policy #0 lag: (min: 13.0, avg: 16.2, max: 45.0) -[2023-10-15 03:07:18,535][87330] Avg episode reward: [(0, '22.580'), (1, '22.350')] -[2023-10-15 03:07:19,528][88300] Updated weights for policy 1, policy_version 22022 (0.0008) -[2023-10-15 03:07:19,903][88300] Updated weights for policy 1, policy_version 22032 (0.0008) -[2023-10-15 03:07:20,277][88300] Updated weights for policy 1, policy_version 22042 (0.0007) -[2023-10-15 03:07:20,577][88298] Updated weights for policy 0, policy_version 21930 (0.0008) -[2023-10-15 03:07:20,950][88298] Updated weights for policy 0, policy_version 21940 (0.0007) -[2023-10-15 03:07:21,317][88298] Updated weights for policy 0, policy_version 21950 (0.0009) -[2023-10-15 03:07:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 45056000. Throughput: 0: 1703.6, 1: 1736.0. Samples: 11272354. Policy #0 lag: (min: 13.0, avg: 16.2, max: 45.0) -[2023-10-15 03:07:23,535][87330] Avg episode reward: [(0, '22.560'), (1, '22.370')] -[2023-10-15 03:07:24,131][88300] Updated weights for policy 1, policy_version 22052 (0.0008) -[2023-10-15 03:07:24,498][88300] Updated weights for policy 1, policy_version 22062 (0.0007) -[2023-10-15 03:07:24,854][88300] Updated weights for policy 1, policy_version 22072 (0.0010) -[2023-10-15 03:07:25,216][88298] Updated weights for policy 0, policy_version 21960 (0.0007) -[2023-10-15 03:07:25,585][88298] Updated weights for policy 0, policy_version 21970 (0.0008) -[2023-10-15 03:07:25,961][88298] Updated weights for policy 0, policy_version 21980 (0.0011) -[2023-10-15 03:07:28,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 45121536. Throughput: 0: 1724.1, 1: 1751.1. Samples: 11293988. Policy #0 lag: (min: 18.0, avg: 24.4, max: 50.0) -[2023-10-15 03:07:28,535][87330] Avg episode reward: [(0, '22.580'), (1, '22.650')] -[2023-10-15 03:07:28,547][88033] Saving new best policy, reward=22.650! -[2023-10-15 03:07:28,819][88300] Updated weights for policy 1, policy_version 22082 (0.0008) -[2023-10-15 03:07:29,191][88300] Updated weights for policy 1, policy_version 22092 (0.0008) -[2023-10-15 03:07:29,562][88300] Updated weights for policy 1, policy_version 22102 (0.0008) -[2023-10-15 03:07:29,737][88298] Updated weights for policy 0, policy_version 21990 (0.0007) -[2023-10-15 03:07:29,922][88300] Updated weights for policy 1, policy_version 22112 (0.0009) -[2023-10-15 03:07:30,113][88298] Updated weights for policy 0, policy_version 22000 (0.0008) -[2023-10-15 03:07:30,473][88298] Updated weights for policy 0, policy_version 22010 (0.0008) -[2023-10-15 03:07:33,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 45187072. Throughput: 0: 1716.7, 1: 1726.5. Samples: 11303556. Policy #0 lag: (min: 18.0, avg: 24.4, max: 50.0) -[2023-10-15 03:07:33,534][87330] Avg episode reward: [(0, '22.640'), (1, '22.480')] -[2023-10-15 03:07:33,720][88300] Updated weights for policy 1, policy_version 22122 (0.0010) -[2023-10-15 03:07:34,093][88300] Updated weights for policy 1, policy_version 22132 (0.0008) -[2023-10-15 03:07:34,462][88300] Updated weights for policy 1, policy_version 22142 (0.0007) -[2023-10-15 03:07:34,665][88298] Updated weights for policy 0, policy_version 22020 (0.0009) -[2023-10-15 03:07:35,041][88298] Updated weights for policy 0, policy_version 22030 (0.0008) -[2023-10-15 03:07:35,402][88298] Updated weights for policy 0, policy_version 22040 (0.0009) -[2023-10-15 03:07:38,190][88300] Updated weights for policy 1, policy_version 22152 (0.0008) -[2023-10-15 03:07:38,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 45252608. Throughput: 0: 1709.5, 1: 1756.4. Samples: 11325142. Policy #0 lag: (min: 18.0, avg: 24.4, max: 50.0) -[2023-10-15 03:07:38,534][87330] Avg episode reward: [(0, '22.700'), (1, '22.250')] -[2023-10-15 03:07:38,555][88300] Updated weights for policy 1, policy_version 22162 (0.0009) -[2023-10-15 03:07:38,924][88300] Updated weights for policy 1, policy_version 22172 (0.0008) -[2023-10-15 03:07:39,530][88298] Updated weights for policy 0, policy_version 22050 (0.0009) -[2023-10-15 03:07:39,903][88298] Updated weights for policy 0, policy_version 22060 (0.0008) -[2023-10-15 03:07:40,279][88298] Updated weights for policy 0, policy_version 22070 (0.0008) -[2023-10-15 03:07:40,645][88298] Updated weights for policy 0, policy_version 22080 (0.0008) -[2023-10-15 03:07:42,896][88300] Updated weights for policy 1, policy_version 22182 (0.0007) -[2023-10-15 03:07:43,262][88300] Updated weights for policy 1, policy_version 22192 (0.0008) -[2023-10-15 03:07:43,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 45318144. Throughput: 0: 1734.0, 1: 1747.2. Samples: 11346182. Policy #0 lag: (min: 18.0, avg: 24.4, max: 50.0) -[2023-10-15 03:07:43,534][87330] Avg episode reward: [(0, '22.740'), (1, '22.100')] -[2023-10-15 03:07:43,643][88300] Updated weights for policy 1, policy_version 22202 (0.0008) -[2023-10-15 03:07:44,567][88298] Updated weights for policy 0, policy_version 22090 (0.0009) -[2023-10-15 03:07:44,938][88298] Updated weights for policy 0, policy_version 22100 (0.0008) -[2023-10-15 03:07:45,321][88298] Updated weights for policy 0, policy_version 22110 (0.0009) -[2023-10-15 03:07:47,611][88300] Updated weights for policy 1, policy_version 22212 (0.0008) -[2023-10-15 03:07:47,985][88300] Updated weights for policy 1, policy_version 22222 (0.0007) -[2023-10-15 03:07:48,355][88300] Updated weights for policy 1, policy_version 22232 (0.0008) -[2023-10-15 03:07:48,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 45383680. Throughput: 0: 1704.1, 1: 1756.7. Samples: 11356202. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-10-15 03:07:48,534][87330] Avg episode reward: [(0, '22.720'), (1, '22.070')] -[2023-10-15 03:07:49,253][88298] Updated weights for policy 0, policy_version 22120 (0.0008) -[2023-10-15 03:07:49,620][88298] Updated weights for policy 0, policy_version 22130 (0.0008) -[2023-10-15 03:07:50,001][88298] Updated weights for policy 0, policy_version 22140 (0.0009) -[2023-10-15 03:07:52,218][88300] Updated weights for policy 1, policy_version 22242 (0.0010) -[2023-10-15 03:07:52,582][88300] Updated weights for policy 1, policy_version 22252 (0.0009) -[2023-10-15 03:07:52,961][88300] Updated weights for policy 1, policy_version 22262 (0.0009) -[2023-10-15 03:07:53,322][88300] Updated weights for policy 1, policy_version 22272 (0.0009) -[2023-10-15 03:07:53,534][87330] Fps is (10 sec: 16384.3, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 45481984. Throughput: 0: 1720.2, 1: 1759.2. Samples: 11377556. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-10-15 03:07:53,534][87330] Avg episode reward: [(0, '22.760'), (1, '22.120')] -[2023-10-15 03:07:53,899][88298] Updated weights for policy 0, policy_version 22150 (0.0009) -[2023-10-15 03:07:54,263][88298] Updated weights for policy 0, policy_version 22160 (0.0008) -[2023-10-15 03:07:54,629][88298] Updated weights for policy 0, policy_version 22170 (0.0011) -[2023-10-15 03:07:56,950][88300] Updated weights for policy 1, policy_version 22282 (0.0010) -[2023-10-15 03:07:57,317][88300] Updated weights for policy 1, policy_version 22292 (0.0010) -[2023-10-15 03:07:57,686][88300] Updated weights for policy 1, policy_version 22302 (0.0007) -[2023-10-15 03:07:58,406][88298] Updated weights for policy 0, policy_version 22180 (0.0009) -[2023-10-15 03:07:58,534][87330] Fps is (10 sec: 16383.7, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 45547520. Throughput: 0: 1742.0, 1: 1740.8. Samples: 11398292. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-10-15 03:07:58,534][87330] Avg episode reward: [(0, '22.760'), (1, '22.100')] -[2023-10-15 03:07:58,776][88298] Updated weights for policy 0, policy_version 22190 (0.0009) -[2023-10-15 03:07:59,146][88298] Updated weights for policy 0, policy_version 22200 (0.0008) -[2023-10-15 03:08:01,660][88300] Updated weights for policy 1, policy_version 22312 (0.0009) -[2023-10-15 03:08:02,032][88300] Updated weights for policy 1, policy_version 22322 (0.0008) -[2023-10-15 03:08:02,397][88300] Updated weights for policy 1, policy_version 22332 (0.0009) -[2023-10-15 03:08:02,924][88298] Updated weights for policy 0, policy_version 22210 (0.0009) -[2023-10-15 03:08:03,325][88298] Updated weights for policy 0, policy_version 22220 (0.0010) -[2023-10-15 03:08:03,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 45613056. Throughput: 0: 1724.0, 1: 1775.9. Samples: 11409334. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-10-15 03:08:03,535][87330] Avg episode reward: [(0, '22.680'), (1, '22.180')] -[2023-10-15 03:08:03,694][88298] Updated weights for policy 0, policy_version 22230 (0.0011) -[2023-10-15 03:08:04,063][88298] Updated weights for policy 0, policy_version 22240 (0.0009) -[2023-10-15 03:08:06,234][88300] Updated weights for policy 1, policy_version 22342 (0.0008) -[2023-10-15 03:08:06,591][88300] Updated weights for policy 1, policy_version 22352 (0.0010) -[2023-10-15 03:08:06,969][88300] Updated weights for policy 1, policy_version 22362 (0.0008) -[2023-10-15 03:08:07,834][88298] Updated weights for policy 0, policy_version 22250 (0.0008) -[2023-10-15 03:08:08,196][88298] Updated weights for policy 0, policy_version 22260 (0.0007) -[2023-10-15 03:08:08,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 45678592. Throughput: 0: 1754.5, 1: 1739.5. Samples: 11429586. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-10-15 03:08:08,535][87330] Avg episode reward: [(0, '22.660'), (1, '22.260')] -[2023-10-15 03:08:08,565][88298] Updated weights for policy 0, policy_version 22270 (0.0009) -[2023-10-15 03:08:10,934][88300] Updated weights for policy 1, policy_version 22372 (0.0007) -[2023-10-15 03:08:11,294][88300] Updated weights for policy 1, policy_version 22382 (0.0007) -[2023-10-15 03:08:11,664][88300] Updated weights for policy 1, policy_version 22392 (0.0009) -[2023-10-15 03:08:12,575][88298] Updated weights for policy 0, policy_version 22280 (0.0008) -[2023-10-15 03:08:12,947][88298] Updated weights for policy 0, policy_version 22290 (0.0007) -[2023-10-15 03:08:13,318][88298] Updated weights for policy 0, policy_version 22300 (0.0007) -[2023-10-15 03:08:13,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 45776896. Throughput: 0: 1735.3, 1: 1741.5. Samples: 11450444. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-10-15 03:08:13,535][87330] Avg episode reward: [(0, '22.590'), (1, '22.570')] -[2023-10-15 03:08:15,421][88300] Updated weights for policy 1, policy_version 22402 (0.0011) -[2023-10-15 03:08:15,796][88300] Updated weights for policy 1, policy_version 22412 (0.0009) -[2023-10-15 03:08:16,161][88300] Updated weights for policy 1, policy_version 22422 (0.0008) -[2023-10-15 03:08:16,524][88300] Updated weights for policy 1, policy_version 22432 (0.0008) -[2023-10-15 03:08:17,288][88298] Updated weights for policy 0, policy_version 22310 (0.0007) -[2023-10-15 03:08:17,662][88298] Updated weights for policy 0, policy_version 22320 (0.0008) -[2023-10-15 03:08:18,035][88298] Updated weights for policy 0, policy_version 22330 (0.0007) -[2023-10-15 03:08:18,534][87330] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 45842432. Throughput: 0: 1747.5, 1: 1747.5. Samples: 11460830. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-10-15 03:08:18,534][87330] Avg episode reward: [(0, '22.530'), (1, '22.570')] -[2023-10-15 03:08:20,183][88300] Updated weights for policy 1, policy_version 22442 (0.0008) -[2023-10-15 03:08:20,547][88300] Updated weights for policy 1, policy_version 22452 (0.0010) -[2023-10-15 03:08:20,912][88300] Updated weights for policy 1, policy_version 22462 (0.0009) -[2023-10-15 03:08:21,924][88298] Updated weights for policy 0, policy_version 22340 (0.0007) -[2023-10-15 03:08:22,296][88298] Updated weights for policy 0, policy_version 22350 (0.0009) -[2023-10-15 03:08:22,659][88298] Updated weights for policy 0, policy_version 22360 (0.0008) -[2023-10-15 03:08:23,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 45907968. Throughput: 0: 1752.7, 1: 1738.7. Samples: 11482258. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:08:23,535][87330] Avg episode reward: [(0, '22.510'), (1, '22.540')] -[2023-10-15 03:08:24,716][88300] Updated weights for policy 1, policy_version 22472 (0.0011) -[2023-10-15 03:08:25,068][88300] Updated weights for policy 1, policy_version 22482 (0.0010) -[2023-10-15 03:08:25,440][88300] Updated weights for policy 1, policy_version 22492 (0.0008) -[2023-10-15 03:08:26,433][88298] Updated weights for policy 0, policy_version 22370 (0.0007) -[2023-10-15 03:08:26,805][88298] Updated weights for policy 0, policy_version 22380 (0.0008) -[2023-10-15 03:08:27,171][88298] Updated weights for policy 0, policy_version 22390 (0.0007) -[2023-10-15 03:08:27,539][88298] Updated weights for policy 0, policy_version 22400 (0.0007) -[2023-10-15 03:08:28,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 45973504. Throughput: 0: 1728.1, 1: 1753.0. Samples: 11502832. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:08:28,535][87330] Avg episode reward: [(0, '22.380'), (1, '22.420')] -[2023-10-15 03:08:29,462][88300] Updated weights for policy 1, policy_version 22502 (0.0007) -[2023-10-15 03:08:29,826][88300] Updated weights for policy 1, policy_version 22512 (0.0008) -[2023-10-15 03:08:30,198][88300] Updated weights for policy 1, policy_version 22522 (0.0008) -[2023-10-15 03:08:31,531][88298] Updated weights for policy 0, policy_version 22410 (0.0009) -[2023-10-15 03:08:31,913][88298] Updated weights for policy 0, policy_version 22420 (0.0009) -[2023-10-15 03:08:32,284][88298] Updated weights for policy 0, policy_version 22430 (0.0009) -[2023-10-15 03:08:33,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 46039040. Throughput: 0: 1758.5, 1: 1739.2. Samples: 11513598. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:08:33,534][87330] Avg episode reward: [(0, '22.550'), (1, '22.200')] -[2023-10-15 03:08:34,099][88300] Updated weights for policy 1, policy_version 22532 (0.0008) -[2023-10-15 03:08:34,463][88300] Updated weights for policy 1, policy_version 22542 (0.0007) -[2023-10-15 03:08:34,834][88300] Updated weights for policy 1, policy_version 22552 (0.0010) -[2023-10-15 03:08:36,084][88298] Updated weights for policy 0, policy_version 22440 (0.0008) -[2023-10-15 03:08:36,455][88298] Updated weights for policy 0, policy_version 22450 (0.0010) -[2023-10-15 03:08:36,836][88298] Updated weights for policy 0, policy_version 22460 (0.0011) -[2023-10-15 03:08:38,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 46104576. Throughput: 0: 1737.5, 1: 1741.3. Samples: 11534102. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:08:38,535][87330] Avg episode reward: [(0, '22.740'), (1, '22.190')] -[2023-10-15 03:08:38,885][88300] Updated weights for policy 1, policy_version 22562 (0.0009) -[2023-10-15 03:08:39,254][88300] Updated weights for policy 1, policy_version 22572 (0.0007) -[2023-10-15 03:08:39,617][88300] Updated weights for policy 1, policy_version 22582 (0.0007) -[2023-10-15 03:08:39,988][88300] Updated weights for policy 1, policy_version 22592 (0.0010) -[2023-10-15 03:08:40,887][88298] Updated weights for policy 0, policy_version 22470 (0.0011) -[2023-10-15 03:08:41,255][88298] Updated weights for policy 0, policy_version 22480 (0.0008) -[2023-10-15 03:08:41,631][88298] Updated weights for policy 0, policy_version 22490 (0.0009) -[2023-10-15 03:08:43,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 46170112. Throughput: 0: 1725.6, 1: 1758.5. Samples: 11555076. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-15 03:08:43,535][87330] Avg episode reward: [(0, '22.760'), (1, '22.180')] -[2023-10-15 03:08:43,952][88300] Updated weights for policy 1, policy_version 22602 (0.0007) -[2023-10-15 03:08:44,318][88300] Updated weights for policy 1, policy_version 22612 (0.0008) -[2023-10-15 03:08:44,696][88300] Updated weights for policy 1, policy_version 22622 (0.0009) -[2023-10-15 03:08:45,554][88298] Updated weights for policy 0, policy_version 22500 (0.0009) -[2023-10-15 03:08:45,922][88298] Updated weights for policy 0, policy_version 22510 (0.0007) -[2023-10-15 03:08:46,292][88298] Updated weights for policy 0, policy_version 22520 (0.0007) -[2023-10-15 03:08:48,524][88300] Updated weights for policy 1, policy_version 22632 (0.0008) -[2023-10-15 03:08:48,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 46235648. Throughput: 0: 1744.9, 1: 1727.1. Samples: 11565570. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-15 03:08:48,534][87330] Avg episode reward: [(0, '22.780'), (1, '22.190')] -[2023-10-15 03:08:48,896][88300] Updated weights for policy 1, policy_version 22642 (0.0009) -[2023-10-15 03:08:49,256][88300] Updated weights for policy 1, policy_version 22652 (0.0009) -[2023-10-15 03:08:50,093][88298] Updated weights for policy 0, policy_version 22530 (0.0008) -[2023-10-15 03:08:50,513][88298] Updated weights for policy 0, policy_version 22540 (0.0008) -[2023-10-15 03:08:50,886][88298] Updated weights for policy 0, policy_version 22550 (0.0007) -[2023-10-15 03:08:51,261][88298] Updated weights for policy 0, policy_version 22560 (0.0010) -[2023-10-15 03:08:53,240][88300] Updated weights for policy 1, policy_version 22662 (0.0008) -[2023-10-15 03:08:53,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 46301184. Throughput: 0: 1718.5, 1: 1753.8. Samples: 11585840. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-15 03:08:53,534][87330] Avg episode reward: [(0, '22.830'), (1, '22.190')] -[2023-10-15 03:08:53,615][88300] Updated weights for policy 1, policy_version 22672 (0.0010) -[2023-10-15 03:08:53,977][88300] Updated weights for policy 1, policy_version 22682 (0.0008) -[2023-10-15 03:08:55,109][88298] Updated weights for policy 0, policy_version 22570 (0.0007) -[2023-10-15 03:08:55,474][88298] Updated weights for policy 0, policy_version 22580 (0.0007) -[2023-10-15 03:08:55,842][88298] Updated weights for policy 0, policy_version 22590 (0.0008) -[2023-10-15 03:08:57,772][88300] Updated weights for policy 1, policy_version 22692 (0.0009) -[2023-10-15 03:08:58,142][88300] Updated weights for policy 1, policy_version 22702 (0.0009) -[2023-10-15 03:08:58,504][88300] Updated weights for policy 1, policy_version 22712 (0.0008) -[2023-10-15 03:08:58,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 46366720. Throughput: 0: 1732.5, 1: 1742.2. Samples: 11606804. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-15 03:08:58,534][87330] Avg episode reward: [(0, '22.950'), (1, '22.320')] -[2023-10-15 03:08:58,544][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000022592_23134208.pth... -[2023-10-15 03:08:58,580][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000020992_21495808.pth -[2023-10-15 03:08:58,584][87905] Saving new best policy, reward=22.950! -[2023-10-15 03:08:58,796][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000022720_23265280.pth... -[2023-10-15 03:08:58,835][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000021088_21594112.pth -[2023-10-15 03:08:59,691][88298] Updated weights for policy 0, policy_version 22600 (0.0009) -[2023-10-15 03:09:00,055][88298] Updated weights for policy 0, policy_version 22610 (0.0009) -[2023-10-15 03:09:00,420][88298] Updated weights for policy 0, policy_version 22620 (0.0010) -[2023-10-15 03:09:02,483][88300] Updated weights for policy 1, policy_version 22722 (0.0008) -[2023-10-15 03:09:02,852][88300] Updated weights for policy 1, policy_version 22732 (0.0010) -[2023-10-15 03:09:03,226][88300] Updated weights for policy 1, policy_version 22742 (0.0009) -[2023-10-15 03:09:03,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 46432256. Throughput: 0: 1721.0, 1: 1749.2. Samples: 11616988. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:09:03,534][87330] Avg episode reward: [(0, '22.940'), (1, '22.420')] -[2023-10-15 03:09:03,592][88300] Updated weights for policy 1, policy_version 22752 (0.0010) -[2023-10-15 03:09:04,323][88298] Updated weights for policy 0, policy_version 22630 (0.0010) -[2023-10-15 03:09:04,696][88298] Updated weights for policy 0, policy_version 22640 (0.0011) -[2023-10-15 03:09:05,080][88298] Updated weights for policy 0, policy_version 22650 (0.0010) -[2023-10-15 03:09:07,424][88300] Updated weights for policy 1, policy_version 22762 (0.0011) -[2023-10-15 03:09:07,790][88300] Updated weights for policy 1, policy_version 22772 (0.0010) -[2023-10-15 03:09:08,168][88300] Updated weights for policy 1, policy_version 22782 (0.0011) -[2023-10-15 03:09:08,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 46530560. Throughput: 0: 1721.1, 1: 1751.2. Samples: 11638508. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:09:08,535][87330] Avg episode reward: [(0, '22.870'), (1, '22.390')] -[2023-10-15 03:09:09,056][88298] Updated weights for policy 0, policy_version 22660 (0.0007) -[2023-10-15 03:09:09,420][88298] Updated weights for policy 0, policy_version 22670 (0.0009) -[2023-10-15 03:09:09,791][88298] Updated weights for policy 0, policy_version 22680 (0.0008) -[2023-10-15 03:09:12,203][88300] Updated weights for policy 1, policy_version 22792 (0.0007) -[2023-10-15 03:09:12,571][88300] Updated weights for policy 1, policy_version 22802 (0.0007) -[2023-10-15 03:09:12,944][88300] Updated weights for policy 1, policy_version 22812 (0.0007) -[2023-10-15 03:09:13,534][87330] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 46596096. Throughput: 0: 1748.9, 1: 1719.3. Samples: 11658902. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:09:13,534][87330] Avg episode reward: [(0, '22.810'), (1, '22.460')] -[2023-10-15 03:09:13,748][88298] Updated weights for policy 0, policy_version 22690 (0.0008) -[2023-10-15 03:09:14,108][88298] Updated weights for policy 0, policy_version 22700 (0.0007) -[2023-10-15 03:09:14,488][88298] Updated weights for policy 0, policy_version 22710 (0.0008) -[2023-10-15 03:09:14,853][88298] Updated weights for policy 0, policy_version 22720 (0.0010) -[2023-10-15 03:09:16,609][88300] Updated weights for policy 1, policy_version 22822 (0.0008) -[2023-10-15 03:09:16,971][88300] Updated weights for policy 1, policy_version 22832 (0.0009) -[2023-10-15 03:09:17,336][88300] Updated weights for policy 1, policy_version 22842 (0.0007) -[2023-10-15 03:09:18,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 46661632. Throughput: 0: 1718.6, 1: 1753.3. Samples: 11669834. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:09:18,534][87330] Avg episode reward: [(0, '22.790'), (1, '22.120')] -[2023-10-15 03:09:18,870][88298] Updated weights for policy 0, policy_version 22730 (0.0008) -[2023-10-15 03:09:19,250][88298] Updated weights for policy 0, policy_version 22740 (0.0009) -[2023-10-15 03:09:19,628][88298] Updated weights for policy 0, policy_version 22750 (0.0009) -[2023-10-15 03:09:21,310][88300] Updated weights for policy 1, policy_version 22852 (0.0008) -[2023-10-15 03:09:21,669][88300] Updated weights for policy 1, policy_version 22862 (0.0011) -[2023-10-15 03:09:22,041][88300] Updated weights for policy 1, policy_version 22872 (0.0009) -[2023-10-15 03:09:23,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 46727168. Throughput: 0: 1739.4, 1: 1724.8. Samples: 11689994. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:09:23,535][87330] Avg episode reward: [(0, '22.810'), (1, '22.100')] -[2023-10-15 03:09:23,535][88298] Updated weights for policy 0, policy_version 22760 (0.0008) -[2023-10-15 03:09:23,917][88298] Updated weights for policy 0, policy_version 22770 (0.0009) -[2023-10-15 03:09:24,275][88298] Updated weights for policy 0, policy_version 22780 (0.0010) -[2023-10-15 03:09:25,894][88300] Updated weights for policy 1, policy_version 22882 (0.0010) -[2023-10-15 03:09:26,269][88300] Updated weights for policy 1, policy_version 22892 (0.0011) -[2023-10-15 03:09:26,636][88300] Updated weights for policy 1, policy_version 22902 (0.0011) -[2023-10-15 03:09:26,999][88300] Updated weights for policy 1, policy_version 22912 (0.0011) -[2023-10-15 03:09:28,168][88298] Updated weights for policy 0, policy_version 22790 (0.0010) -[2023-10-15 03:09:28,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 46792704. Throughput: 0: 1746.8, 1: 1732.2. Samples: 11711634. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:09:28,534][87330] Avg episode reward: [(0, '22.770'), (1, '22.140')] -[2023-10-15 03:09:28,538][88298] Updated weights for policy 0, policy_version 22800 (0.0010) -[2023-10-15 03:09:28,904][88298] Updated weights for policy 0, policy_version 22810 (0.0010) -[2023-10-15 03:09:30,857][88300] Updated weights for policy 1, policy_version 22922 (0.0008) -[2023-10-15 03:09:31,226][88300] Updated weights for policy 1, policy_version 22932 (0.0008) -[2023-10-15 03:09:31,595][88300] Updated weights for policy 1, policy_version 22942 (0.0010) -[2023-10-15 03:09:32,882][88298] Updated weights for policy 0, policy_version 22820 (0.0008) -[2023-10-15 03:09:33,255][88298] Updated weights for policy 0, policy_version 22830 (0.0008) -[2023-10-15 03:09:33,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 46858240. Throughput: 0: 1721.0, 1: 1741.9. Samples: 11721402. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:09:33,534][87330] Avg episode reward: [(0, '22.760'), (1, '22.110')] -[2023-10-15 03:09:33,634][88298] Updated weights for policy 0, policy_version 22840 (0.0009) -[2023-10-15 03:09:35,559][88300] Updated weights for policy 1, policy_version 22952 (0.0007) -[2023-10-15 03:09:35,922][88300] Updated weights for policy 1, policy_version 22962 (0.0007) -[2023-10-15 03:09:36,297][88300] Updated weights for policy 1, policy_version 22972 (0.0007) -[2023-10-15 03:09:37,658][88298] Updated weights for policy 0, policy_version 22850 (0.0009) -[2023-10-15 03:09:38,066][88298] Updated weights for policy 0, policy_version 22860 (0.0009) -[2023-10-15 03:09:38,446][88298] Updated weights for policy 0, policy_version 22870 (0.0008) -[2023-10-15 03:09:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 46923776. Throughput: 0: 1740.6, 1: 1732.9. Samples: 11742150. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:09:38,534][87330] Avg episode reward: [(0, '22.720'), (1, '22.330')] -[2023-10-15 03:09:38,815][88298] Updated weights for policy 0, policy_version 22880 (0.0010) -[2023-10-15 03:09:40,081][88300] Updated weights for policy 1, policy_version 22982 (0.0008) -[2023-10-15 03:09:40,458][88300] Updated weights for policy 1, policy_version 22992 (0.0008) -[2023-10-15 03:09:40,825][88300] Updated weights for policy 1, policy_version 23002 (0.0009) -[2023-10-15 03:09:42,746][88298] Updated weights for policy 0, policy_version 22890 (0.0007) -[2023-10-15 03:09:43,109][88298] Updated weights for policy 0, policy_version 22900 (0.0010) -[2023-10-15 03:09:43,487][88298] Updated weights for policy 0, policy_version 22910 (0.0009) -[2023-10-15 03:09:43,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 46989312. Throughput: 0: 1724.8, 1: 1749.7. Samples: 11763158. Policy #0 lag: (min: 16.0, avg: 39.7, max: 48.0) -[2023-10-15 03:09:43,535][87330] Avg episode reward: [(0, '22.530'), (1, '22.200')] -[2023-10-15 03:09:44,855][88300] Updated weights for policy 1, policy_version 23012 (0.0009) -[2023-10-15 03:09:45,217][88300] Updated weights for policy 1, policy_version 23022 (0.0008) -[2023-10-15 03:09:45,595][88300] Updated weights for policy 1, policy_version 23032 (0.0008) -[2023-10-15 03:09:47,273][88298] Updated weights for policy 0, policy_version 22920 (0.0009) -[2023-10-15 03:09:47,639][88298] Updated weights for policy 0, policy_version 22930 (0.0008) -[2023-10-15 03:09:48,010][88298] Updated weights for policy 0, policy_version 22940 (0.0009) -[2023-10-15 03:09:48,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 47087616. Throughput: 0: 1737.8, 1: 1733.2. Samples: 11773180. Policy #0 lag: (min: 16.0, avg: 39.7, max: 48.0) -[2023-10-15 03:09:48,534][87330] Avg episode reward: [(0, '22.410'), (1, '22.510')] -[2023-10-15 03:09:49,482][88300] Updated weights for policy 1, policy_version 23042 (0.0007) -[2023-10-15 03:09:49,856][88300] Updated weights for policy 1, policy_version 23052 (0.0009) -[2023-10-15 03:09:50,223][88300] Updated weights for policy 1, policy_version 23062 (0.0008) -[2023-10-15 03:09:50,581][88300] Updated weights for policy 1, policy_version 23072 (0.0009) -[2023-10-15 03:09:52,028][88298] Updated weights for policy 0, policy_version 22950 (0.0007) -[2023-10-15 03:09:52,404][88298] Updated weights for policy 0, policy_version 22960 (0.0007) -[2023-10-15 03:09:52,772][88298] Updated weights for policy 0, policy_version 22970 (0.0007) -[2023-10-15 03:09:53,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 47153152. Throughput: 0: 1734.5, 1: 1735.9. Samples: 11794676. Policy #0 lag: (min: 16.0, avg: 39.7, max: 48.0) -[2023-10-15 03:09:53,535][87330] Avg episode reward: [(0, '22.330'), (1, '22.510')] -[2023-10-15 03:09:54,403][88300] Updated weights for policy 1, policy_version 23082 (0.0008) -[2023-10-15 03:09:54,761][88300] Updated weights for policy 1, policy_version 23092 (0.0009) -[2023-10-15 03:09:55,130][88300] Updated weights for policy 1, policy_version 23102 (0.0009) -[2023-10-15 03:09:56,593][88298] Updated weights for policy 0, policy_version 22980 (0.0007) -[2023-10-15 03:09:56,954][88298] Updated weights for policy 0, policy_version 22990 (0.0007) -[2023-10-15 03:09:57,327][88298] Updated weights for policy 0, policy_version 23000 (0.0007) -[2023-10-15 03:09:58,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 47218688. Throughput: 0: 1703.2, 1: 1767.0. Samples: 11815060. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-15 03:09:58,534][87330] Avg episode reward: [(0, '22.320'), (1, '22.510')] -[2023-10-15 03:09:59,128][88300] Updated weights for policy 1, policy_version 23112 (0.0008) -[2023-10-15 03:09:59,495][88300] Updated weights for policy 1, policy_version 23122 (0.0008) -[2023-10-15 03:09:59,863][88300] Updated weights for policy 1, policy_version 23132 (0.0009) -[2023-10-15 03:10:01,271][88298] Updated weights for policy 0, policy_version 23010 (0.0009) -[2023-10-15 03:10:01,648][88298] Updated weights for policy 0, policy_version 23020 (0.0010) -[2023-10-15 03:10:02,012][88298] Updated weights for policy 0, policy_version 23030 (0.0010) -[2023-10-15 03:10:02,388][88298] Updated weights for policy 0, policy_version 23040 (0.0009) -[2023-10-15 03:10:03,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 47284224. Throughput: 0: 1734.5, 1: 1736.7. Samples: 11826036. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-15 03:10:03,535][87330] Avg episode reward: [(0, '22.320'), (1, '22.480')] -[2023-10-15 03:10:03,573][88300] Updated weights for policy 1, policy_version 23142 (0.0008) -[2023-10-15 03:10:03,936][88300] Updated weights for policy 1, policy_version 23152 (0.0008) -[2023-10-15 03:10:04,300][88300] Updated weights for policy 1, policy_version 23162 (0.0010) -[2023-10-15 03:10:06,224][88298] Updated weights for policy 0, policy_version 23050 (0.0007) -[2023-10-15 03:10:06,591][88298] Updated weights for policy 0, policy_version 23060 (0.0008) -[2023-10-15 03:10:06,971][88298] Updated weights for policy 0, policy_version 23070 (0.0009) -[2023-10-15 03:10:08,167][88300] Updated weights for policy 1, policy_version 23172 (0.0007) -[2023-10-15 03:10:08,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 47349760. Throughput: 0: 1716.9, 1: 1772.4. Samples: 11847010. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-15 03:10:08,534][87330] Avg episode reward: [(0, '22.180'), (1, '22.460')] -[2023-10-15 03:10:08,535][88300] Updated weights for policy 1, policy_version 23182 (0.0007) -[2023-10-15 03:10:08,914][88300] Updated weights for policy 1, policy_version 23192 (0.0009) -[2023-10-15 03:10:10,687][88298] Updated weights for policy 0, policy_version 23080 (0.0009) -[2023-10-15 03:10:11,058][88298] Updated weights for policy 0, policy_version 23090 (0.0008) -[2023-10-15 03:10:11,428][88298] Updated weights for policy 0, policy_version 23100 (0.0009) -[2023-10-15 03:10:12,817][88300] Updated weights for policy 1, policy_version 23202 (0.0009) -[2023-10-15 03:10:13,186][88300] Updated weights for policy 1, policy_version 23212 (0.0008) -[2023-10-15 03:10:13,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 47415296. Throughput: 0: 1710.2, 1: 1760.7. Samples: 11867824. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-15 03:10:13,535][87330] Avg episode reward: [(0, '22.120'), (1, '22.570')] -[2023-10-15 03:10:13,558][88300] Updated weights for policy 1, policy_version 23222 (0.0007) -[2023-10-15 03:10:13,916][88300] Updated weights for policy 1, policy_version 23232 (0.0007) -[2023-10-15 03:10:15,348][88298] Updated weights for policy 0, policy_version 23110 (0.0008) -[2023-10-15 03:10:15,713][88298] Updated weights for policy 0, policy_version 23120 (0.0008) -[2023-10-15 03:10:16,083][88298] Updated weights for policy 0, policy_version 23130 (0.0008) -[2023-10-15 03:10:17,708][88300] Updated weights for policy 1, policy_version 23242 (0.0008) -[2023-10-15 03:10:18,081][88300] Updated weights for policy 1, policy_version 23252 (0.0009) -[2023-10-15 03:10:18,445][88300] Updated weights for policy 1, policy_version 23262 (0.0008) -[2023-10-15 03:10:18,534][87330] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 47513600. Throughput: 0: 1728.7, 1: 1759.8. Samples: 11878386. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:10:18,535][87330] Avg episode reward: [(0, '22.370'), (1, '22.550')] -[2023-10-15 03:10:19,999][88298] Updated weights for policy 0, policy_version 23140 (0.0008) -[2023-10-15 03:10:20,374][88298] Updated weights for policy 0, policy_version 23150 (0.0009) -[2023-10-15 03:10:20,733][88298] Updated weights for policy 0, policy_version 23160 (0.0011) -[2023-10-15 03:10:22,207][88300] Updated weights for policy 1, policy_version 23272 (0.0009) -[2023-10-15 03:10:22,570][88300] Updated weights for policy 1, policy_version 23282 (0.0009) -[2023-10-15 03:10:22,942][88300] Updated weights for policy 1, policy_version 23292 (0.0008) -[2023-10-15 03:10:23,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 47579136. Throughput: 0: 1717.2, 1: 1768.3. Samples: 11898998. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:10:23,534][87330] Avg episode reward: [(0, '22.570'), (1, '22.600')] -[2023-10-15 03:10:24,679][88298] Updated weights for policy 0, policy_version 23170 (0.0008) -[2023-10-15 03:10:25,103][88298] Updated weights for policy 0, policy_version 23180 (0.0007) -[2023-10-15 03:10:25,479][88298] Updated weights for policy 0, policy_version 23190 (0.0008) -[2023-10-15 03:10:25,839][88298] Updated weights for policy 0, policy_version 23200 (0.0008) -[2023-10-15 03:10:27,009][88300] Updated weights for policy 1, policy_version 23302 (0.0009) -[2023-10-15 03:10:27,394][88300] Updated weights for policy 1, policy_version 23312 (0.0008) -[2023-10-15 03:10:27,773][88300] Updated weights for policy 1, policy_version 23322 (0.0010) -[2023-10-15 03:10:28,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 47644672. Throughput: 0: 1731.9, 1: 1738.9. Samples: 11919344. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:10:28,535][87330] Avg episode reward: [(0, '22.580'), (1, '22.570')] -[2023-10-15 03:10:29,722][88298] Updated weights for policy 0, policy_version 23210 (0.0007) -[2023-10-15 03:10:30,096][88298] Updated weights for policy 0, policy_version 23220 (0.0010) -[2023-10-15 03:10:30,466][88298] Updated weights for policy 0, policy_version 23230 (0.0008) -[2023-10-15 03:10:31,643][88300] Updated weights for policy 1, policy_version 23332 (0.0009) -[2023-10-15 03:10:32,014][88300] Updated weights for policy 1, policy_version 23342 (0.0007) -[2023-10-15 03:10:32,370][88300] Updated weights for policy 1, policy_version 23352 (0.0008) -[2023-10-15 03:10:33,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 47710208. Throughput: 0: 1717.9, 1: 1771.6. Samples: 11930208. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:10:33,534][87330] Avg episode reward: [(0, '22.570'), (1, '22.650')] -[2023-10-15 03:10:34,465][88298] Updated weights for policy 0, policy_version 23240 (0.0008) -[2023-10-15 03:10:34,837][88298] Updated weights for policy 0, policy_version 23250 (0.0008) -[2023-10-15 03:10:35,203][88298] Updated weights for policy 0, policy_version 23260 (0.0009) -[2023-10-15 03:10:36,135][88300] Updated weights for policy 1, policy_version 23362 (0.0008) -[2023-10-15 03:10:36,505][88300] Updated weights for policy 1, policy_version 23372 (0.0009) -[2023-10-15 03:10:36,875][88300] Updated weights for policy 1, policy_version 23382 (0.0008) -[2023-10-15 03:10:37,244][88300] Updated weights for policy 1, policy_version 23392 (0.0011) -[2023-10-15 03:10:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 47775744. Throughput: 0: 1721.0, 1: 1748.7. Samples: 11950812. Policy #0 lag: (min: 0.0, avg: 20.9, max: 32.0) -[2023-10-15 03:10:38,535][87330] Avg episode reward: [(0, '22.770'), (1, '22.650')] -[2023-10-15 03:10:39,096][88298] Updated weights for policy 0, policy_version 23270 (0.0010) -[2023-10-15 03:10:39,464][88298] Updated weights for policy 0, policy_version 23280 (0.0009) -[2023-10-15 03:10:39,831][88298] Updated weights for policy 0, policy_version 23290 (0.0010) -[2023-10-15 03:10:41,090][88300] Updated weights for policy 1, policy_version 23402 (0.0010) -[2023-10-15 03:10:41,455][88300] Updated weights for policy 1, policy_version 23412 (0.0010) -[2023-10-15 03:10:41,828][88300] Updated weights for policy 1, policy_version 23422 (0.0012) -[2023-10-15 03:10:43,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 47841280. Throughput: 0: 1750.8, 1: 1742.4. Samples: 11972258. Policy #0 lag: (min: 0.0, avg: 20.9, max: 32.0) -[2023-10-15 03:10:43,535][87330] Avg episode reward: [(0, '22.690'), (1, '22.700')] -[2023-10-15 03:10:43,545][88033] Saving new best policy, reward=22.700! -[2023-10-15 03:10:43,855][88298] Updated weights for policy 0, policy_version 23300 (0.0011) -[2023-10-15 03:10:44,235][88298] Updated weights for policy 0, policy_version 23310 (0.0011) -[2023-10-15 03:10:44,608][88298] Updated weights for policy 0, policy_version 23320 (0.0009) -[2023-10-15 03:10:45,799][88300] Updated weights for policy 1, policy_version 23432 (0.0009) -[2023-10-15 03:10:46,161][88300] Updated weights for policy 1, policy_version 23442 (0.0007) -[2023-10-15 03:10:46,529][88300] Updated weights for policy 1, policy_version 23452 (0.0007) -[2023-10-15 03:10:48,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 47906816. Throughput: 0: 1720.3, 1: 1750.1. Samples: 11982202. Policy #0 lag: (min: 0.0, avg: 20.9, max: 32.0) -[2023-10-15 03:10:48,535][87330] Avg episode reward: [(0, '22.600'), (1, '22.560')] -[2023-10-15 03:10:48,591][88298] Updated weights for policy 0, policy_version 23330 (0.0007) -[2023-10-15 03:10:48,959][88298] Updated weights for policy 0, policy_version 23340 (0.0007) -[2023-10-15 03:10:49,337][88298] Updated weights for policy 0, policy_version 23350 (0.0007) -[2023-10-15 03:10:49,717][88298] Updated weights for policy 0, policy_version 23360 (0.0009) -[2023-10-15 03:10:50,417][88300] Updated weights for policy 1, policy_version 23462 (0.0007) -[2023-10-15 03:10:50,780][88300] Updated weights for policy 1, policy_version 23472 (0.0008) -[2023-10-15 03:10:51,145][88300] Updated weights for policy 1, policy_version 23482 (0.0011) -[2023-10-15 03:10:53,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 47972352. Throughput: 0: 1742.3, 1: 1729.6. Samples: 12003246. Policy #0 lag: (min: 0.0, avg: 20.9, max: 32.0) -[2023-10-15 03:10:53,534][87330] Avg episode reward: [(0, '22.590'), (1, '22.570')] -[2023-10-15 03:10:53,705][88298] Updated weights for policy 0, policy_version 23370 (0.0008) -[2023-10-15 03:10:54,078][88298] Updated weights for policy 0, policy_version 23380 (0.0009) -[2023-10-15 03:10:54,444][88298] Updated weights for policy 0, policy_version 23390 (0.0007) -[2023-10-15 03:10:55,131][88300] Updated weights for policy 1, policy_version 23492 (0.0008) -[2023-10-15 03:10:55,495][88300] Updated weights for policy 1, policy_version 23502 (0.0007) -[2023-10-15 03:10:55,867][88300] Updated weights for policy 1, policy_version 23512 (0.0007) -[2023-10-15 03:10:58,189][88298] Updated weights for policy 0, policy_version 23400 (0.0007) -[2023-10-15 03:10:58,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.2, 300 sec: 13884.7). Total num frames: 48037888. Throughput: 0: 1750.9, 1: 1736.3. Samples: 12024750. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:10:58,535][87330] Avg episode reward: [(0, '22.590'), (1, '22.570')] -[2023-10-15 03:10:58,546][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000023520_24084480.pth... -[2023-10-15 03:10:58,562][88298] Updated weights for policy 0, policy_version 23410 (0.0007) -[2023-10-15 03:10:58,577][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000021888_22413312.pth -[2023-10-15 03:10:58,940][88298] Updated weights for policy 0, policy_version 23420 (0.0007) -[2023-10-15 03:10:59,089][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000023424_23986176.pth... -[2023-10-15 03:10:59,127][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000021792_22315008.pth -[2023-10-15 03:10:59,913][88300] Updated weights for policy 1, policy_version 23522 (0.0007) -[2023-10-15 03:11:00,270][88300] Updated weights for policy 1, policy_version 23532 (0.0010) -[2023-10-15 03:11:00,631][88300] Updated weights for policy 1, policy_version 23542 (0.0009) -[2023-10-15 03:11:00,996][88300] Updated weights for policy 1, policy_version 23552 (0.0007) -[2023-10-15 03:11:02,813][88298] Updated weights for policy 0, policy_version 23430 (0.0009) -[2023-10-15 03:11:03,186][88298] Updated weights for policy 0, policy_version 23440 (0.0007) -[2023-10-15 03:11:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 48103424. Throughput: 0: 1737.3, 1: 1724.8. Samples: 12034182. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:11:03,534][87330] Avg episode reward: [(0, '22.590'), (1, '22.490')] -[2023-10-15 03:11:03,560][88298] Updated weights for policy 0, policy_version 23450 (0.0007) -[2023-10-15 03:11:04,771][88300] Updated weights for policy 1, policy_version 23562 (0.0008) -[2023-10-15 03:11:05,144][88300] Updated weights for policy 1, policy_version 23572 (0.0009) -[2023-10-15 03:11:05,512][88300] Updated weights for policy 1, policy_version 23582 (0.0009) -[2023-10-15 03:11:07,558][88298] Updated weights for policy 0, policy_version 23460 (0.0008) -[2023-10-15 03:11:07,930][88298] Updated weights for policy 0, policy_version 23470 (0.0007) -[2023-10-15 03:11:08,310][88298] Updated weights for policy 0, policy_version 23480 (0.0007) -[2023-10-15 03:11:08,534][87330] Fps is (10 sec: 13107.7, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 48168960. Throughput: 0: 1749.3, 1: 1731.4. Samples: 12055630. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:11:08,534][87330] Avg episode reward: [(0, '22.560'), (1, '22.490')] -[2023-10-15 03:11:09,420][88300] Updated weights for policy 1, policy_version 23592 (0.0010) -[2023-10-15 03:11:09,796][88300] Updated weights for policy 1, policy_version 23602 (0.0009) -[2023-10-15 03:11:10,166][88300] Updated weights for policy 1, policy_version 23612 (0.0010) -[2023-10-15 03:11:12,181][88298] Updated weights for policy 0, policy_version 23490 (0.0007) -[2023-10-15 03:11:12,577][88298] Updated weights for policy 0, policy_version 23500 (0.0008) -[2023-10-15 03:11:12,945][88298] Updated weights for policy 0, policy_version 23510 (0.0007) -[2023-10-15 03:11:13,317][88298] Updated weights for policy 0, policy_version 23520 (0.0008) -[2023-10-15 03:11:13,534][87330] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 48267264. Throughput: 0: 1732.0, 1: 1757.4. Samples: 12076368. Policy #0 lag: (min: 20.0, avg: 38.7, max: 40.0) -[2023-10-15 03:11:13,535][87330] Avg episode reward: [(0, '22.590'), (1, '22.400')] -[2023-10-15 03:11:14,106][88300] Updated weights for policy 1, policy_version 23622 (0.0009) -[2023-10-15 03:11:14,492][88300] Updated weights for policy 1, policy_version 23632 (0.0009) -[2023-10-15 03:11:14,858][88300] Updated weights for policy 1, policy_version 23642 (0.0009) -[2023-10-15 03:11:17,296][88298] Updated weights for policy 0, policy_version 23530 (0.0008) -[2023-10-15 03:11:17,667][88298] Updated weights for policy 0, policy_version 23540 (0.0008) -[2023-10-15 03:11:18,048][88298] Updated weights for policy 0, policy_version 23550 (0.0008) -[2023-10-15 03:11:18,534][87330] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 48332800. Throughput: 0: 1746.3, 1: 1725.7. Samples: 12086448. Policy #0 lag: (min: 20.0, avg: 38.7, max: 40.0) -[2023-10-15 03:11:18,534][87330] Avg episode reward: [(0, '22.760'), (1, '22.470')] -[2023-10-15 03:11:18,638][88300] Updated weights for policy 1, policy_version 23652 (0.0010) -[2023-10-15 03:11:19,005][88300] Updated weights for policy 1, policy_version 23662 (0.0009) -[2023-10-15 03:11:19,369][88300] Updated weights for policy 1, policy_version 23672 (0.0010) -[2023-10-15 03:11:22,008][88298] Updated weights for policy 0, policy_version 23560 (0.0008) -[2023-10-15 03:11:22,376][88298] Updated weights for policy 0, policy_version 23570 (0.0008) -[2023-10-15 03:11:22,751][88298] Updated weights for policy 0, policy_version 23580 (0.0009) -[2023-10-15 03:11:23,144][88300] Updated weights for policy 1, policy_version 23682 (0.0009) -[2023-10-15 03:11:23,513][88300] Updated weights for policy 1, policy_version 23692 (0.0012) -[2023-10-15 03:11:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 48398336. Throughput: 0: 1741.2, 1: 1750.6. Samples: 12107944. Policy #0 lag: (min: 20.0, avg: 38.7, max: 40.0) -[2023-10-15 03:11:23,535][87330] Avg episode reward: [(0, '22.730'), (1, '22.630')] -[2023-10-15 03:11:23,890][88300] Updated weights for policy 1, policy_version 23702 (0.0009) -[2023-10-15 03:11:24,263][88300] Updated weights for policy 1, policy_version 23712 (0.0008) -[2023-10-15 03:11:26,711][88298] Updated weights for policy 0, policy_version 23590 (0.0009) -[2023-10-15 03:11:27,084][88298] Updated weights for policy 0, policy_version 23600 (0.0008) -[2023-10-15 03:11:27,449][88298] Updated weights for policy 0, policy_version 23610 (0.0007) -[2023-10-15 03:11:28,262][88300] Updated weights for policy 1, policy_version 23722 (0.0008) -[2023-10-15 03:11:28,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 48463872. Throughput: 0: 1711.6, 1: 1745.6. Samples: 12127832. Policy #0 lag: (min: 20.0, avg: 38.7, max: 40.0) -[2023-10-15 03:11:28,534][87330] Avg episode reward: [(0, '22.740'), (1, '22.630')] -[2023-10-15 03:11:28,637][88300] Updated weights for policy 1, policy_version 23732 (0.0008) -[2023-10-15 03:11:29,008][88300] Updated weights for policy 1, policy_version 23742 (0.0008) -[2023-10-15 03:11:31,238][88298] Updated weights for policy 0, policy_version 23620 (0.0008) -[2023-10-15 03:11:31,610][88298] Updated weights for policy 0, policy_version 23630 (0.0009) -[2023-10-15 03:11:31,987][88298] Updated weights for policy 0, policy_version 23640 (0.0008) -[2023-10-15 03:11:32,980][88300] Updated weights for policy 1, policy_version 23752 (0.0007) -[2023-10-15 03:11:33,342][88300] Updated weights for policy 1, policy_version 23762 (0.0007) -[2023-10-15 03:11:33,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 48529408. Throughput: 0: 1748.1, 1: 1738.1. Samples: 12139084. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:11:33,534][87330] Avg episode reward: [(0, '22.740'), (1, '22.590')] -[2023-10-15 03:11:33,715][88300] Updated weights for policy 1, policy_version 23772 (0.0009) -[2023-10-15 03:11:35,908][88298] Updated weights for policy 0, policy_version 23650 (0.0007) -[2023-10-15 03:11:36,275][88298] Updated weights for policy 0, policy_version 23660 (0.0007) -[2023-10-15 03:11:36,646][88298] Updated weights for policy 0, policy_version 23670 (0.0008) -[2023-10-15 03:11:37,009][88298] Updated weights for policy 0, policy_version 23680 (0.0008) -[2023-10-15 03:11:37,611][88300] Updated weights for policy 1, policy_version 23782 (0.0009) -[2023-10-15 03:11:37,995][88300] Updated weights for policy 1, policy_version 23792 (0.0009) -[2023-10-15 03:11:38,361][88300] Updated weights for policy 1, policy_version 23802 (0.0008) -[2023-10-15 03:11:38,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 48594944. Throughput: 0: 1721.7, 1: 1751.6. Samples: 12159546. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:11:38,534][87330] Avg episode reward: [(0, '22.600'), (1, '22.590')] -[2023-10-15 03:11:40,849][88298] Updated weights for policy 0, policy_version 23690 (0.0007) -[2023-10-15 03:11:41,221][88298] Updated weights for policy 0, policy_version 23700 (0.0007) -[2023-10-15 03:11:41,593][88298] Updated weights for policy 0, policy_version 23710 (0.0008) -[2023-10-15 03:11:42,350][88300] Updated weights for policy 1, policy_version 23812 (0.0010) -[2023-10-15 03:11:42,718][88300] Updated weights for policy 1, policy_version 23822 (0.0008) -[2023-10-15 03:11:43,082][88300] Updated weights for policy 1, policy_version 23832 (0.0009) -[2023-10-15 03:11:43,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 48693248. Throughput: 0: 1715.5, 1: 1732.1. Samples: 12179892. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:11:43,534][87330] Avg episode reward: [(0, '22.480'), (1, '22.630')] -[2023-10-15 03:11:45,515][88298] Updated weights for policy 0, policy_version 23720 (0.0007) -[2023-10-15 03:11:45,884][88298] Updated weights for policy 0, policy_version 23730 (0.0007) -[2023-10-15 03:11:46,265][88298] Updated weights for policy 0, policy_version 23740 (0.0008) -[2023-10-15 03:11:46,880][88300] Updated weights for policy 1, policy_version 23842 (0.0010) -[2023-10-15 03:11:47,243][88300] Updated weights for policy 1, policy_version 23852 (0.0008) -[2023-10-15 03:11:47,609][88300] Updated weights for policy 1, policy_version 23862 (0.0010) -[2023-10-15 03:11:47,973][88300] Updated weights for policy 1, policy_version 23872 (0.0011) -[2023-10-15 03:11:48,534][87330] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 48758784. Throughput: 0: 1731.2, 1: 1757.6. Samples: 12191180. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:11:48,535][87330] Avg episode reward: [(0, '22.450'), (1, '22.530')] -[2023-10-15 03:11:50,242][88298] Updated weights for policy 0, policy_version 23750 (0.0008) -[2023-10-15 03:11:50,617][88298] Updated weights for policy 0, policy_version 23760 (0.0009) -[2023-10-15 03:11:50,988][88298] Updated weights for policy 0, policy_version 23770 (0.0007) -[2023-10-15 03:11:51,912][88300] Updated weights for policy 1, policy_version 23882 (0.0010) -[2023-10-15 03:11:52,286][88300] Updated weights for policy 1, policy_version 23892 (0.0010) -[2023-10-15 03:11:52,649][88300] Updated weights for policy 1, policy_version 23902 (0.0009) -[2023-10-15 03:11:53,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13884.8). Total num frames: 48824320. Throughput: 0: 1715.2, 1: 1740.2. Samples: 12211124. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:11:53,535][87330] Avg episode reward: [(0, '22.490'), (1, '22.450')] -[2023-10-15 03:11:55,014][88298] Updated weights for policy 0, policy_version 23780 (0.0008) -[2023-10-15 03:11:55,388][88298] Updated weights for policy 0, policy_version 23790 (0.0011) -[2023-10-15 03:11:55,760][88298] Updated weights for policy 0, policy_version 23800 (0.0011) -[2023-10-15 03:11:56,419][88300] Updated weights for policy 1, policy_version 23912 (0.0008) -[2023-10-15 03:11:56,785][88300] Updated weights for policy 1, policy_version 23922 (0.0008) -[2023-10-15 03:11:57,149][88300] Updated weights for policy 1, policy_version 23932 (0.0008) -[2023-10-15 03:11:58,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 48889856. Throughput: 0: 1731.5, 1: 1729.2. Samples: 12232098. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:11:58,535][87330] Avg episode reward: [(0, '22.430'), (1, '22.380')] -[2023-10-15 03:11:59,756][88298] Updated weights for policy 0, policy_version 23810 (0.0009) -[2023-10-15 03:12:00,135][88298] Updated weights for policy 0, policy_version 23820 (0.0008) -[2023-10-15 03:12:00,502][88298] Updated weights for policy 0, policy_version 23830 (0.0007) -[2023-10-15 03:12:00,873][88298] Updated weights for policy 0, policy_version 23840 (0.0008) -[2023-10-15 03:12:01,095][88300] Updated weights for policy 1, policy_version 23942 (0.0010) -[2023-10-15 03:12:01,494][88300] Updated weights for policy 1, policy_version 23952 (0.0010) -[2023-10-15 03:12:01,868][88300] Updated weights for policy 1, policy_version 23962 (0.0009) -[2023-10-15 03:12:03,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 48955392. Throughput: 0: 1716.8, 1: 1752.5. Samples: 12242566. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:12:03,534][87330] Avg episode reward: [(0, '22.460'), (1, '22.160')] -[2023-10-15 03:12:04,639][88298] Updated weights for policy 0, policy_version 23850 (0.0007) -[2023-10-15 03:12:05,005][88298] Updated weights for policy 0, policy_version 23860 (0.0010) -[2023-10-15 03:12:05,382][88298] Updated weights for policy 0, policy_version 23870 (0.0008) -[2023-10-15 03:12:05,832][88300] Updated weights for policy 1, policy_version 23972 (0.0008) -[2023-10-15 03:12:06,192][88300] Updated weights for policy 1, policy_version 23982 (0.0007) -[2023-10-15 03:12:06,562][88300] Updated weights for policy 1, policy_version 23992 (0.0008) -[2023-10-15 03:12:08,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 49020928. Throughput: 0: 1719.3, 1: 1728.5. Samples: 12263094. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:12:08,534][87330] Avg episode reward: [(0, '22.420'), (1, '22.090')] -[2023-10-15 03:12:09,307][88298] Updated weights for policy 0, policy_version 23880 (0.0008) -[2023-10-15 03:12:09,687][88298] Updated weights for policy 0, policy_version 23890 (0.0009) -[2023-10-15 03:12:10,052][88298] Updated weights for policy 0, policy_version 23900 (0.0007) -[2023-10-15 03:12:10,223][88300] Updated weights for policy 1, policy_version 24002 (0.0007) -[2023-10-15 03:12:10,597][88300] Updated weights for policy 1, policy_version 24012 (0.0008) -[2023-10-15 03:12:10,962][88300] Updated weights for policy 1, policy_version 24022 (0.0008) -[2023-10-15 03:12:11,329][88300] Updated weights for policy 1, policy_version 24032 (0.0011) -[2023-10-15 03:12:13,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 49086464. Throughput: 0: 1747.5, 1: 1747.6. Samples: 12285110. Policy #0 lag: (min: 13.0, avg: 13.7, max: 31.0) -[2023-10-15 03:12:13,535][87330] Avg episode reward: [(0, '22.340'), (1, '22.070')] -[2023-10-15 03:12:14,056][88298] Updated weights for policy 0, policy_version 23910 (0.0008) -[2023-10-15 03:12:14,434][88298] Updated weights for policy 0, policy_version 23920 (0.0010) -[2023-10-15 03:12:14,806][88298] Updated weights for policy 0, policy_version 23930 (0.0011) -[2023-10-15 03:12:15,159][88300] Updated weights for policy 1, policy_version 24042 (0.0008) -[2023-10-15 03:12:15,531][88300] Updated weights for policy 1, policy_version 24052 (0.0010) -[2023-10-15 03:12:15,900][88300] Updated weights for policy 1, policy_version 24062 (0.0008) -[2023-10-15 03:12:18,534][87330] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 49152000. Throughput: 0: 1709.0, 1: 1740.6. Samples: 12294316. Policy #0 lag: (min: 13.0, avg: 13.7, max: 31.0) -[2023-10-15 03:12:18,535][87330] Avg episode reward: [(0, '22.530'), (1, '21.960')] -[2023-10-15 03:12:18,742][88298] Updated weights for policy 0, policy_version 23940 (0.0007) -[2023-10-15 03:12:19,115][88298] Updated weights for policy 0, policy_version 23950 (0.0007) -[2023-10-15 03:12:19,485][88298] Updated weights for policy 0, policy_version 23960 (0.0007) -[2023-10-15 03:12:19,819][88300] Updated weights for policy 1, policy_version 24072 (0.0009) -[2023-10-15 03:12:20,197][88300] Updated weights for policy 1, policy_version 24082 (0.0009) -[2023-10-15 03:12:20,562][88300] Updated weights for policy 1, policy_version 24092 (0.0009) -[2023-10-15 03:12:23,367][88298] Updated weights for policy 0, policy_version 23970 (0.0009) -[2023-10-15 03:12:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 49217536. Throughput: 0: 1735.9, 1: 1740.7. Samples: 12315992. Policy #0 lag: (min: 13.0, avg: 13.7, max: 31.0) -[2023-10-15 03:12:23,534][87330] Avg episode reward: [(0, '22.310'), (1, '22.030')] -[2023-10-15 03:12:23,736][88298] Updated weights for policy 0, policy_version 23980 (0.0010) -[2023-10-15 03:12:24,106][88298] Updated weights for policy 0, policy_version 23990 (0.0007) -[2023-10-15 03:12:24,348][88300] Updated weights for policy 1, policy_version 24102 (0.0008) -[2023-10-15 03:12:24,481][88298] Updated weights for policy 0, policy_version 24000 (0.0007) -[2023-10-15 03:12:24,710][88300] Updated weights for policy 1, policy_version 24112 (0.0007) -[2023-10-15 03:12:25,071][88300] Updated weights for policy 1, policy_version 24122 (0.0007) -[2023-10-15 03:12:28,414][88298] Updated weights for policy 0, policy_version 24010 (0.0010) -[2023-10-15 03:12:28,534][87330] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 49283072. Throughput: 0: 1737.8, 1: 1767.0. Samples: 12337610. Policy #0 lag: (min: 13.0, avg: 13.7, max: 31.0) -[2023-10-15 03:12:28,534][87330] Avg episode reward: [(0, '22.390'), (1, '22.060')] -[2023-10-15 03:12:28,783][88298] Updated weights for policy 0, policy_version 24020 (0.0009) -[2023-10-15 03:12:28,899][88300] Updated weights for policy 1, policy_version 24132 (0.0007) -[2023-10-15 03:12:29,155][88298] Updated weights for policy 0, policy_version 24030 (0.0008) -[2023-10-15 03:12:29,259][88300] Updated weights for policy 1, policy_version 24142 (0.0008) -[2023-10-15 03:12:29,625][88300] Updated weights for policy 1, policy_version 24152 (0.0010) -[2023-10-15 03:12:33,196][88298] Updated weights for policy 0, policy_version 24040 (0.0007) -[2023-10-15 03:12:33,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 49348608. Throughput: 0: 1719.5, 1: 1746.5. Samples: 12347150. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-15 03:12:33,534][87330] Avg episode reward: [(0, '22.420'), (1, '22.130')] -[2023-10-15 03:12:33,563][88300] Updated weights for policy 1, policy_version 24162 (0.0009) -[2023-10-15 03:12:33,573][88298] Updated weights for policy 0, policy_version 24050 (0.0007) -[2023-10-15 03:12:33,927][88300] Updated weights for policy 1, policy_version 24172 (0.0009) -[2023-10-15 03:12:33,943][88298] Updated weights for policy 0, policy_version 24060 (0.0008) -[2023-10-15 03:12:34,295][88300] Updated weights for policy 1, policy_version 24182 (0.0010) -[2023-10-15 03:12:34,666][88300] Updated weights for policy 1, policy_version 24192 (0.0010) -[2023-10-15 03:12:37,882][88298] Updated weights for policy 0, policy_version 24070 (0.0008) -[2023-10-15 03:12:38,245][88298] Updated weights for policy 0, policy_version 24080 (0.0010) -[2023-10-15 03:12:38,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 49414144. Throughput: 0: 1736.2, 1: 1760.8. Samples: 12368488. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-15 03:12:38,534][87330] Avg episode reward: [(0, '22.420'), (1, '22.340')] -[2023-10-15 03:12:38,596][88300] Updated weights for policy 1, policy_version 24202 (0.0008) -[2023-10-15 03:12:38,614][88298] Updated weights for policy 0, policy_version 24090 (0.0008) -[2023-10-15 03:12:38,969][88300] Updated weights for policy 1, policy_version 24212 (0.0007) -[2023-10-15 03:12:39,334][88300] Updated weights for policy 1, policy_version 24222 (0.0008) -[2023-10-15 03:12:42,305][88298] Updated weights for policy 0, policy_version 24100 (0.0007) -[2023-10-15 03:12:42,678][88298] Updated weights for policy 0, policy_version 24110 (0.0009) -[2023-10-15 03:12:43,059][88298] Updated weights for policy 0, policy_version 24120 (0.0009) -[2023-10-15 03:12:43,161][88300] Updated weights for policy 1, policy_version 24232 (0.0009) -[2023-10-15 03:12:43,533][88300] Updated weights for policy 1, policy_version 24242 (0.0007) -[2023-10-15 03:12:43,534][87330] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13995.8). Total num frames: 49512448. Throughput: 0: 1721.6, 1: 1763.7. Samples: 12388934. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-15 03:12:43,534][87330] Avg episode reward: [(0, '22.590'), (1, '22.490')] -[2023-10-15 03:12:43,894][88300] Updated weights for policy 1, policy_version 24252 (0.0007) -[2023-10-15 03:12:47,173][88298] Updated weights for policy 0, policy_version 24130 (0.0011) -[2023-10-15 03:12:47,581][88298] Updated weights for policy 0, policy_version 24140 (0.0009) -[2023-10-15 03:12:47,924][88300] Updated weights for policy 1, policy_version 24262 (0.0007) -[2023-10-15 03:12:47,954][88298] Updated weights for policy 0, policy_version 24150 (0.0008) -[2023-10-15 03:12:48,307][88300] Updated weights for policy 1, policy_version 24272 (0.0008) -[2023-10-15 03:12:48,320][88298] Updated weights for policy 0, policy_version 24160 (0.0009) -[2023-10-15 03:12:48,534][87330] Fps is (10 sec: 16384.2, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 49577984. Throughput: 0: 1734.4, 1: 1748.4. Samples: 12399290. Policy #0 lag: (min: 5.0, avg: 18.4, max: 37.0) -[2023-10-15 03:12:48,534][87330] Avg episode reward: [(0, '22.670'), (1, '22.540')] -[2023-10-15 03:12:48,679][88300] Updated weights for policy 1, policy_version 24282 (0.0008) -[2023-10-15 03:12:52,160][88298] Updated weights for policy 0, policy_version 24170 (0.0007) -[2023-10-15 03:12:52,500][88300] Updated weights for policy 1, policy_version 24292 (0.0007) -[2023-10-15 03:12:52,531][88298] Updated weights for policy 0, policy_version 24180 (0.0007) -[2023-10-15 03:12:52,867][88300] Updated weights for policy 1, policy_version 24302 (0.0008) -[2023-10-15 03:12:52,898][88298] Updated weights for policy 0, policy_version 24190 (0.0009) -[2023-10-15 03:12:53,238][88300] Updated weights for policy 1, policy_version 24312 (0.0009) -[2023-10-15 03:12:53,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 49676288. Throughput: 0: 1735.7, 1: 1765.8. Samples: 12420662. Policy #0 lag: (min: 5.0, avg: 18.4, max: 37.0) -[2023-10-15 03:12:53,534][87330] Avg episode reward: [(0, '22.640'), (1, '22.690')] -[2023-10-15 03:12:56,749][88298] Updated weights for policy 0, policy_version 24200 (0.0008) -[2023-10-15 03:12:57,127][88298] Updated weights for policy 0, policy_version 24210 (0.0007) -[2023-10-15 03:12:57,208][88300] Updated weights for policy 1, policy_version 24322 (0.0010) -[2023-10-15 03:12:57,505][88298] Updated weights for policy 0, policy_version 24220 (0.0007) -[2023-10-15 03:12:57,582][88300] Updated weights for policy 1, policy_version 24332 (0.0008) -[2023-10-15 03:12:57,943][88300] Updated weights for policy 1, policy_version 24342 (0.0008) -[2023-10-15 03:12:58,311][88300] Updated weights for policy 1, policy_version 24352 (0.0009) -[2023-10-15 03:12:58,534][87330] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 49741824. Throughput: 0: 1704.9, 1: 1727.1. Samples: 12439548. Policy #0 lag: (min: 5.0, avg: 18.4, max: 37.0) -[2023-10-15 03:12:58,535][87330] Avg episode reward: [(0, '22.690'), (1, '22.690')] -[2023-10-15 03:12:58,544][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000024352_24936448.pth... -[2023-10-15 03:12:58,544][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000024224_24805376.pth... -[2023-10-15 03:12:58,577][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000022720_23265280.pth -[2023-10-15 03:12:58,580][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000022592_23134208.pth -[2023-10-15 03:12:58,581][88033] Saving a milestone ./train_atari/atari_seaquest_APPO/checkpoint_p1/milestones/checkpoint_000024352_24936448.pth -[2023-10-15 03:12:58,584][87905] Saving a milestone ./train_atari/atari_seaquest_APPO/checkpoint_p0/milestones/checkpoint_000024224_24805376.pth -[2023-10-15 03:13:01,352][88298] Updated weights for policy 0, policy_version 24230 (0.0009) -[2023-10-15 03:13:01,714][88298] Updated weights for policy 0, policy_version 24240 (0.0008) -[2023-10-15 03:13:02,084][88298] Updated weights for policy 0, policy_version 24250 (0.0008) -[2023-10-15 03:13:02,182][88300] Updated weights for policy 1, policy_version 24362 (0.0009) -[2023-10-15 03:13:02,552][88300] Updated weights for policy 1, policy_version 24372 (0.0008) -[2023-10-15 03:13:02,915][88300] Updated weights for policy 1, policy_version 24382 (0.0008) -[2023-10-15 03:13:03,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 49807360. Throughput: 0: 1735.6, 1: 1757.6. Samples: 12451508. Policy #0 lag: (min: 5.0, avg: 18.4, max: 37.0) -[2023-10-15 03:13:03,534][87330] Avg episode reward: [(0, '22.700'), (1, '22.680')] -[2023-10-15 03:13:05,968][88298] Updated weights for policy 0, policy_version 24260 (0.0009) -[2023-10-15 03:13:06,341][88298] Updated weights for policy 0, policy_version 24270 (0.0009) -[2023-10-15 03:13:06,706][88298] Updated weights for policy 0, policy_version 24280 (0.0008) -[2023-10-15 03:13:06,903][88300] Updated weights for policy 1, policy_version 24392 (0.0007) -[2023-10-15 03:13:07,276][88300] Updated weights for policy 1, policy_version 24402 (0.0007) -[2023-10-15 03:13:07,645][88300] Updated weights for policy 1, policy_version 24412 (0.0010) -[2023-10-15 03:13:08,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 49872896. Throughput: 0: 1709.5, 1: 1737.6. Samples: 12471110. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:13:08,534][87330] Avg episode reward: [(0, '22.600'), (1, '22.710')] -[2023-10-15 03:13:08,535][88033] Saving new best policy, reward=22.710! -[2023-10-15 03:13:10,749][88298] Updated weights for policy 0, policy_version 24290 (0.0007) -[2023-10-15 03:13:11,119][88298] Updated weights for policy 0, policy_version 24300 (0.0008) -[2023-10-15 03:13:11,490][88298] Updated weights for policy 0, policy_version 24310 (0.0010) -[2023-10-15 03:13:11,568][88300] Updated weights for policy 1, policy_version 24422 (0.0007) -[2023-10-15 03:13:11,861][88298] Updated weights for policy 0, policy_version 24320 (0.0008) -[2023-10-15 03:13:11,933][88300] Updated weights for policy 1, policy_version 24432 (0.0009) -[2023-10-15 03:13:12,304][88300] Updated weights for policy 1, policy_version 24442 (0.0010) -[2023-10-15 03:13:13,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 49938432. Throughput: 0: 1709.7, 1: 1720.7. Samples: 12491982. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:13:13,535][87330] Avg episode reward: [(0, '22.550'), (1, '22.880')] -[2023-10-15 03:13:13,547][88033] Saving new best policy, reward=22.880! -[2023-10-15 03:13:15,712][88298] Updated weights for policy 0, policy_version 24330 (0.0007) -[2023-10-15 03:13:16,076][88298] Updated weights for policy 0, policy_version 24340 (0.0008) -[2023-10-15 03:13:16,180][88300] Updated weights for policy 1, policy_version 24452 (0.0009) -[2023-10-15 03:13:16,454][88298] Updated weights for policy 0, policy_version 24350 (0.0009) -[2023-10-15 03:13:16,544][88300] Updated weights for policy 1, policy_version 24462 (0.0009) -[2023-10-15 03:13:16,916][88300] Updated weights for policy 1, policy_version 24472 (0.0007) -[2023-10-15 03:13:18,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 50003968. Throughput: 0: 1731.1, 1: 1741.5. Samples: 12503416. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:13:18,534][87330] Avg episode reward: [(0, '22.560'), (1, '22.880')] -[2023-10-15 03:13:20,304][88298] Updated weights for policy 0, policy_version 24360 (0.0008) -[2023-10-15 03:13:20,680][88298] Updated weights for policy 0, policy_version 24370 (0.0007) -[2023-10-15 03:13:20,865][88300] Updated weights for policy 1, policy_version 24482 (0.0007) -[2023-10-15 03:13:21,047][88298] Updated weights for policy 0, policy_version 24380 (0.0008) -[2023-10-15 03:13:21,224][88300] Updated weights for policy 1, policy_version 24492 (0.0008) -[2023-10-15 03:13:21,591][88300] Updated weights for policy 1, policy_version 24502 (0.0007) -[2023-10-15 03:13:21,949][88300] Updated weights for policy 1, policy_version 24512 (0.0009) -[2023-10-15 03:13:23,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 50069504. Throughput: 0: 1714.1, 1: 1718.5. Samples: 12522956. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:13:23,535][87330] Avg episode reward: [(0, '22.550'), (1, '22.950')] -[2023-10-15 03:13:23,536][88033] Saving new best policy, reward=22.950! -[2023-10-15 03:13:25,054][88298] Updated weights for policy 0, policy_version 24390 (0.0008) -[2023-10-15 03:13:25,420][88298] Updated weights for policy 0, policy_version 24400 (0.0007) -[2023-10-15 03:13:25,773][88300] Updated weights for policy 1, policy_version 24522 (0.0007) -[2023-10-15 03:13:25,799][88298] Updated weights for policy 0, policy_version 24410 (0.0007) -[2023-10-15 03:13:26,144][88300] Updated weights for policy 1, policy_version 24532 (0.0008) -[2023-10-15 03:13:26,511][88300] Updated weights for policy 1, policy_version 24542 (0.0010) -[2023-10-15 03:13:28,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 50135040. Throughput: 0: 1728.3, 1: 1730.4. Samples: 12544580. Policy #0 lag: (min: 16.0, avg: 40.2, max: 48.0) -[2023-10-15 03:13:28,535][87330] Avg episode reward: [(0, '22.670'), (1, '22.940')] -[2023-10-15 03:13:29,760][88298] Updated weights for policy 0, policy_version 24420 (0.0009) -[2023-10-15 03:13:30,128][88298] Updated weights for policy 0, policy_version 24430 (0.0008) -[2023-10-15 03:13:30,430][88300] Updated weights for policy 1, policy_version 24552 (0.0009) -[2023-10-15 03:13:30,500][88298] Updated weights for policy 0, policy_version 24440 (0.0008) -[2023-10-15 03:13:30,794][88300] Updated weights for policy 1, policy_version 24562 (0.0008) -[2023-10-15 03:13:31,161][88300] Updated weights for policy 1, policy_version 24572 (0.0008) -[2023-10-15 03:13:33,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 50200576. Throughput: 0: 1718.2, 1: 1727.6. Samples: 12554350. Policy #0 lag: (min: 16.0, avg: 40.2, max: 48.0) -[2023-10-15 03:13:33,534][87330] Avg episode reward: [(0, '22.600'), (1, '22.800')] -[2023-10-15 03:13:34,261][88298] Updated weights for policy 0, policy_version 24450 (0.0009) -[2023-10-15 03:13:34,628][88298] Updated weights for policy 0, policy_version 24460 (0.0010) -[2023-10-15 03:13:34,975][88300] Updated weights for policy 1, policy_version 24582 (0.0009) -[2023-10-15 03:13:35,005][88298] Updated weights for policy 0, policy_version 24470 (0.0008) -[2023-10-15 03:13:35,336][88300] Updated weights for policy 1, policy_version 24592 (0.0008) -[2023-10-15 03:13:35,368][88298] Updated weights for policy 0, policy_version 24480 (0.0008) -[2023-10-15 03:13:35,706][88300] Updated weights for policy 1, policy_version 24602 (0.0008) -[2023-10-15 03:13:38,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 50266112. Throughput: 0: 1717.6, 1: 1728.8. Samples: 12575750. Policy #0 lag: (min: 16.0, avg: 40.2, max: 48.0) -[2023-10-15 03:13:38,535][87330] Avg episode reward: [(0, '22.670'), (1, '22.670')] -[2023-10-15 03:13:39,501][88298] Updated weights for policy 0, policy_version 24490 (0.0008) -[2023-10-15 03:13:39,796][88300] Updated weights for policy 1, policy_version 24612 (0.0009) -[2023-10-15 03:13:39,876][88298] Updated weights for policy 0, policy_version 24500 (0.0009) -[2023-10-15 03:13:40,203][88300] Updated weights for policy 1, policy_version 24622 (0.0007) -[2023-10-15 03:13:40,255][88298] Updated weights for policy 0, policy_version 24510 (0.0007) -[2023-10-15 03:13:40,574][88300] Updated weights for policy 1, policy_version 24632 (0.0007) -[2023-10-15 03:13:43,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 50331648. Throughput: 0: 1744.7, 1: 1754.2. Samples: 12597000. Policy #0 lag: (min: 16.0, avg: 40.2, max: 48.0) -[2023-10-15 03:13:43,535][87330] Avg episode reward: [(0, '22.740'), (1, '22.510')] -[2023-10-15 03:13:44,290][88298] Updated weights for policy 0, policy_version 24520 (0.0009) -[2023-10-15 03:13:44,356][88300] Updated weights for policy 1, policy_version 24642 (0.0007) -[2023-10-15 03:13:44,660][88298] Updated weights for policy 0, policy_version 24530 (0.0007) -[2023-10-15 03:13:44,724][88300] Updated weights for policy 1, policy_version 24652 (0.0007) -[2023-10-15 03:13:45,041][88298] Updated weights for policy 0, policy_version 24540 (0.0007) -[2023-10-15 03:13:45,092][88300] Updated weights for policy 1, policy_version 24662 (0.0007) -[2023-10-15 03:13:45,467][88300] Updated weights for policy 1, policy_version 24672 (0.0009) -[2023-10-15 03:13:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 50397184. Throughput: 0: 1714.4, 1: 1727.4. Samples: 12606386. Policy #0 lag: (min: 3.0, avg: 6.4, max: 35.0) -[2023-10-15 03:13:48,535][87330] Avg episode reward: [(0, '22.690'), (1, '22.290')] -[2023-10-15 03:13:48,953][88298] Updated weights for policy 0, policy_version 24550 (0.0008) -[2023-10-15 03:13:49,258][88300] Updated weights for policy 1, policy_version 24682 (0.0007) -[2023-10-15 03:13:49,319][88298] Updated weights for policy 0, policy_version 24560 (0.0008) -[2023-10-15 03:13:49,621][88300] Updated weights for policy 1, policy_version 24692 (0.0007) -[2023-10-15 03:13:49,678][88298] Updated weights for policy 0, policy_version 24570 (0.0007) -[2023-10-15 03:13:49,990][88300] Updated weights for policy 1, policy_version 24702 (0.0007) -[2023-10-15 03:13:53,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13884.7). Total num frames: 50462720. Throughput: 0: 1735.5, 1: 1743.6. Samples: 12627668. Policy #0 lag: (min: 3.0, avg: 6.4, max: 35.0) -[2023-10-15 03:13:53,534][87330] Avg episode reward: [(0, '22.690'), (1, '22.270')] -[2023-10-15 03:13:53,661][88298] Updated weights for policy 0, policy_version 24580 (0.0007) -[2023-10-15 03:13:53,994][88300] Updated weights for policy 1, policy_version 24712 (0.0008) -[2023-10-15 03:13:54,029][88298] Updated weights for policy 0, policy_version 24590 (0.0008) -[2023-10-15 03:13:54,373][88300] Updated weights for policy 1, policy_version 24722 (0.0007) -[2023-10-15 03:13:54,407][88298] Updated weights for policy 0, policy_version 24600 (0.0008) -[2023-10-15 03:13:54,739][88300] Updated weights for policy 1, policy_version 24732 (0.0008) -[2023-10-15 03:13:58,209][88298] Updated weights for policy 0, policy_version 24610 (0.0007) -[2023-10-15 03:13:58,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13884.7). Total num frames: 50528256. Throughput: 0: 1742.1, 1: 1756.5. Samples: 12649420. Policy #0 lag: (min: 3.0, avg: 6.4, max: 35.0) -[2023-10-15 03:13:58,535][87330] Avg episode reward: [(0, '22.690'), (1, '22.300')] -[2023-10-15 03:13:58,547][88300] Updated weights for policy 1, policy_version 24742 (0.0007) -[2023-10-15 03:13:58,580][88298] Updated weights for policy 0, policy_version 24620 (0.0008) -[2023-10-15 03:13:58,905][88300] Updated weights for policy 1, policy_version 24752 (0.0007) -[2023-10-15 03:13:58,956][88298] Updated weights for policy 0, policy_version 24630 (0.0008) -[2023-10-15 03:13:59,283][88300] Updated weights for policy 1, policy_version 24762 (0.0009) -[2023-10-15 03:13:59,322][88298] Updated weights for policy 0, policy_version 24640 (0.0008) -[2023-10-15 03:14:03,069][88300] Updated weights for policy 1, policy_version 24772 (0.0008) -[2023-10-15 03:14:03,272][88298] Updated weights for policy 0, policy_version 24650 (0.0009) -[2023-10-15 03:14:03,440][88300] Updated weights for policy 1, policy_version 24782 (0.0007) -[2023-10-15 03:14:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 50593792. Throughput: 0: 1720.7, 1: 1731.6. Samples: 12658766. Policy #0 lag: (min: 3.0, avg: 6.4, max: 35.0) -[2023-10-15 03:14:03,534][87330] Avg episode reward: [(0, '22.780'), (1, '22.120')] -[2023-10-15 03:14:03,635][88298] Updated weights for policy 0, policy_version 24660 (0.0008) -[2023-10-15 03:14:03,799][88300] Updated weights for policy 1, policy_version 24792 (0.0008) -[2023-10-15 03:14:04,006][88298] Updated weights for policy 0, policy_version 24670 (0.0009) -[2023-10-15 03:14:07,710][88300] Updated weights for policy 1, policy_version 24802 (0.0007) -[2023-10-15 03:14:08,005][88298] Updated weights for policy 0, policy_version 24680 (0.0007) -[2023-10-15 03:14:08,066][88300] Updated weights for policy 1, policy_version 24812 (0.0008) -[2023-10-15 03:14:08,377][88298] Updated weights for policy 0, policy_version 24690 (0.0009) -[2023-10-15 03:14:08,445][88300] Updated weights for policy 1, policy_version 24822 (0.0009) -[2023-10-15 03:14:08,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 50659328. Throughput: 0: 1739.2, 1: 1757.0. Samples: 12680288. Policy #0 lag: (min: 4.0, avg: 12.3, max: 36.0) -[2023-10-15 03:14:08,534][87330] Avg episode reward: [(0, '22.610'), (1, '22.330')] -[2023-10-15 03:14:08,741][88298] Updated weights for policy 0, policy_version 24700 (0.0008) -[2023-10-15 03:14:08,809][88300] Updated weights for policy 1, policy_version 24832 (0.0007) -[2023-10-15 03:14:12,689][88298] Updated weights for policy 0, policy_version 24710 (0.0008) -[2023-10-15 03:14:12,696][88300] Updated weights for policy 1, policy_version 24842 (0.0007) -[2023-10-15 03:14:13,056][88298] Updated weights for policy 0, policy_version 24720 (0.0010) -[2023-10-15 03:14:13,066][88300] Updated weights for policy 1, policy_version 24852 (0.0008) -[2023-10-15 03:14:13,426][88300] Updated weights for policy 1, policy_version 24862 (0.0007) -[2023-10-15 03:14:13,428][88298] Updated weights for policy 0, policy_version 24730 (0.0008) -[2023-10-15 03:14:13,534][87330] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 50757632. Throughput: 0: 1729.8, 1: 1731.5. Samples: 12700338. Policy #0 lag: (min: 4.0, avg: 12.3, max: 36.0) -[2023-10-15 03:14:13,534][87330] Avg episode reward: [(0, '22.590'), (1, '22.490')] -[2023-10-15 03:14:17,359][88298] Updated weights for policy 0, policy_version 24740 (0.0008) -[2023-10-15 03:14:17,398][88300] Updated weights for policy 1, policy_version 24872 (0.0009) -[2023-10-15 03:14:17,731][88298] Updated weights for policy 0, policy_version 24750 (0.0007) -[2023-10-15 03:14:17,774][88300] Updated weights for policy 1, policy_version 24882 (0.0008) -[2023-10-15 03:14:18,108][88298] Updated weights for policy 0, policy_version 24760 (0.0007) -[2023-10-15 03:14:18,139][88300] Updated weights for policy 1, policy_version 24892 (0.0010) -[2023-10-15 03:14:18,534][87330] Fps is (10 sec: 19661.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 50855936. Throughput: 0: 1737.2, 1: 1747.0. Samples: 12711142. Policy #0 lag: (min: 4.0, avg: 12.3, max: 36.0) -[2023-10-15 03:14:18,534][87330] Avg episode reward: [(0, '22.560'), (1, '22.010')] -[2023-10-15 03:14:21,872][88298] Updated weights for policy 0, policy_version 24770 (0.0007) -[2023-10-15 03:14:22,022][88300] Updated weights for policy 1, policy_version 24902 (0.0008) -[2023-10-15 03:14:22,245][88298] Updated weights for policy 0, policy_version 24780 (0.0007) -[2023-10-15 03:14:22,383][88300] Updated weights for policy 1, policy_version 24912 (0.0008) -[2023-10-15 03:14:22,613][88298] Updated weights for policy 0, policy_version 24790 (0.0007) -[2023-10-15 03:14:22,751][88300] Updated weights for policy 1, policy_version 24922 (0.0008) -[2023-10-15 03:14:22,992][88298] Updated weights for policy 0, policy_version 24800 (0.0007) -[2023-10-15 03:14:23,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 50921472. Throughput: 0: 1738.4, 1: 1740.4. Samples: 12732292. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-15 03:14:23,534][87330] Avg episode reward: [(0, '22.490'), (1, '21.860')] -[2023-10-15 03:14:26,632][88300] Updated weights for policy 1, policy_version 24932 (0.0007) -[2023-10-15 03:14:27,033][88300] Updated weights for policy 1, policy_version 24942 (0.0007) -[2023-10-15 03:14:27,072][88298] Updated weights for policy 0, policy_version 24810 (0.0009) -[2023-10-15 03:14:27,396][88300] Updated weights for policy 1, policy_version 24952 (0.0007) -[2023-10-15 03:14:27,436][88298] Updated weights for policy 0, policy_version 24820 (0.0009) -[2023-10-15 03:14:27,810][88298] Updated weights for policy 0, policy_version 24830 (0.0010) -[2023-10-15 03:14:28,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 50987008. Throughput: 0: 1711.6, 1: 1723.2. Samples: 12751566. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-15 03:14:28,535][87330] Avg episode reward: [(0, '22.370'), (1, '21.800')] -[2023-10-15 03:14:31,138][88300] Updated weights for policy 1, policy_version 24962 (0.0007) -[2023-10-15 03:14:31,493][88300] Updated weights for policy 1, policy_version 24972 (0.0008) -[2023-10-15 03:14:31,639][88298] Updated weights for policy 0, policy_version 24840 (0.0009) -[2023-10-15 03:14:31,852][88300] Updated weights for policy 1, policy_version 24982 (0.0008) -[2023-10-15 03:14:32,015][88298] Updated weights for policy 0, policy_version 24850 (0.0008) -[2023-10-15 03:14:32,214][88300] Updated weights for policy 1, policy_version 24992 (0.0008) -[2023-10-15 03:14:32,383][88298] Updated weights for policy 0, policy_version 24860 (0.0008) -[2023-10-15 03:14:33,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 51052544. Throughput: 0: 1739.1, 1: 1752.4. Samples: 12763502. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-15 03:14:33,535][87330] Avg episode reward: [(0, '22.280'), (1, '21.860')] -[2023-10-15 03:14:36,035][88300] Updated weights for policy 1, policy_version 25002 (0.0008) -[2023-10-15 03:14:36,245][88298] Updated weights for policy 0, policy_version 24870 (0.0009) -[2023-10-15 03:14:36,391][88300] Updated weights for policy 1, policy_version 25012 (0.0008) -[2023-10-15 03:14:36,615][88298] Updated weights for policy 0, policy_version 24880 (0.0008) -[2023-10-15 03:14:36,758][88300] Updated weights for policy 1, policy_version 25022 (0.0009) -[2023-10-15 03:14:36,984][88298] Updated weights for policy 0, policy_version 24890 (0.0009) -[2023-10-15 03:14:38,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 51118080. Throughput: 0: 1724.8, 1: 1734.5. Samples: 12783338. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-15 03:14:38,535][87330] Avg episode reward: [(0, '22.280'), (1, '21.860')] -[2023-10-15 03:14:40,658][88300] Updated weights for policy 1, policy_version 25032 (0.0010) -[2023-10-15 03:14:40,912][88298] Updated weights for policy 0, policy_version 24900 (0.0009) -[2023-10-15 03:14:41,022][88300] Updated weights for policy 1, policy_version 25042 (0.0008) -[2023-10-15 03:14:41,286][88298] Updated weights for policy 0, policy_version 24910 (0.0007) -[2023-10-15 03:14:41,384][88300] Updated weights for policy 1, policy_version 25052 (0.0008) -[2023-10-15 03:14:41,653][88298] Updated weights for policy 0, policy_version 24920 (0.0007) -[2023-10-15 03:14:43,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 51183616. Throughput: 0: 1709.6, 1: 1738.5. Samples: 12804588. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-15 03:14:43,535][87330] Avg episode reward: [(0, '22.080'), (1, '21.830')] -[2023-10-15 03:14:45,253][88300] Updated weights for policy 1, policy_version 25062 (0.0008) -[2023-10-15 03:14:45,575][88298] Updated weights for policy 0, policy_version 24930 (0.0007) -[2023-10-15 03:14:45,624][88300] Updated weights for policy 1, policy_version 25072 (0.0009) -[2023-10-15 03:14:45,940][88298] Updated weights for policy 0, policy_version 24940 (0.0007) -[2023-10-15 03:14:45,991][88300] Updated weights for policy 1, policy_version 25082 (0.0008) -[2023-10-15 03:14:46,303][88298] Updated weights for policy 0, policy_version 24950 (0.0009) -[2023-10-15 03:14:46,672][88298] Updated weights for policy 0, policy_version 24960 (0.0009) -[2023-10-15 03:14:48,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 51249152. Throughput: 0: 1734.1, 1: 1740.0. Samples: 12815100. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-15 03:14:48,535][87330] Avg episode reward: [(0, '22.130'), (1, '22.230')] -[2023-10-15 03:14:49,893][88300] Updated weights for policy 1, policy_version 25092 (0.0009) -[2023-10-15 03:14:50,263][88300] Updated weights for policy 1, policy_version 25102 (0.0009) -[2023-10-15 03:14:50,621][88300] Updated weights for policy 1, policy_version 25112 (0.0007) -[2023-10-15 03:14:50,683][88298] Updated weights for policy 0, policy_version 24970 (0.0007) -[2023-10-15 03:14:51,048][88298] Updated weights for policy 0, policy_version 24980 (0.0007) -[2023-10-15 03:14:51,424][88298] Updated weights for policy 0, policy_version 24990 (0.0013) -[2023-10-15 03:14:53,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 51314688. Throughput: 0: 1711.1, 1: 1734.6. Samples: 12835346. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-15 03:14:53,535][87330] Avg episode reward: [(0, '22.150'), (1, '22.190')] -[2023-10-15 03:14:54,618][88300] Updated weights for policy 1, policy_version 25122 (0.0007) -[2023-10-15 03:14:54,985][88300] Updated weights for policy 1, policy_version 25132 (0.0008) -[2023-10-15 03:14:55,343][88300] Updated weights for policy 1, policy_version 25142 (0.0007) -[2023-10-15 03:14:55,497][88298] Updated weights for policy 0, policy_version 25000 (0.0009) -[2023-10-15 03:14:55,699][88300] Updated weights for policy 1, policy_version 25152 (0.0007) -[2023-10-15 03:14:55,872][88298] Updated weights for policy 0, policy_version 25010 (0.0010) -[2023-10-15 03:14:56,237][88298] Updated weights for policy 0, policy_version 25020 (0.0008) -[2023-10-15 03:14:58,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 51380224. Throughput: 0: 1724.0, 1: 1759.2. Samples: 12857084. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-15 03:14:58,534][87330] Avg episode reward: [(0, '22.260'), (1, '22.030')] -[2023-10-15 03:14:58,545][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000025024_25624576.pth... -[2023-10-15 03:14:58,545][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000025152_25755648.pth... -[2023-10-15 03:14:58,584][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000023520_24084480.pth -[2023-10-15 03:14:58,586][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000023424_23986176.pth -[2023-10-15 03:14:59,749][88300] Updated weights for policy 1, policy_version 25162 (0.0009) -[2023-10-15 03:15:00,068][88298] Updated weights for policy 0, policy_version 25030 (0.0008) -[2023-10-15 03:15:00,104][88300] Updated weights for policy 1, policy_version 25172 (0.0008) -[2023-10-15 03:15:00,444][88298] Updated weights for policy 0, policy_version 25040 (0.0007) -[2023-10-15 03:15:00,475][88300] Updated weights for policy 1, policy_version 25182 (0.0008) -[2023-10-15 03:15:00,816][88298] Updated weights for policy 0, policy_version 25050 (0.0009) -[2023-10-15 03:15:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 51445760. Throughput: 0: 1723.5, 1: 1736.6. Samples: 12866846. Policy #0 lag: (min: 1.0, avg: 11.9, max: 33.0) -[2023-10-15 03:15:03,535][87330] Avg episode reward: [(0, '22.240'), (1, '22.070')] -[2023-10-15 03:15:04,533][88300] Updated weights for policy 1, policy_version 25192 (0.0008) -[2023-10-15 03:15:04,687][88298] Updated weights for policy 0, policy_version 25060 (0.0009) -[2023-10-15 03:15:04,901][88300] Updated weights for policy 1, policy_version 25202 (0.0007) -[2023-10-15 03:15:05,062][88298] Updated weights for policy 0, policy_version 25070 (0.0008) -[2023-10-15 03:15:05,265][88300] Updated weights for policy 1, policy_version 25212 (0.0008) -[2023-10-15 03:15:05,432][88298] Updated weights for policy 0, policy_version 25080 (0.0007) -[2023-10-15 03:15:08,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 51511296. Throughput: 0: 1718.7, 1: 1737.6. Samples: 12887822. Policy #0 lag: (min: 1.0, avg: 11.9, max: 33.0) -[2023-10-15 03:15:08,535][87330] Avg episode reward: [(0, '22.360'), (1, '22.080')] -[2023-10-15 03:15:09,203][88300] Updated weights for policy 1, policy_version 25222 (0.0007) -[2023-10-15 03:15:09,258][88298] Updated weights for policy 0, policy_version 25090 (0.0008) -[2023-10-15 03:15:09,576][88300] Updated weights for policy 1, policy_version 25232 (0.0008) -[2023-10-15 03:15:09,636][88298] Updated weights for policy 0, policy_version 25100 (0.0008) -[2023-10-15 03:15:09,933][88300] Updated weights for policy 1, policy_version 25242 (0.0008) -[2023-10-15 03:15:10,008][88298] Updated weights for policy 0, policy_version 25110 (0.0007) -[2023-10-15 03:15:10,374][88298] Updated weights for policy 0, policy_version 25120 (0.0008) -[2023-10-15 03:15:13,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 51576832. Throughput: 0: 1749.3, 1: 1760.7. Samples: 12909512. Policy #0 lag: (min: 1.0, avg: 11.9, max: 33.0) -[2023-10-15 03:15:13,534][87330] Avg episode reward: [(0, '22.140'), (1, '22.100')] -[2023-10-15 03:15:13,947][88300] Updated weights for policy 1, policy_version 25252 (0.0009) -[2023-10-15 03:15:14,350][88300] Updated weights for policy 1, policy_version 25262 (0.0009) -[2023-10-15 03:15:14,385][88298] Updated weights for policy 0, policy_version 25130 (0.0008) -[2023-10-15 03:15:14,713][88300] Updated weights for policy 1, policy_version 25272 (0.0007) -[2023-10-15 03:15:14,758][88298] Updated weights for policy 0, policy_version 25140 (0.0008) -[2023-10-15 03:15:15,133][88298] Updated weights for policy 0, policy_version 25150 (0.0008) -[2023-10-15 03:15:18,354][88300] Updated weights for policy 1, policy_version 25282 (0.0010) -[2023-10-15 03:15:18,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 51642368. Throughput: 0: 1719.5, 1: 1730.3. Samples: 12918742. Policy #0 lag: (min: 1.0, avg: 11.9, max: 33.0) -[2023-10-15 03:15:18,534][87330] Avg episode reward: [(0, '22.280'), (1, '22.090')] -[2023-10-15 03:15:18,722][88300] Updated weights for policy 1, policy_version 25292 (0.0008) -[2023-10-15 03:15:18,966][88298] Updated weights for policy 0, policy_version 25160 (0.0008) -[2023-10-15 03:15:19,089][88300] Updated weights for policy 1, policy_version 25302 (0.0008) -[2023-10-15 03:15:19,329][88298] Updated weights for policy 0, policy_version 25170 (0.0008) -[2023-10-15 03:15:19,453][88300] Updated weights for policy 1, policy_version 25312 (0.0008) -[2023-10-15 03:15:19,707][88298] Updated weights for policy 0, policy_version 25180 (0.0010) -[2023-10-15 03:15:23,417][88300] Updated weights for policy 1, policy_version 25322 (0.0010) -[2023-10-15 03:15:23,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 51707904. Throughput: 0: 1736.8, 1: 1751.3. Samples: 12940300. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:15:23,534][87330] Avg episode reward: [(0, '21.870'), (1, '22.360')] -[2023-10-15 03:15:23,601][88298] Updated weights for policy 0, policy_version 25190 (0.0009) -[2023-10-15 03:15:23,793][88300] Updated weights for policy 1, policy_version 25332 (0.0008) -[2023-10-15 03:15:23,967][88298] Updated weights for policy 0, policy_version 25200 (0.0008) -[2023-10-15 03:15:24,162][88300] Updated weights for policy 1, policy_version 25342 (0.0008) -[2023-10-15 03:15:24,333][88298] Updated weights for policy 0, policy_version 25210 (0.0009) -[2023-10-15 03:15:28,120][88300] Updated weights for policy 1, policy_version 25352 (0.0009) -[2023-10-15 03:15:28,413][88298] Updated weights for policy 0, policy_version 25220 (0.0008) -[2023-10-15 03:15:28,485][88300] Updated weights for policy 1, policy_version 25362 (0.0007) -[2023-10-15 03:15:28,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 51773440. Throughput: 0: 1742.8, 1: 1732.8. Samples: 12960986. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:15:28,534][87330] Avg episode reward: [(0, '21.990'), (1, '22.350')] -[2023-10-15 03:15:28,781][88298] Updated weights for policy 0, policy_version 25230 (0.0008) -[2023-10-15 03:15:28,850][88300] Updated weights for policy 1, policy_version 25372 (0.0008) -[2023-10-15 03:15:29,148][88298] Updated weights for policy 0, policy_version 25240 (0.0009) -[2023-10-15 03:15:32,991][88300] Updated weights for policy 1, policy_version 25382 (0.0007) -[2023-10-15 03:15:33,294][88298] Updated weights for policy 0, policy_version 25250 (0.0008) -[2023-10-15 03:15:33,359][88300] Updated weights for policy 1, policy_version 25392 (0.0008) -[2023-10-15 03:15:33,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 51838976. Throughput: 0: 1718.7, 1: 1742.0. Samples: 12970830. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:15:33,535][87330] Avg episode reward: [(0, '22.030'), (1, '22.560')] -[2023-10-15 03:15:33,662][88298] Updated weights for policy 0, policy_version 25260 (0.0009) -[2023-10-15 03:15:33,725][88300] Updated weights for policy 1, policy_version 25402 (0.0007) -[2023-10-15 03:15:34,033][88298] Updated weights for policy 0, policy_version 25270 (0.0009) -[2023-10-15 03:15:34,403][88298] Updated weights for policy 0, policy_version 25280 (0.0010) -[2023-10-15 03:15:37,641][88300] Updated weights for policy 1, policy_version 25412 (0.0009) -[2023-10-15 03:15:38,006][88300] Updated weights for policy 1, policy_version 25422 (0.0008) -[2023-10-15 03:15:38,341][88298] Updated weights for policy 0, policy_version 25290 (0.0008) -[2023-10-15 03:15:38,378][88300] Updated weights for policy 1, policy_version 25432 (0.0008) -[2023-10-15 03:15:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 13773.7). Total num frames: 51904512. Throughput: 0: 1738.4, 1: 1744.9. Samples: 12992090. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:15:38,534][87330] Avg episode reward: [(0, '21.860'), (1, '22.620')] -[2023-10-15 03:15:38,713][88298] Updated weights for policy 0, policy_version 25300 (0.0007) -[2023-10-15 03:15:39,086][88298] Updated weights for policy 0, policy_version 25310 (0.0008) -[2023-10-15 03:15:42,249][88300] Updated weights for policy 1, policy_version 25442 (0.0011) -[2023-10-15 03:15:42,610][88300] Updated weights for policy 1, policy_version 25452 (0.0008) -[2023-10-15 03:15:42,765][88298] Updated weights for policy 0, policy_version 25320 (0.0009) -[2023-10-15 03:15:42,979][88300] Updated weights for policy 1, policy_version 25462 (0.0008) -[2023-10-15 03:15:43,131][88298] Updated weights for policy 0, policy_version 25330 (0.0008) -[2023-10-15 03:15:43,335][88300] Updated weights for policy 1, policy_version 25472 (0.0007) -[2023-10-15 03:15:43,508][88298] Updated weights for policy 0, policy_version 25340 (0.0009) -[2023-10-15 03:15:43,534][87330] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 52002816. Throughput: 0: 1733.2, 1: 1713.5. Samples: 13012184. Policy #0 lag: (min: 3.0, avg: 3.0, max: 6.0) -[2023-10-15 03:15:43,535][87330] Avg episode reward: [(0, '21.990'), (1, '22.540')] -[2023-10-15 03:15:47,261][88300] Updated weights for policy 1, policy_version 25482 (0.0009) -[2023-10-15 03:15:47,507][88298] Updated weights for policy 0, policy_version 25350 (0.0007) -[2023-10-15 03:15:47,632][88300] Updated weights for policy 1, policy_version 25492 (0.0009) -[2023-10-15 03:15:47,862][88298] Updated weights for policy 0, policy_version 25360 (0.0007) -[2023-10-15 03:15:47,992][88300] Updated weights for policy 1, policy_version 25502 (0.0007) -[2023-10-15 03:15:48,237][88298] Updated weights for policy 0, policy_version 25370 (0.0008) -[2023-10-15 03:15:48,534][87330] Fps is (10 sec: 19660.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 52101120. Throughput: 0: 1731.4, 1: 1736.4. Samples: 13022896. Policy #0 lag: (min: 3.0, avg: 3.0, max: 6.0) -[2023-10-15 03:15:48,535][87330] Avg episode reward: [(0, '22.190'), (1, '22.530')] -[2023-10-15 03:15:51,998][88300] Updated weights for policy 1, policy_version 25512 (0.0008) -[2023-10-15 03:15:52,082][88298] Updated weights for policy 0, policy_version 25380 (0.0011) -[2023-10-15 03:15:52,362][88300] Updated weights for policy 1, policy_version 25522 (0.0008) -[2023-10-15 03:15:52,449][88298] Updated weights for policy 0, policy_version 25390 (0.0008) -[2023-10-15 03:15:52,735][88300] Updated weights for policy 1, policy_version 25532 (0.0007) -[2023-10-15 03:15:52,825][88298] Updated weights for policy 0, policy_version 25400 (0.0008) -[2023-10-15 03:15:53,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 52166656. Throughput: 0: 1734.2, 1: 1725.6. Samples: 13043512. Policy #0 lag: (min: 3.0, avg: 3.0, max: 6.0) -[2023-10-15 03:15:53,535][87330] Avg episode reward: [(0, '22.210'), (1, '22.430')] -[2023-10-15 03:15:56,731][88300] Updated weights for policy 1, policy_version 25542 (0.0009) -[2023-10-15 03:15:56,775][88298] Updated weights for policy 0, policy_version 25410 (0.0009) -[2023-10-15 03:15:57,098][88300] Updated weights for policy 1, policy_version 25552 (0.0010) -[2023-10-15 03:15:57,154][88298] Updated weights for policy 0, policy_version 25420 (0.0010) -[2023-10-15 03:15:57,471][88300] Updated weights for policy 1, policy_version 25562 (0.0010) -[2023-10-15 03:15:57,525][88298] Updated weights for policy 0, policy_version 25430 (0.0008) -[2023-10-15 03:15:57,896][88298] Updated weights for policy 0, policy_version 25440 (0.0008) -[2023-10-15 03:15:58,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 52232192. Throughput: 0: 1704.2, 1: 1702.2. Samples: 13062800. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-15 03:15:58,534][87330] Avg episode reward: [(0, '22.400'), (1, '22.390')] -[2023-10-15 03:16:01,318][88300] Updated weights for policy 1, policy_version 25572 (0.0009) -[2023-10-15 03:16:01,715][88300] Updated weights for policy 1, policy_version 25582 (0.0009) -[2023-10-15 03:16:02,004][88298] Updated weights for policy 0, policy_version 25450 (0.0009) -[2023-10-15 03:16:02,081][88300] Updated weights for policy 1, policy_version 25592 (0.0011) -[2023-10-15 03:16:02,373][88298] Updated weights for policy 0, policy_version 25460 (0.0008) -[2023-10-15 03:16:02,743][88298] Updated weights for policy 0, policy_version 25470 (0.0009) -[2023-10-15 03:16:03,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 52297728. Throughput: 0: 1733.6, 1: 1733.4. Samples: 13074756. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-15 03:16:03,534][87330] Avg episode reward: [(0, '22.460'), (1, '22.410')] -[2023-10-15 03:16:05,981][88300] Updated weights for policy 1, policy_version 25602 (0.0007) -[2023-10-15 03:16:06,352][88300] Updated weights for policy 1, policy_version 25612 (0.0008) -[2023-10-15 03:16:06,720][88300] Updated weights for policy 1, policy_version 25622 (0.0009) -[2023-10-15 03:16:06,730][88298] Updated weights for policy 0, policy_version 25480 (0.0010) -[2023-10-15 03:16:07,083][88300] Updated weights for policy 1, policy_version 25632 (0.0008) -[2023-10-15 03:16:07,100][88298] Updated weights for policy 0, policy_version 25490 (0.0009) -[2023-10-15 03:16:07,484][88298] Updated weights for policy 0, policy_version 25500 (0.0007) -[2023-10-15 03:16:08,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 52363264. Throughput: 0: 1720.1, 1: 1703.9. Samples: 13094380. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-15 03:16:08,534][87330] Avg episode reward: [(0, '22.350'), (1, '22.450')] -[2023-10-15 03:16:11,021][88300] Updated weights for policy 1, policy_version 25642 (0.0008) -[2023-10-15 03:16:11,387][88300] Updated weights for policy 1, policy_version 25652 (0.0010) -[2023-10-15 03:16:11,481][88298] Updated weights for policy 0, policy_version 25510 (0.0009) -[2023-10-15 03:16:11,760][88300] Updated weights for policy 1, policy_version 25662 (0.0009) -[2023-10-15 03:16:11,847][88298] Updated weights for policy 0, policy_version 25520 (0.0008) -[2023-10-15 03:16:12,221][88298] Updated weights for policy 0, policy_version 25530 (0.0008) -[2023-10-15 03:16:13,534][87330] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 52428800. Throughput: 0: 1702.7, 1: 1719.5. Samples: 13114986. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-15 03:16:13,535][87330] Avg episode reward: [(0, '22.250'), (1, '22.460')] -[2023-10-15 03:16:15,848][88300] Updated weights for policy 1, policy_version 25672 (0.0010) -[2023-10-15 03:16:15,953][88298] Updated weights for policy 0, policy_version 25540 (0.0007) -[2023-10-15 03:16:16,221][88300] Updated weights for policy 1, policy_version 25682 (0.0008) -[2023-10-15 03:16:16,320][88298] Updated weights for policy 0, policy_version 25550 (0.0007) -[2023-10-15 03:16:16,587][88300] Updated weights for policy 1, policy_version 25692 (0.0009) -[2023-10-15 03:16:16,680][88298] Updated weights for policy 0, policy_version 25560 (0.0008) -[2023-10-15 03:16:18,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 52494336. Throughput: 0: 1737.6, 1: 1719.2. Samples: 13126384. Policy #0 lag: (min: 15.0, avg: 17.7, max: 47.0) -[2023-10-15 03:16:18,535][87330] Avg episode reward: [(0, '22.230'), (1, '22.550')] -[2023-10-15 03:16:20,426][88300] Updated weights for policy 1, policy_version 25702 (0.0008) -[2023-10-15 03:16:20,671][88298] Updated weights for policy 0, policy_version 25570 (0.0007) -[2023-10-15 03:16:20,807][88300] Updated weights for policy 1, policy_version 25712 (0.0007) -[2023-10-15 03:16:21,036][88298] Updated weights for policy 0, policy_version 25580 (0.0008) -[2023-10-15 03:16:21,171][88300] Updated weights for policy 1, policy_version 25722 (0.0009) -[2023-10-15 03:16:21,408][88298] Updated weights for policy 0, policy_version 25590 (0.0008) -[2023-10-15 03:16:21,770][88298] Updated weights for policy 0, policy_version 25600 (0.0009) -[2023-10-15 03:16:23,534][87330] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 52559872. Throughput: 0: 1715.9, 1: 1708.4. Samples: 13146182. Policy #0 lag: (min: 15.0, avg: 17.7, max: 47.0) -[2023-10-15 03:16:23,534][87330] Avg episode reward: [(0, '22.260'), (1, '22.650')] -[2023-10-15 03:16:25,062][88300] Updated weights for policy 1, policy_version 25732 (0.0008) -[2023-10-15 03:16:25,428][88300] Updated weights for policy 1, policy_version 25742 (0.0009) -[2023-10-15 03:16:25,607][88298] Updated weights for policy 0, policy_version 25610 (0.0008) -[2023-10-15 03:16:25,791][88300] Updated weights for policy 1, policy_version 25752 (0.0013) -[2023-10-15 03:16:25,978][88298] Updated weights for policy 0, policy_version 25620 (0.0008) -[2023-10-15 03:16:26,353][88298] Updated weights for policy 0, policy_version 25630 (0.0010) -[2023-10-15 03:16:28,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 52625408. Throughput: 0: 1713.1, 1: 1735.2. Samples: 13167358. Policy #0 lag: (min: 15.0, avg: 17.7, max: 47.0) -[2023-10-15 03:16:28,535][87330] Avg episode reward: [(0, '22.370'), (1, '22.600')] -[2023-10-15 03:16:29,712][88300] Updated weights for policy 1, policy_version 25762 (0.0009) -[2023-10-15 03:16:30,070][88300] Updated weights for policy 1, policy_version 25772 (0.0008) -[2023-10-15 03:16:30,237][88298] Updated weights for policy 0, policy_version 25640 (0.0007) -[2023-10-15 03:16:30,436][88300] Updated weights for policy 1, policy_version 25782 (0.0007) -[2023-10-15 03:16:30,602][88298] Updated weights for policy 0, policy_version 25650 (0.0007) -[2023-10-15 03:16:30,800][88300] Updated weights for policy 1, policy_version 25792 (0.0007) -[2023-10-15 03:16:30,978][88298] Updated weights for policy 0, policy_version 25660 (0.0007) -[2023-10-15 03:16:33,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 52690944. Throughput: 0: 1719.1, 1: 1709.6. Samples: 13177184. Policy #0 lag: (min: 15.0, avg: 17.7, max: 47.0) -[2023-10-15 03:16:33,534][87330] Avg episode reward: [(0, '22.200'), (1, '22.620')] -[2023-10-15 03:16:34,879][88300] Updated weights for policy 1, policy_version 25802 (0.0008) -[2023-10-15 03:16:34,927][88298] Updated weights for policy 0, policy_version 25670 (0.0009) -[2023-10-15 03:16:35,248][88300] Updated weights for policy 1, policy_version 25812 (0.0009) -[2023-10-15 03:16:35,296][88298] Updated weights for policy 0, policy_version 25680 (0.0008) -[2023-10-15 03:16:35,608][88300] Updated weights for policy 1, policy_version 25822 (0.0009) -[2023-10-15 03:16:35,670][88298] Updated weights for policy 0, policy_version 25690 (0.0010) -[2023-10-15 03:16:38,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 52756480. Throughput: 0: 1709.8, 1: 1728.2. Samples: 13198222. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-15 03:16:38,535][87330] Avg episode reward: [(0, '22.120'), (1, '22.550')] -[2023-10-15 03:16:39,511][88300] Updated weights for policy 1, policy_version 25832 (0.0010) -[2023-10-15 03:16:39,604][88298] Updated weights for policy 0, policy_version 25700 (0.0008) -[2023-10-15 03:16:39,879][88300] Updated weights for policy 1, policy_version 25842 (0.0010) -[2023-10-15 03:16:39,983][88298] Updated weights for policy 0, policy_version 25710 (0.0009) -[2023-10-15 03:16:40,248][88300] Updated weights for policy 1, policy_version 25852 (0.0007) -[2023-10-15 03:16:40,350][88298] Updated weights for policy 0, policy_version 25720 (0.0009) -[2023-10-15 03:16:43,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 52822016. Throughput: 0: 1735.8, 1: 1746.7. Samples: 13219510. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-15 03:16:43,535][87330] Avg episode reward: [(0, '22.320'), (1, '22.520')] -[2023-10-15 03:16:44,197][88300] Updated weights for policy 1, policy_version 25862 (0.0008) -[2023-10-15 03:16:44,343][88298] Updated weights for policy 0, policy_version 25730 (0.0009) -[2023-10-15 03:16:44,565][88300] Updated weights for policy 1, policy_version 25872 (0.0007) -[2023-10-15 03:16:44,711][88298] Updated weights for policy 0, policy_version 25740 (0.0008) -[2023-10-15 03:16:44,941][88300] Updated weights for policy 1, policy_version 25882 (0.0013) -[2023-10-15 03:16:45,072][88298] Updated weights for policy 0, policy_version 25750 (0.0007) -[2023-10-15 03:16:45,443][88298] Updated weights for policy 0, policy_version 25760 (0.0007) -[2023-10-15 03:16:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 52887552. Throughput: 0: 1710.2, 1: 1715.8. Samples: 13228928. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-15 03:16:48,534][87330] Avg episode reward: [(0, '22.530'), (1, '22.360')] -[2023-10-15 03:16:48,978][88300] Updated weights for policy 1, policy_version 25892 (0.0007) -[2023-10-15 03:16:49,385][88300] Updated weights for policy 1, policy_version 25902 (0.0008) -[2023-10-15 03:16:49,494][88298] Updated weights for policy 0, policy_version 25770 (0.0007) -[2023-10-15 03:16:49,750][88300] Updated weights for policy 1, policy_version 25912 (0.0007) -[2023-10-15 03:16:49,862][88298] Updated weights for policy 0, policy_version 25780 (0.0007) -[2023-10-15 03:16:50,227][88298] Updated weights for policy 0, policy_version 25790 (0.0008) -[2023-10-15 03:16:53,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 52953088. Throughput: 0: 1719.5, 1: 1736.7. Samples: 13249908. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-15 03:16:53,534][87330] Avg episode reward: [(0, '22.520'), (1, '22.370')] -[2023-10-15 03:16:53,630][88300] Updated weights for policy 1, policy_version 25922 (0.0009) -[2023-10-15 03:16:53,999][88300] Updated weights for policy 1, policy_version 25932 (0.0008) -[2023-10-15 03:16:54,118][88298] Updated weights for policy 0, policy_version 25800 (0.0010) -[2023-10-15 03:16:54,368][88300] Updated weights for policy 1, policy_version 25942 (0.0009) -[2023-10-15 03:16:54,493][88298] Updated weights for policy 0, policy_version 25810 (0.0009) -[2023-10-15 03:16:54,738][88300] Updated weights for policy 1, policy_version 25952 (0.0007) -[2023-10-15 03:16:54,859][88298] Updated weights for policy 0, policy_version 25820 (0.0010) -[2023-10-15 03:16:58,534][87330] Fps is (10 sec: 13106.4, 60 sec: 13107.1, 300 sec: 13773.6). Total num frames: 53018624. Throughput: 0: 1741.9, 1: 1734.5. Samples: 13271428. Policy #0 lag: (min: 31.0, avg: 35.5, max: 63.0) -[2023-10-15 03:16:58,536][87330] Avg episode reward: [(0, '22.350'), (1, '22.340')] -[2023-10-15 03:16:58,546][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000025824_26443776.pth... -[2023-10-15 03:16:58,582][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000024224_24805376.pth -[2023-10-15 03:16:58,818][88300] Updated weights for policy 1, policy_version 25962 (0.0008) -[2023-10-15 03:16:58,922][88298] Updated weights for policy 0, policy_version 25830 (0.0007) -[2023-10-15 03:16:59,189][88300] Updated weights for policy 1, policy_version 25972 (0.0007) -[2023-10-15 03:16:59,297][88298] Updated weights for policy 0, policy_version 25840 (0.0007) -[2023-10-15 03:16:59,554][88300] Updated weights for policy 1, policy_version 25982 (0.0008) -[2023-10-15 03:16:59,629][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000025984_26607616.pth... -[2023-10-15 03:16:59,669][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000024352_24936448.pth -[2023-10-15 03:16:59,671][88298] Updated weights for policy 0, policy_version 25850 (0.0007) -[2023-10-15 03:17:03,338][88300] Updated weights for policy 1, policy_version 25992 (0.0007) -[2023-10-15 03:17:03,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 53084160. Throughput: 0: 1705.7, 1: 1726.3. Samples: 13280826. Policy #0 lag: (min: 31.0, avg: 35.5, max: 63.0) -[2023-10-15 03:17:03,535][87330] Avg episode reward: [(0, '22.450'), (1, '22.270')] -[2023-10-15 03:17:03,663][88298] Updated weights for policy 0, policy_version 25860 (0.0007) -[2023-10-15 03:17:03,698][88300] Updated weights for policy 1, policy_version 26002 (0.0008) -[2023-10-15 03:17:04,035][88298] Updated weights for policy 0, policy_version 25870 (0.0009) -[2023-10-15 03:17:04,062][88300] Updated weights for policy 1, policy_version 26012 (0.0008) -[2023-10-15 03:17:04,399][88298] Updated weights for policy 0, policy_version 25880 (0.0009) -[2023-10-15 03:17:08,117][88300] Updated weights for policy 1, policy_version 26022 (0.0009) -[2023-10-15 03:17:08,351][88298] Updated weights for policy 0, policy_version 25890 (0.0009) -[2023-10-15 03:17:08,474][88300] Updated weights for policy 1, policy_version 26032 (0.0008) -[2023-10-15 03:17:08,534][87330] Fps is (10 sec: 13108.0, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 53149696. Throughput: 0: 1728.4, 1: 1737.2. Samples: 13302136. Policy #0 lag: (min: 31.0, avg: 35.5, max: 63.0) -[2023-10-15 03:17:08,534][87330] Avg episode reward: [(0, '22.470'), (1, '22.310')] -[2023-10-15 03:17:08,714][88298] Updated weights for policy 0, policy_version 25900 (0.0008) -[2023-10-15 03:17:08,844][88300] Updated weights for policy 1, policy_version 26042 (0.0007) -[2023-10-15 03:17:09,084][88298] Updated weights for policy 0, policy_version 25910 (0.0008) -[2023-10-15 03:17:09,457][88298] Updated weights for policy 0, policy_version 25920 (0.0009) -[2023-10-15 03:17:12,748][88300] Updated weights for policy 1, policy_version 26052 (0.0008) -[2023-10-15 03:17:13,124][88300] Updated weights for policy 1, policy_version 26062 (0.0009) -[2023-10-15 03:17:13,296][88298] Updated weights for policy 0, policy_version 25930 (0.0007) -[2023-10-15 03:17:13,491][88300] Updated weights for policy 1, policy_version 26072 (0.0009) -[2023-10-15 03:17:13,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13107.3, 300 sec: 13773.7). Total num frames: 53215232. Throughput: 0: 1734.7, 1: 1726.6. Samples: 13323114. Policy #0 lag: (min: 31.0, avg: 35.5, max: 63.0) -[2023-10-15 03:17:13,534][87330] Avg episode reward: [(0, '22.450'), (1, '22.340')] -[2023-10-15 03:17:13,672][88298] Updated weights for policy 0, policy_version 25940 (0.0007) -[2023-10-15 03:17:14,037][88298] Updated weights for policy 0, policy_version 25950 (0.0008) -[2023-10-15 03:17:17,347][88300] Updated weights for policy 1, policy_version 26082 (0.0009) -[2023-10-15 03:17:17,721][88300] Updated weights for policy 1, policy_version 26092 (0.0009) -[2023-10-15 03:17:17,845][88298] Updated weights for policy 0, policy_version 25960 (0.0009) -[2023-10-15 03:17:18,092][88300] Updated weights for policy 1, policy_version 26102 (0.0008) -[2023-10-15 03:17:18,206][88298] Updated weights for policy 0, policy_version 25970 (0.0007) -[2023-10-15 03:17:18,461][88300] Updated weights for policy 1, policy_version 26112 (0.0008) -[2023-10-15 03:17:18,534][87330] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 53313536. Throughput: 0: 1720.1, 1: 1741.8. Samples: 13332970. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 03:17:18,534][87330] Avg episode reward: [(0, '22.270'), (1, '22.510')] -[2023-10-15 03:17:18,581][88298] Updated weights for policy 0, policy_version 25980 (0.0007) -[2023-10-15 03:17:22,311][88300] Updated weights for policy 1, policy_version 26122 (0.0008) -[2023-10-15 03:17:22,586][88298] Updated weights for policy 0, policy_version 25990 (0.0008) -[2023-10-15 03:17:22,677][88300] Updated weights for policy 1, policy_version 26132 (0.0007) -[2023-10-15 03:17:22,951][88298] Updated weights for policy 0, policy_version 26000 (0.0008) -[2023-10-15 03:17:23,050][88300] Updated weights for policy 1, policy_version 26142 (0.0007) -[2023-10-15 03:17:23,324][88298] Updated weights for policy 0, policy_version 26010 (0.0009) -[2023-10-15 03:17:23,534][87330] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 53379072. Throughput: 0: 1731.6, 1: 1736.3. Samples: 13354276. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 03:17:23,534][87330] Avg episode reward: [(0, '22.290'), (1, '22.520')] -[2023-10-15 03:17:26,850][88300] Updated weights for policy 1, policy_version 26152 (0.0008) -[2023-10-15 03:17:27,203][88300] Updated weights for policy 1, policy_version 26162 (0.0007) -[2023-10-15 03:17:27,304][88298] Updated weights for policy 0, policy_version 26020 (0.0007) -[2023-10-15 03:17:27,568][88300] Updated weights for policy 1, policy_version 26172 (0.0008) -[2023-10-15 03:17:27,675][88298] Updated weights for policy 0, policy_version 26030 (0.0009) -[2023-10-15 03:17:28,037][88298] Updated weights for policy 0, policy_version 26040 (0.0008) -[2023-10-15 03:17:28,534][87330] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 53477376. Throughput: 0: 1716.5, 1: 1711.8. Samples: 13373786. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 03:17:28,534][87330] Avg episode reward: [(0, '22.490'), (1, '22.480')] -[2023-10-15 03:17:31,407][88300] Updated weights for policy 1, policy_version 26182 (0.0008) -[2023-10-15 03:17:31,773][88300] Updated weights for policy 1, policy_version 26192 (0.0007) -[2023-10-15 03:17:32,089][88298] Updated weights for policy 0, policy_version 26050 (0.0009) -[2023-10-15 03:17:32,139][88300] Updated weights for policy 1, policy_version 26202 (0.0008) -[2023-10-15 03:17:32,462][88298] Updated weights for policy 0, policy_version 26060 (0.0008) -[2023-10-15 03:17:32,832][88298] Updated weights for policy 0, policy_version 26070 (0.0007) -[2023-10-15 03:17:33,209][88298] Updated weights for policy 0, policy_version 26080 (0.0008) -[2023-10-15 03:17:33,534][87330] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 53542912. Throughput: 0: 1728.5, 1: 1746.2. Samples: 13385290. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-10-15 03:17:33,535][87330] Avg episode reward: [(0, '22.570'), (1, '22.720')] -[2023-10-15 03:17:36,111][88300] Updated weights for policy 1, policy_version 26212 (0.0008) -[2023-10-15 03:17:36,479][88300] Updated weights for policy 1, policy_version 26222 (0.0008) -[2023-10-15 03:17:36,846][88300] Updated weights for policy 1, policy_version 26232 (0.0008) -[2023-10-15 03:17:37,262][88298] Updated weights for policy 0, policy_version 26090 (0.0009) -[2023-10-15 03:17:37,641][88298] Updated weights for policy 0, policy_version 26100 (0.0010) -[2023-10-15 03:17:38,011][88298] Updated weights for policy 0, policy_version 26110 (0.0010) -[2023-10-15 03:17:38,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 53608448. Throughput: 0: 1729.2, 1: 1725.8. Samples: 13405382. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-10-15 03:17:38,535][87330] Avg episode reward: [(0, '22.590'), (1, '22.730')] -[2023-10-15 03:17:40,637][88300] Updated weights for policy 1, policy_version 26242 (0.0008) -[2023-10-15 03:17:41,007][88300] Updated weights for policy 1, policy_version 26252 (0.0007) -[2023-10-15 03:17:41,363][88300] Updated weights for policy 1, policy_version 26262 (0.0009) -[2023-10-15 03:17:41,691][88298] Updated weights for policy 0, policy_version 26120 (0.0009) -[2023-10-15 03:17:41,727][88300] Updated weights for policy 1, policy_version 26272 (0.0009) -[2023-10-15 03:17:42,062][88298] Updated weights for policy 0, policy_version 26130 (0.0007) -[2023-10-15 03:17:42,424][88298] Updated weights for policy 0, policy_version 26140 (0.0008) -[2023-10-15 03:17:43,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 53673984. Throughput: 0: 1697.1, 1: 1732.1. Samples: 13425738. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-10-15 03:17:43,535][87330] Avg episode reward: [(0, '22.580'), (1, '22.660')] -[2023-10-15 03:17:45,564][88300] Updated weights for policy 1, policy_version 26282 (0.0007) -[2023-10-15 03:17:45,936][88300] Updated weights for policy 1, policy_version 26292 (0.0007) -[2023-10-15 03:17:46,280][88298] Updated weights for policy 0, policy_version 26150 (0.0009) -[2023-10-15 03:17:46,301][88300] Updated weights for policy 1, policy_version 26302 (0.0008) -[2023-10-15 03:17:46,644][88298] Updated weights for policy 0, policy_version 26160 (0.0007) -[2023-10-15 03:17:47,022][88298] Updated weights for policy 0, policy_version 26170 (0.0007) -[2023-10-15 03:17:48,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 53739520. Throughput: 0: 1734.1, 1: 1735.7. Samples: 13436964. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-10-15 03:17:48,534][87330] Avg episode reward: [(0, '22.730'), (1, '22.640')] -[2023-10-15 03:17:50,003][88300] Updated weights for policy 1, policy_version 26312 (0.0007) -[2023-10-15 03:17:50,374][88300] Updated weights for policy 1, policy_version 26322 (0.0007) -[2023-10-15 03:17:50,733][88300] Updated weights for policy 1, policy_version 26332 (0.0008) -[2023-10-15 03:17:50,963][88298] Updated weights for policy 0, policy_version 26180 (0.0008) -[2023-10-15 03:17:51,337][88298] Updated weights for policy 0, policy_version 26190 (0.0009) -[2023-10-15 03:17:51,705][88298] Updated weights for policy 0, policy_version 26200 (0.0007) -[2023-10-15 03:17:53,534][87330] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 53805056. Throughput: 0: 1714.6, 1: 1734.4. Samples: 13457344. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:17:53,534][87330] Avg episode reward: [(0, '22.790'), (1, '22.640')] -[2023-10-15 03:17:54,637][88300] Updated weights for policy 1, policy_version 26342 (0.0008) -[2023-10-15 03:17:54,996][88300] Updated weights for policy 1, policy_version 26352 (0.0008) -[2023-10-15 03:17:55,358][88300] Updated weights for policy 1, policy_version 26362 (0.0008) -[2023-10-15 03:17:55,527][88298] Updated weights for policy 0, policy_version 26210 (0.0007) -[2023-10-15 03:17:55,900][88298] Updated weights for policy 0, policy_version 26220 (0.0008) -[2023-10-15 03:17:56,261][88298] Updated weights for policy 0, policy_version 26230 (0.0008) -[2023-10-15 03:17:56,633][88298] Updated weights for policy 0, policy_version 26240 (0.0008) -[2023-10-15 03:17:58,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.6, 300 sec: 13773.7). Total num frames: 53870592. Throughput: 0: 1710.0, 1: 1750.0. Samples: 13478810. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:17:58,534][87330] Avg episode reward: [(0, '22.760'), (1, '22.620')] -[2023-10-15 03:17:59,208][88300] Updated weights for policy 1, policy_version 26372 (0.0007) -[2023-10-15 03:17:59,583][88300] Updated weights for policy 1, policy_version 26382 (0.0007) -[2023-10-15 03:17:59,958][88300] Updated weights for policy 1, policy_version 26392 (0.0009) -[2023-10-15 03:18:00,548][88298] Updated weights for policy 0, policy_version 26250 (0.0009) -[2023-10-15 03:18:00,928][88298] Updated weights for policy 0, policy_version 26260 (0.0009) -[2023-10-15 03:18:01,300][88298] Updated weights for policy 0, policy_version 26270 (0.0009) -[2023-10-15 03:18:03,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 53936128. Throughput: 0: 1727.7, 1: 1741.7. Samples: 13489094. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:18:03,534][87330] Avg episode reward: [(0, '22.580'), (1, '22.620')] -[2023-10-15 03:18:03,861][88300] Updated weights for policy 1, policy_version 26402 (0.0009) -[2023-10-15 03:18:04,232][88300] Updated weights for policy 1, policy_version 26412 (0.0009) -[2023-10-15 03:18:04,598][88300] Updated weights for policy 1, policy_version 26422 (0.0007) -[2023-10-15 03:18:04,966][88300] Updated weights for policy 1, policy_version 26432 (0.0008) -[2023-10-15 03:18:05,417][88298] Updated weights for policy 0, policy_version 26280 (0.0008) -[2023-10-15 03:18:05,781][88298] Updated weights for policy 0, policy_version 26290 (0.0008) -[2023-10-15 03:18:06,148][88298] Updated weights for policy 0, policy_version 26300 (0.0007) -[2023-10-15 03:18:08,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 54001664. Throughput: 0: 1709.6, 1: 1746.9. Samples: 13509818. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:18:08,535][87330] Avg episode reward: [(0, '22.600'), (1, '22.510')] -[2023-10-15 03:18:08,883][88300] Updated weights for policy 1, policy_version 26442 (0.0008) -[2023-10-15 03:18:09,248][88300] Updated weights for policy 1, policy_version 26452 (0.0008) -[2023-10-15 03:18:09,627][88300] Updated weights for policy 1, policy_version 26462 (0.0008) -[2023-10-15 03:18:10,031][88298] Updated weights for policy 0, policy_version 26310 (0.0008) -[2023-10-15 03:18:10,397][88298] Updated weights for policy 0, policy_version 26320 (0.0009) -[2023-10-15 03:18:10,759][88298] Updated weights for policy 0, policy_version 26330 (0.0007) -[2023-10-15 03:18:13,449][88300] Updated weights for policy 1, policy_version 26472 (0.0008) -[2023-10-15 03:18:13,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 54067200. Throughput: 0: 1730.4, 1: 1772.3. Samples: 13531408. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:18:13,534][87330] Avg episode reward: [(0, '22.510'), (1, '22.500')] -[2023-10-15 03:18:13,817][88300] Updated weights for policy 1, policy_version 26482 (0.0010) -[2023-10-15 03:18:14,181][88300] Updated weights for policy 1, policy_version 26492 (0.0010) -[2023-10-15 03:18:14,761][88298] Updated weights for policy 0, policy_version 26340 (0.0008) -[2023-10-15 03:18:15,127][88298] Updated weights for policy 0, policy_version 26350 (0.0009) -[2023-10-15 03:18:15,496][88298] Updated weights for policy 0, policy_version 26360 (0.0008) -[2023-10-15 03:18:18,107][88300] Updated weights for policy 1, policy_version 26502 (0.0008) -[2023-10-15 03:18:18,484][88300] Updated weights for policy 1, policy_version 26512 (0.0008) -[2023-10-15 03:18:18,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 54132736. Throughput: 0: 1720.7, 1: 1741.6. Samples: 13541094. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:18:18,535][87330] Avg episode reward: [(0, '22.460'), (1, '22.570')] -[2023-10-15 03:18:18,862][88300] Updated weights for policy 1, policy_version 26522 (0.0008) -[2023-10-15 03:18:19,466][88298] Updated weights for policy 0, policy_version 26370 (0.0009) -[2023-10-15 03:18:19,837][88298] Updated weights for policy 0, policy_version 26380 (0.0007) -[2023-10-15 03:18:20,198][88298] Updated weights for policy 0, policy_version 26390 (0.0007) -[2023-10-15 03:18:20,571][88298] Updated weights for policy 0, policy_version 26400 (0.0007) -[2023-10-15 03:18:22,793][88300] Updated weights for policy 1, policy_version 26532 (0.0008) -[2023-10-15 03:18:23,186][88300] Updated weights for policy 1, policy_version 26542 (0.0007) -[2023-10-15 03:18:23,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 54198272. Throughput: 0: 1723.9, 1: 1776.5. Samples: 13562898. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:18:23,535][87330] Avg episode reward: [(0, '22.480'), (1, '22.580')] -[2023-10-15 03:18:23,563][88300] Updated weights for policy 1, policy_version 26552 (0.0009) -[2023-10-15 03:18:24,461][88298] Updated weights for policy 0, policy_version 26410 (0.0010) -[2023-10-15 03:18:24,844][88298] Updated weights for policy 0, policy_version 26420 (0.0008) -[2023-10-15 03:18:25,208][88298] Updated weights for policy 0, policy_version 26430 (0.0007) -[2023-10-15 03:18:27,235][88300] Updated weights for policy 1, policy_version 26562 (0.0010) -[2023-10-15 03:18:27,598][88300] Updated weights for policy 1, policy_version 26572 (0.0009) -[2023-10-15 03:18:27,972][88300] Updated weights for policy 1, policy_version 26582 (0.0008) -[2023-10-15 03:18:28,333][88300] Updated weights for policy 1, policy_version 26592 (0.0008) -[2023-10-15 03:18:28,534][87330] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 54296576. Throughput: 0: 1750.0, 1: 1744.5. Samples: 13582988. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:18:28,535][87330] Avg episode reward: [(0, '22.530'), (1, '22.570')] -[2023-10-15 03:18:29,228][88298] Updated weights for policy 0, policy_version 26440 (0.0009) -[2023-10-15 03:18:29,598][88298] Updated weights for policy 0, policy_version 26450 (0.0008) -[2023-10-15 03:18:29,971][88298] Updated weights for policy 0, policy_version 26460 (0.0009) -[2023-10-15 03:18:32,353][88300] Updated weights for policy 1, policy_version 26602 (0.0011) -[2023-10-15 03:18:32,716][88300] Updated weights for policy 1, policy_version 26612 (0.0010) -[2023-10-15 03:18:33,086][88300] Updated weights for policy 1, policy_version 26622 (0.0009) -[2023-10-15 03:18:33,534][87330] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 54362112. Throughput: 0: 1711.9, 1: 1764.3. Samples: 13593392. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:18:33,535][87330] Avg episode reward: [(0, '22.720'), (1, '22.490')] -[2023-10-15 03:18:33,767][88298] Updated weights for policy 0, policy_version 26470 (0.0009) -[2023-10-15 03:18:34,141][88298] Updated weights for policy 0, policy_version 26480 (0.0009) -[2023-10-15 03:18:34,521][88298] Updated weights for policy 0, policy_version 26490 (0.0007) -[2023-10-15 03:18:36,875][88300] Updated weights for policy 1, policy_version 26632 (0.0008) -[2023-10-15 03:18:37,245][88300] Updated weights for policy 1, policy_version 26642 (0.0008) -[2023-10-15 03:18:37,616][88300] Updated weights for policy 1, policy_version 26652 (0.0008) -[2023-10-15 03:18:38,459][88298] Updated weights for policy 0, policy_version 26500 (0.0008) -[2023-10-15 03:18:38,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 54427648. Throughput: 0: 1734.7, 1: 1755.2. Samples: 13614392. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:18:38,535][87330] Avg episode reward: [(0, '22.720'), (1, '22.590')] -[2023-10-15 03:18:38,826][88298] Updated weights for policy 0, policy_version 26510 (0.0008) -[2023-10-15 03:18:39,202][88298] Updated weights for policy 0, policy_version 26520 (0.0007) -[2023-10-15 03:18:41,386][88300] Updated weights for policy 1, policy_version 26662 (0.0008) -[2023-10-15 03:18:41,750][88300] Updated weights for policy 1, policy_version 26672 (0.0008) -[2023-10-15 03:18:42,118][88300] Updated weights for policy 1, policy_version 26682 (0.0008) -[2023-10-15 03:18:42,936][88298] Updated weights for policy 0, policy_version 26530 (0.0008) -[2023-10-15 03:18:43,299][88298] Updated weights for policy 0, policy_version 26540 (0.0008) -[2023-10-15 03:18:43,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 54493184. Throughput: 0: 1746.2, 1: 1742.8. Samples: 13635818. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:18:43,534][87330] Avg episode reward: [(0, '22.740'), (1, '22.610')] -[2023-10-15 03:18:43,683][88298] Updated weights for policy 0, policy_version 26550 (0.0010) -[2023-10-15 03:18:44,044][88298] Updated weights for policy 0, policy_version 26560 (0.0007) -[2023-10-15 03:18:45,875][88300] Updated weights for policy 1, policy_version 26692 (0.0007) -[2023-10-15 03:18:46,240][88300] Updated weights for policy 1, policy_version 26702 (0.0008) -[2023-10-15 03:18:46,605][88300] Updated weights for policy 1, policy_version 26712 (0.0008) -[2023-10-15 03:18:47,971][88298] Updated weights for policy 0, policy_version 26570 (0.0007) -[2023-10-15 03:18:48,343][88298] Updated weights for policy 0, policy_version 26580 (0.0007) -[2023-10-15 03:18:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 54558720. Throughput: 0: 1728.6, 1: 1761.6. Samples: 13646154. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:18:48,535][87330] Avg episode reward: [(0, '22.790'), (1, '22.610')] -[2023-10-15 03:18:48,711][88298] Updated weights for policy 0, policy_version 26590 (0.0009) -[2023-10-15 03:18:50,601][88300] Updated weights for policy 1, policy_version 26722 (0.0010) -[2023-10-15 03:18:50,963][88300] Updated weights for policy 1, policy_version 26732 (0.0008) -[2023-10-15 03:18:51,328][88300] Updated weights for policy 1, policy_version 26742 (0.0008) -[2023-10-15 03:18:51,701][88300] Updated weights for policy 1, policy_version 26752 (0.0008) -[2023-10-15 03:18:52,790][88298] Updated weights for policy 0, policy_version 26600 (0.0008) -[2023-10-15 03:18:53,161][88298] Updated weights for policy 0, policy_version 26610 (0.0007) -[2023-10-15 03:18:53,526][88298] Updated weights for policy 0, policy_version 26620 (0.0009) -[2023-10-15 03:18:53,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 54624256. Throughput: 0: 1748.0, 1: 1749.7. Samples: 13667216. Policy #0 lag: (min: 7.0, avg: 9.9, max: 39.0) -[2023-10-15 03:18:53,535][87330] Avg episode reward: [(0, '22.790'), (1, '22.610')] -[2023-10-15 03:18:55,347][88300] Updated weights for policy 1, policy_version 26762 (0.0009) -[2023-10-15 03:18:55,720][88300] Updated weights for policy 1, policy_version 26772 (0.0008) -[2023-10-15 03:18:56,103][88300] Updated weights for policy 1, policy_version 26782 (0.0009) -[2023-10-15 03:18:57,465][88298] Updated weights for policy 0, policy_version 26630 (0.0008) -[2023-10-15 03:18:57,840][88298] Updated weights for policy 0, policy_version 26640 (0.0009) -[2023-10-15 03:18:58,210][88298] Updated weights for policy 0, policy_version 26650 (0.0010) -[2023-10-15 03:18:58,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 54722560. Throughput: 0: 1732.5, 1: 1753.5. Samples: 13688278. Policy #0 lag: (min: 7.0, avg: 9.9, max: 39.0) -[2023-10-15 03:18:58,534][87330] Avg episode reward: [(0, '22.770'), (1, '22.310')] -[2023-10-15 03:18:58,546][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000026656_27295744.pth... -[2023-10-15 03:18:58,546][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000026784_27426816.pth... -[2023-10-15 03:18:58,579][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000025024_25624576.pth -[2023-10-15 03:18:58,581][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000025152_25755648.pth -[2023-10-15 03:19:00,033][88300] Updated weights for policy 1, policy_version 26792 (0.0008) -[2023-10-15 03:19:00,397][88300] Updated weights for policy 1, policy_version 26802 (0.0009) -[2023-10-15 03:19:00,761][88300] Updated weights for policy 1, policy_version 26812 (0.0008) -[2023-10-15 03:19:02,088][88298] Updated weights for policy 0, policy_version 26660 (0.0009) -[2023-10-15 03:19:02,462][88298] Updated weights for policy 0, policy_version 26670 (0.0008) -[2023-10-15 03:19:02,833][88298] Updated weights for policy 0, policy_version 26680 (0.0010) -[2023-10-15 03:19:03,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 54788096. Throughput: 0: 1746.4, 1: 1748.2. Samples: 13698348. Policy #0 lag: (min: 7.0, avg: 9.9, max: 39.0) -[2023-10-15 03:19:03,535][87330] Avg episode reward: [(0, '22.730'), (1, '22.440')] -[2023-10-15 03:19:04,623][88300] Updated weights for policy 1, policy_version 26822 (0.0009) -[2023-10-15 03:19:04,984][88300] Updated weights for policy 1, policy_version 26832 (0.0007) -[2023-10-15 03:19:05,358][88300] Updated weights for policy 1, policy_version 26842 (0.0008) -[2023-10-15 03:19:06,689][88298] Updated weights for policy 0, policy_version 26690 (0.0008) -[2023-10-15 03:19:07,062][88298] Updated weights for policy 0, policy_version 26700 (0.0007) -[2023-10-15 03:19:07,434][88298] Updated weights for policy 0, policy_version 26710 (0.0008) -[2023-10-15 03:19:07,799][88298] Updated weights for policy 0, policy_version 26720 (0.0009) -[2023-10-15 03:19:08,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 54853632. Throughput: 0: 1737.4, 1: 1747.9. Samples: 13719738. Policy #0 lag: (min: 33.0, avg: 53.7, max: 56.0) -[2023-10-15 03:19:08,534][87330] Avg episode reward: [(0, '22.720'), (1, '22.450')] -[2023-10-15 03:19:09,287][88300] Updated weights for policy 1, policy_version 26852 (0.0008) -[2023-10-15 03:19:09,696][88300] Updated weights for policy 1, policy_version 26862 (0.0008) -[2023-10-15 03:19:10,061][88300] Updated weights for policy 1, policy_version 26872 (0.0009) -[2023-10-15 03:19:11,643][88298] Updated weights for policy 0, policy_version 26730 (0.0007) -[2023-10-15 03:19:12,021][88298] Updated weights for policy 0, policy_version 26740 (0.0007) -[2023-10-15 03:19:12,400][88298] Updated weights for policy 0, policy_version 26750 (0.0007) -[2023-10-15 03:19:13,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 54919168. Throughput: 0: 1715.0, 1: 1773.4. Samples: 13739966. Policy #0 lag: (min: 33.0, avg: 53.7, max: 56.0) -[2023-10-15 03:19:13,534][87330] Avg episode reward: [(0, '22.740'), (1, '22.410')] -[2023-10-15 03:19:14,025][88300] Updated weights for policy 1, policy_version 26882 (0.0009) -[2023-10-15 03:19:14,389][88300] Updated weights for policy 1, policy_version 26892 (0.0010) -[2023-10-15 03:19:14,763][88300] Updated weights for policy 1, policy_version 26902 (0.0009) -[2023-10-15 03:19:15,127][88300] Updated weights for policy 1, policy_version 26912 (0.0009) -[2023-10-15 03:19:16,255][88298] Updated weights for policy 0, policy_version 26760 (0.0008) -[2023-10-15 03:19:16,629][88298] Updated weights for policy 0, policy_version 26770 (0.0008) -[2023-10-15 03:19:16,996][88298] Updated weights for policy 0, policy_version 26780 (0.0007) -[2023-10-15 03:19:18,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 54984704. Throughput: 0: 1750.5, 1: 1743.5. Samples: 13750622. Policy #0 lag: (min: 33.0, avg: 53.7, max: 56.0) -[2023-10-15 03:19:18,534][87330] Avg episode reward: [(0, '22.790'), (1, '22.200')] -[2023-10-15 03:19:18,988][88300] Updated weights for policy 1, policy_version 26922 (0.0008) -[2023-10-15 03:19:19,363][88300] Updated weights for policy 1, policy_version 26932 (0.0007) -[2023-10-15 03:19:19,726][88300] Updated weights for policy 1, policy_version 26942 (0.0009) -[2023-10-15 03:19:20,956][88298] Updated weights for policy 0, policy_version 26790 (0.0008) -[2023-10-15 03:19:21,327][88298] Updated weights for policy 0, policy_version 26800 (0.0008) -[2023-10-15 03:19:21,697][88298] Updated weights for policy 0, policy_version 26810 (0.0008) -[2023-10-15 03:19:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 55050240. Throughput: 0: 1726.5, 1: 1759.5. Samples: 13771260. Policy #0 lag: (min: 33.0, avg: 53.7, max: 56.0) -[2023-10-15 03:19:23,534][87330] Avg episode reward: [(0, '22.810'), (1, '22.180')] -[2023-10-15 03:19:23,537][88300] Updated weights for policy 1, policy_version 26952 (0.0010) -[2023-10-15 03:19:23,899][88300] Updated weights for policy 1, policy_version 26962 (0.0009) -[2023-10-15 03:19:24,274][88300] Updated weights for policy 1, policy_version 26972 (0.0008) -[2023-10-15 03:19:25,662][88298] Updated weights for policy 0, policy_version 26820 (0.0008) -[2023-10-15 03:19:26,036][88298] Updated weights for policy 0, policy_version 26830 (0.0008) -[2023-10-15 03:19:26,407][88298] Updated weights for policy 0, policy_version 26840 (0.0008) -[2023-10-15 03:19:28,393][88300] Updated weights for policy 1, policy_version 26982 (0.0010) -[2023-10-15 03:19:28,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 55115776. Throughput: 0: 1710.9, 1: 1768.2. Samples: 13792378. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) -[2023-10-15 03:19:28,534][87330] Avg episode reward: [(0, '22.790'), (1, '22.120')] -[2023-10-15 03:19:28,755][88300] Updated weights for policy 1, policy_version 26992 (0.0009) -[2023-10-15 03:19:29,120][88300] Updated weights for policy 1, policy_version 27002 (0.0010) -[2023-10-15 03:19:30,451][88298] Updated weights for policy 0, policy_version 26850 (0.0009) -[2023-10-15 03:19:30,825][88298] Updated weights for policy 0, policy_version 26860 (0.0008) -[2023-10-15 03:19:31,197][88298] Updated weights for policy 0, policy_version 26870 (0.0009) -[2023-10-15 03:19:31,556][88298] Updated weights for policy 0, policy_version 26880 (0.0010) -[2023-10-15 03:19:32,773][88300] Updated weights for policy 1, policy_version 27012 (0.0010) -[2023-10-15 03:19:33,140][88300] Updated weights for policy 1, policy_version 27022 (0.0007) -[2023-10-15 03:19:33,509][88300] Updated weights for policy 1, policy_version 27032 (0.0007) -[2023-10-15 03:19:33,534][87330] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 55181312. Throughput: 0: 1734.9, 1: 1751.9. Samples: 13803058. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) -[2023-10-15 03:19:33,535][87330] Avg episode reward: [(0, '22.800'), (1, '22.200')] -[2023-10-15 03:19:35,477][88298] Updated weights for policy 0, policy_version 26890 (0.0007) -[2023-10-15 03:19:35,846][88298] Updated weights for policy 0, policy_version 26900 (0.0008) -[2023-10-15 03:19:36,213][88298] Updated weights for policy 0, policy_version 26910 (0.0008) -[2023-10-15 03:19:37,386][88300] Updated weights for policy 1, policy_version 27042 (0.0007) -[2023-10-15 03:19:37,758][88300] Updated weights for policy 1, policy_version 27052 (0.0007) -[2023-10-15 03:19:38,125][88300] Updated weights for policy 1, policy_version 27062 (0.0008) -[2023-10-15 03:19:38,496][88300] Updated weights for policy 1, policy_version 27072 (0.0009) -[2023-10-15 03:19:38,534][87330] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 55279616. Throughput: 0: 1713.3, 1: 1764.6. Samples: 13823722. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) -[2023-10-15 03:19:38,535][87330] Avg episode reward: [(0, '22.800'), (1, '22.170')] -[2023-10-15 03:19:40,220][88298] Updated weights for policy 0, policy_version 26920 (0.0008) -[2023-10-15 03:19:40,584][88298] Updated weights for policy 0, policy_version 26930 (0.0007) -[2023-10-15 03:19:40,957][88298] Updated weights for policy 0, policy_version 26940 (0.0007) -[2023-10-15 03:19:42,339][88300] Updated weights for policy 1, policy_version 27082 (0.0008) -[2023-10-15 03:19:42,706][88300] Updated weights for policy 1, policy_version 27092 (0.0010) -[2023-10-15 03:19:43,080][88300] Updated weights for policy 1, policy_version 27102 (0.0007) -[2023-10-15 03:19:43,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 55345152. Throughput: 0: 1728.5, 1: 1733.6. Samples: 13844070. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) -[2023-10-15 03:19:43,535][87330] Avg episode reward: [(0, '22.820'), (1, '22.160')] -[2023-10-15 03:19:44,803][88298] Updated weights for policy 0, policy_version 26950 (0.0009) -[2023-10-15 03:19:45,175][88298] Updated weights for policy 0, policy_version 26960 (0.0008) -[2023-10-15 03:19:45,555][88298] Updated weights for policy 0, policy_version 26970 (0.0009) -[2023-10-15 03:19:47,002][88300] Updated weights for policy 1, policy_version 27112 (0.0008) -[2023-10-15 03:19:47,364][88300] Updated weights for policy 1, policy_version 27122 (0.0007) -[2023-10-15 03:19:47,735][88300] Updated weights for policy 1, policy_version 27132 (0.0008) -[2023-10-15 03:19:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 55410688. Throughput: 0: 1715.1, 1: 1766.7. Samples: 13855030. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:19:48,535][87330] Avg episode reward: [(0, '22.820'), (1, '22.340')] -[2023-10-15 03:19:49,421][88298] Updated weights for policy 0, policy_version 26980 (0.0009) -[2023-10-15 03:19:49,790][88298] Updated weights for policy 0, policy_version 26990 (0.0010) -[2023-10-15 03:19:50,164][88298] Updated weights for policy 0, policy_version 27000 (0.0008) -[2023-10-15 03:19:51,558][88300] Updated weights for policy 1, policy_version 27142 (0.0009) -[2023-10-15 03:19:51,923][88300] Updated weights for policy 1, policy_version 27152 (0.0011) -[2023-10-15 03:19:52,286][88300] Updated weights for policy 1, policy_version 27162 (0.0010) -[2023-10-15 03:19:53,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 55476224. Throughput: 0: 1721.3, 1: 1742.7. Samples: 13875616. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:19:53,535][87330] Avg episode reward: [(0, '22.850'), (1, '22.370')] -[2023-10-15 03:19:53,942][88298] Updated weights for policy 0, policy_version 27010 (0.0008) -[2023-10-15 03:19:54,307][88298] Updated weights for policy 0, policy_version 27020 (0.0011) -[2023-10-15 03:19:54,686][88298] Updated weights for policy 0, policy_version 27030 (0.0008) -[2023-10-15 03:19:55,051][88298] Updated weights for policy 0, policy_version 27040 (0.0009) -[2023-10-15 03:19:56,259][88300] Updated weights for policy 1, policy_version 27172 (0.0010) -[2023-10-15 03:19:56,624][88300] Updated weights for policy 1, policy_version 27182 (0.0009) -[2023-10-15 03:19:56,996][88300] Updated weights for policy 1, policy_version 27192 (0.0009) -[2023-10-15 03:19:58,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 55541760. Throughput: 0: 1750.3, 1: 1730.3. Samples: 13896590. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:19:58,534][87330] Avg episode reward: [(0, '22.860'), (1, '22.350')] -[2023-10-15 03:19:59,119][88298] Updated weights for policy 0, policy_version 27050 (0.0008) -[2023-10-15 03:19:59,499][88298] Updated weights for policy 0, policy_version 27060 (0.0008) -[2023-10-15 03:19:59,868][88298] Updated weights for policy 0, policy_version 27070 (0.0009) -[2023-10-15 03:20:00,914][88300] Updated weights for policy 1, policy_version 27202 (0.0008) -[2023-10-15 03:20:01,284][88300] Updated weights for policy 1, policy_version 27212 (0.0008) -[2023-10-15 03:20:01,653][88300] Updated weights for policy 1, policy_version 27222 (0.0007) -[2023-10-15 03:20:02,021][88300] Updated weights for policy 1, policy_version 27232 (0.0009) -[2023-10-15 03:20:03,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 55607296. Throughput: 0: 1713.2, 1: 1756.1. Samples: 13906744. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:20:03,535][87330] Avg episode reward: [(0, '22.810'), (1, '22.550')] -[2023-10-15 03:20:03,859][88298] Updated weights for policy 0, policy_version 27080 (0.0009) -[2023-10-15 03:20:04,232][88298] Updated weights for policy 0, policy_version 27090 (0.0008) -[2023-10-15 03:20:04,610][88298] Updated weights for policy 0, policy_version 27100 (0.0008) -[2023-10-15 03:20:05,697][88300] Updated weights for policy 1, policy_version 27242 (0.0008) -[2023-10-15 03:20:06,061][88300] Updated weights for policy 1, policy_version 27252 (0.0008) -[2023-10-15 03:20:06,424][88300] Updated weights for policy 1, policy_version 27262 (0.0007) -[2023-10-15 03:20:08,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 55672832. Throughput: 0: 1736.0, 1: 1734.0. Samples: 13927412. Policy #0 lag: (min: 8.0, avg: 31.4, max: 40.0) -[2023-10-15 03:20:08,535][87330] Avg episode reward: [(0, '22.710'), (1, '22.560')] -[2023-10-15 03:20:08,538][88298] Updated weights for policy 0, policy_version 27110 (0.0009) -[2023-10-15 03:20:08,908][88298] Updated weights for policy 0, policy_version 27120 (0.0007) -[2023-10-15 03:20:09,282][88298] Updated weights for policy 0, policy_version 27130 (0.0010) -[2023-10-15 03:20:10,294][88300] Updated weights for policy 1, policy_version 27272 (0.0007) -[2023-10-15 03:20:10,659][88300] Updated weights for policy 1, policy_version 27282 (0.0009) -[2023-10-15 03:20:11,030][88300] Updated weights for policy 1, policy_version 27292 (0.0008) -[2023-10-15 03:20:13,160][88298] Updated weights for policy 0, policy_version 27140 (0.0007) -[2023-10-15 03:20:13,527][88298] Updated weights for policy 0, policy_version 27150 (0.0007) -[2023-10-15 03:20:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 55738368. Throughput: 0: 1748.7, 1: 1741.8. Samples: 13949452. Policy #0 lag: (min: 8.0, avg: 31.4, max: 40.0) -[2023-10-15 03:20:13,535][87330] Avg episode reward: [(0, '22.680'), (1, '22.600')] -[2023-10-15 03:20:13,898][88298] Updated weights for policy 0, policy_version 27160 (0.0009) -[2023-10-15 03:20:14,904][88300] Updated weights for policy 1, policy_version 27302 (0.0007) -[2023-10-15 03:20:15,274][88300] Updated weights for policy 1, policy_version 27312 (0.0009) -[2023-10-15 03:20:15,640][88300] Updated weights for policy 1, policy_version 27322 (0.0009) -[2023-10-15 03:20:17,713][88298] Updated weights for policy 0, policy_version 27170 (0.0008) -[2023-10-15 03:20:18,088][88298] Updated weights for policy 0, policy_version 27180 (0.0008) -[2023-10-15 03:20:18,458][88298] Updated weights for policy 0, policy_version 27190 (0.0007) -[2023-10-15 03:20:18,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.2, 300 sec: 13884.7). Total num frames: 55803904. Throughput: 0: 1725.3, 1: 1737.0. Samples: 13958864. Policy #0 lag: (min: 8.0, avg: 31.4, max: 40.0) -[2023-10-15 03:20:18,535][87330] Avg episode reward: [(0, '22.660'), (1, '22.430')] -[2023-10-15 03:20:18,823][88298] Updated weights for policy 0, policy_version 27200 (0.0008) -[2023-10-15 03:20:19,583][88300] Updated weights for policy 1, policy_version 27332 (0.0011) -[2023-10-15 03:20:19,950][88300] Updated weights for policy 1, policy_version 27342 (0.0011) -[2023-10-15 03:20:20,319][88300] Updated weights for policy 1, policy_version 27352 (0.0011) -[2023-10-15 03:20:22,843][88298] Updated weights for policy 0, policy_version 27210 (0.0007) -[2023-10-15 03:20:23,221][88298] Updated weights for policy 0, policy_version 27220 (0.0009) -[2023-10-15 03:20:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 55869440. Throughput: 0: 1743.4, 1: 1735.4. Samples: 13980268. Policy #0 lag: (min: 8.0, avg: 31.4, max: 40.0) -[2023-10-15 03:20:23,534][87330] Avg episode reward: [(0, '22.690'), (1, '22.400')] -[2023-10-15 03:20:23,590][88298] Updated weights for policy 0, policy_version 27230 (0.0010) -[2023-10-15 03:20:24,245][88300] Updated weights for policy 1, policy_version 27362 (0.0008) -[2023-10-15 03:20:24,610][88300] Updated weights for policy 1, policy_version 27372 (0.0009) -[2023-10-15 03:20:24,987][88300] Updated weights for policy 1, policy_version 27382 (0.0008) -[2023-10-15 03:20:25,349][88300] Updated weights for policy 1, policy_version 27392 (0.0009) -[2023-10-15 03:20:27,429][88298] Updated weights for policy 0, policy_version 27240 (0.0010) -[2023-10-15 03:20:27,796][88298] Updated weights for policy 0, policy_version 27250 (0.0009) -[2023-10-15 03:20:28,162][88298] Updated weights for policy 0, policy_version 27260 (0.0011) -[2023-10-15 03:20:28,534][87330] Fps is (10 sec: 16384.6, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 55967744. Throughput: 0: 1729.3, 1: 1768.4. Samples: 14001468. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:20:28,534][87330] Avg episode reward: [(0, '22.670'), (1, '22.400')] -[2023-10-15 03:20:29,381][88300] Updated weights for policy 1, policy_version 27402 (0.0008) -[2023-10-15 03:20:29,746][88300] Updated weights for policy 1, policy_version 27412 (0.0008) -[2023-10-15 03:20:30,101][88300] Updated weights for policy 1, policy_version 27422 (0.0008) -[2023-10-15 03:20:32,019][88298] Updated weights for policy 0, policy_version 27270 (0.0010) -[2023-10-15 03:20:32,396][88298] Updated weights for policy 0, policy_version 27280 (0.0009) -[2023-10-15 03:20:32,775][88298] Updated weights for policy 0, policy_version 27290 (0.0011) -[2023-10-15 03:20:33,534][87330] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 56033280. Throughput: 0: 1744.6, 1: 1734.5. Samples: 14011588. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:20:33,534][87330] Avg episode reward: [(0, '22.640'), (1, '22.430')] -[2023-10-15 03:20:33,992][88300] Updated weights for policy 1, policy_version 27432 (0.0011) -[2023-10-15 03:20:34,363][88300] Updated weights for policy 1, policy_version 27442 (0.0009) -[2023-10-15 03:20:34,733][88300] Updated weights for policy 1, policy_version 27452 (0.0008) -[2023-10-15 03:20:36,781][88298] Updated weights for policy 0, policy_version 27300 (0.0010) -[2023-10-15 03:20:37,155][88298] Updated weights for policy 0, policy_version 27310 (0.0010) -[2023-10-15 03:20:37,521][88298] Updated weights for policy 0, policy_version 27320 (0.0010) -[2023-10-15 03:20:38,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 56098816. Throughput: 0: 1738.7, 1: 1756.0. Samples: 14032878. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:20:38,535][87330] Avg episode reward: [(0, '22.770'), (1, '22.420')] -[2023-10-15 03:20:38,705][88300] Updated weights for policy 1, policy_version 27462 (0.0009) -[2023-10-15 03:20:39,070][88300] Updated weights for policy 1, policy_version 27472 (0.0008) -[2023-10-15 03:20:39,446][88300] Updated weights for policy 1, policy_version 27482 (0.0010) -[2023-10-15 03:20:41,430][88298] Updated weights for policy 0, policy_version 27330 (0.0010) -[2023-10-15 03:20:41,792][88298] Updated weights for policy 0, policy_version 27340 (0.0008) -[2023-10-15 03:20:42,161][88298] Updated weights for policy 0, policy_version 27350 (0.0009) -[2023-10-15 03:20:42,535][88298] Updated weights for policy 0, policy_version 27360 (0.0008) -[2023-10-15 03:20:43,243][88300] Updated weights for policy 1, policy_version 27492 (0.0009) -[2023-10-15 03:20:43,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 56164352. Throughput: 0: 1709.0, 1: 1764.2. Samples: 14052882. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:20:43,534][87330] Avg episode reward: [(0, '22.810'), (1, '22.400')] -[2023-10-15 03:20:43,637][88300] Updated weights for policy 1, policy_version 27502 (0.0011) -[2023-10-15 03:20:43,998][88300] Updated weights for policy 1, policy_version 27512 (0.0010) -[2023-10-15 03:20:46,689][88298] Updated weights for policy 0, policy_version 27370 (0.0010) -[2023-10-15 03:20:47,065][88298] Updated weights for policy 0, policy_version 27380 (0.0010) -[2023-10-15 03:20:47,440][88298] Updated weights for policy 0, policy_version 27390 (0.0008) -[2023-10-15 03:20:48,074][88300] Updated weights for policy 1, policy_version 27522 (0.0010) -[2023-10-15 03:20:48,453][88300] Updated weights for policy 1, policy_version 27532 (0.0011) -[2023-10-15 03:20:48,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 56229888. Throughput: 0: 1746.2, 1: 1740.7. Samples: 14063656. Policy #0 lag: (min: 1.0, avg: 12.9, max: 33.0) -[2023-10-15 03:20:48,534][87330] Avg episode reward: [(0, '22.820'), (1, '22.390')] -[2023-10-15 03:20:48,814][88300] Updated weights for policy 1, policy_version 27542 (0.0010) -[2023-10-15 03:20:49,185][88300] Updated weights for policy 1, policy_version 27552 (0.0009) -[2023-10-15 03:20:51,274][88298] Updated weights for policy 0, policy_version 27400 (0.0008) -[2023-10-15 03:20:51,651][88298] Updated weights for policy 0, policy_version 27410 (0.0007) -[2023-10-15 03:20:52,017][88298] Updated weights for policy 0, policy_version 27420 (0.0008) -[2023-10-15 03:20:53,103][88300] Updated weights for policy 1, policy_version 27562 (0.0007) -[2023-10-15 03:20:53,467][88300] Updated weights for policy 1, policy_version 27572 (0.0008) -[2023-10-15 03:20:53,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 56295424. Throughput: 0: 1723.6, 1: 1758.3. Samples: 14084098. Policy #0 lag: (min: 1.0, avg: 12.9, max: 33.0) -[2023-10-15 03:20:53,535][87330] Avg episode reward: [(0, '22.770'), (1, '22.440')] -[2023-10-15 03:20:53,826][88300] Updated weights for policy 1, policy_version 27582 (0.0008) -[2023-10-15 03:20:55,939][88298] Updated weights for policy 0, policy_version 27430 (0.0008) -[2023-10-15 03:20:56,311][88298] Updated weights for policy 0, policy_version 27440 (0.0008) -[2023-10-15 03:20:56,668][88298] Updated weights for policy 0, policy_version 27450 (0.0009) -[2023-10-15 03:20:57,667][88300] Updated weights for policy 1, policy_version 27592 (0.0010) -[2023-10-15 03:20:58,041][88300] Updated weights for policy 1, policy_version 27602 (0.0009) -[2023-10-15 03:20:58,404][88300] Updated weights for policy 1, policy_version 27612 (0.0007) -[2023-10-15 03:20:58,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 56360960. Throughput: 0: 1708.0, 1: 1731.6. Samples: 14104234. Policy #0 lag: (min: 1.0, avg: 12.9, max: 33.0) -[2023-10-15 03:20:58,535][87330] Avg episode reward: [(0, '22.710'), (1, '22.490')] -[2023-10-15 03:20:58,545][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000027456_28114944.pth... -[2023-10-15 03:20:58,552][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000027616_28278784.pth... -[2023-10-15 03:20:58,582][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000025984_26607616.pth -[2023-10-15 03:20:58,586][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000025824_26443776.pth -[2023-10-15 03:21:00,631][88298] Updated weights for policy 0, policy_version 27460 (0.0008) -[2023-10-15 03:21:01,008][88298] Updated weights for policy 0, policy_version 27470 (0.0008) -[2023-10-15 03:21:01,383][88298] Updated weights for policy 0, policy_version 27480 (0.0008) -[2023-10-15 03:21:02,365][88300] Updated weights for policy 1, policy_version 27622 (0.0007) -[2023-10-15 03:21:02,724][88300] Updated weights for policy 1, policy_version 27632 (0.0008) -[2023-10-15 03:21:03,098][88300] Updated weights for policy 1, policy_version 27642 (0.0009) -[2023-10-15 03:21:03,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 56459264. Throughput: 0: 1730.1, 1: 1750.0. Samples: 14115468. Policy #0 lag: (min: 1.0, avg: 12.9, max: 33.0) -[2023-10-15 03:21:03,535][87330] Avg episode reward: [(0, '22.690'), (1, '22.410')] -[2023-10-15 03:21:05,269][88298] Updated weights for policy 0, policy_version 27490 (0.0009) -[2023-10-15 03:21:05,642][88298] Updated weights for policy 0, policy_version 27500 (0.0010) -[2023-10-15 03:21:06,028][88298] Updated weights for policy 0, policy_version 27510 (0.0007) -[2023-10-15 03:21:06,405][88298] Updated weights for policy 0, policy_version 27520 (0.0009) -[2023-10-15 03:21:06,899][88300] Updated weights for policy 1, policy_version 27652 (0.0009) -[2023-10-15 03:21:07,259][88300] Updated weights for policy 1, policy_version 27662 (0.0008) -[2023-10-15 03:21:07,636][88300] Updated weights for policy 1, policy_version 27672 (0.0007) -[2023-10-15 03:21:08,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 56524800. Throughput: 0: 1710.7, 1: 1741.5. Samples: 14135614. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-15 03:21:08,535][87330] Avg episode reward: [(0, '22.720'), (1, '22.370')] -[2023-10-15 03:21:10,324][88298] Updated weights for policy 0, policy_version 27530 (0.0009) -[2023-10-15 03:21:10,703][88298] Updated weights for policy 0, policy_version 27540 (0.0009) -[2023-10-15 03:21:11,071][88298] Updated weights for policy 0, policy_version 27550 (0.0011) -[2023-10-15 03:21:11,481][88300] Updated weights for policy 1, policy_version 27682 (0.0009) -[2023-10-15 03:21:11,854][88300] Updated weights for policy 1, policy_version 27692 (0.0007) -[2023-10-15 03:21:12,217][88300] Updated weights for policy 1, policy_version 27702 (0.0007) -[2023-10-15 03:21:12,577][88300] Updated weights for policy 1, policy_version 27712 (0.0008) -[2023-10-15 03:21:13,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 56590336. Throughput: 0: 1726.7, 1: 1717.4. Samples: 14156454. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-15 03:21:13,534][87330] Avg episode reward: [(0, '22.690'), (1, '22.380')] -[2023-10-15 03:21:14,916][88298] Updated weights for policy 0, policy_version 27560 (0.0010) -[2023-10-15 03:21:15,290][88298] Updated weights for policy 0, policy_version 27570 (0.0008) -[2023-10-15 03:21:15,660][88298] Updated weights for policy 0, policy_version 27580 (0.0008) -[2023-10-15 03:21:16,378][88300] Updated weights for policy 1, policy_version 27722 (0.0008) -[2023-10-15 03:21:16,745][88300] Updated weights for policy 1, policy_version 27732 (0.0007) -[2023-10-15 03:21:17,110][88300] Updated weights for policy 1, policy_version 27742 (0.0009) -[2023-10-15 03:21:18,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 56655872. Throughput: 0: 1710.4, 1: 1750.4. Samples: 14167326. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-15 03:21:18,535][87330] Avg episode reward: [(0, '22.690'), (1, '22.380')] -[2023-10-15 03:21:19,629][88298] Updated weights for policy 0, policy_version 27590 (0.0009) -[2023-10-15 03:21:19,987][88298] Updated weights for policy 0, policy_version 27600 (0.0010) -[2023-10-15 03:21:20,362][88298] Updated weights for policy 0, policy_version 27610 (0.0010) -[2023-10-15 03:21:21,018][88300] Updated weights for policy 1, policy_version 27752 (0.0010) -[2023-10-15 03:21:21,389][88300] Updated weights for policy 1, policy_version 27762 (0.0009) -[2023-10-15 03:21:21,752][88300] Updated weights for policy 1, policy_version 27772 (0.0010) -[2023-10-15 03:21:23,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 56721408. Throughput: 0: 1715.8, 1: 1722.3. Samples: 14187590. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-15 03:21:23,534][87330] Avg episode reward: [(0, '22.690'), (1, '22.350')] -[2023-10-15 03:21:24,168][88298] Updated weights for policy 0, policy_version 27620 (0.0010) -[2023-10-15 03:21:24,542][88298] Updated weights for policy 0, policy_version 27630 (0.0009) -[2023-10-15 03:21:24,914][88298] Updated weights for policy 0, policy_version 27640 (0.0008) -[2023-10-15 03:21:25,746][88300] Updated weights for policy 1, policy_version 27782 (0.0008) -[2023-10-15 03:21:26,121][88300] Updated weights for policy 1, policy_version 27792 (0.0008) -[2023-10-15 03:21:26,495][88300] Updated weights for policy 1, policy_version 27802 (0.0007) -[2023-10-15 03:21:28,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 56786944. Throughput: 0: 1748.3, 1: 1723.4. Samples: 14209108. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-15 03:21:28,534][87330] Avg episode reward: [(0, '22.720'), (1, '22.480')] -[2023-10-15 03:21:28,810][88298] Updated weights for policy 0, policy_version 27650 (0.0011) -[2023-10-15 03:21:29,189][88298] Updated weights for policy 0, policy_version 27660 (0.0007) -[2023-10-15 03:21:29,558][88298] Updated weights for policy 0, policy_version 27670 (0.0008) -[2023-10-15 03:21:29,927][88298] Updated weights for policy 0, policy_version 27680 (0.0010) -[2023-10-15 03:21:30,466][88300] Updated weights for policy 1, policy_version 27812 (0.0008) -[2023-10-15 03:21:30,860][88300] Updated weights for policy 1, policy_version 27822 (0.0009) -[2023-10-15 03:21:31,229][88300] Updated weights for policy 1, policy_version 27832 (0.0010) -[2023-10-15 03:21:33,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 56852480. Throughput: 0: 1716.1, 1: 1734.0. Samples: 14218910. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-15 03:21:33,534][87330] Avg episode reward: [(0, '22.840'), (1, '22.590')] -[2023-10-15 03:21:33,871][88298] Updated weights for policy 0, policy_version 27690 (0.0007) -[2023-10-15 03:21:34,244][88298] Updated weights for policy 0, policy_version 27700 (0.0009) -[2023-10-15 03:21:34,616][88298] Updated weights for policy 0, policy_version 27710 (0.0008) -[2023-10-15 03:21:35,058][88300] Updated weights for policy 1, policy_version 27842 (0.0008) -[2023-10-15 03:21:35,422][88300] Updated weights for policy 1, policy_version 27852 (0.0007) -[2023-10-15 03:21:35,786][88300] Updated weights for policy 1, policy_version 27862 (0.0008) -[2023-10-15 03:21:36,161][88300] Updated weights for policy 1, policy_version 27872 (0.0007) -[2023-10-15 03:21:38,532][88298] Updated weights for policy 0, policy_version 27720 (0.0007) -[2023-10-15 03:21:38,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 56918016. Throughput: 0: 1739.6, 1: 1725.7. Samples: 14240036. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-15 03:21:38,535][87330] Avg episode reward: [(0, '22.810'), (1, '22.620')] -[2023-10-15 03:21:38,908][88298] Updated weights for policy 0, policy_version 27730 (0.0007) -[2023-10-15 03:21:39,281][88298] Updated weights for policy 0, policy_version 27740 (0.0008) -[2023-10-15 03:21:40,001][88300] Updated weights for policy 1, policy_version 27882 (0.0009) -[2023-10-15 03:21:40,360][88300] Updated weights for policy 1, policy_version 27892 (0.0009) -[2023-10-15 03:21:40,729][88300] Updated weights for policy 1, policy_version 27902 (0.0008) -[2023-10-15 03:21:43,168][88298] Updated weights for policy 0, policy_version 27750 (0.0008) -[2023-10-15 03:21:43,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 56983552. Throughput: 0: 1750.2, 1: 1743.3. Samples: 14261440. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-15 03:21:43,534][87330] Avg episode reward: [(0, '22.830'), (1, '22.580')] -[2023-10-15 03:21:43,538][88298] Updated weights for policy 0, policy_version 27760 (0.0008) -[2023-10-15 03:21:43,912][88298] Updated weights for policy 0, policy_version 27770 (0.0008) -[2023-10-15 03:21:44,726][88300] Updated weights for policy 1, policy_version 27912 (0.0010) -[2023-10-15 03:21:45,097][88300] Updated weights for policy 1, policy_version 27922 (0.0010) -[2023-10-15 03:21:45,462][88300] Updated weights for policy 1, policy_version 27932 (0.0009) -[2023-10-15 03:21:47,872][88298] Updated weights for policy 0, policy_version 27780 (0.0010) -[2023-10-15 03:21:48,261][88298] Updated weights for policy 0, policy_version 27790 (0.0009) -[2023-10-15 03:21:48,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 57049088. Throughput: 0: 1730.6, 1: 1724.1. Samples: 14270930. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-15 03:21:48,534][87330] Avg episode reward: [(0, '22.830'), (1, '22.620')] -[2023-10-15 03:21:48,631][88298] Updated weights for policy 0, policy_version 27800 (0.0008) -[2023-10-15 03:21:49,544][88300] Updated weights for policy 1, policy_version 27942 (0.0009) -[2023-10-15 03:21:49,908][88300] Updated weights for policy 1, policy_version 27952 (0.0008) -[2023-10-15 03:21:50,273][88300] Updated weights for policy 1, policy_version 27962 (0.0007) -[2023-10-15 03:21:52,564][88298] Updated weights for policy 0, policy_version 27810 (0.0008) -[2023-10-15 03:21:52,928][88298] Updated weights for policy 0, policy_version 27820 (0.0008) -[2023-10-15 03:21:53,299][88298] Updated weights for policy 0, policy_version 27830 (0.0008) -[2023-10-15 03:21:53,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 57114624. Throughput: 0: 1748.5, 1: 1732.0. Samples: 14292236. Policy #0 lag: (min: 9.0, avg: 19.4, max: 41.0) -[2023-10-15 03:21:53,535][87330] Avg episode reward: [(0, '22.810'), (1, '22.650')] -[2023-10-15 03:21:53,669][88298] Updated weights for policy 0, policy_version 27840 (0.0008) -[2023-10-15 03:21:54,118][88300] Updated weights for policy 1, policy_version 27972 (0.0010) -[2023-10-15 03:21:54,486][88300] Updated weights for policy 1, policy_version 27982 (0.0009) -[2023-10-15 03:21:54,849][88300] Updated weights for policy 1, policy_version 27992 (0.0008) -[2023-10-15 03:21:57,518][88298] Updated weights for policy 0, policy_version 27850 (0.0007) -[2023-10-15 03:21:57,885][88298] Updated weights for policy 0, policy_version 27860 (0.0007) -[2023-10-15 03:21:58,250][88298] Updated weights for policy 0, policy_version 27870 (0.0007) -[2023-10-15 03:21:58,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 57212928. Throughput: 0: 1731.2, 1: 1746.8. Samples: 14312964. Policy #0 lag: (min: 9.0, avg: 19.4, max: 41.0) -[2023-10-15 03:21:58,534][87330] Avg episode reward: [(0, '22.810'), (1, '22.540')] -[2023-10-15 03:21:58,762][88300] Updated weights for policy 1, policy_version 28002 (0.0008) -[2023-10-15 03:21:59,145][88300] Updated weights for policy 1, policy_version 28012 (0.0010) -[2023-10-15 03:21:59,514][88300] Updated weights for policy 1, policy_version 28022 (0.0008) -[2023-10-15 03:21:59,894][88300] Updated weights for policy 1, policy_version 28032 (0.0008) -[2023-10-15 03:22:02,171][88298] Updated weights for policy 0, policy_version 27880 (0.0008) -[2023-10-15 03:22:02,543][88298] Updated weights for policy 0, policy_version 27890 (0.0010) -[2023-10-15 03:22:02,928][88298] Updated weights for policy 0, policy_version 27900 (0.0009) -[2023-10-15 03:22:03,534][87330] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 57278464. Throughput: 0: 1746.4, 1: 1716.0. Samples: 14323130. Policy #0 lag: (min: 9.0, avg: 19.4, max: 41.0) -[2023-10-15 03:22:03,535][87330] Avg episode reward: [(0, '22.810'), (1, '22.510')] -[2023-10-15 03:22:03,682][88300] Updated weights for policy 1, policy_version 28042 (0.0007) -[2023-10-15 03:22:04,058][88300] Updated weights for policy 1, policy_version 28052 (0.0008) -[2023-10-15 03:22:04,435][88300] Updated weights for policy 1, policy_version 28062 (0.0009) -[2023-10-15 03:22:06,787][88298] Updated weights for policy 0, policy_version 27910 (0.0011) -[2023-10-15 03:22:07,153][88298] Updated weights for policy 0, policy_version 27920 (0.0011) -[2023-10-15 03:22:07,526][88298] Updated weights for policy 0, policy_version 27930 (0.0007) -[2023-10-15 03:22:08,139][88300] Updated weights for policy 1, policy_version 28072 (0.0010) -[2023-10-15 03:22:08,508][88300] Updated weights for policy 1, policy_version 28082 (0.0008) -[2023-10-15 03:22:08,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 57344000. Throughput: 0: 1741.9, 1: 1746.4. Samples: 14344566. Policy #0 lag: (min: 31.0, avg: 31.9, max: 51.0) -[2023-10-15 03:22:08,535][87330] Avg episode reward: [(0, '22.860'), (1, '22.510')] -[2023-10-15 03:22:08,881][88300] Updated weights for policy 1, policy_version 28092 (0.0007) -[2023-10-15 03:22:11,400][88298] Updated weights for policy 0, policy_version 27940 (0.0008) -[2023-10-15 03:22:11,765][88298] Updated weights for policy 0, policy_version 27950 (0.0008) -[2023-10-15 03:22:12,140][88298] Updated weights for policy 0, policy_version 27960 (0.0007) -[2023-10-15 03:22:12,751][88300] Updated weights for policy 1, policy_version 28102 (0.0008) -[2023-10-15 03:22:13,116][88300] Updated weights for policy 1, policy_version 28112 (0.0007) -[2023-10-15 03:22:13,484][88300] Updated weights for policy 1, policy_version 28122 (0.0007) -[2023-10-15 03:22:13,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 57409536. Throughput: 0: 1712.4, 1: 1736.4. Samples: 14364304. Policy #0 lag: (min: 31.0, avg: 31.9, max: 51.0) -[2023-10-15 03:22:13,535][87330] Avg episode reward: [(0, '22.850'), (1, '22.610')] -[2023-10-15 03:22:16,009][88298] Updated weights for policy 0, policy_version 27970 (0.0007) -[2023-10-15 03:22:16,390][88298] Updated weights for policy 0, policy_version 27980 (0.0009) -[2023-10-15 03:22:16,755][88298] Updated weights for policy 0, policy_version 27990 (0.0010) -[2023-10-15 03:22:17,126][88298] Updated weights for policy 0, policy_version 28000 (0.0008) -[2023-10-15 03:22:17,483][88300] Updated weights for policy 1, policy_version 28132 (0.0008) -[2023-10-15 03:22:17,879][88300] Updated weights for policy 1, policy_version 28142 (0.0008) -[2023-10-15 03:22:18,243][88300] Updated weights for policy 1, policy_version 28152 (0.0010) -[2023-10-15 03:22:18,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 57475072. Throughput: 0: 1745.7, 1: 1744.1. Samples: 14375954. Policy #0 lag: (min: 31.0, avg: 31.9, max: 51.0) -[2023-10-15 03:22:18,534][87330] Avg episode reward: [(0, '22.860'), (1, '22.610')] -[2023-10-15 03:22:21,194][88298] Updated weights for policy 0, policy_version 28010 (0.0008) -[2023-10-15 03:22:21,567][88298] Updated weights for policy 0, policy_version 28020 (0.0010) -[2023-10-15 03:22:21,933][88298] Updated weights for policy 0, policy_version 28030 (0.0008) -[2023-10-15 03:22:22,070][88300] Updated weights for policy 1, policy_version 28162 (0.0008) -[2023-10-15 03:22:22,432][88300] Updated weights for policy 1, policy_version 28172 (0.0007) -[2023-10-15 03:22:22,802][88300] Updated weights for policy 1, policy_version 28182 (0.0009) -[2023-10-15 03:22:23,161][88300] Updated weights for policy 1, policy_version 28192 (0.0010) -[2023-10-15 03:22:23,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 57573376. Throughput: 0: 1726.5, 1: 1745.2. Samples: 14396260. Policy #0 lag: (min: 31.0, avg: 31.9, max: 51.0) -[2023-10-15 03:22:23,535][87330] Avg episode reward: [(0, '22.840'), (1, '22.600')] -[2023-10-15 03:22:25,670][88298] Updated weights for policy 0, policy_version 28040 (0.0008) -[2023-10-15 03:22:26,053][88298] Updated weights for policy 0, policy_version 28050 (0.0010) -[2023-10-15 03:22:26,420][88298] Updated weights for policy 0, policy_version 28060 (0.0010) -[2023-10-15 03:22:27,036][88300] Updated weights for policy 1, policy_version 28202 (0.0010) -[2023-10-15 03:22:27,398][88300] Updated weights for policy 1, policy_version 28212 (0.0009) -[2023-10-15 03:22:27,760][88300] Updated weights for policy 1, policy_version 28222 (0.0009) -[2023-10-15 03:22:28,534][87330] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 57638912. Throughput: 0: 1725.4, 1: 1725.2. Samples: 14416716. Policy #0 lag: (min: 31.0, avg: 31.9, max: 51.0) -[2023-10-15 03:22:28,535][87330] Avg episode reward: [(0, '22.830'), (1, '22.710')] -[2023-10-15 03:22:30,243][88298] Updated weights for policy 0, policy_version 28070 (0.0010) -[2023-10-15 03:22:30,624][88298] Updated weights for policy 0, policy_version 28080 (0.0008) -[2023-10-15 03:22:31,000][88298] Updated weights for policy 0, policy_version 28090 (0.0008) -[2023-10-15 03:22:31,656][88300] Updated weights for policy 1, policy_version 28232 (0.0008) -[2023-10-15 03:22:32,031][88300] Updated weights for policy 1, policy_version 28242 (0.0007) -[2023-10-15 03:22:32,387][88300] Updated weights for policy 1, policy_version 28252 (0.0010) -[2023-10-15 03:22:33,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 57704448. Throughput: 0: 1734.1, 1: 1757.9. Samples: 14428070. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-15 03:22:33,535][87330] Avg episode reward: [(0, '22.840'), (1, '22.730')] -[2023-10-15 03:22:34,942][88298] Updated weights for policy 0, policy_version 28100 (0.0009) -[2023-10-15 03:22:35,315][88298] Updated weights for policy 0, policy_version 28110 (0.0008) -[2023-10-15 03:22:35,681][88298] Updated weights for policy 0, policy_version 28120 (0.0009) -[2023-10-15 03:22:36,352][88300] Updated weights for policy 1, policy_version 28262 (0.0010) -[2023-10-15 03:22:36,728][88300] Updated weights for policy 1, policy_version 28272 (0.0008) -[2023-10-15 03:22:37,089][88300] Updated weights for policy 1, policy_version 28282 (0.0008) -[2023-10-15 03:22:38,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 57769984. Throughput: 0: 1723.8, 1: 1732.5. Samples: 14447766. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-15 03:22:38,534][87330] Avg episode reward: [(0, '22.800'), (1, '22.690')] -[2023-10-15 03:22:39,785][88298] Updated weights for policy 0, policy_version 28130 (0.0009) -[2023-10-15 03:22:40,155][88298] Updated weights for policy 0, policy_version 28140 (0.0010) -[2023-10-15 03:22:40,533][88298] Updated weights for policy 0, policy_version 28150 (0.0010) -[2023-10-15 03:22:40,904][88298] Updated weights for policy 0, policy_version 28160 (0.0009) -[2023-10-15 03:22:41,120][88300] Updated weights for policy 1, policy_version 28292 (0.0011) -[2023-10-15 03:22:41,484][88300] Updated weights for policy 1, policy_version 28302 (0.0009) -[2023-10-15 03:22:41,851][88300] Updated weights for policy 1, policy_version 28312 (0.0007) -[2023-10-15 03:22:43,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 57835520. Throughput: 0: 1734.8, 1: 1734.7. Samples: 14469092. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-15 03:22:43,534][87330] Avg episode reward: [(0, '22.770'), (1, '22.570')] -[2023-10-15 03:22:44,743][88298] Updated weights for policy 0, policy_version 28170 (0.0007) -[2023-10-15 03:22:45,115][88298] Updated weights for policy 0, policy_version 28180 (0.0007) -[2023-10-15 03:22:45,487][88298] Updated weights for policy 0, policy_version 28190 (0.0007) -[2023-10-15 03:22:45,749][88300] Updated weights for policy 1, policy_version 28322 (0.0008) -[2023-10-15 03:22:46,118][88300] Updated weights for policy 1, policy_version 28332 (0.0011) -[2023-10-15 03:22:46,498][88300] Updated weights for policy 1, policy_version 28342 (0.0010) -[2023-10-15 03:22:46,865][88300] Updated weights for policy 1, policy_version 28352 (0.0009) -[2023-10-15 03:22:48,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 57901056. Throughput: 0: 1716.7, 1: 1756.1. Samples: 14479404. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-15 03:22:48,534][87330] Avg episode reward: [(0, '22.740'), (1, '22.560')] -[2023-10-15 03:22:49,440][88298] Updated weights for policy 0, policy_version 28200 (0.0008) -[2023-10-15 03:22:49,805][88298] Updated weights for policy 0, policy_version 28210 (0.0008) -[2023-10-15 03:22:50,172][88298] Updated weights for policy 0, policy_version 28220 (0.0007) -[2023-10-15 03:22:50,926][88300] Updated weights for policy 1, policy_version 28362 (0.0008) -[2023-10-15 03:22:51,293][88300] Updated weights for policy 1, policy_version 28372 (0.0009) -[2023-10-15 03:22:51,660][88300] Updated weights for policy 1, policy_version 28382 (0.0007) -[2023-10-15 03:22:53,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 57966592. Throughput: 0: 1727.8, 1: 1729.3. Samples: 14500138. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-15 03:22:53,535][87330] Avg episode reward: [(0, '22.750'), (1, '22.520')] -[2023-10-15 03:22:54,077][88298] Updated weights for policy 0, policy_version 28230 (0.0010) -[2023-10-15 03:22:54,441][88298] Updated weights for policy 0, policy_version 28240 (0.0010) -[2023-10-15 03:22:54,822][88298] Updated weights for policy 0, policy_version 28250 (0.0009) -[2023-10-15 03:22:55,580][88300] Updated weights for policy 1, policy_version 28392 (0.0007) -[2023-10-15 03:22:55,941][88300] Updated weights for policy 1, policy_version 28402 (0.0009) -[2023-10-15 03:22:56,316][88300] Updated weights for policy 1, policy_version 28412 (0.0008) -[2023-10-15 03:22:58,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 58032128. Throughput: 0: 1756.2, 1: 1748.0. Samples: 14521994. Policy #0 lag: (min: 26.0, avg: 26.1, max: 33.0) -[2023-10-15 03:22:58,534][87330] Avg episode reward: [(0, '22.760'), (1, '22.530')] -[2023-10-15 03:22:58,546][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000028416_29097984.pth... -[2023-10-15 03:22:58,579][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000026784_27426816.pth -[2023-10-15 03:22:58,602][88298] Updated weights for policy 0, policy_version 28260 (0.0009) -[2023-10-15 03:22:58,983][88298] Updated weights for policy 0, policy_version 28270 (0.0010) -[2023-10-15 03:22:59,359][88298] Updated weights for policy 0, policy_version 28280 (0.0010) -[2023-10-15 03:22:59,658][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000028288_28966912.pth... -[2023-10-15 03:22:59,687][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000026656_27295744.pth -[2023-10-15 03:22:59,911][88300] Updated weights for policy 1, policy_version 28422 (0.0007) -[2023-10-15 03:23:00,274][88300] Updated weights for policy 1, policy_version 28432 (0.0009) -[2023-10-15 03:23:00,637][88300] Updated weights for policy 1, policy_version 28442 (0.0010) -[2023-10-15 03:23:03,366][88298] Updated weights for policy 0, policy_version 28290 (0.0009) -[2023-10-15 03:23:03,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 58097664. Throughput: 0: 1721.6, 1: 1733.8. Samples: 14531446. Policy #0 lag: (min: 26.0, avg: 26.1, max: 33.0) -[2023-10-15 03:23:03,534][87330] Avg episode reward: [(0, '22.770'), (1, '22.550')] -[2023-10-15 03:23:03,748][88298] Updated weights for policy 0, policy_version 28300 (0.0010) -[2023-10-15 03:23:04,110][88298] Updated weights for policy 0, policy_version 28310 (0.0010) -[2023-10-15 03:23:04,483][88298] Updated weights for policy 0, policy_version 28320 (0.0009) -[2023-10-15 03:23:04,532][88300] Updated weights for policy 1, policy_version 28452 (0.0010) -[2023-10-15 03:23:04,909][88300] Updated weights for policy 1, policy_version 28462 (0.0010) -[2023-10-15 03:23:05,288][88300] Updated weights for policy 1, policy_version 28472 (0.0010) -[2023-10-15 03:23:08,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 58163200. Throughput: 0: 1739.7, 1: 1740.9. Samples: 14552886. Policy #0 lag: (min: 26.0, avg: 26.1, max: 33.0) -[2023-10-15 03:23:08,535][87330] Avg episode reward: [(0, '22.740'), (1, '22.360')] -[2023-10-15 03:23:08,580][88298] Updated weights for policy 0, policy_version 28330 (0.0008) -[2023-10-15 03:23:08,941][88298] Updated weights for policy 0, policy_version 28340 (0.0010) -[2023-10-15 03:23:09,183][88300] Updated weights for policy 1, policy_version 28482 (0.0010) -[2023-10-15 03:23:09,320][88298] Updated weights for policy 0, policy_version 28350 (0.0008) -[2023-10-15 03:23:09,586][88300] Updated weights for policy 1, policy_version 28492 (0.0009) -[2023-10-15 03:23:09,954][88300] Updated weights for policy 1, policy_version 28502 (0.0008) -[2023-10-15 03:23:10,318][88300] Updated weights for policy 1, policy_version 28512 (0.0008) -[2023-10-15 03:23:13,124][88298] Updated weights for policy 0, policy_version 28360 (0.0008) -[2023-10-15 03:23:13,499][88298] Updated weights for policy 0, policy_version 28370 (0.0008) -[2023-10-15 03:23:13,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 58228736. Throughput: 0: 1746.1, 1: 1765.7. Samples: 14574746. Policy #0 lag: (min: 26.0, avg: 26.1, max: 33.0) -[2023-10-15 03:23:13,535][87330] Avg episode reward: [(0, '22.790'), (1, '22.460')] -[2023-10-15 03:23:13,863][88298] Updated weights for policy 0, policy_version 28380 (0.0009) -[2023-10-15 03:23:14,109][88300] Updated weights for policy 1, policy_version 28522 (0.0007) -[2023-10-15 03:23:14,479][88300] Updated weights for policy 1, policy_version 28532 (0.0008) -[2023-10-15 03:23:14,840][88300] Updated weights for policy 1, policy_version 28542 (0.0009) -[2023-10-15 03:23:17,718][88298] Updated weights for policy 0, policy_version 28390 (0.0007) -[2023-10-15 03:23:18,090][88298] Updated weights for policy 0, policy_version 28400 (0.0009) -[2023-10-15 03:23:18,467][88298] Updated weights for policy 0, policy_version 28410 (0.0007) -[2023-10-15 03:23:18,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 58294272. Throughput: 0: 1737.7, 1: 1737.0. Samples: 14584432. Policy #0 lag: (min: 26.0, avg: 26.1, max: 33.0) -[2023-10-15 03:23:18,534][87330] Avg episode reward: [(0, '22.790'), (1, '22.440')] -[2023-10-15 03:23:18,622][88300] Updated weights for policy 1, policy_version 28552 (0.0008) -[2023-10-15 03:23:18,999][88300] Updated weights for policy 1, policy_version 28562 (0.0007) -[2023-10-15 03:23:19,366][88300] Updated weights for policy 1, policy_version 28572 (0.0007) -[2023-10-15 03:23:22,402][88298] Updated weights for policy 0, policy_version 28420 (0.0010) -[2023-10-15 03:23:22,771][88298] Updated weights for policy 0, policy_version 28430 (0.0008) -[2023-10-15 03:23:23,133][88298] Updated weights for policy 0, policy_version 28440 (0.0007) -[2023-10-15 03:23:23,270][88300] Updated weights for policy 1, policy_version 28582 (0.0008) -[2023-10-15 03:23:23,534][87330] Fps is (10 sec: 16384.3, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 58392576. Throughput: 0: 1751.5, 1: 1765.0. Samples: 14606010. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-15 03:23:23,534][87330] Avg episode reward: [(0, '22.850'), (1, '22.420')] -[2023-10-15 03:23:23,643][88300] Updated weights for policy 1, policy_version 28592 (0.0007) -[2023-10-15 03:23:24,008][88300] Updated weights for policy 1, policy_version 28602 (0.0007) -[2023-10-15 03:23:26,987][88298] Updated weights for policy 0, policy_version 28450 (0.0009) -[2023-10-15 03:23:27,347][88298] Updated weights for policy 0, policy_version 28460 (0.0010) -[2023-10-15 03:23:27,721][88298] Updated weights for policy 0, policy_version 28470 (0.0011) -[2023-10-15 03:23:27,978][88300] Updated weights for policy 1, policy_version 28612 (0.0007) -[2023-10-15 03:23:28,097][88298] Updated weights for policy 0, policy_version 28480 (0.0007) -[2023-10-15 03:23:28,336][88300] Updated weights for policy 1, policy_version 28622 (0.0007) -[2023-10-15 03:23:28,534][87330] Fps is (10 sec: 16383.6, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 58458112. Throughput: 0: 1732.8, 1: 1755.3. Samples: 14626056. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-15 03:23:28,535][87330] Avg episode reward: [(0, '22.810'), (1, '22.430')] -[2023-10-15 03:23:28,706][88300] Updated weights for policy 1, policy_version 28632 (0.0007) -[2023-10-15 03:23:32,005][88298] Updated weights for policy 0, policy_version 28490 (0.0007) -[2023-10-15 03:23:32,377][88298] Updated weights for policy 0, policy_version 28500 (0.0007) -[2023-10-15 03:23:32,549][88300] Updated weights for policy 1, policy_version 28642 (0.0008) -[2023-10-15 03:23:32,747][88298] Updated weights for policy 0, policy_version 28510 (0.0008) -[2023-10-15 03:23:32,918][88300] Updated weights for policy 1, policy_version 28652 (0.0008) -[2023-10-15 03:23:33,290][88300] Updated weights for policy 1, policy_version 28662 (0.0010) -[2023-10-15 03:23:33,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 58523648. Throughput: 0: 1754.0, 1: 1742.8. Samples: 14636762. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-15 03:23:33,535][87330] Avg episode reward: [(0, '22.820'), (1, '22.410')] -[2023-10-15 03:23:33,660][88300] Updated weights for policy 1, policy_version 28672 (0.0007) -[2023-10-15 03:23:36,747][88298] Updated weights for policy 0, policy_version 28520 (0.0007) -[2023-10-15 03:23:37,115][88298] Updated weights for policy 0, policy_version 28530 (0.0007) -[2023-10-15 03:23:37,479][88298] Updated weights for policy 0, policy_version 28540 (0.0008) -[2023-10-15 03:23:37,505][88300] Updated weights for policy 1, policy_version 28682 (0.0008) -[2023-10-15 03:23:37,860][88300] Updated weights for policy 1, policy_version 28692 (0.0011) -[2023-10-15 03:23:38,231][88300] Updated weights for policy 1, policy_version 28702 (0.0012) -[2023-10-15 03:23:38,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 58621952. Throughput: 0: 1741.0, 1: 1763.3. Samples: 14657830. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-15 03:23:38,535][87330] Avg episode reward: [(0, '22.840'), (1, '22.480')] -[2023-10-15 03:23:41,354][88298] Updated weights for policy 0, policy_version 28550 (0.0009) -[2023-10-15 03:23:41,724][88298] Updated weights for policy 0, policy_version 28560 (0.0007) -[2023-10-15 03:23:42,103][88298] Updated weights for policy 0, policy_version 28570 (0.0007) -[2023-10-15 03:23:42,118][88300] Updated weights for policy 1, policy_version 28712 (0.0008) -[2023-10-15 03:23:42,489][88300] Updated weights for policy 1, policy_version 28722 (0.0007) -[2023-10-15 03:23:42,859][88300] Updated weights for policy 1, policy_version 28732 (0.0007) -[2023-10-15 03:23:43,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 58687488. Throughput: 0: 1716.8, 1: 1728.9. Samples: 14677052. Policy #0 lag: (min: 1.0, avg: 11.1, max: 33.0) -[2023-10-15 03:23:43,535][87330] Avg episode reward: [(0, '22.830'), (1, '22.400')] -[2023-10-15 03:23:46,042][88298] Updated weights for policy 0, policy_version 28580 (0.0007) -[2023-10-15 03:23:46,422][88298] Updated weights for policy 0, policy_version 28590 (0.0009) -[2023-10-15 03:23:46,731][88300] Updated weights for policy 1, policy_version 28742 (0.0008) -[2023-10-15 03:23:46,789][88298] Updated weights for policy 0, policy_version 28600 (0.0007) -[2023-10-15 03:23:47,096][88300] Updated weights for policy 1, policy_version 28752 (0.0007) -[2023-10-15 03:23:47,462][88300] Updated weights for policy 1, policy_version 28762 (0.0010) -[2023-10-15 03:23:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 58753024. Throughput: 0: 1746.8, 1: 1758.9. Samples: 14689202. Policy #0 lag: (min: 1.0, avg: 11.1, max: 33.0) -[2023-10-15 03:23:48,535][87330] Avg episode reward: [(0, '22.860'), (1, '22.380')] -[2023-10-15 03:23:50,605][88298] Updated weights for policy 0, policy_version 28610 (0.0010) -[2023-10-15 03:23:50,980][88298] Updated weights for policy 0, policy_version 28620 (0.0009) -[2023-10-15 03:23:51,345][88298] Updated weights for policy 0, policy_version 28630 (0.0010) -[2023-10-15 03:23:51,367][88300] Updated weights for policy 1, policy_version 28772 (0.0010) -[2023-10-15 03:23:51,719][88298] Updated weights for policy 0, policy_version 28640 (0.0009) -[2023-10-15 03:23:51,731][88300] Updated weights for policy 1, policy_version 28782 (0.0009) -[2023-10-15 03:23:52,101][88300] Updated weights for policy 1, policy_version 28792 (0.0008) -[2023-10-15 03:23:53,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 58818560. Throughput: 0: 1719.3, 1: 1735.5. Samples: 14708352. Policy #0 lag: (min: 1.0, avg: 11.1, max: 33.0) -[2023-10-15 03:23:53,535][87330] Avg episode reward: [(0, '22.850'), (1, '22.270')] -[2023-10-15 03:23:55,819][88298] Updated weights for policy 0, policy_version 28650 (0.0009) -[2023-10-15 03:23:56,093][88300] Updated weights for policy 1, policy_version 28802 (0.0008) -[2023-10-15 03:23:56,190][88298] Updated weights for policy 0, policy_version 28660 (0.0009) -[2023-10-15 03:23:56,487][88300] Updated weights for policy 1, policy_version 28812 (0.0009) -[2023-10-15 03:23:56,552][88298] Updated weights for policy 0, policy_version 28670 (0.0009) -[2023-10-15 03:23:56,850][88300] Updated weights for policy 1, policy_version 28822 (0.0008) -[2023-10-15 03:23:57,219][88300] Updated weights for policy 1, policy_version 28832 (0.0009) -[2023-10-15 03:23:58,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 58884096. Throughput: 0: 1712.7, 1: 1723.9. Samples: 14729392. Policy #0 lag: (min: 1.0, avg: 11.1, max: 33.0) -[2023-10-15 03:23:58,535][87330] Avg episode reward: [(0, '22.830'), (1, '22.250')] -[2023-10-15 03:24:00,518][88298] Updated weights for policy 0, policy_version 28680 (0.0008) -[2023-10-15 03:24:00,892][88298] Updated weights for policy 0, policy_version 28690 (0.0008) -[2023-10-15 03:24:01,110][88300] Updated weights for policy 1, policy_version 28842 (0.0008) -[2023-10-15 03:24:01,265][88298] Updated weights for policy 0, policy_version 28700 (0.0008) -[2023-10-15 03:24:01,484][88300] Updated weights for policy 1, policy_version 28852 (0.0008) -[2023-10-15 03:24:01,850][88300] Updated weights for policy 1, policy_version 28862 (0.0008) -[2023-10-15 03:24:03,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 58949632. Throughput: 0: 1725.7, 1: 1742.4. Samples: 14740498. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-15 03:24:03,534][87330] Avg episode reward: [(0, '22.800'), (1, '22.280')] -[2023-10-15 03:24:05,101][88298] Updated weights for policy 0, policy_version 28710 (0.0008) -[2023-10-15 03:24:05,475][88298] Updated weights for policy 0, policy_version 28720 (0.0007) -[2023-10-15 03:24:05,843][88300] Updated weights for policy 1, policy_version 28872 (0.0007) -[2023-10-15 03:24:05,849][88298] Updated weights for policy 0, policy_version 28730 (0.0007) -[2023-10-15 03:24:06,213][88300] Updated weights for policy 1, policy_version 28882 (0.0007) -[2023-10-15 03:24:06,583][88300] Updated weights for policy 1, policy_version 28892 (0.0009) -[2023-10-15 03:24:08,534][87330] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 59015168. Throughput: 0: 1712.3, 1: 1719.9. Samples: 14760458. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-15 03:24:08,534][87330] Avg episode reward: [(0, '22.780'), (1, '22.320')] -[2023-10-15 03:24:09,658][88298] Updated weights for policy 0, policy_version 28740 (0.0009) -[2023-10-15 03:24:10,027][88298] Updated weights for policy 0, policy_version 28750 (0.0011) -[2023-10-15 03:24:10,410][88298] Updated weights for policy 0, policy_version 28760 (0.0010) -[2023-10-15 03:24:10,439][88300] Updated weights for policy 1, policy_version 28902 (0.0009) -[2023-10-15 03:24:10,799][88300] Updated weights for policy 1, policy_version 28912 (0.0007) -[2023-10-15 03:24:11,167][88300] Updated weights for policy 1, policy_version 28922 (0.0007) -[2023-10-15 03:24:13,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 59080704. Throughput: 0: 1740.4, 1: 1728.9. Samples: 14782178. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-15 03:24:13,535][87330] Avg episode reward: [(0, '22.790'), (1, '22.510')] -[2023-10-15 03:24:14,251][88298] Updated weights for policy 0, policy_version 28770 (0.0008) -[2023-10-15 03:24:14,628][88298] Updated weights for policy 0, policy_version 28780 (0.0008) -[2023-10-15 03:24:14,992][88298] Updated weights for policy 0, policy_version 28790 (0.0008) -[2023-10-15 03:24:15,157][88300] Updated weights for policy 1, policy_version 28932 (0.0008) -[2023-10-15 03:24:15,370][88298] Updated weights for policy 0, policy_version 28800 (0.0010) -[2023-10-15 03:24:15,524][88300] Updated weights for policy 1, policy_version 28942 (0.0008) -[2023-10-15 03:24:15,888][88300] Updated weights for policy 1, policy_version 28952 (0.0007) -[2023-10-15 03:24:18,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 59146240. Throughput: 0: 1720.4, 1: 1722.5. Samples: 14791690. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-15 03:24:18,535][87330] Avg episode reward: [(0, '22.760'), (1, '22.430')] -[2023-10-15 03:24:19,140][88298] Updated weights for policy 0, policy_version 28810 (0.0007) -[2023-10-15 03:24:19,507][88298] Updated weights for policy 0, policy_version 28820 (0.0009) -[2023-10-15 03:24:19,740][88300] Updated weights for policy 1, policy_version 28962 (0.0009) -[2023-10-15 03:24:19,878][88298] Updated weights for policy 0, policy_version 28830 (0.0009) -[2023-10-15 03:24:20,098][88300] Updated weights for policy 1, policy_version 28972 (0.0008) -[2023-10-15 03:24:20,473][88300] Updated weights for policy 1, policy_version 28982 (0.0008) -[2023-10-15 03:24:20,841][88300] Updated weights for policy 1, policy_version 28992 (0.0010) -[2023-10-15 03:24:23,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 59211776. Throughput: 0: 1737.5, 1: 1720.8. Samples: 14813450. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-15 03:24:23,534][87330] Avg episode reward: [(0, '22.760'), (1, '22.390')] -[2023-10-15 03:24:23,650][88298] Updated weights for policy 0, policy_version 28840 (0.0007) -[2023-10-15 03:24:24,017][88298] Updated weights for policy 0, policy_version 28850 (0.0009) -[2023-10-15 03:24:24,394][88298] Updated weights for policy 0, policy_version 28860 (0.0007) -[2023-10-15 03:24:24,737][88300] Updated weights for policy 1, policy_version 29002 (0.0009) -[2023-10-15 03:24:25,110][88300] Updated weights for policy 1, policy_version 29012 (0.0009) -[2023-10-15 03:24:25,476][88300] Updated weights for policy 1, policy_version 29022 (0.0010) -[2023-10-15 03:24:28,420][88298] Updated weights for policy 0, policy_version 28870 (0.0007) -[2023-10-15 03:24:28,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 59277312. Throughput: 0: 1758.3, 1: 1748.0. Samples: 14834836. Policy #0 lag: (min: 15.0, avg: 19.4, max: 47.0) -[2023-10-15 03:24:28,535][87330] Avg episode reward: [(0, '22.780'), (1, '22.480')] -[2023-10-15 03:24:28,783][88298] Updated weights for policy 0, policy_version 28880 (0.0007) -[2023-10-15 03:24:29,151][88298] Updated weights for policy 0, policy_version 28890 (0.0009) -[2023-10-15 03:24:29,455][88300] Updated weights for policy 1, policy_version 29032 (0.0008) -[2023-10-15 03:24:29,822][88300] Updated weights for policy 1, policy_version 29042 (0.0009) -[2023-10-15 03:24:30,183][88300] Updated weights for policy 1, policy_version 29052 (0.0008) -[2023-10-15 03:24:32,994][88298] Updated weights for policy 0, policy_version 28900 (0.0008) -[2023-10-15 03:24:33,365][88298] Updated weights for policy 0, policy_version 28910 (0.0007) -[2023-10-15 03:24:33,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 59342848. Throughput: 0: 1730.7, 1: 1717.9. Samples: 14844390. Policy #0 lag: (min: 15.0, avg: 19.4, max: 47.0) -[2023-10-15 03:24:33,534][87330] Avg episode reward: [(0, '22.810'), (1, '22.340')] -[2023-10-15 03:24:33,733][88298] Updated weights for policy 0, policy_version 28920 (0.0008) -[2023-10-15 03:24:34,055][88300] Updated weights for policy 1, policy_version 29062 (0.0009) -[2023-10-15 03:24:34,431][88300] Updated weights for policy 1, policy_version 29072 (0.0009) -[2023-10-15 03:24:34,794][88300] Updated weights for policy 1, policy_version 29082 (0.0009) -[2023-10-15 03:24:37,581][88298] Updated weights for policy 0, policy_version 28930 (0.0008) -[2023-10-15 03:24:37,955][88298] Updated weights for policy 0, policy_version 28940 (0.0007) -[2023-10-15 03:24:38,320][88298] Updated weights for policy 0, policy_version 28950 (0.0007) -[2023-10-15 03:24:38,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 59408384. Throughput: 0: 1761.5, 1: 1738.4. Samples: 14865846. Policy #0 lag: (min: 15.0, avg: 19.4, max: 47.0) -[2023-10-15 03:24:38,534][87330] Avg episode reward: [(0, '22.840'), (1, '22.300')] -[2023-10-15 03:24:38,690][88298] Updated weights for policy 0, policy_version 28960 (0.0007) -[2023-10-15 03:24:38,794][88300] Updated weights for policy 1, policy_version 29092 (0.0008) -[2023-10-15 03:24:39,159][88300] Updated weights for policy 1, policy_version 29102 (0.0008) -[2023-10-15 03:24:39,526][88300] Updated weights for policy 1, policy_version 29112 (0.0010) -[2023-10-15 03:24:42,656][88298] Updated weights for policy 0, policy_version 28970 (0.0010) -[2023-10-15 03:24:43,029][88298] Updated weights for policy 0, policy_version 28980 (0.0008) -[2023-10-15 03:24:43,409][88298] Updated weights for policy 0, policy_version 28990 (0.0008) -[2023-10-15 03:24:43,507][88300] Updated weights for policy 1, policy_version 29122 (0.0010) -[2023-10-15 03:24:43,534][87330] Fps is (10 sec: 16383.6, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 59506688. Throughput: 0: 1750.8, 1: 1745.6. Samples: 14886730. Policy #0 lag: (min: 15.0, avg: 19.4, max: 47.0) -[2023-10-15 03:24:43,535][87330] Avg episode reward: [(0, '22.700'), (1, '22.330')] -[2023-10-15 03:24:43,879][88300] Updated weights for policy 1, policy_version 29132 (0.0008) -[2023-10-15 03:24:44,244][88300] Updated weights for policy 1, policy_version 29142 (0.0008) -[2023-10-15 03:24:44,614][88300] Updated weights for policy 1, policy_version 29152 (0.0008) -[2023-10-15 03:24:47,378][88298] Updated weights for policy 0, policy_version 29000 (0.0007) -[2023-10-15 03:24:47,763][88298] Updated weights for policy 0, policy_version 29010 (0.0008) -[2023-10-15 03:24:48,135][88298] Updated weights for policy 0, policy_version 29020 (0.0008) -[2023-10-15 03:24:48,376][88300] Updated weights for policy 1, policy_version 29162 (0.0008) -[2023-10-15 03:24:48,534][87330] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 59572224. Throughput: 0: 1746.6, 1: 1724.7. Samples: 14896708. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:24:48,534][87330] Avg episode reward: [(0, '22.660'), (1, '22.420')] -[2023-10-15 03:24:48,739][88300] Updated weights for policy 1, policy_version 29172 (0.0009) -[2023-10-15 03:24:49,111][88300] Updated weights for policy 1, policy_version 29182 (0.0008) -[2023-10-15 03:24:52,142][88298] Updated weights for policy 0, policy_version 29030 (0.0008) -[2023-10-15 03:24:52,528][88298] Updated weights for policy 0, policy_version 29040 (0.0009) -[2023-10-15 03:24:52,904][88298] Updated weights for policy 0, policy_version 29050 (0.0008) -[2023-10-15 03:24:53,113][88300] Updated weights for policy 1, policy_version 29192 (0.0010) -[2023-10-15 03:24:53,482][88300] Updated weights for policy 1, policy_version 29202 (0.0008) -[2023-10-15 03:24:53,534][87330] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 59637760. Throughput: 0: 1755.5, 1: 1745.1. Samples: 14917986. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:24:53,534][87330] Avg episode reward: [(0, '22.670'), (1, '22.370')] -[2023-10-15 03:24:53,851][88300] Updated weights for policy 1, policy_version 29212 (0.0010) -[2023-10-15 03:24:56,816][88298] Updated weights for policy 0, policy_version 29060 (0.0009) -[2023-10-15 03:24:57,182][88298] Updated weights for policy 0, policy_version 29070 (0.0011) -[2023-10-15 03:24:57,544][88298] Updated weights for policy 0, policy_version 29080 (0.0007) -[2023-10-15 03:24:57,941][88300] Updated weights for policy 1, policy_version 29222 (0.0009) -[2023-10-15 03:24:58,304][88300] Updated weights for policy 1, policy_version 29232 (0.0007) -[2023-10-15 03:24:58,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 59703296. Throughput: 0: 1721.0, 1: 1733.7. Samples: 14937640. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:24:58,534][87330] Avg episode reward: [(0, '22.650'), (1, '22.130')] -[2023-10-15 03:24:58,542][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000029088_29786112.pth... -[2023-10-15 03:24:58,576][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000027456_28114944.pth -[2023-10-15 03:24:58,676][88300] Updated weights for policy 1, policy_version 29242 (0.0008) -[2023-10-15 03:24:58,894][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000029248_29949952.pth... -[2023-10-15 03:24:58,923][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000027616_28278784.pth -[2023-10-15 03:25:01,299][88298] Updated weights for policy 0, policy_version 29090 (0.0008) -[2023-10-15 03:25:01,672][88298] Updated weights for policy 0, policy_version 29100 (0.0009) -[2023-10-15 03:25:02,043][88298] Updated weights for policy 0, policy_version 29110 (0.0007) -[2023-10-15 03:25:02,413][88298] Updated weights for policy 0, policy_version 29120 (0.0008) -[2023-10-15 03:25:02,652][88300] Updated weights for policy 1, policy_version 29252 (0.0008) -[2023-10-15 03:25:03,018][88300] Updated weights for policy 1, policy_version 29262 (0.0008) -[2023-10-15 03:25:03,393][88300] Updated weights for policy 1, policy_version 29272 (0.0009) -[2023-10-15 03:25:03,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 59768832. Throughput: 0: 1750.1, 1: 1743.7. Samples: 14948910. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:25:03,534][87330] Avg episode reward: [(0, '22.640'), (1, '22.340')] -[2023-10-15 03:25:06,397][88298] Updated weights for policy 0, policy_version 29130 (0.0007) -[2023-10-15 03:25:06,763][88298] Updated weights for policy 0, policy_version 29140 (0.0011) -[2023-10-15 03:25:07,134][88298] Updated weights for policy 0, policy_version 29150 (0.0010) -[2023-10-15 03:25:07,398][88300] Updated weights for policy 1, policy_version 29282 (0.0008) -[2023-10-15 03:25:07,759][88300] Updated weights for policy 1, policy_version 29292 (0.0009) -[2023-10-15 03:25:08,128][88300] Updated weights for policy 1, policy_version 29302 (0.0009) -[2023-10-15 03:25:08,494][88300] Updated weights for policy 1, policy_version 29312 (0.0009) -[2023-10-15 03:25:08,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 59867136. Throughput: 0: 1725.9, 1: 1743.1. Samples: 14969554. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:25:08,534][87330] Avg episode reward: [(0, '22.650'), (1, '22.340')] -[2023-10-15 03:25:11,113][88298] Updated weights for policy 0, policy_version 29160 (0.0009) -[2023-10-15 03:25:11,478][88298] Updated weights for policy 0, policy_version 29170 (0.0008) -[2023-10-15 03:25:11,843][88298] Updated weights for policy 0, policy_version 29180 (0.0007) -[2023-10-15 03:25:12,256][88300] Updated weights for policy 1, policy_version 29322 (0.0010) -[2023-10-15 03:25:12,622][88300] Updated weights for policy 1, policy_version 29332 (0.0011) -[2023-10-15 03:25:12,995][88300] Updated weights for policy 1, policy_version 29342 (0.0007) -[2023-10-15 03:25:13,534][87330] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 59932672. Throughput: 0: 1713.7, 1: 1718.4. Samples: 14989284. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:25:13,535][87330] Avg episode reward: [(0, '22.670'), (1, '22.250')] -[2023-10-15 03:25:15,911][88298] Updated weights for policy 0, policy_version 29190 (0.0008) -[2023-10-15 03:25:16,279][88298] Updated weights for policy 0, policy_version 29200 (0.0007) -[2023-10-15 03:25:16,648][88298] Updated weights for policy 0, policy_version 29210 (0.0008) -[2023-10-15 03:25:16,900][88300] Updated weights for policy 1, policy_version 29352 (0.0007) -[2023-10-15 03:25:17,262][88300] Updated weights for policy 1, policy_version 29362 (0.0010) -[2023-10-15 03:25:17,635][88300] Updated weights for policy 1, policy_version 29372 (0.0008) -[2023-10-15 03:25:18,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 59998208. Throughput: 0: 1736.5, 1: 1744.3. Samples: 15001024. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:25:18,534][87330] Avg episode reward: [(0, '22.840'), (1, '22.060')] -[2023-10-15 03:25:20,734][88298] Updated weights for policy 0, policy_version 29220 (0.0008) -[2023-10-15 03:25:21,108][88298] Updated weights for policy 0, policy_version 29230 (0.0009) -[2023-10-15 03:25:21,482][88298] Updated weights for policy 0, policy_version 29240 (0.0010) -[2023-10-15 03:25:21,500][88300] Updated weights for policy 1, policy_version 29382 (0.0009) -[2023-10-15 03:25:21,863][88300] Updated weights for policy 1, policy_version 29392 (0.0007) -[2023-10-15 03:25:22,231][88300] Updated weights for policy 1, policy_version 29402 (0.0007) -[2023-10-15 03:25:23,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 60063744. Throughput: 0: 1701.7, 1: 1728.2. Samples: 15020192. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:25:23,535][87330] Avg episode reward: [(0, '22.850'), (1, '22.080')] -[2023-10-15 03:25:25,393][88298] Updated weights for policy 0, policy_version 29250 (0.0009) -[2023-10-15 03:25:25,759][88298] Updated weights for policy 0, policy_version 29260 (0.0010) -[2023-10-15 03:25:26,050][88300] Updated weights for policy 1, policy_version 29412 (0.0007) -[2023-10-15 03:25:26,136][88298] Updated weights for policy 0, policy_version 29270 (0.0009) -[2023-10-15 03:25:26,414][88300] Updated weights for policy 1, policy_version 29422 (0.0008) -[2023-10-15 03:25:26,507][88298] Updated weights for policy 0, policy_version 29280 (0.0008) -[2023-10-15 03:25:26,778][88300] Updated weights for policy 1, policy_version 29432 (0.0007) -[2023-10-15 03:25:28,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 60129280. Throughput: 0: 1709.2, 1: 1725.4. Samples: 15041288. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:25:28,535][87330] Avg episode reward: [(0, '22.820'), (1, '22.420')] -[2023-10-15 03:25:30,392][88298] Updated weights for policy 0, policy_version 29290 (0.0007) -[2023-10-15 03:25:30,752][88298] Updated weights for policy 0, policy_version 29300 (0.0007) -[2023-10-15 03:25:30,759][88300] Updated weights for policy 1, policy_version 29442 (0.0007) -[2023-10-15 03:25:31,127][88298] Updated weights for policy 0, policy_version 29310 (0.0007) -[2023-10-15 03:25:31,172][88300] Updated weights for policy 1, policy_version 29452 (0.0009) -[2023-10-15 03:25:31,535][88300] Updated weights for policy 1, policy_version 29462 (0.0008) -[2023-10-15 03:25:31,900][88300] Updated weights for policy 1, policy_version 29472 (0.0009) -[2023-10-15 03:25:33,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 60194816. Throughput: 0: 1711.1, 1: 1737.9. Samples: 15051914. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:25:33,535][87330] Avg episode reward: [(0, '22.820'), (1, '22.410')] -[2023-10-15 03:25:35,064][88298] Updated weights for policy 0, policy_version 29320 (0.0007) -[2023-10-15 03:25:35,432][88298] Updated weights for policy 0, policy_version 29330 (0.0010) -[2023-10-15 03:25:35,714][88300] Updated weights for policy 1, policy_version 29482 (0.0007) -[2023-10-15 03:25:35,805][88298] Updated weights for policy 0, policy_version 29340 (0.0008) -[2023-10-15 03:25:36,076][88300] Updated weights for policy 1, policy_version 29492 (0.0007) -[2023-10-15 03:25:36,444][88300] Updated weights for policy 1, policy_version 29502 (0.0009) -[2023-10-15 03:25:38,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 60260352. Throughput: 0: 1700.0, 1: 1723.6. Samples: 15072050. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:25:38,534][87330] Avg episode reward: [(0, '22.780'), (1, '22.370')] -[2023-10-15 03:25:39,699][88298] Updated weights for policy 0, policy_version 29350 (0.0008) -[2023-10-15 03:25:40,079][88298] Updated weights for policy 0, policy_version 29360 (0.0010) -[2023-10-15 03:25:40,424][88300] Updated weights for policy 1, policy_version 29512 (0.0007) -[2023-10-15 03:25:40,455][88298] Updated weights for policy 0, policy_version 29370 (0.0007) -[2023-10-15 03:25:40,792][88300] Updated weights for policy 1, policy_version 29522 (0.0008) -[2023-10-15 03:25:41,151][88300] Updated weights for policy 1, policy_version 29532 (0.0009) -[2023-10-15 03:25:43,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 60325888. Throughput: 0: 1731.5, 1: 1732.7. Samples: 15093528. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:25:43,534][87330] Avg episode reward: [(0, '22.800'), (1, '22.340')] -[2023-10-15 03:25:44,261][88298] Updated weights for policy 0, policy_version 29380 (0.0008) -[2023-10-15 03:25:44,629][88298] Updated weights for policy 0, policy_version 29390 (0.0007) -[2023-10-15 03:25:45,001][88298] Updated weights for policy 0, policy_version 29400 (0.0007) -[2023-10-15 03:25:45,145][88300] Updated weights for policy 1, policy_version 29542 (0.0008) -[2023-10-15 03:25:45,509][88300] Updated weights for policy 1, policy_version 29552 (0.0008) -[2023-10-15 03:25:45,878][88300] Updated weights for policy 1, policy_version 29562 (0.0008) -[2023-10-15 03:25:48,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 60391424. Throughput: 0: 1705.1, 1: 1721.7. Samples: 15103118. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:25:48,535][87330] Avg episode reward: [(0, '22.770'), (1, '22.420')] -[2023-10-15 03:25:48,677][88298] Updated weights for policy 0, policy_version 29410 (0.0008) -[2023-10-15 03:25:49,053][88298] Updated weights for policy 0, policy_version 29420 (0.0008) -[2023-10-15 03:25:49,427][88298] Updated weights for policy 0, policy_version 29430 (0.0009) -[2023-10-15 03:25:49,724][88300] Updated weights for policy 1, policy_version 29572 (0.0010) -[2023-10-15 03:25:49,797][88298] Updated weights for policy 0, policy_version 29440 (0.0007) -[2023-10-15 03:25:50,095][88300] Updated weights for policy 1, policy_version 29582 (0.0008) -[2023-10-15 03:25:50,462][88300] Updated weights for policy 1, policy_version 29592 (0.0009) -[2023-10-15 03:25:53,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 60456960. Throughput: 0: 1726.6, 1: 1727.8. Samples: 15125000. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:25:53,535][87330] Avg episode reward: [(0, '22.790'), (1, '22.690')] -[2023-10-15 03:25:53,725][88298] Updated weights for policy 0, policy_version 29450 (0.0007) -[2023-10-15 03:25:54,093][88298] Updated weights for policy 0, policy_version 29460 (0.0008) -[2023-10-15 03:25:54,395][88300] Updated weights for policy 1, policy_version 29602 (0.0008) -[2023-10-15 03:25:54,470][88298] Updated weights for policy 0, policy_version 29470 (0.0008) -[2023-10-15 03:25:54,754][88300] Updated weights for policy 1, policy_version 29612 (0.0007) -[2023-10-15 03:25:55,116][88300] Updated weights for policy 1, policy_version 29622 (0.0009) -[2023-10-15 03:25:55,489][88300] Updated weights for policy 1, policy_version 29632 (0.0009) -[2023-10-15 03:25:58,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 60522496. Throughput: 0: 1744.3, 1: 1751.7. Samples: 15146604. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:25:58,534][87330] Avg episode reward: [(0, '22.810'), (1, '22.720')] -[2023-10-15 03:25:58,612][88298] Updated weights for policy 0, policy_version 29480 (0.0008) -[2023-10-15 03:25:58,990][88298] Updated weights for policy 0, policy_version 29490 (0.0007) -[2023-10-15 03:25:59,359][88298] Updated weights for policy 0, policy_version 29500 (0.0008) -[2023-10-15 03:25:59,452][88300] Updated weights for policy 1, policy_version 29642 (0.0007) -[2023-10-15 03:25:59,809][88300] Updated weights for policy 1, policy_version 29652 (0.0008) -[2023-10-15 03:26:00,176][88300] Updated weights for policy 1, policy_version 29662 (0.0008) -[2023-10-15 03:26:03,318][88298] Updated weights for policy 0, policy_version 29510 (0.0008) -[2023-10-15 03:26:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 60588032. Throughput: 0: 1719.4, 1: 1723.6. Samples: 15155960. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:26:03,535][87330] Avg episode reward: [(0, '22.840'), (1, '22.530')] -[2023-10-15 03:26:03,684][88298] Updated weights for policy 0, policy_version 29520 (0.0008) -[2023-10-15 03:26:04,050][88298] Updated weights for policy 0, policy_version 29530 (0.0007) -[2023-10-15 03:26:04,120][88300] Updated weights for policy 1, policy_version 29672 (0.0009) -[2023-10-15 03:26:04,488][88300] Updated weights for policy 1, policy_version 29682 (0.0008) -[2023-10-15 03:26:04,864][88300] Updated weights for policy 1, policy_version 29692 (0.0008) -[2023-10-15 03:26:08,004][88298] Updated weights for policy 0, policy_version 29540 (0.0009) -[2023-10-15 03:26:08,377][88298] Updated weights for policy 0, policy_version 29550 (0.0008) -[2023-10-15 03:26:08,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 60653568. Throughput: 0: 1752.2, 1: 1743.4. Samples: 15177494. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:26:08,534][87330] Avg episode reward: [(0, '22.640'), (1, '22.590')] -[2023-10-15 03:26:08,736][88300] Updated weights for policy 1, policy_version 29702 (0.0009) -[2023-10-15 03:26:08,752][88298] Updated weights for policy 0, policy_version 29560 (0.0008) -[2023-10-15 03:26:09,098][88300] Updated weights for policy 1, policy_version 29712 (0.0008) -[2023-10-15 03:26:09,476][88300] Updated weights for policy 1, policy_version 29722 (0.0011) -[2023-10-15 03:26:12,610][88298] Updated weights for policy 0, policy_version 29570 (0.0007) -[2023-10-15 03:26:12,986][88298] Updated weights for policy 0, policy_version 29580 (0.0008) -[2023-10-15 03:26:13,356][88298] Updated weights for policy 0, policy_version 29590 (0.0007) -[2023-10-15 03:26:13,368][88300] Updated weights for policy 1, policy_version 29732 (0.0009) -[2023-10-15 03:26:13,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13107.3, 300 sec: 13773.7). Total num frames: 60719104. Throughput: 0: 1748.6, 1: 1751.8. Samples: 15198804. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:26:13,534][87330] Avg episode reward: [(0, '22.660'), (1, '22.560')] -[2023-10-15 03:26:13,731][88298] Updated weights for policy 0, policy_version 29600 (0.0007) -[2023-10-15 03:26:13,737][88300] Updated weights for policy 1, policy_version 29742 (0.0007) -[2023-10-15 03:26:14,092][88300] Updated weights for policy 1, policy_version 29752 (0.0009) -[2023-10-15 03:26:17,682][88298] Updated weights for policy 0, policy_version 29610 (0.0010) -[2023-10-15 03:26:17,982][88300] Updated weights for policy 1, policy_version 29762 (0.0010) -[2023-10-15 03:26:18,056][88298] Updated weights for policy 0, policy_version 29620 (0.0008) -[2023-10-15 03:26:18,349][88300] Updated weights for policy 1, policy_version 29772 (0.0009) -[2023-10-15 03:26:18,434][88298] Updated weights for policy 0, policy_version 29630 (0.0009) -[2023-10-15 03:26:18,534][87330] Fps is (10 sec: 16383.6, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 60817408. Throughput: 0: 1742.2, 1: 1737.4. Samples: 15208496. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:26:18,535][87330] Avg episode reward: [(0, '22.570'), (1, '22.580')] -[2023-10-15 03:26:18,712][88300] Updated weights for policy 1, policy_version 29782 (0.0008) -[2023-10-15 03:26:19,081][88300] Updated weights for policy 1, policy_version 29792 (0.0009) -[2023-10-15 03:26:22,432][88298] Updated weights for policy 0, policy_version 29640 (0.0007) -[2023-10-15 03:26:22,797][88298] Updated weights for policy 0, policy_version 29650 (0.0007) -[2023-10-15 03:26:23,055][88300] Updated weights for policy 1, policy_version 29802 (0.0008) -[2023-10-15 03:26:23,175][88298] Updated weights for policy 0, policy_version 29660 (0.0007) -[2023-10-15 03:26:23,422][88300] Updated weights for policy 1, policy_version 29812 (0.0008) -[2023-10-15 03:26:23,534][87330] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 60882944. Throughput: 0: 1748.2, 1: 1748.8. Samples: 15229414. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:26:23,534][87330] Avg episode reward: [(0, '22.580'), (1, '22.580')] -[2023-10-15 03:26:23,781][88300] Updated weights for policy 1, policy_version 29822 (0.0009) -[2023-10-15 03:26:27,026][88298] Updated weights for policy 0, policy_version 29670 (0.0009) -[2023-10-15 03:26:27,404][88298] Updated weights for policy 0, policy_version 29680 (0.0009) -[2023-10-15 03:26:27,760][88300] Updated weights for policy 1, policy_version 29832 (0.0008) -[2023-10-15 03:26:27,764][88298] Updated weights for policy 0, policy_version 29690 (0.0009) -[2023-10-15 03:26:28,125][88300] Updated weights for policy 1, policy_version 29842 (0.0008) -[2023-10-15 03:26:28,489][88300] Updated weights for policy 1, policy_version 29852 (0.0008) -[2023-10-15 03:26:28,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 60948480. Throughput: 0: 1721.1, 1: 1735.8. Samples: 15249090. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:26:28,535][87330] Avg episode reward: [(0, '22.440'), (1, '22.480')] -[2023-10-15 03:26:31,510][88298] Updated weights for policy 0, policy_version 29700 (0.0008) -[2023-10-15 03:26:31,885][88298] Updated weights for policy 0, policy_version 29710 (0.0008) -[2023-10-15 03:26:32,253][88298] Updated weights for policy 0, policy_version 29720 (0.0009) -[2023-10-15 03:26:32,299][88300] Updated weights for policy 1, policy_version 29862 (0.0009) -[2023-10-15 03:26:32,658][88300] Updated weights for policy 1, policy_version 29872 (0.0010) -[2023-10-15 03:26:33,023][88300] Updated weights for policy 1, policy_version 29882 (0.0007) -[2023-10-15 03:26:33,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 61046784. Throughput: 0: 1744.4, 1: 1757.7. Samples: 15260714. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:26:33,534][87330] Avg episode reward: [(0, '22.400'), (1, '22.450')] -[2023-10-15 03:26:36,266][88298] Updated weights for policy 0, policy_version 29730 (0.0009) -[2023-10-15 03:26:36,637][88298] Updated weights for policy 0, policy_version 29740 (0.0008) -[2023-10-15 03:26:36,916][88300] Updated weights for policy 1, policy_version 29892 (0.0009) -[2023-10-15 03:26:37,009][88298] Updated weights for policy 0, policy_version 29750 (0.0009) -[2023-10-15 03:26:37,289][88300] Updated weights for policy 1, policy_version 29902 (0.0008) -[2023-10-15 03:26:37,371][88298] Updated weights for policy 0, policy_version 29760 (0.0008) -[2023-10-15 03:26:37,645][88300] Updated weights for policy 1, policy_version 29912 (0.0009) -[2023-10-15 03:26:38,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 61112320. Throughput: 0: 1727.4, 1: 1743.6. Samples: 15281196. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:26:38,535][87330] Avg episode reward: [(0, '22.440'), (1, '22.660')] -[2023-10-15 03:26:41,113][88298] Updated weights for policy 0, policy_version 29770 (0.0008) -[2023-10-15 03:26:41,420][88300] Updated weights for policy 1, policy_version 29922 (0.0008) -[2023-10-15 03:26:41,487][88298] Updated weights for policy 0, policy_version 29780 (0.0009) -[2023-10-15 03:26:41,791][88300] Updated weights for policy 1, policy_version 29932 (0.0008) -[2023-10-15 03:26:41,862][88298] Updated weights for policy 0, policy_version 29790 (0.0007) -[2023-10-15 03:26:42,148][88300] Updated weights for policy 1, policy_version 29942 (0.0007) -[2023-10-15 03:26:42,514][88300] Updated weights for policy 1, policy_version 29952 (0.0010) -[2023-10-15 03:26:43,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 61177856. Throughput: 0: 1714.2, 1: 1734.5. Samples: 15301798. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:26:43,534][87330] Avg episode reward: [(0, '22.450'), (1, '22.500')] -[2023-10-15 03:26:45,585][88298] Updated weights for policy 0, policy_version 29800 (0.0010) -[2023-10-15 03:26:45,953][88298] Updated weights for policy 0, policy_version 29810 (0.0009) -[2023-10-15 03:26:46,282][88300] Updated weights for policy 1, policy_version 29962 (0.0007) -[2023-10-15 03:26:46,321][88298] Updated weights for policy 0, policy_version 29820 (0.0008) -[2023-10-15 03:26:46,653][88300] Updated weights for policy 1, policy_version 29972 (0.0008) -[2023-10-15 03:26:47,019][88300] Updated weights for policy 1, policy_version 29982 (0.0007) -[2023-10-15 03:26:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 61243392. Throughput: 0: 1734.6, 1: 1762.9. Samples: 15313348. Policy #0 lag: (min: 1.0, avg: 10.7, max: 33.0) -[2023-10-15 03:26:48,534][87330] Avg episode reward: [(0, '22.420'), (1, '22.440')] -[2023-10-15 03:26:50,259][88298] Updated weights for policy 0, policy_version 29830 (0.0008) -[2023-10-15 03:26:50,621][88298] Updated weights for policy 0, policy_version 29840 (0.0008) -[2023-10-15 03:26:50,761][88300] Updated weights for policy 1, policy_version 29992 (0.0008) -[2023-10-15 03:26:50,986][88298] Updated weights for policy 0, policy_version 29850 (0.0007) -[2023-10-15 03:26:51,124][88300] Updated weights for policy 1, policy_version 30002 (0.0007) -[2023-10-15 03:26:51,496][88300] Updated weights for policy 1, policy_version 30012 (0.0009) -[2023-10-15 03:26:53,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 61308928. Throughput: 0: 1715.7, 1: 1741.9. Samples: 15333086. Policy #0 lag: (min: 1.0, avg: 10.7, max: 33.0) -[2023-10-15 03:26:53,534][87330] Avg episode reward: [(0, '22.510'), (1, '22.400')] -[2023-10-15 03:26:55,003][88298] Updated weights for policy 0, policy_version 29860 (0.0009) -[2023-10-15 03:26:55,368][88298] Updated weights for policy 0, policy_version 29870 (0.0007) -[2023-10-15 03:26:55,465][88300] Updated weights for policy 1, policy_version 30022 (0.0009) -[2023-10-15 03:26:55,736][88298] Updated weights for policy 0, policy_version 29880 (0.0007) -[2023-10-15 03:26:55,831][88300] Updated weights for policy 1, policy_version 30032 (0.0007) -[2023-10-15 03:26:56,211][88300] Updated weights for policy 1, policy_version 30042 (0.0009) -[2023-10-15 03:26:58,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 61374464. Throughput: 0: 1733.1, 1: 1739.3. Samples: 15355062. Policy #0 lag: (min: 1.0, avg: 10.7, max: 33.0) -[2023-10-15 03:26:58,535][87330] Avg episode reward: [(0, '22.260'), (1, '22.460')] -[2023-10-15 03:26:58,544][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000030048_30769152.pth... -[2023-10-15 03:26:58,544][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000029888_30605312.pth... -[2023-10-15 03:26:58,574][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000028416_29097984.pth -[2023-10-15 03:26:58,579][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000028288_28966912.pth -[2023-10-15 03:26:59,731][88298] Updated weights for policy 0, policy_version 29890 (0.0009) -[2023-10-15 03:27:00,097][88298] Updated weights for policy 0, policy_version 29900 (0.0010) -[2023-10-15 03:27:00,120][88300] Updated weights for policy 1, policy_version 30052 (0.0007) -[2023-10-15 03:27:00,462][88298] Updated weights for policy 0, policy_version 29910 (0.0008) -[2023-10-15 03:27:00,493][88300] Updated weights for policy 1, policy_version 30062 (0.0008) -[2023-10-15 03:27:00,835][88298] Updated weights for policy 0, policy_version 29920 (0.0007) -[2023-10-15 03:27:00,849][88300] Updated weights for policy 1, policy_version 30072 (0.0009) -[2023-10-15 03:27:03,534][87330] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 61440000. Throughput: 0: 1725.1, 1: 1738.5. Samples: 15364358. Policy #0 lag: (min: 1.0, avg: 10.7, max: 33.0) -[2023-10-15 03:27:03,535][87330] Avg episode reward: [(0, '22.080'), (1, '22.360')] -[2023-10-15 03:27:04,763][88300] Updated weights for policy 1, policy_version 30082 (0.0009) -[2023-10-15 03:27:04,840][88298] Updated weights for policy 0, policy_version 29930 (0.0009) -[2023-10-15 03:27:05,132][88300] Updated weights for policy 1, policy_version 30092 (0.0008) -[2023-10-15 03:27:05,210][88298] Updated weights for policy 0, policy_version 29940 (0.0007) -[2023-10-15 03:27:05,486][88300] Updated weights for policy 1, policy_version 30102 (0.0008) -[2023-10-15 03:27:05,581][88298] Updated weights for policy 0, policy_version 29950 (0.0007) -[2023-10-15 03:27:05,849][88300] Updated weights for policy 1, policy_version 30112 (0.0010) -[2023-10-15 03:27:08,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 61505536. Throughput: 0: 1733.6, 1: 1741.6. Samples: 15385798. Policy #0 lag: (min: 1.0, avg: 10.7, max: 33.0) -[2023-10-15 03:27:08,535][87330] Avg episode reward: [(0, '22.190'), (1, '22.280')] -[2023-10-15 03:27:09,695][88298] Updated weights for policy 0, policy_version 29960 (0.0008) -[2023-10-15 03:27:09,768][88300] Updated weights for policy 1, policy_version 30122 (0.0009) -[2023-10-15 03:27:10,073][88298] Updated weights for policy 0, policy_version 29970 (0.0008) -[2023-10-15 03:27:10,145][88300] Updated weights for policy 1, policy_version 30132 (0.0008) -[2023-10-15 03:27:10,442][88298] Updated weights for policy 0, policy_version 29980 (0.0009) -[2023-10-15 03:27:10,510][88300] Updated weights for policy 1, policy_version 30142 (0.0007) -[2023-10-15 03:27:13,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 61571072. Throughput: 0: 1752.0, 1: 1760.0. Samples: 15407130. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:27:13,535][87330] Avg episode reward: [(0, '22.180'), (1, '22.270')] -[2023-10-15 03:27:14,291][88298] Updated weights for policy 0, policy_version 29990 (0.0008) -[2023-10-15 03:27:14,453][88300] Updated weights for policy 1, policy_version 30152 (0.0007) -[2023-10-15 03:27:14,666][88298] Updated weights for policy 0, policy_version 30000 (0.0008) -[2023-10-15 03:27:14,826][88300] Updated weights for policy 1, policy_version 30162 (0.0009) -[2023-10-15 03:27:15,033][88298] Updated weights for policy 0, policy_version 30010 (0.0008) -[2023-10-15 03:27:15,184][88300] Updated weights for policy 1, policy_version 30172 (0.0008) -[2023-10-15 03:27:18,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 61636608. Throughput: 0: 1725.1, 1: 1735.6. Samples: 15416442. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:27:18,535][87330] Avg episode reward: [(0, '22.200'), (1, '22.250')] -[2023-10-15 03:27:18,879][88298] Updated weights for policy 0, policy_version 30020 (0.0007) -[2023-10-15 03:27:19,223][88300] Updated weights for policy 1, policy_version 30182 (0.0008) -[2023-10-15 03:27:19,249][88298] Updated weights for policy 0, policy_version 30030 (0.0008) -[2023-10-15 03:27:19,585][88300] Updated weights for policy 1, policy_version 30192 (0.0008) -[2023-10-15 03:27:19,621][88298] Updated weights for policy 0, policy_version 30040 (0.0009) -[2023-10-15 03:27:19,957][88300] Updated weights for policy 1, policy_version 30202 (0.0008) -[2023-10-15 03:27:23,436][88298] Updated weights for policy 0, policy_version 30050 (0.0009) -[2023-10-15 03:27:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 61702144. Throughput: 0: 1738.0, 1: 1739.8. Samples: 15437698. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:27:23,535][87330] Avg episode reward: [(0, '22.190'), (1, '21.910')] -[2023-10-15 03:27:23,808][88298] Updated weights for policy 0, policy_version 30060 (0.0007) -[2023-10-15 03:27:23,838][88300] Updated weights for policy 1, policy_version 30212 (0.0008) -[2023-10-15 03:27:24,176][88298] Updated weights for policy 0, policy_version 30070 (0.0008) -[2023-10-15 03:27:24,205][88300] Updated weights for policy 1, policy_version 30222 (0.0007) -[2023-10-15 03:27:24,542][88298] Updated weights for policy 0, policy_version 30080 (0.0009) -[2023-10-15 03:27:24,568][88300] Updated weights for policy 1, policy_version 30232 (0.0008) -[2023-10-15 03:27:28,387][88300] Updated weights for policy 1, policy_version 30242 (0.0008) -[2023-10-15 03:27:28,407][88298] Updated weights for policy 0, policy_version 30090 (0.0009) -[2023-10-15 03:27:28,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 61767680. Throughput: 0: 1746.8, 1: 1754.1. Samples: 15459336. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:27:28,534][87330] Avg episode reward: [(0, '22.380'), (1, '21.900')] -[2023-10-15 03:27:28,762][88300] Updated weights for policy 1, policy_version 30252 (0.0008) -[2023-10-15 03:27:28,766][88298] Updated weights for policy 0, policy_version 30100 (0.0008) -[2023-10-15 03:27:29,128][88300] Updated weights for policy 1, policy_version 30262 (0.0009) -[2023-10-15 03:27:29,139][88298] Updated weights for policy 0, policy_version 30110 (0.0008) -[2023-10-15 03:27:29,500][88300] Updated weights for policy 1, policy_version 30272 (0.0007) -[2023-10-15 03:27:32,956][88298] Updated weights for policy 0, policy_version 30120 (0.0007) -[2023-10-15 03:27:33,331][88298] Updated weights for policy 0, policy_version 30130 (0.0008) -[2023-10-15 03:27:33,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 61833216. Throughput: 0: 1729.5, 1: 1722.7. Samples: 15468696. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:27:33,535][87330] Avg episode reward: [(0, '22.310'), (1, '22.020')] -[2023-10-15 03:27:33,592][88300] Updated weights for policy 1, policy_version 30282 (0.0007) -[2023-10-15 03:27:33,698][88298] Updated weights for policy 0, policy_version 30140 (0.0007) -[2023-10-15 03:27:33,964][88300] Updated weights for policy 1, policy_version 30292 (0.0009) -[2023-10-15 03:27:34,327][88300] Updated weights for policy 1, policy_version 30302 (0.0011) -[2023-10-15 03:27:37,680][88298] Updated weights for policy 0, policy_version 30150 (0.0011) -[2023-10-15 03:27:38,050][88298] Updated weights for policy 0, policy_version 30160 (0.0008) -[2023-10-15 03:27:38,264][88300] Updated weights for policy 1, policy_version 30312 (0.0008) -[2023-10-15 03:27:38,417][88298] Updated weights for policy 0, policy_version 30170 (0.0009) -[2023-10-15 03:27:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 61898752. Throughput: 0: 1746.4, 1: 1740.5. Samples: 15489996. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-15 03:27:38,534][87330] Avg episode reward: [(0, '22.290'), (1, '22.060')] -[2023-10-15 03:27:38,633][88300] Updated weights for policy 1, policy_version 30322 (0.0007) -[2023-10-15 03:27:39,007][88300] Updated weights for policy 1, policy_version 30332 (0.0007) -[2023-10-15 03:27:42,329][88298] Updated weights for policy 0, policy_version 30180 (0.0008) -[2023-10-15 03:27:42,706][88298] Updated weights for policy 0, policy_version 30190 (0.0007) -[2023-10-15 03:27:42,941][88300] Updated weights for policy 1, policy_version 30342 (0.0010) -[2023-10-15 03:27:43,080][88298] Updated weights for policy 0, policy_version 30200 (0.0009) -[2023-10-15 03:27:43,306][88300] Updated weights for policy 1, policy_version 30352 (0.0007) -[2023-10-15 03:27:43,534][87330] Fps is (10 sec: 16384.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 61997056. Throughput: 0: 1722.8, 1: 1722.0. Samples: 15510080. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-15 03:27:43,534][87330] Avg episode reward: [(0, '22.020'), (1, '22.280')] -[2023-10-15 03:27:43,665][88300] Updated weights for policy 1, policy_version 30362 (0.0009) -[2023-10-15 03:27:46,864][88298] Updated weights for policy 0, policy_version 30210 (0.0009) -[2023-10-15 03:27:47,235][88298] Updated weights for policy 0, policy_version 30220 (0.0008) -[2023-10-15 03:27:47,595][88298] Updated weights for policy 0, policy_version 30230 (0.0009) -[2023-10-15 03:27:47,599][88300] Updated weights for policy 1, policy_version 30372 (0.0008) -[2023-10-15 03:27:47,959][88298] Updated weights for policy 0, policy_version 30240 (0.0007) -[2023-10-15 03:27:47,966][88300] Updated weights for policy 1, policy_version 30382 (0.0008) -[2023-10-15 03:27:48,335][88300] Updated weights for policy 1, policy_version 30392 (0.0010) -[2023-10-15 03:27:48,534][87330] Fps is (10 sec: 16383.5, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 62062592. Throughput: 0: 1742.6, 1: 1732.0. Samples: 15520714. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-15 03:27:48,535][87330] Avg episode reward: [(0, '21.850'), (1, '22.280')] -[2023-10-15 03:27:51,953][88298] Updated weights for policy 0, policy_version 30250 (0.0009) -[2023-10-15 03:27:52,320][88300] Updated weights for policy 1, policy_version 30402 (0.0007) -[2023-10-15 03:27:52,327][88298] Updated weights for policy 0, policy_version 30260 (0.0008) -[2023-10-15 03:27:52,691][88298] Updated weights for policy 0, policy_version 30270 (0.0008) -[2023-10-15 03:27:52,701][88300] Updated weights for policy 1, policy_version 30412 (0.0008) -[2023-10-15 03:27:53,079][88300] Updated weights for policy 1, policy_version 30422 (0.0009) -[2023-10-15 03:27:53,445][88300] Updated weights for policy 1, policy_version 30432 (0.0010) -[2023-10-15 03:27:53,534][87330] Fps is (10 sec: 16383.5, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 62160896. Throughput: 0: 1736.5, 1: 1731.1. Samples: 15541840. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-15 03:27:53,535][87330] Avg episode reward: [(0, '21.830'), (1, '22.710')] -[2023-10-15 03:27:56,594][88298] Updated weights for policy 0, policy_version 30280 (0.0009) -[2023-10-15 03:27:56,978][88298] Updated weights for policy 0, policy_version 30290 (0.0008) -[2023-10-15 03:27:57,296][88300] Updated weights for policy 1, policy_version 30442 (0.0008) -[2023-10-15 03:27:57,340][88298] Updated weights for policy 0, policy_version 30300 (0.0009) -[2023-10-15 03:27:57,657][88300] Updated weights for policy 1, policy_version 30452 (0.0007) -[2023-10-15 03:27:58,011][88300] Updated weights for policy 1, policy_version 30462 (0.0007) -[2023-10-15 03:27:58,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 62226432. Throughput: 0: 1719.9, 1: 1696.0. Samples: 15560842. Policy #0 lag: (min: 28.0, avg: 33.9, max: 60.0) -[2023-10-15 03:27:58,535][87330] Avg episode reward: [(0, '21.620'), (1, '22.670')] -[2023-10-15 03:28:01,246][88298] Updated weights for policy 0, policy_version 30310 (0.0008) -[2023-10-15 03:28:01,616][88298] Updated weights for policy 0, policy_version 30320 (0.0009) -[2023-10-15 03:28:01,986][88298] Updated weights for policy 0, policy_version 30330 (0.0007) -[2023-10-15 03:28:02,080][88300] Updated weights for policy 1, policy_version 30472 (0.0009) -[2023-10-15 03:28:02,448][88300] Updated weights for policy 1, policy_version 30482 (0.0007) -[2023-10-15 03:28:02,812][88300] Updated weights for policy 1, policy_version 30492 (0.0007) -[2023-10-15 03:28:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 62291968. Throughput: 0: 1753.6, 1: 1726.5. Samples: 15573050. Policy #0 lag: (min: 28.0, avg: 33.9, max: 60.0) -[2023-10-15 03:28:03,535][87330] Avg episode reward: [(0, '21.710'), (1, '22.700')] -[2023-10-15 03:28:06,080][88298] Updated weights for policy 0, policy_version 30340 (0.0008) -[2023-10-15 03:28:06,446][88298] Updated weights for policy 0, policy_version 30350 (0.0007) -[2023-10-15 03:28:06,542][88300] Updated weights for policy 1, policy_version 30502 (0.0007) -[2023-10-15 03:28:06,811][88298] Updated weights for policy 0, policy_version 30360 (0.0008) -[2023-10-15 03:28:06,906][88300] Updated weights for policy 1, policy_version 30512 (0.0007) -[2023-10-15 03:28:07,273][88300] Updated weights for policy 1, policy_version 30522 (0.0009) -[2023-10-15 03:28:08,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 62357504. Throughput: 0: 1730.1, 1: 1717.5. Samples: 15592838. Policy #0 lag: (min: 28.0, avg: 33.9, max: 60.0) -[2023-10-15 03:28:08,535][87330] Avg episode reward: [(0, '21.730'), (1, '22.690')] -[2023-10-15 03:28:10,702][88298] Updated weights for policy 0, policy_version 30370 (0.0008) -[2023-10-15 03:28:11,076][88298] Updated weights for policy 0, policy_version 30380 (0.0009) -[2023-10-15 03:28:11,325][88300] Updated weights for policy 1, policy_version 30532 (0.0009) -[2023-10-15 03:28:11,452][88298] Updated weights for policy 0, policy_version 30390 (0.0008) -[2023-10-15 03:28:11,697][88300] Updated weights for policy 1, policy_version 30542 (0.0008) -[2023-10-15 03:28:11,813][88298] Updated weights for policy 0, policy_version 30400 (0.0007) -[2023-10-15 03:28:12,061][88300] Updated weights for policy 1, policy_version 30552 (0.0009) -[2023-10-15 03:28:13,534][87330] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 62423040. Throughput: 0: 1723.5, 1: 1705.3. Samples: 15613632. Policy #0 lag: (min: 28.0, avg: 33.9, max: 60.0) -[2023-10-15 03:28:13,534][87330] Avg episode reward: [(0, '22.070'), (1, '22.710')] -[2023-10-15 03:28:15,796][88298] Updated weights for policy 0, policy_version 30410 (0.0007) -[2023-10-15 03:28:16,009][88300] Updated weights for policy 1, policy_version 30562 (0.0010) -[2023-10-15 03:28:16,164][88298] Updated weights for policy 0, policy_version 30420 (0.0007) -[2023-10-15 03:28:16,381][88300] Updated weights for policy 1, policy_version 30572 (0.0009) -[2023-10-15 03:28:16,531][88298] Updated weights for policy 0, policy_version 30430 (0.0007) -[2023-10-15 03:28:16,754][88300] Updated weights for policy 1, policy_version 30582 (0.0007) -[2023-10-15 03:28:17,121][88300] Updated weights for policy 1, policy_version 30592 (0.0009) -[2023-10-15 03:28:18,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 62488576. Throughput: 0: 1740.7, 1: 1732.0. Samples: 15624968. Policy #0 lag: (min: 28.0, avg: 33.9, max: 60.0) -[2023-10-15 03:28:18,535][87330] Avg episode reward: [(0, '22.070'), (1, '22.700')] -[2023-10-15 03:28:20,319][88298] Updated weights for policy 0, policy_version 30440 (0.0009) -[2023-10-15 03:28:20,693][88298] Updated weights for policy 0, policy_version 30450 (0.0012) -[2023-10-15 03:28:21,017][88300] Updated weights for policy 1, policy_version 30602 (0.0007) -[2023-10-15 03:28:21,063][88298] Updated weights for policy 0, policy_version 30460 (0.0009) -[2023-10-15 03:28:21,385][88300] Updated weights for policy 1, policy_version 30612 (0.0008) -[2023-10-15 03:28:21,750][88300] Updated weights for policy 1, policy_version 30622 (0.0007) -[2023-10-15 03:28:23,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 62554112. Throughput: 0: 1721.6, 1: 1715.9. Samples: 15644686. Policy #0 lag: (min: 12.0, avg: 15.9, max: 44.0) -[2023-10-15 03:28:23,535][87330] Avg episode reward: [(0, '22.260'), (1, '22.560')] -[2023-10-15 03:28:24,979][88298] Updated weights for policy 0, policy_version 30470 (0.0008) -[2023-10-15 03:28:25,345][88298] Updated weights for policy 0, policy_version 30480 (0.0007) -[2023-10-15 03:28:25,668][88300] Updated weights for policy 1, policy_version 30632 (0.0007) -[2023-10-15 03:28:25,712][88298] Updated weights for policy 0, policy_version 30490 (0.0007) -[2023-10-15 03:28:26,028][88300] Updated weights for policy 1, policy_version 30642 (0.0008) -[2023-10-15 03:28:26,403][88300] Updated weights for policy 1, policy_version 30652 (0.0009) -[2023-10-15 03:28:28,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 62619648. Throughput: 0: 1741.7, 1: 1735.7. Samples: 15666564. Policy #0 lag: (min: 12.0, avg: 15.9, max: 44.0) -[2023-10-15 03:28:28,535][87330] Avg episode reward: [(0, '22.270'), (1, '22.600')] -[2023-10-15 03:28:29,736][88298] Updated weights for policy 0, policy_version 30500 (0.0008) -[2023-10-15 03:28:30,098][88298] Updated weights for policy 0, policy_version 30510 (0.0009) -[2023-10-15 03:28:30,385][88300] Updated weights for policy 1, policy_version 30662 (0.0009) -[2023-10-15 03:28:30,464][88298] Updated weights for policy 0, policy_version 30520 (0.0007) -[2023-10-15 03:28:30,752][88300] Updated weights for policy 1, policy_version 30672 (0.0007) -[2023-10-15 03:28:31,109][88300] Updated weights for policy 1, policy_version 30682 (0.0009) -[2023-10-15 03:28:33,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 62685184. Throughput: 0: 1724.7, 1: 1733.9. Samples: 15676352. Policy #0 lag: (min: 12.0, avg: 15.9, max: 44.0) -[2023-10-15 03:28:33,535][87330] Avg episode reward: [(0, '22.430'), (1, '22.600')] -[2023-10-15 03:28:34,353][88298] Updated weights for policy 0, policy_version 30530 (0.0007) -[2023-10-15 03:28:34,732][88298] Updated weights for policy 0, policy_version 30540 (0.0007) -[2023-10-15 03:28:34,820][88300] Updated weights for policy 1, policy_version 30692 (0.0009) -[2023-10-15 03:28:35,099][88298] Updated weights for policy 0, policy_version 30550 (0.0008) -[2023-10-15 03:28:35,188][88300] Updated weights for policy 1, policy_version 30702 (0.0009) -[2023-10-15 03:28:35,466][88298] Updated weights for policy 0, policy_version 30560 (0.0008) -[2023-10-15 03:28:35,550][88300] Updated weights for policy 1, policy_version 30712 (0.0007) -[2023-10-15 03:28:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 62750720. Throughput: 0: 1728.4, 1: 1730.4. Samples: 15697482. Policy #0 lag: (min: 12.0, avg: 15.9, max: 44.0) -[2023-10-15 03:28:38,534][87330] Avg episode reward: [(0, '22.540'), (1, '22.610')] -[2023-10-15 03:28:39,186][88298] Updated weights for policy 0, policy_version 30570 (0.0007) -[2023-10-15 03:28:39,548][88298] Updated weights for policy 0, policy_version 30580 (0.0007) -[2023-10-15 03:28:39,601][88300] Updated weights for policy 1, policy_version 30722 (0.0008) -[2023-10-15 03:28:39,928][88298] Updated weights for policy 0, policy_version 30590 (0.0007) -[2023-10-15 03:28:39,969][88300] Updated weights for policy 1, policy_version 30732 (0.0008) -[2023-10-15 03:28:40,340][88300] Updated weights for policy 1, policy_version 30742 (0.0008) -[2023-10-15 03:28:40,698][88300] Updated weights for policy 1, policy_version 30752 (0.0008) -[2023-10-15 03:28:43,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 62816256. Throughput: 0: 1752.9, 1: 1763.4. Samples: 15719078. Policy #0 lag: (min: 12.0, avg: 15.9, max: 44.0) -[2023-10-15 03:28:43,534][87330] Avg episode reward: [(0, '22.490'), (1, '22.630')] -[2023-10-15 03:28:44,080][88298] Updated weights for policy 0, policy_version 30600 (0.0008) -[2023-10-15 03:28:44,462][88298] Updated weights for policy 0, policy_version 30610 (0.0009) -[2023-10-15 03:28:44,489][88300] Updated weights for policy 1, policy_version 30762 (0.0007) -[2023-10-15 03:28:44,822][88298] Updated weights for policy 0, policy_version 30620 (0.0009) -[2023-10-15 03:28:44,854][88300] Updated weights for policy 1, policy_version 30772 (0.0007) -[2023-10-15 03:28:45,213][88300] Updated weights for policy 1, policy_version 30782 (0.0008) -[2023-10-15 03:28:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 62881792. Throughput: 0: 1714.0, 1: 1736.7. Samples: 15728330. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:28:48,534][87330] Avg episode reward: [(0, '22.420'), (1, '22.610')] -[2023-10-15 03:28:48,684][88298] Updated weights for policy 0, policy_version 30630 (0.0008) -[2023-10-15 03:28:49,047][88298] Updated weights for policy 0, policy_version 30640 (0.0007) -[2023-10-15 03:28:49,063][88300] Updated weights for policy 1, policy_version 30792 (0.0009) -[2023-10-15 03:28:49,419][88300] Updated weights for policy 1, policy_version 30802 (0.0007) -[2023-10-15 03:28:49,426][88298] Updated weights for policy 0, policy_version 30650 (0.0007) -[2023-10-15 03:28:49,785][88300] Updated weights for policy 1, policy_version 30812 (0.0008) -[2023-10-15 03:28:53,361][88298] Updated weights for policy 0, policy_version 30660 (0.0009) -[2023-10-15 03:28:53,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 62947328. Throughput: 0: 1738.2, 1: 1749.6. Samples: 15749786. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:28:53,535][87330] Avg episode reward: [(0, '22.430'), (1, '22.550')] -[2023-10-15 03:28:53,694][88300] Updated weights for policy 1, policy_version 30822 (0.0007) -[2023-10-15 03:28:53,736][88298] Updated weights for policy 0, policy_version 30670 (0.0009) -[2023-10-15 03:28:54,059][88300] Updated weights for policy 1, policy_version 30832 (0.0009) -[2023-10-15 03:28:54,093][88298] Updated weights for policy 0, policy_version 30680 (0.0009) -[2023-10-15 03:28:54,424][88300] Updated weights for policy 1, policy_version 30842 (0.0008) -[2023-10-15 03:28:57,996][88298] Updated weights for policy 0, policy_version 30690 (0.0008) -[2023-10-15 03:28:58,334][88300] Updated weights for policy 1, policy_version 30852 (0.0007) -[2023-10-15 03:28:58,362][88298] Updated weights for policy 0, policy_version 30700 (0.0007) -[2023-10-15 03:28:58,534][87330] Fps is (10 sec: 13106.7, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 63012864. Throughput: 0: 1741.5, 1: 1766.7. Samples: 15771502. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:28:58,535][87330] Avg episode reward: [(0, '22.430'), (1, '22.670')] -[2023-10-15 03:28:58,704][88300] Updated weights for policy 1, policy_version 30862 (0.0007) -[2023-10-15 03:28:58,736][88298] Updated weights for policy 0, policy_version 30710 (0.0009) -[2023-10-15 03:28:59,075][88300] Updated weights for policy 1, policy_version 30872 (0.0007) -[2023-10-15 03:28:59,103][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000030720_31457280.pth... -[2023-10-15 03:28:59,104][88298] Updated weights for policy 0, policy_version 30720 (0.0009) -[2023-10-15 03:28:59,132][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000029088_29786112.pth -[2023-10-15 03:28:59,361][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000030880_31621120.pth... -[2023-10-15 03:28:59,400][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000029248_29949952.pth -[2023-10-15 03:29:03,066][88300] Updated weights for policy 1, policy_version 30882 (0.0009) -[2023-10-15 03:29:03,128][88298] Updated weights for policy 0, policy_version 30730 (0.0009) -[2023-10-15 03:29:03,422][88300] Updated weights for policy 1, policy_version 30892 (0.0008) -[2023-10-15 03:29:03,499][88298] Updated weights for policy 0, policy_version 30740 (0.0008) -[2023-10-15 03:29:03,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 63078400. Throughput: 0: 1722.4, 1: 1742.0. Samples: 15780868. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:29:03,535][87330] Avg episode reward: [(0, '22.530'), (1, '22.670')] -[2023-10-15 03:29:03,789][88300] Updated weights for policy 1, policy_version 30902 (0.0007) -[2023-10-15 03:29:03,874][88298] Updated weights for policy 0, policy_version 30750 (0.0007) -[2023-10-15 03:29:04,159][88300] Updated weights for policy 1, policy_version 30912 (0.0008) -[2023-10-15 03:29:07,903][88298] Updated weights for policy 0, policy_version 30760 (0.0007) -[2023-10-15 03:29:08,057][88300] Updated weights for policy 1, policy_version 30922 (0.0007) -[2023-10-15 03:29:08,272][88298] Updated weights for policy 0, policy_version 30770 (0.0007) -[2023-10-15 03:29:08,423][88300] Updated weights for policy 1, policy_version 30932 (0.0007) -[2023-10-15 03:29:08,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 63143936. Throughput: 0: 1739.6, 1: 1763.5. Samples: 15802324. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:29:08,534][87330] Avg episode reward: [(0, '22.730'), (1, '22.640')] -[2023-10-15 03:29:08,632][88298] Updated weights for policy 0, policy_version 30780 (0.0007) -[2023-10-15 03:29:08,791][88300] Updated weights for policy 1, policy_version 30942 (0.0007) -[2023-10-15 03:29:12,616][88300] Updated weights for policy 1, policy_version 30952 (0.0008) -[2023-10-15 03:29:12,648][88298] Updated weights for policy 0, policy_version 30790 (0.0008) -[2023-10-15 03:29:12,981][88300] Updated weights for policy 1, policy_version 30962 (0.0007) -[2023-10-15 03:29:13,014][88298] Updated weights for policy 0, policy_version 30800 (0.0008) -[2023-10-15 03:29:13,355][88300] Updated weights for policy 1, policy_version 30972 (0.0008) -[2023-10-15 03:29:13,383][88298] Updated weights for policy 0, policy_version 30810 (0.0008) -[2023-10-15 03:29:13,534][87330] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 63242240. Throughput: 0: 1723.5, 1: 1740.9. Samples: 15822460. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-15 03:29:13,535][87330] Avg episode reward: [(0, '22.820'), (1, '22.640')] -[2023-10-15 03:29:17,298][88300] Updated weights for policy 1, policy_version 30982 (0.0010) -[2023-10-15 03:29:17,309][88298] Updated weights for policy 0, policy_version 30820 (0.0008) -[2023-10-15 03:29:17,671][88298] Updated weights for policy 0, policy_version 30830 (0.0008) -[2023-10-15 03:29:17,676][88300] Updated weights for policy 1, policy_version 30992 (0.0009) -[2023-10-15 03:29:18,036][88298] Updated weights for policy 0, policy_version 30840 (0.0009) -[2023-10-15 03:29:18,039][88300] Updated weights for policy 1, policy_version 31002 (0.0008) -[2023-10-15 03:29:18,534][87330] Fps is (10 sec: 19660.3, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 63340544. Throughput: 0: 1729.9, 1: 1754.7. Samples: 15833160. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-15 03:29:18,535][87330] Avg episode reward: [(0, '22.840'), (1, '22.650')] -[2023-10-15 03:29:21,810][88298] Updated weights for policy 0, policy_version 30850 (0.0007) -[2023-10-15 03:29:21,899][88300] Updated weights for policy 1, policy_version 31012 (0.0009) -[2023-10-15 03:29:22,182][88298] Updated weights for policy 0, policy_version 30860 (0.0007) -[2023-10-15 03:29:22,269][88300] Updated weights for policy 1, policy_version 31022 (0.0009) -[2023-10-15 03:29:22,547][88298] Updated weights for policy 0, policy_version 30870 (0.0008) -[2023-10-15 03:29:22,636][88300] Updated weights for policy 1, policy_version 31032 (0.0007) -[2023-10-15 03:29:22,913][88298] Updated weights for policy 0, policy_version 30880 (0.0008) -[2023-10-15 03:29:23,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 63406080. Throughput: 0: 1736.1, 1: 1748.4. Samples: 15854288. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-15 03:29:23,535][87330] Avg episode reward: [(0, '22.840'), (1, '22.780')] -[2023-10-15 03:29:26,485][88300] Updated weights for policy 1, policy_version 31042 (0.0009) -[2023-10-15 03:29:26,781][88298] Updated weights for policy 0, policy_version 30890 (0.0008) -[2023-10-15 03:29:26,888][88300] Updated weights for policy 1, policy_version 31052 (0.0007) -[2023-10-15 03:29:27,143][88298] Updated weights for policy 0, policy_version 30900 (0.0008) -[2023-10-15 03:29:27,256][88300] Updated weights for policy 1, policy_version 31062 (0.0007) -[2023-10-15 03:29:27,519][88298] Updated weights for policy 0, policy_version 30910 (0.0008) -[2023-10-15 03:29:27,621][88300] Updated weights for policy 1, policy_version 31072 (0.0009) -[2023-10-15 03:29:28,534][87330] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 63471616. Throughput: 0: 1705.3, 1: 1727.2. Samples: 15873540. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-15 03:29:28,534][87330] Avg episode reward: [(0, '22.840'), (1, '22.770')] -[2023-10-15 03:29:31,544][88298] Updated weights for policy 0, policy_version 30920 (0.0008) -[2023-10-15 03:29:31,583][88300] Updated weights for policy 1, policy_version 31082 (0.0007) -[2023-10-15 03:29:31,912][88298] Updated weights for policy 0, policy_version 30930 (0.0007) -[2023-10-15 03:29:31,947][88300] Updated weights for policy 1, policy_version 31092 (0.0007) -[2023-10-15 03:29:32,289][88298] Updated weights for policy 0, policy_version 30940 (0.0008) -[2023-10-15 03:29:32,315][88300] Updated weights for policy 1, policy_version 31102 (0.0009) -[2023-10-15 03:29:33,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 63537152. Throughput: 0: 1740.0, 1: 1755.5. Samples: 15885626. Policy #0 lag: (min: 4.0, avg: 7.1, max: 36.0) -[2023-10-15 03:29:33,534][87330] Avg episode reward: [(0, '22.870'), (1, '22.740')] -[2023-10-15 03:29:36,055][88300] Updated weights for policy 1, policy_version 31112 (0.0008) -[2023-10-15 03:29:36,173][88298] Updated weights for policy 0, policy_version 30950 (0.0008) -[2023-10-15 03:29:36,432][88300] Updated weights for policy 1, policy_version 31122 (0.0009) -[2023-10-15 03:29:36,529][88298] Updated weights for policy 0, policy_version 30960 (0.0007) -[2023-10-15 03:29:36,791][88300] Updated weights for policy 1, policy_version 31132 (0.0008) -[2023-10-15 03:29:36,890][88298] Updated weights for policy 0, policy_version 30970 (0.0008) -[2023-10-15 03:29:38,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 63602688. Throughput: 0: 1717.2, 1: 1728.4. Samples: 15904838. Policy #0 lag: (min: 4.0, avg: 7.1, max: 36.0) -[2023-10-15 03:29:38,534][87330] Avg episode reward: [(0, '22.860'), (1, '22.640')] -[2023-10-15 03:29:40,636][88300] Updated weights for policy 1, policy_version 31142 (0.0008) -[2023-10-15 03:29:40,818][88298] Updated weights for policy 0, policy_version 30980 (0.0007) -[2023-10-15 03:29:41,003][88300] Updated weights for policy 1, policy_version 31152 (0.0008) -[2023-10-15 03:29:41,184][88298] Updated weights for policy 0, policy_version 30990 (0.0009) -[2023-10-15 03:29:41,373][88300] Updated weights for policy 1, policy_version 31162 (0.0008) -[2023-10-15 03:29:41,556][88298] Updated weights for policy 0, policy_version 31000 (0.0007) -[2023-10-15 03:29:43,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 63668224. Throughput: 0: 1708.5, 1: 1725.2. Samples: 15926020. Policy #0 lag: (min: 4.0, avg: 7.1, max: 36.0) -[2023-10-15 03:29:43,535][87330] Avg episode reward: [(0, '22.820'), (1, '22.480')] -[2023-10-15 03:29:45,314][88300] Updated weights for policy 1, policy_version 31172 (0.0008) -[2023-10-15 03:29:45,623][88298] Updated weights for policy 0, policy_version 31010 (0.0009) -[2023-10-15 03:29:45,678][88300] Updated weights for policy 1, policy_version 31182 (0.0007) -[2023-10-15 03:29:45,999][88298] Updated weights for policy 0, policy_version 31020 (0.0008) -[2023-10-15 03:29:46,044][88300] Updated weights for policy 1, policy_version 31192 (0.0007) -[2023-10-15 03:29:46,371][88298] Updated weights for policy 0, policy_version 31030 (0.0008) -[2023-10-15 03:29:46,740][88298] Updated weights for policy 0, policy_version 31040 (0.0007) -[2023-10-15 03:29:48,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 63733760. Throughput: 0: 1735.7, 1: 1729.7. Samples: 15936810. Policy #0 lag: (min: 4.0, avg: 7.1, max: 36.0) -[2023-10-15 03:29:48,534][87330] Avg episode reward: [(0, '22.860'), (1, '22.500')] -[2023-10-15 03:29:50,018][88300] Updated weights for policy 1, policy_version 31202 (0.0007) -[2023-10-15 03:29:50,380][88300] Updated weights for policy 1, policy_version 31212 (0.0009) -[2023-10-15 03:29:50,756][88300] Updated weights for policy 1, policy_version 31222 (0.0008) -[2023-10-15 03:29:50,834][88298] Updated weights for policy 0, policy_version 31050 (0.0008) -[2023-10-15 03:29:51,122][88300] Updated weights for policy 1, policy_version 31232 (0.0008) -[2023-10-15 03:29:51,203][88298] Updated weights for policy 0, policy_version 31060 (0.0009) -[2023-10-15 03:29:51,581][88298] Updated weights for policy 0, policy_version 31070 (0.0008) -[2023-10-15 03:29:53,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 63799296. Throughput: 0: 1710.8, 1: 1723.5. Samples: 15956870. Policy #0 lag: (min: 4.0, avg: 7.1, max: 36.0) -[2023-10-15 03:29:53,535][87330] Avg episode reward: [(0, '22.870'), (1, '22.500')] -[2023-10-15 03:29:54,809][88300] Updated weights for policy 1, policy_version 31242 (0.0011) -[2023-10-15 03:29:55,175][88300] Updated weights for policy 1, policy_version 31252 (0.0009) -[2023-10-15 03:29:55,315][88298] Updated weights for policy 0, policy_version 31080 (0.0009) -[2023-10-15 03:29:55,539][88300] Updated weights for policy 1, policy_version 31262 (0.0008) -[2023-10-15 03:29:55,681][88298] Updated weights for policy 0, policy_version 31090 (0.0007) -[2023-10-15 03:29:56,061][88298] Updated weights for policy 0, policy_version 31100 (0.0008) -[2023-10-15 03:29:58,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 63864832. Throughput: 0: 1721.5, 1: 1748.9. Samples: 15978630. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-15 03:29:58,535][87330] Avg episode reward: [(0, '22.840'), (1, '22.390')] -[2023-10-15 03:29:59,353][88300] Updated weights for policy 1, policy_version 31272 (0.0008) -[2023-10-15 03:29:59,713][88300] Updated weights for policy 1, policy_version 31282 (0.0010) -[2023-10-15 03:29:59,930][88298] Updated weights for policy 0, policy_version 31110 (0.0007) -[2023-10-15 03:30:00,072][88300] Updated weights for policy 1, policy_version 31292 (0.0009) -[2023-10-15 03:30:00,304][88298] Updated weights for policy 0, policy_version 31120 (0.0007) -[2023-10-15 03:30:00,677][88298] Updated weights for policy 0, policy_version 31130 (0.0008) -[2023-10-15 03:30:03,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 63930368. Throughput: 0: 1717.7, 1: 1728.2. Samples: 15988228. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-15 03:30:03,534][87330] Avg episode reward: [(0, '22.820'), (1, '22.390')] -[2023-10-15 03:30:03,975][88300] Updated weights for policy 1, policy_version 31302 (0.0009) -[2023-10-15 03:30:04,335][88300] Updated weights for policy 1, policy_version 31312 (0.0010) -[2023-10-15 03:30:04,662][88298] Updated weights for policy 0, policy_version 31140 (0.0008) -[2023-10-15 03:30:04,703][88300] Updated weights for policy 1, policy_version 31322 (0.0008) -[2023-10-15 03:30:05,031][88298] Updated weights for policy 0, policy_version 31150 (0.0008) -[2023-10-15 03:30:05,399][88298] Updated weights for policy 0, policy_version 31160 (0.0007) -[2023-10-15 03:30:08,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 63995904. Throughput: 0: 1706.9, 1: 1745.7. Samples: 16009656. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-15 03:30:08,535][87330] Avg episode reward: [(0, '22.810'), (1, '22.180')] -[2023-10-15 03:30:08,553][88300] Updated weights for policy 1, policy_version 31332 (0.0008) -[2023-10-15 03:30:08,915][88300] Updated weights for policy 1, policy_version 31342 (0.0009) -[2023-10-15 03:30:09,161][88298] Updated weights for policy 0, policy_version 31170 (0.0007) -[2023-10-15 03:30:09,290][88300] Updated weights for policy 1, policy_version 31352 (0.0008) -[2023-10-15 03:30:09,522][88298] Updated weights for policy 0, policy_version 31180 (0.0007) -[2023-10-15 03:30:09,897][88298] Updated weights for policy 0, policy_version 31190 (0.0007) -[2023-10-15 03:30:10,268][88298] Updated weights for policy 0, policy_version 31200 (0.0008) -[2023-10-15 03:30:13,342][88300] Updated weights for policy 1, policy_version 31362 (0.0009) -[2023-10-15 03:30:13,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 64061440. Throughput: 0: 1741.5, 1: 1766.8. Samples: 16031416. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-15 03:30:13,535][87330] Avg episode reward: [(0, '22.830'), (1, '22.220')] -[2023-10-15 03:30:13,730][88300] Updated weights for policy 1, policy_version 31372 (0.0008) -[2023-10-15 03:30:14,089][88300] Updated weights for policy 1, policy_version 31382 (0.0009) -[2023-10-15 03:30:14,117][88298] Updated weights for policy 0, policy_version 31210 (0.0009) -[2023-10-15 03:30:14,458][88300] Updated weights for policy 1, policy_version 31392 (0.0008) -[2023-10-15 03:30:14,486][88298] Updated weights for policy 0, policy_version 31220 (0.0010) -[2023-10-15 03:30:14,844][88298] Updated weights for policy 0, policy_version 31230 (0.0009) -[2023-10-15 03:30:18,483][88300] Updated weights for policy 1, policy_version 31402 (0.0007) -[2023-10-15 03:30:18,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13107.3, 300 sec: 13773.7). Total num frames: 64126976. Throughput: 0: 1711.5, 1: 1734.0. Samples: 16040674. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-15 03:30:18,534][87330] Avg episode reward: [(0, '22.650'), (1, '22.160')] -[2023-10-15 03:30:18,826][88298] Updated weights for policy 0, policy_version 31240 (0.0009) -[2023-10-15 03:30:18,854][88300] Updated weights for policy 1, policy_version 31412 (0.0007) -[2023-10-15 03:30:19,211][88298] Updated weights for policy 0, policy_version 31250 (0.0008) -[2023-10-15 03:30:19,211][88300] Updated weights for policy 1, policy_version 31422 (0.0007) -[2023-10-15 03:30:19,575][88298] Updated weights for policy 0, policy_version 31260 (0.0008) -[2023-10-15 03:30:23,002][88300] Updated weights for policy 1, policy_version 31432 (0.0007) -[2023-10-15 03:30:23,363][88300] Updated weights for policy 1, policy_version 31442 (0.0007) -[2023-10-15 03:30:23,509][88298] Updated weights for policy 0, policy_version 31270 (0.0007) -[2023-10-15 03:30:23,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 64192512. Throughput: 0: 1730.4, 1: 1764.1. Samples: 16062092. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:30:23,534][87330] Avg episode reward: [(0, '22.660'), (1, '22.120')] -[2023-10-15 03:30:23,733][88300] Updated weights for policy 1, policy_version 31452 (0.0007) -[2023-10-15 03:30:23,884][88298] Updated weights for policy 0, policy_version 31280 (0.0007) -[2023-10-15 03:30:24,248][88298] Updated weights for policy 0, policy_version 31290 (0.0010) -[2023-10-15 03:30:27,646][88300] Updated weights for policy 1, policy_version 31462 (0.0010) -[2023-10-15 03:30:28,009][88300] Updated weights for policy 1, policy_version 31472 (0.0009) -[2023-10-15 03:30:28,372][88298] Updated weights for policy 0, policy_version 31300 (0.0010) -[2023-10-15 03:30:28,384][88300] Updated weights for policy 1, policy_version 31482 (0.0009) -[2023-10-15 03:30:28,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 64258048. Throughput: 0: 1737.8, 1: 1743.4. Samples: 16082674. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:30:28,534][87330] Avg episode reward: [(0, '22.540'), (1, '22.040')] -[2023-10-15 03:30:28,739][88298] Updated weights for policy 0, policy_version 31310 (0.0009) -[2023-10-15 03:30:29,118][88298] Updated weights for policy 0, policy_version 31320 (0.0008) -[2023-10-15 03:30:32,360][88300] Updated weights for policy 1, policy_version 31492 (0.0007) -[2023-10-15 03:30:32,731][88300] Updated weights for policy 1, policy_version 31502 (0.0008) -[2023-10-15 03:30:32,993][88298] Updated weights for policy 0, policy_version 31330 (0.0008) -[2023-10-15 03:30:33,098][88300] Updated weights for policy 1, policy_version 31512 (0.0007) -[2023-10-15 03:30:33,364][88298] Updated weights for policy 0, policy_version 31340 (0.0008) -[2023-10-15 03:30:33,534][87330] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 64356352. Throughput: 0: 1711.9, 1: 1759.6. Samples: 16093024. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:30:33,534][87330] Avg episode reward: [(0, '22.440'), (1, '22.180')] -[2023-10-15 03:30:33,743][88298] Updated weights for policy 0, policy_version 31350 (0.0010) -[2023-10-15 03:30:34,106][88298] Updated weights for policy 0, policy_version 31360 (0.0008) -[2023-10-15 03:30:36,995][88300] Updated weights for policy 1, policy_version 31522 (0.0009) -[2023-10-15 03:30:37,365][88300] Updated weights for policy 1, policy_version 31532 (0.0011) -[2023-10-15 03:30:37,722][88300] Updated weights for policy 1, policy_version 31542 (0.0008) -[2023-10-15 03:30:37,963][88298] Updated weights for policy 0, policy_version 31370 (0.0009) -[2023-10-15 03:30:38,083][88300] Updated weights for policy 1, policy_version 31552 (0.0009) -[2023-10-15 03:30:38,342][88298] Updated weights for policy 0, policy_version 31380 (0.0007) -[2023-10-15 03:30:38,534][87330] Fps is (10 sec: 16383.6, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 64421888. Throughput: 0: 1743.4, 1: 1758.7. Samples: 16114466. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:30:38,535][87330] Avg episode reward: [(0, '22.280'), (1, '22.400')] -[2023-10-15 03:30:38,717][88298] Updated weights for policy 0, policy_version 31390 (0.0009) -[2023-10-15 03:30:41,927][88300] Updated weights for policy 1, policy_version 31562 (0.0007) -[2023-10-15 03:30:42,289][88300] Updated weights for policy 1, policy_version 31572 (0.0007) -[2023-10-15 03:30:42,663][88300] Updated weights for policy 1, policy_version 31582 (0.0007) -[2023-10-15 03:30:42,688][88298] Updated weights for policy 0, policy_version 31400 (0.0009) -[2023-10-15 03:30:43,052][88298] Updated weights for policy 0, policy_version 31410 (0.0008) -[2023-10-15 03:30:43,434][88298] Updated weights for policy 0, policy_version 31420 (0.0009) -[2023-10-15 03:30:43,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 64487424. Throughput: 0: 1734.0, 1: 1732.3. Samples: 16134612. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:30:43,534][87330] Avg episode reward: [(0, '22.260'), (1, '22.550')] -[2023-10-15 03:30:46,614][88300] Updated weights for policy 1, policy_version 31592 (0.0007) -[2023-10-15 03:30:46,982][88300] Updated weights for policy 1, policy_version 31602 (0.0009) -[2023-10-15 03:30:47,351][88300] Updated weights for policy 1, policy_version 31612 (0.0008) -[2023-10-15 03:30:47,400][88298] Updated weights for policy 0, policy_version 31430 (0.0009) -[2023-10-15 03:30:47,764][88298] Updated weights for policy 0, policy_version 31440 (0.0008) -[2023-10-15 03:30:48,127][88298] Updated weights for policy 0, policy_version 31450 (0.0007) -[2023-10-15 03:30:48,534][87330] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 64585728. Throughput: 0: 1740.1, 1: 1761.8. Samples: 16145812. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-15 03:30:48,534][87330] Avg episode reward: [(0, '22.420'), (1, '22.700')] -[2023-10-15 03:30:51,208][88300] Updated weights for policy 1, policy_version 31622 (0.0008) -[2023-10-15 03:30:51,564][88300] Updated weights for policy 1, policy_version 31632 (0.0007) -[2023-10-15 03:30:51,942][88300] Updated weights for policy 1, policy_version 31642 (0.0007) -[2023-10-15 03:30:52,052][88298] Updated weights for policy 0, policy_version 31460 (0.0009) -[2023-10-15 03:30:52,434][88298] Updated weights for policy 0, policy_version 31470 (0.0010) -[2023-10-15 03:30:52,794][88298] Updated weights for policy 0, policy_version 31480 (0.0007) -[2023-10-15 03:30:53,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 64651264. Throughput: 0: 1749.4, 1: 1725.3. Samples: 16166018. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-15 03:30:53,534][87330] Avg episode reward: [(0, '22.440'), (1, '22.690')] -[2023-10-15 03:30:55,940][88300] Updated weights for policy 1, policy_version 31652 (0.0008) -[2023-10-15 03:30:56,301][88300] Updated weights for policy 1, policy_version 31662 (0.0012) -[2023-10-15 03:30:56,644][88298] Updated weights for policy 0, policy_version 31490 (0.0007) -[2023-10-15 03:30:56,666][88300] Updated weights for policy 1, policy_version 31672 (0.0009) -[2023-10-15 03:30:57,014][88298] Updated weights for policy 0, policy_version 31500 (0.0008) -[2023-10-15 03:30:57,382][88298] Updated weights for policy 0, policy_version 31510 (0.0009) -[2023-10-15 03:30:57,751][88298] Updated weights for policy 0, policy_version 31520 (0.0008) -[2023-10-15 03:30:58,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 64716800. Throughput: 0: 1714.5, 1: 1725.4. Samples: 16186212. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-15 03:30:58,534][87330] Avg episode reward: [(0, '22.300'), (1, '22.760')] -[2023-10-15 03:30:58,541][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000031680_32440320.pth... -[2023-10-15 03:30:58,541][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000031520_32276480.pth... -[2023-10-15 03:30:58,571][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000030048_30769152.pth -[2023-10-15 03:30:58,580][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000029888_30605312.pth -[2023-10-15 03:31:00,571][88300] Updated weights for policy 1, policy_version 31682 (0.0009) -[2023-10-15 03:31:00,972][88300] Updated weights for policy 1, policy_version 31692 (0.0010) -[2023-10-15 03:31:01,337][88300] Updated weights for policy 1, policy_version 31702 (0.0009) -[2023-10-15 03:31:01,560][88298] Updated weights for policy 0, policy_version 31530 (0.0010) -[2023-10-15 03:31:01,701][88300] Updated weights for policy 1, policy_version 31712 (0.0009) -[2023-10-15 03:31:01,933][88298] Updated weights for policy 0, policy_version 31540 (0.0007) -[2023-10-15 03:31:02,306][88298] Updated weights for policy 0, policy_version 31550 (0.0008) -[2023-10-15 03:31:03,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 64782336. Throughput: 0: 1745.0, 1: 1738.1. Samples: 16197414. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-15 03:31:03,535][87330] Avg episode reward: [(0, '22.450'), (1, '22.760')] -[2023-10-15 03:31:05,577][88300] Updated weights for policy 1, policy_version 31722 (0.0008) -[2023-10-15 03:31:05,942][88300] Updated weights for policy 1, policy_version 31732 (0.0009) -[2023-10-15 03:31:06,305][88300] Updated weights for policy 1, policy_version 31742 (0.0007) -[2023-10-15 03:31:06,372][88298] Updated weights for policy 0, policy_version 31560 (0.0009) -[2023-10-15 03:31:06,743][88298] Updated weights for policy 0, policy_version 31570 (0.0009) -[2023-10-15 03:31:07,110][88298] Updated weights for policy 0, policy_version 31580 (0.0008) -[2023-10-15 03:31:08,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 64847872. Throughput: 0: 1727.5, 1: 1723.8. Samples: 16217400. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-10-15 03:31:08,535][87330] Avg episode reward: [(0, '22.350'), (1, '22.620')] -[2023-10-15 03:31:10,060][88300] Updated weights for policy 1, policy_version 31752 (0.0007) -[2023-10-15 03:31:10,431][88300] Updated weights for policy 1, policy_version 31762 (0.0008) -[2023-10-15 03:31:10,804][88300] Updated weights for policy 1, policy_version 31772 (0.0009) -[2023-10-15 03:31:10,917][88298] Updated weights for policy 0, policy_version 31590 (0.0008) -[2023-10-15 03:31:11,299][88298] Updated weights for policy 0, policy_version 31600 (0.0009) -[2023-10-15 03:31:11,666][88298] Updated weights for policy 0, policy_version 31610 (0.0008) -[2023-10-15 03:31:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 64913408. Throughput: 0: 1722.5, 1: 1742.2. Samples: 16238586. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-10-15 03:31:13,535][87330] Avg episode reward: [(0, '22.500'), (1, '22.580')] -[2023-10-15 03:31:14,724][88300] Updated weights for policy 1, policy_version 31782 (0.0008) -[2023-10-15 03:31:15,090][88300] Updated weights for policy 1, policy_version 31792 (0.0011) -[2023-10-15 03:31:15,452][88300] Updated weights for policy 1, policy_version 31802 (0.0008) -[2023-10-15 03:31:15,634][88298] Updated weights for policy 0, policy_version 31620 (0.0008) -[2023-10-15 03:31:16,007][88298] Updated weights for policy 0, policy_version 31630 (0.0007) -[2023-10-15 03:31:16,384][88298] Updated weights for policy 0, policy_version 31640 (0.0007) -[2023-10-15 03:31:18,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 64978944. Throughput: 0: 1741.8, 1: 1726.4. Samples: 16249094. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-10-15 03:31:18,534][87330] Avg episode reward: [(0, '22.520'), (1, '22.570')] -[2023-10-15 03:31:19,316][88300] Updated weights for policy 1, policy_version 31812 (0.0010) -[2023-10-15 03:31:19,682][88300] Updated weights for policy 1, policy_version 31822 (0.0011) -[2023-10-15 03:31:20,053][88300] Updated weights for policy 1, policy_version 31832 (0.0009) -[2023-10-15 03:31:20,305][88298] Updated weights for policy 0, policy_version 31650 (0.0011) -[2023-10-15 03:31:20,681][88298] Updated weights for policy 0, policy_version 31660 (0.0009) -[2023-10-15 03:31:21,049][88298] Updated weights for policy 0, policy_version 31670 (0.0008) -[2023-10-15 03:31:21,420][88298] Updated weights for policy 0, policy_version 31680 (0.0007) -[2023-10-15 03:31:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 65044480. Throughput: 0: 1716.0, 1: 1732.5. Samples: 16269648. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-10-15 03:31:23,535][87330] Avg episode reward: [(0, '22.490'), (1, '22.610')] -[2023-10-15 03:31:24,001][88300] Updated weights for policy 1, policy_version 31842 (0.0008) -[2023-10-15 03:31:24,368][88300] Updated weights for policy 1, policy_version 31852 (0.0009) -[2023-10-15 03:31:24,723][88300] Updated weights for policy 1, policy_version 31862 (0.0007) -[2023-10-15 03:31:25,093][88300] Updated weights for policy 1, policy_version 31872 (0.0009) -[2023-10-15 03:31:25,105][88298] Updated weights for policy 0, policy_version 31690 (0.0007) -[2023-10-15 03:31:25,473][88298] Updated weights for policy 0, policy_version 31700 (0.0008) -[2023-10-15 03:31:25,844][88298] Updated weights for policy 0, policy_version 31710 (0.0008) -[2023-10-15 03:31:28,534][87330] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 65110016. Throughput: 0: 1727.2, 1: 1758.7. Samples: 16291480. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-10-15 03:31:28,535][87330] Avg episode reward: [(0, '22.310'), (1, '22.640')] -[2023-10-15 03:31:28,962][88300] Updated weights for policy 1, policy_version 31882 (0.0007) -[2023-10-15 03:31:29,329][88300] Updated weights for policy 1, policy_version 31892 (0.0008) -[2023-10-15 03:31:29,695][88300] Updated weights for policy 1, policy_version 31902 (0.0010) -[2023-10-15 03:31:29,739][88298] Updated weights for policy 0, policy_version 31720 (0.0007) -[2023-10-15 03:31:30,108][88298] Updated weights for policy 0, policy_version 31730 (0.0007) -[2023-10-15 03:31:30,481][88298] Updated weights for policy 0, policy_version 31740 (0.0008) -[2023-10-15 03:31:33,493][88300] Updated weights for policy 1, policy_version 31912 (0.0007) -[2023-10-15 03:31:33,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 65175552. Throughput: 0: 1718.8, 1: 1730.4. Samples: 16301026. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) -[2023-10-15 03:31:33,534][87330] Avg episode reward: [(0, '22.440'), (1, '22.630')] -[2023-10-15 03:31:33,858][88300] Updated weights for policy 1, policy_version 31922 (0.0008) -[2023-10-15 03:31:34,217][88300] Updated weights for policy 1, policy_version 31932 (0.0009) -[2023-10-15 03:31:34,612][88298] Updated weights for policy 0, policy_version 31750 (0.0008) -[2023-10-15 03:31:34,981][88298] Updated weights for policy 0, policy_version 31760 (0.0009) -[2023-10-15 03:31:35,349][88298] Updated weights for policy 0, policy_version 31770 (0.0007) -[2023-10-15 03:31:38,087][88300] Updated weights for policy 1, policy_version 31942 (0.0007) -[2023-10-15 03:31:38,451][88300] Updated weights for policy 1, policy_version 31952 (0.0007) -[2023-10-15 03:31:38,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 65241088. Throughput: 0: 1717.3, 1: 1762.8. Samples: 16322622. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) -[2023-10-15 03:31:38,535][87330] Avg episode reward: [(0, '22.420'), (1, '22.620')] -[2023-10-15 03:31:38,820][88300] Updated weights for policy 1, policy_version 31962 (0.0009) -[2023-10-15 03:31:39,217][88298] Updated weights for policy 0, policy_version 31780 (0.0008) -[2023-10-15 03:31:39,592][88298] Updated weights for policy 0, policy_version 31790 (0.0007) -[2023-10-15 03:31:39,964][88298] Updated weights for policy 0, policy_version 31800 (0.0007) -[2023-10-15 03:31:42,784][88300] Updated weights for policy 1, policy_version 31972 (0.0009) -[2023-10-15 03:31:43,147][88300] Updated weights for policy 1, policy_version 31982 (0.0010) -[2023-10-15 03:31:43,516][88300] Updated weights for policy 1, policy_version 31992 (0.0008) -[2023-10-15 03:31:43,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 65306624. Throughput: 0: 1748.8, 1: 1753.6. Samples: 16343824. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) -[2023-10-15 03:31:43,534][87330] Avg episode reward: [(0, '22.610'), (1, '22.640')] -[2023-10-15 03:31:43,856][88298] Updated weights for policy 0, policy_version 31810 (0.0008) -[2023-10-15 03:31:44,234][88298] Updated weights for policy 0, policy_version 31820 (0.0008) -[2023-10-15 03:31:44,598][88298] Updated weights for policy 0, policy_version 31830 (0.0008) -[2023-10-15 03:31:44,972][88298] Updated weights for policy 0, policy_version 31840 (0.0008) -[2023-10-15 03:31:47,523][88300] Updated weights for policy 1, policy_version 32002 (0.0009) -[2023-10-15 03:31:47,945][88300] Updated weights for policy 1, policy_version 32012 (0.0010) -[2023-10-15 03:31:48,323][88300] Updated weights for policy 1, policy_version 32022 (0.0011) -[2023-10-15 03:31:48,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 65372160. Throughput: 0: 1718.7, 1: 1755.1. Samples: 16353732. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) -[2023-10-15 03:31:48,535][87330] Avg episode reward: [(0, '22.440'), (1, '22.420')] -[2023-10-15 03:31:48,691][88300] Updated weights for policy 1, policy_version 32032 (0.0007) -[2023-10-15 03:31:48,793][88298] Updated weights for policy 0, policy_version 31850 (0.0007) -[2023-10-15 03:31:49,171][88298] Updated weights for policy 0, policy_version 31860 (0.0007) -[2023-10-15 03:31:49,534][88298] Updated weights for policy 0, policy_version 31870 (0.0008) -[2023-10-15 03:31:52,554][88300] Updated weights for policy 1, policy_version 32042 (0.0009) -[2023-10-15 03:31:52,928][88300] Updated weights for policy 1, policy_version 32052 (0.0007) -[2023-10-15 03:31:53,293][88300] Updated weights for policy 1, policy_version 32062 (0.0007) -[2023-10-15 03:31:53,394][88298] Updated weights for policy 0, policy_version 31880 (0.0009) -[2023-10-15 03:31:53,534][87330] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 65470464. Throughput: 0: 1739.9, 1: 1765.7. Samples: 16375154. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) -[2023-10-15 03:31:53,534][87330] Avg episode reward: [(0, '22.450'), (1, '22.410')] -[2023-10-15 03:31:53,773][88298] Updated weights for policy 0, policy_version 31890 (0.0010) -[2023-10-15 03:31:54,144][88298] Updated weights for policy 0, policy_version 31900 (0.0009) -[2023-10-15 03:31:57,133][88300] Updated weights for policy 1, policy_version 32072 (0.0010) -[2023-10-15 03:31:57,497][88300] Updated weights for policy 1, policy_version 32082 (0.0008) -[2023-10-15 03:31:57,867][88300] Updated weights for policy 1, policy_version 32092 (0.0007) -[2023-10-15 03:31:58,113][88298] Updated weights for policy 0, policy_version 31910 (0.0008) -[2023-10-15 03:31:58,495][88298] Updated weights for policy 0, policy_version 31920 (0.0010) -[2023-10-15 03:31:58,534][87330] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 65536000. Throughput: 0: 1750.0, 1: 1735.9. Samples: 16395452. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-15 03:31:58,535][87330] Avg episode reward: [(0, '22.630'), (1, '22.360')] -[2023-10-15 03:31:58,868][88298] Updated weights for policy 0, policy_version 31930 (0.0010) -[2023-10-15 03:32:01,687][88300] Updated weights for policy 1, policy_version 32102 (0.0008) -[2023-10-15 03:32:02,052][88300] Updated weights for policy 1, policy_version 32112 (0.0010) -[2023-10-15 03:32:02,426][88300] Updated weights for policy 1, policy_version 32122 (0.0010) -[2023-10-15 03:32:02,738][88298] Updated weights for policy 0, policy_version 31940 (0.0009) -[2023-10-15 03:32:03,108][88298] Updated weights for policy 0, policy_version 31950 (0.0008) -[2023-10-15 03:32:03,482][88298] Updated weights for policy 0, policy_version 31960 (0.0009) -[2023-10-15 03:32:03,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 65601536. Throughput: 0: 1724.5, 1: 1767.3. Samples: 16406226. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-15 03:32:03,535][87330] Avg episode reward: [(0, '22.660'), (1, '22.360')] -[2023-10-15 03:32:06,323][88300] Updated weights for policy 1, policy_version 32132 (0.0009) -[2023-10-15 03:32:06,687][88300] Updated weights for policy 1, policy_version 32142 (0.0011) -[2023-10-15 03:32:07,055][88300] Updated weights for policy 1, policy_version 32152 (0.0010) -[2023-10-15 03:32:07,372][88298] Updated weights for policy 0, policy_version 31970 (0.0008) -[2023-10-15 03:32:07,747][88298] Updated weights for policy 0, policy_version 31980 (0.0012) -[2023-10-15 03:32:08,128][88298] Updated weights for policy 0, policy_version 31990 (0.0011) -[2023-10-15 03:32:08,491][88298] Updated weights for policy 0, policy_version 32000 (0.0009) -[2023-10-15 03:32:08,534][87330] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 65699840. Throughput: 0: 1751.0, 1: 1738.4. Samples: 16426668. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-15 03:32:08,535][87330] Avg episode reward: [(0, '22.650'), (1, '22.510')] -[2023-10-15 03:32:10,991][88300] Updated weights for policy 1, policy_version 32162 (0.0010) -[2023-10-15 03:32:11,357][88300] Updated weights for policy 1, policy_version 32172 (0.0008) -[2023-10-15 03:32:11,714][88300] Updated weights for policy 1, policy_version 32182 (0.0007) -[2023-10-15 03:32:12,084][88300] Updated weights for policy 1, policy_version 32192 (0.0007) -[2023-10-15 03:32:12,277][88298] Updated weights for policy 0, policy_version 32010 (0.0008) -[2023-10-15 03:32:12,650][88298] Updated weights for policy 0, policy_version 32020 (0.0008) -[2023-10-15 03:32:13,014][88298] Updated weights for policy 0, policy_version 32030 (0.0007) -[2023-10-15 03:32:13,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 65765376. Throughput: 0: 1732.6, 1: 1729.8. Samples: 16447286. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-15 03:32:13,535][87330] Avg episode reward: [(0, '22.660'), (1, '22.460')] -[2023-10-15 03:32:15,912][88300] Updated weights for policy 1, policy_version 32202 (0.0009) -[2023-10-15 03:32:16,282][88300] Updated weights for policy 1, policy_version 32212 (0.0007) -[2023-10-15 03:32:16,654][88300] Updated weights for policy 1, policy_version 32222 (0.0008) -[2023-10-15 03:32:16,988][88298] Updated weights for policy 0, policy_version 32040 (0.0007) -[2023-10-15 03:32:17,354][88298] Updated weights for policy 0, policy_version 32050 (0.0008) -[2023-10-15 03:32:17,720][88298] Updated weights for policy 0, policy_version 32060 (0.0010) -[2023-10-15 03:32:18,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 65830912. Throughput: 0: 1752.7, 1: 1741.1. Samples: 16458250. Policy #0 lag: (min: 25.0, avg: 25.0, max: 25.0) -[2023-10-15 03:32:18,535][87330] Avg episode reward: [(0, '22.670'), (1, '22.710')] -[2023-10-15 03:32:20,455][88300] Updated weights for policy 1, policy_version 32232 (0.0008) -[2023-10-15 03:32:20,818][88300] Updated weights for policy 1, policy_version 32242 (0.0007) -[2023-10-15 03:32:21,185][88300] Updated weights for policy 1, policy_version 32252 (0.0009) -[2023-10-15 03:32:21,708][88298] Updated weights for policy 0, policy_version 32070 (0.0008) -[2023-10-15 03:32:22,082][88298] Updated weights for policy 0, policy_version 32080 (0.0008) -[2023-10-15 03:32:22,446][88298] Updated weights for policy 0, policy_version 32090 (0.0008) -[2023-10-15 03:32:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 65896448. Throughput: 0: 1745.0, 1: 1728.9. Samples: 16478948. Policy #0 lag: (min: 25.0, avg: 25.0, max: 25.0) -[2023-10-15 03:32:23,535][87330] Avg episode reward: [(0, '22.810'), (1, '22.550')] -[2023-10-15 03:32:24,997][88300] Updated weights for policy 1, policy_version 32262 (0.0010) -[2023-10-15 03:32:25,367][88300] Updated weights for policy 1, policy_version 32272 (0.0008) -[2023-10-15 03:32:25,742][88300] Updated weights for policy 1, policy_version 32282 (0.0009) -[2023-10-15 03:32:26,442][88298] Updated weights for policy 0, policy_version 32100 (0.0008) -[2023-10-15 03:32:26,803][88298] Updated weights for policy 0, policy_version 32110 (0.0010) -[2023-10-15 03:32:27,176][88298] Updated weights for policy 0, policy_version 32120 (0.0007) -[2023-10-15 03:32:28,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 65961984. Throughput: 0: 1721.2, 1: 1743.9. Samples: 16499752. Policy #0 lag: (min: 25.0, avg: 25.0, max: 25.0) -[2023-10-15 03:32:28,534][87330] Avg episode reward: [(0, '22.790'), (1, '22.520')] -[2023-10-15 03:32:29,613][88300] Updated weights for policy 1, policy_version 32292 (0.0010) -[2023-10-15 03:32:29,987][88300] Updated weights for policy 1, policy_version 32302 (0.0010) -[2023-10-15 03:32:30,353][88300] Updated weights for policy 1, policy_version 32312 (0.0010) -[2023-10-15 03:32:31,043][88298] Updated weights for policy 0, policy_version 32130 (0.0007) -[2023-10-15 03:32:31,420][88298] Updated weights for policy 0, policy_version 32140 (0.0007) -[2023-10-15 03:32:31,788][88298] Updated weights for policy 0, policy_version 32150 (0.0007) -[2023-10-15 03:32:32,166][88298] Updated weights for policy 0, policy_version 32160 (0.0008) -[2023-10-15 03:32:33,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 66027520. Throughput: 0: 1752.8, 1: 1730.5. Samples: 16510480. Policy #0 lag: (min: 25.0, avg: 25.0, max: 25.0) -[2023-10-15 03:32:33,534][87330] Avg episode reward: [(0, '22.790'), (1, '22.520')] -[2023-10-15 03:32:34,343][88300] Updated weights for policy 1, policy_version 32322 (0.0010) -[2023-10-15 03:32:34,710][88300] Updated weights for policy 1, policy_version 32332 (0.0010) -[2023-10-15 03:32:35,076][88300] Updated weights for policy 1, policy_version 32342 (0.0008) -[2023-10-15 03:32:35,443][88300] Updated weights for policy 1, policy_version 32352 (0.0009) -[2023-10-15 03:32:35,901][88298] Updated weights for policy 0, policy_version 32170 (0.0009) -[2023-10-15 03:32:36,273][88298] Updated weights for policy 0, policy_version 32180 (0.0008) -[2023-10-15 03:32:36,645][88298] Updated weights for policy 0, policy_version 32190 (0.0008) -[2023-10-15 03:32:38,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 66093056. Throughput: 0: 1729.7, 1: 1736.7. Samples: 16531142. Policy #0 lag: (min: 25.0, avg: 25.0, max: 25.0) -[2023-10-15 03:32:38,535][87330] Avg episode reward: [(0, '22.790'), (1, '22.340')] -[2023-10-15 03:32:39,454][88300] Updated weights for policy 1, policy_version 32362 (0.0008) -[2023-10-15 03:32:39,825][88300] Updated weights for policy 1, policy_version 32372 (0.0010) -[2023-10-15 03:32:40,193][88300] Updated weights for policy 1, policy_version 32382 (0.0009) -[2023-10-15 03:32:40,506][88298] Updated weights for policy 0, policy_version 32200 (0.0009) -[2023-10-15 03:32:40,872][88298] Updated weights for policy 0, policy_version 32210 (0.0008) -[2023-10-15 03:32:41,242][88298] Updated weights for policy 0, policy_version 32220 (0.0008) -[2023-10-15 03:32:43,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 66158592. Throughput: 0: 1730.8, 1: 1765.6. Samples: 16552792. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:32:43,535][87330] Avg episode reward: [(0, '22.800'), (1, '22.280')] -[2023-10-15 03:32:43,868][88300] Updated weights for policy 1, policy_version 32392 (0.0010) -[2023-10-15 03:32:44,246][88300] Updated weights for policy 1, policy_version 32402 (0.0010) -[2023-10-15 03:32:44,613][88300] Updated weights for policy 1, policy_version 32412 (0.0009) -[2023-10-15 03:32:45,055][88298] Updated weights for policy 0, policy_version 32230 (0.0009) -[2023-10-15 03:32:45,423][88298] Updated weights for policy 0, policy_version 32240 (0.0008) -[2023-10-15 03:32:45,804][88298] Updated weights for policy 0, policy_version 32250 (0.0008) -[2023-10-15 03:32:48,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 66224128. Throughput: 0: 1746.1, 1: 1731.1. Samples: 16562700. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:32:48,534][87330] Avg episode reward: [(0, '22.820'), (1, '22.140')] -[2023-10-15 03:32:48,578][88300] Updated weights for policy 1, policy_version 32422 (0.0008) -[2023-10-15 03:32:48,941][88300] Updated weights for policy 1, policy_version 32432 (0.0008) -[2023-10-15 03:32:49,314][88300] Updated weights for policy 1, policy_version 32442 (0.0007) -[2023-10-15 03:32:49,787][88298] Updated weights for policy 0, policy_version 32260 (0.0008) -[2023-10-15 03:32:50,156][88298] Updated weights for policy 0, policy_version 32270 (0.0008) -[2023-10-15 03:32:50,533][88298] Updated weights for policy 0, policy_version 32280 (0.0007) -[2023-10-15 03:32:53,164][88300] Updated weights for policy 1, policy_version 32452 (0.0007) -[2023-10-15 03:32:53,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 66289664. Throughput: 0: 1733.7, 1: 1757.0. Samples: 16583752. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:32:53,535][87330] Avg episode reward: [(0, '22.560'), (1, '22.220')] -[2023-10-15 03:32:53,541][88300] Updated weights for policy 1, policy_version 32462 (0.0009) -[2023-10-15 03:32:53,912][88300] Updated weights for policy 1, policy_version 32472 (0.0008) -[2023-10-15 03:32:54,457][88298] Updated weights for policy 0, policy_version 32290 (0.0008) -[2023-10-15 03:32:54,833][88298] Updated weights for policy 0, policy_version 32300 (0.0009) -[2023-10-15 03:32:55,201][88298] Updated weights for policy 0, policy_version 32310 (0.0007) -[2023-10-15 03:32:55,566][88298] Updated weights for policy 0, policy_version 32320 (0.0008) -[2023-10-15 03:32:57,814][88300] Updated weights for policy 1, policy_version 32482 (0.0009) -[2023-10-15 03:32:58,174][88300] Updated weights for policy 1, policy_version 32492 (0.0009) -[2023-10-15 03:32:58,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 66355200. Throughput: 0: 1753.1, 1: 1748.9. Samples: 16604874. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:32:58,535][87330] Avg episode reward: [(0, '22.590'), (1, '22.400')] -[2023-10-15 03:32:58,545][88300] Updated weights for policy 1, policy_version 32502 (0.0007) -[2023-10-15 03:32:58,548][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000032320_33095680.pth... -[2023-10-15 03:32:58,581][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000030720_31457280.pth -[2023-10-15 03:32:58,585][87905] Saving a milestone ./train_atari/atari_seaquest_APPO/checkpoint_p0/milestones/checkpoint_000032320_33095680.pth -[2023-10-15 03:32:58,907][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000032512_33292288.pth... -[2023-10-15 03:32:58,911][88300] Updated weights for policy 1, policy_version 32512 (0.0007) -[2023-10-15 03:32:58,936][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000030880_31621120.pth -[2023-10-15 03:32:58,939][88033] Saving a milestone ./train_atari/atari_seaquest_APPO/checkpoint_p1/milestones/checkpoint_000032512_33292288.pth -[2023-10-15 03:32:59,483][88298] Updated weights for policy 0, policy_version 32330 (0.0007) -[2023-10-15 03:32:59,859][88298] Updated weights for policy 0, policy_version 32340 (0.0010) -[2023-10-15 03:33:00,233][88298] Updated weights for policy 0, policy_version 32350 (0.0011) -[2023-10-15 03:33:02,754][88300] Updated weights for policy 1, policy_version 32522 (0.0008) -[2023-10-15 03:33:03,119][88300] Updated weights for policy 1, policy_version 32532 (0.0011) -[2023-10-15 03:33:03,491][88300] Updated weights for policy 1, policy_version 32542 (0.0009) -[2023-10-15 03:33:03,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 66420736. Throughput: 0: 1733.3, 1: 1752.3. Samples: 16615100. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:33:03,534][87330] Avg episode reward: [(0, '22.620'), (1, '22.280')] -[2023-10-15 03:33:04,091][88298] Updated weights for policy 0, policy_version 32360 (0.0008) -[2023-10-15 03:33:04,464][88298] Updated weights for policy 0, policy_version 32370 (0.0010) -[2023-10-15 03:33:04,839][88298] Updated weights for policy 0, policy_version 32380 (0.0008) -[2023-10-15 03:33:07,360][88300] Updated weights for policy 1, policy_version 32552 (0.0009) -[2023-10-15 03:33:07,724][88300] Updated weights for policy 1, policy_version 32562 (0.0009) -[2023-10-15 03:33:08,078][88300] Updated weights for policy 1, policy_version 32572 (0.0009) -[2023-10-15 03:33:08,534][87330] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 66519040. Throughput: 0: 1743.4, 1: 1759.6. Samples: 16636584. Policy #0 lag: (min: 27.0, avg: 34.1, max: 59.0) -[2023-10-15 03:33:08,535][87330] Avg episode reward: [(0, '22.400'), (1, '22.310')] -[2023-10-15 03:33:08,736][88298] Updated weights for policy 0, policy_version 32390 (0.0009) -[2023-10-15 03:33:09,105][88298] Updated weights for policy 0, policy_version 32400 (0.0008) -[2023-10-15 03:33:09,481][88298] Updated weights for policy 0, policy_version 32410 (0.0009) -[2023-10-15 03:33:12,013][88300] Updated weights for policy 1, policy_version 32582 (0.0008) -[2023-10-15 03:33:12,382][88300] Updated weights for policy 1, policy_version 32592 (0.0007) -[2023-10-15 03:33:12,746][88300] Updated weights for policy 1, policy_version 32602 (0.0010) -[2023-10-15 03:33:13,519][88298] Updated weights for policy 0, policy_version 32420 (0.0009) -[2023-10-15 03:33:13,534][87330] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 66584576. Throughput: 0: 1762.7, 1: 1729.5. Samples: 16656898. Policy #0 lag: (min: 27.0, avg: 34.1, max: 59.0) -[2023-10-15 03:33:13,534][87330] Avg episode reward: [(0, '22.390'), (1, '22.430')] -[2023-10-15 03:33:13,888][88298] Updated weights for policy 0, policy_version 32430 (0.0011) -[2023-10-15 03:33:14,255][88298] Updated weights for policy 0, policy_version 32440 (0.0010) -[2023-10-15 03:33:16,595][88300] Updated weights for policy 1, policy_version 32612 (0.0009) -[2023-10-15 03:33:16,962][88300] Updated weights for policy 1, policy_version 32622 (0.0010) -[2023-10-15 03:33:17,338][88300] Updated weights for policy 1, policy_version 32632 (0.0008) -[2023-10-15 03:33:18,111][88298] Updated weights for policy 0, policy_version 32450 (0.0010) -[2023-10-15 03:33:18,477][88298] Updated weights for policy 0, policy_version 32460 (0.0008) -[2023-10-15 03:33:18,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 66650112. Throughput: 0: 1728.6, 1: 1760.9. Samples: 16667506. Policy #0 lag: (min: 27.0, avg: 34.1, max: 59.0) -[2023-10-15 03:33:18,535][87330] Avg episode reward: [(0, '22.360'), (1, '22.440')] -[2023-10-15 03:33:18,851][88298] Updated weights for policy 0, policy_version 32470 (0.0007) -[2023-10-15 03:33:19,223][88298] Updated weights for policy 0, policy_version 32480 (0.0007) -[2023-10-15 03:33:21,331][88300] Updated weights for policy 1, policy_version 32642 (0.0008) -[2023-10-15 03:33:21,696][88300] Updated weights for policy 1, policy_version 32652 (0.0011) -[2023-10-15 03:33:22,068][88300] Updated weights for policy 1, policy_version 32662 (0.0010) -[2023-10-15 03:33:22,444][88300] Updated weights for policy 1, policy_version 32672 (0.0009) -[2023-10-15 03:33:23,069][88298] Updated weights for policy 0, policy_version 32490 (0.0010) -[2023-10-15 03:33:23,450][88298] Updated weights for policy 0, policy_version 32500 (0.0009) -[2023-10-15 03:33:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 66715648. Throughput: 0: 1753.7, 1: 1731.6. Samples: 16687982. Policy #0 lag: (min: 27.0, avg: 34.1, max: 59.0) -[2023-10-15 03:33:23,534][87330] Avg episode reward: [(0, '22.180'), (1, '22.560')] -[2023-10-15 03:33:23,820][88298] Updated weights for policy 0, policy_version 32510 (0.0009) -[2023-10-15 03:33:26,343][88300] Updated weights for policy 1, policy_version 32682 (0.0011) -[2023-10-15 03:33:26,716][88300] Updated weights for policy 1, policy_version 32692 (0.0008) -[2023-10-15 03:33:27,089][88300] Updated weights for policy 1, policy_version 32702 (0.0007) -[2023-10-15 03:33:27,794][88298] Updated weights for policy 0, policy_version 32520 (0.0007) -[2023-10-15 03:33:28,172][88298] Updated weights for policy 0, policy_version 32530 (0.0009) -[2023-10-15 03:33:28,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 66781184. Throughput: 0: 1744.0, 1: 1721.5. Samples: 16708738. Policy #0 lag: (min: 27.0, avg: 34.1, max: 59.0) -[2023-10-15 03:33:28,534][87330] Avg episode reward: [(0, '22.330'), (1, '22.560')] -[2023-10-15 03:33:28,549][88298] Updated weights for policy 0, policy_version 32540 (0.0007) -[2023-10-15 03:33:30,868][88300] Updated weights for policy 1, policy_version 32712 (0.0008) -[2023-10-15 03:33:31,233][88300] Updated weights for policy 1, policy_version 32722 (0.0008) -[2023-10-15 03:33:31,594][88300] Updated weights for policy 1, policy_version 32732 (0.0011) -[2023-10-15 03:33:32,433][88298] Updated weights for policy 0, policy_version 32550 (0.0008) -[2023-10-15 03:33:32,801][88298] Updated weights for policy 0, policy_version 32560 (0.0007) -[2023-10-15 03:33:33,175][88298] Updated weights for policy 0, policy_version 32570 (0.0007) -[2023-10-15 03:33:33,534][87330] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 66879488. Throughput: 0: 1743.6, 1: 1739.0. Samples: 16719418. Policy #0 lag: (min: 31.0, avg: 32.5, max: 56.0) -[2023-10-15 03:33:33,535][87330] Avg episode reward: [(0, '22.340'), (1, '22.540')] -[2023-10-15 03:33:35,726][88300] Updated weights for policy 1, policy_version 32742 (0.0009) -[2023-10-15 03:33:36,098][88300] Updated weights for policy 1, policy_version 32752 (0.0008) -[2023-10-15 03:33:36,476][88300] Updated weights for policy 1, policy_version 32762 (0.0012) -[2023-10-15 03:33:36,998][88298] Updated weights for policy 0, policy_version 32580 (0.0007) -[2023-10-15 03:33:37,372][88298] Updated weights for policy 0, policy_version 32590 (0.0008) -[2023-10-15 03:33:37,744][88298] Updated weights for policy 0, policy_version 32600 (0.0007) -[2023-10-15 03:33:38,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 66945024. Throughput: 0: 1756.6, 1: 1721.2. Samples: 16740252. Policy #0 lag: (min: 31.0, avg: 32.5, max: 56.0) -[2023-10-15 03:33:38,534][87330] Avg episode reward: [(0, '22.360'), (1, '22.650')] -[2023-10-15 03:33:40,460][88300] Updated weights for policy 1, policy_version 32772 (0.0009) -[2023-10-15 03:33:40,823][88300] Updated weights for policy 1, policy_version 32782 (0.0010) -[2023-10-15 03:33:41,195][88300] Updated weights for policy 1, policy_version 32792 (0.0011) -[2023-10-15 03:33:41,513][88298] Updated weights for policy 0, policy_version 32610 (0.0009) -[2023-10-15 03:33:41,889][88298] Updated weights for policy 0, policy_version 32620 (0.0009) -[2023-10-15 03:33:42,259][88298] Updated weights for policy 0, policy_version 32630 (0.0008) -[2023-10-15 03:33:42,632][88298] Updated weights for policy 0, policy_version 32640 (0.0009) -[2023-10-15 03:33:43,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 67010560. Throughput: 0: 1724.4, 1: 1734.9. Samples: 16760542. Policy #0 lag: (min: 31.0, avg: 32.5, max: 56.0) -[2023-10-15 03:33:43,535][87330] Avg episode reward: [(0, '22.400'), (1, '22.650')] -[2023-10-15 03:33:45,054][88300] Updated weights for policy 1, policy_version 32802 (0.0008) -[2023-10-15 03:33:45,421][88300] Updated weights for policy 1, policy_version 32812 (0.0007) -[2023-10-15 03:33:45,789][88300] Updated weights for policy 1, policy_version 32822 (0.0008) -[2023-10-15 03:33:46,151][88300] Updated weights for policy 1, policy_version 32832 (0.0009) -[2023-10-15 03:33:46,435][88298] Updated weights for policy 0, policy_version 32650 (0.0009) -[2023-10-15 03:33:46,802][88298] Updated weights for policy 0, policy_version 32660 (0.0008) -[2023-10-15 03:33:47,172][88298] Updated weights for policy 0, policy_version 32670 (0.0007) -[2023-10-15 03:33:48,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 67076096. Throughput: 0: 1753.7, 1: 1720.1. Samples: 16771420. Policy #0 lag: (min: 31.0, avg: 32.5, max: 56.0) -[2023-10-15 03:33:48,535][87330] Avg episode reward: [(0, '22.290'), (1, '22.640')] -[2023-10-15 03:33:50,039][88300] Updated weights for policy 1, policy_version 32842 (0.0011) -[2023-10-15 03:33:50,407][88300] Updated weights for policy 1, policy_version 32852 (0.0009) -[2023-10-15 03:33:50,762][88300] Updated weights for policy 1, policy_version 32862 (0.0008) -[2023-10-15 03:33:51,060][88298] Updated weights for policy 0, policy_version 32680 (0.0009) -[2023-10-15 03:33:51,436][88298] Updated weights for policy 0, policy_version 32690 (0.0010) -[2023-10-15 03:33:51,805][88298] Updated weights for policy 0, policy_version 32700 (0.0009) -[2023-10-15 03:33:53,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 67141632. Throughput: 0: 1728.4, 1: 1726.2. Samples: 16792040. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-15 03:33:53,535][87330] Avg episode reward: [(0, '22.280'), (1, '22.610')] -[2023-10-15 03:33:54,559][88300] Updated weights for policy 1, policy_version 32872 (0.0007) -[2023-10-15 03:33:54,928][88300] Updated weights for policy 1, policy_version 32882 (0.0008) -[2023-10-15 03:33:55,297][88300] Updated weights for policy 1, policy_version 32892 (0.0009) -[2023-10-15 03:33:55,702][88298] Updated weights for policy 0, policy_version 32710 (0.0007) -[2023-10-15 03:33:56,074][88298] Updated weights for policy 0, policy_version 32720 (0.0007) -[2023-10-15 03:33:56,454][88298] Updated weights for policy 0, policy_version 32730 (0.0007) -[2023-10-15 03:33:58,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 67207168. Throughput: 0: 1727.5, 1: 1752.0. Samples: 16813474. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-15 03:33:58,535][87330] Avg episode reward: [(0, '22.420'), (1, '22.640')] -[2023-10-15 03:33:59,272][88300] Updated weights for policy 1, policy_version 32902 (0.0009) -[2023-10-15 03:33:59,648][88300] Updated weights for policy 1, policy_version 32912 (0.0009) -[2023-10-15 03:34:00,019][88300] Updated weights for policy 1, policy_version 32922 (0.0009) -[2023-10-15 03:34:00,307][88298] Updated weights for policy 0, policy_version 32740 (0.0008) -[2023-10-15 03:34:00,674][88298] Updated weights for policy 0, policy_version 32750 (0.0009) -[2023-10-15 03:34:01,052][88298] Updated weights for policy 0, policy_version 32760 (0.0008) -[2023-10-15 03:34:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 67272704. Throughput: 0: 1748.4, 1: 1723.5. Samples: 16823740. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-15 03:34:03,535][87330] Avg episode reward: [(0, '22.360'), (1, '22.680')] -[2023-10-15 03:34:03,936][88300] Updated weights for policy 1, policy_version 32932 (0.0009) -[2023-10-15 03:34:04,304][88300] Updated weights for policy 1, policy_version 32942 (0.0008) -[2023-10-15 03:34:04,670][88300] Updated weights for policy 1, policy_version 32952 (0.0009) -[2023-10-15 03:34:04,991][88298] Updated weights for policy 0, policy_version 32770 (0.0007) -[2023-10-15 03:34:05,364][88298] Updated weights for policy 0, policy_version 32780 (0.0009) -[2023-10-15 03:34:05,741][88298] Updated weights for policy 0, policy_version 32790 (0.0008) -[2023-10-15 03:34:06,108][88298] Updated weights for policy 0, policy_version 32800 (0.0008) -[2023-10-15 03:34:08,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 67338240. Throughput: 0: 1729.3, 1: 1752.6. Samples: 16844668. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-15 03:34:08,534][87330] Avg episode reward: [(0, '22.350'), (1, '22.850')] -[2023-10-15 03:34:08,554][88300] Updated weights for policy 1, policy_version 32962 (0.0007) -[2023-10-15 03:34:08,923][88300] Updated weights for policy 1, policy_version 32972 (0.0009) -[2023-10-15 03:34:09,299][88300] Updated weights for policy 1, policy_version 32982 (0.0011) -[2023-10-15 03:34:09,668][88300] Updated weights for policy 1, policy_version 32992 (0.0009) -[2023-10-15 03:34:09,982][88298] Updated weights for policy 0, policy_version 32810 (0.0010) -[2023-10-15 03:34:10,357][88298] Updated weights for policy 0, policy_version 32820 (0.0009) -[2023-10-15 03:34:10,727][88298] Updated weights for policy 0, policy_version 32830 (0.0010) -[2023-10-15 03:34:13,329][88300] Updated weights for policy 1, policy_version 33002 (0.0008) -[2023-10-15 03:34:13,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 67403776. Throughput: 0: 1742.0, 1: 1760.6. Samples: 16866356. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-15 03:34:13,535][87330] Avg episode reward: [(0, '22.540'), (1, '22.820')] -[2023-10-15 03:34:13,705][88300] Updated weights for policy 1, policy_version 33012 (0.0008) -[2023-10-15 03:34:14,078][88300] Updated weights for policy 1, policy_version 33022 (0.0009) -[2023-10-15 03:34:14,723][88298] Updated weights for policy 0, policy_version 32840 (0.0007) -[2023-10-15 03:34:15,104][88298] Updated weights for policy 0, policy_version 32850 (0.0007) -[2023-10-15 03:34:15,478][88298] Updated weights for policy 0, policy_version 32860 (0.0009) -[2023-10-15 03:34:18,143][88300] Updated weights for policy 1, policy_version 33032 (0.0007) -[2023-10-15 03:34:18,516][88300] Updated weights for policy 1, policy_version 33042 (0.0008) -[2023-10-15 03:34:18,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 67469312. Throughput: 0: 1728.4, 1: 1744.7. Samples: 16875704. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-15 03:34:18,535][87330] Avg episode reward: [(0, '22.650'), (1, '22.810')] -[2023-10-15 03:34:18,886][88300] Updated weights for policy 1, policy_version 33052 (0.0007) -[2023-10-15 03:34:19,502][88298] Updated weights for policy 0, policy_version 32870 (0.0009) -[2023-10-15 03:34:19,869][88298] Updated weights for policy 0, policy_version 32880 (0.0010) -[2023-10-15 03:34:20,246][88298] Updated weights for policy 0, policy_version 32890 (0.0009) -[2023-10-15 03:34:22,820][88300] Updated weights for policy 1, policy_version 33062 (0.0008) -[2023-10-15 03:34:23,183][88300] Updated weights for policy 1, policy_version 33072 (0.0007) -[2023-10-15 03:34:23,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 67534848. Throughput: 0: 1725.3, 1: 1761.3. Samples: 16897152. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-15 03:34:23,535][87330] Avg episode reward: [(0, '22.660'), (1, '22.570')] -[2023-10-15 03:34:23,549][88300] Updated weights for policy 1, policy_version 33082 (0.0008) -[2023-10-15 03:34:23,988][88298] Updated weights for policy 0, policy_version 32900 (0.0010) -[2023-10-15 03:34:24,356][88298] Updated weights for policy 0, policy_version 32910 (0.0009) -[2023-10-15 03:34:24,729][88298] Updated weights for policy 0, policy_version 32920 (0.0009) -[2023-10-15 03:34:27,351][88300] Updated weights for policy 1, policy_version 33092 (0.0009) -[2023-10-15 03:34:27,708][88300] Updated weights for policy 1, policy_version 33102 (0.0007) -[2023-10-15 03:34:28,077][88300] Updated weights for policy 1, policy_version 33112 (0.0008) -[2023-10-15 03:34:28,534][87330] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 67633152. Throughput: 0: 1750.9, 1: 1738.3. Samples: 16917554. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-15 03:34:28,534][87330] Avg episode reward: [(0, '22.620'), (1, '22.540')] -[2023-10-15 03:34:28,811][88298] Updated weights for policy 0, policy_version 32930 (0.0010) -[2023-10-15 03:34:29,180][88298] Updated weights for policy 0, policy_version 32940 (0.0008) -[2023-10-15 03:34:29,555][88298] Updated weights for policy 0, policy_version 32950 (0.0010) -[2023-10-15 03:34:29,922][88298] Updated weights for policy 0, policy_version 32960 (0.0009) -[2023-10-15 03:34:32,035][88300] Updated weights for policy 1, policy_version 33122 (0.0007) -[2023-10-15 03:34:32,406][88300] Updated weights for policy 1, policy_version 33132 (0.0007) -[2023-10-15 03:34:32,780][88300] Updated weights for policy 1, policy_version 33142 (0.0008) -[2023-10-15 03:34:33,149][88300] Updated weights for policy 1, policy_version 33152 (0.0009) -[2023-10-15 03:34:33,534][87330] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 67698688. Throughput: 0: 1722.0, 1: 1764.4. Samples: 16928312. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-15 03:34:33,535][87330] Avg episode reward: [(0, '22.720'), (1, '22.330')] -[2023-10-15 03:34:33,784][88298] Updated weights for policy 0, policy_version 32970 (0.0008) -[2023-10-15 03:34:34,154][88298] Updated weights for policy 0, policy_version 32980 (0.0009) -[2023-10-15 03:34:34,525][88298] Updated weights for policy 0, policy_version 32990 (0.0009) -[2023-10-15 03:34:37,015][88300] Updated weights for policy 1, policy_version 33162 (0.0009) -[2023-10-15 03:34:37,381][88300] Updated weights for policy 1, policy_version 33172 (0.0008) -[2023-10-15 03:34:37,752][88300] Updated weights for policy 1, policy_version 33182 (0.0007) -[2023-10-15 03:34:38,419][88298] Updated weights for policy 0, policy_version 33000 (0.0008) -[2023-10-15 03:34:38,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 67764224. Throughput: 0: 1741.6, 1: 1748.7. Samples: 16949104. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-15 03:34:38,534][87330] Avg episode reward: [(0, '22.870'), (1, '22.300')] -[2023-10-15 03:34:38,793][88298] Updated weights for policy 0, policy_version 33010 (0.0008) -[2023-10-15 03:34:39,163][88298] Updated weights for policy 0, policy_version 33020 (0.0007) -[2023-10-15 03:34:41,643][88300] Updated weights for policy 1, policy_version 33192 (0.0008) -[2023-10-15 03:34:42,001][88300] Updated weights for policy 1, policy_version 33202 (0.0008) -[2023-10-15 03:34:42,366][88300] Updated weights for policy 1, policy_version 33212 (0.0008) -[2023-10-15 03:34:43,271][88298] Updated weights for policy 0, policy_version 33030 (0.0009) -[2023-10-15 03:34:43,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 67829760. Throughput: 0: 1741.3, 1: 1731.7. Samples: 16969762. Policy #0 lag: (min: 13.0, avg: 18.6, max: 45.0) -[2023-10-15 03:34:43,535][87330] Avg episode reward: [(0, '22.850'), (1, '22.290')] -[2023-10-15 03:34:43,652][88298] Updated weights for policy 0, policy_version 33040 (0.0008) -[2023-10-15 03:34:44,013][88298] Updated weights for policy 0, policy_version 33050 (0.0008) -[2023-10-15 03:34:46,272][88300] Updated weights for policy 1, policy_version 33222 (0.0008) -[2023-10-15 03:34:46,645][88300] Updated weights for policy 1, policy_version 33232 (0.0009) -[2023-10-15 03:34:47,004][88300] Updated weights for policy 1, policy_version 33242 (0.0009) -[2023-10-15 03:34:47,964][88298] Updated weights for policy 0, policy_version 33060 (0.0009) -[2023-10-15 03:34:48,340][88298] Updated weights for policy 0, policy_version 33070 (0.0010) -[2023-10-15 03:34:48,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 67895296. Throughput: 0: 1722.5, 1: 1760.7. Samples: 16980484. Policy #0 lag: (min: 13.0, avg: 18.6, max: 45.0) -[2023-10-15 03:34:48,535][87330] Avg episode reward: [(0, '22.700'), (1, '22.280')] -[2023-10-15 03:34:48,703][88298] Updated weights for policy 0, policy_version 33080 (0.0008) -[2023-10-15 03:34:50,835][88300] Updated weights for policy 1, policy_version 33252 (0.0010) -[2023-10-15 03:34:51,192][88300] Updated weights for policy 1, policy_version 33262 (0.0008) -[2023-10-15 03:34:51,564][88300] Updated weights for policy 1, policy_version 33272 (0.0008) -[2023-10-15 03:34:52,499][88298] Updated weights for policy 0, policy_version 33090 (0.0010) -[2023-10-15 03:34:52,865][88298] Updated weights for policy 0, policy_version 33100 (0.0010) -[2023-10-15 03:34:53,239][88298] Updated weights for policy 0, policy_version 33110 (0.0007) -[2023-10-15 03:34:53,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 67960832. Throughput: 0: 1739.1, 1: 1728.7. Samples: 17000722. Policy #0 lag: (min: 13.0, avg: 18.6, max: 45.0) -[2023-10-15 03:34:53,535][87330] Avg episode reward: [(0, '22.560'), (1, '22.150')] -[2023-10-15 03:34:53,603][88298] Updated weights for policy 0, policy_version 33120 (0.0007) -[2023-10-15 03:34:55,312][88300] Updated weights for policy 1, policy_version 33282 (0.0008) -[2023-10-15 03:34:55,685][88300] Updated weights for policy 1, policy_version 33292 (0.0011) -[2023-10-15 03:34:56,058][88300] Updated weights for policy 1, policy_version 33302 (0.0009) -[2023-10-15 03:34:56,431][88300] Updated weights for policy 1, policy_version 33312 (0.0008) -[2023-10-15 03:34:57,584][88298] Updated weights for policy 0, policy_version 33130 (0.0009) -[2023-10-15 03:34:57,953][88298] Updated weights for policy 0, policy_version 33140 (0.0010) -[2023-10-15 03:34:58,330][88298] Updated weights for policy 0, policy_version 33150 (0.0010) -[2023-10-15 03:34:58,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 68059136. Throughput: 0: 1720.4, 1: 1739.6. Samples: 17022054. Policy #0 lag: (min: 13.0, avg: 18.6, max: 45.0) -[2023-10-15 03:34:58,534][87330] Avg episode reward: [(0, '22.620'), (1, '22.360')] -[2023-10-15 03:34:58,542][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000033152_33947648.pth... -[2023-10-15 03:34:58,542][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000033312_34111488.pth... -[2023-10-15 03:34:58,579][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000031520_32276480.pth -[2023-10-15 03:34:58,584][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000031680_32440320.pth -[2023-10-15 03:35:00,490][88300] Updated weights for policy 1, policy_version 33322 (0.0009) -[2023-10-15 03:35:00,864][88300] Updated weights for policy 1, policy_version 33332 (0.0008) -[2023-10-15 03:35:01,241][88300] Updated weights for policy 1, policy_version 33342 (0.0008) -[2023-10-15 03:35:02,370][88298] Updated weights for policy 0, policy_version 33160 (0.0007) -[2023-10-15 03:35:02,751][88298] Updated weights for policy 0, policy_version 33170 (0.0008) -[2023-10-15 03:35:03,131][88298] Updated weights for policy 0, policy_version 33180 (0.0007) -[2023-10-15 03:35:03,534][87330] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 68124672. Throughput: 0: 1736.1, 1: 1739.8. Samples: 17032118. Policy #0 lag: (min: 19.0, avg: 26.4, max: 51.0) -[2023-10-15 03:35:03,534][87330] Avg episode reward: [(0, '22.430'), (1, '22.550')] -[2023-10-15 03:35:05,004][88300] Updated weights for policy 1, policy_version 33352 (0.0010) -[2023-10-15 03:35:05,376][88300] Updated weights for policy 1, policy_version 33362 (0.0008) -[2023-10-15 03:35:05,739][88300] Updated weights for policy 1, policy_version 33372 (0.0007) -[2023-10-15 03:35:07,133][88298] Updated weights for policy 0, policy_version 33190 (0.0007) -[2023-10-15 03:35:07,500][88298] Updated weights for policy 0, policy_version 33200 (0.0010) -[2023-10-15 03:35:07,873][88298] Updated weights for policy 0, policy_version 33210 (0.0008) -[2023-10-15 03:35:08,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 68190208. Throughput: 0: 1727.6, 1: 1736.4. Samples: 17053028. Policy #0 lag: (min: 19.0, avg: 26.4, max: 51.0) -[2023-10-15 03:35:08,534][87330] Avg episode reward: [(0, '22.400'), (1, '22.620')] -[2023-10-15 03:35:09,575][88300] Updated weights for policy 1, policy_version 33382 (0.0007) -[2023-10-15 03:35:09,944][88300] Updated weights for policy 1, policy_version 33392 (0.0011) -[2023-10-15 03:35:10,313][88300] Updated weights for policy 1, policy_version 33402 (0.0011) -[2023-10-15 03:35:11,797][88298] Updated weights for policy 0, policy_version 33220 (0.0007) -[2023-10-15 03:35:12,161][88298] Updated weights for policy 0, policy_version 33230 (0.0011) -[2023-10-15 03:35:12,531][88298] Updated weights for policy 0, policy_version 33240 (0.0010) -[2023-10-15 03:35:13,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 68255744. Throughput: 0: 1706.1, 1: 1758.3. Samples: 17073452. Policy #0 lag: (min: 19.0, avg: 26.4, max: 51.0) -[2023-10-15 03:35:13,535][87330] Avg episode reward: [(0, '22.270'), (1, '22.620')] -[2023-10-15 03:35:14,121][88300] Updated weights for policy 1, policy_version 33412 (0.0008) -[2023-10-15 03:35:14,496][88300] Updated weights for policy 1, policy_version 33422 (0.0008) -[2023-10-15 03:35:14,859][88300] Updated weights for policy 1, policy_version 33432 (0.0008) -[2023-10-15 03:35:16,355][88298] Updated weights for policy 0, policy_version 33250 (0.0010) -[2023-10-15 03:35:16,723][88298] Updated weights for policy 0, policy_version 33260 (0.0009) -[2023-10-15 03:35:17,090][88298] Updated weights for policy 0, policy_version 33270 (0.0007) -[2023-10-15 03:35:17,451][88298] Updated weights for policy 0, policy_version 33280 (0.0007) -[2023-10-15 03:35:18,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 68321280. Throughput: 0: 1731.0, 1: 1731.0. Samples: 17084104. Policy #0 lag: (min: 19.0, avg: 26.4, max: 51.0) -[2023-10-15 03:35:18,535][87330] Avg episode reward: [(0, '22.280'), (1, '22.510')] -[2023-10-15 03:35:18,765][88300] Updated weights for policy 1, policy_version 33442 (0.0009) -[2023-10-15 03:35:19,138][88300] Updated weights for policy 1, policy_version 33452 (0.0008) -[2023-10-15 03:35:19,506][88300] Updated weights for policy 1, policy_version 33462 (0.0009) -[2023-10-15 03:35:19,862][88300] Updated weights for policy 1, policy_version 33472 (0.0009) -[2023-10-15 03:35:21,370][88298] Updated weights for policy 0, policy_version 33290 (0.0007) -[2023-10-15 03:35:21,737][88298] Updated weights for policy 0, policy_version 33300 (0.0007) -[2023-10-15 03:35:22,100][88298] Updated weights for policy 0, policy_version 33310 (0.0007) -[2023-10-15 03:35:23,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 68386816. Throughput: 0: 1717.1, 1: 1747.2. Samples: 17104994. Policy #0 lag: (min: 19.0, avg: 26.4, max: 51.0) -[2023-10-15 03:35:23,534][87330] Avg episode reward: [(0, '22.430'), (1, '22.540')] -[2023-10-15 03:35:23,800][88300] Updated weights for policy 1, policy_version 33482 (0.0008) -[2023-10-15 03:35:24,167][88300] Updated weights for policy 1, policy_version 33492 (0.0011) -[2023-10-15 03:35:24,531][88300] Updated weights for policy 1, policy_version 33502 (0.0007) -[2023-10-15 03:35:25,953][88298] Updated weights for policy 0, policy_version 33320 (0.0008) -[2023-10-15 03:35:26,330][88298] Updated weights for policy 0, policy_version 33330 (0.0007) -[2023-10-15 03:35:26,704][88298] Updated weights for policy 0, policy_version 33340 (0.0007) -[2023-10-15 03:35:28,446][88300] Updated weights for policy 1, policy_version 33512 (0.0007) -[2023-10-15 03:35:28,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 68452352. Throughput: 0: 1709.9, 1: 1763.9. Samples: 17126082. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:35:28,535][87330] Avg episode reward: [(0, '22.570'), (1, '22.570')] -[2023-10-15 03:35:28,827][88300] Updated weights for policy 1, policy_version 33522 (0.0008) -[2023-10-15 03:35:29,191][88300] Updated weights for policy 1, policy_version 33532 (0.0008) -[2023-10-15 03:35:30,621][88298] Updated weights for policy 0, policy_version 33350 (0.0010) -[2023-10-15 03:35:30,997][88298] Updated weights for policy 0, policy_version 33360 (0.0011) -[2023-10-15 03:35:31,367][88298] Updated weights for policy 0, policy_version 33370 (0.0011) -[2023-10-15 03:35:33,150][88300] Updated weights for policy 1, policy_version 33542 (0.0008) -[2023-10-15 03:35:33,515][88300] Updated weights for policy 1, policy_version 33552 (0.0008) -[2023-10-15 03:35:33,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 68517888. Throughput: 0: 1732.5, 1: 1737.3. Samples: 17136626. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:35:33,535][87330] Avg episode reward: [(0, '22.530'), (1, '22.580')] -[2023-10-15 03:35:33,885][88300] Updated weights for policy 1, policy_version 33562 (0.0009) -[2023-10-15 03:35:35,195][88298] Updated weights for policy 0, policy_version 33380 (0.0010) -[2023-10-15 03:35:35,564][88298] Updated weights for policy 0, policy_version 33390 (0.0008) -[2023-10-15 03:35:35,933][88298] Updated weights for policy 0, policy_version 33400 (0.0008) -[2023-10-15 03:35:37,711][88300] Updated weights for policy 1, policy_version 33572 (0.0010) -[2023-10-15 03:35:38,075][88300] Updated weights for policy 1, policy_version 33582 (0.0007) -[2023-10-15 03:35:38,446][88300] Updated weights for policy 1, policy_version 33592 (0.0007) -[2023-10-15 03:35:38,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 68583424. Throughput: 0: 1711.2, 1: 1766.9. Samples: 17157236. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:35:38,535][87330] Avg episode reward: [(0, '22.570'), (1, '22.560')] -[2023-10-15 03:35:39,751][88298] Updated weights for policy 0, policy_version 33410 (0.0009) -[2023-10-15 03:35:40,122][88298] Updated weights for policy 0, policy_version 33420 (0.0007) -[2023-10-15 03:35:40,490][88298] Updated weights for policy 0, policy_version 33430 (0.0008) -[2023-10-15 03:35:40,868][88298] Updated weights for policy 0, policy_version 33440 (0.0010) -[2023-10-15 03:35:42,289][88300] Updated weights for policy 1, policy_version 33602 (0.0009) -[2023-10-15 03:35:42,654][88300] Updated weights for policy 1, policy_version 33612 (0.0007) -[2023-10-15 03:35:43,019][88300] Updated weights for policy 1, policy_version 33622 (0.0007) -[2023-10-15 03:35:43,392][88300] Updated weights for policy 1, policy_version 33632 (0.0007) -[2023-10-15 03:35:43,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 68681728. Throughput: 0: 1728.0, 1: 1738.0. Samples: 17178022. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:35:43,534][87330] Avg episode reward: [(0, '22.690'), (1, '22.540')] -[2023-10-15 03:35:44,752][88298] Updated weights for policy 0, policy_version 33450 (0.0011) -[2023-10-15 03:35:45,119][88298] Updated weights for policy 0, policy_version 33460 (0.0009) -[2023-10-15 03:35:45,505][88298] Updated weights for policy 0, policy_version 33470 (0.0009) -[2023-10-15 03:35:47,287][88300] Updated weights for policy 1, policy_version 33642 (0.0011) -[2023-10-15 03:35:47,650][88300] Updated weights for policy 1, policy_version 33652 (0.0009) -[2023-10-15 03:35:48,012][88300] Updated weights for policy 1, policy_version 33662 (0.0010) -[2023-10-15 03:35:48,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 68747264. Throughput: 0: 1713.7, 1: 1762.1. Samples: 17188532. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:35:48,534][87330] Avg episode reward: [(0, '22.700'), (1, '22.490')] -[2023-10-15 03:35:49,571][88298] Updated weights for policy 0, policy_version 33480 (0.0011) -[2023-10-15 03:35:49,953][88298] Updated weights for policy 0, policy_version 33490 (0.0009) -[2023-10-15 03:35:50,327][88298] Updated weights for policy 0, policy_version 33500 (0.0011) -[2023-10-15 03:35:51,953][88300] Updated weights for policy 1, policy_version 33672 (0.0009) -[2023-10-15 03:35:52,327][88300] Updated weights for policy 1, policy_version 33682 (0.0009) -[2023-10-15 03:35:52,688][88300] Updated weights for policy 1, policy_version 33692 (0.0007) -[2023-10-15 03:35:53,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.6, 300 sec: 13884.7). Total num frames: 68812800. Throughput: 0: 1723.2, 1: 1750.3. Samples: 17209336. Policy #0 lag: (min: 17.0, avg: 23.2, max: 49.0) -[2023-10-15 03:35:53,534][87330] Avg episode reward: [(0, '22.730'), (1, '22.700')] -[2023-10-15 03:35:54,188][88298] Updated weights for policy 0, policy_version 33510 (0.0009) -[2023-10-15 03:35:54,548][88298] Updated weights for policy 0, policy_version 33520 (0.0009) -[2023-10-15 03:35:54,923][88298] Updated weights for policy 0, policy_version 33530 (0.0009) -[2023-10-15 03:35:56,441][88300] Updated weights for policy 1, policy_version 33702 (0.0008) -[2023-10-15 03:35:56,813][88300] Updated weights for policy 1, policy_version 33712 (0.0010) -[2023-10-15 03:35:57,173][88300] Updated weights for policy 1, policy_version 33722 (0.0009) -[2023-10-15 03:35:58,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 68878336. Throughput: 0: 1747.9, 1: 1733.3. Samples: 17230108. Policy #0 lag: (min: 17.0, avg: 23.2, max: 49.0) -[2023-10-15 03:35:58,535][87330] Avg episode reward: [(0, '22.720'), (1, '22.700')] -[2023-10-15 03:35:58,927][88298] Updated weights for policy 0, policy_version 33540 (0.0009) -[2023-10-15 03:35:59,286][88298] Updated weights for policy 0, policy_version 33550 (0.0009) -[2023-10-15 03:35:59,653][88298] Updated weights for policy 0, policy_version 33560 (0.0009) -[2023-10-15 03:36:00,973][88300] Updated weights for policy 1, policy_version 33732 (0.0008) -[2023-10-15 03:36:01,343][88300] Updated weights for policy 1, policy_version 33742 (0.0008) -[2023-10-15 03:36:01,707][88300] Updated weights for policy 1, policy_version 33752 (0.0010) -[2023-10-15 03:36:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 68943872. Throughput: 0: 1717.6, 1: 1761.2. Samples: 17240648. Policy #0 lag: (min: 17.0, avg: 23.2, max: 49.0) -[2023-10-15 03:36:03,534][87330] Avg episode reward: [(0, '22.720'), (1, '22.650')] -[2023-10-15 03:36:03,675][88298] Updated weights for policy 0, policy_version 33570 (0.0008) -[2023-10-15 03:36:04,048][88298] Updated weights for policy 0, policy_version 33580 (0.0010) -[2023-10-15 03:36:04,415][88298] Updated weights for policy 0, policy_version 33590 (0.0008) -[2023-10-15 03:36:04,785][88298] Updated weights for policy 0, policy_version 33600 (0.0007) -[2023-10-15 03:36:05,569][88300] Updated weights for policy 1, policy_version 33762 (0.0008) -[2023-10-15 03:36:05,937][88300] Updated weights for policy 1, policy_version 33772 (0.0007) -[2023-10-15 03:36:06,306][88300] Updated weights for policy 1, policy_version 33782 (0.0008) -[2023-10-15 03:36:06,669][88300] Updated weights for policy 1, policy_version 33792 (0.0011) -[2023-10-15 03:36:08,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 69009408. Throughput: 0: 1735.1, 1: 1738.0. Samples: 17261282. Policy #0 lag: (min: 17.0, avg: 23.2, max: 49.0) -[2023-10-15 03:36:08,535][87330] Avg episode reward: [(0, '22.730'), (1, '22.600')] -[2023-10-15 03:36:08,749][88298] Updated weights for policy 0, policy_version 33610 (0.0007) -[2023-10-15 03:36:09,120][88298] Updated weights for policy 0, policy_version 33620 (0.0010) -[2023-10-15 03:36:09,492][88298] Updated weights for policy 0, policy_version 33630 (0.0011) -[2023-10-15 03:36:10,558][88300] Updated weights for policy 1, policy_version 33802 (0.0007) -[2023-10-15 03:36:10,926][88300] Updated weights for policy 1, policy_version 33812 (0.0009) -[2023-10-15 03:36:11,290][88300] Updated weights for policy 1, policy_version 33822 (0.0007) -[2023-10-15 03:36:13,481][88298] Updated weights for policy 0, policy_version 33640 (0.0008) -[2023-10-15 03:36:13,534][87330] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 69074944. Throughput: 0: 1745.5, 1: 1743.5. Samples: 17283084. Policy #0 lag: (min: 17.0, avg: 23.2, max: 49.0) -[2023-10-15 03:36:13,535][87330] Avg episode reward: [(0, '22.900'), (1, '22.630')] -[2023-10-15 03:36:13,849][88298] Updated weights for policy 0, policy_version 33650 (0.0007) -[2023-10-15 03:36:14,224][88298] Updated weights for policy 0, policy_version 33660 (0.0007) -[2023-10-15 03:36:15,048][88300] Updated weights for policy 1, policy_version 33832 (0.0008) -[2023-10-15 03:36:15,422][88300] Updated weights for policy 1, policy_version 33842 (0.0010) -[2023-10-15 03:36:15,789][88300] Updated weights for policy 1, policy_version 33852 (0.0008) -[2023-10-15 03:36:18,207][88298] Updated weights for policy 0, policy_version 33670 (0.0008) -[2023-10-15 03:36:18,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 69140480. Throughput: 0: 1723.2, 1: 1741.7. Samples: 17292550. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:36:18,535][87330] Avg episode reward: [(0, '22.930'), (1, '22.570')] -[2023-10-15 03:36:18,577][88298] Updated weights for policy 0, policy_version 33680 (0.0007) -[2023-10-15 03:36:18,956][88298] Updated weights for policy 0, policy_version 33690 (0.0007) -[2023-10-15 03:36:19,694][88300] Updated weights for policy 1, policy_version 33862 (0.0009) -[2023-10-15 03:36:20,059][88300] Updated weights for policy 1, policy_version 33872 (0.0009) -[2023-10-15 03:36:20,424][88300] Updated weights for policy 1, policy_version 33882 (0.0008) -[2023-10-15 03:36:22,774][88298] Updated weights for policy 0, policy_version 33700 (0.0007) -[2023-10-15 03:36:23,142][88298] Updated weights for policy 0, policy_version 33710 (0.0007) -[2023-10-15 03:36:23,520][88298] Updated weights for policy 0, policy_version 33720 (0.0007) -[2023-10-15 03:36:23,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 69206016. Throughput: 0: 1744.7, 1: 1739.8. Samples: 17314036. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:36:23,534][87330] Avg episode reward: [(0, '22.930'), (1, '22.550')] -[2023-10-15 03:36:24,366][88300] Updated weights for policy 1, policy_version 33892 (0.0008) -[2023-10-15 03:36:24,729][88300] Updated weights for policy 1, policy_version 33902 (0.0007) -[2023-10-15 03:36:25,098][88300] Updated weights for policy 1, policy_version 33912 (0.0007) -[2023-10-15 03:36:27,371][88298] Updated weights for policy 0, policy_version 33730 (0.0009) -[2023-10-15 03:36:27,731][88298] Updated weights for policy 0, policy_version 33740 (0.0010) -[2023-10-15 03:36:28,104][88298] Updated weights for policy 0, policy_version 33750 (0.0009) -[2023-10-15 03:36:28,466][88298] Updated weights for policy 0, policy_version 33760 (0.0009) -[2023-10-15 03:36:28,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 69304320. Throughput: 0: 1734.1, 1: 1760.0. Samples: 17335260. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:36:28,535][87330] Avg episode reward: [(0, '22.910'), (1, '22.450')] -[2023-10-15 03:36:29,053][88300] Updated weights for policy 1, policy_version 33922 (0.0007) -[2023-10-15 03:36:29,416][88300] Updated weights for policy 1, policy_version 33932 (0.0007) -[2023-10-15 03:36:29,792][88300] Updated weights for policy 1, policy_version 33942 (0.0010) -[2023-10-15 03:36:30,158][88300] Updated weights for policy 1, policy_version 33952 (0.0007) -[2023-10-15 03:36:32,461][88298] Updated weights for policy 0, policy_version 33770 (0.0009) -[2023-10-15 03:36:32,827][88298] Updated weights for policy 0, policy_version 33780 (0.0007) -[2023-10-15 03:36:33,196][88298] Updated weights for policy 0, policy_version 33790 (0.0008) -[2023-10-15 03:36:33,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 69369856. Throughput: 0: 1747.6, 1: 1737.1. Samples: 17345348. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:36:33,535][87330] Avg episode reward: [(0, '22.920'), (1, '22.490')] -[2023-10-15 03:36:34,189][88300] Updated weights for policy 1, policy_version 33962 (0.0007) -[2023-10-15 03:36:34,557][88300] Updated weights for policy 1, policy_version 33972 (0.0007) -[2023-10-15 03:36:34,924][88300] Updated weights for policy 1, policy_version 33982 (0.0011) -[2023-10-15 03:36:37,201][88298] Updated weights for policy 0, policy_version 33800 (0.0007) -[2023-10-15 03:36:37,591][88298] Updated weights for policy 0, policy_version 33810 (0.0008) -[2023-10-15 03:36:37,959][88298] Updated weights for policy 0, policy_version 33820 (0.0008) -[2023-10-15 03:36:38,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 69435392. Throughput: 0: 1744.7, 1: 1749.0. Samples: 17366550. Policy #0 lag: (min: 16.0, avg: 42.3, max: 48.0) -[2023-10-15 03:36:38,534][87330] Avg episode reward: [(0, '22.930'), (1, '22.560')] -[2023-10-15 03:36:38,961][88300] Updated weights for policy 1, policy_version 33992 (0.0009) -[2023-10-15 03:36:39,319][88300] Updated weights for policy 1, policy_version 34002 (0.0008) -[2023-10-15 03:36:39,684][88300] Updated weights for policy 1, policy_version 34012 (0.0011) -[2023-10-15 03:36:41,660][88298] Updated weights for policy 0, policy_version 33830 (0.0008) -[2023-10-15 03:36:42,028][88298] Updated weights for policy 0, policy_version 33840 (0.0008) -[2023-10-15 03:36:42,399][88298] Updated weights for policy 0, policy_version 33850 (0.0009) -[2023-10-15 03:36:43,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 69500928. Throughput: 0: 1715.1, 1: 1766.3. Samples: 17386770. Policy #0 lag: (min: 16.0, avg: 42.3, max: 48.0) -[2023-10-15 03:36:43,534][87330] Avg episode reward: [(0, '22.900'), (1, '22.540')] -[2023-10-15 03:36:43,561][88300] Updated weights for policy 1, policy_version 34022 (0.0009) -[2023-10-15 03:36:43,935][88300] Updated weights for policy 1, policy_version 34032 (0.0009) -[2023-10-15 03:36:44,305][88300] Updated weights for policy 1, policy_version 34042 (0.0008) -[2023-10-15 03:36:46,147][88298] Updated weights for policy 0, policy_version 33860 (0.0009) -[2023-10-15 03:36:46,515][88298] Updated weights for policy 0, policy_version 33870 (0.0009) -[2023-10-15 03:36:46,889][88298] Updated weights for policy 0, policy_version 33880 (0.0010) -[2023-10-15 03:36:48,242][88300] Updated weights for policy 1, policy_version 34052 (0.0008) -[2023-10-15 03:36:48,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 69566464. Throughput: 0: 1756.1, 1: 1736.2. Samples: 17397802. Policy #0 lag: (min: 16.0, avg: 42.3, max: 48.0) -[2023-10-15 03:36:48,534][87330] Avg episode reward: [(0, '22.880'), (1, '22.500')] -[2023-10-15 03:36:48,600][88300] Updated weights for policy 1, policy_version 34062 (0.0009) -[2023-10-15 03:36:48,972][88300] Updated weights for policy 1, policy_version 34072 (0.0008) -[2023-10-15 03:36:50,750][88298] Updated weights for policy 0, policy_version 33890 (0.0007) -[2023-10-15 03:36:51,118][88298] Updated weights for policy 0, policy_version 33900 (0.0007) -[2023-10-15 03:36:51,493][88298] Updated weights for policy 0, policy_version 33910 (0.0008) -[2023-10-15 03:36:51,866][88298] Updated weights for policy 0, policy_version 33920 (0.0007) -[2023-10-15 03:36:52,918][88300] Updated weights for policy 1, policy_version 34082 (0.0008) -[2023-10-15 03:36:53,291][88300] Updated weights for policy 1, policy_version 34092 (0.0007) -[2023-10-15 03:36:53,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 69632000. Throughput: 0: 1731.9, 1: 1756.2. Samples: 17418246. Policy #0 lag: (min: 16.0, avg: 42.3, max: 48.0) -[2023-10-15 03:36:53,534][87330] Avg episode reward: [(0, '22.870'), (1, '22.700')] -[2023-10-15 03:36:53,658][88300] Updated weights for policy 1, policy_version 34102 (0.0007) -[2023-10-15 03:36:54,020][88300] Updated weights for policy 1, policy_version 34112 (0.0008) -[2023-10-15 03:36:55,764][88298] Updated weights for policy 0, policy_version 33930 (0.0009) -[2023-10-15 03:36:56,146][88298] Updated weights for policy 0, policy_version 33940 (0.0008) -[2023-10-15 03:36:56,513][88298] Updated weights for policy 0, policy_version 33950 (0.0008) -[2023-10-15 03:36:57,945][88300] Updated weights for policy 1, policy_version 34122 (0.0009) -[2023-10-15 03:36:58,313][88300] Updated weights for policy 1, policy_version 34132 (0.0008) -[2023-10-15 03:36:58,534][87330] Fps is (10 sec: 13106.7, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 69697536. Throughput: 0: 1730.4, 1: 1736.1. Samples: 17439076. Policy #0 lag: (min: 16.0, avg: 42.3, max: 48.0) -[2023-10-15 03:36:58,535][87330] Avg episode reward: [(0, '22.750'), (1, '22.780')] -[2023-10-15 03:36:58,545][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000033952_34766848.pth... -[2023-10-15 03:36:58,578][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000032320_33095680.pth -[2023-10-15 03:36:58,681][88300] Updated weights for policy 1, policy_version 34142 (0.0008) -[2023-10-15 03:36:58,751][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000034144_34963456.pth... -[2023-10-15 03:36:58,789][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000032512_33292288.pth -[2023-10-15 03:37:00,390][88298] Updated weights for policy 0, policy_version 33960 (0.0008) -[2023-10-15 03:37:00,759][88298] Updated weights for policy 0, policy_version 33970 (0.0009) -[2023-10-15 03:37:01,139][88298] Updated weights for policy 0, policy_version 33980 (0.0009) -[2023-10-15 03:37:02,461][88300] Updated weights for policy 1, policy_version 34152 (0.0010) -[2023-10-15 03:37:02,821][88300] Updated weights for policy 1, policy_version 34162 (0.0009) -[2023-10-15 03:37:03,189][88300] Updated weights for policy 1, policy_version 34172 (0.0009) -[2023-10-15 03:37:03,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 69795840. Throughput: 0: 1744.3, 1: 1753.2. Samples: 17449938. Policy #0 lag: (min: 29.0, avg: 31.9, max: 61.0) -[2023-10-15 03:37:03,534][87330] Avg episode reward: [(0, '22.640'), (1, '22.780')] -[2023-10-15 03:37:04,909][88298] Updated weights for policy 0, policy_version 33990 (0.0008) -[2023-10-15 03:37:05,272][88298] Updated weights for policy 0, policy_version 34000 (0.0007) -[2023-10-15 03:37:05,646][88298] Updated weights for policy 0, policy_version 34010 (0.0008) -[2023-10-15 03:37:07,074][88300] Updated weights for policy 1, policy_version 34182 (0.0010) -[2023-10-15 03:37:07,447][88300] Updated weights for policy 1, policy_version 34192 (0.0009) -[2023-10-15 03:37:07,807][88300] Updated weights for policy 1, policy_version 34202 (0.0007) -[2023-10-15 03:37:08,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 69861376. Throughput: 0: 1731.3, 1: 1748.8. Samples: 17470640. Policy #0 lag: (min: 29.0, avg: 31.9, max: 61.0) -[2023-10-15 03:37:08,535][87330] Avg episode reward: [(0, '22.520'), (1, '22.770')] -[2023-10-15 03:37:09,568][88298] Updated weights for policy 0, policy_version 34020 (0.0009) -[2023-10-15 03:37:09,937][88298] Updated weights for policy 0, policy_version 34030 (0.0009) -[2023-10-15 03:37:10,310][88298] Updated weights for policy 0, policy_version 34040 (0.0008) -[2023-10-15 03:37:11,623][88300] Updated weights for policy 1, policy_version 34212 (0.0008) -[2023-10-15 03:37:11,994][88300] Updated weights for policy 1, policy_version 34222 (0.0010) -[2023-10-15 03:37:12,363][88300] Updated weights for policy 1, policy_version 34232 (0.0009) -[2023-10-15 03:37:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 69926912. Throughput: 0: 1744.9, 1: 1729.3. Samples: 17491596. Policy #0 lag: (min: 29.0, avg: 31.9, max: 61.0) -[2023-10-15 03:37:13,534][87330] Avg episode reward: [(0, '22.320'), (1, '22.790')] -[2023-10-15 03:37:14,217][88298] Updated weights for policy 0, policy_version 34050 (0.0008) -[2023-10-15 03:37:14,597][88298] Updated weights for policy 0, policy_version 34060 (0.0008) -[2023-10-15 03:37:14,966][88298] Updated weights for policy 0, policy_version 34070 (0.0009) -[2023-10-15 03:37:15,332][88298] Updated weights for policy 0, policy_version 34080 (0.0009) -[2023-10-15 03:37:16,127][88300] Updated weights for policy 1, policy_version 34242 (0.0007) -[2023-10-15 03:37:16,491][88300] Updated weights for policy 1, policy_version 34252 (0.0009) -[2023-10-15 03:37:16,856][88300] Updated weights for policy 1, policy_version 34262 (0.0007) -[2023-10-15 03:37:17,220][88300] Updated weights for policy 1, policy_version 34272 (0.0008) -[2023-10-15 03:37:18,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 69992448. Throughput: 0: 1731.5, 1: 1756.3. Samples: 17502296. Policy #0 lag: (min: 29.0, avg: 31.9, max: 61.0) -[2023-10-15 03:37:18,535][87330] Avg episode reward: [(0, '22.330'), (1, '22.650')] -[2023-10-15 03:37:19,175][88298] Updated weights for policy 0, policy_version 34090 (0.0008) -[2023-10-15 03:37:19,553][88298] Updated weights for policy 0, policy_version 34100 (0.0010) -[2023-10-15 03:37:19,923][88298] Updated weights for policy 0, policy_version 34110 (0.0009) -[2023-10-15 03:37:21,194][88300] Updated weights for policy 1, policy_version 34282 (0.0008) -[2023-10-15 03:37:21,562][88300] Updated weights for policy 1, policy_version 34292 (0.0009) -[2023-10-15 03:37:21,932][88300] Updated weights for policy 1, policy_version 34302 (0.0009) -[2023-10-15 03:37:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 70057984. Throughput: 0: 1738.7, 1: 1731.1. Samples: 17522692. Policy #0 lag: (min: 29.0, avg: 31.9, max: 61.0) -[2023-10-15 03:37:23,534][87330] Avg episode reward: [(0, '22.300'), (1, '22.640')] -[2023-10-15 03:37:23,772][88298] Updated weights for policy 0, policy_version 34120 (0.0007) -[2023-10-15 03:37:24,146][88298] Updated weights for policy 0, policy_version 34130 (0.0007) -[2023-10-15 03:37:24,510][88298] Updated weights for policy 0, policy_version 34140 (0.0007) -[2023-10-15 03:37:25,712][88300] Updated weights for policy 1, policy_version 34312 (0.0010) -[2023-10-15 03:37:26,080][88300] Updated weights for policy 1, policy_version 34322 (0.0008) -[2023-10-15 03:37:26,464][88300] Updated weights for policy 1, policy_version 34332 (0.0007) -[2023-10-15 03:37:28,216][88298] Updated weights for policy 0, policy_version 34150 (0.0009) -[2023-10-15 03:37:28,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 70123520. Throughput: 0: 1773.1, 1: 1732.9. Samples: 17544542. Policy #0 lag: (min: 1.0, avg: 14.5, max: 33.0) -[2023-10-15 03:37:28,534][87330] Avg episode reward: [(0, '22.410'), (1, '22.670')] -[2023-10-15 03:37:28,597][88298] Updated weights for policy 0, policy_version 34160 (0.0009) -[2023-10-15 03:37:28,971][88298] Updated weights for policy 0, policy_version 34170 (0.0008) -[2023-10-15 03:37:30,277][88300] Updated weights for policy 1, policy_version 34342 (0.0008) -[2023-10-15 03:37:30,654][88300] Updated weights for policy 1, policy_version 34352 (0.0007) -[2023-10-15 03:37:31,029][88300] Updated weights for policy 1, policy_version 34362 (0.0009) -[2023-10-15 03:37:32,912][88298] Updated weights for policy 0, policy_version 34180 (0.0007) -[2023-10-15 03:37:33,273][88298] Updated weights for policy 0, policy_version 34190 (0.0008) -[2023-10-15 03:37:33,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 70189056. Throughput: 0: 1734.0, 1: 1738.5. Samples: 17554066. Policy #0 lag: (min: 1.0, avg: 14.5, max: 33.0) -[2023-10-15 03:37:33,534][87330] Avg episode reward: [(0, '22.520'), (1, '22.560')] -[2023-10-15 03:37:33,647][88298] Updated weights for policy 0, policy_version 34200 (0.0008) -[2023-10-15 03:37:35,058][88300] Updated weights for policy 1, policy_version 34372 (0.0008) -[2023-10-15 03:37:35,428][88300] Updated weights for policy 1, policy_version 34382 (0.0009) -[2023-10-15 03:37:35,803][88300] Updated weights for policy 1, policy_version 34392 (0.0008) -[2023-10-15 03:37:37,675][88298] Updated weights for policy 0, policy_version 34210 (0.0009) -[2023-10-15 03:37:38,059][88298] Updated weights for policy 0, policy_version 34220 (0.0008) -[2023-10-15 03:37:38,428][88298] Updated weights for policy 0, policy_version 34230 (0.0008) -[2023-10-15 03:37:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 70254592. Throughput: 0: 1759.4, 1: 1733.8. Samples: 17575440. Policy #0 lag: (min: 1.0, avg: 14.5, max: 33.0) -[2023-10-15 03:37:38,534][87330] Avg episode reward: [(0, '22.270'), (1, '22.530')] -[2023-10-15 03:37:38,803][88298] Updated weights for policy 0, policy_version 34240 (0.0008) -[2023-10-15 03:37:39,710][88300] Updated weights for policy 1, policy_version 34402 (0.0009) -[2023-10-15 03:37:40,071][88300] Updated weights for policy 1, policy_version 34412 (0.0009) -[2023-10-15 03:37:40,446][88300] Updated weights for policy 1, policy_version 34422 (0.0008) -[2023-10-15 03:37:40,806][88300] Updated weights for policy 1, policy_version 34432 (0.0009) -[2023-10-15 03:37:42,755][88298] Updated weights for policy 0, policy_version 34250 (0.0007) -[2023-10-15 03:37:43,123][88298] Updated weights for policy 0, policy_version 34260 (0.0011) -[2023-10-15 03:37:43,500][88298] Updated weights for policy 0, policy_version 34270 (0.0011) -[2023-10-15 03:37:43,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 70320128. Throughput: 0: 1749.1, 1: 1751.7. Samples: 17596610. Policy #0 lag: (min: 1.0, avg: 14.5, max: 33.0) -[2023-10-15 03:37:43,534][87330] Avg episode reward: [(0, '22.350'), (1, '22.500')] -[2023-10-15 03:37:44,605][88300] Updated weights for policy 1, policy_version 34442 (0.0009) -[2023-10-15 03:37:44,966][88300] Updated weights for policy 1, policy_version 34452 (0.0009) -[2023-10-15 03:37:45,331][88300] Updated weights for policy 1, policy_version 34462 (0.0008) -[2023-10-15 03:37:47,419][88298] Updated weights for policy 0, policy_version 34280 (0.0008) -[2023-10-15 03:37:47,791][88298] Updated weights for policy 0, policy_version 34290 (0.0008) -[2023-10-15 03:37:48,163][88298] Updated weights for policy 0, policy_version 34300 (0.0009) -[2023-10-15 03:37:48,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 70418432. Throughput: 0: 1748.0, 1: 1734.4. Samples: 17606646. Policy #0 lag: (min: 23.0, avg: 23.2, max: 34.0) -[2023-10-15 03:37:48,534][87330] Avg episode reward: [(0, '22.350'), (1, '22.630')] -[2023-10-15 03:37:49,250][88300] Updated weights for policy 1, policy_version 34472 (0.0008) -[2023-10-15 03:37:49,626][88300] Updated weights for policy 1, policy_version 34482 (0.0008) -[2023-10-15 03:37:49,996][88300] Updated weights for policy 1, policy_version 34492 (0.0008) -[2023-10-15 03:37:52,106][88298] Updated weights for policy 0, policy_version 34310 (0.0009) -[2023-10-15 03:37:52,480][88298] Updated weights for policy 0, policy_version 34320 (0.0009) -[2023-10-15 03:37:52,851][88298] Updated weights for policy 0, policy_version 34330 (0.0010) -[2023-10-15 03:37:53,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 70483968. Throughput: 0: 1759.3, 1: 1736.5. Samples: 17627954. Policy #0 lag: (min: 23.0, avg: 23.2, max: 34.0) -[2023-10-15 03:37:53,535][87330] Avg episode reward: [(0, '22.210'), (1, '22.610')] -[2023-10-15 03:37:53,816][88300] Updated weights for policy 1, policy_version 34502 (0.0008) -[2023-10-15 03:37:54,190][88300] Updated weights for policy 1, policy_version 34512 (0.0008) -[2023-10-15 03:37:54,557][88300] Updated weights for policy 1, policy_version 34522 (0.0011) -[2023-10-15 03:37:56,815][88298] Updated weights for policy 0, policy_version 34340 (0.0009) -[2023-10-15 03:37:57,180][88298] Updated weights for policy 0, policy_version 34350 (0.0008) -[2023-10-15 03:37:57,551][88298] Updated weights for policy 0, policy_version 34360 (0.0008) -[2023-10-15 03:37:58,523][88300] Updated weights for policy 1, policy_version 34532 (0.0010) -[2023-10-15 03:37:58,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 70549504. Throughput: 0: 1723.1, 1: 1759.9. Samples: 17648330. Policy #0 lag: (min: 23.0, avg: 23.2, max: 34.0) -[2023-10-15 03:37:58,534][87330] Avg episode reward: [(0, '22.190'), (1, '22.640')] -[2023-10-15 03:37:58,897][88300] Updated weights for policy 1, policy_version 34542 (0.0008) -[2023-10-15 03:37:59,253][88300] Updated weights for policy 1, policy_version 34552 (0.0009) -[2023-10-15 03:38:01,456][88298] Updated weights for policy 0, policy_version 34370 (0.0008) -[2023-10-15 03:38:01,825][88298] Updated weights for policy 0, policy_version 34380 (0.0007) -[2023-10-15 03:38:02,190][88298] Updated weights for policy 0, policy_version 34390 (0.0010) -[2023-10-15 03:38:02,564][88298] Updated weights for policy 0, policy_version 34400 (0.0009) -[2023-10-15 03:38:03,123][88300] Updated weights for policy 1, policy_version 34562 (0.0008) -[2023-10-15 03:38:03,477][88300] Updated weights for policy 1, policy_version 34572 (0.0007) -[2023-10-15 03:38:03,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 70615040. Throughput: 0: 1753.1, 1: 1731.2. Samples: 17659088. Policy #0 lag: (min: 23.0, avg: 23.2, max: 34.0) -[2023-10-15 03:38:03,534][87330] Avg episode reward: [(0, '22.220'), (1, '22.610')] -[2023-10-15 03:38:03,844][88300] Updated weights for policy 1, policy_version 34582 (0.0008) -[2023-10-15 03:38:04,214][88300] Updated weights for policy 1, policy_version 34592 (0.0007) -[2023-10-15 03:38:06,309][88298] Updated weights for policy 0, policy_version 34410 (0.0009) -[2023-10-15 03:38:06,678][88298] Updated weights for policy 0, policy_version 34420 (0.0007) -[2023-10-15 03:38:07,044][88298] Updated weights for policy 0, policy_version 34430 (0.0007) -[2023-10-15 03:38:08,234][88300] Updated weights for policy 1, policy_version 34602 (0.0008) -[2023-10-15 03:38:08,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 70680576. Throughput: 0: 1732.5, 1: 1767.2. Samples: 17680180. Policy #0 lag: (min: 23.0, avg: 23.2, max: 34.0) -[2023-10-15 03:38:08,534][87330] Avg episode reward: [(0, '22.560'), (1, '22.780')] -[2023-10-15 03:38:08,622][88300] Updated weights for policy 1, policy_version 34612 (0.0010) -[2023-10-15 03:38:08,993][88300] Updated weights for policy 1, policy_version 34622 (0.0009) -[2023-10-15 03:38:11,057][88298] Updated weights for policy 0, policy_version 34440 (0.0009) -[2023-10-15 03:38:11,423][88298] Updated weights for policy 0, policy_version 34450 (0.0009) -[2023-10-15 03:38:11,801][88298] Updated weights for policy 0, policy_version 34460 (0.0009) -[2023-10-15 03:38:12,732][88300] Updated weights for policy 1, policy_version 34632 (0.0008) -[2023-10-15 03:38:13,098][88300] Updated weights for policy 1, policy_version 34642 (0.0008) -[2023-10-15 03:38:13,468][88300] Updated weights for policy 1, policy_version 34652 (0.0008) -[2023-10-15 03:38:13,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 70746112. Throughput: 0: 1721.8, 1: 1742.0. Samples: 17700414. Policy #0 lag: (min: 20.0, avg: 20.0, max: 23.0) -[2023-10-15 03:38:13,534][87330] Avg episode reward: [(0, '22.690'), (1, '22.780')] -[2023-10-15 03:38:15,735][88298] Updated weights for policy 0, policy_version 34470 (0.0007) -[2023-10-15 03:38:16,094][88298] Updated weights for policy 0, policy_version 34480 (0.0007) -[2023-10-15 03:38:16,473][88298] Updated weights for policy 0, policy_version 34490 (0.0007) -[2023-10-15 03:38:17,133][88300] Updated weights for policy 1, policy_version 34662 (0.0007) -[2023-10-15 03:38:17,508][88300] Updated weights for policy 1, policy_version 34672 (0.0007) -[2023-10-15 03:38:17,865][88300] Updated weights for policy 1, policy_version 34682 (0.0010) -[2023-10-15 03:38:18,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 70844416. Throughput: 0: 1747.1, 1: 1756.7. Samples: 17711734. Policy #0 lag: (min: 20.0, avg: 20.0, max: 23.0) -[2023-10-15 03:38:18,534][87330] Avg episode reward: [(0, '22.700'), (1, '22.610')] -[2023-10-15 03:38:20,233][88298] Updated weights for policy 0, policy_version 34500 (0.0007) -[2023-10-15 03:38:20,603][88298] Updated weights for policy 0, policy_version 34510 (0.0007) -[2023-10-15 03:38:20,980][88298] Updated weights for policy 0, policy_version 34520 (0.0007) -[2023-10-15 03:38:21,849][88300] Updated weights for policy 1, policy_version 34692 (0.0010) -[2023-10-15 03:38:22,208][88300] Updated weights for policy 1, policy_version 34702 (0.0007) -[2023-10-15 03:38:22,580][88300] Updated weights for policy 1, policy_version 34712 (0.0007) -[2023-10-15 03:38:23,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 70909952. Throughput: 0: 1722.5, 1: 1753.5. Samples: 17731862. Policy #0 lag: (min: 20.0, avg: 20.0, max: 23.0) -[2023-10-15 03:38:23,535][87330] Avg episode reward: [(0, '22.650'), (1, '22.100')] -[2023-10-15 03:38:24,913][88298] Updated weights for policy 0, policy_version 34530 (0.0008) -[2023-10-15 03:38:25,285][88298] Updated weights for policy 0, policy_version 34540 (0.0008) -[2023-10-15 03:38:25,662][88298] Updated weights for policy 0, policy_version 34550 (0.0009) -[2023-10-15 03:38:26,036][88298] Updated weights for policy 0, policy_version 34560 (0.0009) -[2023-10-15 03:38:26,475][88300] Updated weights for policy 1, policy_version 34722 (0.0007) -[2023-10-15 03:38:26,846][88300] Updated weights for policy 1, policy_version 34732 (0.0010) -[2023-10-15 03:38:27,222][88300] Updated weights for policy 1, policy_version 34742 (0.0008) -[2023-10-15 03:38:27,582][88300] Updated weights for policy 1, policy_version 34752 (0.0007) -[2023-10-15 03:38:28,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 70975488. Throughput: 0: 1734.6, 1: 1730.8. Samples: 17752556. Policy #0 lag: (min: 20.0, avg: 20.0, max: 23.0) -[2023-10-15 03:38:28,534][87330] Avg episode reward: [(0, '22.700'), (1, '21.940')] -[2023-10-15 03:38:29,892][88298] Updated weights for policy 0, policy_version 34570 (0.0007) -[2023-10-15 03:38:30,272][88298] Updated weights for policy 0, policy_version 34580 (0.0008) -[2023-10-15 03:38:30,648][88298] Updated weights for policy 0, policy_version 34590 (0.0009) -[2023-10-15 03:38:31,458][88300] Updated weights for policy 1, policy_version 34762 (0.0009) -[2023-10-15 03:38:31,827][88300] Updated weights for policy 1, policy_version 34772 (0.0007) -[2023-10-15 03:38:32,195][88300] Updated weights for policy 1, policy_version 34782 (0.0007) -[2023-10-15 03:38:33,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 71041024. Throughput: 0: 1724.7, 1: 1756.6. Samples: 17763302. Policy #0 lag: (min: 20.0, avg: 20.0, max: 23.0) -[2023-10-15 03:38:33,535][87330] Avg episode reward: [(0, '22.690'), (1, '21.980')] -[2023-10-15 03:38:34,575][88298] Updated weights for policy 0, policy_version 34600 (0.0008) -[2023-10-15 03:38:34,947][88298] Updated weights for policy 0, policy_version 34610 (0.0008) -[2023-10-15 03:38:35,324][88298] Updated weights for policy 0, policy_version 34620 (0.0009) -[2023-10-15 03:38:36,050][88300] Updated weights for policy 1, policy_version 34792 (0.0007) -[2023-10-15 03:38:36,406][88300] Updated weights for policy 1, policy_version 34802 (0.0008) -[2023-10-15 03:38:36,773][88300] Updated weights for policy 1, policy_version 34812 (0.0010) -[2023-10-15 03:38:38,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 71106560. Throughput: 0: 1728.1, 1: 1732.8. Samples: 17783696. Policy #0 lag: (min: 18.0, avg: 18.1, max: 24.0) -[2023-10-15 03:38:38,535][87330] Avg episode reward: [(0, '22.730'), (1, '21.920')] -[2023-10-15 03:38:39,191][88298] Updated weights for policy 0, policy_version 34630 (0.0009) -[2023-10-15 03:38:39,555][88298] Updated weights for policy 0, policy_version 34640 (0.0010) -[2023-10-15 03:38:39,925][88298] Updated weights for policy 0, policy_version 34650 (0.0011) -[2023-10-15 03:38:40,739][88300] Updated weights for policy 1, policy_version 34822 (0.0010) -[2023-10-15 03:38:41,105][88300] Updated weights for policy 1, policy_version 34832 (0.0009) -[2023-10-15 03:38:41,471][88300] Updated weights for policy 1, policy_version 34842 (0.0009) -[2023-10-15 03:38:43,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 71172096. Throughput: 0: 1760.6, 1: 1732.0. Samples: 17805498. Policy #0 lag: (min: 18.0, avg: 18.1, max: 24.0) -[2023-10-15 03:38:43,535][87330] Avg episode reward: [(0, '22.730'), (1, '21.590')] -[2023-10-15 03:38:43,820][88298] Updated weights for policy 0, policy_version 34660 (0.0011) -[2023-10-15 03:38:44,187][88298] Updated weights for policy 0, policy_version 34670 (0.0008) -[2023-10-15 03:38:44,559][88298] Updated weights for policy 0, policy_version 34680 (0.0009) -[2023-10-15 03:38:45,390][88300] Updated weights for policy 1, policy_version 34852 (0.0009) -[2023-10-15 03:38:45,763][88300] Updated weights for policy 1, policy_version 34862 (0.0009) -[2023-10-15 03:38:46,134][88300] Updated weights for policy 1, policy_version 34872 (0.0008) -[2023-10-15 03:38:48,280][88298] Updated weights for policy 0, policy_version 34690 (0.0008) -[2023-10-15 03:38:48,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 71237632. Throughput: 0: 1735.5, 1: 1737.8. Samples: 17815386. Policy #0 lag: (min: 18.0, avg: 18.1, max: 24.0) -[2023-10-15 03:38:48,534][87330] Avg episode reward: [(0, '22.750'), (1, '21.650')] -[2023-10-15 03:38:48,651][88298] Updated weights for policy 0, policy_version 34700 (0.0010) -[2023-10-15 03:38:49,029][88298] Updated weights for policy 0, policy_version 34710 (0.0007) -[2023-10-15 03:38:49,395][88298] Updated weights for policy 0, policy_version 34720 (0.0011) -[2023-10-15 03:38:50,024][88300] Updated weights for policy 1, policy_version 34882 (0.0007) -[2023-10-15 03:38:50,396][88300] Updated weights for policy 1, policy_version 34892 (0.0009) -[2023-10-15 03:38:50,752][88300] Updated weights for policy 1, policy_version 34902 (0.0008) -[2023-10-15 03:38:51,122][88300] Updated weights for policy 1, policy_version 34912 (0.0007) -[2023-10-15 03:38:53,353][88298] Updated weights for policy 0, policy_version 34730 (0.0007) -[2023-10-15 03:38:53,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 71303168. Throughput: 0: 1751.0, 1: 1725.2. Samples: 17836610. Policy #0 lag: (min: 18.0, avg: 18.1, max: 24.0) -[2023-10-15 03:38:53,534][87330] Avg episode reward: [(0, '22.940'), (1, '21.830')] -[2023-10-15 03:38:53,716][88298] Updated weights for policy 0, policy_version 34740 (0.0008) -[2023-10-15 03:38:54,092][88298] Updated weights for policy 0, policy_version 34750 (0.0008) -[2023-10-15 03:38:55,264][88300] Updated weights for policy 1, policy_version 34922 (0.0008) -[2023-10-15 03:38:55,638][88300] Updated weights for policy 1, policy_version 34932 (0.0007) -[2023-10-15 03:38:56,010][88300] Updated weights for policy 1, policy_version 34942 (0.0008) -[2023-10-15 03:38:58,025][88298] Updated weights for policy 0, policy_version 34760 (0.0010) -[2023-10-15 03:38:58,396][88298] Updated weights for policy 0, policy_version 34770 (0.0009) -[2023-10-15 03:38:58,534][87330] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 71368704. Throughput: 0: 1756.5, 1: 1743.8. Samples: 17857930. Policy #0 lag: (min: 18.0, avg: 18.1, max: 24.0) -[2023-10-15 03:38:58,535][87330] Avg episode reward: [(0, '22.820'), (1, '22.110')] -[2023-10-15 03:38:58,546][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000034944_35782656.pth... -[2023-10-15 03:38:58,586][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000033312_34111488.pth -[2023-10-15 03:38:58,760][88298] Updated weights for policy 0, policy_version 34780 (0.0008) -[2023-10-15 03:38:58,907][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000034784_35618816.pth... -[2023-10-15 03:38:58,946][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000033152_33947648.pth -[2023-10-15 03:38:59,865][88300] Updated weights for policy 1, policy_version 34952 (0.0008) -[2023-10-15 03:39:00,237][88300] Updated weights for policy 1, policy_version 34962 (0.0008) -[2023-10-15 03:39:00,598][88300] Updated weights for policy 1, policy_version 34972 (0.0007) -[2023-10-15 03:39:02,647][88298] Updated weights for policy 0, policy_version 34790 (0.0008) -[2023-10-15 03:39:03,009][88298] Updated weights for policy 0, policy_version 34800 (0.0007) -[2023-10-15 03:39:03,388][88298] Updated weights for policy 0, policy_version 34810 (0.0008) -[2023-10-15 03:39:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 71434240. Throughput: 0: 1733.9, 1: 1724.6. Samples: 17867366. Policy #0 lag: (min: 27.0, avg: 30.1, max: 59.0) -[2023-10-15 03:39:03,535][87330] Avg episode reward: [(0, '22.840'), (1, '22.300')] -[2023-10-15 03:39:04,448][88300] Updated weights for policy 1, policy_version 34982 (0.0008) -[2023-10-15 03:39:04,822][88300] Updated weights for policy 1, policy_version 34992 (0.0010) -[2023-10-15 03:39:05,191][88300] Updated weights for policy 1, policy_version 35002 (0.0007) -[2023-10-15 03:39:07,178][88298] Updated weights for policy 0, policy_version 34820 (0.0010) -[2023-10-15 03:39:07,543][88298] Updated weights for policy 0, policy_version 34830 (0.0007) -[2023-10-15 03:39:07,908][88298] Updated weights for policy 0, policy_version 34840 (0.0008) -[2023-10-15 03:39:08,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 71532544. Throughput: 0: 1756.8, 1: 1736.8. Samples: 17889076. Policy #0 lag: (min: 27.0, avg: 30.1, max: 59.0) -[2023-10-15 03:39:08,535][87330] Avg episode reward: [(0, '22.710'), (1, '22.270')] -[2023-10-15 03:39:09,150][88300] Updated weights for policy 1, policy_version 35012 (0.0007) -[2023-10-15 03:39:09,523][88300] Updated weights for policy 1, policy_version 35022 (0.0007) -[2023-10-15 03:39:09,895][88300] Updated weights for policy 1, policy_version 35032 (0.0008) -[2023-10-15 03:39:11,659][88298] Updated weights for policy 0, policy_version 34850 (0.0008) -[2023-10-15 03:39:12,040][88298] Updated weights for policy 0, policy_version 34860 (0.0007) -[2023-10-15 03:39:12,405][88298] Updated weights for policy 0, policy_version 34870 (0.0007) -[2023-10-15 03:39:12,773][88298] Updated weights for policy 0, policy_version 34880 (0.0009) -[2023-10-15 03:39:13,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 71598080. Throughput: 0: 1732.4, 1: 1758.8. Samples: 17909660. Policy #0 lag: (min: 27.0, avg: 30.1, max: 59.0) -[2023-10-15 03:39:13,534][87330] Avg episode reward: [(0, '22.540'), (1, '22.490')] -[2023-10-15 03:39:13,842][88300] Updated weights for policy 1, policy_version 35042 (0.0011) -[2023-10-15 03:39:14,214][88300] Updated weights for policy 1, policy_version 35052 (0.0009) -[2023-10-15 03:39:14,580][88300] Updated weights for policy 1, policy_version 35062 (0.0009) -[2023-10-15 03:39:14,945][88300] Updated weights for policy 1, policy_version 35072 (0.0008) -[2023-10-15 03:39:16,681][88298] Updated weights for policy 0, policy_version 34890 (0.0009) -[2023-10-15 03:39:17,059][88298] Updated weights for policy 0, policy_version 34900 (0.0008) -[2023-10-15 03:39:17,425][88298] Updated weights for policy 0, policy_version 34910 (0.0008) -[2023-10-15 03:39:18,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 71663616. Throughput: 0: 1759.0, 1: 1732.5. Samples: 17920422. Policy #0 lag: (min: 27.0, avg: 30.1, max: 59.0) -[2023-10-15 03:39:18,535][87330] Avg episode reward: [(0, '22.520'), (1, '22.780')] -[2023-10-15 03:39:18,741][88300] Updated weights for policy 1, policy_version 35082 (0.0009) -[2023-10-15 03:39:19,103][88300] Updated weights for policy 1, policy_version 35092 (0.0010) -[2023-10-15 03:39:19,472][88300] Updated weights for policy 1, policy_version 35102 (0.0009) -[2023-10-15 03:39:21,235][88298] Updated weights for policy 0, policy_version 34920 (0.0008) -[2023-10-15 03:39:21,603][88298] Updated weights for policy 0, policy_version 34930 (0.0010) -[2023-10-15 03:39:21,974][88298] Updated weights for policy 0, policy_version 34940 (0.0008) -[2023-10-15 03:39:23,340][88300] Updated weights for policy 1, policy_version 35112 (0.0007) -[2023-10-15 03:39:23,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 71729152. Throughput: 0: 1739.8, 1: 1765.0. Samples: 17941414. Policy #0 lag: (min: 27.0, avg: 30.1, max: 59.0) -[2023-10-15 03:39:23,534][87330] Avg episode reward: [(0, '22.530'), (1, '22.720')] -[2023-10-15 03:39:23,704][88300] Updated weights for policy 1, policy_version 35122 (0.0009) -[2023-10-15 03:39:24,064][88300] Updated weights for policy 1, policy_version 35132 (0.0010) -[2023-10-15 03:39:26,013][88298] Updated weights for policy 0, policy_version 34950 (0.0009) -[2023-10-15 03:39:26,380][88298] Updated weights for policy 0, policy_version 34960 (0.0009) -[2023-10-15 03:39:26,746][88298] Updated weights for policy 0, policy_version 34970 (0.0009) -[2023-10-15 03:39:27,958][88300] Updated weights for policy 1, policy_version 35142 (0.0009) -[2023-10-15 03:39:28,323][88300] Updated weights for policy 1, policy_version 35152 (0.0007) -[2023-10-15 03:39:28,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 71794688. Throughput: 0: 1725.8, 1: 1748.1. Samples: 17961824. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:39:28,534][87330] Avg episode reward: [(0, '22.540'), (1, '22.560')] -[2023-10-15 03:39:28,692][88300] Updated weights for policy 1, policy_version 35162 (0.0007) -[2023-10-15 03:39:30,666][88298] Updated weights for policy 0, policy_version 34980 (0.0007) -[2023-10-15 03:39:31,023][88298] Updated weights for policy 0, policy_version 34990 (0.0008) -[2023-10-15 03:39:31,392][88298] Updated weights for policy 0, policy_version 35000 (0.0007) -[2023-10-15 03:39:32,582][88300] Updated weights for policy 1, policy_version 35172 (0.0009) -[2023-10-15 03:39:32,950][88300] Updated weights for policy 1, policy_version 35182 (0.0007) -[2023-10-15 03:39:33,325][88300] Updated weights for policy 1, policy_version 35192 (0.0007) -[2023-10-15 03:39:33,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 71860224. Throughput: 0: 1748.9, 1: 1755.8. Samples: 17973096. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:39:33,534][87330] Avg episode reward: [(0, '22.480'), (1, '22.430')] -[2023-10-15 03:39:35,435][88298] Updated weights for policy 0, policy_version 35010 (0.0008) -[2023-10-15 03:39:35,806][88298] Updated weights for policy 0, policy_version 35020 (0.0010) -[2023-10-15 03:39:36,175][88298] Updated weights for policy 0, policy_version 35030 (0.0011) -[2023-10-15 03:39:36,543][88298] Updated weights for policy 0, policy_version 35040 (0.0011) -[2023-10-15 03:39:37,106][88300] Updated weights for policy 1, policy_version 35202 (0.0008) -[2023-10-15 03:39:37,481][88300] Updated weights for policy 1, policy_version 35212 (0.0010) -[2023-10-15 03:39:37,840][88300] Updated weights for policy 1, policy_version 35222 (0.0009) -[2023-10-15 03:39:38,221][88300] Updated weights for policy 1, policy_version 35232 (0.0009) -[2023-10-15 03:39:38,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 71958528. Throughput: 0: 1721.2, 1: 1757.8. Samples: 17993162. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:39:38,535][87330] Avg episode reward: [(0, '22.390'), (1, '22.450')] -[2023-10-15 03:39:40,469][88298] Updated weights for policy 0, policy_version 35050 (0.0010) -[2023-10-15 03:39:40,856][88298] Updated weights for policy 0, policy_version 35060 (0.0010) -[2023-10-15 03:39:41,225][88298] Updated weights for policy 0, policy_version 35070 (0.0010) -[2023-10-15 03:39:42,238][88300] Updated weights for policy 1, policy_version 35242 (0.0007) -[2023-10-15 03:39:42,595][88300] Updated weights for policy 1, policy_version 35252 (0.0008) -[2023-10-15 03:39:42,965][88300] Updated weights for policy 1, policy_version 35262 (0.0008) -[2023-10-15 03:39:43,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 72024064. Throughput: 0: 1724.9, 1: 1729.3. Samples: 18013368. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:39:43,535][87330] Avg episode reward: [(0, '22.570'), (1, '22.140')] -[2023-10-15 03:39:45,213][88298] Updated weights for policy 0, policy_version 35080 (0.0008) -[2023-10-15 03:39:45,591][88298] Updated weights for policy 0, policy_version 35090 (0.0007) -[2023-10-15 03:39:45,967][88298] Updated weights for policy 0, policy_version 35100 (0.0010) -[2023-10-15 03:39:46,793][88300] Updated weights for policy 1, policy_version 35272 (0.0008) -[2023-10-15 03:39:47,148][88300] Updated weights for policy 1, policy_version 35282 (0.0010) -[2023-10-15 03:39:47,520][88300] Updated weights for policy 1, policy_version 35292 (0.0007) -[2023-10-15 03:39:48,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 72089600. Throughput: 0: 1730.0, 1: 1766.5. Samples: 18024710. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:39:48,534][87330] Avg episode reward: [(0, '22.570'), (1, '22.100')] -[2023-10-15 03:39:49,999][88298] Updated weights for policy 0, policy_version 35110 (0.0008) -[2023-10-15 03:39:50,371][88298] Updated weights for policy 0, policy_version 35120 (0.0008) -[2023-10-15 03:39:50,746][88298] Updated weights for policy 0, policy_version 35130 (0.0010) -[2023-10-15 03:39:51,494][88300] Updated weights for policy 1, policy_version 35302 (0.0007) -[2023-10-15 03:39:51,854][88300] Updated weights for policy 1, policy_version 35312 (0.0009) -[2023-10-15 03:39:52,228][88300] Updated weights for policy 1, policy_version 35322 (0.0008) -[2023-10-15 03:39:53,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 72155136. Throughput: 0: 1716.0, 1: 1738.5. Samples: 18044530. Policy #0 lag: (min: 13.0, avg: 18.4, max: 45.0) -[2023-10-15 03:39:53,534][87330] Avg episode reward: [(0, '22.570'), (1, '22.180')] -[2023-10-15 03:39:54,642][88298] Updated weights for policy 0, policy_version 35140 (0.0008) -[2023-10-15 03:39:55,010][88298] Updated weights for policy 0, policy_version 35150 (0.0007) -[2023-10-15 03:39:55,378][88298] Updated weights for policy 0, policy_version 35160 (0.0008) -[2023-10-15 03:39:56,274][88300] Updated weights for policy 1, policy_version 35332 (0.0007) -[2023-10-15 03:39:56,641][88300] Updated weights for policy 1, policy_version 35342 (0.0011) -[2023-10-15 03:39:57,014][88300] Updated weights for policy 1, policy_version 35352 (0.0009) -[2023-10-15 03:39:58,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 72220672. Throughput: 0: 1747.2, 1: 1725.4. Samples: 18065926. Policy #0 lag: (min: 13.0, avg: 18.4, max: 45.0) -[2023-10-15 03:39:58,534][87330] Avg episode reward: [(0, '22.550'), (1, '22.210')] -[2023-10-15 03:39:59,141][88298] Updated weights for policy 0, policy_version 35170 (0.0010) -[2023-10-15 03:39:59,513][88298] Updated weights for policy 0, policy_version 35180 (0.0011) -[2023-10-15 03:39:59,894][88298] Updated weights for policy 0, policy_version 35190 (0.0009) -[2023-10-15 03:40:00,270][88298] Updated weights for policy 0, policy_version 35200 (0.0008) -[2023-10-15 03:40:00,770][88300] Updated weights for policy 1, policy_version 35362 (0.0010) -[2023-10-15 03:40:01,133][88300] Updated weights for policy 1, policy_version 35372 (0.0007) -[2023-10-15 03:40:01,498][88300] Updated weights for policy 1, policy_version 35382 (0.0009) -[2023-10-15 03:40:01,866][88300] Updated weights for policy 1, policy_version 35392 (0.0011) -[2023-10-15 03:40:03,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 72286208. Throughput: 0: 1719.0, 1: 1744.4. Samples: 18076274. Policy #0 lag: (min: 13.0, avg: 18.4, max: 45.0) -[2023-10-15 03:40:03,534][87330] Avg episode reward: [(0, '22.510'), (1, '22.010')] -[2023-10-15 03:40:04,166][88298] Updated weights for policy 0, policy_version 35210 (0.0009) -[2023-10-15 03:40:04,535][88298] Updated weights for policy 0, policy_version 35220 (0.0009) -[2023-10-15 03:40:04,909][88298] Updated weights for policy 0, policy_version 35230 (0.0009) -[2023-10-15 03:40:05,874][88300] Updated weights for policy 1, policy_version 35402 (0.0009) -[2023-10-15 03:40:06,239][88300] Updated weights for policy 1, policy_version 35412 (0.0007) -[2023-10-15 03:40:06,601][88300] Updated weights for policy 1, policy_version 35422 (0.0008) -[2023-10-15 03:40:08,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 72351744. Throughput: 0: 1736.2, 1: 1726.6. Samples: 18097240. Policy #0 lag: (min: 13.0, avg: 18.4, max: 45.0) -[2023-10-15 03:40:08,534][87330] Avg episode reward: [(0, '22.700'), (1, '21.810')] -[2023-10-15 03:40:09,014][88298] Updated weights for policy 0, policy_version 35240 (0.0008) -[2023-10-15 03:40:09,384][88298] Updated weights for policy 0, policy_version 35250 (0.0008) -[2023-10-15 03:40:09,754][88298] Updated weights for policy 0, policy_version 35260 (0.0008) -[2023-10-15 03:40:10,449][88300] Updated weights for policy 1, policy_version 35432 (0.0009) -[2023-10-15 03:40:10,820][88300] Updated weights for policy 1, policy_version 35442 (0.0010) -[2023-10-15 03:40:11,187][88300] Updated weights for policy 1, policy_version 35452 (0.0008) -[2023-10-15 03:40:13,497][88298] Updated weights for policy 0, policy_version 35270 (0.0007) -[2023-10-15 03:40:13,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 72417280. Throughput: 0: 1751.8, 1: 1735.0. Samples: 18118730. Policy #0 lag: (min: 13.0, avg: 18.4, max: 45.0) -[2023-10-15 03:40:13,535][87330] Avg episode reward: [(0, '22.720'), (1, '21.920')] -[2023-10-15 03:40:13,865][88298] Updated weights for policy 0, policy_version 35280 (0.0008) -[2023-10-15 03:40:14,236][88298] Updated weights for policy 0, policy_version 35290 (0.0009) -[2023-10-15 03:40:15,109][88300] Updated weights for policy 1, policy_version 35462 (0.0008) -[2023-10-15 03:40:15,475][88300] Updated weights for policy 1, policy_version 35472 (0.0011) -[2023-10-15 03:40:15,843][88300] Updated weights for policy 1, policy_version 35482 (0.0007) -[2023-10-15 03:40:17,988][88298] Updated weights for policy 0, policy_version 35300 (0.0007) -[2023-10-15 03:40:18,366][88298] Updated weights for policy 0, policy_version 35310 (0.0007) -[2023-10-15 03:40:18,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 72482816. Throughput: 0: 1726.3, 1: 1720.5. Samples: 18128202. Policy #0 lag: (min: 22.0, avg: 24.7, max: 54.0) -[2023-10-15 03:40:18,535][87330] Avg episode reward: [(0, '22.680'), (1, '21.830')] -[2023-10-15 03:40:18,740][88298] Updated weights for policy 0, policy_version 35320 (0.0007) -[2023-10-15 03:40:19,519][88300] Updated weights for policy 1, policy_version 35492 (0.0008) -[2023-10-15 03:40:19,890][88300] Updated weights for policy 1, policy_version 35502 (0.0008) -[2023-10-15 03:40:20,257][88300] Updated weights for policy 1, policy_version 35512 (0.0011) -[2023-10-15 03:40:22,719][88298] Updated weights for policy 0, policy_version 35330 (0.0009) -[2023-10-15 03:40:23,091][88298] Updated weights for policy 0, policy_version 35340 (0.0007) -[2023-10-15 03:40:23,465][88298] Updated weights for policy 0, policy_version 35350 (0.0011) -[2023-10-15 03:40:23,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 72548352. Throughput: 0: 1752.5, 1: 1730.6. Samples: 18149900. Policy #0 lag: (min: 22.0, avg: 24.7, max: 54.0) -[2023-10-15 03:40:23,534][87330] Avg episode reward: [(0, '22.570'), (1, '21.790')] -[2023-10-15 03:40:23,841][88298] Updated weights for policy 0, policy_version 35360 (0.0009) -[2023-10-15 03:40:24,205][88300] Updated weights for policy 1, policy_version 35522 (0.0010) -[2023-10-15 03:40:24,573][88300] Updated weights for policy 1, policy_version 35532 (0.0007) -[2023-10-15 03:40:24,937][88300] Updated weights for policy 1, policy_version 35542 (0.0007) -[2023-10-15 03:40:25,307][88300] Updated weights for policy 1, policy_version 35552 (0.0008) -[2023-10-15 03:40:27,672][88298] Updated weights for policy 0, policy_version 35370 (0.0009) -[2023-10-15 03:40:28,039][88298] Updated weights for policy 0, policy_version 35380 (0.0007) -[2023-10-15 03:40:28,402][88298] Updated weights for policy 0, policy_version 35390 (0.0008) -[2023-10-15 03:40:28,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 72646656. Throughput: 0: 1739.1, 1: 1768.1. Samples: 18171192. Policy #0 lag: (min: 22.0, avg: 24.7, max: 54.0) -[2023-10-15 03:40:28,534][87330] Avg episode reward: [(0, '22.540'), (1, '21.960')] -[2023-10-15 03:40:29,212][88300] Updated weights for policy 1, policy_version 35562 (0.0007) -[2023-10-15 03:40:29,576][88300] Updated weights for policy 1, policy_version 35572 (0.0009) -[2023-10-15 03:40:29,947][88300] Updated weights for policy 1, policy_version 35582 (0.0010) -[2023-10-15 03:40:32,426][88298] Updated weights for policy 0, policy_version 35400 (0.0007) -[2023-10-15 03:40:32,807][88298] Updated weights for policy 0, policy_version 35410 (0.0008) -[2023-10-15 03:40:33,177][88298] Updated weights for policy 0, policy_version 35420 (0.0009) -[2023-10-15 03:40:33,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 72712192. Throughput: 0: 1745.7, 1: 1728.8. Samples: 18181066. Policy #0 lag: (min: 22.0, avg: 24.7, max: 54.0) -[2023-10-15 03:40:33,535][87330] Avg episode reward: [(0, '22.360'), (1, '22.110')] -[2023-10-15 03:40:33,862][88300] Updated weights for policy 1, policy_version 35592 (0.0008) -[2023-10-15 03:40:34,223][88300] Updated weights for policy 1, policy_version 35602 (0.0007) -[2023-10-15 03:40:34,588][88300] Updated weights for policy 1, policy_version 35612 (0.0007) -[2023-10-15 03:40:36,992][88298] Updated weights for policy 0, policy_version 35430 (0.0008) -[2023-10-15 03:40:37,365][88298] Updated weights for policy 0, policy_version 35440 (0.0007) -[2023-10-15 03:40:37,733][88298] Updated weights for policy 0, policy_version 35450 (0.0007) -[2023-10-15 03:40:38,430][88300] Updated weights for policy 1, policy_version 35622 (0.0008) -[2023-10-15 03:40:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 72777728. Throughput: 0: 1758.6, 1: 1755.0. Samples: 18202644. Policy #0 lag: (min: 4.0, avg: 9.4, max: 36.0) -[2023-10-15 03:40:38,534][87330] Avg episode reward: [(0, '22.530'), (1, '22.290')] -[2023-10-15 03:40:38,793][88300] Updated weights for policy 1, policy_version 35632 (0.0009) -[2023-10-15 03:40:39,156][88300] Updated weights for policy 1, policy_version 35642 (0.0007) -[2023-10-15 03:40:41,545][88298] Updated weights for policy 0, policy_version 35460 (0.0007) -[2023-10-15 03:40:41,923][88298] Updated weights for policy 0, policy_version 35470 (0.0007) -[2023-10-15 03:40:42,298][88298] Updated weights for policy 0, policy_version 35480 (0.0008) -[2023-10-15 03:40:42,905][88300] Updated weights for policy 1, policy_version 35652 (0.0008) -[2023-10-15 03:40:43,266][88300] Updated weights for policy 1, policy_version 35662 (0.0007) -[2023-10-15 03:40:43,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 72843264. Throughput: 0: 1726.3, 1: 1758.5. Samples: 18222742. Policy #0 lag: (min: 4.0, avg: 9.4, max: 36.0) -[2023-10-15 03:40:43,535][87330] Avg episode reward: [(0, '22.570'), (1, '22.600')] -[2023-10-15 03:40:43,637][88300] Updated weights for policy 1, policy_version 35672 (0.0007) -[2023-10-15 03:40:46,295][88298] Updated weights for policy 0, policy_version 35490 (0.0008) -[2023-10-15 03:40:46,663][88298] Updated weights for policy 0, policy_version 35500 (0.0010) -[2023-10-15 03:40:47,038][88298] Updated weights for policy 0, policy_version 35510 (0.0010) -[2023-10-15 03:40:47,372][88300] Updated weights for policy 1, policy_version 35682 (0.0007) -[2023-10-15 03:40:47,400][88298] Updated weights for policy 0, policy_version 35520 (0.0008) -[2023-10-15 03:40:47,740][88300] Updated weights for policy 1, policy_version 35692 (0.0010) -[2023-10-15 03:40:48,109][88300] Updated weights for policy 1, policy_version 35702 (0.0010) -[2023-10-15 03:40:48,484][88300] Updated weights for policy 1, policy_version 35712 (0.0008) -[2023-10-15 03:40:48,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 72941568. Throughput: 0: 1755.9, 1: 1749.9. Samples: 18234034. Policy #0 lag: (min: 4.0, avg: 9.4, max: 36.0) -[2023-10-15 03:40:48,534][87330] Avg episode reward: [(0, '22.580'), (1, '22.580')] -[2023-10-15 03:40:51,362][88298] Updated weights for policy 0, policy_version 35530 (0.0009) -[2023-10-15 03:40:51,738][88298] Updated weights for policy 0, policy_version 35540 (0.0007) -[2023-10-15 03:40:52,112][88298] Updated weights for policy 0, policy_version 35550 (0.0008) -[2023-10-15 03:40:52,347][88300] Updated weights for policy 1, policy_version 35722 (0.0009) -[2023-10-15 03:40:52,711][88300] Updated weights for policy 1, policy_version 35732 (0.0010) -[2023-10-15 03:40:53,077][88300] Updated weights for policy 1, policy_version 35742 (0.0010) -[2023-10-15 03:40:53,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 73007104. Throughput: 0: 1737.8, 1: 1763.0. Samples: 18254774. Policy #0 lag: (min: 4.0, avg: 9.4, max: 36.0) -[2023-10-15 03:40:53,534][87330] Avg episode reward: [(0, '22.390'), (1, '22.690')] -[2023-10-15 03:40:56,101][88298] Updated weights for policy 0, policy_version 35560 (0.0007) -[2023-10-15 03:40:56,477][88298] Updated weights for policy 0, policy_version 35570 (0.0008) -[2023-10-15 03:40:56,843][88298] Updated weights for policy 0, policy_version 35580 (0.0009) -[2023-10-15 03:40:56,876][88300] Updated weights for policy 1, policy_version 35752 (0.0009) -[2023-10-15 03:40:57,233][88300] Updated weights for policy 1, policy_version 35762 (0.0010) -[2023-10-15 03:40:57,596][88300] Updated weights for policy 1, policy_version 35772 (0.0010) -[2023-10-15 03:40:58,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 73072640. Throughput: 0: 1719.4, 1: 1745.1. Samples: 18274634. Policy #0 lag: (min: 4.0, avg: 9.4, max: 36.0) -[2023-10-15 03:40:58,534][87330] Avg episode reward: [(0, '22.480'), (1, '22.700')] -[2023-10-15 03:40:58,544][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000035776_36634624.pth... -[2023-10-15 03:40:58,544][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000035584_36438016.pth... -[2023-10-15 03:40:58,573][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000034144_34963456.pth -[2023-10-15 03:40:58,577][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000033952_34766848.pth -[2023-10-15 03:41:00,613][88298] Updated weights for policy 0, policy_version 35590 (0.0008) -[2023-10-15 03:41:00,983][88298] Updated weights for policy 0, policy_version 35600 (0.0008) -[2023-10-15 03:41:01,351][88298] Updated weights for policy 0, policy_version 35610 (0.0007) -[2023-10-15 03:41:01,473][88300] Updated weights for policy 1, policy_version 35782 (0.0009) -[2023-10-15 03:41:01,845][88300] Updated weights for policy 1, policy_version 35792 (0.0009) -[2023-10-15 03:41:02,218][88300] Updated weights for policy 1, policy_version 35802 (0.0010) -[2023-10-15 03:41:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 73138176. Throughput: 0: 1740.3, 1: 1776.8. Samples: 18286468. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:41:03,534][87330] Avg episode reward: [(0, '22.550'), (1, '22.720')] -[2023-10-15 03:41:05,175][88298] Updated weights for policy 0, policy_version 35620 (0.0008) -[2023-10-15 03:41:05,539][88298] Updated weights for policy 0, policy_version 35630 (0.0009) -[2023-10-15 03:41:05,908][88298] Updated weights for policy 0, policy_version 35640 (0.0011) -[2023-10-15 03:41:06,197][88300] Updated weights for policy 1, policy_version 35812 (0.0009) -[2023-10-15 03:41:06,573][88300] Updated weights for policy 1, policy_version 35822 (0.0008) -[2023-10-15 03:41:06,926][88300] Updated weights for policy 1, policy_version 35832 (0.0007) -[2023-10-15 03:41:08,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 73203712. Throughput: 0: 1720.0, 1: 1742.4. Samples: 18305704. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:41:08,534][87330] Avg episode reward: [(0, '22.540'), (1, '22.720')] -[2023-10-15 03:41:09,810][88298] Updated weights for policy 0, policy_version 35650 (0.0008) -[2023-10-15 03:41:10,181][88298] Updated weights for policy 0, policy_version 35660 (0.0009) -[2023-10-15 03:41:10,544][88298] Updated weights for policy 0, policy_version 35670 (0.0007) -[2023-10-15 03:41:10,873][88300] Updated weights for policy 1, policy_version 35842 (0.0008) -[2023-10-15 03:41:10,910][88298] Updated weights for policy 0, policy_version 35680 (0.0007) -[2023-10-15 03:41:11,245][88300] Updated weights for policy 1, policy_version 35852 (0.0008) -[2023-10-15 03:41:11,607][88300] Updated weights for policy 1, policy_version 35862 (0.0008) -[2023-10-15 03:41:11,980][88300] Updated weights for policy 1, policy_version 35872 (0.0010) -[2023-10-15 03:41:13,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 73269248. Throughput: 0: 1735.6, 1: 1735.2. Samples: 18327380. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:41:13,535][87330] Avg episode reward: [(0, '22.270'), (1, '22.780')] -[2023-10-15 03:41:14,811][88298] Updated weights for policy 0, policy_version 35690 (0.0009) -[2023-10-15 03:41:15,176][88298] Updated weights for policy 0, policy_version 35700 (0.0007) -[2023-10-15 03:41:15,545][88298] Updated weights for policy 0, policy_version 35710 (0.0007) -[2023-10-15 03:41:16,029][88300] Updated weights for policy 1, policy_version 35882 (0.0008) -[2023-10-15 03:41:16,404][88300] Updated weights for policy 1, policy_version 35892 (0.0008) -[2023-10-15 03:41:16,774][88300] Updated weights for policy 1, policy_version 35902 (0.0008) -[2023-10-15 03:41:18,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 73334784. Throughput: 0: 1721.5, 1: 1751.7. Samples: 18337360. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:41:18,534][87330] Avg episode reward: [(0, '22.250'), (1, '22.730')] -[2023-10-15 03:41:19,427][88298] Updated weights for policy 0, policy_version 35720 (0.0009) -[2023-10-15 03:41:19,805][88298] Updated weights for policy 0, policy_version 35730 (0.0007) -[2023-10-15 03:41:20,172][88298] Updated weights for policy 0, policy_version 35740 (0.0007) -[2023-10-15 03:41:20,784][88300] Updated weights for policy 1, policy_version 35912 (0.0010) -[2023-10-15 03:41:21,146][88300] Updated weights for policy 1, policy_version 35922 (0.0009) -[2023-10-15 03:41:21,510][88300] Updated weights for policy 1, policy_version 35932 (0.0008) -[2023-10-15 03:41:23,534][87330] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 73400320. Throughput: 0: 1727.6, 1: 1725.9. Samples: 18358052. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:41:23,534][87330] Avg episode reward: [(0, '22.440'), (1, '22.780')] -[2023-10-15 03:41:24,152][88298] Updated weights for policy 0, policy_version 35750 (0.0008) -[2023-10-15 03:41:24,525][88298] Updated weights for policy 0, policy_version 35760 (0.0007) -[2023-10-15 03:41:24,886][88298] Updated weights for policy 0, policy_version 35770 (0.0010) -[2023-10-15 03:41:25,307][88300] Updated weights for policy 1, policy_version 35942 (0.0008) -[2023-10-15 03:41:25,676][88300] Updated weights for policy 1, policy_version 35952 (0.0009) -[2023-10-15 03:41:26,039][88300] Updated weights for policy 1, policy_version 35962 (0.0009) -[2023-10-15 03:41:28,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 73465856. Throughput: 0: 1754.2, 1: 1738.5. Samples: 18379914. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:41:28,535][87330] Avg episode reward: [(0, '22.450'), (1, '22.770')] -[2023-10-15 03:41:28,816][88298] Updated weights for policy 0, policy_version 35780 (0.0009) -[2023-10-15 03:41:29,185][88298] Updated weights for policy 0, policy_version 35790 (0.0010) -[2023-10-15 03:41:29,559][88298] Updated weights for policy 0, policy_version 35800 (0.0009) -[2023-10-15 03:41:30,171][88300] Updated weights for policy 1, policy_version 35972 (0.0011) -[2023-10-15 03:41:30,545][88300] Updated weights for policy 1, policy_version 35982 (0.0010) -[2023-10-15 03:41:30,910][88300] Updated weights for policy 1, policy_version 35992 (0.0008) -[2023-10-15 03:41:33,337][88298] Updated weights for policy 0, policy_version 35810 (0.0008) -[2023-10-15 03:41:33,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 73531392. Throughput: 0: 1725.0, 1: 1729.1. Samples: 18389466. Policy #0 lag: (min: 31.0, avg: 32.4, max: 57.0) -[2023-10-15 03:41:33,534][87330] Avg episode reward: [(0, '22.460'), (1, '22.600')] -[2023-10-15 03:41:33,714][88298] Updated weights for policy 0, policy_version 35820 (0.0007) -[2023-10-15 03:41:34,082][88298] Updated weights for policy 0, policy_version 35830 (0.0008) -[2023-10-15 03:41:34,454][88298] Updated weights for policy 0, policy_version 35840 (0.0008) -[2023-10-15 03:41:34,767][88300] Updated weights for policy 1, policy_version 36002 (0.0008) -[2023-10-15 03:41:35,134][88300] Updated weights for policy 1, policy_version 36012 (0.0007) -[2023-10-15 03:41:35,510][88300] Updated weights for policy 1, policy_version 36022 (0.0008) -[2023-10-15 03:41:35,872][88300] Updated weights for policy 1, policy_version 36032 (0.0008) -[2023-10-15 03:41:38,485][88298] Updated weights for policy 0, policy_version 35850 (0.0007) -[2023-10-15 03:41:38,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 73596928. Throughput: 0: 1745.7, 1: 1724.9. Samples: 18410952. Policy #0 lag: (min: 31.0, avg: 32.4, max: 57.0) -[2023-10-15 03:41:38,534][87330] Avg episode reward: [(0, '22.450'), (1, '22.600')] -[2023-10-15 03:41:38,857][88298] Updated weights for policy 0, policy_version 35860 (0.0007) -[2023-10-15 03:41:39,237][88298] Updated weights for policy 0, policy_version 35870 (0.0007) -[2023-10-15 03:41:39,606][88300] Updated weights for policy 1, policy_version 36042 (0.0007) -[2023-10-15 03:41:39,972][88300] Updated weights for policy 1, policy_version 36052 (0.0007) -[2023-10-15 03:41:40,337][88300] Updated weights for policy 1, policy_version 36062 (0.0007) -[2023-10-15 03:41:43,117][88298] Updated weights for policy 0, policy_version 35880 (0.0007) -[2023-10-15 03:41:43,493][88298] Updated weights for policy 0, policy_version 35890 (0.0008) -[2023-10-15 03:41:43,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 73662464. Throughput: 0: 1760.2, 1: 1755.2. Samples: 18432824. Policy #0 lag: (min: 31.0, avg: 32.4, max: 57.0) -[2023-10-15 03:41:43,534][87330] Avg episode reward: [(0, '22.580'), (1, '22.520')] -[2023-10-15 03:41:43,854][88298] Updated weights for policy 0, policy_version 35900 (0.0008) -[2023-10-15 03:41:44,047][88300] Updated weights for policy 1, policy_version 36072 (0.0008) -[2023-10-15 03:41:44,411][88300] Updated weights for policy 1, policy_version 36082 (0.0007) -[2023-10-15 03:41:44,777][88300] Updated weights for policy 1, policy_version 36092 (0.0010) -[2023-10-15 03:41:47,631][88298] Updated weights for policy 0, policy_version 35910 (0.0010) -[2023-10-15 03:41:48,009][88298] Updated weights for policy 0, policy_version 35920 (0.0010) -[2023-10-15 03:41:48,384][88298] Updated weights for policy 0, policy_version 35930 (0.0008) -[2023-10-15 03:41:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13884.7). Total num frames: 73728000. Throughput: 0: 1741.4, 1: 1723.5. Samples: 18442388. Policy #0 lag: (min: 31.0, avg: 32.4, max: 57.0) -[2023-10-15 03:41:48,534][87330] Avg episode reward: [(0, '22.700'), (1, '22.650')] -[2023-10-15 03:41:48,678][88300] Updated weights for policy 1, policy_version 36102 (0.0009) -[2023-10-15 03:41:49,044][88300] Updated weights for policy 1, policy_version 36112 (0.0009) -[2023-10-15 03:41:49,412][88300] Updated weights for policy 1, policy_version 36122 (0.0007) -[2023-10-15 03:41:52,318][88298] Updated weights for policy 0, policy_version 35940 (0.0008) -[2023-10-15 03:41:52,686][88298] Updated weights for policy 0, policy_version 35950 (0.0007) -[2023-10-15 03:41:53,055][88298] Updated weights for policy 0, policy_version 35960 (0.0007) -[2023-10-15 03:41:53,322][88300] Updated weights for policy 1, policy_version 36132 (0.0008) -[2023-10-15 03:41:53,534][87330] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 73826304. Throughput: 0: 1763.2, 1: 1750.3. Samples: 18463808. Policy #0 lag: (min: 31.0, avg: 32.4, max: 57.0) -[2023-10-15 03:41:53,534][87330] Avg episode reward: [(0, '22.720'), (1, '22.620')] -[2023-10-15 03:41:53,692][88300] Updated weights for policy 1, policy_version 36142 (0.0007) -[2023-10-15 03:41:54,052][88300] Updated weights for policy 1, policy_version 36152 (0.0009) -[2023-10-15 03:41:56,889][88298] Updated weights for policy 0, policy_version 35970 (0.0008) -[2023-10-15 03:41:57,254][88298] Updated weights for policy 0, policy_version 35980 (0.0008) -[2023-10-15 03:41:57,621][88298] Updated weights for policy 0, policy_version 35990 (0.0007) -[2023-10-15 03:41:57,958][88300] Updated weights for policy 1, policy_version 36162 (0.0009) -[2023-10-15 03:41:57,991][88298] Updated weights for policy 0, policy_version 36000 (0.0008) -[2023-10-15 03:41:58,330][88300] Updated weights for policy 1, policy_version 36172 (0.0008) -[2023-10-15 03:41:58,534][87330] Fps is (10 sec: 16383.4, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 73891840. Throughput: 0: 1738.2, 1: 1747.5. Samples: 18484236. Policy #0 lag: (min: 5.0, avg: 29.8, max: 32.0) -[2023-10-15 03:41:58,535][87330] Avg episode reward: [(0, '22.700'), (1, '22.500')] -[2023-10-15 03:41:58,706][88300] Updated weights for policy 1, policy_version 36182 (0.0009) -[2023-10-15 03:41:59,075][88300] Updated weights for policy 1, policy_version 36192 (0.0008) -[2023-10-15 03:42:01,869][88298] Updated weights for policy 0, policy_version 36010 (0.0008) -[2023-10-15 03:42:02,244][88298] Updated weights for policy 0, policy_version 36020 (0.0009) -[2023-10-15 03:42:02,615][88298] Updated weights for policy 0, policy_version 36030 (0.0009) -[2023-10-15 03:42:03,104][88300] Updated weights for policy 1, policy_version 36202 (0.0010) -[2023-10-15 03:42:03,487][88300] Updated weights for policy 1, policy_version 36212 (0.0009) -[2023-10-15 03:42:03,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 73957376. Throughput: 0: 1764.6, 1: 1740.0. Samples: 18495068. Policy #0 lag: (min: 5.0, avg: 29.8, max: 32.0) -[2023-10-15 03:42:03,535][87330] Avg episode reward: [(0, '22.710'), (1, '22.500')] -[2023-10-15 03:42:03,863][88300] Updated weights for policy 1, policy_version 36222 (0.0009) -[2023-10-15 03:42:06,548][88298] Updated weights for policy 0, policy_version 36040 (0.0008) -[2023-10-15 03:42:06,924][88298] Updated weights for policy 0, policy_version 36050 (0.0007) -[2023-10-15 03:42:07,302][88298] Updated weights for policy 0, policy_version 36060 (0.0008) -[2023-10-15 03:42:07,701][88300] Updated weights for policy 1, policy_version 36232 (0.0009) -[2023-10-15 03:42:08,075][88300] Updated weights for policy 1, policy_version 36242 (0.0007) -[2023-10-15 03:42:08,437][88300] Updated weights for policy 1, policy_version 36252 (0.0007) -[2023-10-15 03:42:08,534][87330] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 74022912. Throughput: 0: 1746.2, 1: 1761.8. Samples: 18515914. Policy #0 lag: (min: 5.0, avg: 29.8, max: 32.0) -[2023-10-15 03:42:08,534][87330] Avg episode reward: [(0, '22.490'), (1, '22.660')] -[2023-10-15 03:42:11,199][88298] Updated weights for policy 0, policy_version 36070 (0.0008) -[2023-10-15 03:42:11,574][88298] Updated weights for policy 0, policy_version 36080 (0.0009) -[2023-10-15 03:42:11,942][88298] Updated weights for policy 0, policy_version 36090 (0.0007) -[2023-10-15 03:42:12,323][88300] Updated weights for policy 1, policy_version 36262 (0.0007) -[2023-10-15 03:42:12,688][88300] Updated weights for policy 1, policy_version 36272 (0.0009) -[2023-10-15 03:42:13,054][88300] Updated weights for policy 1, policy_version 36282 (0.0008) -[2023-10-15 03:42:13,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 74121216. Throughput: 0: 1729.7, 1: 1732.3. Samples: 18535706. Policy #0 lag: (min: 5.0, avg: 29.8, max: 32.0) -[2023-10-15 03:42:13,535][87330] Avg episode reward: [(0, '22.410'), (1, '22.690')] -[2023-10-15 03:42:15,760][88298] Updated weights for policy 0, policy_version 36100 (0.0008) -[2023-10-15 03:42:16,136][88298] Updated weights for policy 0, policy_version 36110 (0.0007) -[2023-10-15 03:42:16,509][88298] Updated weights for policy 0, policy_version 36120 (0.0008) -[2023-10-15 03:42:16,912][88300] Updated weights for policy 1, policy_version 36292 (0.0008) -[2023-10-15 03:42:17,282][88300] Updated weights for policy 1, policy_version 36302 (0.0008) -[2023-10-15 03:42:17,646][88300] Updated weights for policy 1, policy_version 36312 (0.0011) -[2023-10-15 03:42:18,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 74186752. Throughput: 0: 1755.6, 1: 1759.8. Samples: 18547658. Policy #0 lag: (min: 5.0, avg: 29.8, max: 32.0) -[2023-10-15 03:42:18,534][87330] Avg episode reward: [(0, '22.420'), (1, '22.560')] -[2023-10-15 03:42:20,320][88298] Updated weights for policy 0, policy_version 36130 (0.0009) -[2023-10-15 03:42:20,686][88298] Updated weights for policy 0, policy_version 36140 (0.0007) -[2023-10-15 03:42:21,058][88298] Updated weights for policy 0, policy_version 36150 (0.0007) -[2023-10-15 03:42:21,423][88298] Updated weights for policy 0, policy_version 36160 (0.0009) -[2023-10-15 03:42:21,449][88300] Updated weights for policy 1, policy_version 36322 (0.0008) -[2023-10-15 03:42:21,824][88300] Updated weights for policy 1, policy_version 36332 (0.0008) -[2023-10-15 03:42:22,194][88300] Updated weights for policy 1, policy_version 36342 (0.0008) -[2023-10-15 03:42:22,563][88300] Updated weights for policy 1, policy_version 36352 (0.0008) -[2023-10-15 03:42:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 74252288. Throughput: 0: 1730.1, 1: 1747.7. Samples: 18567456. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:42:23,535][87330] Avg episode reward: [(0, '22.410'), (1, '22.630')] -[2023-10-15 03:42:25,243][88298] Updated weights for policy 0, policy_version 36170 (0.0007) -[2023-10-15 03:42:25,618][88298] Updated weights for policy 0, policy_version 36180 (0.0008) -[2023-10-15 03:42:25,985][88298] Updated weights for policy 0, policy_version 36190 (0.0010) -[2023-10-15 03:42:26,434][88300] Updated weights for policy 1, policy_version 36362 (0.0007) -[2023-10-15 03:42:26,799][88300] Updated weights for policy 1, policy_version 36372 (0.0007) -[2023-10-15 03:42:27,175][88300] Updated weights for policy 1, policy_version 36382 (0.0008) -[2023-10-15 03:42:28,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 74317824. Throughput: 0: 1732.4, 1: 1734.1. Samples: 18588814. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:42:28,534][87330] Avg episode reward: [(0, '22.420'), (1, '22.690')] -[2023-10-15 03:42:29,832][88298] Updated weights for policy 0, policy_version 36200 (0.0007) -[2023-10-15 03:42:30,207][88298] Updated weights for policy 0, policy_version 36210 (0.0007) -[2023-10-15 03:42:30,576][88298] Updated weights for policy 0, policy_version 36220 (0.0008) -[2023-10-15 03:42:31,115][88300] Updated weights for policy 1, policy_version 36392 (0.0008) -[2023-10-15 03:42:31,493][88300] Updated weights for policy 1, policy_version 36402 (0.0008) -[2023-10-15 03:42:31,854][88300] Updated weights for policy 1, policy_version 36412 (0.0010) -[2023-10-15 03:42:33,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 74383360. Throughput: 0: 1732.3, 1: 1756.4. Samples: 18599382. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:42:33,534][87330] Avg episode reward: [(0, '22.460'), (1, '22.690')] -[2023-10-15 03:42:34,557][88298] Updated weights for policy 0, policy_version 36230 (0.0011) -[2023-10-15 03:42:34,925][88298] Updated weights for policy 0, policy_version 36240 (0.0007) -[2023-10-15 03:42:35,296][88298] Updated weights for policy 0, policy_version 36250 (0.0007) -[2023-10-15 03:42:35,797][88300] Updated weights for policy 1, policy_version 36422 (0.0009) -[2023-10-15 03:42:36,170][88300] Updated weights for policy 1, policy_version 36432 (0.0007) -[2023-10-15 03:42:36,541][88300] Updated weights for policy 1, policy_version 36442 (0.0009) -[2023-10-15 03:42:38,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 74448896. Throughput: 0: 1730.5, 1: 1735.4. Samples: 18619776. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:42:38,535][87330] Avg episode reward: [(0, '22.510'), (1, '22.670')] -[2023-10-15 03:42:39,232][88298] Updated weights for policy 0, policy_version 36260 (0.0007) -[2023-10-15 03:42:39,597][88298] Updated weights for policy 0, policy_version 36270 (0.0008) -[2023-10-15 03:42:39,968][88298] Updated weights for policy 0, policy_version 36280 (0.0010) -[2023-10-15 03:42:40,391][88300] Updated weights for policy 1, policy_version 36452 (0.0009) -[2023-10-15 03:42:40,758][88300] Updated weights for policy 1, policy_version 36462 (0.0008) -[2023-10-15 03:42:41,131][88300] Updated weights for policy 1, policy_version 36472 (0.0008) -[2023-10-15 03:42:43,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 74514432. Throughput: 0: 1752.6, 1: 1742.3. Samples: 18641506. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:42:43,534][87330] Avg episode reward: [(0, '22.860'), (1, '22.700')] -[2023-10-15 03:42:43,803][88298] Updated weights for policy 0, policy_version 36290 (0.0009) -[2023-10-15 03:42:44,173][88298] Updated weights for policy 0, policy_version 36300 (0.0009) -[2023-10-15 03:42:44,547][88298] Updated weights for policy 0, policy_version 36310 (0.0009) -[2023-10-15 03:42:44,914][88298] Updated weights for policy 0, policy_version 36320 (0.0008) -[2023-10-15 03:42:44,990][88300] Updated weights for policy 1, policy_version 36482 (0.0008) -[2023-10-15 03:42:45,351][88300] Updated weights for policy 1, policy_version 36492 (0.0008) -[2023-10-15 03:42:45,720][88300] Updated weights for policy 1, policy_version 36502 (0.0009) -[2023-10-15 03:42:46,088][88300] Updated weights for policy 1, policy_version 36512 (0.0008) -[2023-10-15 03:42:48,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 74579968. Throughput: 0: 1728.2, 1: 1739.3. Samples: 18651106. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:42:48,534][87330] Avg episode reward: [(0, '22.690'), (1, '22.860')] -[2023-10-15 03:42:48,742][88298] Updated weights for policy 0, policy_version 36330 (0.0010) -[2023-10-15 03:42:49,106][88298] Updated weights for policy 0, policy_version 36340 (0.0007) -[2023-10-15 03:42:49,480][88298] Updated weights for policy 0, policy_version 36350 (0.0008) -[2023-10-15 03:42:50,012][88300] Updated weights for policy 1, policy_version 36522 (0.0009) -[2023-10-15 03:42:50,377][88300] Updated weights for policy 1, policy_version 36532 (0.0007) -[2023-10-15 03:42:50,751][88300] Updated weights for policy 1, policy_version 36542 (0.0007) -[2023-10-15 03:42:53,484][88298] Updated weights for policy 0, policy_version 36360 (0.0007) -[2023-10-15 03:42:53,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 74645504. Throughput: 0: 1743.1, 1: 1743.3. Samples: 18672802. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:42:53,534][87330] Avg episode reward: [(0, '22.690'), (1, '22.450')] -[2023-10-15 03:42:53,857][88298] Updated weights for policy 0, policy_version 36370 (0.0008) -[2023-10-15 03:42:54,237][88298] Updated weights for policy 0, policy_version 36380 (0.0011) -[2023-10-15 03:42:54,571][88300] Updated weights for policy 1, policy_version 36552 (0.0007) -[2023-10-15 03:42:54,950][88300] Updated weights for policy 1, policy_version 36562 (0.0011) -[2023-10-15 03:42:55,312][88300] Updated weights for policy 1, policy_version 36572 (0.0008) -[2023-10-15 03:42:58,211][88298] Updated weights for policy 0, policy_version 36390 (0.0008) -[2023-10-15 03:42:58,534][87330] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 74711040. Throughput: 0: 1754.3, 1: 1770.1. Samples: 18694304. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:42:58,535][87330] Avg episode reward: [(0, '22.640'), (1, '22.490')] -[2023-10-15 03:42:58,549][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000036576_37453824.pth... -[2023-10-15 03:42:58,578][88298] Updated weights for policy 0, policy_version 36400 (0.0008) -[2023-10-15 03:42:58,584][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000034944_35782656.pth -[2023-10-15 03:42:58,963][88298] Updated weights for policy 0, policy_version 36410 (0.0008) -[2023-10-15 03:42:59,089][88300] Updated weights for policy 1, policy_version 36582 (0.0009) -[2023-10-15 03:42:59,178][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000036416_37289984.pth... -[2023-10-15 03:42:59,211][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000034784_35618816.pth -[2023-10-15 03:42:59,455][88300] Updated weights for policy 1, policy_version 36592 (0.0007) -[2023-10-15 03:42:59,822][88300] Updated weights for policy 1, policy_version 36602 (0.0009) -[2023-10-15 03:43:02,900][88298] Updated weights for policy 0, policy_version 36420 (0.0008) -[2023-10-15 03:43:03,282][88298] Updated weights for policy 0, policy_version 36430 (0.0010) -[2023-10-15 03:43:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 74776576. Throughput: 0: 1726.6, 1: 1741.2. Samples: 18703712. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:43:03,534][87330] Avg episode reward: [(0, '22.500'), (1, '22.460')] -[2023-10-15 03:43:03,646][88298] Updated weights for policy 0, policy_version 36440 (0.0008) -[2023-10-15 03:43:03,680][88300] Updated weights for policy 1, policy_version 36612 (0.0007) -[2023-10-15 03:43:04,048][88300] Updated weights for policy 1, policy_version 36622 (0.0007) -[2023-10-15 03:43:04,418][88300] Updated weights for policy 1, policy_version 36632 (0.0008) -[2023-10-15 03:43:07,578][88298] Updated weights for policy 0, policy_version 36450 (0.0008) -[2023-10-15 03:43:07,950][88298] Updated weights for policy 0, policy_version 36460 (0.0009) -[2023-10-15 03:43:08,204][88300] Updated weights for policy 1, policy_version 36642 (0.0009) -[2023-10-15 03:43:08,314][88298] Updated weights for policy 0, policy_version 36470 (0.0007) -[2023-10-15 03:43:08,534][87330] Fps is (10 sec: 13107.6, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 74842112. Throughput: 0: 1757.2, 1: 1759.9. Samples: 18725724. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:43:08,534][87330] Avg episode reward: [(0, '22.310'), (1, '22.320')] -[2023-10-15 03:43:08,563][88300] Updated weights for policy 1, policy_version 36652 (0.0010) -[2023-10-15 03:43:08,673][88298] Updated weights for policy 0, policy_version 36480 (0.0009) -[2023-10-15 03:43:08,931][88300] Updated weights for policy 1, policy_version 36662 (0.0009) -[2023-10-15 03:43:09,303][88300] Updated weights for policy 1, policy_version 36672 (0.0007) -[2023-10-15 03:43:12,639][88298] Updated weights for policy 0, policy_version 36490 (0.0010) -[2023-10-15 03:43:13,012][88298] Updated weights for policy 0, policy_version 36500 (0.0009) -[2023-10-15 03:43:13,225][88300] Updated weights for policy 1, policy_version 36682 (0.0007) -[2023-10-15 03:43:13,382][88298] Updated weights for policy 0, policy_version 36510 (0.0009) -[2023-10-15 03:43:13,534][87330] Fps is (10 sec: 16383.5, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 74940416. Throughput: 0: 1741.9, 1: 1761.9. Samples: 18746484. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:43:13,535][87330] Avg episode reward: [(0, '22.340'), (1, '22.350')] -[2023-10-15 03:43:13,588][88300] Updated weights for policy 1, policy_version 36692 (0.0009) -[2023-10-15 03:43:13,956][88300] Updated weights for policy 1, policy_version 36702 (0.0009) -[2023-10-15 03:43:17,237][88298] Updated weights for policy 0, policy_version 36520 (0.0008) -[2023-10-15 03:43:17,612][88298] Updated weights for policy 0, policy_version 36530 (0.0008) -[2023-10-15 03:43:17,798][88300] Updated weights for policy 1, policy_version 36712 (0.0008) -[2023-10-15 03:43:17,977][88298] Updated weights for policy 0, policy_version 36540 (0.0009) -[2023-10-15 03:43:18,168][88300] Updated weights for policy 1, policy_version 36722 (0.0007) -[2023-10-15 03:43:18,533][88300] Updated weights for policy 1, policy_version 36732 (0.0007) -[2023-10-15 03:43:18,534][87330] Fps is (10 sec: 16383.6, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 75005952. Throughput: 0: 1753.8, 1: 1749.6. Samples: 18757036. Policy #0 lag: (min: 15.0, avg: 17.8, max: 47.0) -[2023-10-15 03:43:18,535][87330] Avg episode reward: [(0, '22.160'), (1, '22.330')] -[2023-10-15 03:43:21,742][88298] Updated weights for policy 0, policy_version 36550 (0.0007) -[2023-10-15 03:43:22,109][88298] Updated weights for policy 0, policy_version 36560 (0.0007) -[2023-10-15 03:43:22,486][88298] Updated weights for policy 0, policy_version 36570 (0.0007) -[2023-10-15 03:43:22,522][88300] Updated weights for policy 1, policy_version 36742 (0.0007) -[2023-10-15 03:43:22,891][88300] Updated weights for policy 1, policy_version 36752 (0.0007) -[2023-10-15 03:43:23,261][88300] Updated weights for policy 1, policy_version 36762 (0.0011) -[2023-10-15 03:43:23,534][87330] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 75104256. Throughput: 0: 1750.5, 1: 1774.0. Samples: 18778378. Policy #0 lag: (min: 15.0, avg: 17.8, max: 47.0) -[2023-10-15 03:43:23,534][87330] Avg episode reward: [(0, '22.330'), (1, '22.490')] -[2023-10-15 03:43:26,341][88298] Updated weights for policy 0, policy_version 36580 (0.0007) -[2023-10-15 03:43:26,704][88298] Updated weights for policy 0, policy_version 36590 (0.0007) -[2023-10-15 03:43:27,079][88298] Updated weights for policy 0, policy_version 36600 (0.0007) -[2023-10-15 03:43:27,171][88300] Updated weights for policy 1, policy_version 36772 (0.0008) -[2023-10-15 03:43:27,543][88300] Updated weights for policy 1, policy_version 36782 (0.0009) -[2023-10-15 03:43:27,920][88300] Updated weights for policy 1, policy_version 36792 (0.0008) -[2023-10-15 03:43:28,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 75169792. Throughput: 0: 1728.7, 1: 1737.9. Samples: 18797504. Policy #0 lag: (min: 15.0, avg: 17.8, max: 47.0) -[2023-10-15 03:43:28,534][87330] Avg episode reward: [(0, '22.310'), (1, '22.690')] -[2023-10-15 03:43:30,835][88298] Updated weights for policy 0, policy_version 36610 (0.0008) -[2023-10-15 03:43:31,201][88298] Updated weights for policy 0, policy_version 36620 (0.0009) -[2023-10-15 03:43:31,579][88298] Updated weights for policy 0, policy_version 36630 (0.0008) -[2023-10-15 03:43:31,806][88300] Updated weights for policy 1, policy_version 36802 (0.0008) -[2023-10-15 03:43:31,950][88298] Updated weights for policy 0, policy_version 36640 (0.0008) -[2023-10-15 03:43:32,169][88300] Updated weights for policy 1, policy_version 36812 (0.0008) -[2023-10-15 03:43:32,537][88300] Updated weights for policy 1, policy_version 36822 (0.0011) -[2023-10-15 03:43:32,915][88300] Updated weights for policy 1, policy_version 36832 (0.0010) -[2023-10-15 03:43:33,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 75235328. Throughput: 0: 1757.3, 1: 1763.6. Samples: 18809546. Policy #0 lag: (min: 15.0, avg: 17.8, max: 47.0) -[2023-10-15 03:43:33,535][87330] Avg episode reward: [(0, '22.450'), (1, '22.710')] -[2023-10-15 03:43:36,024][88298] Updated weights for policy 0, policy_version 36650 (0.0009) -[2023-10-15 03:43:36,394][88298] Updated weights for policy 0, policy_version 36660 (0.0008) -[2023-10-15 03:43:36,770][88298] Updated weights for policy 0, policy_version 36670 (0.0008) -[2023-10-15 03:43:36,935][88300] Updated weights for policy 1, policy_version 36842 (0.0009) -[2023-10-15 03:43:37,300][88300] Updated weights for policy 1, policy_version 36852 (0.0007) -[2023-10-15 03:43:37,671][88300] Updated weights for policy 1, policy_version 36862 (0.0009) -[2023-10-15 03:43:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 75300864. Throughput: 0: 1726.4, 1: 1742.0. Samples: 18828884. Policy #0 lag: (min: 15.0, avg: 17.8, max: 47.0) -[2023-10-15 03:43:38,534][87330] Avg episode reward: [(0, '22.460'), (1, '22.700')] -[2023-10-15 03:43:40,780][88298] Updated weights for policy 0, policy_version 36680 (0.0007) -[2023-10-15 03:43:41,149][88298] Updated weights for policy 0, policy_version 36690 (0.0008) -[2023-10-15 03:43:41,511][88298] Updated weights for policy 0, policy_version 36700 (0.0008) -[2023-10-15 03:43:41,615][88300] Updated weights for policy 1, policy_version 36872 (0.0008) -[2023-10-15 03:43:41,989][88300] Updated weights for policy 1, policy_version 36882 (0.0007) -[2023-10-15 03:43:42,351][88300] Updated weights for policy 1, policy_version 36892 (0.0008) -[2023-10-15 03:43:43,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 75366400. Throughput: 0: 1726.9, 1: 1724.8. Samples: 18849632. Policy #0 lag: (min: 15.0, avg: 17.8, max: 47.0) -[2023-10-15 03:43:43,535][87330] Avg episode reward: [(0, '22.620'), (1, '22.840')] -[2023-10-15 03:43:45,197][88298] Updated weights for policy 0, policy_version 36710 (0.0007) -[2023-10-15 03:43:45,565][88298] Updated weights for policy 0, policy_version 36720 (0.0008) -[2023-10-15 03:43:45,925][88298] Updated weights for policy 0, policy_version 36730 (0.0007) -[2023-10-15 03:43:46,257][88300] Updated weights for policy 1, policy_version 36902 (0.0008) -[2023-10-15 03:43:46,616][88300] Updated weights for policy 1, policy_version 36912 (0.0007) -[2023-10-15 03:43:46,989][88300] Updated weights for policy 1, policy_version 36922 (0.0008) -[2023-10-15 03:43:48,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 75431936. Throughput: 0: 1743.0, 1: 1753.1. Samples: 18861036. Policy #0 lag: (min: 27.0, avg: 30.0, max: 59.0) -[2023-10-15 03:43:48,534][87330] Avg episode reward: [(0, '22.760'), (1, '22.800')] -[2023-10-15 03:43:49,990][88298] Updated weights for policy 0, policy_version 36740 (0.0008) -[2023-10-15 03:43:50,357][88298] Updated weights for policy 0, policy_version 36750 (0.0007) -[2023-10-15 03:43:50,723][88298] Updated weights for policy 0, policy_version 36760 (0.0008) -[2023-10-15 03:43:50,815][88300] Updated weights for policy 1, policy_version 36932 (0.0008) -[2023-10-15 03:43:51,177][88300] Updated weights for policy 1, policy_version 36942 (0.0009) -[2023-10-15 03:43:51,543][88300] Updated weights for policy 1, policy_version 36952 (0.0008) -[2023-10-15 03:43:53,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 75497472. Throughput: 0: 1721.7, 1: 1725.7. Samples: 18880858. Policy #0 lag: (min: 27.0, avg: 30.0, max: 59.0) -[2023-10-15 03:43:53,534][87330] Avg episode reward: [(0, '22.770'), (1, '22.740')] -[2023-10-15 03:43:54,751][88298] Updated weights for policy 0, policy_version 36770 (0.0007) -[2023-10-15 03:43:55,120][88298] Updated weights for policy 0, policy_version 36780 (0.0007) -[2023-10-15 03:43:55,487][88298] Updated weights for policy 0, policy_version 36790 (0.0007) -[2023-10-15 03:43:55,488][88300] Updated weights for policy 1, policy_version 36962 (0.0008) -[2023-10-15 03:43:55,850][88300] Updated weights for policy 1, policy_version 36972 (0.0007) -[2023-10-15 03:43:55,852][88298] Updated weights for policy 0, policy_version 36800 (0.0009) -[2023-10-15 03:43:56,223][88300] Updated weights for policy 1, policy_version 36982 (0.0007) -[2023-10-15 03:43:56,580][88300] Updated weights for policy 1, policy_version 36992 (0.0010) -[2023-10-15 03:43:58,534][87330] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 75563008. Throughput: 0: 1729.2, 1: 1730.1. Samples: 18902156. Policy #0 lag: (min: 27.0, avg: 30.0, max: 59.0) -[2023-10-15 03:43:58,535][87330] Avg episode reward: [(0, '22.740'), (1, '22.690')] -[2023-10-15 03:43:59,885][88298] Updated weights for policy 0, policy_version 36810 (0.0009) -[2023-10-15 03:44:00,259][88298] Updated weights for policy 0, policy_version 36820 (0.0007) -[2023-10-15 03:44:00,508][88300] Updated weights for policy 1, policy_version 37002 (0.0007) -[2023-10-15 03:44:00,624][88298] Updated weights for policy 0, policy_version 36830 (0.0008) -[2023-10-15 03:44:00,879][88300] Updated weights for policy 1, policy_version 37012 (0.0007) -[2023-10-15 03:44:01,247][88300] Updated weights for policy 1, policy_version 37022 (0.0007) -[2023-10-15 03:44:03,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 75628544. Throughput: 0: 1714.5, 1: 1721.6. Samples: 18911660. Policy #0 lag: (min: 27.0, avg: 30.0, max: 59.0) -[2023-10-15 03:44:03,534][87330] Avg episode reward: [(0, '22.760'), (1, '22.650')] -[2023-10-15 03:44:04,435][88298] Updated weights for policy 0, policy_version 36840 (0.0009) -[2023-10-15 03:44:04,810][88298] Updated weights for policy 0, policy_version 36850 (0.0008) -[2023-10-15 03:44:05,106][88300] Updated weights for policy 1, policy_version 37032 (0.0007) -[2023-10-15 03:44:05,178][88298] Updated weights for policy 0, policy_version 36860 (0.0007) -[2023-10-15 03:44:05,477][88300] Updated weights for policy 1, policy_version 37042 (0.0007) -[2023-10-15 03:44:05,837][88300] Updated weights for policy 1, policy_version 37052 (0.0008) -[2023-10-15 03:44:08,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 75694080. Throughput: 0: 1718.0, 1: 1713.1. Samples: 18932776. Policy #0 lag: (min: 27.0, avg: 30.0, max: 59.0) -[2023-10-15 03:44:08,534][87330] Avg episode reward: [(0, '22.640'), (1, '22.590')] -[2023-10-15 03:44:09,154][88298] Updated weights for policy 0, policy_version 36870 (0.0007) -[2023-10-15 03:44:09,514][88298] Updated weights for policy 0, policy_version 36880 (0.0008) -[2023-10-15 03:44:09,731][88300] Updated weights for policy 1, policy_version 37062 (0.0009) -[2023-10-15 03:44:09,886][88298] Updated weights for policy 0, policy_version 36890 (0.0007) -[2023-10-15 03:44:10,097][88300] Updated weights for policy 1, policy_version 37072 (0.0007) -[2023-10-15 03:44:10,471][88300] Updated weights for policy 1, policy_version 37082 (0.0007) -[2023-10-15 03:44:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 75759616. Throughput: 0: 1739.5, 1: 1751.4. Samples: 18954596. Policy #0 lag: (min: 27.0, avg: 30.0, max: 59.0) -[2023-10-15 03:44:13,535][87330] Avg episode reward: [(0, '22.560'), (1, '22.600')] -[2023-10-15 03:44:13,737][88298] Updated weights for policy 0, policy_version 36900 (0.0008) -[2023-10-15 03:44:14,101][88298] Updated weights for policy 0, policy_version 36910 (0.0009) -[2023-10-15 03:44:14,262][88300] Updated weights for policy 1, policy_version 37092 (0.0008) -[2023-10-15 03:44:14,475][88298] Updated weights for policy 0, policy_version 36920 (0.0008) -[2023-10-15 03:44:14,623][88300] Updated weights for policy 1, policy_version 37102 (0.0008) -[2023-10-15 03:44:14,988][88300] Updated weights for policy 1, policy_version 37112 (0.0009) -[2023-10-15 03:44:18,354][88298] Updated weights for policy 0, policy_version 36930 (0.0008) -[2023-10-15 03:44:18,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 75825152. Throughput: 0: 1708.0, 1: 1724.5. Samples: 18964006. Policy #0 lag: (min: 31.0, avg: 31.2, max: 41.0) -[2023-10-15 03:44:18,535][87330] Avg episode reward: [(0, '22.540'), (1, '22.600')] -[2023-10-15 03:44:18,729][88298] Updated weights for policy 0, policy_version 36940 (0.0010) -[2023-10-15 03:44:18,969][88300] Updated weights for policy 1, policy_version 37122 (0.0007) -[2023-10-15 03:44:19,103][88298] Updated weights for policy 0, policy_version 36950 (0.0009) -[2023-10-15 03:44:19,330][88300] Updated weights for policy 1, policy_version 37132 (0.0008) -[2023-10-15 03:44:19,466][88298] Updated weights for policy 0, policy_version 36960 (0.0008) -[2023-10-15 03:44:19,703][88300] Updated weights for policy 1, policy_version 37142 (0.0008) -[2023-10-15 03:44:20,072][88300] Updated weights for policy 1, policy_version 37152 (0.0009) -[2023-10-15 03:44:23,436][88298] Updated weights for policy 0, policy_version 36970 (0.0008) -[2023-10-15 03:44:23,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13884.8). Total num frames: 75890688. Throughput: 0: 1738.0, 1: 1740.8. Samples: 18985432. Policy #0 lag: (min: 31.0, avg: 31.2, max: 41.0) -[2023-10-15 03:44:23,534][87330] Avg episode reward: [(0, '22.540'), (1, '22.640')] -[2023-10-15 03:44:23,806][88298] Updated weights for policy 0, policy_version 36980 (0.0008) -[2023-10-15 03:44:24,135][88300] Updated weights for policy 1, policy_version 37162 (0.0008) -[2023-10-15 03:44:24,167][88298] Updated weights for policy 0, policy_version 36990 (0.0009) -[2023-10-15 03:44:24,499][88300] Updated weights for policy 1, policy_version 37172 (0.0008) -[2023-10-15 03:44:24,865][88300] Updated weights for policy 1, policy_version 37182 (0.0010) -[2023-10-15 03:44:28,257][88298] Updated weights for policy 0, policy_version 37000 (0.0008) -[2023-10-15 03:44:28,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13884.7). Total num frames: 75956224. Throughput: 0: 1738.0, 1: 1757.9. Samples: 19006946. Policy #0 lag: (min: 31.0, avg: 31.2, max: 41.0) -[2023-10-15 03:44:28,534][87330] Avg episode reward: [(0, '22.540'), (1, '22.650')] -[2023-10-15 03:44:28,598][88300] Updated weights for policy 1, policy_version 37192 (0.0008) -[2023-10-15 03:44:28,637][88298] Updated weights for policy 0, policy_version 37010 (0.0009) -[2023-10-15 03:44:28,969][88300] Updated weights for policy 1, policy_version 37202 (0.0008) -[2023-10-15 03:44:28,995][88298] Updated weights for policy 0, policy_version 37020 (0.0007) -[2023-10-15 03:44:29,338][88300] Updated weights for policy 1, policy_version 37212 (0.0009) -[2023-10-15 03:44:33,105][88298] Updated weights for policy 0, policy_version 37030 (0.0008) -[2023-10-15 03:44:33,267][88300] Updated weights for policy 1, policy_version 37222 (0.0009) -[2023-10-15 03:44:33,469][88298] Updated weights for policy 0, policy_version 37040 (0.0007) -[2023-10-15 03:44:33,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 76021760. Throughput: 0: 1721.3, 1: 1729.3. Samples: 19016314. Policy #0 lag: (min: 31.0, avg: 31.2, max: 41.0) -[2023-10-15 03:44:33,534][87330] Avg episode reward: [(0, '22.600'), (1, '22.660')] -[2023-10-15 03:44:33,634][88300] Updated weights for policy 1, policy_version 37232 (0.0008) -[2023-10-15 03:44:33,843][88298] Updated weights for policy 0, policy_version 37050 (0.0009) -[2023-10-15 03:44:33,997][88300] Updated weights for policy 1, policy_version 37242 (0.0007) -[2023-10-15 03:44:37,712][88298] Updated weights for policy 0, policy_version 37060 (0.0008) -[2023-10-15 03:44:37,932][88300] Updated weights for policy 1, policy_version 37252 (0.0008) -[2023-10-15 03:44:38,080][88298] Updated weights for policy 0, policy_version 37070 (0.0007) -[2023-10-15 03:44:38,299][88300] Updated weights for policy 1, policy_version 37262 (0.0008) -[2023-10-15 03:44:38,449][88298] Updated weights for policy 0, policy_version 37080 (0.0008) -[2023-10-15 03:44:38,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 76087296. Throughput: 0: 1726.2, 1: 1753.0. Samples: 19037420. Policy #0 lag: (min: 31.0, avg: 31.2, max: 41.0) -[2023-10-15 03:44:38,534][87330] Avg episode reward: [(0, '22.480'), (1, '22.750')] -[2023-10-15 03:44:38,667][88300] Updated weights for policy 1, policy_version 37272 (0.0008) -[2023-10-15 03:44:42,390][88298] Updated weights for policy 0, policy_version 37090 (0.0007) -[2023-10-15 03:44:42,627][88300] Updated weights for policy 1, policy_version 37282 (0.0008) -[2023-10-15 03:44:42,746][88298] Updated weights for policy 0, policy_version 37100 (0.0008) -[2023-10-15 03:44:42,995][88300] Updated weights for policy 1, policy_version 37292 (0.0008) -[2023-10-15 03:44:43,118][88298] Updated weights for policy 0, policy_version 37110 (0.0009) -[2023-10-15 03:44:43,367][88300] Updated weights for policy 1, policy_version 37302 (0.0007) -[2023-10-15 03:44:43,497][88298] Updated weights for policy 0, policy_version 37120 (0.0008) -[2023-10-15 03:44:43,534][87330] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 76185600. Throughput: 0: 1719.1, 1: 1736.1. Samples: 19057638. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:44:43,534][87330] Avg episode reward: [(0, '22.530'), (1, '22.700')] -[2023-10-15 03:44:43,723][88300] Updated weights for policy 1, policy_version 37312 (0.0007) -[2023-10-15 03:44:47,297][88298] Updated weights for policy 0, policy_version 37130 (0.0007) -[2023-10-15 03:44:47,661][88298] Updated weights for policy 0, policy_version 37140 (0.0007) -[2023-10-15 03:44:47,718][88300] Updated weights for policy 1, policy_version 37322 (0.0007) -[2023-10-15 03:44:48,025][88298] Updated weights for policy 0, policy_version 37150 (0.0009) -[2023-10-15 03:44:48,075][88300] Updated weights for policy 1, policy_version 37332 (0.0007) -[2023-10-15 03:44:48,437][88300] Updated weights for policy 1, policy_version 37342 (0.0010) -[2023-10-15 03:44:48,534][87330] Fps is (10 sec: 19660.5, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 76283904. Throughput: 0: 1733.2, 1: 1747.3. Samples: 19068282. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:44:48,535][87330] Avg episode reward: [(0, '22.640'), (1, '22.650')] -[2023-10-15 03:44:52,117][88298] Updated weights for policy 0, policy_version 37160 (0.0008) -[2023-10-15 03:44:52,360][88300] Updated weights for policy 1, policy_version 37352 (0.0008) -[2023-10-15 03:44:52,492][88298] Updated weights for policy 0, policy_version 37170 (0.0008) -[2023-10-15 03:44:52,729][88300] Updated weights for policy 1, policy_version 37362 (0.0007) -[2023-10-15 03:44:52,861][88298] Updated weights for policy 0, policy_version 37180 (0.0008) -[2023-10-15 03:44:53,095][88300] Updated weights for policy 1, policy_version 37372 (0.0007) -[2023-10-15 03:44:53,534][87330] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 76349440. Throughput: 0: 1729.7, 1: 1755.3. Samples: 19089600. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:44:53,535][87330] Avg episode reward: [(0, '22.650'), (1, '22.710')] -[2023-10-15 03:44:56,852][88298] Updated weights for policy 0, policy_version 37190 (0.0009) -[2023-10-15 03:44:57,058][88300] Updated weights for policy 1, policy_version 37382 (0.0008) -[2023-10-15 03:44:57,219][88298] Updated weights for policy 0, policy_version 37200 (0.0007) -[2023-10-15 03:44:57,419][88300] Updated weights for policy 1, policy_version 37392 (0.0008) -[2023-10-15 03:44:57,595][88298] Updated weights for policy 0, policy_version 37210 (0.0007) -[2023-10-15 03:44:57,789][88300] Updated weights for policy 1, policy_version 37402 (0.0008) -[2023-10-15 03:44:58,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 76414976. Throughput: 0: 1700.5, 1: 1719.1. Samples: 19108480. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:44:58,535][87330] Avg episode reward: [(0, '22.630'), (1, '22.770')] -[2023-10-15 03:44:58,545][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000037216_38109184.pth... -[2023-10-15 03:44:58,545][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000037408_38305792.pth... -[2023-10-15 03:44:58,586][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000035776_36634624.pth -[2023-10-15 03:44:58,587][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000035584_36438016.pth -[2023-10-15 03:45:01,523][88298] Updated weights for policy 0, policy_version 37220 (0.0007) -[2023-10-15 03:45:01,717][88300] Updated weights for policy 1, policy_version 37412 (0.0010) -[2023-10-15 03:45:01,887][88298] Updated weights for policy 0, policy_version 37230 (0.0007) -[2023-10-15 03:45:02,076][88300] Updated weights for policy 1, policy_version 37422 (0.0008) -[2023-10-15 03:45:02,253][88298] Updated weights for policy 0, policy_version 37240 (0.0008) -[2023-10-15 03:45:02,447][88300] Updated weights for policy 1, policy_version 37432 (0.0007) -[2023-10-15 03:45:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 76480512. Throughput: 0: 1729.1, 1: 1748.8. Samples: 19120508. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:45:03,535][87330] Avg episode reward: [(0, '22.630'), (1, '22.750')] -[2023-10-15 03:45:06,237][88298] Updated weights for policy 0, policy_version 37250 (0.0008) -[2023-10-15 03:45:06,359][88300] Updated weights for policy 1, policy_version 37442 (0.0009) -[2023-10-15 03:45:06,611][88298] Updated weights for policy 0, policy_version 37260 (0.0008) -[2023-10-15 03:45:06,720][88300] Updated weights for policy 1, policy_version 37452 (0.0008) -[2023-10-15 03:45:06,970][88298] Updated weights for policy 0, policy_version 37270 (0.0008) -[2023-10-15 03:45:07,091][88300] Updated weights for policy 1, policy_version 37462 (0.0008) -[2023-10-15 03:45:07,338][88298] Updated weights for policy 0, policy_version 37280 (0.0009) -[2023-10-15 03:45:07,460][88300] Updated weights for policy 1, policy_version 37472 (0.0008) -[2023-10-15 03:45:08,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 76546048. Throughput: 0: 1709.0, 1: 1725.4. Samples: 19139978. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:45:08,534][87330] Avg episode reward: [(0, '22.600'), (1, '22.770')] -[2023-10-15 03:45:11,315][88298] Updated weights for policy 0, policy_version 37290 (0.0008) -[2023-10-15 03:45:11,326][88300] Updated weights for policy 1, policy_version 37482 (0.0009) -[2023-10-15 03:45:11,692][88298] Updated weights for policy 0, policy_version 37300 (0.0009) -[2023-10-15 03:45:11,693][88300] Updated weights for policy 1, policy_version 37492 (0.0008) -[2023-10-15 03:45:12,053][88298] Updated weights for policy 0, policy_version 37310 (0.0008) -[2023-10-15 03:45:12,065][88300] Updated weights for policy 1, policy_version 37502 (0.0008) -[2023-10-15 03:45:13,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 76611584. Throughput: 0: 1697.2, 1: 1712.8. Samples: 19160398. Policy #0 lag: (min: 28.0, avg: 32.7, max: 60.0) -[2023-10-15 03:45:13,534][87330] Avg episode reward: [(0, '22.740'), (1, '22.620')] -[2023-10-15 03:45:15,953][88298] Updated weights for policy 0, policy_version 37320 (0.0007) -[2023-10-15 03:45:15,999][88300] Updated weights for policy 1, policy_version 37512 (0.0009) -[2023-10-15 03:45:16,325][88298] Updated weights for policy 0, policy_version 37330 (0.0010) -[2023-10-15 03:45:16,362][88300] Updated weights for policy 1, policy_version 37522 (0.0007) -[2023-10-15 03:45:16,697][88298] Updated weights for policy 0, policy_version 37340 (0.0007) -[2023-10-15 03:45:16,736][88300] Updated weights for policy 1, policy_version 37532 (0.0008) -[2023-10-15 03:45:18,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 76677120. Throughput: 0: 1725.2, 1: 1729.2. Samples: 19171760. Policy #0 lag: (min: 28.0, avg: 32.7, max: 60.0) -[2023-10-15 03:45:18,534][87330] Avg episode reward: [(0, '22.830'), (1, '22.530')] -[2023-10-15 03:45:20,633][88300] Updated weights for policy 1, policy_version 37542 (0.0007) -[2023-10-15 03:45:20,727][88298] Updated weights for policy 0, policy_version 37350 (0.0007) -[2023-10-15 03:45:20,995][88300] Updated weights for policy 1, policy_version 37552 (0.0008) -[2023-10-15 03:45:21,088][88298] Updated weights for policy 0, policy_version 37360 (0.0007) -[2023-10-15 03:45:21,367][88300] Updated weights for policy 1, policy_version 37562 (0.0009) -[2023-10-15 03:45:21,470][88298] Updated weights for policy 0, policy_version 37370 (0.0007) -[2023-10-15 03:45:23,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 76742656. Throughput: 0: 1701.5, 1: 1713.9. Samples: 19191110. Policy #0 lag: (min: 28.0, avg: 32.7, max: 60.0) -[2023-10-15 03:45:23,535][87330] Avg episode reward: [(0, '22.810'), (1, '22.540')] -[2023-10-15 03:45:25,282][88300] Updated weights for policy 1, policy_version 37572 (0.0008) -[2023-10-15 03:45:25,400][88298] Updated weights for policy 0, policy_version 37380 (0.0007) -[2023-10-15 03:45:25,670][88300] Updated weights for policy 1, policy_version 37582 (0.0007) -[2023-10-15 03:45:25,769][88298] Updated weights for policy 0, policy_version 37390 (0.0007) -[2023-10-15 03:45:26,025][88300] Updated weights for policy 1, policy_version 37592 (0.0007) -[2023-10-15 03:45:26,143][88298] Updated weights for policy 0, policy_version 37400 (0.0007) -[2023-10-15 03:45:28,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 76808192. Throughput: 0: 1708.3, 1: 1732.0. Samples: 19212454. Policy #0 lag: (min: 28.0, avg: 32.7, max: 60.0) -[2023-10-15 03:45:28,535][87330] Avg episode reward: [(0, '22.790'), (1, '22.550')] -[2023-10-15 03:45:29,942][88300] Updated weights for policy 1, policy_version 37602 (0.0008) -[2023-10-15 03:45:29,996][88298] Updated weights for policy 0, policy_version 37410 (0.0008) -[2023-10-15 03:45:30,304][88300] Updated weights for policy 1, policy_version 37612 (0.0007) -[2023-10-15 03:45:30,355][88298] Updated weights for policy 0, policy_version 37420 (0.0008) -[2023-10-15 03:45:30,670][88300] Updated weights for policy 1, policy_version 37622 (0.0007) -[2023-10-15 03:45:30,719][88298] Updated weights for policy 0, policy_version 37430 (0.0009) -[2023-10-15 03:45:31,037][88300] Updated weights for policy 1, policy_version 37632 (0.0007) -[2023-10-15 03:45:31,092][88298] Updated weights for policy 0, policy_version 37440 (0.0008) -[2023-10-15 03:45:33,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 76873728. Throughput: 0: 1709.0, 1: 1719.1. Samples: 19222546. Policy #0 lag: (min: 28.0, avg: 32.7, max: 60.0) -[2023-10-15 03:45:33,535][87330] Avg episode reward: [(0, '22.820'), (1, '22.550')] -[2023-10-15 03:45:34,841][88300] Updated weights for policy 1, policy_version 37642 (0.0008) -[2023-10-15 03:45:35,015][88298] Updated weights for policy 0, policy_version 37450 (0.0008) -[2023-10-15 03:45:35,200][88300] Updated weights for policy 1, policy_version 37652 (0.0008) -[2023-10-15 03:45:35,383][88298] Updated weights for policy 0, policy_version 37460 (0.0008) -[2023-10-15 03:45:35,566][88300] Updated weights for policy 1, policy_version 37662 (0.0007) -[2023-10-15 03:45:35,753][88298] Updated weights for policy 0, policy_version 37470 (0.0010) -[2023-10-15 03:45:38,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 76939264. Throughput: 0: 1702.4, 1: 1723.8. Samples: 19243778. Policy #0 lag: (min: 28.0, avg: 32.7, max: 60.0) -[2023-10-15 03:45:38,534][87330] Avg episode reward: [(0, '22.820'), (1, '22.510')] -[2023-10-15 03:45:39,523][88300] Updated weights for policy 1, policy_version 37672 (0.0007) -[2023-10-15 03:45:39,630][88298] Updated weights for policy 0, policy_version 37480 (0.0008) -[2023-10-15 03:45:39,887][88300] Updated weights for policy 1, policy_version 37682 (0.0008) -[2023-10-15 03:45:40,001][88298] Updated weights for policy 0, policy_version 37490 (0.0010) -[2023-10-15 03:45:40,245][88300] Updated weights for policy 1, policy_version 37692 (0.0007) -[2023-10-15 03:45:40,373][88298] Updated weights for policy 0, policy_version 37500 (0.0010) -[2023-10-15 03:45:43,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 77004800. Throughput: 0: 1733.9, 1: 1759.6. Samples: 19265690. Policy #0 lag: (min: 8.0, avg: 32.9, max: 40.0) -[2023-10-15 03:45:43,535][87330] Avg episode reward: [(0, '22.840'), (1, '22.510')] -[2023-10-15 03:45:44,080][88300] Updated weights for policy 1, policy_version 37702 (0.0008) -[2023-10-15 03:45:44,272][88298] Updated weights for policy 0, policy_version 37510 (0.0009) -[2023-10-15 03:45:44,442][88300] Updated weights for policy 1, policy_version 37712 (0.0008) -[2023-10-15 03:45:44,631][88298] Updated weights for policy 0, policy_version 37520 (0.0007) -[2023-10-15 03:45:44,809][88300] Updated weights for policy 1, policy_version 37722 (0.0009) -[2023-10-15 03:45:45,002][88298] Updated weights for policy 0, policy_version 37530 (0.0009) -[2023-10-15 03:45:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 77070336. Throughput: 0: 1710.1, 1: 1730.1. Samples: 19275318. Policy #0 lag: (min: 8.0, avg: 32.9, max: 40.0) -[2023-10-15 03:45:48,534][87330] Avg episode reward: [(0, '22.810'), (1, '22.810')] -[2023-10-15 03:45:48,824][88300] Updated weights for policy 1, policy_version 37732 (0.0007) -[2023-10-15 03:45:48,941][88298] Updated weights for policy 0, policy_version 37540 (0.0009) -[2023-10-15 03:45:49,186][88300] Updated weights for policy 1, policy_version 37742 (0.0008) -[2023-10-15 03:45:49,309][88298] Updated weights for policy 0, policy_version 37550 (0.0008) -[2023-10-15 03:45:49,555][88300] Updated weights for policy 1, policy_version 37752 (0.0009) -[2023-10-15 03:45:49,677][88298] Updated weights for policy 0, policy_version 37560 (0.0008) -[2023-10-15 03:45:53,294][88300] Updated weights for policy 1, policy_version 37762 (0.0008) -[2023-10-15 03:45:53,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 77135872. Throughput: 0: 1727.6, 1: 1756.5. Samples: 19296764. Policy #0 lag: (min: 8.0, avg: 32.9, max: 40.0) -[2023-10-15 03:45:53,534][87330] Avg episode reward: [(0, '22.810'), (1, '22.780')] -[2023-10-15 03:45:53,620][88298] Updated weights for policy 0, policy_version 37570 (0.0008) -[2023-10-15 03:45:53,665][88300] Updated weights for policy 1, policy_version 37772 (0.0009) -[2023-10-15 03:45:53,995][88298] Updated weights for policy 0, policy_version 37580 (0.0008) -[2023-10-15 03:45:54,023][88300] Updated weights for policy 1, policy_version 37782 (0.0008) -[2023-10-15 03:45:54,369][88298] Updated weights for policy 0, policy_version 37590 (0.0009) -[2023-10-15 03:45:54,391][88300] Updated weights for policy 1, policy_version 37792 (0.0008) -[2023-10-15 03:45:54,735][88298] Updated weights for policy 0, policy_version 37600 (0.0010) -[2023-10-15 03:45:58,526][88300] Updated weights for policy 1, policy_version 37802 (0.0007) -[2023-10-15 03:45:58,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 77201408. Throughput: 0: 1745.2, 1: 1759.7. Samples: 19318118. Policy #0 lag: (min: 8.0, avg: 32.9, max: 40.0) -[2023-10-15 03:45:58,534][87330] Avg episode reward: [(0, '22.850'), (1, '22.770')] -[2023-10-15 03:45:58,738][88298] Updated weights for policy 0, policy_version 37610 (0.0008) -[2023-10-15 03:45:58,904][88300] Updated weights for policy 1, policy_version 37812 (0.0007) -[2023-10-15 03:45:59,115][88298] Updated weights for policy 0, policy_version 37620 (0.0008) -[2023-10-15 03:45:59,268][88300] Updated weights for policy 1, policy_version 37822 (0.0008) -[2023-10-15 03:45:59,495][88298] Updated weights for policy 0, policy_version 37630 (0.0007) -[2023-10-15 03:46:03,191][88300] Updated weights for policy 1, policy_version 37832 (0.0007) -[2023-10-15 03:46:03,377][88298] Updated weights for policy 0, policy_version 37640 (0.0009) -[2023-10-15 03:46:03,534][87330] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 77266944. Throughput: 0: 1720.6, 1: 1741.1. Samples: 19327534. Policy #0 lag: (min: 8.0, avg: 32.9, max: 40.0) -[2023-10-15 03:46:03,535][87330] Avg episode reward: [(0, '22.850'), (1, '22.770')] -[2023-10-15 03:46:03,560][88300] Updated weights for policy 1, policy_version 37842 (0.0007) -[2023-10-15 03:46:03,743][88298] Updated weights for policy 0, policy_version 37650 (0.0010) -[2023-10-15 03:46:03,921][88300] Updated weights for policy 1, policy_version 37852 (0.0007) -[2023-10-15 03:46:04,110][88298] Updated weights for policy 0, policy_version 37660 (0.0007) -[2023-10-15 03:46:07,902][88300] Updated weights for policy 1, policy_version 37862 (0.0009) -[2023-10-15 03:46:07,993][88298] Updated weights for policy 0, policy_version 37670 (0.0009) -[2023-10-15 03:46:08,282][88300] Updated weights for policy 1, policy_version 37872 (0.0008) -[2023-10-15 03:46:08,365][88298] Updated weights for policy 0, policy_version 37680 (0.0009) -[2023-10-15 03:46:08,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 77332480. Throughput: 0: 1748.6, 1: 1753.6. Samples: 19348708. Policy #0 lag: (min: 8.0, avg: 32.9, max: 40.0) -[2023-10-15 03:46:08,534][87330] Avg episode reward: [(0, '22.850'), (1, '22.810')] -[2023-10-15 03:46:08,653][88300] Updated weights for policy 1, policy_version 37882 (0.0009) -[2023-10-15 03:46:08,738][88298] Updated weights for policy 0, policy_version 37690 (0.0010) -[2023-10-15 03:46:12,573][88300] Updated weights for policy 1, policy_version 37892 (0.0008) -[2023-10-15 03:46:12,800][88298] Updated weights for policy 0, policy_version 37700 (0.0010) -[2023-10-15 03:46:12,938][88300] Updated weights for policy 1, policy_version 37902 (0.0007) -[2023-10-15 03:46:13,186][88298] Updated weights for policy 0, policy_version 37710 (0.0009) -[2023-10-15 03:46:13,304][88300] Updated weights for policy 1, policy_version 37912 (0.0007) -[2023-10-15 03:46:13,534][87330] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 77398016. Throughput: 0: 1741.6, 1: 1733.9. Samples: 19368848. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:46:13,534][87330] Avg episode reward: [(0, '22.850'), (1, '22.820')] -[2023-10-15 03:46:13,553][88298] Updated weights for policy 0, policy_version 37720 (0.0010) -[2023-10-15 03:46:17,216][88300] Updated weights for policy 1, policy_version 37922 (0.0007) -[2023-10-15 03:46:17,519][88298] Updated weights for policy 0, policy_version 37730 (0.0008) -[2023-10-15 03:46:17,586][88300] Updated weights for policy 1, policy_version 37932 (0.0009) -[2023-10-15 03:46:17,890][88298] Updated weights for policy 0, policy_version 37740 (0.0008) -[2023-10-15 03:46:17,952][88300] Updated weights for policy 1, policy_version 37942 (0.0007) -[2023-10-15 03:46:18,256][88298] Updated weights for policy 0, policy_version 37750 (0.0008) -[2023-10-15 03:46:18,315][88300] Updated weights for policy 1, policy_version 37952 (0.0007) -[2023-10-15 03:46:18,534][87330] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 77496320. Throughput: 0: 1732.5, 1: 1750.4. Samples: 19379272. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:46:18,534][87330] Avg episode reward: [(0, '22.710'), (1, '22.630')] -[2023-10-15 03:46:18,621][88298] Updated weights for policy 0, policy_version 37760 (0.0007) -[2023-10-15 03:46:22,185][88300] Updated weights for policy 1, policy_version 37962 (0.0007) -[2023-10-15 03:46:22,555][88300] Updated weights for policy 1, policy_version 37972 (0.0009) -[2023-10-15 03:46:22,576][88298] Updated weights for policy 0, policy_version 37770 (0.0009) -[2023-10-15 03:46:22,927][88300] Updated weights for policy 1, policy_version 37982 (0.0009) -[2023-10-15 03:46:22,943][88298] Updated weights for policy 0, policy_version 37780 (0.0007) -[2023-10-15 03:46:23,307][88298] Updated weights for policy 0, policy_version 37790 (0.0009) -[2023-10-15 03:46:23,534][87330] Fps is (10 sec: 19660.8, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 77594624. Throughput: 0: 1740.8, 1: 1738.4. Samples: 19400342. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:46:23,535][87330] Avg episode reward: [(0, '22.680'), (1, '22.480')] -[2023-10-15 03:46:26,770][88300] Updated weights for policy 1, policy_version 37992 (0.0011) -[2023-10-15 03:46:27,145][88300] Updated weights for policy 1, policy_version 38002 (0.0007) -[2023-10-15 03:46:27,250][88298] Updated weights for policy 0, policy_version 37800 (0.0008) -[2023-10-15 03:46:27,506][88300] Updated weights for policy 1, policy_version 38012 (0.0008) -[2023-10-15 03:46:27,614][88298] Updated weights for policy 0, policy_version 37810 (0.0007) -[2023-10-15 03:46:27,991][88298] Updated weights for policy 0, policy_version 37820 (0.0009) -[2023-10-15 03:46:28,534][87330] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 77660160. Throughput: 0: 1714.9, 1: 1715.1. Samples: 19420038. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:46:28,535][87330] Avg episode reward: [(0, '22.650'), (1, '22.360')] -[2023-10-15 03:46:31,286][88300] Updated weights for policy 1, policy_version 38022 (0.0009) -[2023-10-15 03:46:31,645][88300] Updated weights for policy 1, policy_version 38032 (0.0008) -[2023-10-15 03:46:31,949][88298] Updated weights for policy 0, policy_version 37830 (0.0007) -[2023-10-15 03:46:32,005][88300] Updated weights for policy 1, policy_version 38042 (0.0007) -[2023-10-15 03:46:32,315][88298] Updated weights for policy 0, policy_version 37840 (0.0008) -[2023-10-15 03:46:32,687][88298] Updated weights for policy 0, policy_version 37850 (0.0009) -[2023-10-15 03:46:33,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 77725696. Throughput: 0: 1732.6, 1: 1746.3. Samples: 19431868. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:46:33,535][87330] Avg episode reward: [(0, '22.610'), (1, '22.260')] -[2023-10-15 03:46:35,796][88300] Updated weights for policy 1, policy_version 38052 (0.0007) -[2023-10-15 03:46:36,156][88300] Updated weights for policy 1, policy_version 38062 (0.0009) -[2023-10-15 03:46:36,516][88300] Updated weights for policy 1, policy_version 38072 (0.0009) -[2023-10-15 03:46:36,541][88298] Updated weights for policy 0, policy_version 37860 (0.0009) -[2023-10-15 03:46:36,911][88298] Updated weights for policy 0, policy_version 37870 (0.0007) -[2023-10-15 03:46:37,289][88298] Updated weights for policy 0, policy_version 37880 (0.0007) -[2023-10-15 03:46:38,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 77791232. Throughput: 0: 1725.1, 1: 1725.5. Samples: 19452042. Policy #0 lag: (min: 25.0, avg: 39.4, max: 57.0) -[2023-10-15 03:46:38,534][87330] Avg episode reward: [(0, '22.620'), (1, '22.250')] -[2023-10-15 03:46:40,459][88300] Updated weights for policy 1, policy_version 38082 (0.0008) -[2023-10-15 03:46:40,830][88300] Updated weights for policy 1, policy_version 38092 (0.0007) -[2023-10-15 03:46:41,121][88298] Updated weights for policy 0, policy_version 37890 (0.0010) -[2023-10-15 03:46:41,199][88300] Updated weights for policy 1, policy_version 38102 (0.0007) -[2023-10-15 03:46:41,495][88298] Updated weights for policy 0, policy_version 37900 (0.0008) -[2023-10-15 03:46:41,562][88300] Updated weights for policy 1, policy_version 38112 (0.0009) -[2023-10-15 03:46:41,860][88298] Updated weights for policy 0, policy_version 37910 (0.0008) -[2023-10-15 03:46:42,232][88298] Updated weights for policy 0, policy_version 37920 (0.0007) -[2023-10-15 03:46:43,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 77856768. Throughput: 0: 1703.7, 1: 1733.3. Samples: 19472784. Policy #0 lag: (min: 25.0, avg: 39.4, max: 57.0) -[2023-10-15 03:46:43,535][87330] Avg episode reward: [(0, '22.620'), (1, '22.200')] -[2023-10-15 03:46:45,588][88300] Updated weights for policy 1, policy_version 38122 (0.0010) -[2023-10-15 03:46:45,961][88300] Updated weights for policy 1, policy_version 38132 (0.0008) -[2023-10-15 03:46:46,121][88298] Updated weights for policy 0, policy_version 37930 (0.0009) -[2023-10-15 03:46:46,333][88300] Updated weights for policy 1, policy_version 38142 (0.0008) -[2023-10-15 03:46:46,483][88298] Updated weights for policy 0, policy_version 37940 (0.0008) -[2023-10-15 03:46:46,858][88298] Updated weights for policy 0, policy_version 37950 (0.0007) -[2023-10-15 03:46:48,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 77922304. Throughput: 0: 1731.7, 1: 1738.7. Samples: 19483698. Policy #0 lag: (min: 25.0, avg: 39.4, max: 57.0) -[2023-10-15 03:46:48,535][87330] Avg episode reward: [(0, '22.650'), (1, '22.160')] -[2023-10-15 03:46:50,197][88300] Updated weights for policy 1, policy_version 38152 (0.0008) -[2023-10-15 03:46:50,571][88300] Updated weights for policy 1, policy_version 38162 (0.0007) -[2023-10-15 03:46:50,924][88298] Updated weights for policy 0, policy_version 37960 (0.0008) -[2023-10-15 03:46:50,938][88300] Updated weights for policy 1, policy_version 38172 (0.0007) -[2023-10-15 03:46:51,299][88298] Updated weights for policy 0, policy_version 37970 (0.0009) -[2023-10-15 03:46:51,668][88298] Updated weights for policy 0, policy_version 37980 (0.0008) -[2023-10-15 03:46:53,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13884.8). Total num frames: 77987840. Throughput: 0: 1701.4, 1: 1736.9. Samples: 19503434. Policy #0 lag: (min: 25.0, avg: 39.4, max: 57.0) -[2023-10-15 03:46:53,535][87330] Avg episode reward: [(0, '22.790'), (1, '22.380')] -[2023-10-15 03:46:54,927][88300] Updated weights for policy 1, policy_version 38182 (0.0008) -[2023-10-15 03:46:55,292][88300] Updated weights for policy 1, policy_version 38192 (0.0008) -[2023-10-15 03:46:55,595][88298] Updated weights for policy 0, policy_version 37990 (0.0007) -[2023-10-15 03:46:55,666][88300] Updated weights for policy 1, policy_version 38202 (0.0007) -[2023-10-15 03:46:55,968][88298] Updated weights for policy 0, policy_version 38000 (0.0007) -[2023-10-15 03:46:56,335][88298] Updated weights for policy 0, policy_version 38010 (0.0008) -[2023-10-15 03:46:58,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 78053376. Throughput: 0: 1711.2, 1: 1754.7. Samples: 19524812. Policy #0 lag: (min: 25.0, avg: 39.4, max: 57.0) -[2023-10-15 03:46:58,534][87330] Avg episode reward: [(0, '22.850'), (1, '22.650')] -[2023-10-15 03:46:58,541][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000038208_39124992.pth... -[2023-10-15 03:46:58,541][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000038016_38928384.pth... -[2023-10-15 03:46:58,571][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000036576_37453824.pth -[2023-10-15 03:46:58,579][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000036416_37289984.pth -[2023-10-15 03:46:59,513][88300] Updated weights for policy 1, policy_version 38212 (0.0008) -[2023-10-15 03:46:59,878][88300] Updated weights for policy 1, policy_version 38222 (0.0009) -[2023-10-15 03:47:00,240][88300] Updated weights for policy 1, policy_version 38232 (0.0007) -[2023-10-15 03:47:00,309][88298] Updated weights for policy 0, policy_version 38020 (0.0008) -[2023-10-15 03:47:00,668][88298] Updated weights for policy 0, policy_version 38030 (0.0008) -[2023-10-15 03:47:01,046][88298] Updated weights for policy 0, policy_version 38040 (0.0008) -[2023-10-15 03:47:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 78118912. Throughput: 0: 1719.4, 1: 1737.3. Samples: 19534822. Policy #0 lag: (min: 25.0, avg: 39.4, max: 57.0) -[2023-10-15 03:47:03,535][87330] Avg episode reward: [(0, '22.860'), (1, '22.780')] -[2023-10-15 03:47:04,090][88300] Updated weights for policy 1, policy_version 38242 (0.0008) -[2023-10-15 03:47:04,465][88300] Updated weights for policy 1, policy_version 38252 (0.0007) -[2023-10-15 03:47:04,830][88300] Updated weights for policy 1, policy_version 38262 (0.0010) -[2023-10-15 03:47:04,955][88298] Updated weights for policy 0, policy_version 38050 (0.0009) -[2023-10-15 03:47:05,193][88300] Updated weights for policy 1, policy_version 38272 (0.0008) -[2023-10-15 03:47:05,320][88298] Updated weights for policy 0, policy_version 38060 (0.0007) -[2023-10-15 03:47:05,691][88298] Updated weights for policy 0, policy_version 38070 (0.0009) -[2023-10-15 03:47:06,060][88298] Updated weights for policy 0, policy_version 38080 (0.0008) -[2023-10-15 03:47:08,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 78184448. Throughput: 0: 1704.6, 1: 1746.6. Samples: 19555648. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:47:08,534][87330] Avg episode reward: [(0, '22.870'), (1, '22.740')] -[2023-10-15 03:47:08,964][88300] Updated weights for policy 1, policy_version 38282 (0.0009) -[2023-10-15 03:47:09,321][88300] Updated weights for policy 1, policy_version 38292 (0.0007) -[2023-10-15 03:47:09,692][88300] Updated weights for policy 1, policy_version 38302 (0.0010) -[2023-10-15 03:47:10,010][88298] Updated weights for policy 0, policy_version 38090 (0.0007) -[2023-10-15 03:47:10,375][88298] Updated weights for policy 0, policy_version 38100 (0.0007) -[2023-10-15 03:47:10,745][88298] Updated weights for policy 0, policy_version 38110 (0.0010) -[2023-10-15 03:47:13,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 78249984. Throughput: 0: 1727.6, 1: 1763.1. Samples: 19577118. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:47:13,534][87330] Avg episode reward: [(0, '22.870'), (1, '22.770')] -[2023-10-15 03:47:13,595][88300] Updated weights for policy 1, policy_version 38312 (0.0010) -[2023-10-15 03:47:13,960][88300] Updated weights for policy 1, policy_version 38322 (0.0007) -[2023-10-15 03:47:14,333][88300] Updated weights for policy 1, policy_version 38332 (0.0007) -[2023-10-15 03:47:14,631][88298] Updated weights for policy 0, policy_version 38120 (0.0008) -[2023-10-15 03:47:14,999][88298] Updated weights for policy 0, policy_version 38130 (0.0010) -[2023-10-15 03:47:15,368][88298] Updated weights for policy 0, policy_version 38140 (0.0008) -[2023-10-15 03:47:18,298][88300] Updated weights for policy 1, policy_version 38342 (0.0008) -[2023-10-15 03:47:18,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 78315520. Throughput: 0: 1708.5, 1: 1730.4. Samples: 19586618. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:47:18,534][87330] Avg episode reward: [(0, '22.830'), (1, '22.620')] -[2023-10-15 03:47:18,660][88300] Updated weights for policy 1, policy_version 38352 (0.0008) -[2023-10-15 03:47:19,024][88300] Updated weights for policy 1, policy_version 38362 (0.0008) -[2023-10-15 03:47:19,200][88298] Updated weights for policy 0, policy_version 38150 (0.0007) -[2023-10-15 03:47:19,560][88298] Updated weights for policy 0, policy_version 38160 (0.0007) -[2023-10-15 03:47:19,935][88298] Updated weights for policy 0, policy_version 38170 (0.0007) -[2023-10-15 03:47:22,999][88300] Updated weights for policy 1, policy_version 38372 (0.0008) -[2023-10-15 03:47:23,370][88300] Updated weights for policy 1, policy_version 38382 (0.0008) -[2023-10-15 03:47:23,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 78381056. Throughput: 0: 1721.5, 1: 1746.5. Samples: 19608100. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:47:23,535][87330] Avg episode reward: [(0, '22.810'), (1, '22.420')] -[2023-10-15 03:47:23,746][88300] Updated weights for policy 1, policy_version 38392 (0.0008) -[2023-10-15 03:47:23,876][88298] Updated weights for policy 0, policy_version 38180 (0.0007) -[2023-10-15 03:47:24,243][88298] Updated weights for policy 0, policy_version 38190 (0.0008) -[2023-10-15 03:47:24,617][88298] Updated weights for policy 0, policy_version 38200 (0.0009) -[2023-10-15 03:47:27,498][88300] Updated weights for policy 1, policy_version 38402 (0.0009) -[2023-10-15 03:47:27,863][88300] Updated weights for policy 1, policy_version 38412 (0.0008) -[2023-10-15 03:47:28,235][88300] Updated weights for policy 1, policy_version 38422 (0.0008) -[2023-10-15 03:47:28,520][88298] Updated weights for policy 0, policy_version 38210 (0.0008) -[2023-10-15 03:47:28,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 78446592. Throughput: 0: 1740.3, 1: 1728.7. Samples: 19628888. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:47:28,534][87330] Avg episode reward: [(0, '22.780'), (1, '22.440')] -[2023-10-15 03:47:28,601][88300] Updated weights for policy 1, policy_version 38432 (0.0008) -[2023-10-15 03:47:28,885][88298] Updated weights for policy 0, policy_version 38220 (0.0008) -[2023-10-15 03:47:29,262][88298] Updated weights for policy 0, policy_version 38230 (0.0008) -[2023-10-15 03:47:29,630][88298] Updated weights for policy 0, policy_version 38240 (0.0009) -[2023-10-15 03:47:32,749][88300] Updated weights for policy 1, policy_version 38442 (0.0010) -[2023-10-15 03:47:33,120][88300] Updated weights for policy 1, policy_version 38452 (0.0009) -[2023-10-15 03:47:33,494][88300] Updated weights for policy 1, policy_version 38462 (0.0008) -[2023-10-15 03:47:33,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 78512128. Throughput: 0: 1710.4, 1: 1744.3. Samples: 19639156. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:47:33,534][87330] Avg episode reward: [(0, '22.770'), (1, '22.440')] -[2023-10-15 03:47:33,581][88298] Updated weights for policy 0, policy_version 38250 (0.0008) -[2023-10-15 03:47:33,953][88298] Updated weights for policy 0, policy_version 38260 (0.0010) -[2023-10-15 03:47:34,331][88298] Updated weights for policy 0, policy_version 38270 (0.0010) -[2023-10-15 03:47:37,397][88300] Updated weights for policy 1, policy_version 38472 (0.0007) -[2023-10-15 03:47:37,761][88300] Updated weights for policy 1, policy_version 38482 (0.0009) -[2023-10-15 03:47:38,126][88300] Updated weights for policy 1, policy_version 38492 (0.0008) -[2023-10-15 03:47:38,343][88298] Updated weights for policy 0, policy_version 38280 (0.0010) -[2023-10-15 03:47:38,534][87330] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 78610432. Throughput: 0: 1742.4, 1: 1745.2. Samples: 19660376. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-15 03:47:38,535][87330] Avg episode reward: [(0, '22.810'), (1, '22.230')] -[2023-10-15 03:47:38,707][88298] Updated weights for policy 0, policy_version 38290 (0.0009) -[2023-10-15 03:47:39,080][88298] Updated weights for policy 0, policy_version 38300 (0.0007) -[2023-10-15 03:47:42,166][88300] Updated weights for policy 1, policy_version 38502 (0.0007) -[2023-10-15 03:47:42,539][88300] Updated weights for policy 1, policy_version 38512 (0.0007) -[2023-10-15 03:47:42,899][88300] Updated weights for policy 1, policy_version 38522 (0.0008) -[2023-10-15 03:47:43,093][88298] Updated weights for policy 0, policy_version 38310 (0.0007) -[2023-10-15 03:47:43,465][88298] Updated weights for policy 0, policy_version 38320 (0.0008) -[2023-10-15 03:47:43,534][87330] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 78675968. Throughput: 0: 1742.4, 1: 1718.5. Samples: 19680556. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-15 03:47:43,534][87330] Avg episode reward: [(0, '22.790'), (1, '22.010')] -[2023-10-15 03:47:43,839][88298] Updated weights for policy 0, policy_version 38330 (0.0009) -[2023-10-15 03:47:46,773][88300] Updated weights for policy 1, policy_version 38532 (0.0007) -[2023-10-15 03:47:47,130][88300] Updated weights for policy 1, policy_version 38542 (0.0009) -[2023-10-15 03:47:47,490][88300] Updated weights for policy 1, policy_version 38552 (0.0011) -[2023-10-15 03:47:47,858][88298] Updated weights for policy 0, policy_version 38340 (0.0008) -[2023-10-15 03:47:48,230][88298] Updated weights for policy 0, policy_version 38350 (0.0010) -[2023-10-15 03:47:48,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 78741504. Throughput: 0: 1726.0, 1: 1751.4. Samples: 19691304. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-15 03:47:48,534][87330] Avg episode reward: [(0, '22.600'), (1, '22.010')] -[2023-10-15 03:47:48,596][88298] Updated weights for policy 0, policy_version 38360 (0.0009) -[2023-10-15 03:47:51,388][88300] Updated weights for policy 1, policy_version 38562 (0.0008) -[2023-10-15 03:47:51,764][88300] Updated weights for policy 1, policy_version 38572 (0.0007) -[2023-10-15 03:47:52,123][88300] Updated weights for policy 1, policy_version 38582 (0.0007) -[2023-10-15 03:47:52,493][88300] Updated weights for policy 1, policy_version 38592 (0.0007) -[2023-10-15 03:47:52,617][88298] Updated weights for policy 0, policy_version 38370 (0.0008) -[2023-10-15 03:47:52,995][88298] Updated weights for policy 0, policy_version 38380 (0.0011) -[2023-10-15 03:47:53,362][88298] Updated weights for policy 0, policy_version 38390 (0.0008) -[2023-10-15 03:47:53,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 78807040. Throughput: 0: 1741.0, 1: 1730.2. Samples: 19711852. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-15 03:47:53,534][87330] Avg episode reward: [(0, '22.610'), (1, '22.240')] -[2023-10-15 03:47:53,735][88298] Updated weights for policy 0, policy_version 38400 (0.0008) -[2023-10-15 03:47:56,261][88300] Updated weights for policy 1, policy_version 38602 (0.0012) -[2023-10-15 03:47:56,637][88300] Updated weights for policy 1, policy_version 38612 (0.0009) -[2023-10-15 03:47:57,003][88300] Updated weights for policy 1, policy_version 38622 (0.0007) -[2023-10-15 03:47:57,609][88298] Updated weights for policy 0, policy_version 38410 (0.0010) -[2023-10-15 03:47:57,990][88298] Updated weights for policy 0, policy_version 38420 (0.0007) -[2023-10-15 03:47:58,362][88298] Updated weights for policy 0, policy_version 38430 (0.0009) -[2023-10-15 03:47:58,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 78905344. Throughput: 0: 1728.6, 1: 1726.8. Samples: 19732608. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-15 03:47:58,534][87330] Avg episode reward: [(0, '22.560'), (1, '22.300')] -[2023-10-15 03:48:00,739][88300] Updated weights for policy 1, policy_version 38632 (0.0009) -[2023-10-15 03:48:01,092][88300] Updated weights for policy 1, policy_version 38642 (0.0008) -[2023-10-15 03:48:01,457][88300] Updated weights for policy 1, policy_version 38652 (0.0009) -[2023-10-15 03:48:02,236][88298] Updated weights for policy 0, policy_version 38440 (0.0009) -[2023-10-15 03:48:02,599][88298] Updated weights for policy 0, policy_version 38450 (0.0007) -[2023-10-15 03:48:02,977][88298] Updated weights for policy 0, policy_version 38460 (0.0007) -[2023-10-15 03:48:03,534][87330] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 78970880. Throughput: 0: 1739.7, 1: 1742.0. Samples: 19743298. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-15 03:48:03,535][87330] Avg episode reward: [(0, '22.610'), (1, '22.210')] -[2023-10-15 03:48:05,355][88300] Updated weights for policy 1, policy_version 38662 (0.0010) -[2023-10-15 03:48:05,717][88300] Updated weights for policy 1, policy_version 38672 (0.0007) -[2023-10-15 03:48:06,076][88300] Updated weights for policy 1, policy_version 38682 (0.0008) -[2023-10-15 03:48:06,771][88298] Updated weights for policy 0, policy_version 38470 (0.0010) -[2023-10-15 03:48:07,134][88298] Updated weights for policy 0, policy_version 38480 (0.0007) -[2023-10-15 03:48:07,510][88298] Updated weights for policy 0, policy_version 38490 (0.0009) -[2023-10-15 03:48:08,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 79036416. Throughput: 0: 1734.9, 1: 1738.1. Samples: 19764384. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-15 03:48:08,534][87330] Avg episode reward: [(0, '22.430'), (1, '22.400')] -[2023-10-15 03:48:09,862][88300] Updated weights for policy 1, policy_version 38692 (0.0007) -[2023-10-15 03:48:10,221][88300] Updated weights for policy 1, policy_version 38702 (0.0009) -[2023-10-15 03:48:10,590][88300] Updated weights for policy 1, policy_version 38712 (0.0007) -[2023-10-15 03:48:11,312][88298] Updated weights for policy 0, policy_version 38500 (0.0008) -[2023-10-15 03:48:11,677][88298] Updated weights for policy 0, policy_version 38510 (0.0009) -[2023-10-15 03:48:12,046][88298] Updated weights for policy 0, policy_version 38520 (0.0007) -[2023-10-15 03:48:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 79101952. Throughput: 0: 1715.9, 1: 1756.9. Samples: 19785164. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-15 03:48:13,535][87330] Avg episode reward: [(0, '22.450'), (1, '22.430')] -[2023-10-15 03:48:14,531][88300] Updated weights for policy 1, policy_version 38722 (0.0008) -[2023-10-15 03:48:14,904][88300] Updated weights for policy 1, policy_version 38732 (0.0009) -[2023-10-15 03:48:15,265][88300] Updated weights for policy 1, policy_version 38742 (0.0009) -[2023-10-15 03:48:15,636][88300] Updated weights for policy 1, policy_version 38752 (0.0009) -[2023-10-15 03:48:15,882][88298] Updated weights for policy 0, policy_version 38530 (0.0007) -[2023-10-15 03:48:16,253][88298] Updated weights for policy 0, policy_version 38540 (0.0007) -[2023-10-15 03:48:16,614][88298] Updated weights for policy 0, policy_version 38550 (0.0007) -[2023-10-15 03:48:16,984][88298] Updated weights for policy 0, policy_version 38560 (0.0008) -[2023-10-15 03:48:18,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 79167488. Throughput: 0: 1746.9, 1: 1738.9. Samples: 19796020. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-15 03:48:18,535][87330] Avg episode reward: [(0, '22.280'), (1, '22.830')] -[2023-10-15 03:48:19,551][88300] Updated weights for policy 1, policy_version 38762 (0.0007) -[2023-10-15 03:48:19,931][88300] Updated weights for policy 1, policy_version 38772 (0.0007) -[2023-10-15 03:48:20,302][88300] Updated weights for policy 1, policy_version 38782 (0.0008) -[2023-10-15 03:48:20,892][88298] Updated weights for policy 0, policy_version 38570 (0.0007) -[2023-10-15 03:48:21,261][88298] Updated weights for policy 0, policy_version 38580 (0.0008) -[2023-10-15 03:48:21,641][88298] Updated weights for policy 0, policy_version 38590 (0.0009) -[2023-10-15 03:48:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 79233024. Throughput: 0: 1719.7, 1: 1743.5. Samples: 19816222. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-15 03:48:23,534][87330] Avg episode reward: [(0, '22.510'), (1, '22.820')] -[2023-10-15 03:48:24,102][88300] Updated weights for policy 1, policy_version 38792 (0.0008) -[2023-10-15 03:48:24,466][88300] Updated weights for policy 1, policy_version 38802 (0.0007) -[2023-10-15 03:48:24,833][88300] Updated weights for policy 1, policy_version 38812 (0.0009) -[2023-10-15 03:48:25,454][88298] Updated weights for policy 0, policy_version 38600 (0.0008) -[2023-10-15 03:48:25,836][88298] Updated weights for policy 0, policy_version 38610 (0.0008) -[2023-10-15 03:48:26,214][88298] Updated weights for policy 0, policy_version 38620 (0.0008) -[2023-10-15 03:48:28,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 79298560. Throughput: 0: 1722.6, 1: 1775.0. Samples: 19837948. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-15 03:48:28,535][87330] Avg episode reward: [(0, '22.590'), (1, '22.790')] -[2023-10-15 03:48:28,710][88300] Updated weights for policy 1, policy_version 38822 (0.0008) -[2023-10-15 03:48:29,074][88300] Updated weights for policy 1, policy_version 38832 (0.0009) -[2023-10-15 03:48:29,440][88300] Updated weights for policy 1, policy_version 38842 (0.0007) -[2023-10-15 03:48:30,095][88298] Updated weights for policy 0, policy_version 38630 (0.0007) -[2023-10-15 03:48:30,453][88298] Updated weights for policy 0, policy_version 38640 (0.0007) -[2023-10-15 03:48:30,825][88298] Updated weights for policy 0, policy_version 38650 (0.0007) -[2023-10-15 03:48:33,345][88300] Updated weights for policy 1, policy_version 38852 (0.0008) -[2023-10-15 03:48:33,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 79364096. Throughput: 0: 1734.5, 1: 1743.7. Samples: 19847824. Policy #0 lag: (min: 1.0, avg: 13.0, max: 33.0) -[2023-10-15 03:48:33,535][87330] Avg episode reward: [(0, '22.530'), (1, '22.760')] -[2023-10-15 03:48:33,709][88300] Updated weights for policy 1, policy_version 38862 (0.0007) -[2023-10-15 03:48:34,071][88300] Updated weights for policy 1, policy_version 38872 (0.0010) -[2023-10-15 03:48:34,761][88298] Updated weights for policy 0, policy_version 38660 (0.0009) -[2023-10-15 03:48:35,124][88298] Updated weights for policy 0, policy_version 38670 (0.0010) -[2023-10-15 03:48:35,487][88298] Updated weights for policy 0, policy_version 38680 (0.0010) -[2023-10-15 03:48:37,904][88300] Updated weights for policy 1, policy_version 38882 (0.0009) -[2023-10-15 03:48:38,280][88300] Updated weights for policy 1, policy_version 38892 (0.0010) -[2023-10-15 03:48:38,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 79429632. Throughput: 0: 1726.7, 1: 1759.2. Samples: 19868716. Policy #0 lag: (min: 1.0, avg: 13.0, max: 33.0) -[2023-10-15 03:48:38,534][87330] Avg episode reward: [(0, '22.520'), (1, '22.740')] -[2023-10-15 03:48:38,657][88300] Updated weights for policy 1, policy_version 38902 (0.0007) -[2023-10-15 03:48:39,018][88300] Updated weights for policy 1, policy_version 38912 (0.0008) -[2023-10-15 03:48:39,580][88298] Updated weights for policy 0, policy_version 38690 (0.0009) -[2023-10-15 03:48:39,958][88298] Updated weights for policy 0, policy_version 38700 (0.0010) -[2023-10-15 03:48:40,325][88298] Updated weights for policy 0, policy_version 38710 (0.0008) -[2023-10-15 03:48:40,692][88298] Updated weights for policy 0, policy_version 38720 (0.0009) -[2023-10-15 03:48:43,019][88300] Updated weights for policy 1, policy_version 38922 (0.0011) -[2023-10-15 03:48:43,379][88300] Updated weights for policy 1, policy_version 38932 (0.0009) -[2023-10-15 03:48:43,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 79495168. Throughput: 0: 1741.8, 1: 1753.9. Samples: 19889912. Policy #0 lag: (min: 1.0, avg: 13.0, max: 33.0) -[2023-10-15 03:48:43,534][87330] Avg episode reward: [(0, '22.660'), (1, '22.770')] -[2023-10-15 03:48:43,748][88300] Updated weights for policy 1, policy_version 38942 (0.0007) -[2023-10-15 03:48:44,598][88298] Updated weights for policy 0, policy_version 38730 (0.0009) -[2023-10-15 03:48:44,966][88298] Updated weights for policy 0, policy_version 38740 (0.0011) -[2023-10-15 03:48:45,334][88298] Updated weights for policy 0, policy_version 38750 (0.0008) -[2023-10-15 03:48:47,584][88300] Updated weights for policy 1, policy_version 38952 (0.0010) -[2023-10-15 03:48:47,956][88300] Updated weights for policy 1, policy_version 38962 (0.0008) -[2023-10-15 03:48:48,320][88300] Updated weights for policy 1, policy_version 38972 (0.0008) -[2023-10-15 03:48:48,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 79593472. Throughput: 0: 1730.7, 1: 1756.5. Samples: 19900222. Policy #0 lag: (min: 1.0, avg: 13.0, max: 33.0) -[2023-10-15 03:48:48,534][87330] Avg episode reward: [(0, '22.670'), (1, '22.770')] -[2023-10-15 03:48:49,245][88298] Updated weights for policy 0, policy_version 38760 (0.0007) -[2023-10-15 03:48:49,616][88298] Updated weights for policy 0, policy_version 38770 (0.0009) -[2023-10-15 03:48:49,978][88298] Updated weights for policy 0, policy_version 38780 (0.0009) -[2023-10-15 03:48:52,055][88300] Updated weights for policy 1, policy_version 38982 (0.0008) -[2023-10-15 03:48:52,413][88300] Updated weights for policy 1, policy_version 38992 (0.0007) -[2023-10-15 03:48:52,785][88300] Updated weights for policy 1, policy_version 39002 (0.0007) -[2023-10-15 03:48:53,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 13884.8). Total num frames: 79659008. Throughput: 0: 1734.3, 1: 1759.5. Samples: 19921606. Policy #0 lag: (min: 1.0, avg: 13.0, max: 33.0) -[2023-10-15 03:48:53,535][87330] Avg episode reward: [(0, '22.830'), (1, '22.750')] -[2023-10-15 03:48:53,798][88298] Updated weights for policy 0, policy_version 38790 (0.0008) -[2023-10-15 03:48:54,174][88298] Updated weights for policy 0, policy_version 38800 (0.0009) -[2023-10-15 03:48:54,539][88298] Updated weights for policy 0, policy_version 38810 (0.0009) -[2023-10-15 03:48:56,662][88300] Updated weights for policy 1, policy_version 39012 (0.0007) -[2023-10-15 03:48:57,028][88300] Updated weights for policy 1, policy_version 39022 (0.0007) -[2023-10-15 03:48:57,400][88300] Updated weights for policy 1, policy_version 39032 (0.0007) -[2023-10-15 03:48:58,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 79724544. Throughput: 0: 1753.6, 1: 1743.0. Samples: 19942512. Policy #0 lag: (min: 1.0, avg: 13.0, max: 33.0) -[2023-10-15 03:48:58,534][87330] Avg episode reward: [(0, '22.810'), (1, '22.740')] -[2023-10-15 03:48:58,546][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000039040_39976960.pth... -[2023-10-15 03:48:58,585][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000037408_38305792.pth -[2023-10-15 03:48:58,626][88298] Updated weights for policy 0, policy_version 38820 (0.0009) -[2023-10-15 03:48:58,991][88298] Updated weights for policy 0, policy_version 38830 (0.0007) -[2023-10-15 03:48:59,358][88298] Updated weights for policy 0, policy_version 38840 (0.0007) -[2023-10-15 03:48:59,649][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000038848_39780352.pth... -[2023-10-15 03:48:59,688][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000037216_38109184.pth -[2023-10-15 03:49:01,309][88300] Updated weights for policy 1, policy_version 39042 (0.0008) -[2023-10-15 03:49:01,678][88300] Updated weights for policy 1, policy_version 39052 (0.0009) -[2023-10-15 03:49:02,048][88300] Updated weights for policy 1, policy_version 39062 (0.0008) -[2023-10-15 03:49:02,423][88300] Updated weights for policy 1, policy_version 39072 (0.0008) -[2023-10-15 03:49:03,255][88298] Updated weights for policy 0, policy_version 38850 (0.0010) -[2023-10-15 03:49:03,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 79790080. Throughput: 0: 1723.0, 1: 1770.8. Samples: 19953242. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:49:03,534][87330] Avg episode reward: [(0, '22.850'), (1, '22.790')] -[2023-10-15 03:49:03,628][88298] Updated weights for policy 0, policy_version 38860 (0.0009) -[2023-10-15 03:49:03,987][88298] Updated weights for policy 0, policy_version 38870 (0.0011) -[2023-10-15 03:49:04,354][88298] Updated weights for policy 0, policy_version 38880 (0.0008) -[2023-10-15 03:49:06,373][88300] Updated weights for policy 1, policy_version 39082 (0.0007) -[2023-10-15 03:49:06,734][88300] Updated weights for policy 1, policy_version 39092 (0.0009) -[2023-10-15 03:49:07,099][88300] Updated weights for policy 1, policy_version 39102 (0.0007) -[2023-10-15 03:49:08,103][88298] Updated weights for policy 0, policy_version 38890 (0.0008) -[2023-10-15 03:49:08,472][88298] Updated weights for policy 0, policy_version 38900 (0.0007) -[2023-10-15 03:49:08,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 79855616. Throughput: 0: 1753.9, 1: 1736.7. Samples: 19973298. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:49:08,535][87330] Avg episode reward: [(0, '22.920'), (1, '22.670')] -[2023-10-15 03:49:08,844][88298] Updated weights for policy 0, policy_version 38910 (0.0008) -[2023-10-15 03:49:10,940][88300] Updated weights for policy 1, policy_version 39112 (0.0008) -[2023-10-15 03:49:11,306][88300] Updated weights for policy 1, policy_version 39122 (0.0009) -[2023-10-15 03:49:11,668][88300] Updated weights for policy 1, policy_version 39132 (0.0009) -[2023-10-15 03:49:12,981][88298] Updated weights for policy 0, policy_version 38920 (0.0008) -[2023-10-15 03:49:13,365][88298] Updated weights for policy 0, policy_version 38930 (0.0010) -[2023-10-15 03:49:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 79921152. Throughput: 0: 1749.6, 1: 1735.4. Samples: 19994776. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:49:13,534][87330] Avg episode reward: [(0, '22.920'), (1, '22.850')] -[2023-10-15 03:49:13,741][88298] Updated weights for policy 0, policy_version 38940 (0.0010) -[2023-10-15 03:49:15,516][88300] Updated weights for policy 1, policy_version 39142 (0.0008) -[2023-10-15 03:49:15,885][88300] Updated weights for policy 1, policy_version 39152 (0.0011) -[2023-10-15 03:49:16,245][88300] Updated weights for policy 1, policy_version 39162 (0.0009) -[2023-10-15 03:49:17,633][88298] Updated weights for policy 0, policy_version 38950 (0.0011) -[2023-10-15 03:49:18,006][88298] Updated weights for policy 0, policy_version 38960 (0.0010) -[2023-10-15 03:49:18,371][88298] Updated weights for policy 0, policy_version 38970 (0.0010) -[2023-10-15 03:49:18,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 79986688. Throughput: 0: 1743.2, 1: 1742.8. Samples: 20004694. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:49:18,535][87330] Avg episode reward: [(0, '22.940'), (1, '22.810')] -[2023-10-15 03:49:20,342][88300] Updated weights for policy 1, policy_version 39172 (0.0010) -[2023-10-15 03:49:20,718][88300] Updated weights for policy 1, policy_version 39182 (0.0009) -[2023-10-15 03:49:21,078][88300] Updated weights for policy 1, policy_version 39192 (0.0007) -[2023-10-15 03:49:22,204][88298] Updated weights for policy 0, policy_version 38980 (0.0009) -[2023-10-15 03:49:22,571][88298] Updated weights for policy 0, policy_version 38990 (0.0007) -[2023-10-15 03:49:22,939][88298] Updated weights for policy 0, policy_version 39000 (0.0008) -[2023-10-15 03:49:23,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 80084992. Throughput: 0: 1752.3, 1: 1736.9. Samples: 20025732. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:49:23,534][87330] Avg episode reward: [(0, '22.940'), (1, '22.830')] -[2023-10-15 03:49:25,028][88300] Updated weights for policy 1, policy_version 39202 (0.0009) -[2023-10-15 03:49:25,401][88300] Updated weights for policy 1, policy_version 39212 (0.0008) -[2023-10-15 03:49:25,772][88300] Updated weights for policy 1, policy_version 39222 (0.0008) -[2023-10-15 03:49:26,130][88300] Updated weights for policy 1, policy_version 39232 (0.0008) -[2023-10-15 03:49:26,812][88298] Updated weights for policy 0, policy_version 39010 (0.0009) -[2023-10-15 03:49:27,184][88298] Updated weights for policy 0, policy_version 39020 (0.0008) -[2023-10-15 03:49:27,552][88298] Updated weights for policy 0, policy_version 39030 (0.0009) -[2023-10-15 03:49:27,922][88298] Updated weights for policy 0, policy_version 39040 (0.0009) -[2023-10-15 03:49:28,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 80150528. Throughput: 0: 1724.0, 1: 1754.1. Samples: 20046430. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:49:28,535][87330] Avg episode reward: [(0, '22.930'), (1, '22.850')] -[2023-10-15 03:49:29,786][88300] Updated weights for policy 1, policy_version 39242 (0.0007) -[2023-10-15 03:49:30,149][88300] Updated weights for policy 1, policy_version 39252 (0.0009) -[2023-10-15 03:49:30,521][88300] Updated weights for policy 1, policy_version 39262 (0.0009) -[2023-10-15 03:49:31,746][88298] Updated weights for policy 0, policy_version 39050 (0.0010) -[2023-10-15 03:49:32,126][88298] Updated weights for policy 0, policy_version 39060 (0.0007) -[2023-10-15 03:49:32,506][88298] Updated weights for policy 0, policy_version 39070 (0.0009) -[2023-10-15 03:49:33,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 80216064. Throughput: 0: 1753.0, 1: 1739.0. Samples: 20057362. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:49:33,535][87330] Avg episode reward: [(0, '22.740'), (1, '22.820')] -[2023-10-15 03:49:34,368][88300] Updated weights for policy 1, policy_version 39272 (0.0009) -[2023-10-15 03:49:34,736][88300] Updated weights for policy 1, policy_version 39282 (0.0008) -[2023-10-15 03:49:35,103][88300] Updated weights for policy 1, policy_version 39292 (0.0009) -[2023-10-15 03:49:36,461][88298] Updated weights for policy 0, policy_version 39080 (0.0010) -[2023-10-15 03:49:36,829][88298] Updated weights for policy 0, policy_version 39090 (0.0010) -[2023-10-15 03:49:37,204][88298] Updated weights for policy 0, policy_version 39100 (0.0007) -[2023-10-15 03:49:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 80281600. Throughput: 0: 1733.5, 1: 1746.0. Samples: 20078180. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:49:38,534][87330] Avg episode reward: [(0, '22.710'), (1, '22.820')] -[2023-10-15 03:49:38,772][88300] Updated weights for policy 1, policy_version 39302 (0.0007) -[2023-10-15 03:49:39,146][88300] Updated weights for policy 1, policy_version 39312 (0.0007) -[2023-10-15 03:49:39,502][88300] Updated weights for policy 1, policy_version 39322 (0.0007) -[2023-10-15 03:49:41,204][88298] Updated weights for policy 0, policy_version 39110 (0.0009) -[2023-10-15 03:49:41,570][88298] Updated weights for policy 0, policy_version 39120 (0.0010) -[2023-10-15 03:49:41,936][88298] Updated weights for policy 0, policy_version 39130 (0.0008) -[2023-10-15 03:49:43,378][88300] Updated weights for policy 1, policy_version 39332 (0.0010) -[2023-10-15 03:49:43,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 80347136. Throughput: 0: 1715.4, 1: 1763.1. Samples: 20099046. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:49:43,535][87330] Avg episode reward: [(0, '22.710'), (1, '22.800')] -[2023-10-15 03:49:43,744][88300] Updated weights for policy 1, policy_version 39342 (0.0008) -[2023-10-15 03:49:44,109][88300] Updated weights for policy 1, policy_version 39352 (0.0009) -[2023-10-15 03:49:45,888][88298] Updated weights for policy 0, policy_version 39140 (0.0009) -[2023-10-15 03:49:46,256][88298] Updated weights for policy 0, policy_version 39150 (0.0008) -[2023-10-15 03:49:46,628][88298] Updated weights for policy 0, policy_version 39160 (0.0009) -[2023-10-15 03:49:48,143][88300] Updated weights for policy 1, policy_version 39362 (0.0009) -[2023-10-15 03:49:48,514][88300] Updated weights for policy 1, policy_version 39372 (0.0009) -[2023-10-15 03:49:48,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 80412672. Throughput: 0: 1742.5, 1: 1735.5. Samples: 20109752. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:49:48,534][87330] Avg episode reward: [(0, '22.700'), (1, '22.780')] -[2023-10-15 03:49:48,880][88300] Updated weights for policy 1, policy_version 39382 (0.0010) -[2023-10-15 03:49:49,250][88300] Updated weights for policy 1, policy_version 39392 (0.0010) -[2023-10-15 03:49:50,540][88298] Updated weights for policy 0, policy_version 39170 (0.0008) -[2023-10-15 03:49:50,914][88298] Updated weights for policy 0, policy_version 39180 (0.0010) -[2023-10-15 03:49:51,291][88298] Updated weights for policy 0, policy_version 39190 (0.0010) -[2023-10-15 03:49:51,662][88298] Updated weights for policy 0, policy_version 39200 (0.0009) -[2023-10-15 03:49:53,139][88300] Updated weights for policy 1, policy_version 39402 (0.0007) -[2023-10-15 03:49:53,509][88300] Updated weights for policy 1, policy_version 39412 (0.0010) -[2023-10-15 03:49:53,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 80478208. Throughput: 0: 1712.9, 1: 1777.2. Samples: 20130352. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:49:53,534][87330] Avg episode reward: [(0, '22.690'), (1, '22.780')] -[2023-10-15 03:49:53,875][88300] Updated weights for policy 1, policy_version 39422 (0.0011) -[2023-10-15 03:49:55,617][88298] Updated weights for policy 0, policy_version 39210 (0.0009) -[2023-10-15 03:49:55,998][88298] Updated weights for policy 0, policy_version 39220 (0.0008) -[2023-10-15 03:49:56,367][88298] Updated weights for policy 0, policy_version 39230 (0.0009) -[2023-10-15 03:49:57,805][88300] Updated weights for policy 1, policy_version 39432 (0.0010) -[2023-10-15 03:49:58,171][88300] Updated weights for policy 1, policy_version 39442 (0.0010) -[2023-10-15 03:49:58,529][88300] Updated weights for policy 1, policy_version 39452 (0.0009) -[2023-10-15 03:49:58,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 80543744. Throughput: 0: 1714.0, 1: 1756.4. Samples: 20150948. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-15 03:49:58,535][87330] Avg episode reward: [(0, '22.590'), (1, '22.770')] -[2023-10-15 03:50:00,178][88298] Updated weights for policy 0, policy_version 39240 (0.0007) -[2023-10-15 03:50:00,560][88298] Updated weights for policy 0, policy_version 39250 (0.0007) -[2023-10-15 03:50:00,940][88298] Updated weights for policy 0, policy_version 39260 (0.0007) -[2023-10-15 03:50:02,476][88300] Updated weights for policy 1, policy_version 39462 (0.0008) -[2023-10-15 03:50:02,851][88300] Updated weights for policy 1, policy_version 39472 (0.0010) -[2023-10-15 03:50:03,213][88300] Updated weights for policy 1, policy_version 39482 (0.0007) -[2023-10-15 03:50:03,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 80642048. Throughput: 0: 1721.1, 1: 1763.1. Samples: 20161482. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-15 03:50:03,534][87330] Avg episode reward: [(0, '22.770'), (1, '22.820')] -[2023-10-15 03:50:04,857][88298] Updated weights for policy 0, policy_version 39270 (0.0008) -[2023-10-15 03:50:05,231][88298] Updated weights for policy 0, policy_version 39280 (0.0008) -[2023-10-15 03:50:05,598][88298] Updated weights for policy 0, policy_version 39290 (0.0007) -[2023-10-15 03:50:06,962][88300] Updated weights for policy 1, policy_version 39492 (0.0007) -[2023-10-15 03:50:07,331][88300] Updated weights for policy 1, policy_version 39502 (0.0007) -[2023-10-15 03:50:07,704][88300] Updated weights for policy 1, policy_version 39512 (0.0009) -[2023-10-15 03:50:08,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 80707584. Throughput: 0: 1708.8, 1: 1767.7. Samples: 20182176. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-15 03:50:08,535][87330] Avg episode reward: [(0, '22.770'), (1, '22.800')] -[2023-10-15 03:50:09,581][88298] Updated weights for policy 0, policy_version 39300 (0.0010) -[2023-10-15 03:50:09,945][88298] Updated weights for policy 0, policy_version 39310 (0.0009) -[2023-10-15 03:50:10,314][88298] Updated weights for policy 0, policy_version 39320 (0.0008) -[2023-10-15 03:50:11,528][88300] Updated weights for policy 1, policy_version 39522 (0.0011) -[2023-10-15 03:50:11,896][88300] Updated weights for policy 1, policy_version 39532 (0.0007) -[2023-10-15 03:50:12,257][88300] Updated weights for policy 1, policy_version 39542 (0.0009) -[2023-10-15 03:50:12,619][88300] Updated weights for policy 1, policy_version 39552 (0.0009) -[2023-10-15 03:50:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 80773120. Throughput: 0: 1737.6, 1: 1741.8. Samples: 20203000. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-15 03:50:13,534][87330] Avg episode reward: [(0, '22.650'), (1, '22.790')] -[2023-10-15 03:50:14,363][88298] Updated weights for policy 0, policy_version 39330 (0.0008) -[2023-10-15 03:50:14,725][88298] Updated weights for policy 0, policy_version 39340 (0.0008) -[2023-10-15 03:50:15,098][88298] Updated weights for policy 0, policy_version 39350 (0.0007) -[2023-10-15 03:50:15,475][88298] Updated weights for policy 0, policy_version 39360 (0.0008) -[2023-10-15 03:50:16,485][88300] Updated weights for policy 1, policy_version 39562 (0.0008) -[2023-10-15 03:50:16,850][88300] Updated weights for policy 1, policy_version 39572 (0.0009) -[2023-10-15 03:50:17,221][88300] Updated weights for policy 1, policy_version 39582 (0.0009) -[2023-10-15 03:50:18,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 80838656. Throughput: 0: 1703.6, 1: 1771.2. Samples: 20213728. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-15 03:50:18,534][87330] Avg episode reward: [(0, '22.650'), (1, '22.810')] -[2023-10-15 03:50:19,327][88298] Updated weights for policy 0, policy_version 39370 (0.0007) -[2023-10-15 03:50:19,694][88298] Updated weights for policy 0, policy_version 39380 (0.0010) -[2023-10-15 03:50:20,082][88298] Updated weights for policy 0, policy_version 39390 (0.0010) -[2023-10-15 03:50:21,057][88300] Updated weights for policy 1, policy_version 39592 (0.0007) -[2023-10-15 03:50:21,425][88300] Updated weights for policy 1, policy_version 39602 (0.0007) -[2023-10-15 03:50:21,792][88300] Updated weights for policy 1, policy_version 39612 (0.0008) -[2023-10-15 03:50:23,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 80904192. Throughput: 0: 1727.3, 1: 1745.0. Samples: 20234432. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-15 03:50:23,535][87330] Avg episode reward: [(0, '22.670'), (1, '22.740')] -[2023-10-15 03:50:23,940][88298] Updated weights for policy 0, policy_version 39400 (0.0008) -[2023-10-15 03:50:24,305][88298] Updated weights for policy 0, policy_version 39410 (0.0007) -[2023-10-15 03:50:24,676][88298] Updated weights for policy 0, policy_version 39420 (0.0008) -[2023-10-15 03:50:25,587][88300] Updated weights for policy 1, policy_version 39622 (0.0008) -[2023-10-15 03:50:25,962][88300] Updated weights for policy 1, policy_version 39632 (0.0007) -[2023-10-15 03:50:26,327][88300] Updated weights for policy 1, policy_version 39642 (0.0007) -[2023-10-15 03:50:28,366][88298] Updated weights for policy 0, policy_version 39430 (0.0009) -[2023-10-15 03:50:28,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 80969728. Throughput: 0: 1751.4, 1: 1752.0. Samples: 20256696. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:50:28,534][87330] Avg episode reward: [(0, '22.780'), (1, '22.510')] -[2023-10-15 03:50:28,742][88298] Updated weights for policy 0, policy_version 39440 (0.0009) -[2023-10-15 03:50:29,112][88298] Updated weights for policy 0, policy_version 39450 (0.0010) -[2023-10-15 03:50:30,219][88300] Updated weights for policy 1, policy_version 39652 (0.0007) -[2023-10-15 03:50:30,583][88300] Updated weights for policy 1, policy_version 39662 (0.0009) -[2023-10-15 03:50:30,942][88300] Updated weights for policy 1, policy_version 39672 (0.0010) -[2023-10-15 03:50:33,083][88298] Updated weights for policy 0, policy_version 39460 (0.0008) -[2023-10-15 03:50:33,457][88298] Updated weights for policy 0, policy_version 39470 (0.0008) -[2023-10-15 03:50:33,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 81035264. Throughput: 0: 1723.2, 1: 1754.5. Samples: 20266252. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:50:33,535][87330] Avg episode reward: [(0, '22.750'), (1, '22.430')] -[2023-10-15 03:50:33,830][88298] Updated weights for policy 0, policy_version 39480 (0.0008) -[2023-10-15 03:50:34,746][88300] Updated weights for policy 1, policy_version 39682 (0.0008) -[2023-10-15 03:50:35,123][88300] Updated weights for policy 1, policy_version 39692 (0.0008) -[2023-10-15 03:50:35,486][88300] Updated weights for policy 1, policy_version 39702 (0.0008) -[2023-10-15 03:50:35,851][88300] Updated weights for policy 1, policy_version 39712 (0.0010) -[2023-10-15 03:50:37,606][88298] Updated weights for policy 0, policy_version 39490 (0.0009) -[2023-10-15 03:50:37,978][88298] Updated weights for policy 0, policy_version 39500 (0.0010) -[2023-10-15 03:50:38,348][88298] Updated weights for policy 0, policy_version 39510 (0.0011) -[2023-10-15 03:50:38,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 81100800. Throughput: 0: 1751.4, 1: 1747.3. Samples: 20287794. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:50:38,534][87330] Avg episode reward: [(0, '22.580'), (1, '22.460')] -[2023-10-15 03:50:38,717][88298] Updated weights for policy 0, policy_version 39520 (0.0008) -[2023-10-15 03:50:39,645][88300] Updated weights for policy 1, policy_version 39722 (0.0007) -[2023-10-15 03:50:40,010][88300] Updated weights for policy 1, policy_version 39732 (0.0007) -[2023-10-15 03:50:40,379][88300] Updated weights for policy 1, policy_version 39742 (0.0008) -[2023-10-15 03:50:42,656][88298] Updated weights for policy 0, policy_version 39530 (0.0007) -[2023-10-15 03:50:43,026][88298] Updated weights for policy 0, policy_version 39540 (0.0008) -[2023-10-15 03:50:43,397][88298] Updated weights for policy 0, policy_version 39550 (0.0007) -[2023-10-15 03:50:43,534][87330] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 81199104. Throughput: 0: 1741.4, 1: 1769.2. Samples: 20308926. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:50:43,534][87330] Avg episode reward: [(0, '22.510'), (1, '22.510')] -[2023-10-15 03:50:44,314][88300] Updated weights for policy 1, policy_version 39752 (0.0010) -[2023-10-15 03:50:44,683][88300] Updated weights for policy 1, policy_version 39762 (0.0010) -[2023-10-15 03:50:45,054][88300] Updated weights for policy 1, policy_version 39772 (0.0010) -[2023-10-15 03:50:47,256][88298] Updated weights for policy 0, policy_version 39560 (0.0007) -[2023-10-15 03:50:47,625][88298] Updated weights for policy 0, policy_version 39570 (0.0009) -[2023-10-15 03:50:47,994][88298] Updated weights for policy 0, policy_version 39580 (0.0010) -[2023-10-15 03:50:48,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 81264640. Throughput: 0: 1746.3, 1: 1751.2. Samples: 20318870. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:50:48,534][87330] Avg episode reward: [(0, '22.300'), (1, '22.560')] -[2023-10-15 03:50:48,909][88300] Updated weights for policy 1, policy_version 39782 (0.0009) -[2023-10-15 03:50:49,272][88300] Updated weights for policy 1, policy_version 39792 (0.0007) -[2023-10-15 03:50:49,634][88300] Updated weights for policy 1, policy_version 39802 (0.0007) -[2023-10-15 03:50:51,938][88298] Updated weights for policy 0, policy_version 39590 (0.0007) -[2023-10-15 03:50:52,306][88298] Updated weights for policy 0, policy_version 39600 (0.0009) -[2023-10-15 03:50:52,673][88298] Updated weights for policy 0, policy_version 39610 (0.0010) -[2023-10-15 03:50:53,502][88300] Updated weights for policy 1, policy_version 39812 (0.0008) -[2023-10-15 03:50:53,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 81330176. Throughput: 0: 1759.1, 1: 1758.2. Samples: 20340454. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:50:53,535][87330] Avg episode reward: [(0, '22.270'), (1, '22.600')] -[2023-10-15 03:50:53,868][88300] Updated weights for policy 1, policy_version 39822 (0.0009) -[2023-10-15 03:50:54,241][88300] Updated weights for policy 1, policy_version 39832 (0.0007) -[2023-10-15 03:50:56,811][88298] Updated weights for policy 0, policy_version 39620 (0.0009) -[2023-10-15 03:50:57,192][88298] Updated weights for policy 0, policy_version 39630 (0.0008) -[2023-10-15 03:50:57,562][88298] Updated weights for policy 0, policy_version 39640 (0.0008) -[2023-10-15 03:50:58,129][88300] Updated weights for policy 1, policy_version 39842 (0.0007) -[2023-10-15 03:50:58,505][88300] Updated weights for policy 1, policy_version 39852 (0.0008) -[2023-10-15 03:50:58,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 81395712. Throughput: 0: 1725.3, 1: 1774.8. Samples: 20360504. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:50:58,535][87330] Avg episode reward: [(0, '22.250'), (1, '22.800')] -[2023-10-15 03:50:58,544][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000039648_40599552.pth... -[2023-10-15 03:50:58,572][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000038016_38928384.pth -[2023-10-15 03:50:58,877][88300] Updated weights for policy 1, policy_version 39862 (0.0008) -[2023-10-15 03:50:59,246][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000039872_40828928.pth... -[2023-10-15 03:50:59,248][88300] Updated weights for policy 1, policy_version 39872 (0.0008) -[2023-10-15 03:50:59,274][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000038208_39124992.pth -[2023-10-15 03:51:01,465][88298] Updated weights for policy 0, policy_version 39650 (0.0010) -[2023-10-15 03:51:01,843][88298] Updated weights for policy 0, policy_version 39660 (0.0009) -[2023-10-15 03:51:02,205][88298] Updated weights for policy 0, policy_version 39670 (0.0010) -[2023-10-15 03:51:02,573][88298] Updated weights for policy 0, policy_version 39680 (0.0009) -[2023-10-15 03:51:03,117][88300] Updated weights for policy 1, policy_version 39882 (0.0007) -[2023-10-15 03:51:03,490][88300] Updated weights for policy 1, policy_version 39892 (0.0010) -[2023-10-15 03:51:03,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 81461248. Throughput: 0: 1755.2, 1: 1744.0. Samples: 20371190. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:51:03,534][87330] Avg episode reward: [(0, '22.250'), (1, '22.770')] -[2023-10-15 03:51:03,865][88300] Updated weights for policy 1, policy_version 39902 (0.0008) -[2023-10-15 03:51:06,581][88298] Updated weights for policy 0, policy_version 39690 (0.0008) -[2023-10-15 03:51:06,948][88298] Updated weights for policy 0, policy_version 39700 (0.0007) -[2023-10-15 03:51:07,314][88298] Updated weights for policy 0, policy_version 39710 (0.0009) -[2023-10-15 03:51:07,753][88300] Updated weights for policy 1, policy_version 39912 (0.0007) -[2023-10-15 03:51:08,117][88300] Updated weights for policy 1, policy_version 39922 (0.0008) -[2023-10-15 03:51:08,492][88300] Updated weights for policy 1, policy_version 39932 (0.0009) -[2023-10-15 03:51:08,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 81526784. Throughput: 0: 1736.4, 1: 1767.7. Samples: 20392116. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:51:08,535][87330] Avg episode reward: [(0, '22.410'), (1, '22.750')] -[2023-10-15 03:51:11,232][88298] Updated weights for policy 0, policy_version 39720 (0.0010) -[2023-10-15 03:51:11,595][88298] Updated weights for policy 0, policy_version 39730 (0.0010) -[2023-10-15 03:51:11,973][88298] Updated weights for policy 0, policy_version 39740 (0.0008) -[2023-10-15 03:51:12,389][88300] Updated weights for policy 1, policy_version 39942 (0.0007) -[2023-10-15 03:51:12,767][88300] Updated weights for policy 1, policy_version 39952 (0.0008) -[2023-10-15 03:51:13,136][88300] Updated weights for policy 1, policy_version 39962 (0.0011) -[2023-10-15 03:51:13,534][87330] Fps is (10 sec: 16383.4, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 81625088. Throughput: 0: 1715.3, 1: 1737.5. Samples: 20412076. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:51:13,535][87330] Avg episode reward: [(0, '22.490'), (1, '22.670')] -[2023-10-15 03:51:15,912][88298] Updated weights for policy 0, policy_version 39750 (0.0007) -[2023-10-15 03:51:16,285][88298] Updated weights for policy 0, policy_version 39760 (0.0007) -[2023-10-15 03:51:16,651][88298] Updated weights for policy 0, policy_version 39770 (0.0007) -[2023-10-15 03:51:16,982][88300] Updated weights for policy 1, policy_version 39972 (0.0007) -[2023-10-15 03:51:17,356][88300] Updated weights for policy 1, policy_version 39982 (0.0007) -[2023-10-15 03:51:17,721][88300] Updated weights for policy 1, policy_version 39992 (0.0010) -[2023-10-15 03:51:18,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 81690624. Throughput: 0: 1741.3, 1: 1759.6. Samples: 20423792. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:51:18,535][87330] Avg episode reward: [(0, '22.880'), (1, '22.660')] -[2023-10-15 03:51:20,603][88298] Updated weights for policy 0, policy_version 39780 (0.0008) -[2023-10-15 03:51:20,969][88298] Updated weights for policy 0, policy_version 39790 (0.0007) -[2023-10-15 03:51:21,335][88298] Updated weights for policy 0, policy_version 39800 (0.0008) -[2023-10-15 03:51:21,464][88300] Updated weights for policy 1, policy_version 40002 (0.0007) -[2023-10-15 03:51:21,831][88300] Updated weights for policy 1, policy_version 40012 (0.0008) -[2023-10-15 03:51:22,210][88300] Updated weights for policy 1, policy_version 40022 (0.0008) -[2023-10-15 03:51:22,575][88300] Updated weights for policy 1, policy_version 40032 (0.0007) -[2023-10-15 03:51:23,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 81756160. Throughput: 0: 1713.0, 1: 1744.2. Samples: 20443368. Policy #0 lag: (min: 31.0, avg: 41.9, max: 63.0) -[2023-10-15 03:51:23,535][87330] Avg episode reward: [(0, '22.870'), (1, '22.490')] -[2023-10-15 03:51:25,409][88298] Updated weights for policy 0, policy_version 39810 (0.0007) -[2023-10-15 03:51:25,782][88298] Updated weights for policy 0, policy_version 39820 (0.0007) -[2023-10-15 03:51:26,153][88298] Updated weights for policy 0, policy_version 39830 (0.0008) -[2023-10-15 03:51:26,509][88300] Updated weights for policy 1, policy_version 40042 (0.0008) -[2023-10-15 03:51:26,521][88298] Updated weights for policy 0, policy_version 39840 (0.0008) -[2023-10-15 03:51:26,878][88300] Updated weights for policy 1, policy_version 40052 (0.0009) -[2023-10-15 03:51:27,248][88300] Updated weights for policy 1, policy_version 40062 (0.0011) -[2023-10-15 03:51:28,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 81821696. Throughput: 0: 1722.5, 1: 1730.5. Samples: 20464312. Policy #0 lag: (min: 31.0, avg: 41.9, max: 63.0) -[2023-10-15 03:51:28,535][87330] Avg episode reward: [(0, '22.900'), (1, '22.460')] -[2023-10-15 03:51:30,356][88298] Updated weights for policy 0, policy_version 39850 (0.0008) -[2023-10-15 03:51:30,746][88298] Updated weights for policy 0, policy_version 39860 (0.0009) -[2023-10-15 03:51:31,111][88298] Updated weights for policy 0, policy_version 39870 (0.0009) -[2023-10-15 03:51:31,145][88300] Updated weights for policy 1, policy_version 40072 (0.0009) -[2023-10-15 03:51:31,518][88300] Updated weights for policy 1, policy_version 40082 (0.0008) -[2023-10-15 03:51:31,886][88300] Updated weights for policy 1, policy_version 40092 (0.0007) -[2023-10-15 03:51:33,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 81887232. Throughput: 0: 1720.9, 1: 1755.5. Samples: 20475310. Policy #0 lag: (min: 31.0, avg: 41.9, max: 63.0) -[2023-10-15 03:51:33,534][87330] Avg episode reward: [(0, '22.910'), (1, '22.530')] -[2023-10-15 03:51:35,014][88298] Updated weights for policy 0, policy_version 39880 (0.0010) -[2023-10-15 03:51:35,381][88298] Updated weights for policy 0, policy_version 39890 (0.0007) -[2023-10-15 03:51:35,694][88300] Updated weights for policy 1, policy_version 40102 (0.0007) -[2023-10-15 03:51:35,756][88298] Updated weights for policy 0, policy_version 39900 (0.0008) -[2023-10-15 03:51:36,062][88300] Updated weights for policy 1, policy_version 40112 (0.0008) -[2023-10-15 03:51:36,426][88300] Updated weights for policy 1, policy_version 40122 (0.0008) -[2023-10-15 03:51:38,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 81952768. Throughput: 0: 1708.8, 1: 1734.0. Samples: 20495378. Policy #0 lag: (min: 31.0, avg: 41.9, max: 63.0) -[2023-10-15 03:51:38,535][87330] Avg episode reward: [(0, '22.890'), (1, '22.640')] -[2023-10-15 03:51:39,795][88298] Updated weights for policy 0, policy_version 39910 (0.0007) -[2023-10-15 03:51:40,181][88298] Updated weights for policy 0, policy_version 39920 (0.0007) -[2023-10-15 03:51:40,283][88300] Updated weights for policy 1, policy_version 40132 (0.0009) -[2023-10-15 03:51:40,553][88298] Updated weights for policy 0, policy_version 39930 (0.0009) -[2023-10-15 03:51:40,652][88300] Updated weights for policy 1, policy_version 40142 (0.0007) -[2023-10-15 03:51:41,015][88300] Updated weights for policy 1, policy_version 40152 (0.0009) -[2023-10-15 03:51:43,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 82018304. Throughput: 0: 1737.4, 1: 1735.7. Samples: 20516794. Policy #0 lag: (min: 31.0, avg: 41.9, max: 63.0) -[2023-10-15 03:51:43,535][87330] Avg episode reward: [(0, '22.890'), (1, '22.690')] -[2023-10-15 03:51:44,153][88298] Updated weights for policy 0, policy_version 39940 (0.0010) -[2023-10-15 03:51:44,535][88298] Updated weights for policy 0, policy_version 39950 (0.0009) -[2023-10-15 03:51:44,884][88300] Updated weights for policy 1, policy_version 40162 (0.0010) -[2023-10-15 03:51:44,902][88298] Updated weights for policy 0, policy_version 39960 (0.0008) -[2023-10-15 03:51:45,247][88300] Updated weights for policy 1, policy_version 40172 (0.0008) -[2023-10-15 03:51:45,623][88300] Updated weights for policy 1, policy_version 40182 (0.0007) -[2023-10-15 03:51:45,986][88300] Updated weights for policy 1, policy_version 40192 (0.0007) -[2023-10-15 03:51:48,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 82083840. Throughput: 0: 1711.9, 1: 1735.7. Samples: 20526334. Policy #0 lag: (min: 31.0, avg: 41.9, max: 63.0) -[2023-10-15 03:51:48,534][87330] Avg episode reward: [(0, '22.860'), (1, '22.710')] -[2023-10-15 03:51:48,806][88298] Updated weights for policy 0, policy_version 39970 (0.0007) -[2023-10-15 03:51:49,181][88298] Updated weights for policy 0, policy_version 39980 (0.0008) -[2023-10-15 03:51:49,550][88298] Updated weights for policy 0, policy_version 39990 (0.0009) -[2023-10-15 03:51:49,833][88300] Updated weights for policy 1, policy_version 40202 (0.0009) -[2023-10-15 03:51:49,916][88298] Updated weights for policy 0, policy_version 40000 (0.0008) -[2023-10-15 03:51:50,199][88300] Updated weights for policy 1, policy_version 40212 (0.0007) -[2023-10-15 03:51:50,573][88300] Updated weights for policy 1, policy_version 40222 (0.0009) -[2023-10-15 03:51:53,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 82149376. Throughput: 0: 1717.6, 1: 1743.1. Samples: 20547846. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:51:53,535][87330] Avg episode reward: [(0, '22.840'), (1, '22.840')] -[2023-10-15 03:51:53,970][88298] Updated weights for policy 0, policy_version 40010 (0.0007) -[2023-10-15 03:51:54,341][88298] Updated weights for policy 0, policy_version 40020 (0.0007) -[2023-10-15 03:51:54,427][88300] Updated weights for policy 1, policy_version 40232 (0.0007) -[2023-10-15 03:51:54,722][88298] Updated weights for policy 0, policy_version 40030 (0.0007) -[2023-10-15 03:51:54,797][88300] Updated weights for policy 1, policy_version 40242 (0.0008) -[2023-10-15 03:51:55,162][88300] Updated weights for policy 1, policy_version 40252 (0.0008) -[2023-10-15 03:51:58,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 82214912. Throughput: 0: 1731.4, 1: 1768.4. Samples: 20569570. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:51:58,535][87330] Avg episode reward: [(0, '22.850'), (1, '22.860')] -[2023-10-15 03:51:58,757][88298] Updated weights for policy 0, policy_version 40040 (0.0009) -[2023-10-15 03:51:58,972][88300] Updated weights for policy 1, policy_version 40262 (0.0009) -[2023-10-15 03:51:59,128][88298] Updated weights for policy 0, policy_version 40050 (0.0008) -[2023-10-15 03:51:59,340][88300] Updated weights for policy 1, policy_version 40272 (0.0008) -[2023-10-15 03:51:59,502][88298] Updated weights for policy 0, policy_version 40060 (0.0008) -[2023-10-15 03:51:59,712][88300] Updated weights for policy 1, policy_version 40282 (0.0008) -[2023-10-15 03:52:03,486][88298] Updated weights for policy 0, policy_version 40070 (0.0007) -[2023-10-15 03:52:03,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 82280448. Throughput: 0: 1704.9, 1: 1742.5. Samples: 20578926. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:52:03,535][87330] Avg episode reward: [(0, '22.720'), (1, '22.800')] -[2023-10-15 03:52:03,756][88300] Updated weights for policy 1, policy_version 40292 (0.0008) -[2023-10-15 03:52:03,855][88298] Updated weights for policy 0, policy_version 40080 (0.0008) -[2023-10-15 03:52:04,124][88300] Updated weights for policy 1, policy_version 40302 (0.0008) -[2023-10-15 03:52:04,221][88298] Updated weights for policy 0, policy_version 40090 (0.0007) -[2023-10-15 03:52:04,491][88300] Updated weights for policy 1, policy_version 40312 (0.0009) -[2023-10-15 03:52:08,242][88298] Updated weights for policy 0, policy_version 40100 (0.0007) -[2023-10-15 03:52:08,491][88300] Updated weights for policy 1, policy_version 40322 (0.0007) -[2023-10-15 03:52:08,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 82345984. Throughput: 0: 1734.5, 1: 1760.4. Samples: 20600638. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:52:08,535][87330] Avg episode reward: [(0, '22.720'), (1, '22.760')] -[2023-10-15 03:52:08,610][88298] Updated weights for policy 0, policy_version 40110 (0.0007) -[2023-10-15 03:52:08,864][88300] Updated weights for policy 1, policy_version 40332 (0.0009) -[2023-10-15 03:52:08,980][88298] Updated weights for policy 0, policy_version 40120 (0.0008) -[2023-10-15 03:52:09,231][88300] Updated weights for policy 1, policy_version 40342 (0.0008) -[2023-10-15 03:52:09,600][88300] Updated weights for policy 1, policy_version 40352 (0.0009) -[2023-10-15 03:52:13,072][88298] Updated weights for policy 0, policy_version 40130 (0.0008) -[2023-10-15 03:52:13,430][88298] Updated weights for policy 0, policy_version 40140 (0.0007) -[2023-10-15 03:52:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13884.7). Total num frames: 82411520. Throughput: 0: 1732.9, 1: 1765.9. Samples: 20621760. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:52:13,534][87330] Avg episode reward: [(0, '22.690'), (1, '22.690')] -[2023-10-15 03:52:13,614][88300] Updated weights for policy 1, policy_version 40362 (0.0008) -[2023-10-15 03:52:13,800][88298] Updated weights for policy 0, policy_version 40150 (0.0007) -[2023-10-15 03:52:13,988][88300] Updated weights for policy 1, policy_version 40372 (0.0009) -[2023-10-15 03:52:14,164][88298] Updated weights for policy 0, policy_version 40160 (0.0008) -[2023-10-15 03:52:14,345][88300] Updated weights for policy 1, policy_version 40382 (0.0009) -[2023-10-15 03:52:18,126][88298] Updated weights for policy 0, policy_version 40170 (0.0007) -[2023-10-15 03:52:18,190][88300] Updated weights for policy 1, policy_version 40392 (0.0007) -[2023-10-15 03:52:18,492][88298] Updated weights for policy 0, policy_version 40180 (0.0007) -[2023-10-15 03:52:18,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13884.7). Total num frames: 82477056. Throughput: 0: 1716.6, 1: 1741.6. Samples: 20630926. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:52:18,535][87330] Avg episode reward: [(0, '22.530'), (1, '22.710')] -[2023-10-15 03:52:18,554][88300] Updated weights for policy 1, policy_version 40402 (0.0008) -[2023-10-15 03:52:18,866][88298] Updated weights for policy 0, policy_version 40190 (0.0007) -[2023-10-15 03:52:18,914][88300] Updated weights for policy 1, policy_version 40412 (0.0008) -[2023-10-15 03:52:22,855][88300] Updated weights for policy 1, policy_version 40422 (0.0009) -[2023-10-15 03:52:22,936][88298] Updated weights for policy 0, policy_version 40200 (0.0007) -[2023-10-15 03:52:23,224][88300] Updated weights for policy 1, policy_version 40432 (0.0009) -[2023-10-15 03:52:23,300][88298] Updated weights for policy 0, policy_version 40210 (0.0007) -[2023-10-15 03:52:23,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13884.8). Total num frames: 82542592. Throughput: 0: 1724.6, 1: 1757.5. Samples: 20652074. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:52:23,534][87330] Avg episode reward: [(0, '22.250'), (1, '22.690')] -[2023-10-15 03:52:23,591][88300] Updated weights for policy 1, policy_version 40442 (0.0008) -[2023-10-15 03:52:23,667][88298] Updated weights for policy 0, policy_version 40220 (0.0007) -[2023-10-15 03:52:27,523][88300] Updated weights for policy 1, policy_version 40452 (0.0008) -[2023-10-15 03:52:27,680][88298] Updated weights for policy 0, policy_version 40230 (0.0009) -[2023-10-15 03:52:27,900][88300] Updated weights for policy 1, policy_version 40462 (0.0009) -[2023-10-15 03:52:28,053][88298] Updated weights for policy 0, policy_version 40240 (0.0007) -[2023-10-15 03:52:28,271][88300] Updated weights for policy 1, policy_version 40472 (0.0008) -[2023-10-15 03:52:28,424][88298] Updated weights for policy 0, policy_version 40250 (0.0008) -[2023-10-15 03:52:28,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13107.3, 300 sec: 13884.7). Total num frames: 82608128. Throughput: 0: 1713.7, 1: 1737.6. Samples: 20672104. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:52:28,534][87330] Avg episode reward: [(0, '22.190'), (1, '22.680')] -[2023-10-15 03:52:32,085][88298] Updated weights for policy 0, policy_version 40260 (0.0010) -[2023-10-15 03:52:32,096][88300] Updated weights for policy 1, policy_version 40482 (0.0008) -[2023-10-15 03:52:32,448][88298] Updated weights for policy 0, policy_version 40270 (0.0009) -[2023-10-15 03:52:32,465][88300] Updated weights for policy 1, policy_version 40492 (0.0008) -[2023-10-15 03:52:32,828][88298] Updated weights for policy 0, policy_version 40280 (0.0009) -[2023-10-15 03:52:32,844][88300] Updated weights for policy 1, policy_version 40502 (0.0009) -[2023-10-15 03:52:33,198][88300] Updated weights for policy 1, policy_version 40512 (0.0009) -[2023-10-15 03:52:33,534][87330] Fps is (10 sec: 19660.7, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 82739200. Throughput: 0: 1722.1, 1: 1759.2. Samples: 20682992. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:52:33,534][87330] Avg episode reward: [(0, '21.960'), (1, '22.500')] -[2023-10-15 03:52:36,624][88298] Updated weights for policy 0, policy_version 40290 (0.0008) -[2023-10-15 03:52:36,987][88298] Updated weights for policy 0, policy_version 40300 (0.0008) -[2023-10-15 03:52:37,123][88300] Updated weights for policy 1, policy_version 40522 (0.0008) -[2023-10-15 03:52:37,357][88298] Updated weights for policy 0, policy_version 40310 (0.0008) -[2023-10-15 03:52:37,489][88300] Updated weights for policy 1, policy_version 40532 (0.0008) -[2023-10-15 03:52:37,727][88298] Updated weights for policy 0, policy_version 40320 (0.0007) -[2023-10-15 03:52:37,851][88300] Updated weights for policy 1, policy_version 40542 (0.0008) -[2023-10-15 03:52:38,534][87330] Fps is (10 sec: 19660.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 82804736. Throughput: 0: 1723.0, 1: 1735.2. Samples: 20703466. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:52:38,535][87330] Avg episode reward: [(0, '22.100'), (1, '22.510')] -[2023-10-15 03:52:41,718][88298] Updated weights for policy 0, policy_version 40330 (0.0007) -[2023-10-15 03:52:41,844][88300] Updated weights for policy 1, policy_version 40552 (0.0010) -[2023-10-15 03:52:42,091][88298] Updated weights for policy 0, policy_version 40340 (0.0008) -[2023-10-15 03:52:42,211][88300] Updated weights for policy 1, policy_version 40562 (0.0008) -[2023-10-15 03:52:42,468][88298] Updated weights for policy 0, policy_version 40350 (0.0008) -[2023-10-15 03:52:42,566][88300] Updated weights for policy 1, policy_version 40572 (0.0009) -[2023-10-15 03:52:43,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 82870272. Throughput: 0: 1701.3, 1: 1709.3. Samples: 20723050. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:52:43,534][87330] Avg episode reward: [(0, '22.120'), (1, '22.560')] -[2023-10-15 03:52:46,281][88298] Updated weights for policy 0, policy_version 40360 (0.0008) -[2023-10-15 03:52:46,543][88300] Updated weights for policy 1, policy_version 40582 (0.0009) -[2023-10-15 03:52:46,649][88298] Updated weights for policy 0, policy_version 40370 (0.0008) -[2023-10-15 03:52:46,905][88300] Updated weights for policy 1, policy_version 40592 (0.0008) -[2023-10-15 03:52:47,018][88298] Updated weights for policy 0, policy_version 40380 (0.0008) -[2023-10-15 03:52:47,273][88300] Updated weights for policy 1, policy_version 40602 (0.0008) -[2023-10-15 03:52:48,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 82935808. Throughput: 0: 1736.4, 1: 1739.2. Samples: 20735332. Policy #0 lag: (min: 11.0, avg: 12.9, max: 37.0) -[2023-10-15 03:52:48,534][87330] Avg episode reward: [(0, '22.310'), (1, '22.540')] -[2023-10-15 03:52:50,917][88298] Updated weights for policy 0, policy_version 40390 (0.0009) -[2023-10-15 03:52:51,213][88300] Updated weights for policy 1, policy_version 40612 (0.0009) -[2023-10-15 03:52:51,293][88298] Updated weights for policy 0, policy_version 40400 (0.0009) -[2023-10-15 03:52:51,579][88300] Updated weights for policy 1, policy_version 40622 (0.0008) -[2023-10-15 03:52:51,657][88298] Updated weights for policy 0, policy_version 40410 (0.0008) -[2023-10-15 03:52:51,946][88300] Updated weights for policy 1, policy_version 40632 (0.0007) -[2023-10-15 03:52:53,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 83001344. Throughput: 0: 1708.9, 1: 1705.0. Samples: 20754262. Policy #0 lag: (min: 11.0, avg: 12.9, max: 37.0) -[2023-10-15 03:52:53,534][87330] Avg episode reward: [(0, '22.290'), (1, '22.530')] -[2023-10-15 03:52:55,609][88298] Updated weights for policy 0, policy_version 40420 (0.0008) -[2023-10-15 03:52:55,858][88300] Updated weights for policy 1, policy_version 40642 (0.0010) -[2023-10-15 03:52:55,977][88298] Updated weights for policy 0, policy_version 40430 (0.0007) -[2023-10-15 03:52:56,233][88300] Updated weights for policy 1, policy_version 40652 (0.0008) -[2023-10-15 03:52:56,350][88298] Updated weights for policy 0, policy_version 40440 (0.0008) -[2023-10-15 03:52:56,595][88300] Updated weights for policy 1, policy_version 40662 (0.0008) -[2023-10-15 03:52:56,969][88300] Updated weights for policy 1, policy_version 40672 (0.0007) -[2023-10-15 03:52:58,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 83066880. Throughput: 0: 1713.9, 1: 1707.7. Samples: 20775730. Policy #0 lag: (min: 11.0, avg: 12.9, max: 37.0) -[2023-10-15 03:52:58,535][87330] Avg episode reward: [(0, '22.580'), (1, '22.520')] -[2023-10-15 03:52:58,544][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000040448_41418752.pth... -[2023-10-15 03:52:58,544][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000040672_41648128.pth... -[2023-10-15 03:52:58,574][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000038848_39780352.pth -[2023-10-15 03:52:58,579][87905] Saving a milestone ./train_atari/atari_seaquest_APPO/checkpoint_p0/milestones/checkpoint_000040448_41418752.pth -[2023-10-15 03:52:58,580][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000039040_39976960.pth -[2023-10-15 03:52:58,584][88033] Saving a milestone ./train_atari/atari_seaquest_APPO/checkpoint_p1/milestones/checkpoint_000040672_41648128.pth -[2023-10-15 03:53:00,173][88298] Updated weights for policy 0, policy_version 40450 (0.0008) -[2023-10-15 03:53:00,536][88298] Updated weights for policy 0, policy_version 40460 (0.0007) -[2023-10-15 03:53:00,908][88298] Updated weights for policy 0, policy_version 40470 (0.0008) -[2023-10-15 03:53:00,947][88300] Updated weights for policy 1, policy_version 40682 (0.0008) -[2023-10-15 03:53:01,274][88298] Updated weights for policy 0, policy_version 40480 (0.0008) -[2023-10-15 03:53:01,321][88300] Updated weights for policy 1, policy_version 40692 (0.0008) -[2023-10-15 03:53:01,689][88300] Updated weights for policy 1, policy_version 40702 (0.0008) -[2023-10-15 03:53:03,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 83132416. Throughput: 0: 1732.4, 1: 1723.5. Samples: 20786442. Policy #0 lag: (min: 11.0, avg: 12.9, max: 37.0) -[2023-10-15 03:53:03,534][87330] Avg episode reward: [(0, '22.820'), (1, '22.670')] -[2023-10-15 03:53:05,275][88298] Updated weights for policy 0, policy_version 40490 (0.0009) -[2023-10-15 03:53:05,453][88300] Updated weights for policy 1, policy_version 40712 (0.0008) -[2023-10-15 03:53:05,649][88298] Updated weights for policy 0, policy_version 40500 (0.0009) -[2023-10-15 03:53:05,813][88300] Updated weights for policy 1, policy_version 40722 (0.0008) -[2023-10-15 03:53:06,019][88298] Updated weights for policy 0, policy_version 40510 (0.0007) -[2023-10-15 03:53:06,182][88300] Updated weights for policy 1, policy_version 40732 (0.0008) -[2023-10-15 03:53:08,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 83197952. Throughput: 0: 1722.4, 1: 1714.8. Samples: 20806752. Policy #0 lag: (min: 11.0, avg: 12.9, max: 37.0) -[2023-10-15 03:53:08,535][87330] Avg episode reward: [(0, '22.840'), (1, '22.780')] -[2023-10-15 03:53:09,898][88298] Updated weights for policy 0, policy_version 40520 (0.0011) -[2023-10-15 03:53:10,178][88300] Updated weights for policy 1, policy_version 40742 (0.0008) -[2023-10-15 03:53:10,276][88298] Updated weights for policy 0, policy_version 40530 (0.0008) -[2023-10-15 03:53:10,538][88300] Updated weights for policy 1, policy_version 40752 (0.0007) -[2023-10-15 03:53:10,656][88298] Updated weights for policy 0, policy_version 40540 (0.0008) -[2023-10-15 03:53:10,908][88300] Updated weights for policy 1, policy_version 40762 (0.0008) -[2023-10-15 03:53:13,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 83263488. Throughput: 0: 1732.3, 1: 1738.8. Samples: 20828304. Policy #0 lag: (min: 11.0, avg: 12.9, max: 37.0) -[2023-10-15 03:53:13,535][87330] Avg episode reward: [(0, '22.730'), (1, '22.600')] -[2023-10-15 03:53:14,667][88298] Updated weights for policy 0, policy_version 40550 (0.0008) -[2023-10-15 03:53:14,786][88300] Updated weights for policy 1, policy_version 40772 (0.0008) -[2023-10-15 03:53:15,047][88298] Updated weights for policy 0, policy_version 40560 (0.0008) -[2023-10-15 03:53:15,148][88300] Updated weights for policy 1, policy_version 40782 (0.0007) -[2023-10-15 03:53:15,426][88298] Updated weights for policy 0, policy_version 40570 (0.0008) -[2023-10-15 03:53:15,519][88300] Updated weights for policy 1, policy_version 40792 (0.0008) -[2023-10-15 03:53:18,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 83329024. Throughput: 0: 1720.6, 1: 1715.8. Samples: 20837630. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:53:18,535][87330] Avg episode reward: [(0, '22.740'), (1, '22.630')] -[2023-10-15 03:53:19,296][88298] Updated weights for policy 0, policy_version 40580 (0.0007) -[2023-10-15 03:53:19,386][88300] Updated weights for policy 1, policy_version 40802 (0.0007) -[2023-10-15 03:53:19,663][88298] Updated weights for policy 0, policy_version 40590 (0.0008) -[2023-10-15 03:53:19,753][88300] Updated weights for policy 1, policy_version 40812 (0.0008) -[2023-10-15 03:53:20,038][88298] Updated weights for policy 0, policy_version 40600 (0.0007) -[2023-10-15 03:53:20,114][88300] Updated weights for policy 1, policy_version 40822 (0.0008) -[2023-10-15 03:53:20,481][88300] Updated weights for policy 1, policy_version 40832 (0.0009) -[2023-10-15 03:53:23,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 83394560. Throughput: 0: 1727.9, 1: 1734.6. Samples: 20859280. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:53:23,535][87330] Avg episode reward: [(0, '22.680'), (1, '22.600')] -[2023-10-15 03:53:23,947][88298] Updated weights for policy 0, policy_version 40610 (0.0009) -[2023-10-15 03:53:24,250][88300] Updated weights for policy 1, policy_version 40842 (0.0007) -[2023-10-15 03:53:24,326][88298] Updated weights for policy 0, policy_version 40620 (0.0007) -[2023-10-15 03:53:24,611][88300] Updated weights for policy 1, policy_version 40852 (0.0007) -[2023-10-15 03:53:24,691][88298] Updated weights for policy 0, policy_version 40630 (0.0007) -[2023-10-15 03:53:24,976][88300] Updated weights for policy 1, policy_version 40862 (0.0007) -[2023-10-15 03:53:25,053][88298] Updated weights for policy 0, policy_version 40640 (0.0008) -[2023-10-15 03:53:28,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 83460096. Throughput: 0: 1757.5, 1: 1757.2. Samples: 20881212. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:53:28,534][87330] Avg episode reward: [(0, '22.710'), (1, '22.610')] -[2023-10-15 03:53:28,932][88298] Updated weights for policy 0, policy_version 40650 (0.0008) -[2023-10-15 03:53:29,044][88300] Updated weights for policy 1, policy_version 40872 (0.0007) -[2023-10-15 03:53:29,308][88298] Updated weights for policy 0, policy_version 40660 (0.0007) -[2023-10-15 03:53:29,403][88300] Updated weights for policy 1, policy_version 40882 (0.0007) -[2023-10-15 03:53:29,675][88298] Updated weights for policy 0, policy_version 40670 (0.0008) -[2023-10-15 03:53:29,763][88300] Updated weights for policy 1, policy_version 40892 (0.0009) -[2023-10-15 03:53:33,500][88298] Updated weights for policy 0, policy_version 40680 (0.0008) -[2023-10-15 03:53:33,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13884.7). Total num frames: 83525632. Throughput: 0: 1723.9, 1: 1727.3. Samples: 20890636. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:53:33,534][87330] Avg episode reward: [(0, '22.730'), (1, '22.610')] -[2023-10-15 03:53:33,681][88300] Updated weights for policy 1, policy_version 40902 (0.0009) -[2023-10-15 03:53:33,866][88298] Updated weights for policy 0, policy_version 40690 (0.0008) -[2023-10-15 03:53:34,042][88300] Updated weights for policy 1, policy_version 40912 (0.0009) -[2023-10-15 03:53:34,244][88298] Updated weights for policy 0, policy_version 40700 (0.0007) -[2023-10-15 03:53:34,419][88300] Updated weights for policy 1, policy_version 40922 (0.0008) -[2023-10-15 03:53:38,189][88300] Updated weights for policy 1, policy_version 40932 (0.0009) -[2023-10-15 03:53:38,261][88298] Updated weights for policy 0, policy_version 40710 (0.0007) -[2023-10-15 03:53:38,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13884.7). Total num frames: 83591168. Throughput: 0: 1746.1, 1: 1757.0. Samples: 20911904. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:53:38,534][87330] Avg episode reward: [(0, '22.570'), (1, '22.610')] -[2023-10-15 03:53:38,553][88300] Updated weights for policy 1, policy_version 40942 (0.0008) -[2023-10-15 03:53:38,626][88298] Updated weights for policy 0, policy_version 40720 (0.0007) -[2023-10-15 03:53:38,914][88300] Updated weights for policy 1, policy_version 40952 (0.0007) -[2023-10-15 03:53:38,999][88298] Updated weights for policy 0, policy_version 40730 (0.0007) -[2023-10-15 03:53:42,890][88300] Updated weights for policy 1, policy_version 40962 (0.0007) -[2023-10-15 03:53:43,097][88298] Updated weights for policy 0, policy_version 40740 (0.0009) -[2023-10-15 03:53:43,255][88300] Updated weights for policy 1, policy_version 40972 (0.0007) -[2023-10-15 03:53:43,471][88298] Updated weights for policy 0, policy_version 40750 (0.0007) -[2023-10-15 03:53:43,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 83656704. Throughput: 0: 1739.3, 1: 1748.9. Samples: 20932694. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:53:43,534][87330] Avg episode reward: [(0, '22.600'), (1, '22.720')] -[2023-10-15 03:53:43,627][88300] Updated weights for policy 1, policy_version 40982 (0.0009) -[2023-10-15 03:53:43,839][88298] Updated weights for policy 0, policy_version 40760 (0.0008) -[2023-10-15 03:53:43,979][88300] Updated weights for policy 1, policy_version 40992 (0.0008) -[2023-10-15 03:53:47,778][88298] Updated weights for policy 0, policy_version 40770 (0.0007) -[2023-10-15 03:53:47,912][88300] Updated weights for policy 1, policy_version 41002 (0.0008) -[2023-10-15 03:53:48,154][88298] Updated weights for policy 0, policy_version 40780 (0.0008) -[2023-10-15 03:53:48,282][88300] Updated weights for policy 1, policy_version 41012 (0.0009) -[2023-10-15 03:53:48,521][88298] Updated weights for policy 0, policy_version 40790 (0.0009) -[2023-10-15 03:53:48,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 83722240. Throughput: 0: 1723.2, 1: 1744.7. Samples: 20942496. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:53:48,534][87330] Avg episode reward: [(0, '22.730'), (1, '22.860')] -[2023-10-15 03:53:48,653][88300] Updated weights for policy 1, policy_version 41022 (0.0009) -[2023-10-15 03:53:48,895][88298] Updated weights for policy 0, policy_version 40800 (0.0008) -[2023-10-15 03:53:52,557][88300] Updated weights for policy 1, policy_version 41032 (0.0009) -[2023-10-15 03:53:52,669][88298] Updated weights for policy 0, policy_version 40810 (0.0007) -[2023-10-15 03:53:52,920][88300] Updated weights for policy 1, policy_version 41042 (0.0008) -[2023-10-15 03:53:53,037][88298] Updated weights for policy 0, policy_version 40820 (0.0008) -[2023-10-15 03:53:53,282][88300] Updated weights for policy 1, policy_version 41052 (0.0010) -[2023-10-15 03:53:53,398][88298] Updated weights for policy 0, policy_version 40830 (0.0007) -[2023-10-15 03:53:53,534][87330] Fps is (10 sec: 19660.4, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 83853312. Throughput: 0: 1736.1, 1: 1752.7. Samples: 20963748. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:53:53,535][87330] Avg episode reward: [(0, '22.590'), (1, '22.780')] -[2023-10-15 03:53:57,267][88300] Updated weights for policy 1, policy_version 41062 (0.0007) -[2023-10-15 03:53:57,274][88298] Updated weights for policy 0, policy_version 40840 (0.0008) -[2023-10-15 03:53:57,630][88300] Updated weights for policy 1, policy_version 41072 (0.0008) -[2023-10-15 03:53:57,638][88298] Updated weights for policy 0, policy_version 40850 (0.0008) -[2023-10-15 03:53:57,990][88300] Updated weights for policy 1, policy_version 41082 (0.0008) -[2023-10-15 03:53:58,007][88298] Updated weights for policy 0, policy_version 40860 (0.0007) -[2023-10-15 03:53:58,534][87330] Fps is (10 sec: 19660.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 83918848. Throughput: 0: 1717.3, 1: 1720.8. Samples: 20983016. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:53:58,534][87330] Avg episode reward: [(0, '22.610'), (1, '22.770')] -[2023-10-15 03:54:01,832][88300] Updated weights for policy 1, policy_version 41092 (0.0010) -[2023-10-15 03:54:01,872][88298] Updated weights for policy 0, policy_version 40870 (0.0008) -[2023-10-15 03:54:02,196][88300] Updated weights for policy 1, policy_version 41102 (0.0008) -[2023-10-15 03:54:02,244][88298] Updated weights for policy 0, policy_version 40880 (0.0007) -[2023-10-15 03:54:02,566][88300] Updated weights for policy 1, policy_version 41112 (0.0007) -[2023-10-15 03:54:02,599][88298] Updated weights for policy 0, policy_version 40890 (0.0007) -[2023-10-15 03:54:03,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 83984384. Throughput: 0: 1743.8, 1: 1750.5. Samples: 20994872. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:54:03,534][87330] Avg episode reward: [(0, '22.620'), (1, '22.780')] -[2023-10-15 03:54:06,437][88300] Updated weights for policy 1, policy_version 41122 (0.0010) -[2023-10-15 03:54:06,696][88298] Updated weights for policy 0, policy_version 40900 (0.0007) -[2023-10-15 03:54:06,797][88300] Updated weights for policy 1, policy_version 41132 (0.0009) -[2023-10-15 03:54:07,071][88298] Updated weights for policy 0, policy_version 40910 (0.0007) -[2023-10-15 03:54:07,162][88300] Updated weights for policy 1, policy_version 41142 (0.0009) -[2023-10-15 03:54:07,443][88298] Updated weights for policy 0, policy_version 40920 (0.0009) -[2023-10-15 03:54:07,530][88300] Updated weights for policy 1, policy_version 41152 (0.0009) -[2023-10-15 03:54:08,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 84049920. Throughput: 0: 1736.8, 1: 1731.1. Samples: 21015336. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:54:08,535][87330] Avg episode reward: [(0, '22.770'), (1, '22.780')] -[2023-10-15 03:54:11,372][88298] Updated weights for policy 0, policy_version 40930 (0.0008) -[2023-10-15 03:54:11,421][88300] Updated weights for policy 1, policy_version 41162 (0.0009) -[2023-10-15 03:54:11,753][88298] Updated weights for policy 0, policy_version 40940 (0.0008) -[2023-10-15 03:54:11,790][88300] Updated weights for policy 1, policy_version 41172 (0.0007) -[2023-10-15 03:54:12,130][88298] Updated weights for policy 0, policy_version 40950 (0.0008) -[2023-10-15 03:54:12,161][88300] Updated weights for policy 1, policy_version 41182 (0.0007) -[2023-10-15 03:54:12,498][88298] Updated weights for policy 0, policy_version 40960 (0.0007) -[2023-10-15 03:54:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 84115456. Throughput: 0: 1704.4, 1: 1720.9. Samples: 21035348. Policy #0 lag: (min: 18.0, avg: 24.9, max: 50.0) -[2023-10-15 03:54:13,534][87330] Avg episode reward: [(0, '22.710'), (1, '22.780')] -[2023-10-15 03:54:15,981][88300] Updated weights for policy 1, policy_version 41192 (0.0010) -[2023-10-15 03:54:16,347][88300] Updated weights for policy 1, policy_version 41202 (0.0007) -[2023-10-15 03:54:16,466][88298] Updated weights for policy 0, policy_version 40970 (0.0008) -[2023-10-15 03:54:16,711][88300] Updated weights for policy 1, policy_version 41212 (0.0007) -[2023-10-15 03:54:16,835][88298] Updated weights for policy 0, policy_version 40980 (0.0008) -[2023-10-15 03:54:17,211][88298] Updated weights for policy 0, policy_version 40990 (0.0009) -[2023-10-15 03:54:18,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 84180992. Throughput: 0: 1734.4, 1: 1741.8. Samples: 21047066. Policy #0 lag: (min: 18.0, avg: 24.9, max: 50.0) -[2023-10-15 03:54:18,535][87330] Avg episode reward: [(0, '22.660'), (1, '22.760')] -[2023-10-15 03:54:20,635][88300] Updated weights for policy 1, policy_version 41222 (0.0008) -[2023-10-15 03:54:21,002][88300] Updated weights for policy 1, policy_version 41232 (0.0007) -[2023-10-15 03:54:21,100][88298] Updated weights for policy 0, policy_version 41000 (0.0009) -[2023-10-15 03:54:21,372][88300] Updated weights for policy 1, policy_version 41242 (0.0010) -[2023-10-15 03:54:21,462][88298] Updated weights for policy 0, policy_version 41010 (0.0007) -[2023-10-15 03:54:21,827][88298] Updated weights for policy 0, policy_version 41020 (0.0009) -[2023-10-15 03:54:23,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 84246528. Throughput: 0: 1713.5, 1: 1731.9. Samples: 21066952. Policy #0 lag: (min: 18.0, avg: 24.9, max: 50.0) -[2023-10-15 03:54:23,535][87330] Avg episode reward: [(0, '22.810'), (1, '22.650')] -[2023-10-15 03:54:25,296][88300] Updated weights for policy 1, policy_version 41252 (0.0007) -[2023-10-15 03:54:25,663][88300] Updated weights for policy 1, policy_version 41262 (0.0009) -[2023-10-15 03:54:25,893][88298] Updated weights for policy 0, policy_version 41030 (0.0010) -[2023-10-15 03:54:26,039][88300] Updated weights for policy 1, policy_version 41272 (0.0009) -[2023-10-15 03:54:26,266][88298] Updated weights for policy 0, policy_version 41040 (0.0007) -[2023-10-15 03:54:26,637][88298] Updated weights for policy 0, policy_version 41050 (0.0007) -[2023-10-15 03:54:28,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 84312064. Throughput: 0: 1711.5, 1: 1743.1. Samples: 21088150. Policy #0 lag: (min: 18.0, avg: 24.9, max: 50.0) -[2023-10-15 03:54:28,534][87330] Avg episode reward: [(0, '22.780'), (1, '22.560')] -[2023-10-15 03:54:29,897][88300] Updated weights for policy 1, policy_version 41282 (0.0008) -[2023-10-15 03:54:30,271][88300] Updated weights for policy 1, policy_version 41292 (0.0011) -[2023-10-15 03:54:30,509][88298] Updated weights for policy 0, policy_version 41060 (0.0007) -[2023-10-15 03:54:30,641][88300] Updated weights for policy 1, policy_version 41302 (0.0008) -[2023-10-15 03:54:30,875][88298] Updated weights for policy 0, policy_version 41070 (0.0008) -[2023-10-15 03:54:31,009][88300] Updated weights for policy 1, policy_version 41312 (0.0007) -[2023-10-15 03:54:31,242][88298] Updated weights for policy 0, policy_version 41080 (0.0010) -[2023-10-15 03:54:33,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 84377600. Throughput: 0: 1735.1, 1: 1736.0. Samples: 21098696. Policy #0 lag: (min: 18.0, avg: 24.9, max: 50.0) -[2023-10-15 03:54:33,535][87330] Avg episode reward: [(0, '22.780'), (1, '22.400')] -[2023-10-15 03:54:34,834][88300] Updated weights for policy 1, policy_version 41322 (0.0008) -[2023-10-15 03:54:35,200][88300] Updated weights for policy 1, policy_version 41332 (0.0008) -[2023-10-15 03:54:35,216][88298] Updated weights for policy 0, policy_version 41090 (0.0010) -[2023-10-15 03:54:35,562][88300] Updated weights for policy 1, policy_version 41342 (0.0008) -[2023-10-15 03:54:35,580][88298] Updated weights for policy 0, policy_version 41100 (0.0008) -[2023-10-15 03:54:35,955][88298] Updated weights for policy 0, policy_version 41110 (0.0007) -[2023-10-15 03:54:36,314][88298] Updated weights for policy 0, policy_version 41120 (0.0009) -[2023-10-15 03:54:38,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 84443136. Throughput: 0: 1714.4, 1: 1739.6. Samples: 21119180. Policy #0 lag: (min: 18.0, avg: 24.9, max: 50.0) -[2023-10-15 03:54:38,535][87330] Avg episode reward: [(0, '22.760'), (1, '22.160')] -[2023-10-15 03:54:39,502][88300] Updated weights for policy 1, policy_version 41352 (0.0008) -[2023-10-15 03:54:39,869][88300] Updated weights for policy 1, policy_version 41362 (0.0008) -[2023-10-15 03:54:40,224][88300] Updated weights for policy 1, policy_version 41372 (0.0007) -[2023-10-15 03:54:40,330][88298] Updated weights for policy 0, policy_version 41130 (0.0007) -[2023-10-15 03:54:40,704][88298] Updated weights for policy 0, policy_version 41140 (0.0008) -[2023-10-15 03:54:41,070][88298] Updated weights for policy 0, policy_version 41150 (0.0011) -[2023-10-15 03:54:43,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 84508672. Throughput: 0: 1727.5, 1: 1769.4. Samples: 21140376. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-10-15 03:54:43,534][87330] Avg episode reward: [(0, '22.580'), (1, '22.150')] -[2023-10-15 03:54:44,159][88300] Updated weights for policy 1, policy_version 41382 (0.0008) -[2023-10-15 03:54:44,522][88300] Updated weights for policy 1, policy_version 41392 (0.0007) -[2023-10-15 03:54:44,884][88300] Updated weights for policy 1, policy_version 41402 (0.0009) -[2023-10-15 03:54:45,011][88298] Updated weights for policy 0, policy_version 41160 (0.0008) -[2023-10-15 03:54:45,383][88298] Updated weights for policy 0, policy_version 41170 (0.0007) -[2023-10-15 03:54:45,754][88298] Updated weights for policy 0, policy_version 41180 (0.0008) -[2023-10-15 03:54:48,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 84574208. Throughput: 0: 1706.7, 1: 1740.8. Samples: 21150006. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-10-15 03:54:48,534][87330] Avg episode reward: [(0, '22.530'), (1, '21.980')] -[2023-10-15 03:54:48,793][88300] Updated weights for policy 1, policy_version 41412 (0.0009) -[2023-10-15 03:54:49,161][88300] Updated weights for policy 1, policy_version 41422 (0.0007) -[2023-10-15 03:54:49,530][88300] Updated weights for policy 1, policy_version 41432 (0.0008) -[2023-10-15 03:54:49,665][88298] Updated weights for policy 0, policy_version 41190 (0.0008) -[2023-10-15 03:54:50,046][88298] Updated weights for policy 0, policy_version 41200 (0.0009) -[2023-10-15 03:54:50,415][88298] Updated weights for policy 0, policy_version 41210 (0.0007) -[2023-10-15 03:54:53,339][88300] Updated weights for policy 1, policy_version 41442 (0.0009) -[2023-10-15 03:54:53,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13884.8). Total num frames: 84639744. Throughput: 0: 1708.0, 1: 1759.1. Samples: 21171354. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-10-15 03:54:53,534][87330] Avg episode reward: [(0, '22.560'), (1, '21.970')] -[2023-10-15 03:54:53,701][88300] Updated weights for policy 1, policy_version 41452 (0.0010) -[2023-10-15 03:54:54,068][88300] Updated weights for policy 1, policy_version 41462 (0.0008) -[2023-10-15 03:54:54,313][88298] Updated weights for policy 0, policy_version 41220 (0.0007) -[2023-10-15 03:54:54,432][88300] Updated weights for policy 1, policy_version 41472 (0.0007) -[2023-10-15 03:54:54,690][88298] Updated weights for policy 0, policy_version 41230 (0.0009) -[2023-10-15 03:54:55,054][88298] Updated weights for policy 0, policy_version 41240 (0.0009) -[2023-10-15 03:54:58,495][88300] Updated weights for policy 1, policy_version 41482 (0.0007) -[2023-10-15 03:54:58,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 84705280. Throughput: 0: 1735.8, 1: 1764.9. Samples: 21192878. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-10-15 03:54:58,534][87330] Avg episode reward: [(0, '22.490'), (1, '22.270')] -[2023-10-15 03:54:58,542][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000041248_42237952.pth... -[2023-10-15 03:54:58,586][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000039648_40599552.pth -[2023-10-15 03:54:58,845][88298] Updated weights for policy 0, policy_version 41250 (0.0007) -[2023-10-15 03:54:58,869][88300] Updated weights for policy 1, policy_version 41492 (0.0007) -[2023-10-15 03:54:59,223][88298] Updated weights for policy 0, policy_version 41260 (0.0009) -[2023-10-15 03:54:59,237][88300] Updated weights for policy 1, policy_version 41502 (0.0007) -[2023-10-15 03:54:59,306][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000041504_42500096.pth... -[2023-10-15 03:54:59,334][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000039872_40828928.pth -[2023-10-15 03:54:59,600][88298] Updated weights for policy 0, policy_version 41270 (0.0007) -[2023-10-15 03:54:59,968][88298] Updated weights for policy 0, policy_version 41280 (0.0009) -[2023-10-15 03:55:03,100][88300] Updated weights for policy 1, policy_version 41512 (0.0007) -[2023-10-15 03:55:03,473][88300] Updated weights for policy 1, policy_version 41522 (0.0008) -[2023-10-15 03:55:03,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 84770816. Throughput: 0: 1704.0, 1: 1746.5. Samples: 21202334. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-10-15 03:55:03,534][87330] Avg episode reward: [(0, '22.530'), (1, '22.440')] -[2023-10-15 03:55:03,839][88300] Updated weights for policy 1, policy_version 41532 (0.0009) -[2023-10-15 03:55:03,959][88298] Updated weights for policy 0, policy_version 41290 (0.0008) -[2023-10-15 03:55:04,335][88298] Updated weights for policy 0, policy_version 41300 (0.0008) -[2023-10-15 03:55:04,696][88298] Updated weights for policy 0, policy_version 41310 (0.0008) -[2023-10-15 03:55:07,414][88300] Updated weights for policy 1, policy_version 41542 (0.0008) -[2023-10-15 03:55:07,783][88300] Updated weights for policy 1, policy_version 41552 (0.0011) -[2023-10-15 03:55:08,160][88300] Updated weights for policy 1, policy_version 41562 (0.0008) -[2023-10-15 03:55:08,534][87330] Fps is (10 sec: 16383.6, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 84869120. Throughput: 0: 1726.6, 1: 1765.6. Samples: 21224102. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-10-15 03:55:08,535][87330] Avg episode reward: [(0, '22.540'), (1, '22.460')] -[2023-10-15 03:55:08,667][88298] Updated weights for policy 0, policy_version 41320 (0.0010) -[2023-10-15 03:55:09,043][88298] Updated weights for policy 0, policy_version 41330 (0.0009) -[2023-10-15 03:55:09,410][88298] Updated weights for policy 0, policy_version 41340 (0.0007) -[2023-10-15 03:55:12,103][88300] Updated weights for policy 1, policy_version 41572 (0.0008) -[2023-10-15 03:55:12,466][88300] Updated weights for policy 1, policy_version 41582 (0.0007) -[2023-10-15 03:55:12,836][88300] Updated weights for policy 1, policy_version 41592 (0.0008) -[2023-10-15 03:55:13,228][88298] Updated weights for policy 0, policy_version 41350 (0.0009) -[2023-10-15 03:55:13,534][87330] Fps is (10 sec: 16383.6, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 84934656. Throughput: 0: 1739.4, 1: 1732.6. Samples: 21244390. Policy #0 lag: (min: 11.0, avg: 20.3, max: 43.0) -[2023-10-15 03:55:13,535][87330] Avg episode reward: [(0, '22.770'), (1, '22.690')] -[2023-10-15 03:55:13,597][88298] Updated weights for policy 0, policy_version 41360 (0.0009) -[2023-10-15 03:55:13,968][88298] Updated weights for policy 0, policy_version 41370 (0.0008) -[2023-10-15 03:55:16,708][88300] Updated weights for policy 1, policy_version 41602 (0.0008) -[2023-10-15 03:55:17,068][88300] Updated weights for policy 1, policy_version 41612 (0.0010) -[2023-10-15 03:55:17,444][88300] Updated weights for policy 1, policy_version 41622 (0.0009) -[2023-10-15 03:55:17,814][88300] Updated weights for policy 1, policy_version 41632 (0.0008) -[2023-10-15 03:55:17,860][88298] Updated weights for policy 0, policy_version 41380 (0.0008) -[2023-10-15 03:55:18,222][88298] Updated weights for policy 0, policy_version 41390 (0.0008) -[2023-10-15 03:55:18,534][87330] Fps is (10 sec: 13107.7, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 85000192. Throughput: 0: 1717.7, 1: 1762.8. Samples: 21255316. Policy #0 lag: (min: 11.0, avg: 20.3, max: 43.0) -[2023-10-15 03:55:18,534][87330] Avg episode reward: [(0, '22.790'), (1, '22.850')] -[2023-10-15 03:55:18,585][88298] Updated weights for policy 0, policy_version 41400 (0.0008) -[2023-10-15 03:55:21,949][88300] Updated weights for policy 1, policy_version 41642 (0.0009) -[2023-10-15 03:55:22,318][88300] Updated weights for policy 1, policy_version 41652 (0.0009) -[2023-10-15 03:55:22,576][88298] Updated weights for policy 0, policy_version 41410 (0.0007) -[2023-10-15 03:55:22,689][88300] Updated weights for policy 1, policy_version 41662 (0.0009) -[2023-10-15 03:55:22,955][88298] Updated weights for policy 0, policy_version 41420 (0.0009) -[2023-10-15 03:55:23,318][88298] Updated weights for policy 0, policy_version 41430 (0.0007) -[2023-10-15 03:55:23,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 85065728. Throughput: 0: 1736.4, 1: 1744.4. Samples: 21275818. Policy #0 lag: (min: 11.0, avg: 20.3, max: 43.0) -[2023-10-15 03:55:23,535][87330] Avg episode reward: [(0, '22.800'), (1, '22.840')] -[2023-10-15 03:55:23,683][88298] Updated weights for policy 0, policy_version 41440 (0.0007) -[2023-10-15 03:55:26,494][88300] Updated weights for policy 1, policy_version 41672 (0.0008) -[2023-10-15 03:55:26,851][88300] Updated weights for policy 1, policy_version 41682 (0.0008) -[2023-10-15 03:55:27,225][88300] Updated weights for policy 1, policy_version 41692 (0.0009) -[2023-10-15 03:55:27,565][88298] Updated weights for policy 0, policy_version 41450 (0.0008) -[2023-10-15 03:55:27,936][88298] Updated weights for policy 0, policy_version 41460 (0.0009) -[2023-10-15 03:55:28,315][88298] Updated weights for policy 0, policy_version 41470 (0.0008) -[2023-10-15 03:55:28,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 85164032. Throughput: 0: 1737.0, 1: 1731.3. Samples: 21296452. Policy #0 lag: (min: 11.0, avg: 20.3, max: 43.0) -[2023-10-15 03:55:28,534][87330] Avg episode reward: [(0, '22.820'), (1, '22.840')] -[2023-10-15 03:55:31,009][88300] Updated weights for policy 1, policy_version 41702 (0.0009) -[2023-10-15 03:55:31,382][88300] Updated weights for policy 1, policy_version 41712 (0.0011) -[2023-10-15 03:55:31,754][88300] Updated weights for policy 1, policy_version 41722 (0.0008) -[2023-10-15 03:55:32,159][88298] Updated weights for policy 0, policy_version 41480 (0.0008) -[2023-10-15 03:55:32,536][88298] Updated weights for policy 0, policy_version 41490 (0.0011) -[2023-10-15 03:55:32,900][88298] Updated weights for policy 0, policy_version 41500 (0.0009) -[2023-10-15 03:55:33,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 85229568. Throughput: 0: 1747.6, 1: 1752.4. Samples: 21307506. Policy #0 lag: (min: 11.0, avg: 20.3, max: 43.0) -[2023-10-15 03:55:33,534][87330] Avg episode reward: [(0, '22.870'), (1, '22.880')] -[2023-10-15 03:55:35,705][88300] Updated weights for policy 1, policy_version 41732 (0.0007) -[2023-10-15 03:55:36,060][88300] Updated weights for policy 1, policy_version 41742 (0.0008) -[2023-10-15 03:55:36,427][88300] Updated weights for policy 1, policy_version 41752 (0.0009) -[2023-10-15 03:55:36,851][88298] Updated weights for policy 0, policy_version 41510 (0.0007) -[2023-10-15 03:55:37,215][88298] Updated weights for policy 0, policy_version 41520 (0.0008) -[2023-10-15 03:55:37,583][88298] Updated weights for policy 0, policy_version 41530 (0.0011) -[2023-10-15 03:55:38,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 85295104. Throughput: 0: 1749.2, 1: 1727.4. Samples: 21327800. Policy #0 lag: (min: 31.0, avg: 41.1, max: 63.0) -[2023-10-15 03:55:38,535][87330] Avg episode reward: [(0, '22.790'), (1, '22.750')] -[2023-10-15 03:55:40,400][88300] Updated weights for policy 1, policy_version 41762 (0.0008) -[2023-10-15 03:55:40,765][88300] Updated weights for policy 1, policy_version 41772 (0.0008) -[2023-10-15 03:55:41,131][88300] Updated weights for policy 1, policy_version 41782 (0.0008) -[2023-10-15 03:55:41,311][88298] Updated weights for policy 0, policy_version 41540 (0.0010) -[2023-10-15 03:55:41,499][88300] Updated weights for policy 1, policy_version 41792 (0.0009) -[2023-10-15 03:55:41,684][88298] Updated weights for policy 0, policy_version 41550 (0.0008) -[2023-10-15 03:55:42,042][88298] Updated weights for policy 0, policy_version 41560 (0.0007) -[2023-10-15 03:55:43,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 85360640. Throughput: 0: 1728.4, 1: 1728.5. Samples: 21348438. Policy #0 lag: (min: 31.0, avg: 41.1, max: 63.0) -[2023-10-15 03:55:43,535][87330] Avg episode reward: [(0, '22.780'), (1, '22.740')] -[2023-10-15 03:55:45,373][88300] Updated weights for policy 1, policy_version 41802 (0.0007) -[2023-10-15 03:55:45,743][88300] Updated weights for policy 1, policy_version 41812 (0.0007) -[2023-10-15 03:55:45,943][88298] Updated weights for policy 0, policy_version 41570 (0.0008) -[2023-10-15 03:55:46,108][88300] Updated weights for policy 1, policy_version 41822 (0.0008) -[2023-10-15 03:55:46,308][88298] Updated weights for policy 0, policy_version 41580 (0.0007) -[2023-10-15 03:55:46,687][88298] Updated weights for policy 0, policy_version 41590 (0.0007) -[2023-10-15 03:55:47,060][88298] Updated weights for policy 0, policy_version 41600 (0.0007) -[2023-10-15 03:55:48,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 85426176. Throughput: 0: 1759.6, 1: 1727.9. Samples: 21359270. Policy #0 lag: (min: 31.0, avg: 41.1, max: 63.0) -[2023-10-15 03:55:48,534][87330] Avg episode reward: [(0, '22.460'), (1, '22.650')] -[2023-10-15 03:55:50,012][88300] Updated weights for policy 1, policy_version 41832 (0.0007) -[2023-10-15 03:55:50,384][88300] Updated weights for policy 1, policy_version 41842 (0.0007) -[2023-10-15 03:55:50,747][88300] Updated weights for policy 1, policy_version 41852 (0.0008) -[2023-10-15 03:55:51,003][88298] Updated weights for policy 0, policy_version 41610 (0.0007) -[2023-10-15 03:55:51,376][88298] Updated weights for policy 0, policy_version 41620 (0.0009) -[2023-10-15 03:55:51,750][88298] Updated weights for policy 0, policy_version 41630 (0.0007) -[2023-10-15 03:55:53,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 85491712. Throughput: 0: 1732.7, 1: 1722.4. Samples: 21379580. Policy #0 lag: (min: 31.0, avg: 41.1, max: 63.0) -[2023-10-15 03:55:53,534][87330] Avg episode reward: [(0, '22.440'), (1, '22.620')] -[2023-10-15 03:55:54,817][88300] Updated weights for policy 1, policy_version 41862 (0.0009) -[2023-10-15 03:55:55,182][88300] Updated weights for policy 1, policy_version 41872 (0.0010) -[2023-10-15 03:55:55,546][88300] Updated weights for policy 1, policy_version 41882 (0.0010) -[2023-10-15 03:55:55,760][88298] Updated weights for policy 0, policy_version 41640 (0.0008) -[2023-10-15 03:55:56,128][88298] Updated weights for policy 0, policy_version 41650 (0.0007) -[2023-10-15 03:55:56,485][88298] Updated weights for policy 0, policy_version 41660 (0.0007) -[2023-10-15 03:55:58,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 85557248. Throughput: 0: 1725.2, 1: 1749.9. Samples: 21400768. Policy #0 lag: (min: 31.0, avg: 41.1, max: 63.0) -[2023-10-15 03:55:58,535][87330] Avg episode reward: [(0, '22.470'), (1, '22.660')] -[2023-10-15 03:55:59,465][88300] Updated weights for policy 1, policy_version 41892 (0.0009) -[2023-10-15 03:55:59,821][88300] Updated weights for policy 1, policy_version 41902 (0.0009) -[2023-10-15 03:56:00,196][88300] Updated weights for policy 1, policy_version 41912 (0.0010) -[2023-10-15 03:56:00,411][88298] Updated weights for policy 0, policy_version 41670 (0.0008) -[2023-10-15 03:56:00,781][88298] Updated weights for policy 0, policy_version 41680 (0.0008) -[2023-10-15 03:56:01,145][88298] Updated weights for policy 0, policy_version 41690 (0.0008) -[2023-10-15 03:56:03,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 85622784. Throughput: 0: 1740.6, 1: 1717.8. Samples: 21410942. Policy #0 lag: (min: 31.0, avg: 41.1, max: 63.0) -[2023-10-15 03:56:03,535][87330] Avg episode reward: [(0, '22.480'), (1, '22.650')] -[2023-10-15 03:56:04,062][88300] Updated weights for policy 1, policy_version 41922 (0.0008) -[2023-10-15 03:56:04,434][88300] Updated weights for policy 1, policy_version 41932 (0.0011) -[2023-10-15 03:56:04,799][88300] Updated weights for policy 1, policy_version 41942 (0.0010) -[2023-10-15 03:56:05,126][88298] Updated weights for policy 0, policy_version 41700 (0.0009) -[2023-10-15 03:56:05,171][88300] Updated weights for policy 1, policy_version 41952 (0.0007) -[2023-10-15 03:56:05,497][88298] Updated weights for policy 0, policy_version 41710 (0.0008) -[2023-10-15 03:56:05,859][88298] Updated weights for policy 0, policy_version 41720 (0.0007) -[2023-10-15 03:56:08,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 85688320. Throughput: 0: 1728.2, 1: 1741.6. Samples: 21431958. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-10-15 03:56:08,535][87330] Avg episode reward: [(0, '22.540'), (1, '22.780')] -[2023-10-15 03:56:09,141][88300] Updated weights for policy 1, policy_version 41962 (0.0009) -[2023-10-15 03:56:09,525][88300] Updated weights for policy 1, policy_version 41972 (0.0009) -[2023-10-15 03:56:09,764][88298] Updated weights for policy 0, policy_version 41730 (0.0008) -[2023-10-15 03:56:09,884][88300] Updated weights for policy 1, policy_version 41982 (0.0008) -[2023-10-15 03:56:10,138][88298] Updated weights for policy 0, policy_version 41740 (0.0009) -[2023-10-15 03:56:10,504][88298] Updated weights for policy 0, policy_version 41750 (0.0009) -[2023-10-15 03:56:10,873][88298] Updated weights for policy 0, policy_version 41760 (0.0007) -[2023-10-15 03:56:13,534][87330] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 85753856. Throughput: 0: 1734.1, 1: 1756.7. Samples: 21453540. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-10-15 03:56:13,535][87330] Avg episode reward: [(0, '22.540'), (1, '22.770')] -[2023-10-15 03:56:13,544][88300] Updated weights for policy 1, policy_version 41992 (0.0009) -[2023-10-15 03:56:13,909][88300] Updated weights for policy 1, policy_version 42002 (0.0007) -[2023-10-15 03:56:14,285][88300] Updated weights for policy 1, policy_version 42012 (0.0007) -[2023-10-15 03:56:15,020][88298] Updated weights for policy 0, policy_version 41770 (0.0009) -[2023-10-15 03:56:15,377][88298] Updated weights for policy 0, policy_version 41780 (0.0009) -[2023-10-15 03:56:15,746][88298] Updated weights for policy 0, policy_version 41790 (0.0010) -[2023-10-15 03:56:18,061][88300] Updated weights for policy 1, policy_version 42022 (0.0009) -[2023-10-15 03:56:18,422][88300] Updated weights for policy 1, policy_version 42032 (0.0009) -[2023-10-15 03:56:18,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 85819392. Throughput: 0: 1720.4, 1: 1738.8. Samples: 21463168. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-10-15 03:56:18,534][87330] Avg episode reward: [(0, '22.600'), (1, '22.860')] -[2023-10-15 03:56:18,801][88300] Updated weights for policy 1, policy_version 42042 (0.0011) -[2023-10-15 03:56:19,566][88298] Updated weights for policy 0, policy_version 41800 (0.0009) -[2023-10-15 03:56:19,935][88298] Updated weights for policy 0, policy_version 41810 (0.0008) -[2023-10-15 03:56:20,304][88298] Updated weights for policy 0, policy_version 41820 (0.0009) -[2023-10-15 03:56:22,661][88300] Updated weights for policy 1, policy_version 42052 (0.0010) -[2023-10-15 03:56:23,016][88300] Updated weights for policy 1, policy_version 42062 (0.0007) -[2023-10-15 03:56:23,396][88300] Updated weights for policy 1, policy_version 42072 (0.0007) -[2023-10-15 03:56:23,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 85884928. Throughput: 0: 1719.3, 1: 1765.8. Samples: 21484628. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-10-15 03:56:23,535][87330] Avg episode reward: [(0, '22.730'), (1, '22.850')] -[2023-10-15 03:56:24,374][88298] Updated weights for policy 0, policy_version 41830 (0.0009) -[2023-10-15 03:56:24,739][88298] Updated weights for policy 0, policy_version 41840 (0.0010) -[2023-10-15 03:56:25,121][88298] Updated weights for policy 0, policy_version 41850 (0.0008) -[2023-10-15 03:56:27,294][88300] Updated weights for policy 1, policy_version 42082 (0.0008) -[2023-10-15 03:56:27,647][88300] Updated weights for policy 1, policy_version 42092 (0.0007) -[2023-10-15 03:56:28,023][88300] Updated weights for policy 1, policy_version 42102 (0.0007) -[2023-10-15 03:56:28,388][88300] Updated weights for policy 1, policy_version 42112 (0.0009) -[2023-10-15 03:56:28,534][87330] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 85983232. Throughput: 0: 1736.4, 1: 1743.5. Samples: 21505032. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-10-15 03:56:28,534][87330] Avg episode reward: [(0, '22.700'), (1, '22.900')] -[2023-10-15 03:56:28,915][88298] Updated weights for policy 0, policy_version 41860 (0.0007) -[2023-10-15 03:56:29,286][88298] Updated weights for policy 0, policy_version 41870 (0.0007) -[2023-10-15 03:56:29,656][88298] Updated weights for policy 0, policy_version 41880 (0.0007) -[2023-10-15 03:56:32,184][88300] Updated weights for policy 1, policy_version 42122 (0.0007) -[2023-10-15 03:56:32,562][88300] Updated weights for policy 1, policy_version 42132 (0.0007) -[2023-10-15 03:56:32,923][88300] Updated weights for policy 1, policy_version 42142 (0.0007) -[2023-10-15 03:56:33,534][87330] Fps is (10 sec: 16384.2, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 86048768. Throughput: 0: 1707.9, 1: 1767.4. Samples: 21515656. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-10-15 03:56:33,534][87330] Avg episode reward: [(0, '22.280'), (1, '22.700')] -[2023-10-15 03:56:33,559][88298] Updated weights for policy 0, policy_version 41890 (0.0007) -[2023-10-15 03:56:33,927][88298] Updated weights for policy 0, policy_version 41900 (0.0008) -[2023-10-15 03:56:34,291][88298] Updated weights for policy 0, policy_version 41910 (0.0008) -[2023-10-15 03:56:34,664][88298] Updated weights for policy 0, policy_version 41920 (0.0007) -[2023-10-15 03:56:36,759][88300] Updated weights for policy 1, policy_version 42152 (0.0010) -[2023-10-15 03:56:37,128][88300] Updated weights for policy 1, policy_version 42162 (0.0010) -[2023-10-15 03:56:37,491][88300] Updated weights for policy 1, policy_version 42172 (0.0008) -[2023-10-15 03:56:38,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 86114304. Throughput: 0: 1736.1, 1: 1752.1. Samples: 21536548. Policy #0 lag: (min: 6.0, avg: 11.3, max: 38.0) -[2023-10-15 03:56:38,534][87330] Avg episode reward: [(0, '22.260'), (1, '22.540')] -[2023-10-15 03:56:38,720][88298] Updated weights for policy 0, policy_version 41930 (0.0009) -[2023-10-15 03:56:39,090][88298] Updated weights for policy 0, policy_version 41940 (0.0009) -[2023-10-15 03:56:39,466][88298] Updated weights for policy 0, policy_version 41950 (0.0009) -[2023-10-15 03:56:41,257][88300] Updated weights for policy 1, policy_version 42182 (0.0009) -[2023-10-15 03:56:41,618][88300] Updated weights for policy 1, policy_version 42192 (0.0008) -[2023-10-15 03:56:41,984][88300] Updated weights for policy 1, policy_version 42202 (0.0007) -[2023-10-15 03:56:43,300][88298] Updated weights for policy 0, policy_version 41960 (0.0007) -[2023-10-15 03:56:43,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 86179840. Throughput: 0: 1738.8, 1: 1745.3. Samples: 21557550. Policy #0 lag: (min: 6.0, avg: 11.3, max: 38.0) -[2023-10-15 03:56:43,534][87330] Avg episode reward: [(0, '22.260'), (1, '22.500')] -[2023-10-15 03:56:43,675][88298] Updated weights for policy 0, policy_version 41970 (0.0007) -[2023-10-15 03:56:44,050][88298] Updated weights for policy 0, policy_version 41980 (0.0009) -[2023-10-15 03:56:45,954][88300] Updated weights for policy 1, policy_version 42212 (0.0008) -[2023-10-15 03:56:46,319][88300] Updated weights for policy 1, policy_version 42222 (0.0011) -[2023-10-15 03:56:46,688][88300] Updated weights for policy 1, policy_version 42232 (0.0008) -[2023-10-15 03:56:47,887][88298] Updated weights for policy 0, policy_version 41990 (0.0010) -[2023-10-15 03:56:48,256][88298] Updated weights for policy 0, policy_version 42000 (0.0011) -[2023-10-15 03:56:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 86245376. Throughput: 0: 1725.3, 1: 1765.4. Samples: 21568022. Policy #0 lag: (min: 6.0, avg: 11.3, max: 38.0) -[2023-10-15 03:56:48,534][87330] Avg episode reward: [(0, '22.390'), (1, '22.490')] -[2023-10-15 03:56:48,624][88298] Updated weights for policy 0, policy_version 42010 (0.0011) -[2023-10-15 03:56:50,734][88300] Updated weights for policy 1, policy_version 42242 (0.0007) -[2023-10-15 03:56:51,101][88300] Updated weights for policy 1, policy_version 42252 (0.0009) -[2023-10-15 03:56:51,470][88300] Updated weights for policy 1, policy_version 42262 (0.0008) -[2023-10-15 03:56:51,834][88300] Updated weights for policy 1, policy_version 42272 (0.0007) -[2023-10-15 03:56:52,531][88298] Updated weights for policy 0, policy_version 42020 (0.0010) -[2023-10-15 03:56:52,908][88298] Updated weights for policy 0, policy_version 42030 (0.0007) -[2023-10-15 03:56:53,269][88298] Updated weights for policy 0, policy_version 42040 (0.0007) -[2023-10-15 03:56:53,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 86310912. Throughput: 0: 1736.7, 1: 1739.8. Samples: 21588400. Policy #0 lag: (min: 6.0, avg: 11.3, max: 38.0) -[2023-10-15 03:56:53,535][87330] Avg episode reward: [(0, '22.400'), (1, '22.520')] -[2023-10-15 03:56:55,812][88300] Updated weights for policy 1, policy_version 42282 (0.0008) -[2023-10-15 03:56:56,185][88300] Updated weights for policy 1, policy_version 42292 (0.0010) -[2023-10-15 03:56:56,547][88300] Updated weights for policy 1, policy_version 42302 (0.0010) -[2023-10-15 03:56:57,157][88298] Updated weights for policy 0, policy_version 42050 (0.0007) -[2023-10-15 03:56:57,529][88298] Updated weights for policy 0, policy_version 42060 (0.0010) -[2023-10-15 03:56:57,896][88298] Updated weights for policy 0, policy_version 42070 (0.0009) -[2023-10-15 03:56:58,275][88298] Updated weights for policy 0, policy_version 42080 (0.0007) -[2023-10-15 03:56:58,534][87330] Fps is (10 sec: 16383.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 86409216. Throughput: 0: 1723.6, 1: 1733.1. Samples: 21609090. Policy #0 lag: (min: 6.0, avg: 11.3, max: 38.0) -[2023-10-15 03:56:58,535][87330] Avg episode reward: [(0, '22.450'), (1, '22.480')] -[2023-10-15 03:56:58,544][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000042304_43319296.pth... -[2023-10-15 03:56:58,544][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000042080_43089920.pth... -[2023-10-15 03:56:58,580][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000040448_41418752.pth -[2023-10-15 03:56:58,588][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000040672_41648128.pth -[2023-10-15 03:57:00,418][88300] Updated weights for policy 1, policy_version 42312 (0.0010) -[2023-10-15 03:57:00,790][88300] Updated weights for policy 1, policy_version 42322 (0.0008) -[2023-10-15 03:57:01,166][88300] Updated weights for policy 1, policy_version 42332 (0.0007) -[2023-10-15 03:57:02,219][88298] Updated weights for policy 0, policy_version 42090 (0.0007) -[2023-10-15 03:57:02,587][88298] Updated weights for policy 0, policy_version 42100 (0.0010) -[2023-10-15 03:57:02,963][88298] Updated weights for policy 0, policy_version 42110 (0.0007) -[2023-10-15 03:57:03,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 86474752. Throughput: 0: 1738.9, 1: 1735.5. Samples: 21619518. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:57:03,534][87330] Avg episode reward: [(0, '22.610'), (1, '22.670')] -[2023-10-15 03:57:04,982][88300] Updated weights for policy 1, policy_version 42342 (0.0008) -[2023-10-15 03:57:05,351][88300] Updated weights for policy 1, policy_version 42352 (0.0007) -[2023-10-15 03:57:05,710][88300] Updated weights for policy 1, policy_version 42362 (0.0008) -[2023-10-15 03:57:07,072][88298] Updated weights for policy 0, policy_version 42120 (0.0007) -[2023-10-15 03:57:07,443][88298] Updated weights for policy 0, policy_version 42130 (0.0008) -[2023-10-15 03:57:07,801][88298] Updated weights for policy 0, policy_version 42140 (0.0009) -[2023-10-15 03:57:08,534][87330] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 86540288. Throughput: 0: 1743.7, 1: 1731.4. Samples: 21641008. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:57:08,534][87330] Avg episode reward: [(0, '22.680'), (1, '22.670')] -[2023-10-15 03:57:09,519][88300] Updated weights for policy 1, policy_version 42372 (0.0007) -[2023-10-15 03:57:09,885][88300] Updated weights for policy 1, policy_version 42382 (0.0007) -[2023-10-15 03:57:10,257][88300] Updated weights for policy 1, policy_version 42392 (0.0007) -[2023-10-15 03:57:11,705][88298] Updated weights for policy 0, policy_version 42150 (0.0007) -[2023-10-15 03:57:12,089][88298] Updated weights for policy 0, policy_version 42160 (0.0007) -[2023-10-15 03:57:12,454][88298] Updated weights for policy 0, policy_version 42170 (0.0008) -[2023-10-15 03:57:13,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 86605824. Throughput: 0: 1714.7, 1: 1760.2. Samples: 21661404. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:57:13,535][87330] Avg episode reward: [(0, '22.700'), (1, '22.790')] -[2023-10-15 03:57:14,182][88300] Updated weights for policy 1, policy_version 42402 (0.0009) -[2023-10-15 03:57:14,543][88300] Updated weights for policy 1, policy_version 42412 (0.0007) -[2023-10-15 03:57:14,912][88300] Updated weights for policy 1, policy_version 42422 (0.0008) -[2023-10-15 03:57:15,276][88300] Updated weights for policy 1, policy_version 42432 (0.0008) -[2023-10-15 03:57:16,308][88298] Updated weights for policy 0, policy_version 42180 (0.0009) -[2023-10-15 03:57:16,674][88298] Updated weights for policy 0, policy_version 42190 (0.0008) -[2023-10-15 03:57:17,047][88298] Updated weights for policy 0, policy_version 42200 (0.0008) -[2023-10-15 03:57:18,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 86671360. Throughput: 0: 1746.0, 1: 1734.3. Samples: 21672272. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:57:18,534][87330] Avg episode reward: [(0, '22.690'), (1, '22.820')] -[2023-10-15 03:57:19,294][88300] Updated weights for policy 1, policy_version 42442 (0.0009) -[2023-10-15 03:57:19,664][88300] Updated weights for policy 1, policy_version 42452 (0.0008) -[2023-10-15 03:57:20,036][88300] Updated weights for policy 1, policy_version 42462 (0.0008) -[2023-10-15 03:57:20,848][88298] Updated weights for policy 0, policy_version 42210 (0.0009) -[2023-10-15 03:57:21,220][88298] Updated weights for policy 0, policy_version 42220 (0.0008) -[2023-10-15 03:57:21,590][88298] Updated weights for policy 0, policy_version 42230 (0.0008) -[2023-10-15 03:57:21,965][88298] Updated weights for policy 0, policy_version 42240 (0.0011) -[2023-10-15 03:57:23,534][87330] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 86736896. Throughput: 0: 1724.4, 1: 1751.5. Samples: 21692966. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:57:23,534][87330] Avg episode reward: [(0, '22.650'), (1, '22.780')] -[2023-10-15 03:57:23,718][88300] Updated weights for policy 1, policy_version 42472 (0.0009) -[2023-10-15 03:57:24,086][88300] Updated weights for policy 1, policy_version 42482 (0.0009) -[2023-10-15 03:57:24,462][88300] Updated weights for policy 1, policy_version 42492 (0.0009) -[2023-10-15 03:57:25,999][88298] Updated weights for policy 0, policy_version 42250 (0.0009) -[2023-10-15 03:57:26,369][88298] Updated weights for policy 0, policy_version 42260 (0.0008) -[2023-10-15 03:57:26,737][88298] Updated weights for policy 0, policy_version 42270 (0.0008) -[2023-10-15 03:57:28,413][88300] Updated weights for policy 1, policy_version 42502 (0.0011) -[2023-10-15 03:57:28,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 86802432. Throughput: 0: 1714.7, 1: 1763.7. Samples: 21714078. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:57:28,535][87330] Avg episode reward: [(0, '22.640'), (1, '22.800')] -[2023-10-15 03:57:28,778][88300] Updated weights for policy 1, policy_version 42512 (0.0010) -[2023-10-15 03:57:29,152][88300] Updated weights for policy 1, policy_version 42522 (0.0009) -[2023-10-15 03:57:30,737][88298] Updated weights for policy 0, policy_version 42280 (0.0009) -[2023-10-15 03:57:31,104][88298] Updated weights for policy 0, policy_version 42290 (0.0010) -[2023-10-15 03:57:31,486][88298] Updated weights for policy 0, policy_version 42300 (0.0009) -[2023-10-15 03:57:33,137][88300] Updated weights for policy 1, policy_version 42532 (0.0007) -[2023-10-15 03:57:33,506][88300] Updated weights for policy 1, policy_version 42542 (0.0008) -[2023-10-15 03:57:33,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 86867968. Throughput: 0: 1733.3, 1: 1740.9. Samples: 21724362. Policy #0 lag: (min: 9.0, avg: 19.3, max: 41.0) -[2023-10-15 03:57:33,534][87330] Avg episode reward: [(0, '22.610'), (1, '22.770')] -[2023-10-15 03:57:33,875][88300] Updated weights for policy 1, policy_version 42552 (0.0010) -[2023-10-15 03:57:35,215][88298] Updated weights for policy 0, policy_version 42310 (0.0010) -[2023-10-15 03:57:35,587][88298] Updated weights for policy 0, policy_version 42320 (0.0008) -[2023-10-15 03:57:35,951][88298] Updated weights for policy 0, policy_version 42330 (0.0008) -[2023-10-15 03:57:37,758][88300] Updated weights for policy 1, policy_version 42562 (0.0008) -[2023-10-15 03:57:38,125][88300] Updated weights for policy 1, policy_version 42572 (0.0007) -[2023-10-15 03:57:38,496][88300] Updated weights for policy 1, policy_version 42582 (0.0010) -[2023-10-15 03:57:38,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 86933504. Throughput: 0: 1720.7, 1: 1762.4. Samples: 21745138. Policy #0 lag: (min: 9.0, avg: 19.3, max: 41.0) -[2023-10-15 03:57:38,534][87330] Avg episode reward: [(0, '22.630'), (1, '22.740')] -[2023-10-15 03:57:38,852][88300] Updated weights for policy 1, policy_version 42592 (0.0010) -[2023-10-15 03:57:39,753][88298] Updated weights for policy 0, policy_version 42340 (0.0010) -[2023-10-15 03:57:40,130][88298] Updated weights for policy 0, policy_version 42350 (0.0008) -[2023-10-15 03:57:40,496][88298] Updated weights for policy 0, policy_version 42360 (0.0008) -[2023-10-15 03:57:42,862][88300] Updated weights for policy 1, policy_version 42602 (0.0007) -[2023-10-15 03:57:43,237][88300] Updated weights for policy 1, policy_version 42612 (0.0008) -[2023-10-15 03:57:43,534][87330] Fps is (10 sec: 13106.6, 60 sec: 13653.2, 300 sec: 13773.7). Total num frames: 86999040. Throughput: 0: 1740.5, 1: 1742.9. Samples: 21765846. Policy #0 lag: (min: 9.0, avg: 19.3, max: 41.0) -[2023-10-15 03:57:43,535][87330] Avg episode reward: [(0, '22.720'), (1, '22.790')] -[2023-10-15 03:57:43,604][88300] Updated weights for policy 1, policy_version 42622 (0.0009) -[2023-10-15 03:57:44,386][88298] Updated weights for policy 0, policy_version 42370 (0.0008) -[2023-10-15 03:57:44,747][88298] Updated weights for policy 0, policy_version 42380 (0.0009) -[2023-10-15 03:57:45,107][88298] Updated weights for policy 0, policy_version 42390 (0.0008) -[2023-10-15 03:57:45,478][88298] Updated weights for policy 0, policy_version 42400 (0.0007) -[2023-10-15 03:57:47,443][88300] Updated weights for policy 1, policy_version 42632 (0.0008) -[2023-10-15 03:57:47,820][88300] Updated weights for policy 1, policy_version 42642 (0.0008) -[2023-10-15 03:57:48,186][88300] Updated weights for policy 1, policy_version 42652 (0.0009) -[2023-10-15 03:57:48,534][87330] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 87097344. Throughput: 0: 1725.9, 1: 1754.6. Samples: 21776140. Policy #0 lag: (min: 9.0, avg: 19.3, max: 41.0) -[2023-10-15 03:57:48,535][87330] Avg episode reward: [(0, '22.760'), (1, '22.740')] -[2023-10-15 03:57:49,198][88298] Updated weights for policy 0, policy_version 42410 (0.0007) -[2023-10-15 03:57:49,561][88298] Updated weights for policy 0, policy_version 42420 (0.0008) -[2023-10-15 03:57:49,938][88298] Updated weights for policy 0, policy_version 42430 (0.0008) -[2023-10-15 03:57:52,118][88300] Updated weights for policy 1, policy_version 42662 (0.0008) -[2023-10-15 03:57:52,481][88300] Updated weights for policy 1, policy_version 42672 (0.0008) -[2023-10-15 03:57:52,841][88300] Updated weights for policy 1, policy_version 42682 (0.0008) -[2023-10-15 03:57:53,534][87330] Fps is (10 sec: 16384.6, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 87162880. Throughput: 0: 1733.6, 1: 1746.9. Samples: 21797632. Policy #0 lag: (min: 9.0, avg: 19.3, max: 41.0) -[2023-10-15 03:57:53,534][87330] Avg episode reward: [(0, '22.780'), (1, '22.750')] -[2023-10-15 03:57:53,729][88298] Updated weights for policy 0, policy_version 42440 (0.0008) -[2023-10-15 03:57:54,091][88298] Updated weights for policy 0, policy_version 42450 (0.0007) -[2023-10-15 03:57:54,466][88298] Updated weights for policy 0, policy_version 42460 (0.0009) -[2023-10-15 03:57:56,600][88300] Updated weights for policy 1, policy_version 42692 (0.0009) -[2023-10-15 03:57:56,970][88300] Updated weights for policy 1, policy_version 42702 (0.0008) -[2023-10-15 03:57:57,332][88300] Updated weights for policy 1, policy_version 42712 (0.0008) -[2023-10-15 03:57:58,475][88298] Updated weights for policy 0, policy_version 42470 (0.0009) -[2023-10-15 03:57:58,534][87330] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 87228416. Throughput: 0: 1771.9, 1: 1721.6. Samples: 21818612. Policy #0 lag: (min: 9.0, avg: 19.3, max: 41.0) -[2023-10-15 03:57:58,535][87330] Avg episode reward: [(0, '22.790'), (1, '22.750')] -[2023-10-15 03:57:58,864][88298] Updated weights for policy 0, policy_version 42480 (0.0007) -[2023-10-15 03:57:59,238][88298] Updated weights for policy 0, policy_version 42490 (0.0007) -[2023-10-15 03:58:01,091][88300] Updated weights for policy 1, policy_version 42722 (0.0008) -[2023-10-15 03:58:01,461][88300] Updated weights for policy 1, policy_version 42732 (0.0008) -[2023-10-15 03:58:01,823][88300] Updated weights for policy 1, policy_version 42742 (0.0007) -[2023-10-15 03:58:02,181][88300] Updated weights for policy 1, policy_version 42752 (0.0008) -[2023-10-15 03:58:03,048][88298] Updated weights for policy 0, policy_version 42500 (0.0007) -[2023-10-15 03:58:03,420][88298] Updated weights for policy 0, policy_version 42510 (0.0007) -[2023-10-15 03:58:03,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 87293952. Throughput: 0: 1737.4, 1: 1752.0. Samples: 21829296. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-15 03:58:03,534][87330] Avg episode reward: [(0, '22.800'), (1, '22.760')] -[2023-10-15 03:58:03,789][88298] Updated weights for policy 0, policy_version 42520 (0.0008) -[2023-10-15 03:58:06,049][88300] Updated weights for policy 1, policy_version 42762 (0.0009) -[2023-10-15 03:58:06,407][88300] Updated weights for policy 1, policy_version 42772 (0.0009) -[2023-10-15 03:58:06,771][88300] Updated weights for policy 1, policy_version 42782 (0.0008) -[2023-10-15 03:58:07,613][88298] Updated weights for policy 0, policy_version 42530 (0.0008) -[2023-10-15 03:58:07,980][88298] Updated weights for policy 0, policy_version 42540 (0.0008) -[2023-10-15 03:58:08,365][88298] Updated weights for policy 0, policy_version 42550 (0.0009) -[2023-10-15 03:58:08,534][87330] Fps is (10 sec: 13107.8, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 87359488. Throughput: 0: 1762.3, 1: 1725.2. Samples: 21849906. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-15 03:58:08,534][87330] Avg episode reward: [(0, '22.810'), (1, '22.670')] -[2023-10-15 03:58:08,733][88298] Updated weights for policy 0, policy_version 42560 (0.0009) -[2023-10-15 03:58:10,660][88300] Updated weights for policy 1, policy_version 42792 (0.0008) -[2023-10-15 03:58:11,036][88300] Updated weights for policy 1, policy_version 42802 (0.0009) -[2023-10-15 03:58:11,395][88300] Updated weights for policy 1, policy_version 42812 (0.0011) -[2023-10-15 03:58:12,549][88298] Updated weights for policy 0, policy_version 42570 (0.0009) -[2023-10-15 03:58:12,916][88298] Updated weights for policy 0, policy_version 42580 (0.0010) -[2023-10-15 03:58:13,283][88298] Updated weights for policy 0, policy_version 42590 (0.0010) -[2023-10-15 03:58:13,534][87330] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 87457792. Throughput: 0: 1759.9, 1: 1734.2. Samples: 21871310. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-15 03:58:13,535][87330] Avg episode reward: [(0, '22.830'), (1, '22.700')] -[2023-10-15 03:58:15,253][88300] Updated weights for policy 1, policy_version 42822 (0.0010) -[2023-10-15 03:58:15,621][88300] Updated weights for policy 1, policy_version 42832 (0.0008) -[2023-10-15 03:58:15,998][88300] Updated weights for policy 1, policy_version 42842 (0.0008) -[2023-10-15 03:58:17,157][88298] Updated weights for policy 0, policy_version 42600 (0.0008) -[2023-10-15 03:58:17,527][88298] Updated weights for policy 0, policy_version 42610 (0.0009) -[2023-10-15 03:58:17,903][88298] Updated weights for policy 0, policy_version 42620 (0.0008) -[2023-10-15 03:58:18,534][87330] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 87523328. Throughput: 0: 1751.7, 1: 1737.0. Samples: 21881352. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-15 03:58:18,535][87330] Avg episode reward: [(0, '22.810'), (1, '22.740')] -[2023-10-15 03:58:19,880][88300] Updated weights for policy 1, policy_version 42852 (0.0010) -[2023-10-15 03:58:20,259][88300] Updated weights for policy 1, policy_version 42862 (0.0007) -[2023-10-15 03:58:20,623][88300] Updated weights for policy 1, policy_version 42872 (0.0010) -[2023-10-15 03:58:21,861][88298] Updated weights for policy 0, policy_version 42630 (0.0008) -[2023-10-15 03:58:22,230][88298] Updated weights for policy 0, policy_version 42640 (0.0008) -[2023-10-15 03:58:22,607][88298] Updated weights for policy 0, policy_version 42650 (0.0009) -[2023-10-15 03:58:23,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 87588864. Throughput: 0: 1766.7, 1: 1733.7. Samples: 21902656. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-15 03:58:23,534][87330] Avg episode reward: [(0, '22.790'), (1, '22.450')] -[2023-10-15 03:58:24,475][88300] Updated weights for policy 1, policy_version 42882 (0.0010) -[2023-10-15 03:58:24,836][88300] Updated weights for policy 1, policy_version 42892 (0.0010) -[2023-10-15 03:58:25,208][88300] Updated weights for policy 1, policy_version 42902 (0.0010) -[2023-10-15 03:58:25,573][88300] Updated weights for policy 1, policy_version 42912 (0.0011) -[2023-10-15 03:58:26,434][88298] Updated weights for policy 0, policy_version 42660 (0.0009) -[2023-10-15 03:58:26,811][88298] Updated weights for policy 0, policy_version 42670 (0.0009) -[2023-10-15 03:58:27,183][88298] Updated weights for policy 0, policy_version 42680 (0.0008) -[2023-10-15 03:58:28,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 87654400. Throughput: 0: 1736.1, 1: 1757.8. Samples: 21923070. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:58:28,535][87330] Avg episode reward: [(0, '22.780'), (1, '22.500')] -[2023-10-15 03:58:29,581][88300] Updated weights for policy 1, policy_version 42922 (0.0010) -[2023-10-15 03:58:29,956][88300] Updated weights for policy 1, policy_version 42932 (0.0010) -[2023-10-15 03:58:30,321][88300] Updated weights for policy 1, policy_version 42942 (0.0008) -[2023-10-15 03:58:31,030][88298] Updated weights for policy 0, policy_version 42690 (0.0008) -[2023-10-15 03:58:31,398][88298] Updated weights for policy 0, policy_version 42700 (0.0009) -[2023-10-15 03:58:31,766][88298] Updated weights for policy 0, policy_version 42710 (0.0007) -[2023-10-15 03:58:32,135][88298] Updated weights for policy 0, policy_version 42720 (0.0009) -[2023-10-15 03:58:33,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 87719936. Throughput: 0: 1769.0, 1: 1735.3. Samples: 21933832. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:58:33,534][87330] Avg episode reward: [(0, '22.670'), (1, '22.390')] -[2023-10-15 03:58:34,151][88300] Updated weights for policy 1, policy_version 42952 (0.0009) -[2023-10-15 03:58:34,520][88300] Updated weights for policy 1, policy_version 42962 (0.0008) -[2023-10-15 03:58:34,883][88300] Updated weights for policy 1, policy_version 42972 (0.0010) -[2023-10-15 03:58:36,108][88298] Updated weights for policy 0, policy_version 42730 (0.0010) -[2023-10-15 03:58:36,477][88298] Updated weights for policy 0, policy_version 42740 (0.0008) -[2023-10-15 03:58:36,846][88298] Updated weights for policy 0, policy_version 42750 (0.0008) -[2023-10-15 03:58:38,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 87785472. Throughput: 0: 1732.4, 1: 1743.2. Samples: 21954034. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:58:38,534][87330] Avg episode reward: [(0, '22.730'), (1, '22.410')] -[2023-10-15 03:58:38,889][88300] Updated weights for policy 1, policy_version 42982 (0.0010) -[2023-10-15 03:58:39,254][88300] Updated weights for policy 1, policy_version 42992 (0.0008) -[2023-10-15 03:58:39,636][88300] Updated weights for policy 1, policy_version 43002 (0.0008) -[2023-10-15 03:58:40,851][88298] Updated weights for policy 0, policy_version 42760 (0.0007) -[2023-10-15 03:58:41,215][88298] Updated weights for policy 0, policy_version 42770 (0.0008) -[2023-10-15 03:58:41,590][88298] Updated weights for policy 0, policy_version 42780 (0.0007) -[2023-10-15 03:58:43,519][88300] Updated weights for policy 1, policy_version 43012 (0.0008) -[2023-10-15 03:58:43,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.6, 300 sec: 13995.8). Total num frames: 87851008. Throughput: 0: 1719.9, 1: 1763.2. Samples: 21975352. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:58:43,534][87330] Avg episode reward: [(0, '22.740'), (1, '22.430')] -[2023-10-15 03:58:43,886][88300] Updated weights for policy 1, policy_version 43022 (0.0008) -[2023-10-15 03:58:44,252][88300] Updated weights for policy 1, policy_version 43032 (0.0007) -[2023-10-15 03:58:45,655][88298] Updated weights for policy 0, policy_version 42790 (0.0009) -[2023-10-15 03:58:46,040][88298] Updated weights for policy 0, policy_version 42800 (0.0010) -[2023-10-15 03:58:46,412][88298] Updated weights for policy 0, policy_version 42810 (0.0008) -[2023-10-15 03:58:48,060][88300] Updated weights for policy 1, policy_version 43042 (0.0009) -[2023-10-15 03:58:48,434][88300] Updated weights for policy 1, policy_version 43052 (0.0008) -[2023-10-15 03:58:48,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 87916544. Throughput: 0: 1743.1, 1: 1734.9. Samples: 21985808. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:58:48,535][87330] Avg episode reward: [(0, '22.720'), (1, '22.400')] -[2023-10-15 03:58:48,797][88300] Updated weights for policy 1, policy_version 43062 (0.0008) -[2023-10-15 03:58:49,165][88300] Updated weights for policy 1, policy_version 43072 (0.0008) -[2023-10-15 03:58:50,346][88298] Updated weights for policy 0, policy_version 42820 (0.0010) -[2023-10-15 03:58:50,712][88298] Updated weights for policy 0, policy_version 42830 (0.0008) -[2023-10-15 03:58:51,087][88298] Updated weights for policy 0, policy_version 42840 (0.0010) -[2023-10-15 03:58:53,038][88300] Updated weights for policy 1, policy_version 43082 (0.0007) -[2023-10-15 03:58:53,410][88300] Updated weights for policy 1, policy_version 43092 (0.0007) -[2023-10-15 03:58:53,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 87982080. Throughput: 0: 1715.9, 1: 1762.4. Samples: 22006430. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:58:53,534][87330] Avg episode reward: [(0, '22.740'), (1, '22.280')] -[2023-10-15 03:58:53,777][88300] Updated weights for policy 1, policy_version 43102 (0.0007) -[2023-10-15 03:58:54,946][88298] Updated weights for policy 0, policy_version 42850 (0.0010) -[2023-10-15 03:58:55,308][88298] Updated weights for policy 0, policy_version 42860 (0.0009) -[2023-10-15 03:58:55,688][88298] Updated weights for policy 0, policy_version 42870 (0.0009) -[2023-10-15 03:58:56,051][88298] Updated weights for policy 0, policy_version 42880 (0.0009) -[2023-10-15 03:58:57,586][88300] Updated weights for policy 1, policy_version 43112 (0.0008) -[2023-10-15 03:58:57,968][88300] Updated weights for policy 1, policy_version 43122 (0.0009) -[2023-10-15 03:58:58,326][88300] Updated weights for policy 1, policy_version 43132 (0.0008) -[2023-10-15 03:58:58,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 88080384. Throughput: 0: 1730.2, 1: 1733.2. Samples: 22027160. Policy #0 lag: (min: 31.0, avg: 31.1, max: 40.0) -[2023-10-15 03:58:58,534][87330] Avg episode reward: [(0, '22.720'), (1, '22.550')] -[2023-10-15 03:58:58,543][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000043136_44171264.pth... -[2023-10-15 03:58:58,543][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000042880_43909120.pth... -[2023-10-15 03:58:58,575][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000041504_42500096.pth -[2023-10-15 03:58:58,582][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000041248_42237952.pth -[2023-10-15 03:58:59,928][88298] Updated weights for policy 0, policy_version 42890 (0.0010) -[2023-10-15 03:59:00,303][88298] Updated weights for policy 0, policy_version 42900 (0.0009) -[2023-10-15 03:59:00,687][88298] Updated weights for policy 0, policy_version 42910 (0.0008) -[2023-10-15 03:59:02,308][88300] Updated weights for policy 1, policy_version 43142 (0.0007) -[2023-10-15 03:59:02,681][88300] Updated weights for policy 1, policy_version 43152 (0.0008) -[2023-10-15 03:59:03,050][88300] Updated weights for policy 1, policy_version 43162 (0.0008) -[2023-10-15 03:59:03,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 88145920. Throughput: 0: 1720.0, 1: 1754.2. Samples: 22037688. Policy #0 lag: (min: 31.0, avg: 31.1, max: 40.0) -[2023-10-15 03:59:03,534][87330] Avg episode reward: [(0, '22.720'), (1, '22.590')] -[2023-10-15 03:59:04,633][88298] Updated weights for policy 0, policy_version 42920 (0.0010) -[2023-10-15 03:59:05,007][88298] Updated weights for policy 0, policy_version 42930 (0.0008) -[2023-10-15 03:59:05,370][88298] Updated weights for policy 0, policy_version 42940 (0.0007) -[2023-10-15 03:59:07,081][88300] Updated weights for policy 1, policy_version 43172 (0.0009) -[2023-10-15 03:59:07,450][88300] Updated weights for policy 1, policy_version 43182 (0.0007) -[2023-10-15 03:59:07,816][88300] Updated weights for policy 1, policy_version 43192 (0.0009) -[2023-10-15 03:59:08,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 88211456. Throughput: 0: 1725.2, 1: 1747.7. Samples: 22058936. Policy #0 lag: (min: 31.0, avg: 31.1, max: 40.0) -[2023-10-15 03:59:08,534][87330] Avg episode reward: [(0, '22.700'), (1, '22.590')] -[2023-10-15 03:59:09,194][88298] Updated weights for policy 0, policy_version 42950 (0.0008) -[2023-10-15 03:59:09,561][88298] Updated weights for policy 0, policy_version 42960 (0.0010) -[2023-10-15 03:59:09,931][88298] Updated weights for policy 0, policy_version 42970 (0.0009) -[2023-10-15 03:59:11,748][88300] Updated weights for policy 1, policy_version 43202 (0.0008) -[2023-10-15 03:59:12,113][88300] Updated weights for policy 1, policy_version 43212 (0.0008) -[2023-10-15 03:59:12,487][88300] Updated weights for policy 1, policy_version 43222 (0.0008) -[2023-10-15 03:59:12,855][88300] Updated weights for policy 1, policy_version 43232 (0.0009) -[2023-10-15 03:59:13,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 88276992. Throughput: 0: 1755.1, 1: 1723.1. Samples: 22079586. Policy #0 lag: (min: 31.0, avg: 31.1, max: 40.0) -[2023-10-15 03:59:13,534][87330] Avg episode reward: [(0, '22.700'), (1, '22.540')] -[2023-10-15 03:59:13,665][88298] Updated weights for policy 0, policy_version 42980 (0.0008) -[2023-10-15 03:59:14,025][88298] Updated weights for policy 0, policy_version 42990 (0.0008) -[2023-10-15 03:59:14,405][88298] Updated weights for policy 0, policy_version 43000 (0.0008) -[2023-10-15 03:59:16,782][88300] Updated weights for policy 1, policy_version 43242 (0.0012) -[2023-10-15 03:59:17,168][88300] Updated weights for policy 1, policy_version 43252 (0.0010) -[2023-10-15 03:59:17,534][88300] Updated weights for policy 1, policy_version 43262 (0.0011) -[2023-10-15 03:59:18,342][88298] Updated weights for policy 0, policy_version 43010 (0.0009) -[2023-10-15 03:59:18,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 88342528. Throughput: 0: 1720.8, 1: 1760.4. Samples: 22090486. Policy #0 lag: (min: 31.0, avg: 31.1, max: 40.0) -[2023-10-15 03:59:18,534][87330] Avg episode reward: [(0, '22.730'), (1, '22.520')] -[2023-10-15 03:59:18,720][88298] Updated weights for policy 0, policy_version 43020 (0.0007) -[2023-10-15 03:59:19,083][88298] Updated weights for policy 0, policy_version 43030 (0.0007) -[2023-10-15 03:59:19,453][88298] Updated weights for policy 0, policy_version 43040 (0.0008) -[2023-10-15 03:59:21,462][88300] Updated weights for policy 1, policy_version 43272 (0.0011) -[2023-10-15 03:59:21,842][88300] Updated weights for policy 1, policy_version 43282 (0.0008) -[2023-10-15 03:59:22,213][88300] Updated weights for policy 1, policy_version 43292 (0.0009) -[2023-10-15 03:59:23,317][88298] Updated weights for policy 0, policy_version 43050 (0.0007) -[2023-10-15 03:59:23,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 88408064. Throughput: 0: 1747.5, 1: 1734.5. Samples: 22110726. Policy #0 lag: (min: 31.0, avg: 31.1, max: 40.0) -[2023-10-15 03:59:23,534][87330] Avg episode reward: [(0, '22.720'), (1, '22.620')] -[2023-10-15 03:59:23,689][88298] Updated weights for policy 0, policy_version 43060 (0.0009) -[2023-10-15 03:59:24,049][88298] Updated weights for policy 0, policy_version 43070 (0.0007) -[2023-10-15 03:59:25,915][88300] Updated weights for policy 1, policy_version 43302 (0.0008) -[2023-10-15 03:59:26,283][88300] Updated weights for policy 1, policy_version 43312 (0.0007) -[2023-10-15 03:59:26,648][88300] Updated weights for policy 1, policy_version 43322 (0.0008) -[2023-10-15 03:59:28,190][88298] Updated weights for policy 0, policy_version 43080 (0.0007) -[2023-10-15 03:59:28,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 88473600. Throughput: 0: 1750.3, 1: 1734.3. Samples: 22132164. Policy #0 lag: (min: 31.0, avg: 31.1, max: 40.0) -[2023-10-15 03:59:28,535][87330] Avg episode reward: [(0, '22.760'), (1, '22.640')] -[2023-10-15 03:59:28,559][88298] Updated weights for policy 0, policy_version 43090 (0.0007) -[2023-10-15 03:59:28,930][88298] Updated weights for policy 0, policy_version 43100 (0.0007) -[2023-10-15 03:59:30,567][88300] Updated weights for policy 1, policy_version 43332 (0.0008) -[2023-10-15 03:59:30,943][88300] Updated weights for policy 1, policy_version 43342 (0.0007) -[2023-10-15 03:59:31,302][88300] Updated weights for policy 1, policy_version 43352 (0.0008) -[2023-10-15 03:59:33,053][88298] Updated weights for policy 0, policy_version 43110 (0.0010) -[2023-10-15 03:59:33,444][88298] Updated weights for policy 0, policy_version 43120 (0.0009) -[2023-10-15 03:59:33,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 88539136. Throughput: 0: 1727.8, 1: 1744.6. Samples: 22142066. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:59:33,535][87330] Avg episode reward: [(0, '22.750'), (1, '22.620')] -[2023-10-15 03:59:33,821][88298] Updated weights for policy 0, policy_version 43130 (0.0009) -[2023-10-15 03:59:35,321][88300] Updated weights for policy 1, policy_version 43362 (0.0008) -[2023-10-15 03:59:35,682][88300] Updated weights for policy 1, policy_version 43372 (0.0010) -[2023-10-15 03:59:36,053][88300] Updated weights for policy 1, policy_version 43382 (0.0008) -[2023-10-15 03:59:36,423][88300] Updated weights for policy 1, policy_version 43392 (0.0009) -[2023-10-15 03:59:37,664][88298] Updated weights for policy 0, policy_version 43140 (0.0008) -[2023-10-15 03:59:38,026][88298] Updated weights for policy 0, policy_version 43150 (0.0007) -[2023-10-15 03:59:38,394][88298] Updated weights for policy 0, policy_version 43160 (0.0009) -[2023-10-15 03:59:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 88604672. Throughput: 0: 1752.2, 1: 1731.0. Samples: 22163176. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:59:38,535][87330] Avg episode reward: [(0, '22.870'), (1, '22.680')] -[2023-10-15 03:59:40,330][88300] Updated weights for policy 1, policy_version 43402 (0.0009) -[2023-10-15 03:59:40,686][88300] Updated weights for policy 1, policy_version 43412 (0.0007) -[2023-10-15 03:59:41,063][88300] Updated weights for policy 1, policy_version 43422 (0.0011) -[2023-10-15 03:59:42,101][88298] Updated weights for policy 0, policy_version 43170 (0.0010) -[2023-10-15 03:59:42,465][88298] Updated weights for policy 0, policy_version 43180 (0.0008) -[2023-10-15 03:59:42,824][88298] Updated weights for policy 0, policy_version 43190 (0.0008) -[2023-10-15 03:59:43,186][88298] Updated weights for policy 0, policy_version 43200 (0.0008) -[2023-10-15 03:59:43,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 88702976. Throughput: 0: 1735.7, 1: 1748.8. Samples: 22183962. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:59:43,535][87330] Avg episode reward: [(0, '22.700'), (1, '22.810')] -[2023-10-15 03:59:44,864][88300] Updated weights for policy 1, policy_version 43432 (0.0009) -[2023-10-15 03:59:45,225][88300] Updated weights for policy 1, policy_version 43442 (0.0010) -[2023-10-15 03:59:45,593][88300] Updated weights for policy 1, policy_version 43452 (0.0007) -[2023-10-15 03:59:47,174][88298] Updated weights for policy 0, policy_version 43210 (0.0007) -[2023-10-15 03:59:47,535][88298] Updated weights for policy 0, policy_version 43220 (0.0007) -[2023-10-15 03:59:47,908][88298] Updated weights for policy 0, policy_version 43230 (0.0008) -[2023-10-15 03:59:48,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 88768512. Throughput: 0: 1750.9, 1: 1729.7. Samples: 22194316. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:59:48,534][87330] Avg episode reward: [(0, '22.630'), (1, '22.800')] -[2023-10-15 03:59:49,375][88300] Updated weights for policy 1, policy_version 43462 (0.0007) -[2023-10-15 03:59:49,740][88300] Updated weights for policy 1, policy_version 43472 (0.0009) -[2023-10-15 03:59:50,109][88300] Updated weights for policy 1, policy_version 43482 (0.0009) -[2023-10-15 03:59:51,701][88298] Updated weights for policy 0, policy_version 43240 (0.0007) -[2023-10-15 03:59:52,078][88298] Updated weights for policy 0, policy_version 43250 (0.0008) -[2023-10-15 03:59:52,443][88298] Updated weights for policy 0, policy_version 43260 (0.0010) -[2023-10-15 03:59:53,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 88834048. Throughput: 0: 1739.5, 1: 1740.0. Samples: 22215516. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:59:53,534][87330] Avg episode reward: [(0, '22.650'), (1, '22.690')] -[2023-10-15 03:59:53,954][88300] Updated weights for policy 1, policy_version 43492 (0.0007) -[2023-10-15 03:59:54,314][88300] Updated weights for policy 1, policy_version 43502 (0.0007) -[2023-10-15 03:59:54,677][88300] Updated weights for policy 1, policy_version 43512 (0.0007) -[2023-10-15 03:59:56,178][88298] Updated weights for policy 0, policy_version 43270 (0.0009) -[2023-10-15 03:59:56,538][88298] Updated weights for policy 0, policy_version 43280 (0.0009) -[2023-10-15 03:59:56,914][88298] Updated weights for policy 0, policy_version 43290 (0.0011) -[2023-10-15 03:59:58,474][88300] Updated weights for policy 1, policy_version 43522 (0.0008) -[2023-10-15 03:59:58,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 88899584. Throughput: 0: 1719.6, 1: 1767.9. Samples: 22236526. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 03:59:58,535][87330] Avg episode reward: [(0, '22.250'), (1, '22.630')] -[2023-10-15 03:59:58,844][88300] Updated weights for policy 1, policy_version 43532 (0.0009) -[2023-10-15 03:59:59,214][88300] Updated weights for policy 1, policy_version 43542 (0.0008) -[2023-10-15 03:59:59,581][88300] Updated weights for policy 1, policy_version 43552 (0.0009) -[2023-10-15 04:00:00,777][88298] Updated weights for policy 0, policy_version 43300 (0.0009) -[2023-10-15 04:00:01,139][88298] Updated weights for policy 0, policy_version 43310 (0.0007) -[2023-10-15 04:00:01,511][88298] Updated weights for policy 0, policy_version 43320 (0.0008) -[2023-10-15 04:00:03,350][88300] Updated weights for policy 1, policy_version 43562 (0.0009) -[2023-10-15 04:00:03,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 88965120. Throughput: 0: 1750.9, 1: 1736.8. Samples: 22247432. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:00:03,535][87330] Avg episode reward: [(0, '22.280'), (1, '22.540')] -[2023-10-15 04:00:03,713][88300] Updated weights for policy 1, policy_version 43572 (0.0007) -[2023-10-15 04:00:04,078][88300] Updated weights for policy 1, policy_version 43582 (0.0008) -[2023-10-15 04:00:05,462][88298] Updated weights for policy 0, policy_version 43330 (0.0010) -[2023-10-15 04:00:05,840][88298] Updated weights for policy 0, policy_version 43340 (0.0008) -[2023-10-15 04:00:06,203][88298] Updated weights for policy 0, policy_version 43350 (0.0010) -[2023-10-15 04:00:06,574][88298] Updated weights for policy 0, policy_version 43360 (0.0008) -[2023-10-15 04:00:07,931][88300] Updated weights for policy 1, policy_version 43592 (0.0007) -[2023-10-15 04:00:08,298][88300] Updated weights for policy 1, policy_version 43602 (0.0007) -[2023-10-15 04:00:08,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 89030656. Throughput: 0: 1722.2, 1: 1769.6. Samples: 22267854. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:00:08,534][87330] Avg episode reward: [(0, '22.270'), (1, '22.550')] -[2023-10-15 04:00:08,666][88300] Updated weights for policy 1, policy_version 43612 (0.0007) -[2023-10-15 04:00:10,567][88298] Updated weights for policy 0, policy_version 43370 (0.0011) -[2023-10-15 04:00:10,937][88298] Updated weights for policy 0, policy_version 43380 (0.0011) -[2023-10-15 04:00:11,301][88298] Updated weights for policy 0, policy_version 43390 (0.0010) -[2023-10-15 04:00:12,611][88300] Updated weights for policy 1, policy_version 43622 (0.0007) -[2023-10-15 04:00:12,974][88300] Updated weights for policy 1, policy_version 43632 (0.0007) -[2023-10-15 04:00:13,349][88300] Updated weights for policy 1, policy_version 43642 (0.0007) -[2023-10-15 04:00:13,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 89096192. Throughput: 0: 1724.4, 1: 1748.2. Samples: 22288434. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:00:13,535][87330] Avg episode reward: [(0, '22.270'), (1, '22.510')] -[2023-10-15 04:00:15,294][88298] Updated weights for policy 0, policy_version 43400 (0.0009) -[2023-10-15 04:00:15,665][88298] Updated weights for policy 0, policy_version 43410 (0.0010) -[2023-10-15 04:00:16,033][88298] Updated weights for policy 0, policy_version 43420 (0.0010) -[2023-10-15 04:00:17,327][88300] Updated weights for policy 1, policy_version 43652 (0.0008) -[2023-10-15 04:00:17,692][88300] Updated weights for policy 1, policy_version 43662 (0.0008) -[2023-10-15 04:00:18,061][88300] Updated weights for policy 1, policy_version 43672 (0.0007) -[2023-10-15 04:00:18,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 89194496. Throughput: 0: 1734.7, 1: 1758.4. Samples: 22299252. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:00:18,534][87330] Avg episode reward: [(0, '22.470'), (1, '22.510')] -[2023-10-15 04:00:20,025][88298] Updated weights for policy 0, policy_version 43430 (0.0010) -[2023-10-15 04:00:20,400][88298] Updated weights for policy 0, policy_version 43440 (0.0009) -[2023-10-15 04:00:20,758][88298] Updated weights for policy 0, policy_version 43450 (0.0008) -[2023-10-15 04:00:21,851][88300] Updated weights for policy 1, policy_version 43682 (0.0008) -[2023-10-15 04:00:22,208][88300] Updated weights for policy 1, policy_version 43692 (0.0008) -[2023-10-15 04:00:22,576][88300] Updated weights for policy 1, policy_version 43702 (0.0007) -[2023-10-15 04:00:22,944][88300] Updated weights for policy 1, policy_version 43712 (0.0008) -[2023-10-15 04:00:23,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 89260032. Throughput: 0: 1722.3, 1: 1760.8. Samples: 22319918. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:00:23,535][87330] Avg episode reward: [(0, '22.390'), (1, '22.640')] -[2023-10-15 04:00:24,705][88298] Updated weights for policy 0, policy_version 43460 (0.0009) -[2023-10-15 04:00:25,073][88298] Updated weights for policy 0, policy_version 43470 (0.0007) -[2023-10-15 04:00:25,446][88298] Updated weights for policy 0, policy_version 43480 (0.0007) -[2023-10-15 04:00:26,605][88300] Updated weights for policy 1, policy_version 43722 (0.0008) -[2023-10-15 04:00:26,973][88300] Updated weights for policy 1, policy_version 43732 (0.0010) -[2023-10-15 04:00:27,343][88300] Updated weights for policy 1, policy_version 43742 (0.0010) -[2023-10-15 04:00:28,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 89325568. Throughput: 0: 1741.7, 1: 1749.1. Samples: 22341050. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:00:28,534][87330] Avg episode reward: [(0, '22.450'), (1, '22.600')] -[2023-10-15 04:00:29,253][88298] Updated weights for policy 0, policy_version 43490 (0.0007) -[2023-10-15 04:00:29,616][88298] Updated weights for policy 0, policy_version 43500 (0.0008) -[2023-10-15 04:00:29,984][88298] Updated weights for policy 0, policy_version 43510 (0.0008) -[2023-10-15 04:00:30,354][88298] Updated weights for policy 0, policy_version 43520 (0.0007) -[2023-10-15 04:00:31,571][88300] Updated weights for policy 1, policy_version 43752 (0.0009) -[2023-10-15 04:00:31,952][88300] Updated weights for policy 1, policy_version 43762 (0.0009) -[2023-10-15 04:00:32,316][88300] Updated weights for policy 1, policy_version 43772 (0.0009) -[2023-10-15 04:00:33,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 89391104. Throughput: 0: 1722.3, 1: 1776.9. Samples: 22351778. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-15 04:00:33,534][87330] Avg episode reward: [(0, '22.650'), (1, '22.700')] -[2023-10-15 04:00:34,320][88298] Updated weights for policy 0, policy_version 43530 (0.0007) -[2023-10-15 04:00:34,692][88298] Updated weights for policy 0, policy_version 43540 (0.0008) -[2023-10-15 04:00:35,061][88298] Updated weights for policy 0, policy_version 43550 (0.0009) -[2023-10-15 04:00:36,335][88300] Updated weights for policy 1, policy_version 43782 (0.0009) -[2023-10-15 04:00:36,702][88300] Updated weights for policy 1, policy_version 43792 (0.0009) -[2023-10-15 04:00:37,065][88300] Updated weights for policy 1, policy_version 43802 (0.0010) -[2023-10-15 04:00:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 89456640. Throughput: 0: 1729.7, 1: 1747.0. Samples: 22371970. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-15 04:00:38,534][87330] Avg episode reward: [(0, '22.570'), (1, '22.620')] -[2023-10-15 04:00:38,955][88298] Updated weights for policy 0, policy_version 43560 (0.0009) -[2023-10-15 04:00:39,330][88298] Updated weights for policy 0, policy_version 43570 (0.0010) -[2023-10-15 04:00:39,700][88298] Updated weights for policy 0, policy_version 43580 (0.0011) -[2023-10-15 04:00:40,714][88300] Updated weights for policy 1, policy_version 43812 (0.0009) -[2023-10-15 04:00:41,079][88300] Updated weights for policy 1, policy_version 43822 (0.0011) -[2023-10-15 04:00:41,447][88300] Updated weights for policy 1, policy_version 43832 (0.0010) -[2023-10-15 04:00:43,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 89522176. Throughput: 0: 1744.4, 1: 1743.8. Samples: 22393494. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-15 04:00:43,535][87330] Avg episode reward: [(0, '22.570'), (1, '22.600')] -[2023-10-15 04:00:43,585][88298] Updated weights for policy 0, policy_version 43590 (0.0010) -[2023-10-15 04:00:43,956][88298] Updated weights for policy 0, policy_version 43600 (0.0007) -[2023-10-15 04:00:44,319][88298] Updated weights for policy 0, policy_version 43610 (0.0008) -[2023-10-15 04:00:45,240][88300] Updated weights for policy 1, policy_version 43842 (0.0011) -[2023-10-15 04:00:45,605][88300] Updated weights for policy 1, policy_version 43852 (0.0009) -[2023-10-15 04:00:45,976][88300] Updated weights for policy 1, policy_version 43862 (0.0008) -[2023-10-15 04:00:46,338][88300] Updated weights for policy 1, policy_version 43872 (0.0009) -[2023-10-15 04:00:48,306][88298] Updated weights for policy 0, policy_version 43620 (0.0009) -[2023-10-15 04:00:48,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 89587712. Throughput: 0: 1712.9, 1: 1749.7. Samples: 22403252. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-15 04:00:48,534][87330] Avg episode reward: [(0, '22.570'), (1, '22.620')] -[2023-10-15 04:00:48,675][88298] Updated weights for policy 0, policy_version 43630 (0.0010) -[2023-10-15 04:00:49,033][88298] Updated weights for policy 0, policy_version 43640 (0.0008) -[2023-10-15 04:00:50,424][88300] Updated weights for policy 1, policy_version 43882 (0.0007) -[2023-10-15 04:00:50,785][88300] Updated weights for policy 1, policy_version 43892 (0.0007) -[2023-10-15 04:00:51,156][88300] Updated weights for policy 1, policy_version 43902 (0.0009) -[2023-10-15 04:00:52,984][88298] Updated weights for policy 0, policy_version 43650 (0.0008) -[2023-10-15 04:00:53,358][88298] Updated weights for policy 0, policy_version 43660 (0.0007) -[2023-10-15 04:00:53,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 89653248. Throughput: 0: 1745.6, 1: 1732.1. Samples: 22424350. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-15 04:00:53,534][87330] Avg episode reward: [(0, '22.670'), (1, '22.630')] -[2023-10-15 04:00:53,725][88298] Updated weights for policy 0, policy_version 43670 (0.0007) -[2023-10-15 04:00:54,099][88298] Updated weights for policy 0, policy_version 43680 (0.0009) -[2023-10-15 04:00:54,795][88300] Updated weights for policy 1, policy_version 43912 (0.0010) -[2023-10-15 04:00:55,166][88300] Updated weights for policy 1, policy_version 43922 (0.0008) -[2023-10-15 04:00:55,526][88300] Updated weights for policy 1, policy_version 43932 (0.0008) -[2023-10-15 04:00:57,895][88298] Updated weights for policy 0, policy_version 43690 (0.0009) -[2023-10-15 04:00:58,260][88298] Updated weights for policy 0, policy_version 43700 (0.0009) -[2023-10-15 04:00:58,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 89718784. Throughput: 0: 1737.5, 1: 1756.4. Samples: 22445662. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-15 04:00:58,535][87330] Avg episode reward: [(0, '22.770'), (1, '22.690')] -[2023-10-15 04:00:58,543][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000043936_44990464.pth... -[2023-10-15 04:00:58,572][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000042304_43319296.pth -[2023-10-15 04:00:58,632][88298] Updated weights for policy 0, policy_version 43710 (0.0010) -[2023-10-15 04:00:58,701][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000043712_44761088.pth... -[2023-10-15 04:00:58,738][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000042080_43089920.pth -[2023-10-15 04:00:59,565][88300] Updated weights for policy 1, policy_version 43942 (0.0010) -[2023-10-15 04:00:59,932][88300] Updated weights for policy 1, policy_version 43952 (0.0008) -[2023-10-15 04:01:00,301][88300] Updated weights for policy 1, policy_version 43962 (0.0008) -[2023-10-15 04:01:02,724][88298] Updated weights for policy 0, policy_version 43720 (0.0008) -[2023-10-15 04:01:03,094][88298] Updated weights for policy 0, policy_version 43730 (0.0008) -[2023-10-15 04:01:03,470][88298] Updated weights for policy 0, policy_version 43740 (0.0009) -[2023-10-15 04:01:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 89784320. Throughput: 0: 1729.1, 1: 1727.5. Samples: 22454798. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-15 04:01:03,534][87330] Avg episode reward: [(0, '22.800'), (1, '22.690')] -[2023-10-15 04:01:04,231][88300] Updated weights for policy 1, policy_version 43972 (0.0008) -[2023-10-15 04:01:04,605][88300] Updated weights for policy 1, policy_version 43982 (0.0007) -[2023-10-15 04:01:04,965][88300] Updated weights for policy 1, policy_version 43992 (0.0009) -[2023-10-15 04:01:07,482][88298] Updated weights for policy 0, policy_version 43750 (0.0008) -[2023-10-15 04:01:07,860][88298] Updated weights for policy 0, policy_version 43760 (0.0008) -[2023-10-15 04:01:08,236][88298] Updated weights for policy 0, policy_version 43770 (0.0008) -[2023-10-15 04:01:08,534][87330] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 89882624. Throughput: 0: 1743.2, 1: 1731.8. Samples: 22476290. Policy #0 lag: (min: 8.0, avg: 29.4, max: 40.0) -[2023-10-15 04:01:08,534][87330] Avg episode reward: [(0, '22.820'), (1, '22.690')] -[2023-10-15 04:01:08,895][88300] Updated weights for policy 1, policy_version 44002 (0.0009) -[2023-10-15 04:01:09,252][88300] Updated weights for policy 1, policy_version 44012 (0.0008) -[2023-10-15 04:01:09,631][88300] Updated weights for policy 1, policy_version 44022 (0.0009) -[2023-10-15 04:01:09,991][88300] Updated weights for policy 1, policy_version 44032 (0.0009) -[2023-10-15 04:01:11,911][88298] Updated weights for policy 0, policy_version 43780 (0.0009) -[2023-10-15 04:01:12,273][88298] Updated weights for policy 0, policy_version 43790 (0.0009) -[2023-10-15 04:01:12,642][88298] Updated weights for policy 0, policy_version 43800 (0.0007) -[2023-10-15 04:01:13,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 89948160. Throughput: 0: 1715.6, 1: 1750.6. Samples: 22497030. Policy #0 lag: (min: 8.0, avg: 29.4, max: 40.0) -[2023-10-15 04:01:13,534][87330] Avg episode reward: [(0, '22.900'), (1, '22.700')] -[2023-10-15 04:01:13,908][88300] Updated weights for policy 1, policy_version 44042 (0.0011) -[2023-10-15 04:01:14,269][88300] Updated weights for policy 1, policy_version 44052 (0.0011) -[2023-10-15 04:01:14,633][88300] Updated weights for policy 1, policy_version 44062 (0.0011) -[2023-10-15 04:01:16,528][88298] Updated weights for policy 0, policy_version 43810 (0.0010) -[2023-10-15 04:01:16,898][88298] Updated weights for policy 0, policy_version 43820 (0.0010) -[2023-10-15 04:01:17,266][88298] Updated weights for policy 0, policy_version 43830 (0.0008) -[2023-10-15 04:01:17,633][88298] Updated weights for policy 0, policy_version 43840 (0.0010) -[2023-10-15 04:01:18,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 90013696. Throughput: 0: 1747.4, 1: 1719.4. Samples: 22507784. Policy #0 lag: (min: 8.0, avg: 29.4, max: 40.0) -[2023-10-15 04:01:18,535][87330] Avg episode reward: [(0, '22.880'), (1, '22.440')] -[2023-10-15 04:01:18,658][88300] Updated weights for policy 1, policy_version 44072 (0.0008) -[2023-10-15 04:01:19,029][88300] Updated weights for policy 1, policy_version 44082 (0.0007) -[2023-10-15 04:01:19,412][88300] Updated weights for policy 1, policy_version 44092 (0.0007) -[2023-10-15 04:01:21,451][88298] Updated weights for policy 0, policy_version 43850 (0.0009) -[2023-10-15 04:01:21,827][88298] Updated weights for policy 0, policy_version 43860 (0.0009) -[2023-10-15 04:01:22,201][88298] Updated weights for policy 0, policy_version 43870 (0.0007) -[2023-10-15 04:01:23,239][88300] Updated weights for policy 1, policy_version 44102 (0.0009) -[2023-10-15 04:01:23,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 90079232. Throughput: 0: 1734.5, 1: 1752.9. Samples: 22528904. Policy #0 lag: (min: 8.0, avg: 29.4, max: 40.0) -[2023-10-15 04:01:23,535][87330] Avg episode reward: [(0, '22.930'), (1, '22.460')] -[2023-10-15 04:01:23,611][88300] Updated weights for policy 1, policy_version 44112 (0.0008) -[2023-10-15 04:01:23,972][88300] Updated weights for policy 1, policy_version 44122 (0.0009) -[2023-10-15 04:01:26,174][88298] Updated weights for policy 0, policy_version 43880 (0.0009) -[2023-10-15 04:01:26,547][88298] Updated weights for policy 0, policy_version 43890 (0.0010) -[2023-10-15 04:01:26,915][88298] Updated weights for policy 0, policy_version 43900 (0.0009) -[2023-10-15 04:01:27,858][88300] Updated weights for policy 1, policy_version 44132 (0.0008) -[2023-10-15 04:01:28,223][88300] Updated weights for policy 1, policy_version 44142 (0.0011) -[2023-10-15 04:01:28,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 90144768. Throughput: 0: 1719.2, 1: 1740.6. Samples: 22549186. Policy #0 lag: (min: 8.0, avg: 29.4, max: 40.0) -[2023-10-15 04:01:28,534][87330] Avg episode reward: [(0, '22.920'), (1, '22.490')] -[2023-10-15 04:01:28,592][88300] Updated weights for policy 1, policy_version 44152 (0.0011) -[2023-10-15 04:01:30,960][88298] Updated weights for policy 0, policy_version 43910 (0.0008) -[2023-10-15 04:01:31,329][88298] Updated weights for policy 0, policy_version 43920 (0.0008) -[2023-10-15 04:01:31,697][88298] Updated weights for policy 0, policy_version 43930 (0.0008) -[2023-10-15 04:01:32,525][88300] Updated weights for policy 1, policy_version 44162 (0.0010) -[2023-10-15 04:01:32,881][88300] Updated weights for policy 1, policy_version 44172 (0.0009) -[2023-10-15 04:01:33,258][88300] Updated weights for policy 1, policy_version 44182 (0.0010) -[2023-10-15 04:01:33,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 90210304. Throughput: 0: 1746.8, 1: 1743.3. Samples: 22560306. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:01:33,535][87330] Avg episode reward: [(0, '22.860'), (1, '22.450')] -[2023-10-15 04:01:33,627][88300] Updated weights for policy 1, policy_version 44192 (0.0009) -[2023-10-15 04:01:35,729][88298] Updated weights for policy 0, policy_version 43940 (0.0008) -[2023-10-15 04:01:36,102][88298] Updated weights for policy 0, policy_version 43950 (0.0009) -[2023-10-15 04:01:36,475][88298] Updated weights for policy 0, policy_version 43960 (0.0008) -[2023-10-15 04:01:37,716][88300] Updated weights for policy 1, policy_version 44202 (0.0007) -[2023-10-15 04:01:38,092][88300] Updated weights for policy 1, policy_version 44212 (0.0008) -[2023-10-15 04:01:38,460][88300] Updated weights for policy 1, policy_version 44222 (0.0010) -[2023-10-15 04:01:38,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 90308608. Throughput: 0: 1717.2, 1: 1754.4. Samples: 22580576. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:01:38,534][87330] Avg episode reward: [(0, '22.840'), (1, '22.560')] -[2023-10-15 04:01:40,168][88298] Updated weights for policy 0, policy_version 43970 (0.0008) -[2023-10-15 04:01:40,542][88298] Updated weights for policy 0, policy_version 43980 (0.0010) -[2023-10-15 04:01:40,907][88298] Updated weights for policy 0, policy_version 43990 (0.0007) -[2023-10-15 04:01:41,274][88298] Updated weights for policy 0, policy_version 44000 (0.0008) -[2023-10-15 04:01:42,174][88300] Updated weights for policy 1, policy_version 44232 (0.0010) -[2023-10-15 04:01:42,544][88300] Updated weights for policy 1, policy_version 44242 (0.0010) -[2023-10-15 04:01:42,906][88300] Updated weights for policy 1, policy_version 44252 (0.0010) -[2023-10-15 04:01:43,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 90374144. Throughput: 0: 1729.1, 1: 1719.6. Samples: 22600854. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:01:43,535][87330] Avg episode reward: [(0, '22.850'), (1, '22.590')] -[2023-10-15 04:01:45,199][88298] Updated weights for policy 0, policy_version 44010 (0.0007) -[2023-10-15 04:01:45,562][88298] Updated weights for policy 0, policy_version 44020 (0.0007) -[2023-10-15 04:01:45,929][88298] Updated weights for policy 0, policy_version 44030 (0.0011) -[2023-10-15 04:01:46,948][88300] Updated weights for policy 1, policy_version 44262 (0.0009) -[2023-10-15 04:01:47,326][88300] Updated weights for policy 1, policy_version 44272 (0.0007) -[2023-10-15 04:01:47,692][88300] Updated weights for policy 1, policy_version 44282 (0.0007) -[2023-10-15 04:01:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 90439680. Throughput: 0: 1736.5, 1: 1755.6. Samples: 22611944. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:01:48,534][87330] Avg episode reward: [(0, '22.880'), (1, '22.560')] -[2023-10-15 04:01:49,753][88298] Updated weights for policy 0, policy_version 44040 (0.0008) -[2023-10-15 04:01:50,112][88298] Updated weights for policy 0, policy_version 44050 (0.0008) -[2023-10-15 04:01:50,482][88298] Updated weights for policy 0, policy_version 44060 (0.0010) -[2023-10-15 04:01:51,586][88300] Updated weights for policy 1, policy_version 44292 (0.0008) -[2023-10-15 04:01:51,949][88300] Updated weights for policy 1, policy_version 44302 (0.0007) -[2023-10-15 04:01:52,318][88300] Updated weights for policy 1, policy_version 44312 (0.0007) -[2023-10-15 04:01:53,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13884.8). Total num frames: 90505216. Throughput: 0: 1731.5, 1: 1738.3. Samples: 22632436. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:01:53,535][87330] Avg episode reward: [(0, '22.700'), (1, '22.860')] -[2023-10-15 04:01:54,420][88298] Updated weights for policy 0, policy_version 44070 (0.0009) -[2023-10-15 04:01:54,792][88298] Updated weights for policy 0, policy_version 44080 (0.0008) -[2023-10-15 04:01:55,166][88298] Updated weights for policy 0, policy_version 44090 (0.0008) -[2023-10-15 04:01:56,068][88300] Updated weights for policy 1, policy_version 44322 (0.0008) -[2023-10-15 04:01:56,425][88300] Updated weights for policy 1, policy_version 44332 (0.0009) -[2023-10-15 04:01:56,803][88300] Updated weights for policy 1, policy_version 44342 (0.0011) -[2023-10-15 04:01:57,169][88300] Updated weights for policy 1, policy_version 44352 (0.0009) -[2023-10-15 04:01:58,534][87330] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 90570752. Throughput: 0: 1754.3, 1: 1725.9. Samples: 22653636. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:01:58,535][87330] Avg episode reward: [(0, '22.720'), (1, '22.850')] -[2023-10-15 04:01:58,975][88298] Updated weights for policy 0, policy_version 44100 (0.0009) -[2023-10-15 04:01:59,345][88298] Updated weights for policy 0, policy_version 44110 (0.0011) -[2023-10-15 04:01:59,725][88298] Updated weights for policy 0, policy_version 44120 (0.0011) -[2023-10-15 04:02:01,209][88300] Updated weights for policy 1, policy_version 44362 (0.0009) -[2023-10-15 04:02:01,579][88300] Updated weights for policy 1, policy_version 44372 (0.0010) -[2023-10-15 04:02:01,953][88300] Updated weights for policy 1, policy_version 44382 (0.0007) -[2023-10-15 04:02:03,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 90636288. Throughput: 0: 1726.1, 1: 1744.9. Samples: 22663978. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:02:03,534][87330] Avg episode reward: [(0, '22.730'), (1, '22.850')] -[2023-10-15 04:02:03,733][88298] Updated weights for policy 0, policy_version 44130 (0.0011) -[2023-10-15 04:02:04,112][88298] Updated weights for policy 0, policy_version 44140 (0.0008) -[2023-10-15 04:02:04,482][88298] Updated weights for policy 0, policy_version 44150 (0.0007) -[2023-10-15 04:02:04,847][88298] Updated weights for policy 0, policy_version 44160 (0.0010) -[2023-10-15 04:02:05,822][88300] Updated weights for policy 1, policy_version 44392 (0.0009) -[2023-10-15 04:02:06,179][88300] Updated weights for policy 1, policy_version 44402 (0.0007) -[2023-10-15 04:02:06,549][88300] Updated weights for policy 1, policy_version 44412 (0.0009) -[2023-10-15 04:02:08,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 90701824. Throughput: 0: 1742.9, 1: 1723.7. Samples: 22684902. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:02:08,535][87330] Avg episode reward: [(0, '22.800'), (1, '22.800')] -[2023-10-15 04:02:08,904][88298] Updated weights for policy 0, policy_version 44170 (0.0008) -[2023-10-15 04:02:09,272][88298] Updated weights for policy 0, policy_version 44180 (0.0007) -[2023-10-15 04:02:09,642][88298] Updated weights for policy 0, policy_version 44190 (0.0008) -[2023-10-15 04:02:10,354][88300] Updated weights for policy 1, policy_version 44422 (0.0008) -[2023-10-15 04:02:10,729][88300] Updated weights for policy 1, policy_version 44432 (0.0008) -[2023-10-15 04:02:11,094][88300] Updated weights for policy 1, policy_version 44442 (0.0008) -[2023-10-15 04:02:13,511][88298] Updated weights for policy 0, policy_version 44200 (0.0009) -[2023-10-15 04:02:13,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 90767360. Throughput: 0: 1755.1, 1: 1747.5. Samples: 22706802. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:02:13,535][87330] Avg episode reward: [(0, '22.830'), (1, '22.790')] -[2023-10-15 04:02:13,878][88298] Updated weights for policy 0, policy_version 44210 (0.0007) -[2023-10-15 04:02:14,254][88298] Updated weights for policy 0, policy_version 44220 (0.0008) -[2023-10-15 04:02:14,650][88300] Updated weights for policy 1, policy_version 44452 (0.0009) -[2023-10-15 04:02:15,005][88300] Updated weights for policy 1, policy_version 44462 (0.0008) -[2023-10-15 04:02:15,367][88300] Updated weights for policy 1, policy_version 44472 (0.0010) -[2023-10-15 04:02:18,188][88298] Updated weights for policy 0, policy_version 44230 (0.0009) -[2023-10-15 04:02:18,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 90832896. Throughput: 0: 1728.7, 1: 1736.2. Samples: 22716226. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:02:18,534][87330] Avg episode reward: [(0, '22.810'), (1, '22.840')] -[2023-10-15 04:02:18,543][88298] Updated weights for policy 0, policy_version 44240 (0.0009) -[2023-10-15 04:02:18,914][88298] Updated weights for policy 0, policy_version 44250 (0.0010) -[2023-10-15 04:02:19,277][88300] Updated weights for policy 1, policy_version 44482 (0.0010) -[2023-10-15 04:02:19,645][88300] Updated weights for policy 1, policy_version 44492 (0.0007) -[2023-10-15 04:02:20,010][88300] Updated weights for policy 1, policy_version 44502 (0.0009) -[2023-10-15 04:02:20,378][88300] Updated weights for policy 1, policy_version 44512 (0.0009) -[2023-10-15 04:02:22,865][88298] Updated weights for policy 0, policy_version 44260 (0.0009) -[2023-10-15 04:02:23,238][88298] Updated weights for policy 0, policy_version 44270 (0.0007) -[2023-10-15 04:02:23,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 90898432. Throughput: 0: 1752.6, 1: 1746.3. Samples: 22738026. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:02:23,535][87330] Avg episode reward: [(0, '22.990'), (1, '22.820')] -[2023-10-15 04:02:23,609][88298] Updated weights for policy 0, policy_version 44280 (0.0008) -[2023-10-15 04:02:23,906][87905] Saving new best policy, reward=22.990! -[2023-10-15 04:02:24,316][88300] Updated weights for policy 1, policy_version 44522 (0.0008) -[2023-10-15 04:02:24,689][88300] Updated weights for policy 1, policy_version 44532 (0.0010) -[2023-10-15 04:02:25,057][88300] Updated weights for policy 1, policy_version 44542 (0.0007) -[2023-10-15 04:02:27,390][88298] Updated weights for policy 0, policy_version 44290 (0.0010) -[2023-10-15 04:02:27,756][88298] Updated weights for policy 0, policy_version 44300 (0.0007) -[2023-10-15 04:02:28,125][88298] Updated weights for policy 0, policy_version 44310 (0.0007) -[2023-10-15 04:02:28,497][88298] Updated weights for policy 0, policy_version 44320 (0.0008) -[2023-10-15 04:02:28,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 90996736. Throughput: 0: 1736.9, 1: 1779.2. Samples: 22759076. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:02:28,534][87330] Avg episode reward: [(0, '22.950'), (1, '22.850')] -[2023-10-15 04:02:28,819][88300] Updated weights for policy 1, policy_version 44552 (0.0008) -[2023-10-15 04:02:29,183][88300] Updated weights for policy 1, policy_version 44562 (0.0010) -[2023-10-15 04:02:29,549][88300] Updated weights for policy 1, policy_version 44572 (0.0008) -[2023-10-15 04:02:32,305][88298] Updated weights for policy 0, policy_version 44330 (0.0008) -[2023-10-15 04:02:32,677][88298] Updated weights for policy 0, policy_version 44340 (0.0008) -[2023-10-15 04:02:33,047][88298] Updated weights for policy 0, policy_version 44350 (0.0007) -[2023-10-15 04:02:33,296][88300] Updated weights for policy 1, policy_version 44582 (0.0008) -[2023-10-15 04:02:33,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 91062272. Throughput: 0: 1747.8, 1: 1750.6. Samples: 22769372. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:02:33,535][87330] Avg episode reward: [(0, '22.960'), (1, '22.730')] -[2023-10-15 04:02:33,669][88300] Updated weights for policy 1, policy_version 44592 (0.0007) -[2023-10-15 04:02:34,036][88300] Updated weights for policy 1, policy_version 44602 (0.0007) -[2023-10-15 04:02:36,846][88298] Updated weights for policy 0, policy_version 44360 (0.0008) -[2023-10-15 04:02:37,222][88298] Updated weights for policy 0, policy_version 44370 (0.0008) -[2023-10-15 04:02:37,585][88298] Updated weights for policy 0, policy_version 44380 (0.0008) -[2023-10-15 04:02:37,939][88300] Updated weights for policy 1, policy_version 44612 (0.0007) -[2023-10-15 04:02:38,298][88300] Updated weights for policy 1, policy_version 44622 (0.0008) -[2023-10-15 04:02:38,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 91127808. Throughput: 0: 1746.9, 1: 1769.4. Samples: 22790666. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:02:38,534][87330] Avg episode reward: [(0, '22.960'), (1, '22.790')] -[2023-10-15 04:02:38,665][88300] Updated weights for policy 1, policy_version 44632 (0.0010) -[2023-10-15 04:02:41,741][88298] Updated weights for policy 0, policy_version 44390 (0.0009) -[2023-10-15 04:02:42,131][88298] Updated weights for policy 0, policy_version 44400 (0.0009) -[2023-10-15 04:02:42,496][88298] Updated weights for policy 0, policy_version 44410 (0.0008) -[2023-10-15 04:02:42,611][88300] Updated weights for policy 1, policy_version 44642 (0.0009) -[2023-10-15 04:02:42,974][88300] Updated weights for policy 1, policy_version 44652 (0.0009) -[2023-10-15 04:02:43,333][88300] Updated weights for policy 1, policy_version 44662 (0.0007) -[2023-10-15 04:02:43,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 91193344. Throughput: 0: 1716.4, 1: 1760.8. Samples: 22810110. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:02:43,535][87330] Avg episode reward: [(0, '22.910'), (1, '22.670')] -[2023-10-15 04:02:43,707][88300] Updated weights for policy 1, policy_version 44672 (0.0007) -[2023-10-15 04:02:46,372][88298] Updated weights for policy 0, policy_version 44420 (0.0009) -[2023-10-15 04:02:46,745][88298] Updated weights for policy 0, policy_version 44430 (0.0009) -[2023-10-15 04:02:47,116][88298] Updated weights for policy 0, policy_version 44440 (0.0011) -[2023-10-15 04:02:47,663][88300] Updated weights for policy 1, policy_version 44682 (0.0009) -[2023-10-15 04:02:48,040][88300] Updated weights for policy 1, policy_version 44692 (0.0008) -[2023-10-15 04:02:48,403][88300] Updated weights for policy 1, policy_version 44702 (0.0009) -[2023-10-15 04:02:48,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 91291648. Throughput: 0: 1750.4, 1: 1754.8. Samples: 22821712. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:02:48,534][87330] Avg episode reward: [(0, '22.650'), (1, '22.650')] -[2023-10-15 04:02:50,958][88298] Updated weights for policy 0, policy_version 44450 (0.0010) -[2023-10-15 04:02:51,329][88298] Updated weights for policy 0, policy_version 44460 (0.0007) -[2023-10-15 04:02:51,703][88298] Updated weights for policy 0, policy_version 44470 (0.0008) -[2023-10-15 04:02:52,070][88298] Updated weights for policy 0, policy_version 44480 (0.0008) -[2023-10-15 04:02:52,227][88300] Updated weights for policy 1, policy_version 44712 (0.0008) -[2023-10-15 04:02:52,591][88300] Updated weights for policy 1, policy_version 44722 (0.0008) -[2023-10-15 04:02:52,963][88300] Updated weights for policy 1, policy_version 44732 (0.0010) -[2023-10-15 04:02:53,534][87330] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 91357184. Throughput: 0: 1725.3, 1: 1768.5. Samples: 22842124. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:02:53,534][87330] Avg episode reward: [(0, '22.650'), (1, '22.630')] -[2023-10-15 04:02:56,153][88298] Updated weights for policy 0, policy_version 44490 (0.0008) -[2023-10-15 04:02:56,507][88298] Updated weights for policy 0, policy_version 44500 (0.0010) -[2023-10-15 04:02:56,884][88298] Updated weights for policy 0, policy_version 44510 (0.0010) -[2023-10-15 04:02:56,935][88300] Updated weights for policy 1, policy_version 44742 (0.0010) -[2023-10-15 04:02:57,301][88300] Updated weights for policy 1, policy_version 44752 (0.0008) -[2023-10-15 04:02:57,670][88300] Updated weights for policy 1, policy_version 44762 (0.0010) -[2023-10-15 04:02:58,534][87330] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 91422720. Throughput: 0: 1715.0, 1: 1728.1. Samples: 22861742. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:02:58,535][87330] Avg episode reward: [(0, '22.650'), (1, '22.590')] -[2023-10-15 04:02:58,550][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000044768_45842432.pth... -[2023-10-15 04:02:58,550][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000044512_45580288.pth... -[2023-10-15 04:02:58,587][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000042880_43909120.pth -[2023-10-15 04:02:58,589][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000043136_44171264.pth -[2023-10-15 04:03:00,819][88298] Updated weights for policy 0, policy_version 44520 (0.0009) -[2023-10-15 04:03:01,187][88298] Updated weights for policy 0, policy_version 44530 (0.0010) -[2023-10-15 04:03:01,561][88298] Updated weights for policy 0, policy_version 44540 (0.0008) -[2023-10-15 04:03:01,619][88300] Updated weights for policy 1, policy_version 44772 (0.0008) -[2023-10-15 04:03:01,990][88300] Updated weights for policy 1, policy_version 44782 (0.0007) -[2023-10-15 04:03:02,360][88300] Updated weights for policy 1, policy_version 44792 (0.0008) -[2023-10-15 04:03:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 91488256. Throughput: 0: 1734.7, 1: 1761.4. Samples: 22873552. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:03:03,534][87330] Avg episode reward: [(0, '22.650'), (1, '22.450')] -[2023-10-15 04:03:05,410][88298] Updated weights for policy 0, policy_version 44550 (0.0008) -[2023-10-15 04:03:05,775][88298] Updated weights for policy 0, policy_version 44560 (0.0008) -[2023-10-15 04:03:06,147][88298] Updated weights for policy 0, policy_version 44570 (0.0009) -[2023-10-15 04:03:06,406][88300] Updated weights for policy 1, policy_version 44802 (0.0008) -[2023-10-15 04:03:06,775][88300] Updated weights for policy 1, policy_version 44812 (0.0008) -[2023-10-15 04:03:07,142][88300] Updated weights for policy 1, policy_version 44822 (0.0008) -[2023-10-15 04:03:07,514][88300] Updated weights for policy 1, policy_version 44832 (0.0009) -[2023-10-15 04:03:08,534][87330] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 91553792. Throughput: 0: 1715.5, 1: 1734.2. Samples: 22893264. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:03:08,534][87330] Avg episode reward: [(0, '22.630'), (1, '22.400')] -[2023-10-15 04:03:10,138][88298] Updated weights for policy 0, policy_version 44580 (0.0008) -[2023-10-15 04:03:10,512][88298] Updated weights for policy 0, policy_version 44590 (0.0007) -[2023-10-15 04:03:10,890][88298] Updated weights for policy 0, policy_version 44600 (0.0008) -[2023-10-15 04:03:11,528][88300] Updated weights for policy 1, policy_version 44842 (0.0010) -[2023-10-15 04:03:11,913][88300] Updated weights for policy 1, policy_version 44852 (0.0009) -[2023-10-15 04:03:12,281][88300] Updated weights for policy 1, policy_version 44862 (0.0009) -[2023-10-15 04:03:13,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 91619328. Throughput: 0: 1726.9, 1: 1725.5. Samples: 22914434. Policy #0 lag: (min: 6.0, avg: 6.0, max: 9.0) -[2023-10-15 04:03:13,535][87330] Avg episode reward: [(0, '22.430'), (1, '22.520')] -[2023-10-15 04:03:14,963][88298] Updated weights for policy 0, policy_version 44610 (0.0009) -[2023-10-15 04:03:15,332][88298] Updated weights for policy 0, policy_version 44620 (0.0008) -[2023-10-15 04:03:15,701][88298] Updated weights for policy 0, policy_version 44630 (0.0008) -[2023-10-15 04:03:15,937][88300] Updated weights for policy 1, policy_version 44872 (0.0007) -[2023-10-15 04:03:16,068][88298] Updated weights for policy 0, policy_version 44640 (0.0008) -[2023-10-15 04:03:16,305][88300] Updated weights for policy 1, policy_version 44882 (0.0009) -[2023-10-15 04:03:16,670][88300] Updated weights for policy 1, policy_version 44892 (0.0009) -[2023-10-15 04:03:18,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 91684864. Throughput: 0: 1714.1, 1: 1745.2. Samples: 22925042. Policy #0 lag: (min: 6.0, avg: 6.0, max: 9.0) -[2023-10-15 04:03:18,534][87330] Avg episode reward: [(0, '22.670'), (1, '22.260')] -[2023-10-15 04:03:19,876][88298] Updated weights for policy 0, policy_version 44650 (0.0009) -[2023-10-15 04:03:20,251][88298] Updated weights for policy 0, policy_version 44660 (0.0008) -[2023-10-15 04:03:20,491][88300] Updated weights for policy 1, policy_version 44902 (0.0007) -[2023-10-15 04:03:20,622][88298] Updated weights for policy 0, policy_version 44670 (0.0009) -[2023-10-15 04:03:20,863][88300] Updated weights for policy 1, policy_version 44912 (0.0008) -[2023-10-15 04:03:21,228][88300] Updated weights for policy 1, policy_version 44922 (0.0008) -[2023-10-15 04:03:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 91750400. Throughput: 0: 1714.3, 1: 1734.4. Samples: 22945858. Policy #0 lag: (min: 6.0, avg: 6.0, max: 9.0) -[2023-10-15 04:03:23,535][87330] Avg episode reward: [(0, '22.720'), (1, '21.910')] -[2023-10-15 04:03:24,601][88298] Updated weights for policy 0, policy_version 44680 (0.0007) -[2023-10-15 04:03:24,979][88298] Updated weights for policy 0, policy_version 44690 (0.0007) -[2023-10-15 04:03:25,085][88300] Updated weights for policy 1, policy_version 44932 (0.0007) -[2023-10-15 04:03:25,344][88298] Updated weights for policy 0, policy_version 44700 (0.0007) -[2023-10-15 04:03:25,451][88300] Updated weights for policy 1, policy_version 44942 (0.0010) -[2023-10-15 04:03:25,824][88300] Updated weights for policy 1, policy_version 44952 (0.0009) -[2023-10-15 04:03:28,534][87330] Fps is (10 sec: 13106.4, 60 sec: 13653.2, 300 sec: 13884.7). Total num frames: 91815936. Throughput: 0: 1745.9, 1: 1750.6. Samples: 22967450. Policy #0 lag: (min: 6.0, avg: 6.0, max: 9.0) -[2023-10-15 04:03:28,535][87330] Avg episode reward: [(0, '22.720'), (1, '21.810')] -[2023-10-15 04:03:29,276][88298] Updated weights for policy 0, policy_version 44710 (0.0009) -[2023-10-15 04:03:29,653][88298] Updated weights for policy 0, policy_version 44720 (0.0008) -[2023-10-15 04:03:29,694][88300] Updated weights for policy 1, policy_version 44962 (0.0009) -[2023-10-15 04:03:30,026][88298] Updated weights for policy 0, policy_version 44730 (0.0008) -[2023-10-15 04:03:30,071][88300] Updated weights for policy 1, policy_version 44972 (0.0008) -[2023-10-15 04:03:30,438][88300] Updated weights for policy 1, policy_version 44982 (0.0010) -[2023-10-15 04:03:30,799][88300] Updated weights for policy 1, policy_version 44992 (0.0008) -[2023-10-15 04:03:33,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 91881472. Throughput: 0: 1708.4, 1: 1739.1. Samples: 22976848. Policy #0 lag: (min: 6.0, avg: 6.0, max: 9.0) -[2023-10-15 04:03:33,534][87330] Avg episode reward: [(0, '22.700'), (1, '21.880')] -[2023-10-15 04:03:33,943][88298] Updated weights for policy 0, policy_version 44740 (0.0008) -[2023-10-15 04:03:34,305][88298] Updated weights for policy 0, policy_version 44750 (0.0008) -[2023-10-15 04:03:34,667][88298] Updated weights for policy 0, policy_version 44760 (0.0009) -[2023-10-15 04:03:34,673][88300] Updated weights for policy 1, policy_version 45002 (0.0009) -[2023-10-15 04:03:35,038][88300] Updated weights for policy 1, policy_version 45012 (0.0008) -[2023-10-15 04:03:35,406][88300] Updated weights for policy 1, policy_version 45022 (0.0009) -[2023-10-15 04:03:38,534][87330] Fps is (10 sec: 13107.8, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 91947008. Throughput: 0: 1728.5, 1: 1738.7. Samples: 22998150. Policy #0 lag: (min: 6.0, avg: 6.0, max: 9.0) -[2023-10-15 04:03:38,535][87330] Avg episode reward: [(0, '22.700'), (1, '21.580')] -[2023-10-15 04:03:38,563][88298] Updated weights for policy 0, policy_version 44770 (0.0007) -[2023-10-15 04:03:38,926][88298] Updated weights for policy 0, policy_version 44780 (0.0007) -[2023-10-15 04:03:39,185][88300] Updated weights for policy 1, policy_version 45032 (0.0008) -[2023-10-15 04:03:39,293][88298] Updated weights for policy 0, policy_version 44790 (0.0007) -[2023-10-15 04:03:39,555][88300] Updated weights for policy 1, policy_version 45042 (0.0007) -[2023-10-15 04:03:39,663][88298] Updated weights for policy 0, policy_version 44800 (0.0008) -[2023-10-15 04:03:39,925][88300] Updated weights for policy 1, policy_version 45052 (0.0010) -[2023-10-15 04:03:43,451][88298] Updated weights for policy 0, policy_version 44810 (0.0008) -[2023-10-15 04:03:43,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 92012544. Throughput: 0: 1748.1, 1: 1772.3. Samples: 23020158. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:03:43,535][87330] Avg episode reward: [(0, '22.700'), (1, '21.330')] -[2023-10-15 04:03:43,669][88300] Updated weights for policy 1, policy_version 45062 (0.0010) -[2023-10-15 04:03:43,810][88298] Updated weights for policy 0, policy_version 44820 (0.0009) -[2023-10-15 04:03:44,027][88300] Updated weights for policy 1, policy_version 45072 (0.0008) -[2023-10-15 04:03:44,181][88298] Updated weights for policy 0, policy_version 44830 (0.0008) -[2023-10-15 04:03:44,397][88300] Updated weights for policy 1, policy_version 45082 (0.0008) -[2023-10-15 04:03:48,192][88298] Updated weights for policy 0, policy_version 44840 (0.0009) -[2023-10-15 04:03:48,379][88300] Updated weights for policy 1, policy_version 45092 (0.0009) -[2023-10-15 04:03:48,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13884.8). Total num frames: 92078080. Throughput: 0: 1726.5, 1: 1742.8. Samples: 23029670. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:03:48,534][87330] Avg episode reward: [(0, '22.870'), (1, '21.110')] -[2023-10-15 04:03:48,559][88298] Updated weights for policy 0, policy_version 44850 (0.0009) -[2023-10-15 04:03:48,739][88300] Updated weights for policy 1, policy_version 45102 (0.0007) -[2023-10-15 04:03:48,934][88298] Updated weights for policy 0, policy_version 44860 (0.0007) -[2023-10-15 04:03:49,100][88300] Updated weights for policy 1, policy_version 45112 (0.0007) -[2023-10-15 04:03:52,828][88298] Updated weights for policy 0, policy_version 44870 (0.0008) -[2023-10-15 04:03:53,002][88300] Updated weights for policy 1, policy_version 45122 (0.0008) -[2023-10-15 04:03:53,198][88298] Updated weights for policy 0, policy_version 44880 (0.0008) -[2023-10-15 04:03:53,358][88300] Updated weights for policy 1, policy_version 45132 (0.0008) -[2023-10-15 04:03:53,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 92143616. Throughput: 0: 1748.0, 1: 1764.5. Samples: 23051326. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:03:53,535][87330] Avg episode reward: [(0, '22.860'), (1, '21.290')] -[2023-10-15 04:03:53,563][88298] Updated weights for policy 0, policy_version 44890 (0.0007) -[2023-10-15 04:03:53,726][88300] Updated weights for policy 1, policy_version 45142 (0.0008) -[2023-10-15 04:03:54,095][88300] Updated weights for policy 1, policy_version 45152 (0.0010) -[2023-10-15 04:03:57,460][88298] Updated weights for policy 0, policy_version 44900 (0.0008) -[2023-10-15 04:03:57,829][88298] Updated weights for policy 0, policy_version 44910 (0.0009) -[2023-10-15 04:03:57,985][88300] Updated weights for policy 1, policy_version 45162 (0.0010) -[2023-10-15 04:03:58,195][88298] Updated weights for policy 0, policy_version 44920 (0.0007) -[2023-10-15 04:03:58,363][88300] Updated weights for policy 1, policy_version 45172 (0.0008) -[2023-10-15 04:03:58,534][87330] Fps is (10 sec: 16383.4, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 92241920. Throughput: 0: 1738.7, 1: 1760.1. Samples: 23071878. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:03:58,535][87330] Avg episode reward: [(0, '22.870'), (1, '21.530')] -[2023-10-15 04:03:58,741][88300] Updated weights for policy 1, policy_version 45182 (0.0009) -[2023-10-15 04:04:02,060][88298] Updated weights for policy 0, policy_version 44930 (0.0007) -[2023-10-15 04:04:02,428][88298] Updated weights for policy 0, policy_version 44940 (0.0008) -[2023-10-15 04:04:02,743][88300] Updated weights for policy 1, policy_version 45192 (0.0008) -[2023-10-15 04:04:02,809][88298] Updated weights for policy 0, policy_version 44950 (0.0009) -[2023-10-15 04:04:03,126][88300] Updated weights for policy 1, policy_version 45202 (0.0008) -[2023-10-15 04:04:03,175][88298] Updated weights for policy 0, policy_version 44960 (0.0007) -[2023-10-15 04:04:03,499][88300] Updated weights for policy 1, policy_version 45212 (0.0008) -[2023-10-15 04:04:03,534][87330] Fps is (10 sec: 16384.4, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 92307456. Throughput: 0: 1746.9, 1: 1752.2. Samples: 23082502. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:04:03,534][87330] Avg episode reward: [(0, '22.840'), (1, '21.710')] -[2023-10-15 04:04:07,218][88298] Updated weights for policy 0, policy_version 44970 (0.0008) -[2023-10-15 04:04:07,492][88300] Updated weights for policy 1, policy_version 45222 (0.0007) -[2023-10-15 04:04:07,592][88298] Updated weights for policy 0, policy_version 44980 (0.0007) -[2023-10-15 04:04:07,859][88300] Updated weights for policy 1, policy_version 45232 (0.0009) -[2023-10-15 04:04:07,968][88298] Updated weights for policy 0, policy_version 44990 (0.0008) -[2023-10-15 04:04:08,231][88300] Updated weights for policy 1, policy_version 45242 (0.0008) -[2023-10-15 04:04:08,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 92405760. Throughput: 0: 1743.2, 1: 1760.7. Samples: 23103536. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:04:08,535][87330] Avg episode reward: [(0, '22.870'), (1, '21.690')] -[2023-10-15 04:04:11,906][88298] Updated weights for policy 0, policy_version 45000 (0.0008) -[2023-10-15 04:04:12,164][88300] Updated weights for policy 1, policy_version 45252 (0.0009) -[2023-10-15 04:04:12,279][88298] Updated weights for policy 0, policy_version 45010 (0.0008) -[2023-10-15 04:04:12,532][88300] Updated weights for policy 1, policy_version 45262 (0.0007) -[2023-10-15 04:04:12,644][88298] Updated weights for policy 0, policy_version 45020 (0.0007) -[2023-10-15 04:04:12,905][88300] Updated weights for policy 1, policy_version 45272 (0.0009) -[2023-10-15 04:04:13,534][87330] Fps is (10 sec: 16383.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 92471296. Throughput: 0: 1709.1, 1: 1732.4. Samples: 23122314. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:04:13,535][87330] Avg episode reward: [(0, '22.910'), (1, '21.830')] -[2023-10-15 04:04:16,699][88298] Updated weights for policy 0, policy_version 45030 (0.0009) -[2023-10-15 04:04:16,727][88300] Updated weights for policy 1, policy_version 45282 (0.0009) -[2023-10-15 04:04:17,076][88298] Updated weights for policy 0, policy_version 45040 (0.0007) -[2023-10-15 04:04:17,096][88300] Updated weights for policy 1, policy_version 45292 (0.0008) -[2023-10-15 04:04:17,440][88298] Updated weights for policy 0, policy_version 45050 (0.0008) -[2023-10-15 04:04:17,462][88300] Updated weights for policy 1, policy_version 45302 (0.0009) -[2023-10-15 04:04:17,836][88300] Updated weights for policy 1, policy_version 45312 (0.0008) -[2023-10-15 04:04:18,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 92536832. Throughput: 0: 1738.7, 1: 1762.6. Samples: 23134406. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:04:18,534][87330] Avg episode reward: [(0, '22.900'), (1, '22.170')] -[2023-10-15 04:04:21,443][88298] Updated weights for policy 0, policy_version 45060 (0.0008) -[2023-10-15 04:04:21,664][88300] Updated weights for policy 1, policy_version 45322 (0.0009) -[2023-10-15 04:04:21,816][88298] Updated weights for policy 0, policy_version 45070 (0.0008) -[2023-10-15 04:04:22,044][88300] Updated weights for policy 1, policy_version 45332 (0.0007) -[2023-10-15 04:04:22,195][88298] Updated weights for policy 0, policy_version 45080 (0.0009) -[2023-10-15 04:04:22,407][88300] Updated weights for policy 1, policy_version 45342 (0.0009) -[2023-10-15 04:04:23,534][87330] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 92602368. Throughput: 0: 1722.8, 1: 1744.1. Samples: 23154162. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:04:23,534][87330] Avg episode reward: [(0, '22.730'), (1, '22.520')] -[2023-10-15 04:04:26,109][88298] Updated weights for policy 0, policy_version 45090 (0.0008) -[2023-10-15 04:04:26,190][88300] Updated weights for policy 1, policy_version 45352 (0.0009) -[2023-10-15 04:04:26,472][88298] Updated weights for policy 0, policy_version 45100 (0.0007) -[2023-10-15 04:04:26,549][88300] Updated weights for policy 1, policy_version 45362 (0.0009) -[2023-10-15 04:04:26,841][88298] Updated weights for policy 0, policy_version 45110 (0.0008) -[2023-10-15 04:04:26,919][88300] Updated weights for policy 1, policy_version 45372 (0.0008) -[2023-10-15 04:04:27,214][88298] Updated weights for policy 0, policy_version 45120 (0.0009) -[2023-10-15 04:04:28,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.6, 300 sec: 13995.8). Total num frames: 92667904. Throughput: 0: 1701.5, 1: 1734.6. Samples: 23174782. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:04:28,535][87330] Avg episode reward: [(0, '22.730'), (1, '22.460')] -[2023-10-15 04:04:30,629][88300] Updated weights for policy 1, policy_version 45382 (0.0008) -[2023-10-15 04:04:31,003][88300] Updated weights for policy 1, policy_version 45392 (0.0007) -[2023-10-15 04:04:31,178][88298] Updated weights for policy 0, policy_version 45130 (0.0008) -[2023-10-15 04:04:31,365][88300] Updated weights for policy 1, policy_version 45402 (0.0008) -[2023-10-15 04:04:31,555][88298] Updated weights for policy 0, policy_version 45140 (0.0007) -[2023-10-15 04:04:31,924][88298] Updated weights for policy 0, policy_version 45150 (0.0008) -[2023-10-15 04:04:33,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 92733440. Throughput: 0: 1732.4, 1: 1746.9. Samples: 23186242. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:04:33,534][87330] Avg episode reward: [(0, '22.760'), (1, '22.410')] -[2023-10-15 04:04:35,202][88300] Updated weights for policy 1, policy_version 45412 (0.0008) -[2023-10-15 04:04:35,565][88300] Updated weights for policy 1, policy_version 45422 (0.0007) -[2023-10-15 04:04:35,936][88300] Updated weights for policy 1, policy_version 45432 (0.0007) -[2023-10-15 04:04:35,940][88298] Updated weights for policy 0, policy_version 45160 (0.0008) -[2023-10-15 04:04:36,300][88298] Updated weights for policy 0, policy_version 45170 (0.0008) -[2023-10-15 04:04:36,667][88298] Updated weights for policy 0, policy_version 45180 (0.0009) -[2023-10-15 04:04:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 92798976. Throughput: 0: 1700.8, 1: 1734.6. Samples: 23205916. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:04:38,534][87330] Avg episode reward: [(0, '22.770'), (1, '22.430')] -[2023-10-15 04:04:39,833][88300] Updated weights for policy 1, policy_version 45442 (0.0008) -[2023-10-15 04:04:40,192][88300] Updated weights for policy 1, policy_version 45452 (0.0009) -[2023-10-15 04:04:40,572][88300] Updated weights for policy 1, policy_version 45462 (0.0009) -[2023-10-15 04:04:40,624][88298] Updated weights for policy 0, policy_version 45190 (0.0009) -[2023-10-15 04:04:40,938][88300] Updated weights for policy 1, policy_version 45472 (0.0008) -[2023-10-15 04:04:40,995][88298] Updated weights for policy 0, policy_version 45200 (0.0008) -[2023-10-15 04:04:41,369][88298] Updated weights for policy 0, policy_version 45210 (0.0008) -[2023-10-15 04:04:43,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 92864512. Throughput: 0: 1705.6, 1: 1747.7. Samples: 23227274. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:04:43,534][87330] Avg episode reward: [(0, '22.750'), (1, '22.460')] -[2023-10-15 04:04:44,924][88300] Updated weights for policy 1, policy_version 45482 (0.0008) -[2023-10-15 04:04:45,284][88298] Updated weights for policy 0, policy_version 45220 (0.0008) -[2023-10-15 04:04:45,303][88300] Updated weights for policy 1, policy_version 45492 (0.0008) -[2023-10-15 04:04:45,663][88298] Updated weights for policy 0, policy_version 45230 (0.0009) -[2023-10-15 04:04:45,672][88300] Updated weights for policy 1, policy_version 45502 (0.0008) -[2023-10-15 04:04:46,031][88298] Updated weights for policy 0, policy_version 45240 (0.0007) -[2023-10-15 04:04:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 92930048. Throughput: 0: 1703.2, 1: 1730.8. Samples: 23237032. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-15 04:04:48,534][87330] Avg episode reward: [(0, '22.730'), (1, '22.400')] -[2023-10-15 04:04:49,573][88300] Updated weights for policy 1, policy_version 45512 (0.0008) -[2023-10-15 04:04:49,941][88300] Updated weights for policy 1, policy_version 45522 (0.0008) -[2023-10-15 04:04:50,049][88298] Updated weights for policy 0, policy_version 45250 (0.0009) -[2023-10-15 04:04:50,312][88300] Updated weights for policy 1, policy_version 45532 (0.0007) -[2023-10-15 04:04:50,425][88298] Updated weights for policy 0, policy_version 45260 (0.0008) -[2023-10-15 04:04:50,795][88298] Updated weights for policy 0, policy_version 45270 (0.0009) -[2023-10-15 04:04:51,166][88298] Updated weights for policy 0, policy_version 45280 (0.0008) -[2023-10-15 04:04:53,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 92995584. Throughput: 0: 1690.3, 1: 1738.9. Samples: 23257850. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-15 04:04:53,534][87330] Avg episode reward: [(0, '22.900'), (1, '22.410')] -[2023-10-15 04:04:54,095][88300] Updated weights for policy 1, policy_version 45542 (0.0008) -[2023-10-15 04:04:54,468][88300] Updated weights for policy 1, policy_version 45552 (0.0007) -[2023-10-15 04:04:54,835][88300] Updated weights for policy 1, policy_version 45562 (0.0011) -[2023-10-15 04:04:55,059][88298] Updated weights for policy 0, policy_version 45290 (0.0008) -[2023-10-15 04:04:55,427][88298] Updated weights for policy 0, policy_version 45300 (0.0010) -[2023-10-15 04:04:55,809][88298] Updated weights for policy 0, policy_version 45310 (0.0009) -[2023-10-15 04:04:58,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 93061120. Throughput: 0: 1726.3, 1: 1771.3. Samples: 23279708. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-15 04:04:58,534][87330] Avg episode reward: [(0, '22.820'), (1, '22.450')] -[2023-10-15 04:04:58,544][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000045312_46399488.pth... -[2023-10-15 04:04:58,582][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000043712_44761088.pth -[2023-10-15 04:04:58,636][88300] Updated weights for policy 1, policy_version 45572 (0.0008) -[2023-10-15 04:04:59,001][88300] Updated weights for policy 1, policy_version 45582 (0.0008) -[2023-10-15 04:04:59,374][88300] Updated weights for policy 1, policy_version 45592 (0.0008) -[2023-10-15 04:04:59,574][88298] Updated weights for policy 0, policy_version 45320 (0.0008) -[2023-10-15 04:04:59,657][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000045600_46694400.pth... -[2023-10-15 04:04:59,688][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000043936_44990464.pth -[2023-10-15 04:04:59,946][88298] Updated weights for policy 0, policy_version 45330 (0.0009) -[2023-10-15 04:05:00,311][88298] Updated weights for policy 0, policy_version 45340 (0.0007) -[2023-10-15 04:05:03,361][88300] Updated weights for policy 1, policy_version 45602 (0.0010) -[2023-10-15 04:05:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 93126656. Throughput: 0: 1702.8, 1: 1742.2. Samples: 23289434. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-15 04:05:03,534][87330] Avg episode reward: [(0, '22.760'), (1, '22.500')] -[2023-10-15 04:05:03,724][88300] Updated weights for policy 1, policy_version 45612 (0.0007) -[2023-10-15 04:05:04,086][88300] Updated weights for policy 1, policy_version 45622 (0.0007) -[2023-10-15 04:05:04,209][88298] Updated weights for policy 0, policy_version 45350 (0.0008) -[2023-10-15 04:05:04,454][88300] Updated weights for policy 1, policy_version 45632 (0.0007) -[2023-10-15 04:05:04,588][88298] Updated weights for policy 0, policy_version 45360 (0.0009) -[2023-10-15 04:05:04,952][88298] Updated weights for policy 0, policy_version 45370 (0.0008) -[2023-10-15 04:05:08,427][88300] Updated weights for policy 1, policy_version 45642 (0.0008) -[2023-10-15 04:05:08,534][87330] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 13884.7). Total num frames: 93192192. Throughput: 0: 1720.1, 1: 1763.1. Samples: 23310906. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-15 04:05:08,535][87330] Avg episode reward: [(0, '22.720'), (1, '22.470')] -[2023-10-15 04:05:08,790][88300] Updated weights for policy 1, policy_version 45652 (0.0008) -[2023-10-15 04:05:08,986][88298] Updated weights for policy 0, policy_version 45380 (0.0010) -[2023-10-15 04:05:09,149][88300] Updated weights for policy 1, policy_version 45662 (0.0007) -[2023-10-15 04:05:09,380][88298] Updated weights for policy 0, policy_version 45390 (0.0009) -[2023-10-15 04:05:09,751][88298] Updated weights for policy 0, policy_version 45400 (0.0008) -[2023-10-15 04:05:13,068][88300] Updated weights for policy 1, policy_version 45672 (0.0007) -[2023-10-15 04:05:13,438][88300] Updated weights for policy 1, policy_version 45682 (0.0008) -[2023-10-15 04:05:13,484][88298] Updated weights for policy 0, policy_version 45410 (0.0009) -[2023-10-15 04:05:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 13773.7). Total num frames: 93257728. Throughput: 0: 1736.5, 1: 1756.7. Samples: 23331976. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-15 04:05:13,534][87330] Avg episode reward: [(0, '22.600'), (1, '22.650')] -[2023-10-15 04:05:13,793][88300] Updated weights for policy 1, policy_version 45692 (0.0007) -[2023-10-15 04:05:13,853][88298] Updated weights for policy 0, policy_version 45420 (0.0008) -[2023-10-15 04:05:14,219][88298] Updated weights for policy 0, policy_version 45430 (0.0009) -[2023-10-15 04:05:14,600][88298] Updated weights for policy 0, policy_version 45440 (0.0009) -[2023-10-15 04:05:17,597][88300] Updated weights for policy 1, policy_version 45702 (0.0009) -[2023-10-15 04:05:17,966][88300] Updated weights for policy 1, policy_version 45712 (0.0009) -[2023-10-15 04:05:18,339][88300] Updated weights for policy 1, policy_version 45722 (0.0008) -[2023-10-15 04:05:18,534][87330] Fps is (10 sec: 13107.7, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 93323264. Throughput: 0: 1708.8, 1: 1751.5. Samples: 23341954. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-15 04:05:18,534][87330] Avg episode reward: [(0, '22.630'), (1, '22.600')] -[2023-10-15 04:05:18,612][88298] Updated weights for policy 0, policy_version 45450 (0.0008) -[2023-10-15 04:05:18,975][88298] Updated weights for policy 0, policy_version 45460 (0.0008) -[2023-10-15 04:05:19,351][88298] Updated weights for policy 0, policy_version 45470 (0.0007) -[2023-10-15 04:05:22,333][88300] Updated weights for policy 1, policy_version 45732 (0.0008) -[2023-10-15 04:05:22,697][88300] Updated weights for policy 1, policy_version 45742 (0.0008) -[2023-10-15 04:05:23,064][88300] Updated weights for policy 1, policy_version 45752 (0.0009) -[2023-10-15 04:05:23,299][88298] Updated weights for policy 0, policy_version 45480 (0.0008) -[2023-10-15 04:05:23,534][87330] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 93421568. Throughput: 0: 1739.6, 1: 1762.0. Samples: 23363490. Policy #0 lag: (min: 8.0, avg: 34.6, max: 40.0) -[2023-10-15 04:05:23,534][87330] Avg episode reward: [(0, '22.660'), (1, '22.550')] -[2023-10-15 04:05:23,668][88298] Updated weights for policy 0, policy_version 45490 (0.0008) -[2023-10-15 04:05:24,041][88298] Updated weights for policy 0, policy_version 45500 (0.0009) -[2023-10-15 04:05:26,968][88300] Updated weights for policy 1, policy_version 45762 (0.0008) -[2023-10-15 04:05:27,327][88300] Updated weights for policy 1, policy_version 45772 (0.0007) -[2023-10-15 04:05:27,697][88300] Updated weights for policy 1, policy_version 45782 (0.0008) -[2023-10-15 04:05:28,065][88300] Updated weights for policy 1, policy_version 45792 (0.0008) -[2023-10-15 04:05:28,080][88298] Updated weights for policy 0, policy_version 45510 (0.0008) -[2023-10-15 04:05:28,445][88298] Updated weights for policy 0, policy_version 45520 (0.0008) -[2023-10-15 04:05:28,534][87330] Fps is (10 sec: 16383.5, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 93487104. Throughput: 0: 1747.3, 1: 1732.5. Samples: 23383866. Policy #0 lag: (min: 8.0, avg: 34.6, max: 40.0) -[2023-10-15 04:05:28,535][87330] Avg episode reward: [(0, '22.700'), (1, '22.630')] -[2023-10-15 04:05:28,822][88298] Updated weights for policy 0, policy_version 45530 (0.0008) -[2023-10-15 04:05:31,853][88300] Updated weights for policy 1, policy_version 45802 (0.0008) -[2023-10-15 04:05:32,233][88300] Updated weights for policy 1, policy_version 45812 (0.0007) -[2023-10-15 04:05:32,597][88300] Updated weights for policy 1, policy_version 45822 (0.0007) -[2023-10-15 04:05:32,762][88298] Updated weights for policy 0, policy_version 45540 (0.0008) -[2023-10-15 04:05:33,143][88298] Updated weights for policy 0, policy_version 45550 (0.0009) -[2023-10-15 04:05:33,515][88298] Updated weights for policy 0, policy_version 45560 (0.0009) -[2023-10-15 04:05:33,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 93552640. Throughput: 0: 1735.1, 1: 1772.2. Samples: 23394860. Policy #0 lag: (min: 8.0, avg: 34.6, max: 40.0) -[2023-10-15 04:05:33,535][87330] Avg episode reward: [(0, '22.740'), (1, '22.530')] -[2023-10-15 04:05:36,316][88300] Updated weights for policy 1, policy_version 45832 (0.0007) -[2023-10-15 04:05:36,690][88300] Updated weights for policy 1, policy_version 45842 (0.0009) -[2023-10-15 04:05:37,056][88300] Updated weights for policy 1, policy_version 45852 (0.0008) -[2023-10-15 04:05:37,409][88298] Updated weights for policy 0, policy_version 45570 (0.0008) -[2023-10-15 04:05:37,769][88298] Updated weights for policy 0, policy_version 45580 (0.0010) -[2023-10-15 04:05:38,145][88298] Updated weights for policy 0, policy_version 45590 (0.0010) -[2023-10-15 04:05:38,520][88298] Updated weights for policy 0, policy_version 45600 (0.0007) -[2023-10-15 04:05:38,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 93650944. Throughput: 0: 1754.7, 1: 1739.2. Samples: 23415074. Policy #0 lag: (min: 8.0, avg: 34.6, max: 40.0) -[2023-10-15 04:05:38,535][87330] Avg episode reward: [(0, '22.730'), (1, '22.500')] -[2023-10-15 04:05:40,900][88300] Updated weights for policy 1, policy_version 45862 (0.0008) -[2023-10-15 04:05:41,262][88300] Updated weights for policy 1, policy_version 45872 (0.0009) -[2023-10-15 04:05:41,636][88300] Updated weights for policy 1, policy_version 45882 (0.0009) -[2023-10-15 04:05:42,278][88298] Updated weights for policy 0, policy_version 45610 (0.0007) -[2023-10-15 04:05:42,640][88298] Updated weights for policy 0, policy_version 45620 (0.0009) -[2023-10-15 04:05:43,018][88298] Updated weights for policy 0, policy_version 45630 (0.0010) -[2023-10-15 04:05:43,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 93716480. Throughput: 0: 1733.8, 1: 1739.0. Samples: 23435982. Policy #0 lag: (min: 8.0, avg: 34.6, max: 40.0) -[2023-10-15 04:05:43,534][87330] Avg episode reward: [(0, '22.790'), (1, '22.420')] -[2023-10-15 04:05:45,411][88300] Updated weights for policy 1, policy_version 45892 (0.0009) -[2023-10-15 04:05:45,777][88300] Updated weights for policy 1, policy_version 45902 (0.0007) -[2023-10-15 04:05:46,138][88300] Updated weights for policy 1, policy_version 45912 (0.0009) -[2023-10-15 04:05:46,771][88298] Updated weights for policy 0, policy_version 45640 (0.0011) -[2023-10-15 04:05:47,140][88298] Updated weights for policy 0, policy_version 45650 (0.0007) -[2023-10-15 04:05:47,512][88298] Updated weights for policy 0, policy_version 45660 (0.0007) -[2023-10-15 04:05:48,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 93782016. Throughput: 0: 1751.1, 1: 1746.2. Samples: 23446810. Policy #0 lag: (min: 8.0, avg: 34.6, max: 40.0) -[2023-10-15 04:05:48,534][87330] Avg episode reward: [(0, '22.910'), (1, '22.510')] -[2023-10-15 04:05:50,122][88300] Updated weights for policy 1, policy_version 45922 (0.0008) -[2023-10-15 04:05:50,482][88300] Updated weights for policy 1, policy_version 45932 (0.0007) -[2023-10-15 04:05:50,854][88300] Updated weights for policy 1, policy_version 45942 (0.0008) -[2023-10-15 04:05:51,212][88300] Updated weights for policy 1, policy_version 45952 (0.0009) -[2023-10-15 04:05:51,293][88298] Updated weights for policy 0, policy_version 45670 (0.0009) -[2023-10-15 04:05:51,672][88298] Updated weights for policy 0, policy_version 45680 (0.0009) -[2023-10-15 04:05:52,037][88298] Updated weights for policy 0, policy_version 45690 (0.0007) -[2023-10-15 04:05:53,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 93847552. Throughput: 0: 1736.8, 1: 1740.9. Samples: 23467398. Policy #0 lag: (min: 31.0, avg: 33.1, max: 62.0) -[2023-10-15 04:05:53,534][87330] Avg episode reward: [(0, '22.860'), (1, '22.530')] -[2023-10-15 04:05:55,168][88300] Updated weights for policy 1, policy_version 45962 (0.0008) -[2023-10-15 04:05:55,540][88300] Updated weights for policy 1, policy_version 45972 (0.0007) -[2023-10-15 04:05:55,901][88300] Updated weights for policy 1, policy_version 45982 (0.0007) -[2023-10-15 04:05:55,963][88298] Updated weights for policy 0, policy_version 45700 (0.0008) -[2023-10-15 04:05:56,358][88298] Updated weights for policy 0, policy_version 45710 (0.0010) -[2023-10-15 04:05:56,725][88298] Updated weights for policy 0, policy_version 45720 (0.0008) -[2023-10-15 04:05:58,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 93913088. Throughput: 0: 1724.8, 1: 1749.9. Samples: 23488338. Policy #0 lag: (min: 31.0, avg: 33.1, max: 62.0) -[2023-10-15 04:05:58,534][87330] Avg episode reward: [(0, '22.870'), (1, '22.550')] -[2023-10-15 04:05:59,813][88300] Updated weights for policy 1, policy_version 45992 (0.0010) -[2023-10-15 04:06:00,181][88300] Updated weights for policy 1, policy_version 46002 (0.0009) -[2023-10-15 04:06:00,545][88300] Updated weights for policy 1, policy_version 46012 (0.0008) -[2023-10-15 04:06:00,606][88298] Updated weights for policy 0, policy_version 45730 (0.0008) -[2023-10-15 04:06:00,970][88298] Updated weights for policy 0, policy_version 45740 (0.0008) -[2023-10-15 04:06:01,340][88298] Updated weights for policy 0, policy_version 45750 (0.0008) -[2023-10-15 04:06:01,712][88298] Updated weights for policy 0, policy_version 45760 (0.0007) -[2023-10-15 04:06:03,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 93978624. Throughput: 0: 1749.5, 1: 1742.1. Samples: 23499078. Policy #0 lag: (min: 31.0, avg: 33.1, max: 62.0) -[2023-10-15 04:06:03,535][87330] Avg episode reward: [(0, '22.820'), (1, '22.540')] -[2023-10-15 04:06:04,587][88300] Updated weights for policy 1, policy_version 46022 (0.0009) -[2023-10-15 04:06:04,960][88300] Updated weights for policy 1, policy_version 46032 (0.0010) -[2023-10-15 04:06:05,334][88300] Updated weights for policy 1, policy_version 46042 (0.0008) -[2023-10-15 04:06:05,480][88298] Updated weights for policy 0, policy_version 45770 (0.0008) -[2023-10-15 04:06:05,841][88298] Updated weights for policy 0, policy_version 45780 (0.0007) -[2023-10-15 04:06:06,222][88298] Updated weights for policy 0, policy_version 45790 (0.0007) -[2023-10-15 04:06:08,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 94044160. Throughput: 0: 1731.2, 1: 1736.0. Samples: 23519516. Policy #0 lag: (min: 31.0, avg: 33.1, max: 62.0) -[2023-10-15 04:06:08,534][87330] Avg episode reward: [(0, '22.910'), (1, '22.600')] -[2023-10-15 04:06:09,292][88300] Updated weights for policy 1, policy_version 46052 (0.0007) -[2023-10-15 04:06:09,654][88300] Updated weights for policy 1, policy_version 46062 (0.0008) -[2023-10-15 04:06:10,024][88300] Updated weights for policy 1, policy_version 46072 (0.0007) -[2023-10-15 04:06:10,140][88298] Updated weights for policy 0, policy_version 45800 (0.0008) -[2023-10-15 04:06:10,515][88298] Updated weights for policy 0, policy_version 45810 (0.0007) -[2023-10-15 04:06:10,883][88298] Updated weights for policy 0, policy_version 45820 (0.0007) -[2023-10-15 04:06:13,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 94109696. Throughput: 0: 1729.8, 1: 1765.2. Samples: 23541140. Policy #0 lag: (min: 31.0, avg: 33.1, max: 62.0) -[2023-10-15 04:06:13,534][87330] Avg episode reward: [(0, '22.900'), (1, '22.710')] -[2023-10-15 04:06:13,933][88300] Updated weights for policy 1, policy_version 46082 (0.0008) -[2023-10-15 04:06:14,299][88300] Updated weights for policy 1, policy_version 46092 (0.0010) -[2023-10-15 04:06:14,663][88300] Updated weights for policy 1, policy_version 46102 (0.0009) -[2023-10-15 04:06:14,843][88298] Updated weights for policy 0, policy_version 45830 (0.0009) -[2023-10-15 04:06:15,029][88300] Updated weights for policy 1, policy_version 46112 (0.0009) -[2023-10-15 04:06:15,209][88298] Updated weights for policy 0, policy_version 45840 (0.0010) -[2023-10-15 04:06:15,580][88298] Updated weights for policy 0, policy_version 45850 (0.0012) -[2023-10-15 04:06:18,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 94175232. Throughput: 0: 1733.6, 1: 1731.3. Samples: 23550780. Policy #0 lag: (min: 31.0, avg: 33.1, max: 62.0) -[2023-10-15 04:06:18,534][87330] Avg episode reward: [(0, '22.720'), (1, '22.750')] -[2023-10-15 04:06:19,021][88300] Updated weights for policy 1, policy_version 46122 (0.0011) -[2023-10-15 04:06:19,391][88300] Updated weights for policy 1, policy_version 46132 (0.0008) -[2023-10-15 04:06:19,555][88298] Updated weights for policy 0, policy_version 45860 (0.0009) -[2023-10-15 04:06:19,759][88300] Updated weights for policy 1, policy_version 46142 (0.0009) -[2023-10-15 04:06:19,932][88298] Updated weights for policy 0, policy_version 45870 (0.0009) -[2023-10-15 04:06:20,299][88298] Updated weights for policy 0, policy_version 45880 (0.0008) -[2023-10-15 04:06:23,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 94240768. Throughput: 0: 1731.4, 1: 1759.5. Samples: 23572162. Policy #0 lag: (min: 31.0, avg: 33.1, max: 62.0) -[2023-10-15 04:06:23,535][87330] Avg episode reward: [(0, '22.740'), (1, '22.760')] -[2023-10-15 04:06:23,677][88300] Updated weights for policy 1, policy_version 46152 (0.0010) -[2023-10-15 04:06:24,052][88300] Updated weights for policy 1, policy_version 46162 (0.0009) -[2023-10-15 04:06:24,145][88298] Updated weights for policy 0, policy_version 45890 (0.0008) -[2023-10-15 04:06:24,417][88300] Updated weights for policy 1, policy_version 46172 (0.0009) -[2023-10-15 04:06:24,520][88298] Updated weights for policy 0, policy_version 45900 (0.0008) -[2023-10-15 04:06:24,884][88298] Updated weights for policy 0, policy_version 45910 (0.0008) -[2023-10-15 04:06:25,254][88298] Updated weights for policy 0, policy_version 45920 (0.0007) -[2023-10-15 04:06:28,257][88300] Updated weights for policy 1, policy_version 46182 (0.0008) -[2023-10-15 04:06:28,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 94306304. Throughput: 0: 1757.6, 1: 1753.0. Samples: 23593960. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-15 04:06:28,535][87330] Avg episode reward: [(0, '22.570'), (1, '22.750')] -[2023-10-15 04:06:28,623][88300] Updated weights for policy 1, policy_version 46192 (0.0010) -[2023-10-15 04:06:28,994][88300] Updated weights for policy 1, policy_version 46202 (0.0007) -[2023-10-15 04:06:29,061][88298] Updated weights for policy 0, policy_version 45930 (0.0007) -[2023-10-15 04:06:29,425][88298] Updated weights for policy 0, policy_version 45940 (0.0008) -[2023-10-15 04:06:29,792][88298] Updated weights for policy 0, policy_version 45950 (0.0008) -[2023-10-15 04:06:32,683][88300] Updated weights for policy 1, policy_version 46212 (0.0007) -[2023-10-15 04:06:33,048][88300] Updated weights for policy 1, policy_version 46222 (0.0008) -[2023-10-15 04:06:33,418][88300] Updated weights for policy 1, policy_version 46232 (0.0008) -[2023-10-15 04:06:33,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 94371840. Throughput: 0: 1737.5, 1: 1748.2. Samples: 23603666. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-15 04:06:33,534][87330] Avg episode reward: [(0, '22.380'), (1, '22.650')] -[2023-10-15 04:06:33,749][88298] Updated weights for policy 0, policy_version 45960 (0.0007) -[2023-10-15 04:06:34,130][88298] Updated weights for policy 0, policy_version 45970 (0.0009) -[2023-10-15 04:06:34,496][88298] Updated weights for policy 0, policy_version 45980 (0.0009) -[2023-10-15 04:06:37,209][88300] Updated weights for policy 1, policy_version 46242 (0.0009) -[2023-10-15 04:06:37,580][88300] Updated weights for policy 1, policy_version 46252 (0.0010) -[2023-10-15 04:06:37,943][88300] Updated weights for policy 1, policy_version 46262 (0.0009) -[2023-10-15 04:06:38,306][88300] Updated weights for policy 1, policy_version 46272 (0.0008) -[2023-10-15 04:06:38,433][88298] Updated weights for policy 0, policy_version 45990 (0.0009) -[2023-10-15 04:06:38,534][87330] Fps is (10 sec: 16384.3, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 94470144. Throughput: 0: 1748.1, 1: 1753.4. Samples: 23624968. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-15 04:06:38,534][87330] Avg episode reward: [(0, '22.400'), (1, '22.610')] -[2023-10-15 04:06:38,806][88298] Updated weights for policy 0, policy_version 46000 (0.0007) -[2023-10-15 04:06:39,166][88298] Updated weights for policy 0, policy_version 46010 (0.0009) -[2023-10-15 04:06:42,093][88300] Updated weights for policy 1, policy_version 46282 (0.0007) -[2023-10-15 04:06:42,467][88300] Updated weights for policy 1, policy_version 46292 (0.0007) -[2023-10-15 04:06:42,834][88300] Updated weights for policy 1, policy_version 46302 (0.0007) -[2023-10-15 04:06:43,068][88298] Updated weights for policy 0, policy_version 46020 (0.0008) -[2023-10-15 04:06:43,432][88298] Updated weights for policy 0, policy_version 46030 (0.0007) -[2023-10-15 04:06:43,534][87330] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 94535680. Throughput: 0: 1761.2, 1: 1732.5. Samples: 23645554. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-15 04:06:43,535][87330] Avg episode reward: [(0, '22.410'), (1, '22.600')] -[2023-10-15 04:06:43,800][88298] Updated weights for policy 0, policy_version 46040 (0.0007) -[2023-10-15 04:06:46,631][88300] Updated weights for policy 1, policy_version 46312 (0.0007) -[2023-10-15 04:06:47,005][88300] Updated weights for policy 1, policy_version 46322 (0.0008) -[2023-10-15 04:06:47,382][88300] Updated weights for policy 1, policy_version 46332 (0.0010) -[2023-10-15 04:06:47,875][88298] Updated weights for policy 0, policy_version 46050 (0.0010) -[2023-10-15 04:06:48,245][88298] Updated weights for policy 0, policy_version 46060 (0.0009) -[2023-10-15 04:06:48,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 94601216. Throughput: 0: 1731.0, 1: 1763.8. Samples: 23656344. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-15 04:06:48,534][87330] Avg episode reward: [(0, '22.580'), (1, '22.640')] -[2023-10-15 04:06:48,615][88298] Updated weights for policy 0, policy_version 46070 (0.0009) -[2023-10-15 04:06:48,986][88298] Updated weights for policy 0, policy_version 46080 (0.0008) -[2023-10-15 04:06:51,286][88300] Updated weights for policy 1, policy_version 46342 (0.0009) -[2023-10-15 04:06:51,658][88300] Updated weights for policy 1, policy_version 46352 (0.0007) -[2023-10-15 04:06:52,033][88300] Updated weights for policy 1, policy_version 46362 (0.0007) -[2023-10-15 04:06:52,909][88298] Updated weights for policy 0, policy_version 46090 (0.0009) -[2023-10-15 04:06:53,274][88298] Updated weights for policy 0, policy_version 46100 (0.0010) -[2023-10-15 04:06:53,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 94666752. Throughput: 0: 1749.9, 1: 1743.0. Samples: 23676694. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-15 04:06:53,535][87330] Avg episode reward: [(0, '22.590'), (1, '22.640')] -[2023-10-15 04:06:53,648][88298] Updated weights for policy 0, policy_version 46110 (0.0007) -[2023-10-15 04:06:55,774][88300] Updated weights for policy 1, policy_version 46372 (0.0008) -[2023-10-15 04:06:56,135][88300] Updated weights for policy 1, policy_version 46382 (0.0007) -[2023-10-15 04:06:56,505][88300] Updated weights for policy 1, policy_version 46392 (0.0007) -[2023-10-15 04:06:57,344][88298] Updated weights for policy 0, policy_version 46120 (0.0009) -[2023-10-15 04:06:57,713][88298] Updated weights for policy 0, policy_version 46130 (0.0007) -[2023-10-15 04:06:58,085][88298] Updated weights for policy 0, policy_version 46140 (0.0008) -[2023-10-15 04:06:58,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 94765056. Throughput: 0: 1733.4, 1: 1745.9. Samples: 23697706. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:06:58,534][87330] Avg episode reward: [(0, '22.570'), (1, '22.610')] -[2023-10-15 04:06:58,544][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000046144_47251456.pth... -[2023-10-15 04:06:58,544][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000046400_47513600.pth... -[2023-10-15 04:06:58,581][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000044768_45842432.pth -[2023-10-15 04:06:58,584][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000044512_45580288.pth -[2023-10-15 04:07:00,240][88300] Updated weights for policy 1, policy_version 46402 (0.0010) -[2023-10-15 04:07:00,605][88300] Updated weights for policy 1, policy_version 46412 (0.0007) -[2023-10-15 04:07:00,983][88300] Updated weights for policy 1, policy_version 46422 (0.0007) -[2023-10-15 04:07:01,346][88300] Updated weights for policy 1, policy_version 46432 (0.0009) -[2023-10-15 04:07:01,936][88298] Updated weights for policy 0, policy_version 46150 (0.0009) -[2023-10-15 04:07:02,305][88298] Updated weights for policy 0, policy_version 46160 (0.0009) -[2023-10-15 04:07:02,681][88298] Updated weights for policy 0, policy_version 46170 (0.0007) -[2023-10-15 04:07:03,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 94830592. Throughput: 0: 1748.4, 1: 1751.9. Samples: 23708296. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:07:03,535][87330] Avg episode reward: [(0, '22.720'), (1, '22.480')] -[2023-10-15 04:07:05,196][88300] Updated weights for policy 1, policy_version 46442 (0.0008) -[2023-10-15 04:07:05,554][88300] Updated weights for policy 1, policy_version 46452 (0.0008) -[2023-10-15 04:07:05,924][88300] Updated weights for policy 1, policy_version 46462 (0.0007) -[2023-10-15 04:07:06,567][88298] Updated weights for policy 0, policy_version 46180 (0.0008) -[2023-10-15 04:07:06,924][88298] Updated weights for policy 0, policy_version 46190 (0.0010) -[2023-10-15 04:07:07,301][88298] Updated weights for policy 0, policy_version 46200 (0.0008) -[2023-10-15 04:07:08,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 94896128. Throughput: 0: 1745.3, 1: 1754.0. Samples: 23729630. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:07:08,534][87330] Avg episode reward: [(0, '22.940'), (1, '22.450')] -[2023-10-15 04:07:09,875][88300] Updated weights for policy 1, policy_version 46472 (0.0009) -[2023-10-15 04:07:10,258][88300] Updated weights for policy 1, policy_version 46482 (0.0008) -[2023-10-15 04:07:10,620][88300] Updated weights for policy 1, policy_version 46492 (0.0007) -[2023-10-15 04:07:11,326][88298] Updated weights for policy 0, policy_version 46210 (0.0008) -[2023-10-15 04:07:11,704][88298] Updated weights for policy 0, policy_version 46220 (0.0008) -[2023-10-15 04:07:12,073][88298] Updated weights for policy 0, policy_version 46230 (0.0008) -[2023-10-15 04:07:12,440][88298] Updated weights for policy 0, policy_version 46240 (0.0008) -[2023-10-15 04:07:13,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 94961664. Throughput: 0: 1715.3, 1: 1758.7. Samples: 23750290. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:07:13,535][87330] Avg episode reward: [(0, '22.930'), (1, '22.430')] -[2023-10-15 04:07:14,364][88300] Updated weights for policy 1, policy_version 46502 (0.0009) -[2023-10-15 04:07:14,738][88300] Updated weights for policy 1, policy_version 46512 (0.0010) -[2023-10-15 04:07:15,101][88300] Updated weights for policy 1, policy_version 46522 (0.0008) -[2023-10-15 04:07:16,453][88298] Updated weights for policy 0, policy_version 46250 (0.0010) -[2023-10-15 04:07:16,831][88298] Updated weights for policy 0, policy_version 46260 (0.0008) -[2023-10-15 04:07:17,200][88298] Updated weights for policy 0, policy_version 46270 (0.0008) -[2023-10-15 04:07:18,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 95027200. Throughput: 0: 1746.8, 1: 1750.8. Samples: 23761058. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:07:18,535][87330] Avg episode reward: [(0, '22.910'), (1, '22.410')] -[2023-10-15 04:07:19,079][88300] Updated weights for policy 1, policy_version 46532 (0.0007) -[2023-10-15 04:07:19,449][88300] Updated weights for policy 1, policy_version 46542 (0.0007) -[2023-10-15 04:07:19,812][88300] Updated weights for policy 1, policy_version 46552 (0.0008) -[2023-10-15 04:07:21,099][88298] Updated weights for policy 0, policy_version 46280 (0.0008) -[2023-10-15 04:07:21,466][88298] Updated weights for policy 0, policy_version 46290 (0.0009) -[2023-10-15 04:07:21,837][88298] Updated weights for policy 0, policy_version 46300 (0.0008) -[2023-10-15 04:07:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 95092736. Throughput: 0: 1727.6, 1: 1757.1. Samples: 23781778. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:07:23,535][87330] Avg episode reward: [(0, '22.900'), (1, '22.400')] -[2023-10-15 04:07:23,578][88300] Updated weights for policy 1, policy_version 46562 (0.0010) -[2023-10-15 04:07:23,939][88300] Updated weights for policy 1, policy_version 46572 (0.0008) -[2023-10-15 04:07:24,304][88300] Updated weights for policy 1, policy_version 46582 (0.0008) -[2023-10-15 04:07:24,670][88300] Updated weights for policy 1, policy_version 46592 (0.0007) -[2023-10-15 04:07:25,673][88298] Updated weights for policy 0, policy_version 46310 (0.0007) -[2023-10-15 04:07:26,048][88298] Updated weights for policy 0, policy_version 46320 (0.0007) -[2023-10-15 04:07:26,419][88298] Updated weights for policy 0, policy_version 46330 (0.0007) -[2023-10-15 04:07:28,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 95158272. Throughput: 0: 1720.8, 1: 1781.8. Samples: 23803170. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:07:28,534][87330] Avg episode reward: [(0, '22.920'), (1, '22.450')] -[2023-10-15 04:07:28,681][88300] Updated weights for policy 1, policy_version 46602 (0.0010) -[2023-10-15 04:07:29,060][88300] Updated weights for policy 1, policy_version 46612 (0.0010) -[2023-10-15 04:07:29,428][88300] Updated weights for policy 1, policy_version 46622 (0.0008) -[2023-10-15 04:07:30,251][88298] Updated weights for policy 0, policy_version 46340 (0.0007) -[2023-10-15 04:07:30,655][88298] Updated weights for policy 0, policy_version 46350 (0.0007) -[2023-10-15 04:07:31,015][88298] Updated weights for policy 0, policy_version 46360 (0.0007) -[2023-10-15 04:07:33,310][88300] Updated weights for policy 1, policy_version 46632 (0.0010) -[2023-10-15 04:07:33,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 95223808. Throughput: 0: 1736.8, 1: 1744.7. Samples: 23813008. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:07:33,535][87330] Avg episode reward: [(0, '22.950'), (1, '22.620')] -[2023-10-15 04:07:33,691][88300] Updated weights for policy 1, policy_version 46642 (0.0008) -[2023-10-15 04:07:34,053][88300] Updated weights for policy 1, policy_version 46652 (0.0009) -[2023-10-15 04:07:34,708][88298] Updated weights for policy 0, policy_version 46370 (0.0010) -[2023-10-15 04:07:35,069][88298] Updated weights for policy 0, policy_version 46380 (0.0007) -[2023-10-15 04:07:35,448][88298] Updated weights for policy 0, policy_version 46390 (0.0008) -[2023-10-15 04:07:35,816][88298] Updated weights for policy 0, policy_version 46400 (0.0007) -[2023-10-15 04:07:38,055][88300] Updated weights for policy 1, policy_version 46662 (0.0009) -[2023-10-15 04:07:38,431][88300] Updated weights for policy 1, policy_version 46672 (0.0007) -[2023-10-15 04:07:38,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 95289344. Throughput: 0: 1726.3, 1: 1769.9. Samples: 23834022. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:07:38,535][87330] Avg episode reward: [(0, '22.900'), (1, '22.690')] -[2023-10-15 04:07:38,788][88300] Updated weights for policy 1, policy_version 46682 (0.0011) -[2023-10-15 04:07:39,737][88298] Updated weights for policy 0, policy_version 46410 (0.0011) -[2023-10-15 04:07:40,118][88298] Updated weights for policy 0, policy_version 46420 (0.0010) -[2023-10-15 04:07:40,473][88298] Updated weights for policy 0, policy_version 46430 (0.0010) -[2023-10-15 04:07:42,576][88300] Updated weights for policy 1, policy_version 46692 (0.0009) -[2023-10-15 04:07:42,940][88300] Updated weights for policy 1, policy_version 46702 (0.0007) -[2023-10-15 04:07:43,303][88300] Updated weights for policy 1, policy_version 46712 (0.0007) -[2023-10-15 04:07:43,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 95354880. Throughput: 0: 1743.7, 1: 1749.9. Samples: 23854916. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:07:43,534][87330] Avg episode reward: [(0, '22.900'), (1, '22.840')] -[2023-10-15 04:07:44,535][88298] Updated weights for policy 0, policy_version 46440 (0.0009) -[2023-10-15 04:07:44,915][88298] Updated weights for policy 0, policy_version 46450 (0.0009) -[2023-10-15 04:07:45,280][88298] Updated weights for policy 0, policy_version 46460 (0.0007) -[2023-10-15 04:07:47,099][88300] Updated weights for policy 1, policy_version 46722 (0.0008) -[2023-10-15 04:07:47,460][88300] Updated weights for policy 1, policy_version 46732 (0.0009) -[2023-10-15 04:07:47,824][88300] Updated weights for policy 1, policy_version 46742 (0.0011) -[2023-10-15 04:07:48,189][88300] Updated weights for policy 1, policy_version 46752 (0.0009) -[2023-10-15 04:07:48,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 95453184. Throughput: 0: 1728.1, 1: 1761.2. Samples: 23865316. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:07:48,535][87330] Avg episode reward: [(0, '22.890'), (1, '22.590')] -[2023-10-15 04:07:49,079][88298] Updated weights for policy 0, policy_version 46470 (0.0010) -[2023-10-15 04:07:49,451][88298] Updated weights for policy 0, policy_version 46480 (0.0009) -[2023-10-15 04:07:49,822][88298] Updated weights for policy 0, policy_version 46490 (0.0010) -[2023-10-15 04:07:52,231][88300] Updated weights for policy 1, policy_version 46762 (0.0009) -[2023-10-15 04:07:52,593][88300] Updated weights for policy 1, policy_version 46772 (0.0007) -[2023-10-15 04:07:52,963][88300] Updated weights for policy 1, policy_version 46782 (0.0007) -[2023-10-15 04:07:53,534][87330] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 95518720. Throughput: 0: 1737.2, 1: 1747.9. Samples: 23886464. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:07:53,535][87330] Avg episode reward: [(0, '22.880'), (1, '22.600')] -[2023-10-15 04:07:53,678][88298] Updated weights for policy 0, policy_version 46500 (0.0009) -[2023-10-15 04:07:54,056][88298] Updated weights for policy 0, policy_version 46510 (0.0007) -[2023-10-15 04:07:54,413][88298] Updated weights for policy 0, policy_version 46520 (0.0009) -[2023-10-15 04:07:56,980][88300] Updated weights for policy 1, policy_version 46792 (0.0009) -[2023-10-15 04:07:57,359][88300] Updated weights for policy 1, policy_version 46802 (0.0009) -[2023-10-15 04:07:57,723][88300] Updated weights for policy 1, policy_version 46812 (0.0009) -[2023-10-15 04:07:58,502][88298] Updated weights for policy 0, policy_version 46530 (0.0010) -[2023-10-15 04:07:58,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 95584256. Throughput: 0: 1756.9, 1: 1724.4. Samples: 23906948. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:07:58,534][87330] Avg episode reward: [(0, '22.860'), (1, '22.580')] -[2023-10-15 04:07:58,878][88298] Updated weights for policy 0, policy_version 46540 (0.0008) -[2023-10-15 04:07:59,255][88298] Updated weights for policy 0, policy_version 46550 (0.0010) -[2023-10-15 04:07:59,622][88298] Updated weights for policy 0, policy_version 46560 (0.0009) -[2023-10-15 04:08:01,412][88300] Updated weights for policy 1, policy_version 46822 (0.0009) -[2023-10-15 04:08:01,779][88300] Updated weights for policy 1, policy_version 46832 (0.0009) -[2023-10-15 04:08:02,146][88300] Updated weights for policy 1, policy_version 46842 (0.0007) -[2023-10-15 04:08:03,417][88298] Updated weights for policy 0, policy_version 46570 (0.0008) -[2023-10-15 04:08:03,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 95649792. Throughput: 0: 1723.7, 1: 1761.3. Samples: 23917884. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:08:03,534][87330] Avg episode reward: [(0, '22.840'), (1, '22.540')] -[2023-10-15 04:08:03,776][88298] Updated weights for policy 0, policy_version 46580 (0.0010) -[2023-10-15 04:08:04,149][88298] Updated weights for policy 0, policy_version 46590 (0.0009) -[2023-10-15 04:08:06,086][88300] Updated weights for policy 1, policy_version 46852 (0.0008) -[2023-10-15 04:08:06,457][88300] Updated weights for policy 1, policy_version 46862 (0.0008) -[2023-10-15 04:08:06,823][88300] Updated weights for policy 1, policy_version 46872 (0.0010) -[2023-10-15 04:08:08,062][88298] Updated weights for policy 0, policy_version 46600 (0.0010) -[2023-10-15 04:08:08,431][88298] Updated weights for policy 0, policy_version 46610 (0.0008) -[2023-10-15 04:08:08,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 95715328. Throughput: 0: 1745.7, 1: 1724.0. Samples: 23937916. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:08:08,534][87330] Avg episode reward: [(0, '22.830'), (1, '22.520')] -[2023-10-15 04:08:08,793][88298] Updated weights for policy 0, policy_version 46620 (0.0007) -[2023-10-15 04:08:10,569][88300] Updated weights for policy 1, policy_version 46882 (0.0007) -[2023-10-15 04:08:10,940][88300] Updated weights for policy 1, policy_version 46892 (0.0010) -[2023-10-15 04:08:11,309][88300] Updated weights for policy 1, policy_version 46902 (0.0010) -[2023-10-15 04:08:11,678][88300] Updated weights for policy 1, policy_version 46912 (0.0007) -[2023-10-15 04:08:12,912][88298] Updated weights for policy 0, policy_version 46630 (0.0008) -[2023-10-15 04:08:13,275][88298] Updated weights for policy 0, policy_version 46640 (0.0009) -[2023-10-15 04:08:13,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 95780864. Throughput: 0: 1744.9, 1: 1726.0. Samples: 23959360. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:08:13,535][87330] Avg episode reward: [(0, '22.880'), (1, '22.330')] -[2023-10-15 04:08:13,646][88298] Updated weights for policy 0, policy_version 46650 (0.0009) -[2023-10-15 04:08:15,509][88300] Updated weights for policy 1, policy_version 46922 (0.0011) -[2023-10-15 04:08:15,867][88300] Updated weights for policy 1, policy_version 46932 (0.0010) -[2023-10-15 04:08:16,246][88300] Updated weights for policy 1, policy_version 46942 (0.0008) -[2023-10-15 04:08:17,602][88298] Updated weights for policy 0, policy_version 46660 (0.0008) -[2023-10-15 04:08:18,003][88298] Updated weights for policy 0, policy_version 46670 (0.0009) -[2023-10-15 04:08:18,367][88298] Updated weights for policy 0, policy_version 46680 (0.0008) -[2023-10-15 04:08:18,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 95846400. Throughput: 0: 1735.4, 1: 1734.1. Samples: 23969136. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:08:18,535][87330] Avg episode reward: [(0, '22.850'), (1, '22.460')] -[2023-10-15 04:08:20,100][88300] Updated weights for policy 1, policy_version 46952 (0.0009) -[2023-10-15 04:08:20,453][88300] Updated weights for policy 1, policy_version 46962 (0.0009) -[2023-10-15 04:08:20,829][88300] Updated weights for policy 1, policy_version 46972 (0.0010) -[2023-10-15 04:08:22,279][88298] Updated weights for policy 0, policy_version 46690 (0.0010) -[2023-10-15 04:08:22,643][88298] Updated weights for policy 0, policy_version 46700 (0.0010) -[2023-10-15 04:08:23,013][88298] Updated weights for policy 0, policy_version 46710 (0.0010) -[2023-10-15 04:08:23,386][88298] Updated weights for policy 0, policy_version 46720 (0.0008) -[2023-10-15 04:08:23,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 95944704. Throughput: 0: 1743.6, 1: 1729.2. Samples: 23990300. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:08:23,535][87330] Avg episode reward: [(0, '22.860'), (1, '22.580')] -[2023-10-15 04:08:24,858][88300] Updated weights for policy 1, policy_version 46982 (0.0009) -[2023-10-15 04:08:25,227][88300] Updated weights for policy 1, policy_version 46992 (0.0008) -[2023-10-15 04:08:25,599][88300] Updated weights for policy 1, policy_version 47002 (0.0008) -[2023-10-15 04:08:27,365][88298] Updated weights for policy 0, policy_version 46730 (0.0009) -[2023-10-15 04:08:27,742][88298] Updated weights for policy 0, policy_version 46740 (0.0009) -[2023-10-15 04:08:28,107][88298] Updated weights for policy 0, policy_version 46750 (0.0009) -[2023-10-15 04:08:28,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 96010240. Throughput: 0: 1721.4, 1: 1752.1. Samples: 24011222. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:08:28,534][87330] Avg episode reward: [(0, '22.710'), (1, '22.540')] -[2023-10-15 04:08:29,435][88300] Updated weights for policy 1, policy_version 47012 (0.0008) -[2023-10-15 04:08:29,806][88300] Updated weights for policy 1, policy_version 47022 (0.0009) -[2023-10-15 04:08:30,184][88300] Updated weights for policy 1, policy_version 47032 (0.0008) -[2023-10-15 04:08:31,954][88298] Updated weights for policy 0, policy_version 46760 (0.0009) -[2023-10-15 04:08:32,335][88298] Updated weights for policy 0, policy_version 46770 (0.0009) -[2023-10-15 04:08:32,705][88298] Updated weights for policy 0, policy_version 46780 (0.0008) -[2023-10-15 04:08:33,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 96075776. Throughput: 0: 1738.5, 1: 1733.1. Samples: 24021538. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:08:33,534][87330] Avg episode reward: [(0, '22.700'), (1, '22.540')] -[2023-10-15 04:08:34,070][88300] Updated weights for policy 1, policy_version 47042 (0.0008) -[2023-10-15 04:08:34,438][88300] Updated weights for policy 1, policy_version 47052 (0.0011) -[2023-10-15 04:08:34,796][88300] Updated weights for policy 1, policy_version 47062 (0.0010) -[2023-10-15 04:08:35,168][88300] Updated weights for policy 1, policy_version 47072 (0.0010) -[2023-10-15 04:08:36,707][88298] Updated weights for policy 0, policy_version 46790 (0.0009) -[2023-10-15 04:08:37,075][88298] Updated weights for policy 0, policy_version 46800 (0.0010) -[2023-10-15 04:08:37,442][88298] Updated weights for policy 0, policy_version 46810 (0.0009) -[2023-10-15 04:08:38,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 96141312. Throughput: 0: 1725.2, 1: 1739.9. Samples: 24042390. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) -[2023-10-15 04:08:38,535][87330] Avg episode reward: [(0, '22.630'), (1, '22.330')] -[2023-10-15 04:08:39,011][88300] Updated weights for policy 1, policy_version 47082 (0.0007) -[2023-10-15 04:08:39,371][88300] Updated weights for policy 1, policy_version 47092 (0.0007) -[2023-10-15 04:08:39,738][88300] Updated weights for policy 1, policy_version 47102 (0.0007) -[2023-10-15 04:08:41,288][88298] Updated weights for policy 0, policy_version 46820 (0.0010) -[2023-10-15 04:08:41,665][88298] Updated weights for policy 0, policy_version 46830 (0.0010) -[2023-10-15 04:08:42,025][88298] Updated weights for policy 0, policy_version 46840 (0.0007) -[2023-10-15 04:08:43,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 96206848. Throughput: 0: 1707.0, 1: 1768.4. Samples: 24063342. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) -[2023-10-15 04:08:43,534][87330] Avg episode reward: [(0, '22.610'), (1, '22.460')] -[2023-10-15 04:08:43,789][88300] Updated weights for policy 1, policy_version 47112 (0.0008) -[2023-10-15 04:08:44,157][88300] Updated weights for policy 1, policy_version 47122 (0.0009) -[2023-10-15 04:08:44,524][88300] Updated weights for policy 1, policy_version 47132 (0.0009) -[2023-10-15 04:08:45,750][88298] Updated weights for policy 0, policy_version 46850 (0.0009) -[2023-10-15 04:08:46,110][88298] Updated weights for policy 0, policy_version 46860 (0.0008) -[2023-10-15 04:08:46,471][88298] Updated weights for policy 0, policy_version 46870 (0.0008) -[2023-10-15 04:08:46,839][88298] Updated weights for policy 0, policy_version 46880 (0.0009) -[2023-10-15 04:08:48,398][88300] Updated weights for policy 1, policy_version 47142 (0.0009) -[2023-10-15 04:08:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 96272384. Throughput: 0: 1740.4, 1: 1733.5. Samples: 24074210. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) -[2023-10-15 04:08:48,534][87330] Avg episode reward: [(0, '22.620'), (1, '22.450')] -[2023-10-15 04:08:48,772][88300] Updated weights for policy 1, policy_version 47152 (0.0011) -[2023-10-15 04:08:49,150][88300] Updated weights for policy 1, policy_version 47162 (0.0009) -[2023-10-15 04:08:50,543][88298] Updated weights for policy 0, policy_version 46890 (0.0007) -[2023-10-15 04:08:50,914][88298] Updated weights for policy 0, policy_version 46900 (0.0007) -[2023-10-15 04:08:51,273][88298] Updated weights for policy 0, policy_version 46910 (0.0009) -[2023-10-15 04:08:52,994][88300] Updated weights for policy 1, policy_version 47172 (0.0009) -[2023-10-15 04:08:53,365][88300] Updated weights for policy 1, policy_version 47182 (0.0008) -[2023-10-15 04:08:53,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 96337920. Throughput: 0: 1720.8, 1: 1764.5. Samples: 24094752. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) -[2023-10-15 04:08:53,534][87330] Avg episode reward: [(0, '22.650'), (1, '22.220')] -[2023-10-15 04:08:53,720][88300] Updated weights for policy 1, policy_version 47192 (0.0008) -[2023-10-15 04:08:55,059][88298] Updated weights for policy 0, policy_version 46920 (0.0008) -[2023-10-15 04:08:55,426][88298] Updated weights for policy 0, policy_version 46930 (0.0007) -[2023-10-15 04:08:55,792][88298] Updated weights for policy 0, policy_version 46940 (0.0008) -[2023-10-15 04:08:57,585][88300] Updated weights for policy 1, policy_version 47202 (0.0008) -[2023-10-15 04:08:57,957][88300] Updated weights for policy 1, policy_version 47212 (0.0007) -[2023-10-15 04:08:58,322][88300] Updated weights for policy 1, policy_version 47222 (0.0007) -[2023-10-15 04:08:58,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 96403456. Throughput: 0: 1733.1, 1: 1747.3. Samples: 24115978. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) -[2023-10-15 04:08:58,535][87330] Avg episode reward: [(0, '22.650'), (1, '22.220')] -[2023-10-15 04:08:58,545][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000046944_48070656.pth... -[2023-10-15 04:08:58,580][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000045312_46399488.pth -[2023-10-15 04:08:58,678][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000047232_48365568.pth... -[2023-10-15 04:08:58,678][88300] Updated weights for policy 1, policy_version 47232 (0.0008) -[2023-10-15 04:08:58,706][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000045600_46694400.pth -[2023-10-15 04:08:59,594][88298] Updated weights for policy 0, policy_version 46950 (0.0007) -[2023-10-15 04:08:59,962][88298] Updated weights for policy 0, policy_version 46960 (0.0008) -[2023-10-15 04:09:00,334][88298] Updated weights for policy 0, policy_version 46970 (0.0008) -[2023-10-15 04:09:02,456][88300] Updated weights for policy 1, policy_version 47242 (0.0007) -[2023-10-15 04:09:02,819][88300] Updated weights for policy 1, policy_version 47252 (0.0007) -[2023-10-15 04:09:03,179][88300] Updated weights for policy 1, policy_version 47262 (0.0007) -[2023-10-15 04:09:03,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 96501760. Throughput: 0: 1731.2, 1: 1765.0. Samples: 24126462. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) -[2023-10-15 04:09:03,534][87330] Avg episode reward: [(0, '22.830'), (1, '22.190')] -[2023-10-15 04:09:04,503][88298] Updated weights for policy 0, policy_version 46980 (0.0008) -[2023-10-15 04:09:04,870][88298] Updated weights for policy 0, policy_version 46990 (0.0007) -[2023-10-15 04:09:05,254][88298] Updated weights for policy 0, policy_version 47000 (0.0011) -[2023-10-15 04:09:07,322][88300] Updated weights for policy 1, policy_version 47272 (0.0007) -[2023-10-15 04:09:07,685][88300] Updated weights for policy 1, policy_version 47282 (0.0007) -[2023-10-15 04:09:08,044][88300] Updated weights for policy 1, policy_version 47292 (0.0007) -[2023-10-15 04:09:08,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 96567296. Throughput: 0: 1730.1, 1: 1763.4. Samples: 24147510. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) -[2023-10-15 04:09:08,535][87330] Avg episode reward: [(0, '22.850'), (1, '22.240')] -[2023-10-15 04:09:09,304][88298] Updated weights for policy 0, policy_version 47010 (0.0011) -[2023-10-15 04:09:09,712][88298] Updated weights for policy 0, policy_version 47020 (0.0009) -[2023-10-15 04:09:10,078][88298] Updated weights for policy 0, policy_version 47030 (0.0007) -[2023-10-15 04:09:10,444][88298] Updated weights for policy 0, policy_version 47040 (0.0008) -[2023-10-15 04:09:11,946][88300] Updated weights for policy 1, policy_version 47302 (0.0008) -[2023-10-15 04:09:12,304][88300] Updated weights for policy 1, policy_version 47312 (0.0008) -[2023-10-15 04:09:12,683][88300] Updated weights for policy 1, policy_version 47322 (0.0009) -[2023-10-15 04:09:13,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 96632832. Throughput: 0: 1744.6, 1: 1735.3. Samples: 24167816. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:09:13,535][87330] Avg episode reward: [(0, '22.920'), (1, '22.370')] -[2023-10-15 04:09:14,525][88298] Updated weights for policy 0, policy_version 47050 (0.0007) -[2023-10-15 04:09:14,894][88298] Updated weights for policy 0, policy_version 47060 (0.0008) -[2023-10-15 04:09:15,270][88298] Updated weights for policy 0, policy_version 47070 (0.0007) -[2023-10-15 04:09:16,621][88300] Updated weights for policy 1, policy_version 47332 (0.0008) -[2023-10-15 04:09:16,991][88300] Updated weights for policy 1, policy_version 47342 (0.0008) -[2023-10-15 04:09:17,358][88300] Updated weights for policy 1, policy_version 47352 (0.0007) -[2023-10-15 04:09:18,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 96698368. Throughput: 0: 1722.7, 1: 1766.4. Samples: 24178548. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:09:18,535][87330] Avg episode reward: [(0, '22.860'), (1, '22.390')] -[2023-10-15 04:09:19,207][88298] Updated weights for policy 0, policy_version 47080 (0.0008) -[2023-10-15 04:09:19,577][88298] Updated weights for policy 0, policy_version 47090 (0.0008) -[2023-10-15 04:09:19,953][88298] Updated weights for policy 0, policy_version 47100 (0.0009) -[2023-10-15 04:09:21,191][88300] Updated weights for policy 1, policy_version 47362 (0.0008) -[2023-10-15 04:09:21,560][88300] Updated weights for policy 1, policy_version 47372 (0.0010) -[2023-10-15 04:09:21,925][88300] Updated weights for policy 1, policy_version 47382 (0.0010) -[2023-10-15 04:09:22,303][88300] Updated weights for policy 1, policy_version 47392 (0.0011) -[2023-10-15 04:09:23,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 96763904. Throughput: 0: 1738.6, 1: 1746.0. Samples: 24199196. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:09:23,534][87330] Avg episode reward: [(0, '22.820'), (1, '22.450')] -[2023-10-15 04:09:23,685][88298] Updated weights for policy 0, policy_version 47110 (0.0008) -[2023-10-15 04:09:24,047][88298] Updated weights for policy 0, policy_version 47120 (0.0009) -[2023-10-15 04:09:24,419][88298] Updated weights for policy 0, policy_version 47130 (0.0007) -[2023-10-15 04:09:26,088][88300] Updated weights for policy 1, policy_version 47402 (0.0007) -[2023-10-15 04:09:26,455][88300] Updated weights for policy 1, policy_version 47412 (0.0007) -[2023-10-15 04:09:26,817][88300] Updated weights for policy 1, policy_version 47422 (0.0007) -[2023-10-15 04:09:28,409][88298] Updated weights for policy 0, policy_version 47140 (0.0009) -[2023-10-15 04:09:28,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 96829440. Throughput: 0: 1762.6, 1: 1735.9. Samples: 24220776. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:09:28,534][87330] Avg episode reward: [(0, '22.820'), (1, '22.610')] -[2023-10-15 04:09:28,790][88298] Updated weights for policy 0, policy_version 47150 (0.0008) -[2023-10-15 04:09:29,159][88298] Updated weights for policy 0, policy_version 47160 (0.0009) -[2023-10-15 04:09:30,808][88300] Updated weights for policy 1, policy_version 47432 (0.0009) -[2023-10-15 04:09:31,192][88300] Updated weights for policy 1, policy_version 47442 (0.0009) -[2023-10-15 04:09:31,558][88300] Updated weights for policy 1, policy_version 47452 (0.0009) -[2023-10-15 04:09:32,988][88298] Updated weights for policy 0, policy_version 47170 (0.0007) -[2023-10-15 04:09:33,357][88298] Updated weights for policy 0, policy_version 47180 (0.0009) -[2023-10-15 04:09:33,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 96894976. Throughput: 0: 1726.8, 1: 1749.6. Samples: 24230648. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:09:33,534][87330] Avg episode reward: [(0, '22.840'), (1, '22.620')] -[2023-10-15 04:09:33,728][88298] Updated weights for policy 0, policy_version 47190 (0.0010) -[2023-10-15 04:09:34,097][88298] Updated weights for policy 0, policy_version 47200 (0.0007) -[2023-10-15 04:09:35,258][88300] Updated weights for policy 1, policy_version 47462 (0.0008) -[2023-10-15 04:09:35,618][88300] Updated weights for policy 1, policy_version 47472 (0.0008) -[2023-10-15 04:09:35,991][88300] Updated weights for policy 1, policy_version 47482 (0.0007) -[2023-10-15 04:09:38,008][88298] Updated weights for policy 0, policy_version 47210 (0.0008) -[2023-10-15 04:09:38,377][88298] Updated weights for policy 0, policy_version 47220 (0.0007) -[2023-10-15 04:09:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 96960512. Throughput: 0: 1748.8, 1: 1737.0. Samples: 24251614. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:09:38,534][87330] Avg episode reward: [(0, '22.820'), (1, '22.730')] -[2023-10-15 04:09:38,741][88298] Updated weights for policy 0, policy_version 47230 (0.0007) -[2023-10-15 04:09:40,032][88300] Updated weights for policy 1, policy_version 47492 (0.0009) -[2023-10-15 04:09:40,405][88300] Updated weights for policy 1, policy_version 47502 (0.0010) -[2023-10-15 04:09:40,767][88300] Updated weights for policy 1, policy_version 47512 (0.0011) -[2023-10-15 04:09:42,732][88298] Updated weights for policy 0, policy_version 47240 (0.0009) -[2023-10-15 04:09:43,113][88298] Updated weights for policy 0, policy_version 47250 (0.0008) -[2023-10-15 04:09:43,480][88298] Updated weights for policy 0, policy_version 47260 (0.0008) -[2023-10-15 04:09:43,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 97026048. Throughput: 0: 1738.1, 1: 1751.3. Samples: 24273000. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:09:43,535][87330] Avg episode reward: [(0, '22.840'), (1, '22.680')] -[2023-10-15 04:09:44,635][88300] Updated weights for policy 1, policy_version 47522 (0.0009) -[2023-10-15 04:09:45,002][88300] Updated weights for policy 1, policy_version 47532 (0.0009) -[2023-10-15 04:09:45,383][88300] Updated weights for policy 1, policy_version 47542 (0.0009) -[2023-10-15 04:09:45,747][88300] Updated weights for policy 1, policy_version 47552 (0.0008) -[2023-10-15 04:09:47,378][88298] Updated weights for policy 0, policy_version 47270 (0.0008) -[2023-10-15 04:09:47,743][88298] Updated weights for policy 0, policy_version 47280 (0.0009) -[2023-10-15 04:09:48,118][88298] Updated weights for policy 0, policy_version 47290 (0.0009) -[2023-10-15 04:09:48,534][87330] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 97124352. Throughput: 0: 1746.6, 1: 1730.0. Samples: 24282908. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-15 04:09:48,535][87330] Avg episode reward: [(0, '22.880'), (1, '22.400')] -[2023-10-15 04:09:49,736][88300] Updated weights for policy 1, policy_version 47562 (0.0009) -[2023-10-15 04:09:50,096][88300] Updated weights for policy 1, policy_version 47572 (0.0008) -[2023-10-15 04:09:50,464][88300] Updated weights for policy 1, policy_version 47582 (0.0012) -[2023-10-15 04:09:51,883][88298] Updated weights for policy 0, policy_version 47300 (0.0009) -[2023-10-15 04:09:52,260][88298] Updated weights for policy 0, policy_version 47310 (0.0009) -[2023-10-15 04:09:52,625][88298] Updated weights for policy 0, policy_version 47320 (0.0007) -[2023-10-15 04:09:53,534][87330] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 97189888. Throughput: 0: 1753.1, 1: 1734.6. Samples: 24304454. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-15 04:09:53,534][87330] Avg episode reward: [(0, '22.920'), (1, '22.360')] -[2023-10-15 04:09:54,291][88300] Updated weights for policy 1, policy_version 47592 (0.0008) -[2023-10-15 04:09:54,650][88300] Updated weights for policy 1, policy_version 47602 (0.0010) -[2023-10-15 04:09:55,035][88300] Updated weights for policy 1, policy_version 47612 (0.0009) -[2023-10-15 04:09:56,627][88298] Updated weights for policy 0, policy_version 47330 (0.0010) -[2023-10-15 04:09:57,035][88298] Updated weights for policy 0, policy_version 47340 (0.0009) -[2023-10-15 04:09:57,405][88298] Updated weights for policy 0, policy_version 47350 (0.0007) -[2023-10-15 04:09:57,783][88298] Updated weights for policy 0, policy_version 47360 (0.0007) -[2023-10-15 04:09:58,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 97255424. Throughput: 0: 1728.0, 1: 1761.8. Samples: 24324856. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-15 04:09:58,534][87330] Avg episode reward: [(0, '22.880'), (1, '22.070')] -[2023-10-15 04:09:58,880][88300] Updated weights for policy 1, policy_version 47622 (0.0011) -[2023-10-15 04:09:59,247][88300] Updated weights for policy 1, policy_version 47632 (0.0008) -[2023-10-15 04:09:59,613][88300] Updated weights for policy 1, policy_version 47642 (0.0008) -[2023-10-15 04:10:01,464][88298] Updated weights for policy 0, policy_version 47370 (0.0008) -[2023-10-15 04:10:01,835][88298] Updated weights for policy 0, policy_version 47380 (0.0009) -[2023-10-15 04:10:02,206][88298] Updated weights for policy 0, policy_version 47390 (0.0008) -[2023-10-15 04:10:03,416][88300] Updated weights for policy 1, policy_version 47652 (0.0008) -[2023-10-15 04:10:03,534][87330] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 97320960. Throughput: 0: 1760.7, 1: 1732.8. Samples: 24335752. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-15 04:10:03,535][87330] Avg episode reward: [(0, '22.710'), (1, '21.670')] -[2023-10-15 04:10:03,777][88300] Updated weights for policy 1, policy_version 47662 (0.0008) -[2023-10-15 04:10:04,156][88300] Updated weights for policy 1, policy_version 47672 (0.0010) -[2023-10-15 04:10:05,948][88298] Updated weights for policy 0, policy_version 47400 (0.0007) -[2023-10-15 04:10:06,315][88298] Updated weights for policy 0, policy_version 47410 (0.0009) -[2023-10-15 04:10:06,687][88298] Updated weights for policy 0, policy_version 47420 (0.0008) -[2023-10-15 04:10:07,933][88300] Updated weights for policy 1, policy_version 47682 (0.0007) -[2023-10-15 04:10:08,303][88300] Updated weights for policy 1, policy_version 47692 (0.0009) -[2023-10-15 04:10:08,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13995.8). Total num frames: 97386496. Throughput: 0: 1733.9, 1: 1762.3. Samples: 24356526. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-15 04:10:08,534][87330] Avg episode reward: [(0, '22.700'), (1, '21.650')] -[2023-10-15 04:10:08,673][88300] Updated weights for policy 1, policy_version 47702 (0.0010) -[2023-10-15 04:10:09,050][88300] Updated weights for policy 1, policy_version 47712 (0.0008) -[2023-10-15 04:10:10,710][88298] Updated weights for policy 0, policy_version 47430 (0.0009) -[2023-10-15 04:10:11,067][88298] Updated weights for policy 0, policy_version 47440 (0.0007) -[2023-10-15 04:10:11,440][88298] Updated weights for policy 0, policy_version 47450 (0.0007) -[2023-10-15 04:10:12,984][88300] Updated weights for policy 1, policy_version 47722 (0.0009) -[2023-10-15 04:10:13,357][88300] Updated weights for policy 1, policy_version 47732 (0.0010) -[2023-10-15 04:10:13,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 97452032. Throughput: 0: 1729.0, 1: 1749.4. Samples: 24377304. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-15 04:10:13,535][87330] Avg episode reward: [(0, '22.710'), (1, '21.820')] -[2023-10-15 04:10:13,726][88300] Updated weights for policy 1, policy_version 47742 (0.0008) -[2023-10-15 04:10:15,307][88298] Updated weights for policy 0, policy_version 47460 (0.0008) -[2023-10-15 04:10:15,672][88298] Updated weights for policy 0, policy_version 47470 (0.0008) -[2023-10-15 04:10:16,035][88298] Updated weights for policy 0, policy_version 47480 (0.0008) -[2023-10-15 04:10:17,386][88300] Updated weights for policy 1, policy_version 47752 (0.0010) -[2023-10-15 04:10:17,759][88300] Updated weights for policy 1, policy_version 47762 (0.0009) -[2023-10-15 04:10:18,121][88300] Updated weights for policy 1, policy_version 47772 (0.0010) -[2023-10-15 04:10:18,534][87330] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 97550336. Throughput: 0: 1748.1, 1: 1757.4. Samples: 24388396. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-15 04:10:18,535][87330] Avg episode reward: [(0, '22.710'), (1, '22.080')] -[2023-10-15 04:10:20,001][88298] Updated weights for policy 0, policy_version 47490 (0.0008) -[2023-10-15 04:10:20,379][88298] Updated weights for policy 0, policy_version 47500 (0.0008) -[2023-10-15 04:10:20,749][88298] Updated weights for policy 0, policy_version 47510 (0.0008) -[2023-10-15 04:10:21,118][88298] Updated weights for policy 0, policy_version 47520 (0.0008) -[2023-10-15 04:10:22,076][88300] Updated weights for policy 1, policy_version 47782 (0.0009) -[2023-10-15 04:10:22,449][88300] Updated weights for policy 1, policy_version 47792 (0.0008) -[2023-10-15 04:10:22,825][88300] Updated weights for policy 1, policy_version 47802 (0.0009) -[2023-10-15 04:10:23,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 97615872. Throughput: 0: 1728.7, 1: 1759.1. Samples: 24408562. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-15 04:10:23,535][87330] Avg episode reward: [(0, '22.730'), (1, '22.070')] -[2023-10-15 04:10:24,897][88298] Updated weights for policy 0, policy_version 47530 (0.0007) -[2023-10-15 04:10:25,263][88298] Updated weights for policy 0, policy_version 47540 (0.0008) -[2023-10-15 04:10:25,622][88298] Updated weights for policy 0, policy_version 47550 (0.0007) -[2023-10-15 04:10:26,701][88300] Updated weights for policy 1, policy_version 47812 (0.0008) -[2023-10-15 04:10:27,078][88300] Updated weights for policy 1, policy_version 47822 (0.0007) -[2023-10-15 04:10:27,443][88300] Updated weights for policy 1, policy_version 47832 (0.0010) -[2023-10-15 04:10:28,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 97681408. Throughput: 0: 1737.4, 1: 1738.2. Samples: 24429402. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-15 04:10:28,534][87330] Avg episode reward: [(0, '22.770'), (1, '22.320')] -[2023-10-15 04:10:29,595][88298] Updated weights for policy 0, policy_version 47560 (0.0008) -[2023-10-15 04:10:29,975][88298] Updated weights for policy 0, policy_version 47570 (0.0009) -[2023-10-15 04:10:30,345][88298] Updated weights for policy 0, policy_version 47580 (0.0009) -[2023-10-15 04:10:31,297][88300] Updated weights for policy 1, policy_version 47842 (0.0009) -[2023-10-15 04:10:31,659][88300] Updated weights for policy 1, policy_version 47852 (0.0007) -[2023-10-15 04:10:32,021][88300] Updated weights for policy 1, policy_version 47862 (0.0007) -[2023-10-15 04:10:32,383][88300] Updated weights for policy 1, policy_version 47872 (0.0007) -[2023-10-15 04:10:33,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 97746944. Throughput: 0: 1728.0, 1: 1767.9. Samples: 24440222. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-15 04:10:33,534][87330] Avg episode reward: [(0, '22.770'), (1, '22.600')] -[2023-10-15 04:10:34,165][88298] Updated weights for policy 0, policy_version 47590 (0.0009) -[2023-10-15 04:10:34,532][88298] Updated weights for policy 0, policy_version 47600 (0.0008) -[2023-10-15 04:10:34,907][88298] Updated weights for policy 0, policy_version 47610 (0.0007) -[2023-10-15 04:10:36,353][88300] Updated weights for policy 1, policy_version 47882 (0.0009) -[2023-10-15 04:10:36,725][88300] Updated weights for policy 1, policy_version 47892 (0.0009) -[2023-10-15 04:10:37,093][88300] Updated weights for policy 1, policy_version 47902 (0.0008) -[2023-10-15 04:10:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 97812480. Throughput: 0: 1728.8, 1: 1738.9. Samples: 24460500. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-15 04:10:38,534][87330] Avg episode reward: [(0, '22.910'), (1, '22.700')] -[2023-10-15 04:10:38,917][88298] Updated weights for policy 0, policy_version 47620 (0.0009) -[2023-10-15 04:10:39,287][88298] Updated weights for policy 0, policy_version 47630 (0.0010) -[2023-10-15 04:10:39,665][88298] Updated weights for policy 0, policy_version 47640 (0.0009) -[2023-10-15 04:10:40,880][88300] Updated weights for policy 1, policy_version 47912 (0.0008) -[2023-10-15 04:10:41,250][88300] Updated weights for policy 1, policy_version 47922 (0.0009) -[2023-10-15 04:10:41,618][88300] Updated weights for policy 1, policy_version 47932 (0.0010) -[2023-10-15 04:10:43,482][88298] Updated weights for policy 0, policy_version 47650 (0.0009) -[2023-10-15 04:10:43,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 97878016. Throughput: 0: 1758.5, 1: 1738.4. Samples: 24482220. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-15 04:10:43,534][87330] Avg episode reward: [(0, '22.900'), (1, '22.650')] -[2023-10-15 04:10:43,854][88298] Updated weights for policy 0, policy_version 47660 (0.0009) -[2023-10-15 04:10:44,238][88298] Updated weights for policy 0, policy_version 47670 (0.0009) -[2023-10-15 04:10:44,597][88298] Updated weights for policy 0, policy_version 47680 (0.0009) -[2023-10-15 04:10:45,473][88300] Updated weights for policy 1, policy_version 47942 (0.0008) -[2023-10-15 04:10:45,841][88300] Updated weights for policy 1, policy_version 47952 (0.0007) -[2023-10-15 04:10:46,206][88300] Updated weights for policy 1, policy_version 47962 (0.0008) -[2023-10-15 04:10:48,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 97943552. Throughput: 0: 1727.4, 1: 1744.9. Samples: 24492006. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-15 04:10:48,534][87330] Avg episode reward: [(0, '22.910'), (1, '22.480')] -[2023-10-15 04:10:48,625][88298] Updated weights for policy 0, policy_version 47690 (0.0009) -[2023-10-15 04:10:48,992][88298] Updated weights for policy 0, policy_version 47700 (0.0008) -[2023-10-15 04:10:49,362][88298] Updated weights for policy 0, policy_version 47710 (0.0008) -[2023-10-15 04:10:50,027][88300] Updated weights for policy 1, policy_version 47972 (0.0009) -[2023-10-15 04:10:50,399][88300] Updated weights for policy 1, policy_version 47982 (0.0007) -[2023-10-15 04:10:50,771][88300] Updated weights for policy 1, policy_version 47992 (0.0008) -[2023-10-15 04:10:53,232][88298] Updated weights for policy 0, policy_version 47720 (0.0008) -[2023-10-15 04:10:53,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 98009088. Throughput: 0: 1747.4, 1: 1735.0. Samples: 24513232. Policy #0 lag: (min: 9.0, avg: 16.8, max: 41.0) -[2023-10-15 04:10:53,535][87330] Avg episode reward: [(0, '22.900'), (1, '22.420')] -[2023-10-15 04:10:53,607][88298] Updated weights for policy 0, policy_version 47730 (0.0008) -[2023-10-15 04:10:53,975][88298] Updated weights for policy 0, policy_version 47740 (0.0009) -[2023-10-15 04:10:54,690][88300] Updated weights for policy 1, policy_version 48002 (0.0008) -[2023-10-15 04:10:55,053][88300] Updated weights for policy 1, policy_version 48012 (0.0008) -[2023-10-15 04:10:55,433][88300] Updated weights for policy 1, policy_version 48022 (0.0011) -[2023-10-15 04:10:55,804][88300] Updated weights for policy 1, policy_version 48032 (0.0010) -[2023-10-15 04:10:57,860][88298] Updated weights for policy 0, policy_version 47750 (0.0009) -[2023-10-15 04:10:58,236][88298] Updated weights for policy 0, policy_version 47760 (0.0009) -[2023-10-15 04:10:58,534][87330] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 98074624. Throughput: 0: 1747.3, 1: 1757.6. Samples: 24535028. Policy #0 lag: (min: 9.0, avg: 16.8, max: 41.0) -[2023-10-15 04:10:58,535][87330] Avg episode reward: [(0, '22.920'), (1, '22.330')] -[2023-10-15 04:10:58,544][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000048032_49184768.pth... -[2023-10-15 04:10:58,578][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000046400_47513600.pth -[2023-10-15 04:10:58,611][88298] Updated weights for policy 0, policy_version 47770 (0.0010) -[2023-10-15 04:10:58,825][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000047776_48922624.pth... -[2023-10-15 04:10:58,854][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000046144_47251456.pth -[2023-10-15 04:10:59,570][88300] Updated weights for policy 1, policy_version 48042 (0.0009) -[2023-10-15 04:10:59,937][88300] Updated weights for policy 1, policy_version 48052 (0.0010) -[2023-10-15 04:11:00,312][88300] Updated weights for policy 1, policy_version 48062 (0.0008) -[2023-10-15 04:11:02,651][88298] Updated weights for policy 0, policy_version 47780 (0.0008) -[2023-10-15 04:11:03,029][88298] Updated weights for policy 0, policy_version 47790 (0.0007) -[2023-10-15 04:11:03,403][88298] Updated weights for policy 0, policy_version 47800 (0.0008) -[2023-10-15 04:11:03,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 98140160. Throughput: 0: 1732.5, 1: 1736.6. Samples: 24544502. Policy #0 lag: (min: 9.0, avg: 16.8, max: 41.0) -[2023-10-15 04:11:03,534][87330] Avg episode reward: [(0, '22.910'), (1, '22.310')] -[2023-10-15 04:11:04,224][88300] Updated weights for policy 1, policy_version 48072 (0.0010) -[2023-10-15 04:11:04,589][88300] Updated weights for policy 1, policy_version 48082 (0.0007) -[2023-10-15 04:11:04,959][88300] Updated weights for policy 1, policy_version 48092 (0.0007) -[2023-10-15 04:11:07,409][88298] Updated weights for policy 0, policy_version 47810 (0.0007) -[2023-10-15 04:11:07,789][88298] Updated weights for policy 0, policy_version 47820 (0.0009) -[2023-10-15 04:11:08,158][88298] Updated weights for policy 0, policy_version 47830 (0.0008) -[2023-10-15 04:11:08,529][88298] Updated weights for policy 0, policy_version 47840 (0.0008) -[2023-10-15 04:11:08,534][87330] Fps is (10 sec: 16384.6, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 98238464. Throughput: 0: 1745.1, 1: 1754.7. Samples: 24566052. Policy #0 lag: (min: 9.0, avg: 16.8, max: 41.0) -[2023-10-15 04:11:08,534][87330] Avg episode reward: [(0, '22.900'), (1, '22.210')] -[2023-10-15 04:11:08,721][88300] Updated weights for policy 1, policy_version 48102 (0.0008) -[2023-10-15 04:11:09,086][88300] Updated weights for policy 1, policy_version 48112 (0.0008) -[2023-10-15 04:11:09,454][88300] Updated weights for policy 1, policy_version 48122 (0.0008) -[2023-10-15 04:11:12,368][88298] Updated weights for policy 0, policy_version 47850 (0.0009) -[2023-10-15 04:11:12,732][88298] Updated weights for policy 0, policy_version 47860 (0.0008) -[2023-10-15 04:11:13,107][88298] Updated weights for policy 0, policy_version 47870 (0.0009) -[2023-10-15 04:11:13,473][88300] Updated weights for policy 1, policy_version 48132 (0.0009) -[2023-10-15 04:11:13,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 98304000. Throughput: 0: 1724.8, 1: 1776.4. Samples: 24586954. Policy #0 lag: (min: 9.0, avg: 16.8, max: 41.0) -[2023-10-15 04:11:13,535][87330] Avg episode reward: [(0, '22.940'), (1, '22.220')] -[2023-10-15 04:11:13,844][88300] Updated weights for policy 1, policy_version 48142 (0.0008) -[2023-10-15 04:11:14,213][88300] Updated weights for policy 1, policy_version 48152 (0.0009) -[2023-10-15 04:11:17,168][88298] Updated weights for policy 0, policy_version 47880 (0.0007) -[2023-10-15 04:11:17,542][88298] Updated weights for policy 0, policy_version 47890 (0.0009) -[2023-10-15 04:11:17,913][88298] Updated weights for policy 0, policy_version 47900 (0.0007) -[2023-10-15 04:11:18,088][88300] Updated weights for policy 1, policy_version 48162 (0.0008) -[2023-10-15 04:11:18,456][88300] Updated weights for policy 1, policy_version 48172 (0.0008) -[2023-10-15 04:11:18,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13995.8). Total num frames: 98369536. Throughput: 0: 1742.8, 1: 1745.4. Samples: 24597188. Policy #0 lag: (min: 9.0, avg: 16.8, max: 41.0) -[2023-10-15 04:11:18,534][87330] Avg episode reward: [(0, '22.970'), (1, '22.270')] -[2023-10-15 04:11:18,813][88300] Updated weights for policy 1, policy_version 48182 (0.0009) -[2023-10-15 04:11:19,178][88300] Updated weights for policy 1, policy_version 48192 (0.0009) -[2023-10-15 04:11:21,782][88298] Updated weights for policy 0, policy_version 47910 (0.0008) -[2023-10-15 04:11:22,163][88298] Updated weights for policy 0, policy_version 47920 (0.0009) -[2023-10-15 04:11:22,529][88298] Updated weights for policy 0, policy_version 47930 (0.0008) -[2023-10-15 04:11:23,064][88300] Updated weights for policy 1, policy_version 48202 (0.0008) -[2023-10-15 04:11:23,430][88300] Updated weights for policy 1, policy_version 48212 (0.0009) -[2023-10-15 04:11:23,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 98435072. Throughput: 0: 1734.1, 1: 1778.3. Samples: 24618558. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-10-15 04:11:23,535][87330] Avg episode reward: [(0, '22.880'), (1, '22.520')] -[2023-10-15 04:11:23,809][88300] Updated weights for policy 1, policy_version 48222 (0.0009) -[2023-10-15 04:11:26,510][88298] Updated weights for policy 0, policy_version 47940 (0.0007) -[2023-10-15 04:11:26,894][88298] Updated weights for policy 0, policy_version 47950 (0.0009) -[2023-10-15 04:11:27,265][88298] Updated weights for policy 0, policy_version 47960 (0.0008) -[2023-10-15 04:11:27,704][88300] Updated weights for policy 1, policy_version 48232 (0.0007) -[2023-10-15 04:11:28,073][88300] Updated weights for policy 1, policy_version 48242 (0.0007) -[2023-10-15 04:11:28,450][88300] Updated weights for policy 1, policy_version 48252 (0.0007) -[2023-10-15 04:11:28,534][87330] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 98500608. Throughput: 0: 1705.8, 1: 1755.6. Samples: 24637986. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-10-15 04:11:28,535][87330] Avg episode reward: [(0, '22.860'), (1, '22.680')] -[2023-10-15 04:11:31,188][88298] Updated weights for policy 0, policy_version 47970 (0.0009) -[2023-10-15 04:11:31,610][88298] Updated weights for policy 0, policy_version 47980 (0.0009) -[2023-10-15 04:11:31,981][88298] Updated weights for policy 0, policy_version 47990 (0.0008) -[2023-10-15 04:11:32,224][88300] Updated weights for policy 1, policy_version 48262 (0.0007) -[2023-10-15 04:11:32,348][88298] Updated weights for policy 0, policy_version 48000 (0.0007) -[2023-10-15 04:11:32,596][88300] Updated weights for policy 1, policy_version 48272 (0.0007) -[2023-10-15 04:11:32,970][88300] Updated weights for policy 1, policy_version 48282 (0.0007) -[2023-10-15 04:11:33,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 98598912. Throughput: 0: 1734.5, 1: 1769.6. Samples: 24649694. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-10-15 04:11:33,535][87330] Avg episode reward: [(0, '22.870'), (1, '22.730')] -[2023-10-15 04:11:36,121][88298] Updated weights for policy 0, policy_version 48010 (0.0009) -[2023-10-15 04:11:36,499][88298] Updated weights for policy 0, policy_version 48020 (0.0009) -[2023-10-15 04:11:36,865][88298] Updated weights for policy 0, policy_version 48030 (0.0008) -[2023-10-15 04:11:36,981][88300] Updated weights for policy 1, policy_version 48292 (0.0008) -[2023-10-15 04:11:37,339][88300] Updated weights for policy 1, policy_version 48302 (0.0007) -[2023-10-15 04:11:37,714][88300] Updated weights for policy 1, policy_version 48312 (0.0008) -[2023-10-15 04:11:38,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 98664448. Throughput: 0: 1705.4, 1: 1763.0. Samples: 24669310. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-10-15 04:11:38,535][87330] Avg episode reward: [(0, '22.870'), (1, '22.650')] -[2023-10-15 04:11:40,954][88298] Updated weights for policy 0, policy_version 48040 (0.0008) -[2023-10-15 04:11:41,336][88298] Updated weights for policy 0, policy_version 48050 (0.0008) -[2023-10-15 04:11:41,589][88300] Updated weights for policy 1, policy_version 48322 (0.0008) -[2023-10-15 04:11:41,703][88298] Updated weights for policy 0, policy_version 48060 (0.0009) -[2023-10-15 04:11:41,949][88300] Updated weights for policy 1, policy_version 48332 (0.0009) -[2023-10-15 04:11:42,320][88300] Updated weights for policy 1, policy_version 48342 (0.0011) -[2023-10-15 04:11:42,680][88300] Updated weights for policy 1, policy_version 48352 (0.0007) -[2023-10-15 04:11:43,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 98729984. Throughput: 0: 1706.5, 1: 1734.5. Samples: 24689872. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-10-15 04:11:43,535][87330] Avg episode reward: [(0, '22.850'), (1, '22.790')] -[2023-10-15 04:11:45,690][88298] Updated weights for policy 0, policy_version 48070 (0.0010) -[2023-10-15 04:11:46,055][88298] Updated weights for policy 0, policy_version 48080 (0.0009) -[2023-10-15 04:11:46,429][88298] Updated weights for policy 0, policy_version 48090 (0.0008) -[2023-10-15 04:11:46,454][88300] Updated weights for policy 1, policy_version 48362 (0.0009) -[2023-10-15 04:11:46,816][88300] Updated weights for policy 1, policy_version 48372 (0.0007) -[2023-10-15 04:11:47,197][88300] Updated weights for policy 1, policy_version 48382 (0.0011) -[2023-10-15 04:11:48,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 98795520. Throughput: 0: 1725.7, 1: 1767.0. Samples: 24701676. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-10-15 04:11:48,534][87330] Avg episode reward: [(0, '22.840'), (1, '22.870')] -[2023-10-15 04:11:50,358][88298] Updated weights for policy 0, policy_version 48100 (0.0008) -[2023-10-15 04:11:50,722][88298] Updated weights for policy 0, policy_version 48110 (0.0007) -[2023-10-15 04:11:51,097][88298] Updated weights for policy 0, policy_version 48120 (0.0007) -[2023-10-15 04:11:51,237][88300] Updated weights for policy 1, policy_version 48392 (0.0009) -[2023-10-15 04:11:51,607][88300] Updated weights for policy 1, policy_version 48402 (0.0010) -[2023-10-15 04:11:51,978][88300] Updated weights for policy 1, policy_version 48412 (0.0010) -[2023-10-15 04:11:53,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 98861056. Throughput: 0: 1709.6, 1: 1729.7. Samples: 24720818. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-10-15 04:11:53,534][87330] Avg episode reward: [(0, '22.850'), (1, '22.710')] -[2023-10-15 04:11:54,913][88298] Updated weights for policy 0, policy_version 48130 (0.0008) -[2023-10-15 04:11:55,278][88298] Updated weights for policy 0, policy_version 48140 (0.0009) -[2023-10-15 04:11:55,648][88298] Updated weights for policy 0, policy_version 48150 (0.0007) -[2023-10-15 04:11:55,911][88300] Updated weights for policy 1, policy_version 48422 (0.0009) -[2023-10-15 04:11:56,023][88298] Updated weights for policy 0, policy_version 48160 (0.0008) -[2023-10-15 04:11:56,281][88300] Updated weights for policy 1, policy_version 48432 (0.0010) -[2023-10-15 04:11:56,648][88300] Updated weights for policy 1, policy_version 48442 (0.0007) -[2023-10-15 04:11:58,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 98926592. Throughput: 0: 1730.0, 1: 1725.9. Samples: 24742470. Policy #0 lag: (min: 10.0, avg: 11.9, max: 40.0) -[2023-10-15 04:11:58,534][87330] Avg episode reward: [(0, '22.850'), (1, '21.980')] -[2023-10-15 04:11:59,707][88298] Updated weights for policy 0, policy_version 48170 (0.0007) -[2023-10-15 04:12:00,080][88298] Updated weights for policy 0, policy_version 48180 (0.0007) -[2023-10-15 04:12:00,449][88298] Updated weights for policy 0, policy_version 48190 (0.0007) -[2023-10-15 04:12:00,495][88300] Updated weights for policy 1, policy_version 48452 (0.0008) -[2023-10-15 04:12:00,861][88300] Updated weights for policy 1, policy_version 48462 (0.0010) -[2023-10-15 04:12:01,226][88300] Updated weights for policy 1, policy_version 48472 (0.0009) -[2023-10-15 04:12:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 98992128. Throughput: 0: 1715.5, 1: 1737.7. Samples: 24752582. Policy #0 lag: (min: 10.0, avg: 11.9, max: 40.0) -[2023-10-15 04:12:03,534][87330] Avg episode reward: [(0, '22.840'), (1, '21.950')] -[2023-10-15 04:12:04,265][88298] Updated weights for policy 0, policy_version 48200 (0.0007) -[2023-10-15 04:12:04,642][88298] Updated weights for policy 0, policy_version 48210 (0.0011) -[2023-10-15 04:12:04,962][88300] Updated weights for policy 1, policy_version 48482 (0.0009) -[2023-10-15 04:12:05,008][88298] Updated weights for policy 0, policy_version 48220 (0.0008) -[2023-10-15 04:12:05,332][88300] Updated weights for policy 1, policy_version 48492 (0.0010) -[2023-10-15 04:12:05,702][88300] Updated weights for policy 1, policy_version 48502 (0.0008) -[2023-10-15 04:12:06,063][88300] Updated weights for policy 1, policy_version 48512 (0.0007) -[2023-10-15 04:12:08,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 99057664. Throughput: 0: 1728.5, 1: 1726.4. Samples: 24774024. Policy #0 lag: (min: 10.0, avg: 11.9, max: 40.0) -[2023-10-15 04:12:08,534][87330] Avg episode reward: [(0, '22.810'), (1, '21.890')] -[2023-10-15 04:12:08,790][88298] Updated weights for policy 0, policy_version 48230 (0.0008) -[2023-10-15 04:12:09,169][88298] Updated weights for policy 0, policy_version 48240 (0.0008) -[2023-10-15 04:12:09,538][88298] Updated weights for policy 0, policy_version 48250 (0.0009) -[2023-10-15 04:12:09,912][88300] Updated weights for policy 1, policy_version 48522 (0.0009) -[2023-10-15 04:12:10,278][88300] Updated weights for policy 1, policy_version 48532 (0.0009) -[2023-10-15 04:12:10,651][88300] Updated weights for policy 1, policy_version 48542 (0.0009) -[2023-10-15 04:12:13,186][88298] Updated weights for policy 0, policy_version 48260 (0.0009) -[2023-10-15 04:12:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 99123200. Throughput: 0: 1759.6, 1: 1745.8. Samples: 24795726. Policy #0 lag: (min: 10.0, avg: 11.9, max: 40.0) -[2023-10-15 04:12:13,534][87330] Avg episode reward: [(0, '22.820'), (1, '21.920')] -[2023-10-15 04:12:13,562][88298] Updated weights for policy 0, policy_version 48270 (0.0007) -[2023-10-15 04:12:13,929][88298] Updated weights for policy 0, policy_version 48280 (0.0008) -[2023-10-15 04:12:14,576][88300] Updated weights for policy 1, policy_version 48552 (0.0011) -[2023-10-15 04:12:14,938][88300] Updated weights for policy 1, policy_version 48562 (0.0008) -[2023-10-15 04:12:15,312][88300] Updated weights for policy 1, policy_version 48572 (0.0010) -[2023-10-15 04:12:17,925][88298] Updated weights for policy 0, policy_version 48290 (0.0008) -[2023-10-15 04:12:18,347][88298] Updated weights for policy 0, policy_version 48300 (0.0007) -[2023-10-15 04:12:18,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 99188736. Throughput: 0: 1734.0, 1: 1723.1. Samples: 24805260. Policy #0 lag: (min: 10.0, avg: 11.9, max: 40.0) -[2023-10-15 04:12:18,535][87330] Avg episode reward: [(0, '22.780'), (1, '21.920')] -[2023-10-15 04:12:18,710][88298] Updated weights for policy 0, policy_version 48310 (0.0007) -[2023-10-15 04:12:19,085][88298] Updated weights for policy 0, policy_version 48320 (0.0007) -[2023-10-15 04:12:19,147][88300] Updated weights for policy 1, policy_version 48582 (0.0008) -[2023-10-15 04:12:19,507][88300] Updated weights for policy 1, policy_version 48592 (0.0010) -[2023-10-15 04:12:19,875][88300] Updated weights for policy 1, policy_version 48602 (0.0010) -[2023-10-15 04:12:23,030][88298] Updated weights for policy 0, policy_version 48330 (0.0007) -[2023-10-15 04:12:23,402][88298] Updated weights for policy 0, policy_version 48340 (0.0010) -[2023-10-15 04:12:23,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 99254272. Throughput: 0: 1767.4, 1: 1734.2. Samples: 24826884. Policy #0 lag: (min: 10.0, avg: 11.9, max: 40.0) -[2023-10-15 04:12:23,535][87330] Avg episode reward: [(0, '22.760'), (1, '22.070')] -[2023-10-15 04:12:23,774][88298] Updated weights for policy 0, policy_version 48350 (0.0009) -[2023-10-15 04:12:23,799][88300] Updated weights for policy 1, policy_version 48612 (0.0009) -[2023-10-15 04:12:24,166][88300] Updated weights for policy 1, policy_version 48622 (0.0009) -[2023-10-15 04:12:24,534][88300] Updated weights for policy 1, policy_version 48632 (0.0009) -[2023-10-15 04:12:27,904][88298] Updated weights for policy 0, policy_version 48360 (0.0009) -[2023-10-15 04:12:28,279][88298] Updated weights for policy 0, policy_version 48370 (0.0009) -[2023-10-15 04:12:28,360][88300] Updated weights for policy 1, policy_version 48642 (0.0008) -[2023-10-15 04:12:28,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 99319808. Throughput: 0: 1761.1, 1: 1761.3. Samples: 24848378. Policy #0 lag: (min: 10.0, avg: 11.9, max: 40.0) -[2023-10-15 04:12:28,534][87330] Avg episode reward: [(0, '22.870'), (1, '22.600')] -[2023-10-15 04:12:28,649][88298] Updated weights for policy 0, policy_version 48380 (0.0007) -[2023-10-15 04:12:28,723][88300] Updated weights for policy 1, policy_version 48652 (0.0009) -[2023-10-15 04:12:29,085][88300] Updated weights for policy 1, policy_version 48662 (0.0010) -[2023-10-15 04:12:29,448][88300] Updated weights for policy 1, policy_version 48672 (0.0011) -[2023-10-15 04:12:32,437][88298] Updated weights for policy 0, policy_version 48390 (0.0008) -[2023-10-15 04:12:32,801][88298] Updated weights for policy 0, policy_version 48400 (0.0009) -[2023-10-15 04:12:33,169][88298] Updated weights for policy 0, policy_version 48410 (0.0010) -[2023-10-15 04:12:33,432][88300] Updated weights for policy 1, policy_version 48682 (0.0007) -[2023-10-15 04:12:33,534][87330] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13995.8). Total num frames: 99418112. Throughput: 0: 1744.9, 1: 1727.7. Samples: 24857944. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:12:33,534][87330] Avg episode reward: [(0, '22.840'), (1, '22.820')] -[2023-10-15 04:12:33,796][88300] Updated weights for policy 1, policy_version 48692 (0.0008) -[2023-10-15 04:12:34,156][88300] Updated weights for policy 1, policy_version 48702 (0.0007) -[2023-10-15 04:12:37,214][88298] Updated weights for policy 0, policy_version 48420 (0.0008) -[2023-10-15 04:12:37,585][88298] Updated weights for policy 0, policy_version 48430 (0.0008) -[2023-10-15 04:12:37,960][88298] Updated weights for policy 0, policy_version 48440 (0.0008) -[2023-10-15 04:12:38,069][88300] Updated weights for policy 1, policy_version 48712 (0.0009) -[2023-10-15 04:12:38,442][88300] Updated weights for policy 1, policy_version 48722 (0.0010) -[2023-10-15 04:12:38,534][87330] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 99483648. Throughput: 0: 1765.7, 1: 1761.9. Samples: 24879564. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:12:38,535][87330] Avg episode reward: [(0, '22.870'), (1, '22.840')] -[2023-10-15 04:12:38,799][88300] Updated weights for policy 1, policy_version 48732 (0.0010) -[2023-10-15 04:12:41,738][88298] Updated weights for policy 0, policy_version 48450 (0.0009) -[2023-10-15 04:12:42,110][88298] Updated weights for policy 0, policy_version 48460 (0.0008) -[2023-10-15 04:12:42,488][88298] Updated weights for policy 0, policy_version 48470 (0.0007) -[2023-10-15 04:12:42,685][88300] Updated weights for policy 1, policy_version 48742 (0.0008) -[2023-10-15 04:12:42,852][88298] Updated weights for policy 0, policy_version 48480 (0.0007) -[2023-10-15 04:12:43,049][88300] Updated weights for policy 1, policy_version 48752 (0.0009) -[2023-10-15 04:12:43,417][88300] Updated weights for policy 1, policy_version 48762 (0.0009) -[2023-10-15 04:12:43,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 99549184. Throughput: 0: 1738.1, 1: 1745.2. Samples: 24899218. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:12:43,534][87330] Avg episode reward: [(0, '22.870'), (1, '22.960')] -[2023-10-15 04:12:43,637][88033] Saving new best policy, reward=22.960! -[2023-10-15 04:12:46,798][88298] Updated weights for policy 0, policy_version 48490 (0.0010) -[2023-10-15 04:12:47,169][88298] Updated weights for policy 0, policy_version 48500 (0.0007) -[2023-10-15 04:12:47,392][88300] Updated weights for policy 1, policy_version 48772 (0.0007) -[2023-10-15 04:12:47,541][88298] Updated weights for policy 0, policy_version 48510 (0.0009) -[2023-10-15 04:12:47,760][88300] Updated weights for policy 1, policy_version 48782 (0.0011) -[2023-10-15 04:12:48,137][88300] Updated weights for policy 1, policy_version 48792 (0.0010) -[2023-10-15 04:12:48,534][87330] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 99647488. Throughput: 0: 1757.4, 1: 1753.4. Samples: 24910568. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:12:48,534][87330] Avg episode reward: [(0, '22.930'), (1, '22.950')] -[2023-10-15 04:12:51,407][88298] Updated weights for policy 0, policy_version 48520 (0.0008) -[2023-10-15 04:12:51,773][88298] Updated weights for policy 0, policy_version 48530 (0.0007) -[2023-10-15 04:12:52,028][88300] Updated weights for policy 1, policy_version 48802 (0.0010) -[2023-10-15 04:12:52,133][88298] Updated weights for policy 0, policy_version 48540 (0.0008) -[2023-10-15 04:12:52,404][88300] Updated weights for policy 1, policy_version 48812 (0.0007) -[2023-10-15 04:12:52,764][88300] Updated weights for policy 1, policy_version 48822 (0.0007) -[2023-10-15 04:12:53,135][88300] Updated weights for policy 1, policy_version 48832 (0.0010) -[2023-10-15 04:12:53,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 99713024. Throughput: 0: 1734.3, 1: 1757.5. Samples: 24931156. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:12:53,535][87330] Avg episode reward: [(0, '22.740'), (1, '22.840')] -[2023-10-15 04:12:56,070][88298] Updated weights for policy 0, policy_version 48550 (0.0010) -[2023-10-15 04:12:56,446][88298] Updated weights for policy 0, policy_version 48560 (0.0008) -[2023-10-15 04:12:56,818][88298] Updated weights for policy 0, policy_version 48570 (0.0008) -[2023-10-15 04:12:57,040][88300] Updated weights for policy 1, policy_version 48842 (0.0008) -[2023-10-15 04:12:57,404][88300] Updated weights for policy 1, policy_version 48852 (0.0010) -[2023-10-15 04:12:57,770][88300] Updated weights for policy 1, policy_version 48862 (0.0010) -[2023-10-15 04:12:58,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 99778560. Throughput: 0: 1717.1, 1: 1733.5. Samples: 24951004. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:12:58,534][87330] Avg episode reward: [(0, '22.620'), (1, '22.810')] -[2023-10-15 04:12:58,543][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000048576_49741824.pth... -[2023-10-15 04:12:58,544][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000048864_50036736.pth... -[2023-10-15 04:12:58,573][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000046944_48070656.pth -[2023-10-15 04:12:58,575][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000047232_48365568.pth -[2023-10-15 04:12:58,577][87905] Saving a milestone ./train_atari/atari_seaquest_APPO/checkpoint_p0/milestones/checkpoint_000048576_49741824.pth -[2023-10-15 04:12:58,579][88033] Saving a milestone ./train_atari/atari_seaquest_APPO/checkpoint_p1/milestones/checkpoint_000048864_50036736.pth -[2023-10-15 04:13:00,714][88298] Updated weights for policy 0, policy_version 48580 (0.0007) -[2023-10-15 04:13:01,090][88298] Updated weights for policy 0, policy_version 48590 (0.0008) -[2023-10-15 04:13:01,463][88298] Updated weights for policy 0, policy_version 48600 (0.0008) -[2023-10-15 04:13:01,590][88300] Updated weights for policy 1, policy_version 48872 (0.0008) -[2023-10-15 04:13:01,963][88300] Updated weights for policy 1, policy_version 48882 (0.0008) -[2023-10-15 04:13:02,328][88300] Updated weights for policy 1, policy_version 48892 (0.0007) -[2023-10-15 04:13:03,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 99844096. Throughput: 0: 1736.1, 1: 1770.1. Samples: 24963040. Policy #0 lag: (min: 26.0, avg: 26.2, max: 35.0) -[2023-10-15 04:13:03,534][87330] Avg episode reward: [(0, '22.640'), (1, '22.810')] -[2023-10-15 04:13:05,481][88298] Updated weights for policy 0, policy_version 48610 (0.0007) -[2023-10-15 04:13:05,858][88298] Updated weights for policy 0, policy_version 48620 (0.0009) -[2023-10-15 04:13:06,207][88300] Updated weights for policy 1, policy_version 48902 (0.0008) -[2023-10-15 04:13:06,229][88298] Updated weights for policy 0, policy_version 48630 (0.0009) -[2023-10-15 04:13:06,579][88300] Updated weights for policy 1, policy_version 48912 (0.0008) -[2023-10-15 04:13:06,594][88298] Updated weights for policy 0, policy_version 48640 (0.0009) -[2023-10-15 04:13:06,952][88300] Updated weights for policy 1, policy_version 48922 (0.0007) -[2023-10-15 04:13:08,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 99909632. Throughput: 0: 1707.2, 1: 1741.6. Samples: 24982080. Policy #0 lag: (min: 26.0, avg: 26.2, max: 35.0) -[2023-10-15 04:13:08,534][87330] Avg episode reward: [(0, '22.450'), (1, '22.810')] -[2023-10-15 04:13:10,700][88298] Updated weights for policy 0, policy_version 48650 (0.0007) -[2023-10-15 04:13:10,842][88300] Updated weights for policy 1, policy_version 48932 (0.0007) -[2023-10-15 04:13:11,075][88298] Updated weights for policy 0, policy_version 48660 (0.0007) -[2023-10-15 04:13:11,212][88300] Updated weights for policy 1, policy_version 48942 (0.0009) -[2023-10-15 04:13:11,432][88298] Updated weights for policy 0, policy_version 48670 (0.0007) -[2023-10-15 04:13:11,582][88300] Updated weights for policy 1, policy_version 48952 (0.0009) -[2023-10-15 04:13:13,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 99975168. Throughput: 0: 1713.6, 1: 1736.2. Samples: 25003618. Policy #0 lag: (min: 26.0, avg: 26.2, max: 35.0) -[2023-10-15 04:13:13,534][87330] Avg episode reward: [(0, '22.440'), (1, '22.800')] -[2023-10-15 04:13:15,382][88298] Updated weights for policy 0, policy_version 48680 (0.0008) -[2023-10-15 04:13:15,464][88300] Updated weights for policy 1, policy_version 48962 (0.0008) -[2023-10-15 04:13:15,757][88298] Updated weights for policy 0, policy_version 48690 (0.0009) -[2023-10-15 04:13:15,827][88300] Updated weights for policy 1, policy_version 48972 (0.0008) -[2023-10-15 04:13:16,133][88298] Updated weights for policy 0, policy_version 48700 (0.0009) -[2023-10-15 04:13:16,203][88300] Updated weights for policy 1, policy_version 48982 (0.0008) -[2023-10-15 04:13:16,572][88300] Updated weights for policy 1, policy_version 48992 (0.0007) -[2023-10-15 04:13:18,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 100040704. Throughput: 0: 1719.1, 1: 1747.9. Samples: 25013962. Policy #0 lag: (min: 26.0, avg: 26.2, max: 35.0) -[2023-10-15 04:13:18,535][87330] Avg episode reward: [(0, '22.440'), (1, '22.790')] -[2023-10-15 04:13:20,021][88298] Updated weights for policy 0, policy_version 48710 (0.0008) -[2023-10-15 04:13:20,381][88298] Updated weights for policy 0, policy_version 48720 (0.0009) -[2023-10-15 04:13:20,546][88300] Updated weights for policy 1, policy_version 49002 (0.0008) -[2023-10-15 04:13:20,752][88298] Updated weights for policy 0, policy_version 48730 (0.0008) -[2023-10-15 04:13:20,910][88300] Updated weights for policy 1, policy_version 49012 (0.0007) -[2023-10-15 04:13:21,276][88300] Updated weights for policy 1, policy_version 49022 (0.0008) -[2023-10-15 04:13:23,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 100106240. Throughput: 0: 1705.9, 1: 1731.3. Samples: 25034238. Policy #0 lag: (min: 26.0, avg: 26.2, max: 35.0) -[2023-10-15 04:13:23,535][87330] Avg episode reward: [(0, '22.600'), (1, '22.790')] -[2023-10-15 04:13:24,804][88298] Updated weights for policy 0, policy_version 48740 (0.0009) -[2023-10-15 04:13:25,178][88298] Updated weights for policy 0, policy_version 48750 (0.0008) -[2023-10-15 04:13:25,311][88300] Updated weights for policy 1, policy_version 49032 (0.0007) -[2023-10-15 04:13:25,550][88298] Updated weights for policy 0, policy_version 48760 (0.0008) -[2023-10-15 04:13:25,696][88300] Updated weights for policy 1, policy_version 49042 (0.0009) -[2023-10-15 04:13:26,062][88300] Updated weights for policy 1, policy_version 49052 (0.0009) -[2023-10-15 04:13:28,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 100171776. Throughput: 0: 1727.6, 1: 1750.0. Samples: 25055710. Policy #0 lag: (min: 26.0, avg: 26.2, max: 35.0) -[2023-10-15 04:13:28,534][87330] Avg episode reward: [(0, '22.610'), (1, '22.750')] -[2023-10-15 04:13:29,392][88298] Updated weights for policy 0, policy_version 48770 (0.0008) -[2023-10-15 04:13:29,755][88298] Updated weights for policy 0, policy_version 48780 (0.0008) -[2023-10-15 04:13:29,864][88300] Updated weights for policy 1, policy_version 49062 (0.0009) -[2023-10-15 04:13:30,120][88298] Updated weights for policy 0, policy_version 48790 (0.0008) -[2023-10-15 04:13:30,226][88300] Updated weights for policy 1, policy_version 49072 (0.0008) -[2023-10-15 04:13:30,498][88298] Updated weights for policy 0, policy_version 48800 (0.0008) -[2023-10-15 04:13:30,588][88300] Updated weights for policy 1, policy_version 49082 (0.0007) -[2023-10-15 04:13:33,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 100237312. Throughput: 0: 1702.4, 1: 1728.7. Samples: 25064966. Policy #0 lag: (min: 26.0, avg: 26.2, max: 35.0) -[2023-10-15 04:13:33,534][87330] Avg episode reward: [(0, '22.740'), (1, '22.760')] -[2023-10-15 04:13:34,478][88298] Updated weights for policy 0, policy_version 48810 (0.0007) -[2023-10-15 04:13:34,520][88300] Updated weights for policy 1, policy_version 49092 (0.0007) -[2023-10-15 04:13:34,845][88298] Updated weights for policy 0, policy_version 48820 (0.0009) -[2023-10-15 04:13:34,884][88300] Updated weights for policy 1, policy_version 49102 (0.0007) -[2023-10-15 04:13:35,222][88298] Updated weights for policy 0, policy_version 48830 (0.0007) -[2023-10-15 04:13:35,258][88300] Updated weights for policy 1, policy_version 49112 (0.0007) -[2023-10-15 04:13:38,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 100302848. Throughput: 0: 1716.8, 1: 1734.7. Samples: 25086474. Policy #0 lag: (min: 31.0, avg: 31.9, max: 51.0) -[2023-10-15 04:13:38,535][87330] Avg episode reward: [(0, '22.810'), (1, '22.720')] -[2023-10-15 04:13:39,080][88298] Updated weights for policy 0, policy_version 48840 (0.0009) -[2023-10-15 04:13:39,092][88300] Updated weights for policy 1, policy_version 49122 (0.0007) -[2023-10-15 04:13:39,446][88298] Updated weights for policy 0, policy_version 48850 (0.0007) -[2023-10-15 04:13:39,467][88300] Updated weights for policy 1, policy_version 49132 (0.0007) -[2023-10-15 04:13:39,812][88298] Updated weights for policy 0, policy_version 48860 (0.0008) -[2023-10-15 04:13:39,832][88300] Updated weights for policy 1, policy_version 49142 (0.0010) -[2023-10-15 04:13:40,207][88300] Updated weights for policy 1, policy_version 49152 (0.0010) -[2023-10-15 04:13:43,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 100368384. Throughput: 0: 1731.5, 1: 1762.9. Samples: 25108252. Policy #0 lag: (min: 31.0, avg: 31.9, max: 51.0) -[2023-10-15 04:13:43,535][87330] Avg episode reward: [(0, '22.830'), (1, '22.600')] -[2023-10-15 04:13:43,624][88298] Updated weights for policy 0, policy_version 48870 (0.0008) -[2023-10-15 04:13:43,996][88298] Updated weights for policy 0, policy_version 48880 (0.0009) -[2023-10-15 04:13:44,025][88300] Updated weights for policy 1, policy_version 49162 (0.0009) -[2023-10-15 04:13:44,364][88298] Updated weights for policy 0, policy_version 48890 (0.0009) -[2023-10-15 04:13:44,387][88300] Updated weights for policy 1, policy_version 49172 (0.0010) -[2023-10-15 04:13:44,755][88300] Updated weights for policy 1, policy_version 49182 (0.0010) -[2023-10-15 04:13:48,235][88298] Updated weights for policy 0, policy_version 48900 (0.0010) -[2023-10-15 04:13:48,536][87330] Fps is (10 sec: 13104.9, 60 sec: 13106.8, 300 sec: 13884.7). Total num frames: 100433920. Throughput: 0: 1709.5, 1: 1724.8. Samples: 25117590. Policy #0 lag: (min: 31.0, avg: 31.9, max: 51.0) -[2023-10-15 04:13:48,536][87330] Avg episode reward: [(0, '22.850'), (1, '22.600')] -[2023-10-15 04:13:48,605][88298] Updated weights for policy 0, policy_version 48910 (0.0010) -[2023-10-15 04:13:48,755][88300] Updated weights for policy 1, policy_version 49192 (0.0008) -[2023-10-15 04:13:48,975][88298] Updated weights for policy 0, policy_version 48920 (0.0008) -[2023-10-15 04:13:49,121][88300] Updated weights for policy 1, policy_version 49202 (0.0008) -[2023-10-15 04:13:49,489][88300] Updated weights for policy 1, policy_version 49212 (0.0007) -[2023-10-15 04:13:53,183][88298] Updated weights for policy 0, policy_version 48930 (0.0009) -[2023-10-15 04:13:53,330][88300] Updated weights for policy 1, policy_version 49222 (0.0008) -[2023-10-15 04:13:53,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13884.7). Total num frames: 100499456. Throughput: 0: 1732.0, 1: 1756.5. Samples: 25139062. Policy #0 lag: (min: 31.0, avg: 31.9, max: 51.0) -[2023-10-15 04:13:53,535][87330] Avg episode reward: [(0, '22.800'), (1, '22.620')] -[2023-10-15 04:13:53,592][88298] Updated weights for policy 0, policy_version 48940 (0.0010) -[2023-10-15 04:13:53,695][88300] Updated weights for policy 1, policy_version 49232 (0.0009) -[2023-10-15 04:13:53,956][88298] Updated weights for policy 0, policy_version 48950 (0.0009) -[2023-10-15 04:13:54,068][88300] Updated weights for policy 1, policy_version 49242 (0.0008) -[2023-10-15 04:13:54,319][88298] Updated weights for policy 0, policy_version 48960 (0.0008) -[2023-10-15 04:13:58,242][88300] Updated weights for policy 1, policy_version 49252 (0.0008) -[2023-10-15 04:13:58,275][88298] Updated weights for policy 0, policy_version 48970 (0.0010) -[2023-10-15 04:13:58,534][87330] Fps is (10 sec: 13109.8, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 100564992. Throughput: 0: 1727.8, 1: 1747.0. Samples: 25159984. Policy #0 lag: (min: 31.0, avg: 31.9, max: 51.0) -[2023-10-15 04:13:58,534][87330] Avg episode reward: [(0, '22.710'), (1, '22.770')] -[2023-10-15 04:13:58,620][88300] Updated weights for policy 1, policy_version 49262 (0.0009) -[2023-10-15 04:13:58,644][88298] Updated weights for policy 0, policy_version 48980 (0.0009) -[2023-10-15 04:13:58,975][88300] Updated weights for policy 1, policy_version 49272 (0.0008) -[2023-10-15 04:13:59,013][88298] Updated weights for policy 0, policy_version 48990 (0.0009) -[2023-10-15 04:14:02,917][88300] Updated weights for policy 1, policy_version 49282 (0.0009) -[2023-10-15 04:14:02,998][88298] Updated weights for policy 0, policy_version 49000 (0.0007) -[2023-10-15 04:14:03,283][88300] Updated weights for policy 1, policy_version 49292 (0.0009) -[2023-10-15 04:14:03,372][88298] Updated weights for policy 0, policy_version 49010 (0.0007) -[2023-10-15 04:14:03,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 100630528. Throughput: 0: 1716.0, 1: 1740.2. Samples: 25169494. Policy #0 lag: (min: 31.0, avg: 31.9, max: 51.0) -[2023-10-15 04:14:03,534][87330] Avg episode reward: [(0, '22.700'), (1, '22.650')] -[2023-10-15 04:14:03,646][88300] Updated weights for policy 1, policy_version 49302 (0.0009) -[2023-10-15 04:14:03,738][88298] Updated weights for policy 0, policy_version 49020 (0.0007) -[2023-10-15 04:14:04,007][88300] Updated weights for policy 1, policy_version 49312 (0.0010) -[2023-10-15 04:14:07,755][88298] Updated weights for policy 0, policy_version 49030 (0.0007) -[2023-10-15 04:14:07,890][88300] Updated weights for policy 1, policy_version 49322 (0.0007) -[2023-10-15 04:14:08,122][88298] Updated weights for policy 0, policy_version 49040 (0.0008) -[2023-10-15 04:14:08,249][88300] Updated weights for policy 1, policy_version 49332 (0.0007) -[2023-10-15 04:14:08,485][88298] Updated weights for policy 0, policy_version 49050 (0.0008) -[2023-10-15 04:14:08,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 100696064. Throughput: 0: 1731.3, 1: 1752.5. Samples: 25191010. Policy #0 lag: (min: 31.0, avg: 31.9, max: 51.0) -[2023-10-15 04:14:08,534][87330] Avg episode reward: [(0, '22.720'), (1, '22.660')] -[2023-10-15 04:14:08,617][88300] Updated weights for policy 1, policy_version 49342 (0.0009) -[2023-10-15 04:14:12,485][88298] Updated weights for policy 0, policy_version 49060 (0.0008) -[2023-10-15 04:14:12,588][88300] Updated weights for policy 1, policy_version 49352 (0.0010) -[2023-10-15 04:14:12,852][88298] Updated weights for policy 0, policy_version 49070 (0.0007) -[2023-10-15 04:14:12,960][88300] Updated weights for policy 1, policy_version 49362 (0.0007) -[2023-10-15 04:14:13,217][88298] Updated weights for policy 0, policy_version 49080 (0.0008) -[2023-10-15 04:14:13,319][88300] Updated weights for policy 1, policy_version 49372 (0.0008) -[2023-10-15 04:14:13,534][87330] Fps is (10 sec: 19660.4, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 100827136. Throughput: 0: 1718.9, 1: 1726.7. Samples: 25210764. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-15 04:14:13,535][87330] Avg episode reward: [(0, '22.840'), (1, '22.770')] -[2023-10-15 04:14:17,042][88300] Updated weights for policy 1, policy_version 49382 (0.0008) -[2023-10-15 04:14:17,162][88298] Updated weights for policy 0, policy_version 49090 (0.0008) -[2023-10-15 04:14:17,412][88300] Updated weights for policy 1, policy_version 49392 (0.0007) -[2023-10-15 04:14:17,531][88298] Updated weights for policy 0, policy_version 49100 (0.0007) -[2023-10-15 04:14:17,776][88300] Updated weights for policy 1, policy_version 49402 (0.0008) -[2023-10-15 04:14:17,908][88298] Updated weights for policy 0, policy_version 49110 (0.0008) -[2023-10-15 04:14:18,272][88298] Updated weights for policy 0, policy_version 49120 (0.0007) -[2023-10-15 04:14:18,534][87330] Fps is (10 sec: 19660.6, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 100892672. Throughput: 0: 1731.0, 1: 1754.7. Samples: 25221822. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-15 04:14:18,535][87330] Avg episode reward: [(0, '22.630'), (1, '22.790')] -[2023-10-15 04:14:21,714][88300] Updated weights for policy 1, policy_version 49412 (0.0008) -[2023-10-15 04:14:22,073][88300] Updated weights for policy 1, policy_version 49422 (0.0009) -[2023-10-15 04:14:22,235][88298] Updated weights for policy 0, policy_version 49130 (0.0008) -[2023-10-15 04:14:22,442][88300] Updated weights for policy 1, policy_version 49432 (0.0009) -[2023-10-15 04:14:22,592][88298] Updated weights for policy 0, policy_version 49140 (0.0008) -[2023-10-15 04:14:22,966][88298] Updated weights for policy 0, policy_version 49150 (0.0010) -[2023-10-15 04:14:23,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 100958208. Throughput: 0: 1729.8, 1: 1737.1. Samples: 25242486. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-15 04:14:23,534][87330] Avg episode reward: [(0, '22.640'), (1, '22.770')] -[2023-10-15 04:14:26,355][88300] Updated weights for policy 1, policy_version 49442 (0.0008) -[2023-10-15 04:14:26,718][88300] Updated weights for policy 1, policy_version 49452 (0.0009) -[2023-10-15 04:14:26,831][88298] Updated weights for policy 0, policy_version 49160 (0.0009) -[2023-10-15 04:14:27,082][88300] Updated weights for policy 1, policy_version 49462 (0.0009) -[2023-10-15 04:14:27,196][88298] Updated weights for policy 0, policy_version 49170 (0.0009) -[2023-10-15 04:14:27,454][88300] Updated weights for policy 1, policy_version 49472 (0.0009) -[2023-10-15 04:14:27,571][88298] Updated weights for policy 0, policy_version 49180 (0.0008) -[2023-10-15 04:14:28,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 101023744. Throughput: 0: 1695.4, 1: 1712.9. Samples: 25261624. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-15 04:14:28,535][87330] Avg episode reward: [(0, '22.770'), (1, '22.730')] -[2023-10-15 04:14:31,272][88300] Updated weights for policy 1, policy_version 49482 (0.0009) -[2023-10-15 04:14:31,618][88298] Updated weights for policy 0, policy_version 49190 (0.0009) -[2023-10-15 04:14:31,636][88300] Updated weights for policy 1, policy_version 49492 (0.0007) -[2023-10-15 04:14:31,989][88298] Updated weights for policy 0, policy_version 49200 (0.0008) -[2023-10-15 04:14:32,005][88300] Updated weights for policy 1, policy_version 49502 (0.0007) -[2023-10-15 04:14:32,368][88298] Updated weights for policy 0, policy_version 49210 (0.0008) -[2023-10-15 04:14:33,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 101089280. Throughput: 0: 1722.5, 1: 1741.8. Samples: 25273476. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-15 04:14:33,535][87330] Avg episode reward: [(0, '22.780'), (1, '22.750')] -[2023-10-15 04:14:35,734][88300] Updated weights for policy 1, policy_version 49512 (0.0008) -[2023-10-15 04:14:36,111][88300] Updated weights for policy 1, policy_version 49522 (0.0008) -[2023-10-15 04:14:36,336][88298] Updated weights for policy 0, policy_version 49220 (0.0009) -[2023-10-15 04:14:36,474][88300] Updated weights for policy 1, policy_version 49532 (0.0008) -[2023-10-15 04:14:36,702][88298] Updated weights for policy 0, policy_version 49230 (0.0011) -[2023-10-15 04:14:37,072][88298] Updated weights for policy 0, policy_version 49240 (0.0009) -[2023-10-15 04:14:38,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 101154816. Throughput: 0: 1710.4, 1: 1720.8. Samples: 25293466. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-15 04:14:38,534][87330] Avg episode reward: [(0, '22.720'), (1, '22.830')] -[2023-10-15 04:14:40,427][88300] Updated weights for policy 1, policy_version 49542 (0.0009) -[2023-10-15 04:14:40,798][88300] Updated weights for policy 1, policy_version 49552 (0.0010) -[2023-10-15 04:14:40,993][88298] Updated weights for policy 0, policy_version 49250 (0.0008) -[2023-10-15 04:14:41,165][88300] Updated weights for policy 1, policy_version 49562 (0.0008) -[2023-10-15 04:14:41,380][88298] Updated weights for policy 0, policy_version 49260 (0.0010) -[2023-10-15 04:14:41,762][88298] Updated weights for policy 0, policy_version 49270 (0.0009) -[2023-10-15 04:14:42,126][88298] Updated weights for policy 0, policy_version 49280 (0.0010) -[2023-10-15 04:14:43,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 101220352. Throughput: 0: 1697.8, 1: 1730.0. Samples: 25314234. Policy #0 lag: (min: 21.0, avg: 22.1, max: 44.0) -[2023-10-15 04:14:43,534][87330] Avg episode reward: [(0, '22.680'), (1, '22.600')] -[2023-10-15 04:14:45,148][88300] Updated weights for policy 1, policy_version 49572 (0.0010) -[2023-10-15 04:14:45,520][88300] Updated weights for policy 1, policy_version 49582 (0.0008) -[2023-10-15 04:14:45,876][88300] Updated weights for policy 1, policy_version 49592 (0.0007) -[2023-10-15 04:14:46,000][88298] Updated weights for policy 0, policy_version 49290 (0.0008) -[2023-10-15 04:14:46,372][88298] Updated weights for policy 0, policy_version 49300 (0.0008) -[2023-10-15 04:14:46,744][88298] Updated weights for policy 0, policy_version 49310 (0.0007) -[2023-10-15 04:14:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.9, 300 sec: 13884.7). Total num frames: 101285888. Throughput: 0: 1728.1, 1: 1724.9. Samples: 25324880. Policy #0 lag: (min: 21.0, avg: 22.1, max: 44.0) -[2023-10-15 04:14:48,534][87330] Avg episode reward: [(0, '22.850'), (1, '22.450')] -[2023-10-15 04:14:49,797][88300] Updated weights for policy 1, policy_version 49602 (0.0008) -[2023-10-15 04:14:50,170][88300] Updated weights for policy 1, policy_version 49612 (0.0009) -[2023-10-15 04:14:50,539][88300] Updated weights for policy 1, policy_version 49622 (0.0007) -[2023-10-15 04:14:50,761][88298] Updated weights for policy 0, policy_version 49320 (0.0007) -[2023-10-15 04:14:50,901][88300] Updated weights for policy 1, policy_version 49632 (0.0009) -[2023-10-15 04:14:51,131][88298] Updated weights for policy 0, policy_version 49330 (0.0008) -[2023-10-15 04:14:51,494][88298] Updated weights for policy 0, policy_version 49340 (0.0009) -[2023-10-15 04:14:53,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 101351424. Throughput: 0: 1699.5, 1: 1722.0. Samples: 25344978. Policy #0 lag: (min: 21.0, avg: 22.1, max: 44.0) -[2023-10-15 04:14:53,534][87330] Avg episode reward: [(0, '22.870'), (1, '22.250')] -[2023-10-15 04:14:54,927][88300] Updated weights for policy 1, policy_version 49642 (0.0008) -[2023-10-15 04:14:55,288][88300] Updated weights for policy 1, policy_version 49652 (0.0008) -[2023-10-15 04:14:55,323][88298] Updated weights for policy 0, policy_version 49350 (0.0008) -[2023-10-15 04:14:55,659][88300] Updated weights for policy 1, policy_version 49662 (0.0008) -[2023-10-15 04:14:55,684][88298] Updated weights for policy 0, policy_version 49360 (0.0009) -[2023-10-15 04:14:56,059][88298] Updated weights for policy 0, policy_version 49370 (0.0008) -[2023-10-15 04:14:58,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13884.8). Total num frames: 101416960. Throughput: 0: 1716.6, 1: 1746.8. Samples: 25366618. Policy #0 lag: (min: 21.0, avg: 22.1, max: 44.0) -[2023-10-15 04:14:58,534][87330] Avg episode reward: [(0, '22.860'), (1, '22.190')] -[2023-10-15 04:14:58,545][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000049376_50561024.pth... -[2023-10-15 04:14:58,545][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000049664_50855936.pth... -[2023-10-15 04:14:58,584][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000048032_49184768.pth -[2023-10-15 04:14:58,584][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000047776_48922624.pth -[2023-10-15 04:14:59,733][88300] Updated weights for policy 1, policy_version 49672 (0.0009) -[2023-10-15 04:14:59,816][88298] Updated weights for policy 0, policy_version 49380 (0.0008) -[2023-10-15 04:15:00,109][88300] Updated weights for policy 1, policy_version 49682 (0.0009) -[2023-10-15 04:15:00,184][88298] Updated weights for policy 0, policy_version 49390 (0.0007) -[2023-10-15 04:15:00,480][88300] Updated weights for policy 1, policy_version 49692 (0.0008) -[2023-10-15 04:15:00,554][88298] Updated weights for policy 0, policy_version 49400 (0.0007) -[2023-10-15 04:15:03,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 101482496. Throughput: 0: 1717.2, 1: 1714.8. Samples: 25376264. Policy #0 lag: (min: 21.0, avg: 22.1, max: 44.0) -[2023-10-15 04:15:03,535][87330] Avg episode reward: [(0, '22.860'), (1, '22.170')] -[2023-10-15 04:15:04,383][88298] Updated weights for policy 0, policy_version 49410 (0.0008) -[2023-10-15 04:15:04,387][88300] Updated weights for policy 1, policy_version 49702 (0.0008) -[2023-10-15 04:15:04,745][88298] Updated weights for policy 0, policy_version 49420 (0.0008) -[2023-10-15 04:15:04,749][88300] Updated weights for policy 1, policy_version 49712 (0.0009) -[2023-10-15 04:15:05,120][88298] Updated weights for policy 0, policy_version 49430 (0.0007) -[2023-10-15 04:15:05,124][88300] Updated weights for policy 1, policy_version 49722 (0.0008) -[2023-10-15 04:15:05,492][88298] Updated weights for policy 0, policy_version 49440 (0.0008) -[2023-10-15 04:15:08,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 101548032. Throughput: 0: 1717.7, 1: 1732.2. Samples: 25397732. Policy #0 lag: (min: 21.0, avg: 22.1, max: 44.0) -[2023-10-15 04:15:08,534][87330] Avg episode reward: [(0, '22.910'), (1, '22.170')] -[2023-10-15 04:15:08,885][88300] Updated weights for policy 1, policy_version 49732 (0.0008) -[2023-10-15 04:15:09,258][88300] Updated weights for policy 1, policy_version 49742 (0.0008) -[2023-10-15 04:15:09,367][88298] Updated weights for policy 0, policy_version 49450 (0.0007) -[2023-10-15 04:15:09,629][88300] Updated weights for policy 1, policy_version 49752 (0.0008) -[2023-10-15 04:15:09,733][88298] Updated weights for policy 0, policy_version 49460 (0.0007) -[2023-10-15 04:15:10,102][88298] Updated weights for policy 0, policy_version 49470 (0.0007) -[2023-10-15 04:15:13,472][88300] Updated weights for policy 1, policy_version 49762 (0.0008) -[2023-10-15 04:15:13,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 101613568. Throughput: 0: 1754.4, 1: 1757.1. Samples: 25419644. Policy #0 lag: (min: 21.0, avg: 22.1, max: 44.0) -[2023-10-15 04:15:13,535][87330] Avg episode reward: [(0, '22.900'), (1, '22.190')] -[2023-10-15 04:15:13,834][88300] Updated weights for policy 1, policy_version 49772 (0.0008) -[2023-10-15 04:15:13,961][88298] Updated weights for policy 0, policy_version 49480 (0.0007) -[2023-10-15 04:15:14,202][88300] Updated weights for policy 1, policy_version 49782 (0.0008) -[2023-10-15 04:15:14,319][88298] Updated weights for policy 0, policy_version 49490 (0.0007) -[2023-10-15 04:15:14,578][88300] Updated weights for policy 1, policy_version 49792 (0.0008) -[2023-10-15 04:15:14,694][88298] Updated weights for policy 0, policy_version 49500 (0.0009) -[2023-10-15 04:15:18,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 101679104. Throughput: 0: 1727.9, 1: 1727.3. Samples: 25428962. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:15:18,534][87330] Avg episode reward: [(0, '22.800'), (1, '22.540')] -[2023-10-15 04:15:18,554][88298] Updated weights for policy 0, policy_version 49510 (0.0009) -[2023-10-15 04:15:18,593][88300] Updated weights for policy 1, policy_version 49802 (0.0008) -[2023-10-15 04:15:18,935][88298] Updated weights for policy 0, policy_version 49520 (0.0008) -[2023-10-15 04:15:18,963][88300] Updated weights for policy 1, policy_version 49812 (0.0007) -[2023-10-15 04:15:19,299][88298] Updated weights for policy 0, policy_version 49530 (0.0007) -[2023-10-15 04:15:19,320][88300] Updated weights for policy 1, policy_version 49822 (0.0007) -[2023-10-15 04:15:23,242][88300] Updated weights for policy 1, policy_version 49832 (0.0010) -[2023-10-15 04:15:23,306][88298] Updated weights for policy 0, policy_version 49540 (0.0008) -[2023-10-15 04:15:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 101744640. Throughput: 0: 1745.5, 1: 1737.4. Samples: 25450196. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:15:23,535][87330] Avg episode reward: [(0, '22.810'), (1, '22.760')] -[2023-10-15 04:15:23,608][88300] Updated weights for policy 1, policy_version 49842 (0.0007) -[2023-10-15 04:15:23,683][88298] Updated weights for policy 0, policy_version 49550 (0.0009) -[2023-10-15 04:15:23,967][88300] Updated weights for policy 1, policy_version 49852 (0.0009) -[2023-10-15 04:15:24,045][88298] Updated weights for policy 0, policy_version 49560 (0.0007) -[2023-10-15 04:15:27,990][88300] Updated weights for policy 1, policy_version 49862 (0.0009) -[2023-10-15 04:15:28,031][88298] Updated weights for policy 0, policy_version 49570 (0.0007) -[2023-10-15 04:15:28,348][88300] Updated weights for policy 1, policy_version 49872 (0.0008) -[2023-10-15 04:15:28,417][88298] Updated weights for policy 0, policy_version 49580 (0.0009) -[2023-10-15 04:15:28,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 101810176. Throughput: 0: 1759.8, 1: 1726.8. Samples: 25471130. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:15:28,534][87330] Avg episode reward: [(0, '22.850'), (1, '22.760')] -[2023-10-15 04:15:28,723][88300] Updated weights for policy 1, policy_version 49882 (0.0008) -[2023-10-15 04:15:28,782][88298] Updated weights for policy 0, policy_version 49590 (0.0008) -[2023-10-15 04:15:29,150][88298] Updated weights for policy 0, policy_version 49600 (0.0008) -[2023-10-15 04:15:32,604][88300] Updated weights for policy 1, policy_version 49892 (0.0009) -[2023-10-15 04:15:32,967][88300] Updated weights for policy 1, policy_version 49902 (0.0009) -[2023-10-15 04:15:33,143][88298] Updated weights for policy 0, policy_version 49610 (0.0008) -[2023-10-15 04:15:33,326][88300] Updated weights for policy 1, policy_version 49912 (0.0007) -[2023-10-15 04:15:33,513][88298] Updated weights for policy 0, policy_version 49620 (0.0008) -[2023-10-15 04:15:33,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 101875712. Throughput: 0: 1724.7, 1: 1741.1. Samples: 25480842. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:15:33,535][87330] Avg episode reward: [(0, '22.820'), (1, '22.870')] -[2023-10-15 04:15:33,893][88298] Updated weights for policy 0, policy_version 49630 (0.0010) -[2023-10-15 04:15:37,186][88300] Updated weights for policy 1, policy_version 49922 (0.0008) -[2023-10-15 04:15:37,546][88300] Updated weights for policy 1, policy_version 49932 (0.0009) -[2023-10-15 04:15:37,908][88300] Updated weights for policy 1, policy_version 49942 (0.0010) -[2023-10-15 04:15:38,067][88298] Updated weights for policy 0, policy_version 49640 (0.0008) -[2023-10-15 04:15:38,270][88300] Updated weights for policy 1, policy_version 49952 (0.0008) -[2023-10-15 04:15:38,436][88298] Updated weights for policy 0, policy_version 49650 (0.0007) -[2023-10-15 04:15:38,534][87330] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 101974016. Throughput: 0: 1750.8, 1: 1744.1. Samples: 25502250. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:15:38,534][87330] Avg episode reward: [(0, '22.830'), (1, '22.900')] -[2023-10-15 04:15:38,803][88298] Updated weights for policy 0, policy_version 49660 (0.0008) -[2023-10-15 04:15:42,048][88300] Updated weights for policy 1, policy_version 49962 (0.0008) -[2023-10-15 04:15:42,415][88300] Updated weights for policy 1, policy_version 49972 (0.0007) -[2023-10-15 04:15:42,777][88300] Updated weights for policy 1, policy_version 49982 (0.0009) -[2023-10-15 04:15:42,831][88298] Updated weights for policy 0, policy_version 49670 (0.0008) -[2023-10-15 04:15:43,203][88298] Updated weights for policy 0, policy_version 49680 (0.0007) -[2023-10-15 04:15:43,534][87330] Fps is (10 sec: 16384.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 102039552. Throughput: 0: 1741.2, 1: 1720.3. Samples: 25522384. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:15:43,534][87330] Avg episode reward: [(0, '22.840'), (1, '22.900')] -[2023-10-15 04:15:43,574][88298] Updated weights for policy 0, policy_version 49690 (0.0007) -[2023-10-15 04:15:46,700][88300] Updated weights for policy 1, policy_version 49992 (0.0010) -[2023-10-15 04:15:47,070][88300] Updated weights for policy 1, policy_version 50002 (0.0009) -[2023-10-15 04:15:47,296][88298] Updated weights for policy 0, policy_version 49700 (0.0008) -[2023-10-15 04:15:47,429][88300] Updated weights for policy 1, policy_version 50012 (0.0007) -[2023-10-15 04:15:47,675][88298] Updated weights for policy 0, policy_version 49710 (0.0008) -[2023-10-15 04:15:48,039][88298] Updated weights for policy 0, policy_version 49720 (0.0011) -[2023-10-15 04:15:48,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 102137856. Throughput: 0: 1740.6, 1: 1753.6. Samples: 25533502. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-15 04:15:48,534][87330] Avg episode reward: [(0, '22.820'), (1, '22.890')] -[2023-10-15 04:15:51,290][88300] Updated weights for policy 1, policy_version 50022 (0.0008) -[2023-10-15 04:15:51,656][88300] Updated weights for policy 1, policy_version 50032 (0.0009) -[2023-10-15 04:15:51,954][88298] Updated weights for policy 0, policy_version 49730 (0.0011) -[2023-10-15 04:15:52,025][88300] Updated weights for policy 1, policy_version 50042 (0.0008) -[2023-10-15 04:15:52,321][88298] Updated weights for policy 0, policy_version 49740 (0.0009) -[2023-10-15 04:15:52,697][88298] Updated weights for policy 0, policy_version 49750 (0.0008) -[2023-10-15 04:15:53,066][88298] Updated weights for policy 0, policy_version 49760 (0.0007) -[2023-10-15 04:15:53,534][87330] Fps is (10 sec: 16383.5, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 102203392. Throughput: 0: 1743.5, 1: 1730.9. Samples: 25554082. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-15 04:15:53,535][87330] Avg episode reward: [(0, '22.940'), (1, '22.790')] -[2023-10-15 04:15:55,880][88300] Updated weights for policy 1, policy_version 50052 (0.0008) -[2023-10-15 04:15:56,248][88300] Updated weights for policy 1, policy_version 50062 (0.0008) -[2023-10-15 04:15:56,610][88300] Updated weights for policy 1, policy_version 50072 (0.0008) -[2023-10-15 04:15:57,016][88298] Updated weights for policy 0, policy_version 49770 (0.0008) -[2023-10-15 04:15:57,377][88298] Updated weights for policy 0, policy_version 49780 (0.0007) -[2023-10-15 04:15:57,749][88298] Updated weights for policy 0, policy_version 49790 (0.0010) -[2023-10-15 04:15:58,534][87330] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 102268928. Throughput: 0: 1712.7, 1: 1722.7. Samples: 25574236. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-15 04:15:58,535][87330] Avg episode reward: [(0, '22.940'), (1, '22.780')] -[2023-10-15 04:16:00,593][88300] Updated weights for policy 1, policy_version 50082 (0.0008) -[2023-10-15 04:16:00,960][88300] Updated weights for policy 1, policy_version 50092 (0.0009) -[2023-10-15 04:16:01,320][88300] Updated weights for policy 1, policy_version 50102 (0.0008) -[2023-10-15 04:16:01,561][88298] Updated weights for policy 0, policy_version 49800 (0.0010) -[2023-10-15 04:16:01,697][88300] Updated weights for policy 1, policy_version 50112 (0.0008) -[2023-10-15 04:16:01,923][88298] Updated weights for policy 0, policy_version 49810 (0.0009) -[2023-10-15 04:16:02,303][88298] Updated weights for policy 0, policy_version 49820 (0.0010) -[2023-10-15 04:16:03,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 102334464. Throughput: 0: 1740.6, 1: 1738.8. Samples: 25585536. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-15 04:16:03,535][87330] Avg episode reward: [(0, '22.840'), (1, '22.730')] -[2023-10-15 04:16:05,524][88300] Updated weights for policy 1, policy_version 50122 (0.0009) -[2023-10-15 04:16:05,889][88300] Updated weights for policy 1, policy_version 50132 (0.0007) -[2023-10-15 04:16:06,154][88298] Updated weights for policy 0, policy_version 49830 (0.0008) -[2023-10-15 04:16:06,260][88300] Updated weights for policy 1, policy_version 50142 (0.0008) -[2023-10-15 04:16:06,523][88298] Updated weights for policy 0, policy_version 49840 (0.0009) -[2023-10-15 04:16:06,885][88298] Updated weights for policy 0, policy_version 49850 (0.0007) -[2023-10-15 04:16:08,534][87330] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 102400000. Throughput: 0: 1721.3, 1: 1733.6. Samples: 25605668. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-15 04:16:08,534][87330] Avg episode reward: [(0, '22.630'), (1, '22.760')] -[2023-10-15 04:16:10,240][88300] Updated weights for policy 1, policy_version 50152 (0.0008) -[2023-10-15 04:16:10,588][88298] Updated weights for policy 0, policy_version 49860 (0.0007) -[2023-10-15 04:16:10,610][88300] Updated weights for policy 1, policy_version 50162 (0.0007) -[2023-10-15 04:16:10,957][88298] Updated weights for policy 0, policy_version 49870 (0.0007) -[2023-10-15 04:16:10,986][88300] Updated weights for policy 1, policy_version 50172 (0.0008) -[2023-10-15 04:16:11,322][88298] Updated weights for policy 0, policy_version 49880 (0.0009) -[2023-10-15 04:16:13,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 102465536. Throughput: 0: 1720.1, 1: 1749.2. Samples: 25627250. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-15 04:16:13,534][87330] Avg episode reward: [(0, '22.600'), (1, '22.750')] -[2023-10-15 04:16:14,741][88300] Updated weights for policy 1, policy_version 50182 (0.0009) -[2023-10-15 04:16:15,114][88300] Updated weights for policy 1, policy_version 50192 (0.0009) -[2023-10-15 04:16:15,225][88298] Updated weights for policy 0, policy_version 49890 (0.0009) -[2023-10-15 04:16:15,487][88300] Updated weights for policy 1, policy_version 50202 (0.0008) -[2023-10-15 04:16:15,605][88298] Updated weights for policy 0, policy_version 49900 (0.0009) -[2023-10-15 04:16:15,979][88298] Updated weights for policy 0, policy_version 49910 (0.0009) -[2023-10-15 04:16:16,337][88298] Updated weights for policy 0, policy_version 49920 (0.0009) -[2023-10-15 04:16:18,534][87330] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 102531072. Throughput: 0: 1740.4, 1: 1738.0. Samples: 25637372. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-15 04:16:18,535][87330] Avg episode reward: [(0, '22.490'), (1, '22.780')] -[2023-10-15 04:16:19,289][88300] Updated weights for policy 1, policy_version 50212 (0.0008) -[2023-10-15 04:16:19,655][88300] Updated weights for policy 1, policy_version 50222 (0.0009) -[2023-10-15 04:16:20,018][88300] Updated weights for policy 1, policy_version 50232 (0.0008) -[2023-10-15 04:16:20,274][88298] Updated weights for policy 0, policy_version 49930 (0.0008) -[2023-10-15 04:16:20,637][88298] Updated weights for policy 0, policy_version 49940 (0.0007) -[2023-10-15 04:16:20,992][88298] Updated weights for policy 0, policy_version 49950 (0.0007) -[2023-10-15 04:16:23,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 102596608. Throughput: 0: 1730.5, 1: 1741.1. Samples: 25658474. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-10-15 04:16:23,535][87330] Avg episode reward: [(0, '22.460'), (1, '22.730')] -[2023-10-15 04:16:24,079][88300] Updated weights for policy 1, policy_version 50242 (0.0008) -[2023-10-15 04:16:24,453][88300] Updated weights for policy 1, policy_version 50252 (0.0008) -[2023-10-15 04:16:24,815][88300] Updated weights for policy 1, policy_version 50262 (0.0009) -[2023-10-15 04:16:24,840][88298] Updated weights for policy 0, policy_version 49960 (0.0007) -[2023-10-15 04:16:25,180][88300] Updated weights for policy 1, policy_version 50272 (0.0009) -[2023-10-15 04:16:25,212][88298] Updated weights for policy 0, policy_version 49970 (0.0007) -[2023-10-15 04:16:25,582][88298] Updated weights for policy 0, policy_version 49980 (0.0010) -[2023-10-15 04:16:28,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 102662144. Throughput: 0: 1742.4, 1: 1768.6. Samples: 25680380. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-10-15 04:16:28,535][87330] Avg episode reward: [(0, '22.170'), (1, '22.700')] -[2023-10-15 04:16:29,052][88300] Updated weights for policy 1, policy_version 50282 (0.0009) -[2023-10-15 04:16:29,311][88298] Updated weights for policy 0, policy_version 49990 (0.0008) -[2023-10-15 04:16:29,414][88300] Updated weights for policy 1, policy_version 50292 (0.0008) -[2023-10-15 04:16:29,685][88298] Updated weights for policy 0, policy_version 50000 (0.0008) -[2023-10-15 04:16:29,789][88300] Updated weights for policy 1, policy_version 50302 (0.0010) -[2023-10-15 04:16:30,052][88298] Updated weights for policy 0, policy_version 50010 (0.0007) -[2023-10-15 04:16:33,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 102727680. Throughput: 0: 1733.5, 1: 1741.5. Samples: 25689876. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-10-15 04:16:33,535][87330] Avg episode reward: [(0, '22.120'), (1, '22.720')] -[2023-10-15 04:16:33,721][88300] Updated weights for policy 1, policy_version 50312 (0.0009) -[2023-10-15 04:16:34,086][88300] Updated weights for policy 1, policy_version 50322 (0.0008) -[2023-10-15 04:16:34,107][88298] Updated weights for policy 0, policy_version 50020 (0.0009) -[2023-10-15 04:16:34,457][88300] Updated weights for policy 1, policy_version 50332 (0.0007) -[2023-10-15 04:16:34,474][88298] Updated weights for policy 0, policy_version 50030 (0.0007) -[2023-10-15 04:16:34,842][88298] Updated weights for policy 0, policy_version 50040 (0.0008) -[2023-10-15 04:16:38,306][88300] Updated weights for policy 1, policy_version 50342 (0.0009) -[2023-10-15 04:16:38,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 102793216. Throughput: 0: 1732.3, 1: 1765.2. Samples: 25711468. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-10-15 04:16:38,535][87330] Avg episode reward: [(0, '22.320'), (1, '22.690')] -[2023-10-15 04:16:38,682][88300] Updated weights for policy 1, policy_version 50352 (0.0010) -[2023-10-15 04:16:38,734][88298] Updated weights for policy 0, policy_version 50050 (0.0008) -[2023-10-15 04:16:39,041][88300] Updated weights for policy 1, policy_version 50362 (0.0010) -[2023-10-15 04:16:39,100][88298] Updated weights for policy 0, policy_version 50060 (0.0008) -[2023-10-15 04:16:39,480][88298] Updated weights for policy 0, policy_version 50070 (0.0010) -[2023-10-15 04:16:39,843][88298] Updated weights for policy 0, policy_version 50080 (0.0011) -[2023-10-15 04:16:42,939][88300] Updated weights for policy 1, policy_version 50372 (0.0007) -[2023-10-15 04:16:43,311][88300] Updated weights for policy 1, policy_version 50382 (0.0008) -[2023-10-15 04:16:43,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 102858752. Throughput: 0: 1763.2, 1: 1755.7. Samples: 25732588. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-10-15 04:16:43,535][87330] Avg episode reward: [(0, '22.050'), (1, '22.660')] -[2023-10-15 04:16:43,664][88298] Updated weights for policy 0, policy_version 50090 (0.0008) -[2023-10-15 04:16:43,686][88300] Updated weights for policy 1, policy_version 50392 (0.0007) -[2023-10-15 04:16:44,024][88298] Updated weights for policy 0, policy_version 50100 (0.0007) -[2023-10-15 04:16:44,397][88298] Updated weights for policy 0, policy_version 50110 (0.0009) -[2023-10-15 04:16:47,418][88300] Updated weights for policy 1, policy_version 50402 (0.0010) -[2023-10-15 04:16:47,783][88300] Updated weights for policy 1, policy_version 50412 (0.0009) -[2023-10-15 04:16:48,159][88300] Updated weights for policy 1, policy_version 50422 (0.0008) -[2023-10-15 04:16:48,249][88298] Updated weights for policy 0, policy_version 50120 (0.0007) -[2023-10-15 04:16:48,517][88300] Updated weights for policy 1, policy_version 50432 (0.0008) -[2023-10-15 04:16:48,534][87330] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 102957056. Throughput: 0: 1738.7, 1: 1752.3. Samples: 25742630. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-10-15 04:16:48,534][87330] Avg episode reward: [(0, '22.190'), (1, '22.660')] -[2023-10-15 04:16:48,614][88298] Updated weights for policy 0, policy_version 50130 (0.0009) -[2023-10-15 04:16:48,991][88298] Updated weights for policy 0, policy_version 50140 (0.0010) -[2023-10-15 04:16:52,485][88300] Updated weights for policy 1, policy_version 50442 (0.0009) -[2023-10-15 04:16:52,854][88300] Updated weights for policy 1, policy_version 50452 (0.0009) -[2023-10-15 04:16:52,988][88298] Updated weights for policy 0, policy_version 50150 (0.0009) -[2023-10-15 04:16:53,213][88300] Updated weights for policy 1, policy_version 50462 (0.0009) -[2023-10-15 04:16:53,355][88298] Updated weights for policy 0, policy_version 50160 (0.0009) -[2023-10-15 04:16:53,534][87330] Fps is (10 sec: 16384.2, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 103022592. Throughput: 0: 1753.7, 1: 1761.4. Samples: 25763848. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-10-15 04:16:53,535][87330] Avg episode reward: [(0, '22.200'), (1, '22.670')] -[2023-10-15 04:16:53,725][88298] Updated weights for policy 0, policy_version 50170 (0.0010) -[2023-10-15 04:16:57,176][88300] Updated weights for policy 1, policy_version 50472 (0.0007) -[2023-10-15 04:16:57,496][88298] Updated weights for policy 0, policy_version 50180 (0.0009) -[2023-10-15 04:16:57,544][88300] Updated weights for policy 1, policy_version 50482 (0.0008) -[2023-10-15 04:16:57,876][88298] Updated weights for policy 0, policy_version 50190 (0.0008) -[2023-10-15 04:16:57,904][88300] Updated weights for policy 1, policy_version 50492 (0.0007) -[2023-10-15 04:16:58,236][88298] Updated weights for policy 0, policy_version 50200 (0.0009) -[2023-10-15 04:16:58,534][87330] Fps is (10 sec: 16383.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 103120896. Throughput: 0: 1752.2, 1: 1726.7. Samples: 25783804. Policy #0 lag: (min: 26.0, avg: 29.1, max: 58.0) -[2023-10-15 04:16:58,535][87330] Avg episode reward: [(0, '22.360'), (1, '22.710')] -[2023-10-15 04:16:58,545][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000050496_51707904.pth... -[2023-10-15 04:16:58,545][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000050208_51412992.pth... -[2023-10-15 04:16:58,575][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000048576_49741824.pth -[2023-10-15 04:16:58,575][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000048864_50036736.pth -[2023-10-15 04:17:01,810][88300] Updated weights for policy 1, policy_version 50502 (0.0008) -[2023-10-15 04:17:02,181][88300] Updated weights for policy 1, policy_version 50512 (0.0010) -[2023-10-15 04:17:02,215][88298] Updated weights for policy 0, policy_version 50210 (0.0007) -[2023-10-15 04:17:02,547][88300] Updated weights for policy 1, policy_version 50522 (0.0008) -[2023-10-15 04:17:02,623][88298] Updated weights for policy 0, policy_version 50220 (0.0007) -[2023-10-15 04:17:02,994][88298] Updated weights for policy 0, policy_version 50230 (0.0008) -[2023-10-15 04:17:03,362][88298] Updated weights for policy 0, policy_version 50240 (0.0007) -[2023-10-15 04:17:03,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 103186432. Throughput: 0: 1748.4, 1: 1756.4. Samples: 25795084. Policy #0 lag: (min: 26.0, avg: 29.1, max: 58.0) -[2023-10-15 04:17:03,535][87330] Avg episode reward: [(0, '22.500'), (1, '22.880')] -[2023-10-15 04:17:06,587][88300] Updated weights for policy 1, policy_version 50532 (0.0010) -[2023-10-15 04:17:06,953][88300] Updated weights for policy 1, policy_version 50542 (0.0008) -[2023-10-15 04:17:07,260][88298] Updated weights for policy 0, policy_version 50250 (0.0007) -[2023-10-15 04:17:07,318][88300] Updated weights for policy 1, policy_version 50552 (0.0007) -[2023-10-15 04:17:07,629][88298] Updated weights for policy 0, policy_version 50260 (0.0007) -[2023-10-15 04:17:08,004][88298] Updated weights for policy 0, policy_version 50270 (0.0007) -[2023-10-15 04:17:08,534][87330] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 103251968. Throughput: 0: 1757.1, 1: 1730.9. Samples: 25815432. Policy #0 lag: (min: 26.0, avg: 29.1, max: 58.0) -[2023-10-15 04:17:08,534][87330] Avg episode reward: [(0, '22.570'), (1, '22.880')] -[2023-10-15 04:17:11,121][88300] Updated weights for policy 1, policy_version 50562 (0.0008) -[2023-10-15 04:17:11,493][88300] Updated weights for policy 1, policy_version 50572 (0.0009) -[2023-10-15 04:17:11,866][88300] Updated weights for policy 1, policy_version 50582 (0.0007) -[2023-10-15 04:17:11,967][88298] Updated weights for policy 0, policy_version 50280 (0.0008) -[2023-10-15 04:17:12,232][88300] Updated weights for policy 1, policy_version 50592 (0.0009) -[2023-10-15 04:17:12,335][88298] Updated weights for policy 0, policy_version 50290 (0.0007) -[2023-10-15 04:17:12,710][88298] Updated weights for policy 0, policy_version 50300 (0.0007) -[2023-10-15 04:17:13,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 103317504. Throughput: 0: 1724.7, 1: 1721.3. Samples: 25835450. Policy #0 lag: (min: 26.0, avg: 29.1, max: 58.0) -[2023-10-15 04:17:13,534][87330] Avg episode reward: [(0, '22.410'), (1, '22.910')] -[2023-10-15 04:17:16,257][88300] Updated weights for policy 1, policy_version 50602 (0.0008) -[2023-10-15 04:17:16,586][88298] Updated weights for policy 0, policy_version 50310 (0.0008) -[2023-10-15 04:17:16,628][88300] Updated weights for policy 1, policy_version 50612 (0.0009) -[2023-10-15 04:17:16,966][88298] Updated weights for policy 0, policy_version 50320 (0.0007) -[2023-10-15 04:17:16,987][88300] Updated weights for policy 1, policy_version 50622 (0.0010) -[2023-10-15 04:17:17,327][88298] Updated weights for policy 0, policy_version 50330 (0.0007) -[2023-10-15 04:17:18,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 103383040. Throughput: 0: 1752.2, 1: 1740.1. Samples: 25847026. Policy #0 lag: (min: 26.0, avg: 29.1, max: 58.0) -[2023-10-15 04:17:18,534][87330] Avg episode reward: [(0, '22.680'), (1, '22.930')] -[2023-10-15 04:17:20,904][88300] Updated weights for policy 1, policy_version 50632 (0.0008) -[2023-10-15 04:17:21,198][88298] Updated weights for policy 0, policy_version 50340 (0.0008) -[2023-10-15 04:17:21,272][88300] Updated weights for policy 1, policy_version 50642 (0.0010) -[2023-10-15 04:17:21,567][88298] Updated weights for policy 0, policy_version 50350 (0.0009) -[2023-10-15 04:17:21,643][88300] Updated weights for policy 1, policy_version 50652 (0.0009) -[2023-10-15 04:17:21,940][88298] Updated weights for policy 0, policy_version 50360 (0.0009) -[2023-10-15 04:17:23,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 103448576. Throughput: 0: 1737.9, 1: 1713.3. Samples: 25866772. Policy #0 lag: (min: 26.0, avg: 29.1, max: 58.0) -[2023-10-15 04:17:23,534][87330] Avg episode reward: [(0, '22.680'), (1, '22.920')] -[2023-10-15 04:17:25,455][88300] Updated weights for policy 1, policy_version 50662 (0.0009) -[2023-10-15 04:17:25,818][88300] Updated weights for policy 1, policy_version 50672 (0.0010) -[2023-10-15 04:17:25,854][88298] Updated weights for policy 0, policy_version 50370 (0.0008) -[2023-10-15 04:17:26,183][88300] Updated weights for policy 1, policy_version 50682 (0.0008) -[2023-10-15 04:17:26,210][88298] Updated weights for policy 0, policy_version 50380 (0.0008) -[2023-10-15 04:17:26,588][88298] Updated weights for policy 0, policy_version 50390 (0.0008) -[2023-10-15 04:17:26,955][88298] Updated weights for policy 0, policy_version 50400 (0.0008) -[2023-10-15 04:17:28,534][87330] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 103514112. Throughput: 0: 1723.4, 1: 1726.7. Samples: 25887844. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 04:17:28,535][87330] Avg episode reward: [(0, '22.660'), (1, '22.940')] -[2023-10-15 04:17:30,131][88300] Updated weights for policy 1, policy_version 50692 (0.0008) -[2023-10-15 04:17:30,490][88300] Updated weights for policy 1, policy_version 50702 (0.0010) -[2023-10-15 04:17:30,694][88298] Updated weights for policy 0, policy_version 50410 (0.0007) -[2023-10-15 04:17:30,855][88300] Updated weights for policy 1, policy_version 50712 (0.0007) -[2023-10-15 04:17:31,071][88298] Updated weights for policy 0, policy_version 50420 (0.0007) -[2023-10-15 04:17:31,443][88298] Updated weights for policy 0, policy_version 50430 (0.0008) -[2023-10-15 04:17:33,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 103579648. Throughput: 0: 1743.4, 1: 1715.3. Samples: 25898272. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 04:17:33,534][87330] Avg episode reward: [(0, '22.670'), (1, '22.900')] -[2023-10-15 04:17:34,795][88300] Updated weights for policy 1, policy_version 50722 (0.0008) -[2023-10-15 04:17:35,154][88300] Updated weights for policy 1, policy_version 50732 (0.0009) -[2023-10-15 04:17:35,341][88298] Updated weights for policy 0, policy_version 50440 (0.0008) -[2023-10-15 04:17:35,523][88300] Updated weights for policy 1, policy_version 50742 (0.0007) -[2023-10-15 04:17:35,716][88298] Updated weights for policy 0, policy_version 50450 (0.0008) -[2023-10-15 04:17:35,883][88300] Updated weights for policy 1, policy_version 50752 (0.0007) -[2023-10-15 04:17:36,081][88298] Updated weights for policy 0, policy_version 50460 (0.0009) -[2023-10-15 04:17:38,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 103645184. Throughput: 0: 1727.2, 1: 1720.0. Samples: 25918972. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 04:17:38,535][87330] Avg episode reward: [(0, '22.570'), (1, '22.920')] -[2023-10-15 04:17:39,763][88300] Updated weights for policy 1, policy_version 50762 (0.0007) -[2023-10-15 04:17:39,906][88298] Updated weights for policy 0, policy_version 50470 (0.0008) -[2023-10-15 04:17:40,134][88300] Updated weights for policy 1, policy_version 50772 (0.0007) -[2023-10-15 04:17:40,275][88298] Updated weights for policy 0, policy_version 50480 (0.0009) -[2023-10-15 04:17:40,503][88300] Updated weights for policy 1, policy_version 50782 (0.0007) -[2023-10-15 04:17:40,655][88298] Updated weights for policy 0, policy_version 50490 (0.0008) -[2023-10-15 04:17:43,534][87330] Fps is (10 sec: 13106.6, 60 sec: 14199.4, 300 sec: 13773.6). Total num frames: 103710720. Throughput: 0: 1737.0, 1: 1749.5. Samples: 25940696. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 04:17:43,535][87330] Avg episode reward: [(0, '22.830'), (1, '22.920')] -[2023-10-15 04:17:44,370][88300] Updated weights for policy 1, policy_version 50792 (0.0007) -[2023-10-15 04:17:44,684][88298] Updated weights for policy 0, policy_version 50500 (0.0009) -[2023-10-15 04:17:44,744][88300] Updated weights for policy 1, policy_version 50802 (0.0008) -[2023-10-15 04:17:45,053][88298] Updated weights for policy 0, policy_version 50510 (0.0009) -[2023-10-15 04:17:45,116][88300] Updated weights for policy 1, policy_version 50812 (0.0008) -[2023-10-15 04:17:45,409][88298] Updated weights for policy 0, policy_version 50520 (0.0009) -[2023-10-15 04:17:48,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 103776256. Throughput: 0: 1725.8, 1: 1720.1. Samples: 25950150. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 04:17:48,534][87330] Avg episode reward: [(0, '22.840'), (1, '22.900')] -[2023-10-15 04:17:48,963][88300] Updated weights for policy 1, policy_version 50822 (0.0008) -[2023-10-15 04:17:49,285][88298] Updated weights for policy 0, policy_version 50530 (0.0007) -[2023-10-15 04:17:49,328][88300] Updated weights for policy 1, policy_version 50832 (0.0008) -[2023-10-15 04:17:49,690][88298] Updated weights for policy 0, policy_version 50540 (0.0008) -[2023-10-15 04:17:49,695][88300] Updated weights for policy 1, policy_version 50842 (0.0008) -[2023-10-15 04:17:50,062][88298] Updated weights for policy 0, policy_version 50550 (0.0009) -[2023-10-15 04:17:50,434][88298] Updated weights for policy 0, policy_version 50560 (0.0010) -[2023-10-15 04:17:53,534][87330] Fps is (10 sec: 13107.8, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 103841792. Throughput: 0: 1725.8, 1: 1744.1. Samples: 25971578. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 04:17:53,534][87330] Avg episode reward: [(0, '22.850'), (1, '22.890')] -[2023-10-15 04:17:53,624][88300] Updated weights for policy 1, policy_version 50852 (0.0008) -[2023-10-15 04:17:53,993][88300] Updated weights for policy 1, policy_version 50862 (0.0009) -[2023-10-15 04:17:54,349][88300] Updated weights for policy 1, policy_version 50872 (0.0009) -[2023-10-15 04:17:54,446][88298] Updated weights for policy 0, policy_version 50570 (0.0008) -[2023-10-15 04:17:54,826][88298] Updated weights for policy 0, policy_version 50580 (0.0008) -[2023-10-15 04:17:55,188][88298] Updated weights for policy 0, policy_version 50590 (0.0007) -[2023-10-15 04:17:58,346][88300] Updated weights for policy 1, policy_version 50882 (0.0009) -[2023-10-15 04:17:58,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 103907328. Throughput: 0: 1755.5, 1: 1750.1. Samples: 25993202. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 04:17:58,535][87330] Avg episode reward: [(0, '22.600'), (1, '22.900')] -[2023-10-15 04:17:58,705][88300] Updated weights for policy 1, policy_version 50892 (0.0007) -[2023-10-15 04:17:59,082][88300] Updated weights for policy 1, policy_version 50902 (0.0007) -[2023-10-15 04:17:59,123][88298] Updated weights for policy 0, policy_version 50600 (0.0007) -[2023-10-15 04:17:59,447][88300] Updated weights for policy 1, policy_version 50912 (0.0007) -[2023-10-15 04:17:59,486][88298] Updated weights for policy 0, policy_version 50610 (0.0007) -[2023-10-15 04:17:59,860][88298] Updated weights for policy 0, policy_version 50620 (0.0009) -[2023-10-15 04:18:03,322][88300] Updated weights for policy 1, policy_version 50922 (0.0009) -[2023-10-15 04:18:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 103972864. Throughput: 0: 1724.6, 1: 1730.7. Samples: 26002514. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-10-15 04:18:03,534][87330] Avg episode reward: [(0, '22.320'), (1, '22.920')] -[2023-10-15 04:18:03,696][88300] Updated weights for policy 1, policy_version 50932 (0.0009) -[2023-10-15 04:18:03,745][88298] Updated weights for policy 0, policy_version 50630 (0.0009) -[2023-10-15 04:18:04,058][88300] Updated weights for policy 1, policy_version 50942 (0.0007) -[2023-10-15 04:18:04,107][88298] Updated weights for policy 0, policy_version 50640 (0.0008) -[2023-10-15 04:18:04,486][88298] Updated weights for policy 0, policy_version 50650 (0.0008) -[2023-10-15 04:18:07,986][88300] Updated weights for policy 1, policy_version 50952 (0.0009) -[2023-10-15 04:18:08,353][88300] Updated weights for policy 1, policy_version 50962 (0.0008) -[2023-10-15 04:18:08,479][88298] Updated weights for policy 0, policy_version 50660 (0.0008) -[2023-10-15 04:18:08,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 104038400. Throughput: 0: 1737.5, 1: 1756.5. Samples: 26024004. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-10-15 04:18:08,534][87330] Avg episode reward: [(0, '22.330'), (1, '22.920')] -[2023-10-15 04:18:08,712][88300] Updated weights for policy 1, policy_version 50972 (0.0008) -[2023-10-15 04:18:08,851][88298] Updated weights for policy 0, policy_version 50670 (0.0008) -[2023-10-15 04:18:09,217][88298] Updated weights for policy 0, policy_version 50680 (0.0008) -[2023-10-15 04:18:12,736][88300] Updated weights for policy 1, policy_version 50982 (0.0009) -[2023-10-15 04:18:13,073][88298] Updated weights for policy 0, policy_version 50690 (0.0008) -[2023-10-15 04:18:13,100][88300] Updated weights for policy 1, policy_version 50992 (0.0007) -[2023-10-15 04:18:13,435][88298] Updated weights for policy 0, policy_version 50700 (0.0007) -[2023-10-15 04:18:13,473][88300] Updated weights for policy 1, policy_version 51002 (0.0008) -[2023-10-15 04:18:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 104103936. Throughput: 0: 1749.8, 1: 1732.4. Samples: 26044542. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-10-15 04:18:13,534][87330] Avg episode reward: [(0, '22.300'), (1, '22.940')] -[2023-10-15 04:18:13,803][88298] Updated weights for policy 0, policy_version 50710 (0.0008) -[2023-10-15 04:18:14,173][88298] Updated weights for policy 0, policy_version 50720 (0.0010) -[2023-10-15 04:18:17,518][88300] Updated weights for policy 1, policy_version 51012 (0.0008) -[2023-10-15 04:18:17,888][88300] Updated weights for policy 1, policy_version 51022 (0.0007) -[2023-10-15 04:18:18,054][88298] Updated weights for policy 0, policy_version 50730 (0.0007) -[2023-10-15 04:18:18,254][88300] Updated weights for policy 1, policy_version 51032 (0.0008) -[2023-10-15 04:18:18,429][88298] Updated weights for policy 0, policy_version 50740 (0.0007) -[2023-10-15 04:18:18,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 104169472. Throughput: 0: 1726.5, 1: 1747.3. Samples: 26054594. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-10-15 04:18:18,535][87330] Avg episode reward: [(0, '22.180'), (1, '22.920')] -[2023-10-15 04:18:18,794][88298] Updated weights for policy 0, policy_version 50750 (0.0008) -[2023-10-15 04:18:22,206][88300] Updated weights for policy 1, policy_version 51042 (0.0008) -[2023-10-15 04:18:22,578][88300] Updated weights for policy 1, policy_version 51052 (0.0007) -[2023-10-15 04:18:22,696][88298] Updated weights for policy 0, policy_version 50760 (0.0007) -[2023-10-15 04:18:22,940][88300] Updated weights for policy 1, policy_version 51062 (0.0007) -[2023-10-15 04:18:23,071][88298] Updated weights for policy 0, policy_version 50770 (0.0007) -[2023-10-15 04:18:23,302][88300] Updated weights for policy 1, policy_version 51072 (0.0007) -[2023-10-15 04:18:23,437][88298] Updated weights for policy 0, policy_version 50780 (0.0009) -[2023-10-15 04:18:23,534][87330] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 104267776. Throughput: 0: 1746.7, 1: 1742.3. Samples: 26075978. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-10-15 04:18:23,534][87330] Avg episode reward: [(0, '22.180'), (1, '22.900')] -[2023-10-15 04:18:27,270][88300] Updated weights for policy 1, policy_version 51082 (0.0008) -[2023-10-15 04:18:27,424][88298] Updated weights for policy 0, policy_version 50790 (0.0010) -[2023-10-15 04:18:27,638][88300] Updated weights for policy 1, policy_version 51092 (0.0009) -[2023-10-15 04:18:27,792][88298] Updated weights for policy 0, policy_version 50800 (0.0010) -[2023-10-15 04:18:28,006][88300] Updated weights for policy 1, policy_version 51102 (0.0009) -[2023-10-15 04:18:28,158][88298] Updated weights for policy 0, policy_version 50810 (0.0008) -[2023-10-15 04:18:28,534][87330] Fps is (10 sec: 19660.8, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 104366080. Throughput: 0: 1725.2, 1: 1709.0. Samples: 26095234. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-10-15 04:18:28,535][87330] Avg episode reward: [(0, '22.230'), (1, '22.890')] -[2023-10-15 04:18:31,909][88300] Updated weights for policy 1, policy_version 51112 (0.0011) -[2023-10-15 04:18:32,129][88298] Updated weights for policy 0, policy_version 50820 (0.0007) -[2023-10-15 04:18:32,286][88300] Updated weights for policy 1, policy_version 51122 (0.0008) -[2023-10-15 04:18:32,492][88298] Updated weights for policy 0, policy_version 50830 (0.0008) -[2023-10-15 04:18:32,650][88300] Updated weights for policy 1, policy_version 51132 (0.0008) -[2023-10-15 04:18:32,866][88298] Updated weights for policy 0, policy_version 50840 (0.0008) -[2023-10-15 04:18:33,534][87330] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 104431616. Throughput: 0: 1742.1, 1: 1740.3. Samples: 26106858. Policy #0 lag: (min: 31.0, avg: 33.0, max: 62.0) -[2023-10-15 04:18:33,535][87330] Avg episode reward: [(0, '22.500'), (1, '22.580')] -[2023-10-15 04:18:36,621][88300] Updated weights for policy 1, policy_version 51142 (0.0010) -[2023-10-15 04:18:36,815][88298] Updated weights for policy 0, policy_version 50850 (0.0007) -[2023-10-15 04:18:36,982][88300] Updated weights for policy 1, policy_version 51152 (0.0008) -[2023-10-15 04:18:37,202][88298] Updated weights for policy 0, policy_version 50860 (0.0009) -[2023-10-15 04:18:37,348][88300] Updated weights for policy 1, policy_version 51162 (0.0007) -[2023-10-15 04:18:37,565][88298] Updated weights for policy 0, policy_version 50870 (0.0009) -[2023-10-15 04:18:37,933][88298] Updated weights for policy 0, policy_version 50880 (0.0009) -[2023-10-15 04:18:38,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 104497152. Throughput: 0: 1741.8, 1: 1719.0. Samples: 26127314. Policy #0 lag: (min: 31.0, avg: 33.0, max: 62.0) -[2023-10-15 04:18:38,535][87330] Avg episode reward: [(0, '22.530'), (1, '22.430')] -[2023-10-15 04:18:41,141][88300] Updated weights for policy 1, policy_version 51172 (0.0007) -[2023-10-15 04:18:41,507][88300] Updated weights for policy 1, policy_version 51182 (0.0008) -[2023-10-15 04:18:41,738][88298] Updated weights for policy 0, policy_version 50890 (0.0008) -[2023-10-15 04:18:41,872][88300] Updated weights for policy 1, policy_version 51192 (0.0007) -[2023-10-15 04:18:42,108][88298] Updated weights for policy 0, policy_version 50900 (0.0008) -[2023-10-15 04:18:42,469][88298] Updated weights for policy 0, policy_version 50910 (0.0009) -[2023-10-15 04:18:43,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.9). Total num frames: 104562688. Throughput: 0: 1714.0, 1: 1713.0. Samples: 26147414. Policy #0 lag: (min: 31.0, avg: 33.0, max: 62.0) -[2023-10-15 04:18:43,535][87330] Avg episode reward: [(0, '22.630'), (1, '22.160')] -[2023-10-15 04:18:45,661][88300] Updated weights for policy 1, policy_version 51202 (0.0008) -[2023-10-15 04:18:46,036][88300] Updated weights for policy 1, policy_version 51212 (0.0008) -[2023-10-15 04:18:46,347][88298] Updated weights for policy 0, policy_version 50920 (0.0007) -[2023-10-15 04:18:46,403][88300] Updated weights for policy 1, policy_version 51222 (0.0008) -[2023-10-15 04:18:46,721][88298] Updated weights for policy 0, policy_version 50930 (0.0007) -[2023-10-15 04:18:46,761][88300] Updated weights for policy 1, policy_version 51232 (0.0007) -[2023-10-15 04:18:47,096][88298] Updated weights for policy 0, policy_version 50940 (0.0007) -[2023-10-15 04:18:48,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 104628224. Throughput: 0: 1750.5, 1: 1730.7. Samples: 26159166. Policy #0 lag: (min: 31.0, avg: 33.0, max: 62.0) -[2023-10-15 04:18:48,534][87330] Avg episode reward: [(0, '22.600'), (1, '21.980')] -[2023-10-15 04:18:50,778][88300] Updated weights for policy 1, policy_version 51242 (0.0008) -[2023-10-15 04:18:51,002][88298] Updated weights for policy 0, policy_version 50950 (0.0008) -[2023-10-15 04:18:51,138][88300] Updated weights for policy 1, policy_version 51252 (0.0008) -[2023-10-15 04:18:51,360][88298] Updated weights for policy 0, policy_version 50960 (0.0009) -[2023-10-15 04:18:51,504][88300] Updated weights for policy 1, policy_version 51262 (0.0007) -[2023-10-15 04:18:51,729][88298] Updated weights for policy 0, policy_version 50970 (0.0009) -[2023-10-15 04:18:53,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 104693760. Throughput: 0: 1727.8, 1: 1714.0. Samples: 26178884. Policy #0 lag: (min: 31.0, avg: 33.0, max: 62.0) -[2023-10-15 04:18:53,534][87330] Avg episode reward: [(0, '22.460'), (1, '22.020')] -[2023-10-15 04:18:55,486][88298] Updated weights for policy 0, policy_version 50980 (0.0007) -[2023-10-15 04:18:55,509][88300] Updated weights for policy 1, policy_version 51272 (0.0008) -[2023-10-15 04:18:55,851][88298] Updated weights for policy 0, policy_version 50990 (0.0007) -[2023-10-15 04:18:55,887][88300] Updated weights for policy 1, policy_version 51282 (0.0007) -[2023-10-15 04:18:56,220][88298] Updated weights for policy 0, policy_version 51000 (0.0007) -[2023-10-15 04:18:56,249][88300] Updated weights for policy 1, policy_version 51292 (0.0007) -[2023-10-15 04:18:58,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 104759296. Throughput: 0: 1725.6, 1: 1732.4. Samples: 26200154. Policy #0 lag: (min: 31.0, avg: 33.0, max: 62.0) -[2023-10-15 04:18:58,534][87330] Avg episode reward: [(0, '22.460'), (1, '22.010')] -[2023-10-15 04:18:58,544][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000051008_52232192.pth... -[2023-10-15 04:18:58,544][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000051296_52527104.pth... -[2023-10-15 04:18:58,580][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000049664_50855936.pth -[2023-10-15 04:18:58,588][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000049376_50561024.pth -[2023-10-15 04:19:00,151][88298] Updated weights for policy 0, policy_version 51010 (0.0008) -[2023-10-15 04:19:00,152][88300] Updated weights for policy 1, policy_version 51302 (0.0008) -[2023-10-15 04:19:00,514][88298] Updated weights for policy 0, policy_version 51020 (0.0008) -[2023-10-15 04:19:00,518][88300] Updated weights for policy 1, policy_version 51312 (0.0009) -[2023-10-15 04:19:00,887][88300] Updated weights for policy 1, policy_version 51322 (0.0009) -[2023-10-15 04:19:00,891][88298] Updated weights for policy 0, policy_version 51030 (0.0007) -[2023-10-15 04:19:01,254][88298] Updated weights for policy 0, policy_version 51040 (0.0009) -[2023-10-15 04:19:03,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 104824832. Throughput: 0: 1738.1, 1: 1718.1. Samples: 26210122. Policy #0 lag: (min: 31.0, avg: 33.0, max: 62.0) -[2023-10-15 04:19:03,534][87330] Avg episode reward: [(0, '22.310'), (1, '21.750')] -[2023-10-15 04:19:04,696][88300] Updated weights for policy 1, policy_version 51332 (0.0008) -[2023-10-15 04:19:05,055][88300] Updated weights for policy 1, policy_version 51342 (0.0008) -[2023-10-15 04:19:05,178][88298] Updated weights for policy 0, policy_version 51050 (0.0009) -[2023-10-15 04:19:05,428][88300] Updated weights for policy 1, policy_version 51352 (0.0008) -[2023-10-15 04:19:05,551][88298] Updated weights for policy 0, policy_version 51060 (0.0007) -[2023-10-15 04:19:05,925][88298] Updated weights for policy 0, policy_version 51070 (0.0008) -[2023-10-15 04:19:08,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 104890368. Throughput: 0: 1720.9, 1: 1722.8. Samples: 26230944. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 04:19:08,535][87330] Avg episode reward: [(0, '22.210'), (1, '21.800')] -[2023-10-15 04:19:09,319][88300] Updated weights for policy 1, policy_version 51362 (0.0008) -[2023-10-15 04:19:09,687][88300] Updated weights for policy 1, policy_version 51372 (0.0008) -[2023-10-15 04:19:10,053][88300] Updated weights for policy 1, policy_version 51382 (0.0007) -[2023-10-15 04:19:10,080][88298] Updated weights for policy 0, policy_version 51080 (0.0007) -[2023-10-15 04:19:10,415][88300] Updated weights for policy 1, policy_version 51392 (0.0008) -[2023-10-15 04:19:10,457][88298] Updated weights for policy 0, policy_version 51090 (0.0007) -[2023-10-15 04:19:10,824][88298] Updated weights for policy 0, policy_version 51100 (0.0007) -[2023-10-15 04:19:13,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 104955904. Throughput: 0: 1732.7, 1: 1757.4. Samples: 26252290. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 04:19:13,535][87330] Avg episode reward: [(0, '22.220'), (1, '22.110')] -[2023-10-15 04:19:14,461][88300] Updated weights for policy 1, policy_version 51402 (0.0009) -[2023-10-15 04:19:14,781][88298] Updated weights for policy 0, policy_version 51110 (0.0008) -[2023-10-15 04:19:14,830][88300] Updated weights for policy 1, policy_version 51412 (0.0008) -[2023-10-15 04:19:15,154][88298] Updated weights for policy 0, policy_version 51120 (0.0008) -[2023-10-15 04:19:15,187][88300] Updated weights for policy 1, policy_version 51422 (0.0008) -[2023-10-15 04:19:15,527][88298] Updated weights for policy 0, policy_version 51130 (0.0008) -[2023-10-15 04:19:18,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 105021440. Throughput: 0: 1717.3, 1: 1724.9. Samples: 26261758. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 04:19:18,535][87330] Avg episode reward: [(0, '22.350'), (1, '22.300')] -[2023-10-15 04:19:19,104][88300] Updated weights for policy 1, policy_version 51432 (0.0010) -[2023-10-15 04:19:19,457][88300] Updated weights for policy 1, policy_version 51442 (0.0007) -[2023-10-15 04:19:19,484][88298] Updated weights for policy 0, policy_version 51140 (0.0009) -[2023-10-15 04:19:19,820][88300] Updated weights for policy 1, policy_version 51452 (0.0008) -[2023-10-15 04:19:19,849][88298] Updated weights for policy 0, policy_version 51150 (0.0009) -[2023-10-15 04:19:20,225][88298] Updated weights for policy 0, policy_version 51160 (0.0010) -[2023-10-15 04:19:23,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 105086976. Throughput: 0: 1717.9, 1: 1742.9. Samples: 26283050. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 04:19:23,534][87330] Avg episode reward: [(0, '22.500'), (1, '22.200')] -[2023-10-15 04:19:23,776][88300] Updated weights for policy 1, policy_version 51462 (0.0008) -[2023-10-15 04:19:24,146][88300] Updated weights for policy 1, policy_version 51472 (0.0009) -[2023-10-15 04:19:24,202][88298] Updated weights for policy 0, policy_version 51170 (0.0009) -[2023-10-15 04:19:24,517][88300] Updated weights for policy 1, policy_version 51482 (0.0009) -[2023-10-15 04:19:24,611][88298] Updated weights for policy 0, policy_version 51180 (0.0008) -[2023-10-15 04:19:24,979][88298] Updated weights for policy 0, policy_version 51190 (0.0010) -[2023-10-15 04:19:25,362][88298] Updated weights for policy 0, policy_version 51200 (0.0010) -[2023-10-15 04:19:28,431][88300] Updated weights for policy 1, policy_version 51492 (0.0009) -[2023-10-15 04:19:28,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 105152512. Throughput: 0: 1741.6, 1: 1750.3. Samples: 26304548. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 04:19:28,534][87330] Avg episode reward: [(0, '22.500'), (1, '22.180')] -[2023-10-15 04:19:28,799][88300] Updated weights for policy 1, policy_version 51502 (0.0011) -[2023-10-15 04:19:29,166][88300] Updated weights for policy 1, policy_version 51512 (0.0009) -[2023-10-15 04:19:29,226][88298] Updated weights for policy 0, policy_version 51210 (0.0009) -[2023-10-15 04:19:29,596][88298] Updated weights for policy 0, policy_version 51220 (0.0008) -[2023-10-15 04:19:29,974][88298] Updated weights for policy 0, policy_version 51230 (0.0009) -[2023-10-15 04:19:32,955][88300] Updated weights for policy 1, policy_version 51522 (0.0009) -[2023-10-15 04:19:33,319][88300] Updated weights for policy 1, policy_version 51532 (0.0009) -[2023-10-15 04:19:33,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 13773.7). Total num frames: 105218048. Throughput: 0: 1706.2, 1: 1735.6. Samples: 26314046. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 04:19:33,534][87330] Avg episode reward: [(0, '22.670'), (1, '22.320')] -[2023-10-15 04:19:33,689][88300] Updated weights for policy 1, policy_version 51542 (0.0008) -[2023-10-15 04:19:33,766][88298] Updated weights for policy 0, policy_version 51240 (0.0008) -[2023-10-15 04:19:34,055][88300] Updated weights for policy 1, policy_version 51552 (0.0007) -[2023-10-15 04:19:34,131][88298] Updated weights for policy 0, policy_version 51250 (0.0007) -[2023-10-15 04:19:34,509][88298] Updated weights for policy 0, policy_version 51260 (0.0008) -[2023-10-15 04:19:37,953][88300] Updated weights for policy 1, policy_version 51562 (0.0007) -[2023-10-15 04:19:38,320][88300] Updated weights for policy 1, policy_version 51572 (0.0007) -[2023-10-15 04:19:38,371][88298] Updated weights for policy 0, policy_version 51270 (0.0007) -[2023-10-15 04:19:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 105283584. Throughput: 0: 1731.0, 1: 1753.6. Samples: 26335692. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 04:19:38,534][87330] Avg episode reward: [(0, '22.810'), (1, '22.710')] -[2023-10-15 04:19:38,684][88300] Updated weights for policy 1, policy_version 51582 (0.0009) -[2023-10-15 04:19:38,751][88298] Updated weights for policy 0, policy_version 51280 (0.0007) -[2023-10-15 04:19:39,122][88298] Updated weights for policy 0, policy_version 51290 (0.0007) -[2023-10-15 04:19:42,692][88300] Updated weights for policy 1, policy_version 51592 (0.0008) -[2023-10-15 04:19:43,008][88298] Updated weights for policy 0, policy_version 51300 (0.0007) -[2023-10-15 04:19:43,074][88300] Updated weights for policy 1, policy_version 51602 (0.0008) -[2023-10-15 04:19:43,374][88298] Updated weights for policy 0, policy_version 51310 (0.0007) -[2023-10-15 04:19:43,455][88300] Updated weights for policy 1, policy_version 51612 (0.0008) -[2023-10-15 04:19:43,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 105349120. Throughput: 0: 1732.2, 1: 1735.1. Samples: 26356182. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:19:43,534][87330] Avg episode reward: [(0, '22.790'), (1, '22.690')] -[2023-10-15 04:19:43,750][88298] Updated weights for policy 0, policy_version 51320 (0.0007) -[2023-10-15 04:19:47,307][88300] Updated weights for policy 1, policy_version 51622 (0.0007) -[2023-10-15 04:19:47,685][88300] Updated weights for policy 1, policy_version 51632 (0.0008) -[2023-10-15 04:19:47,718][88298] Updated weights for policy 0, policy_version 51330 (0.0007) -[2023-10-15 04:19:48,041][88300] Updated weights for policy 1, policy_version 51642 (0.0008) -[2023-10-15 04:19:48,076][88298] Updated weights for policy 0, policy_version 51340 (0.0008) -[2023-10-15 04:19:48,455][88298] Updated weights for policy 0, policy_version 51350 (0.0009) -[2023-10-15 04:19:48,534][87330] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 105447424. Throughput: 0: 1720.1, 1: 1754.0. Samples: 26366454. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:19:48,534][87330] Avg episode reward: [(0, '22.840'), (1, '22.700')] -[2023-10-15 04:19:48,819][88298] Updated weights for policy 0, policy_version 51360 (0.0007) -[2023-10-15 04:19:51,830][88300] Updated weights for policy 1, policy_version 51652 (0.0009) -[2023-10-15 04:19:52,195][88300] Updated weights for policy 1, policy_version 51662 (0.0010) -[2023-10-15 04:19:52,560][88300] Updated weights for policy 1, policy_version 51672 (0.0008) -[2023-10-15 04:19:52,729][88298] Updated weights for policy 0, policy_version 51370 (0.0009) -[2023-10-15 04:19:53,095][88298] Updated weights for policy 0, policy_version 51380 (0.0008) -[2023-10-15 04:19:53,475][88298] Updated weights for policy 0, policy_version 51390 (0.0008) -[2023-10-15 04:19:53,534][87330] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 105512960. Throughput: 0: 1736.9, 1: 1744.0. Samples: 26387586. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:19:53,535][87330] Avg episode reward: [(0, '22.540'), (1, '22.770')] -[2023-10-15 04:19:56,637][88300] Updated weights for policy 1, policy_version 51682 (0.0007) -[2023-10-15 04:19:56,993][88300] Updated weights for policy 1, policy_version 51692 (0.0009) -[2023-10-15 04:19:57,360][88300] Updated weights for policy 1, policy_version 51702 (0.0008) -[2023-10-15 04:19:57,501][88298] Updated weights for policy 0, policy_version 51400 (0.0007) -[2023-10-15 04:19:57,719][88300] Updated weights for policy 1, policy_version 51712 (0.0009) -[2023-10-15 04:19:57,874][88298] Updated weights for policy 0, policy_version 51410 (0.0009) -[2023-10-15 04:19:58,236][88298] Updated weights for policy 0, policy_version 51420 (0.0009) -[2023-10-15 04:19:58,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 105611264. Throughput: 0: 1731.2, 1: 1721.9. Samples: 26407680. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:19:58,534][87330] Avg episode reward: [(0, '22.520'), (1, '22.820')] -[2023-10-15 04:20:01,460][88300] Updated weights for policy 1, policy_version 51722 (0.0010) -[2023-10-15 04:20:01,832][88300] Updated weights for policy 1, policy_version 51732 (0.0008) -[2023-10-15 04:20:02,191][88300] Updated weights for policy 1, policy_version 51742 (0.0009) -[2023-10-15 04:20:02,257][88298] Updated weights for policy 0, policy_version 51430 (0.0007) -[2023-10-15 04:20:02,621][88298] Updated weights for policy 0, policy_version 51440 (0.0008) -[2023-10-15 04:20:02,988][88298] Updated weights for policy 0, policy_version 51450 (0.0007) -[2023-10-15 04:20:03,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 105676800. Throughput: 0: 1744.2, 1: 1757.7. Samples: 26419344. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:20:03,534][87330] Avg episode reward: [(0, '22.380'), (1, '22.560')] -[2023-10-15 04:20:05,992][88300] Updated weights for policy 1, policy_version 51752 (0.0007) -[2023-10-15 04:20:06,356][88300] Updated weights for policy 1, policy_version 51762 (0.0008) -[2023-10-15 04:20:06,730][88300] Updated weights for policy 1, policy_version 51772 (0.0008) -[2023-10-15 04:20:06,946][88298] Updated weights for policy 0, policy_version 51460 (0.0008) -[2023-10-15 04:20:07,307][88298] Updated weights for policy 0, policy_version 51470 (0.0007) -[2023-10-15 04:20:07,683][88298] Updated weights for policy 0, policy_version 51480 (0.0009) -[2023-10-15 04:20:08,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 105742336. Throughput: 0: 1746.6, 1: 1736.2. Samples: 26439776. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:20:08,535][87330] Avg episode reward: [(0, '22.230'), (1, '22.450')] -[2023-10-15 04:20:10,584][88300] Updated weights for policy 1, policy_version 51782 (0.0009) -[2023-10-15 04:20:10,938][88300] Updated weights for policy 1, policy_version 51792 (0.0008) -[2023-10-15 04:20:11,307][88300] Updated weights for policy 1, policy_version 51802 (0.0009) -[2023-10-15 04:20:11,576][88298] Updated weights for policy 0, policy_version 51490 (0.0009) -[2023-10-15 04:20:11,990][88298] Updated weights for policy 0, policy_version 51500 (0.0007) -[2023-10-15 04:20:12,347][88298] Updated weights for policy 0, policy_version 51510 (0.0009) -[2023-10-15 04:20:12,710][88298] Updated weights for policy 0, policy_version 51520 (0.0009) -[2023-10-15 04:20:13,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 105807872. Throughput: 0: 1718.6, 1: 1737.2. Samples: 26460058. Policy #0 lag: (min: 11.0, avg: 19.0, max: 43.0) -[2023-10-15 04:20:13,534][87330] Avg episode reward: [(0, '22.290'), (1, '22.460')] -[2023-10-15 04:20:15,227][88300] Updated weights for policy 1, policy_version 51812 (0.0007) -[2023-10-15 04:20:15,598][88300] Updated weights for policy 1, policy_version 51822 (0.0007) -[2023-10-15 04:20:15,957][88300] Updated weights for policy 1, policy_version 51832 (0.0007) -[2023-10-15 04:20:16,556][88298] Updated weights for policy 0, policy_version 51530 (0.0010) -[2023-10-15 04:20:16,934][88298] Updated weights for policy 0, policy_version 51540 (0.0008) -[2023-10-15 04:20:17,308][88298] Updated weights for policy 0, policy_version 51550 (0.0010) -[2023-10-15 04:20:18,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 105873408. Throughput: 0: 1751.5, 1: 1738.5. Samples: 26471094. Policy #0 lag: (min: 11.0, avg: 19.0, max: 43.0) -[2023-10-15 04:20:18,535][87330] Avg episode reward: [(0, '22.250'), (1, '22.510')] -[2023-10-15 04:20:19,977][88300] Updated weights for policy 1, policy_version 51842 (0.0008) -[2023-10-15 04:20:20,342][88300] Updated weights for policy 1, policy_version 51852 (0.0007) -[2023-10-15 04:20:20,708][88300] Updated weights for policy 1, policy_version 51862 (0.0007) -[2023-10-15 04:20:21,037][88298] Updated weights for policy 0, policy_version 51560 (0.0008) -[2023-10-15 04:20:21,077][88300] Updated weights for policy 1, policy_version 51872 (0.0009) -[2023-10-15 04:20:21,400][88298] Updated weights for policy 0, policy_version 51570 (0.0010) -[2023-10-15 04:20:21,770][88298] Updated weights for policy 0, policy_version 51580 (0.0010) -[2023-10-15 04:20:23,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 105938944. Throughput: 0: 1732.4, 1: 1732.9. Samples: 26491632. Policy #0 lag: (min: 11.0, avg: 19.0, max: 43.0) -[2023-10-15 04:20:23,534][87330] Avg episode reward: [(0, '22.530'), (1, '22.310')] -[2023-10-15 04:20:24,787][88300] Updated weights for policy 1, policy_version 51882 (0.0009) -[2023-10-15 04:20:25,170][88300] Updated weights for policy 1, policy_version 51892 (0.0011) -[2023-10-15 04:20:25,536][88300] Updated weights for policy 1, policy_version 51902 (0.0008) -[2023-10-15 04:20:25,651][88298] Updated weights for policy 0, policy_version 51590 (0.0009) -[2023-10-15 04:20:26,023][88298] Updated weights for policy 0, policy_version 51600 (0.0008) -[2023-10-15 04:20:26,389][88298] Updated weights for policy 0, policy_version 51610 (0.0010) -[2023-10-15 04:20:28,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 106004480. Throughput: 0: 1732.7, 1: 1759.3. Samples: 26513320. Policy #0 lag: (min: 11.0, avg: 19.0, max: 43.0) -[2023-10-15 04:20:28,534][87330] Avg episode reward: [(0, '22.510'), (1, '22.270')] -[2023-10-15 04:20:29,524][88300] Updated weights for policy 1, policy_version 51912 (0.0008) -[2023-10-15 04:20:29,912][88300] Updated weights for policy 1, policy_version 51922 (0.0010) -[2023-10-15 04:20:30,283][88300] Updated weights for policy 1, policy_version 51932 (0.0009) -[2023-10-15 04:20:30,318][88298] Updated weights for policy 0, policy_version 51620 (0.0010) -[2023-10-15 04:20:30,693][88298] Updated weights for policy 0, policy_version 51630 (0.0009) -[2023-10-15 04:20:31,062][88298] Updated weights for policy 0, policy_version 51640 (0.0007) -[2023-10-15 04:20:33,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 106070016. Throughput: 0: 1747.1, 1: 1735.7. Samples: 26523178. Policy #0 lag: (min: 11.0, avg: 19.0, max: 43.0) -[2023-10-15 04:20:33,535][87330] Avg episode reward: [(0, '22.500'), (1, '22.250')] -[2023-10-15 04:20:34,107][88300] Updated weights for policy 1, policy_version 51942 (0.0008) -[2023-10-15 04:20:34,476][88300] Updated weights for policy 1, policy_version 51952 (0.0008) -[2023-10-15 04:20:34,835][88300] Updated weights for policy 1, policy_version 51962 (0.0009) -[2023-10-15 04:20:34,850][88298] Updated weights for policy 0, policy_version 51650 (0.0008) -[2023-10-15 04:20:35,230][88298] Updated weights for policy 0, policy_version 51660 (0.0009) -[2023-10-15 04:20:35,601][88298] Updated weights for policy 0, policy_version 51670 (0.0008) -[2023-10-15 04:20:35,963][88298] Updated weights for policy 0, policy_version 51680 (0.0009) -[2023-10-15 04:20:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 106135552. Throughput: 0: 1732.1, 1: 1745.3. Samples: 26544066. Policy #0 lag: (min: 11.0, avg: 19.0, max: 43.0) -[2023-10-15 04:20:38,534][87330] Avg episode reward: [(0, '22.660'), (1, '22.330')] -[2023-10-15 04:20:38,816][88300] Updated weights for policy 1, policy_version 51972 (0.0008) -[2023-10-15 04:20:39,180][88300] Updated weights for policy 1, policy_version 51982 (0.0008) -[2023-10-15 04:20:39,553][88300] Updated weights for policy 1, policy_version 51992 (0.0008) -[2023-10-15 04:20:39,827][88298] Updated weights for policy 0, policy_version 51690 (0.0007) -[2023-10-15 04:20:40,199][88298] Updated weights for policy 0, policy_version 51700 (0.0007) -[2023-10-15 04:20:40,561][88298] Updated weights for policy 0, policy_version 51710 (0.0007) -[2023-10-15 04:20:43,322][88300] Updated weights for policy 1, policy_version 52002 (0.0007) -[2023-10-15 04:20:43,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 106201088. Throughput: 0: 1742.4, 1: 1768.8. Samples: 26565684. Policy #0 lag: (min: 11.0, avg: 19.0, max: 43.0) -[2023-10-15 04:20:43,534][87330] Avg episode reward: [(0, '22.640'), (1, '22.320')] -[2023-10-15 04:20:43,697][88300] Updated weights for policy 1, policy_version 52012 (0.0009) -[2023-10-15 04:20:44,053][88300] Updated weights for policy 1, policy_version 52022 (0.0008) -[2023-10-15 04:20:44,426][88300] Updated weights for policy 1, policy_version 52032 (0.0008) -[2023-10-15 04:20:44,478][88298] Updated weights for policy 0, policy_version 51720 (0.0010) -[2023-10-15 04:20:44,841][88298] Updated weights for policy 0, policy_version 51730 (0.0010) -[2023-10-15 04:20:45,204][88298] Updated weights for policy 0, policy_version 51740 (0.0010) -[2023-10-15 04:20:48,255][88300] Updated weights for policy 1, policy_version 52042 (0.0007) -[2023-10-15 04:20:48,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 106266624. Throughput: 0: 1732.4, 1: 1730.8. Samples: 26575190. Policy #0 lag: (min: 1.0, avg: 14.6, max: 33.0) -[2023-10-15 04:20:48,534][87330] Avg episode reward: [(0, '22.670'), (1, '22.350')] -[2023-10-15 04:20:48,628][88300] Updated weights for policy 1, policy_version 52052 (0.0009) -[2023-10-15 04:20:48,997][88300] Updated weights for policy 1, policy_version 52062 (0.0009) -[2023-10-15 04:20:49,149][88298] Updated weights for policy 0, policy_version 51750 (0.0007) -[2023-10-15 04:20:49,512][88298] Updated weights for policy 0, policy_version 51760 (0.0008) -[2023-10-15 04:20:49,881][88298] Updated weights for policy 0, policy_version 51770 (0.0007) -[2023-10-15 04:20:53,083][88300] Updated weights for policy 1, policy_version 52072 (0.0009) -[2023-10-15 04:20:53,461][88300] Updated weights for policy 1, policy_version 52082 (0.0009) -[2023-10-15 04:20:53,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 106332160. Throughput: 0: 1735.6, 1: 1752.7. Samples: 26596748. Policy #0 lag: (min: 1.0, avg: 14.6, max: 33.0) -[2023-10-15 04:20:53,535][87330] Avg episode reward: [(0, '22.700'), (1, '22.410')] -[2023-10-15 04:20:53,708][88298] Updated weights for policy 0, policy_version 51780 (0.0007) -[2023-10-15 04:20:53,821][88300] Updated weights for policy 1, policy_version 52092 (0.0008) -[2023-10-15 04:20:54,088][88298] Updated weights for policy 0, policy_version 51790 (0.0010) -[2023-10-15 04:20:54,455][88298] Updated weights for policy 0, policy_version 51800 (0.0008) -[2023-10-15 04:20:57,673][88300] Updated weights for policy 1, policy_version 52102 (0.0010) -[2023-10-15 04:20:58,032][88300] Updated weights for policy 1, policy_version 52112 (0.0007) -[2023-10-15 04:20:58,399][88300] Updated weights for policy 1, policy_version 52122 (0.0007) -[2023-10-15 04:20:58,465][88298] Updated weights for policy 0, policy_version 51810 (0.0007) -[2023-10-15 04:20:58,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 106397696. Throughput: 0: 1766.4, 1: 1730.3. Samples: 26617408. Policy #0 lag: (min: 1.0, avg: 14.6, max: 33.0) -[2023-10-15 04:20:58,534][87330] Avg episode reward: [(0, '22.660'), (1, '22.370')] -[2023-10-15 04:20:58,610][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000052128_53379072.pth... -[2023-10-15 04:20:58,649][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000050496_51707904.pth -[2023-10-15 04:20:58,876][88298] Updated weights for policy 0, policy_version 51820 (0.0010) -[2023-10-15 04:20:59,240][88298] Updated weights for policy 0, policy_version 51830 (0.0009) -[2023-10-15 04:20:59,599][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000051840_53084160.pth... -[2023-10-15 04:20:59,600][88298] Updated weights for policy 0, policy_version 51840 (0.0007) -[2023-10-15 04:20:59,637][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000050208_51412992.pth -[2023-10-15 04:21:02,363][88300] Updated weights for policy 1, policy_version 52132 (0.0007) -[2023-10-15 04:21:02,724][88300] Updated weights for policy 1, policy_version 52142 (0.0007) -[2023-10-15 04:21:03,101][88300] Updated weights for policy 1, policy_version 52152 (0.0007) -[2023-10-15 04:21:03,310][88298] Updated weights for policy 0, policy_version 51850 (0.0007) -[2023-10-15 04:21:03,534][87330] Fps is (10 sec: 16384.3, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 106496000. Throughput: 0: 1729.6, 1: 1747.8. Samples: 26627576. Policy #0 lag: (min: 1.0, avg: 14.6, max: 33.0) -[2023-10-15 04:21:03,534][87330] Avg episode reward: [(0, '22.680'), (1, '22.410')] -[2023-10-15 04:21:03,681][88298] Updated weights for policy 0, policy_version 51860 (0.0009) -[2023-10-15 04:21:04,039][88298] Updated weights for policy 0, policy_version 51870 (0.0010) -[2023-10-15 04:21:06,998][88300] Updated weights for policy 1, policy_version 52162 (0.0008) -[2023-10-15 04:21:07,361][88300] Updated weights for policy 1, policy_version 52172 (0.0007) -[2023-10-15 04:21:07,730][88300] Updated weights for policy 1, policy_version 52182 (0.0007) -[2023-10-15 04:21:08,065][88298] Updated weights for policy 0, policy_version 51880 (0.0009) -[2023-10-15 04:21:08,090][88300] Updated weights for policy 1, policy_version 52192 (0.0007) -[2023-10-15 04:21:08,432][88298] Updated weights for policy 0, policy_version 51890 (0.0008) -[2023-10-15 04:21:08,534][87330] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 106561536. Throughput: 0: 1752.9, 1: 1744.8. Samples: 26649026. Policy #0 lag: (min: 1.0, avg: 14.6, max: 33.0) -[2023-10-15 04:21:08,534][87330] Avg episode reward: [(0, '22.890'), (1, '22.640')] -[2023-10-15 04:21:08,812][88298] Updated weights for policy 0, policy_version 51900 (0.0008) -[2023-10-15 04:21:12,005][88300] Updated weights for policy 1, policy_version 52202 (0.0008) -[2023-10-15 04:21:12,373][88300] Updated weights for policy 1, policy_version 52212 (0.0009) -[2023-10-15 04:21:12,680][88298] Updated weights for policy 0, policy_version 51910 (0.0007) -[2023-10-15 04:21:12,748][88300] Updated weights for policy 1, policy_version 52222 (0.0007) -[2023-10-15 04:21:13,046][88298] Updated weights for policy 0, policy_version 51920 (0.0008) -[2023-10-15 04:21:13,419][88298] Updated weights for policy 0, policy_version 51930 (0.0009) -[2023-10-15 04:21:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 106627072. Throughput: 0: 1747.4, 1: 1717.3. Samples: 26669232. Policy #0 lag: (min: 1.0, avg: 14.6, max: 33.0) -[2023-10-15 04:21:13,534][87330] Avg episode reward: [(0, '22.710'), (1, '22.660')] -[2023-10-15 04:21:16,624][88300] Updated weights for policy 1, policy_version 52232 (0.0007) -[2023-10-15 04:21:17,003][88300] Updated weights for policy 1, policy_version 52242 (0.0008) -[2023-10-15 04:21:17,148][88298] Updated weights for policy 0, policy_version 51940 (0.0009) -[2023-10-15 04:21:17,383][88300] Updated weights for policy 1, policy_version 52252 (0.0008) -[2023-10-15 04:21:17,519][88298] Updated weights for policy 0, policy_version 51950 (0.0009) -[2023-10-15 04:21:17,895][88298] Updated weights for policy 0, policy_version 51960 (0.0009) -[2023-10-15 04:21:18,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 106725376. Throughput: 0: 1743.9, 1: 1758.9. Samples: 26680804. Policy #0 lag: (min: 14.0, avg: 37.3, max: 40.0) -[2023-10-15 04:21:18,534][87330] Avg episode reward: [(0, '22.730'), (1, '22.740')] -[2023-10-15 04:21:21,223][88300] Updated weights for policy 1, policy_version 52262 (0.0009) -[2023-10-15 04:21:21,595][88300] Updated weights for policy 1, policy_version 52272 (0.0007) -[2023-10-15 04:21:21,822][88298] Updated weights for policy 0, policy_version 51970 (0.0008) -[2023-10-15 04:21:21,968][88300] Updated weights for policy 1, policy_version 52282 (0.0008) -[2023-10-15 04:21:22,182][88298] Updated weights for policy 0, policy_version 51980 (0.0009) -[2023-10-15 04:21:22,556][88298] Updated weights for policy 0, policy_version 51990 (0.0007) -[2023-10-15 04:21:22,925][88298] Updated weights for policy 0, policy_version 52000 (0.0007) -[2023-10-15 04:21:23,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 106790912. Throughput: 0: 1759.4, 1: 1726.7. Samples: 26700940. Policy #0 lag: (min: 14.0, avg: 37.3, max: 40.0) -[2023-10-15 04:21:23,535][87330] Avg episode reward: [(0, '22.730'), (1, '22.680')] -[2023-10-15 04:21:25,800][88300] Updated weights for policy 1, policy_version 52292 (0.0008) -[2023-10-15 04:21:26,166][88300] Updated weights for policy 1, policy_version 52302 (0.0007) -[2023-10-15 04:21:26,526][88300] Updated weights for policy 1, policy_version 52312 (0.0008) -[2023-10-15 04:21:26,681][88298] Updated weights for policy 0, policy_version 52010 (0.0007) -[2023-10-15 04:21:27,057][88298] Updated weights for policy 0, policy_version 52020 (0.0008) -[2023-10-15 04:21:27,425][88298] Updated weights for policy 0, policy_version 52030 (0.0008) -[2023-10-15 04:21:28,534][87330] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 106856448. Throughput: 0: 1737.9, 1: 1729.0. Samples: 26721694. Policy #0 lag: (min: 14.0, avg: 37.3, max: 40.0) -[2023-10-15 04:21:28,535][87330] Avg episode reward: [(0, '22.760'), (1, '22.660')] -[2023-10-15 04:21:30,378][88300] Updated weights for policy 1, policy_version 52322 (0.0008) -[2023-10-15 04:21:30,747][88300] Updated weights for policy 1, policy_version 52332 (0.0007) -[2023-10-15 04:21:31,125][88300] Updated weights for policy 1, policy_version 52342 (0.0007) -[2023-10-15 04:21:31,149][88298] Updated weights for policy 0, policy_version 52040 (0.0007) -[2023-10-15 04:21:31,486][88300] Updated weights for policy 1, policy_version 52352 (0.0009) -[2023-10-15 04:21:31,511][88298] Updated weights for policy 0, policy_version 52050 (0.0008) -[2023-10-15 04:21:31,880][88298] Updated weights for policy 0, policy_version 52060 (0.0010) -[2023-10-15 04:21:33,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 106921984. Throughput: 0: 1769.4, 1: 1736.6. Samples: 26732962. Policy #0 lag: (min: 14.0, avg: 37.3, max: 40.0) -[2023-10-15 04:21:33,535][87330] Avg episode reward: [(0, '22.760'), (1, '22.710')] -[2023-10-15 04:21:35,507][88300] Updated weights for policy 1, policy_version 52362 (0.0009) -[2023-10-15 04:21:35,732][88298] Updated weights for policy 0, policy_version 52070 (0.0009) -[2023-10-15 04:21:35,879][88300] Updated weights for policy 1, policy_version 52372 (0.0009) -[2023-10-15 04:21:36,097][88298] Updated weights for policy 0, policy_version 52080 (0.0009) -[2023-10-15 04:21:36,240][88300] Updated weights for policy 1, policy_version 52382 (0.0009) -[2023-10-15 04:21:36,476][88298] Updated weights for policy 0, policy_version 52090 (0.0008) -[2023-10-15 04:21:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 106987520. Throughput: 0: 1734.1, 1: 1729.0. Samples: 26752590. Policy #0 lag: (min: 14.0, avg: 37.3, max: 40.0) -[2023-10-15 04:21:38,535][87330] Avg episode reward: [(0, '22.750'), (1, '22.500')] -[2023-10-15 04:21:40,078][88300] Updated weights for policy 1, policy_version 52392 (0.0008) -[2023-10-15 04:21:40,445][88300] Updated weights for policy 1, policy_version 52402 (0.0007) -[2023-10-15 04:21:40,502][88298] Updated weights for policy 0, policy_version 52100 (0.0010) -[2023-10-15 04:21:40,812][88300] Updated weights for policy 1, policy_version 52412 (0.0007) -[2023-10-15 04:21:40,871][88298] Updated weights for policy 0, policy_version 52110 (0.0010) -[2023-10-15 04:21:41,232][88298] Updated weights for policy 0, policy_version 52120 (0.0009) -[2023-10-15 04:21:43,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 107053056. Throughput: 0: 1730.0, 1: 1755.1. Samples: 26774242. Policy #0 lag: (min: 14.0, avg: 37.3, max: 40.0) -[2023-10-15 04:21:43,535][87330] Avg episode reward: [(0, '22.770'), (1, '22.470')] -[2023-10-15 04:21:44,694][88300] Updated weights for policy 1, policy_version 52422 (0.0009) -[2023-10-15 04:21:45,078][88300] Updated weights for policy 1, policy_version 52432 (0.0009) -[2023-10-15 04:21:45,292][88298] Updated weights for policy 0, policy_version 52130 (0.0008) -[2023-10-15 04:21:45,443][88300] Updated weights for policy 1, policy_version 52442 (0.0009) -[2023-10-15 04:21:45,714][88298] Updated weights for policy 0, policy_version 52140 (0.0008) -[2023-10-15 04:21:46,085][88298] Updated weights for policy 0, policy_version 52150 (0.0009) -[2023-10-15 04:21:46,456][88298] Updated weights for policy 0, policy_version 52160 (0.0010) -[2023-10-15 04:21:48,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 107118592. Throughput: 0: 1751.4, 1: 1734.4. Samples: 26784438. Policy #0 lag: (min: 14.0, avg: 37.3, max: 40.0) -[2023-10-15 04:21:48,535][87330] Avg episode reward: [(0, '22.930'), (1, '22.370')] -[2023-10-15 04:21:49,350][88300] Updated weights for policy 1, policy_version 52452 (0.0008) -[2023-10-15 04:21:49,718][88300] Updated weights for policy 1, policy_version 52462 (0.0009) -[2023-10-15 04:21:50,087][88300] Updated weights for policy 1, policy_version 52472 (0.0008) -[2023-10-15 04:21:50,339][88298] Updated weights for policy 0, policy_version 52170 (0.0008) -[2023-10-15 04:21:50,720][88298] Updated weights for policy 0, policy_version 52180 (0.0009) -[2023-10-15 04:21:51,092][88298] Updated weights for policy 0, policy_version 52190 (0.0007) -[2023-10-15 04:21:53,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 107184128. Throughput: 0: 1725.7, 1: 1740.7. Samples: 26805012. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:21:53,534][87330] Avg episode reward: [(0, '22.970'), (1, '22.430')] -[2023-10-15 04:21:53,849][88300] Updated weights for policy 1, policy_version 52482 (0.0008) -[2023-10-15 04:21:54,219][88300] Updated weights for policy 1, policy_version 52492 (0.0008) -[2023-10-15 04:21:54,579][88300] Updated weights for policy 1, policy_version 52502 (0.0008) -[2023-10-15 04:21:54,946][88300] Updated weights for policy 1, policy_version 52512 (0.0007) -[2023-10-15 04:21:55,059][88298] Updated weights for policy 0, policy_version 52200 (0.0007) -[2023-10-15 04:21:55,435][88298] Updated weights for policy 0, policy_version 52210 (0.0009) -[2023-10-15 04:21:55,795][88298] Updated weights for policy 0, policy_version 52220 (0.0008) -[2023-10-15 04:21:58,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 107249664. Throughput: 0: 1729.6, 1: 1769.7. Samples: 26826702. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:21:58,535][87330] Avg episode reward: [(0, '23.000'), (1, '22.360')] -[2023-10-15 04:21:58,543][87905] Saving new best policy, reward=23.000! -[2023-10-15 04:21:58,804][88300] Updated weights for policy 1, policy_version 52522 (0.0009) -[2023-10-15 04:21:59,172][88300] Updated weights for policy 1, policy_version 52532 (0.0008) -[2023-10-15 04:21:59,540][88300] Updated weights for policy 1, policy_version 52542 (0.0007) -[2023-10-15 04:21:59,790][88298] Updated weights for policy 0, policy_version 52230 (0.0009) -[2023-10-15 04:22:00,159][88298] Updated weights for policy 0, policy_version 52240 (0.0008) -[2023-10-15 04:22:00,534][88298] Updated weights for policy 0, policy_version 52250 (0.0010) -[2023-10-15 04:22:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 107315200. Throughput: 0: 1719.3, 1: 1732.1. Samples: 26836118. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:22:03,534][87330] Avg episode reward: [(0, '23.000'), (1, '22.350')] -[2023-10-15 04:22:03,565][88300] Updated weights for policy 1, policy_version 52552 (0.0007) -[2023-10-15 04:22:03,927][88300] Updated weights for policy 1, policy_version 52562 (0.0007) -[2023-10-15 04:22:04,295][88300] Updated weights for policy 1, policy_version 52572 (0.0008) -[2023-10-15 04:22:04,444][88298] Updated weights for policy 0, policy_version 52260 (0.0010) -[2023-10-15 04:22:04,819][88298] Updated weights for policy 0, policy_version 52270 (0.0010) -[2023-10-15 04:22:05,189][88298] Updated weights for policy 0, policy_version 52280 (0.0009) -[2023-10-15 04:22:08,217][88300] Updated weights for policy 1, policy_version 52582 (0.0007) -[2023-10-15 04:22:08,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 107380736. Throughput: 0: 1712.0, 1: 1758.2. Samples: 26857096. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:22:08,535][87330] Avg episode reward: [(0, '22.990'), (1, '22.330')] -[2023-10-15 04:22:08,589][88300] Updated weights for policy 1, policy_version 52592 (0.0009) -[2023-10-15 04:22:08,950][88300] Updated weights for policy 1, policy_version 52602 (0.0008) -[2023-10-15 04:22:09,177][88298] Updated weights for policy 0, policy_version 52290 (0.0008) -[2023-10-15 04:22:09,545][88298] Updated weights for policy 0, policy_version 52300 (0.0009) -[2023-10-15 04:22:09,914][88298] Updated weights for policy 0, policy_version 52310 (0.0009) -[2023-10-15 04:22:10,283][88298] Updated weights for policy 0, policy_version 52320 (0.0007) -[2023-10-15 04:22:12,941][88300] Updated weights for policy 1, policy_version 52612 (0.0008) -[2023-10-15 04:22:13,303][88300] Updated weights for policy 1, policy_version 52622 (0.0011) -[2023-10-15 04:22:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 107446272. Throughput: 0: 1732.9, 1: 1743.1. Samples: 26878114. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:22:13,534][87330] Avg episode reward: [(0, '22.980'), (1, '22.560')] -[2023-10-15 04:22:13,677][88300] Updated weights for policy 1, policy_version 52632 (0.0010) -[2023-10-15 04:22:14,171][88298] Updated weights for policy 0, policy_version 52330 (0.0009) -[2023-10-15 04:22:14,540][88298] Updated weights for policy 0, policy_version 52340 (0.0009) -[2023-10-15 04:22:14,913][88298] Updated weights for policy 0, policy_version 52350 (0.0008) -[2023-10-15 04:22:17,470][88300] Updated weights for policy 1, policy_version 52642 (0.0008) -[2023-10-15 04:22:17,850][88300] Updated weights for policy 1, policy_version 52652 (0.0008) -[2023-10-15 04:22:18,223][88300] Updated weights for policy 1, policy_version 52662 (0.0009) -[2023-10-15 04:22:18,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 107511808. Throughput: 0: 1700.0, 1: 1746.6. Samples: 26888058. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:22:18,535][87330] Avg episode reward: [(0, '23.010'), (1, '22.650')] -[2023-10-15 04:22:18,594][88300] Updated weights for policy 1, policy_version 52672 (0.0007) -[2023-10-15 04:22:18,747][88298] Updated weights for policy 0, policy_version 52360 (0.0009) -[2023-10-15 04:22:19,114][88298] Updated weights for policy 0, policy_version 52370 (0.0007) -[2023-10-15 04:22:19,482][88298] Updated weights for policy 0, policy_version 52380 (0.0009) -[2023-10-15 04:22:19,621][87905] Saving new best policy, reward=23.010! -[2023-10-15 04:22:22,425][88300] Updated weights for policy 1, policy_version 52682 (0.0008) -[2023-10-15 04:22:22,788][88300] Updated weights for policy 1, policy_version 52692 (0.0010) -[2023-10-15 04:22:23,158][88300] Updated weights for policy 1, policy_version 52702 (0.0009) -[2023-10-15 04:22:23,354][88298] Updated weights for policy 0, policy_version 52390 (0.0008) -[2023-10-15 04:22:23,534][87330] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 107610112. Throughput: 0: 1734.2, 1: 1752.5. Samples: 26909490. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:22:23,534][87330] Avg episode reward: [(0, '22.960'), (1, '22.670')] -[2023-10-15 04:22:23,722][88298] Updated weights for policy 0, policy_version 52400 (0.0007) -[2023-10-15 04:22:24,098][88298] Updated weights for policy 0, policy_version 52410 (0.0009) -[2023-10-15 04:22:27,077][88300] Updated weights for policy 1, policy_version 52712 (0.0010) -[2023-10-15 04:22:27,441][88300] Updated weights for policy 1, policy_version 52722 (0.0009) -[2023-10-15 04:22:27,814][88300] Updated weights for policy 1, policy_version 52732 (0.0007) -[2023-10-15 04:22:28,081][88298] Updated weights for policy 0, policy_version 52420 (0.0007) -[2023-10-15 04:22:28,458][88298] Updated weights for policy 0, policy_version 52430 (0.0010) -[2023-10-15 04:22:28,534][87330] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 107675648. Throughput: 0: 1740.3, 1: 1719.8. Samples: 26929946. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:22:28,534][87330] Avg episode reward: [(0, '22.940'), (1, '22.720')] -[2023-10-15 04:22:28,822][88298] Updated weights for policy 0, policy_version 52440 (0.0008) -[2023-10-15 04:22:31,903][88300] Updated weights for policy 1, policy_version 52742 (0.0007) -[2023-10-15 04:22:32,266][88300] Updated weights for policy 1, policy_version 52752 (0.0009) -[2023-10-15 04:22:32,634][88300] Updated weights for policy 1, policy_version 52762 (0.0009) -[2023-10-15 04:22:32,935][88298] Updated weights for policy 0, policy_version 52450 (0.0010) -[2023-10-15 04:22:33,341][88298] Updated weights for policy 0, policy_version 52460 (0.0008) -[2023-10-15 04:22:33,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 107741184. Throughput: 0: 1722.3, 1: 1751.3. Samples: 26940748. Policy #0 lag: (min: 24.0, avg: 50.4, max: 56.0) -[2023-10-15 04:22:33,534][87330] Avg episode reward: [(0, '22.920'), (1, '22.900')] -[2023-10-15 04:22:33,707][88298] Updated weights for policy 0, policy_version 52470 (0.0007) -[2023-10-15 04:22:34,080][88298] Updated weights for policy 0, policy_version 52480 (0.0009) -[2023-10-15 04:22:36,454][88300] Updated weights for policy 1, policy_version 52772 (0.0010) -[2023-10-15 04:22:36,820][88300] Updated weights for policy 1, policy_version 52782 (0.0011) -[2023-10-15 04:22:37,181][88300] Updated weights for policy 1, policy_version 52792 (0.0010) -[2023-10-15 04:22:38,018][88298] Updated weights for policy 0, policy_version 52490 (0.0007) -[2023-10-15 04:22:38,384][88298] Updated weights for policy 0, policy_version 52500 (0.0007) -[2023-10-15 04:22:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 107806720. Throughput: 0: 1741.4, 1: 1724.7. Samples: 26960988. Policy #0 lag: (min: 24.0, avg: 50.4, max: 56.0) -[2023-10-15 04:22:38,534][87330] Avg episode reward: [(0, '22.930'), (1, '22.940')] -[2023-10-15 04:22:38,751][88298] Updated weights for policy 0, policy_version 52510 (0.0009) -[2023-10-15 04:22:41,124][88300] Updated weights for policy 1, policy_version 52802 (0.0008) -[2023-10-15 04:22:41,499][88300] Updated weights for policy 1, policy_version 52812 (0.0008) -[2023-10-15 04:22:41,864][88300] Updated weights for policy 1, policy_version 52822 (0.0009) -[2023-10-15 04:22:42,228][88300] Updated weights for policy 1, policy_version 52832 (0.0008) -[2023-10-15 04:22:42,514][88298] Updated weights for policy 0, policy_version 52520 (0.0008) -[2023-10-15 04:22:42,876][88298] Updated weights for policy 0, policy_version 52530 (0.0008) -[2023-10-15 04:22:43,245][88298] Updated weights for policy 0, policy_version 52540 (0.0011) -[2023-10-15 04:22:43,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 107905024. Throughput: 0: 1730.1, 1: 1712.1. Samples: 26981602. Policy #0 lag: (min: 24.0, avg: 50.4, max: 56.0) -[2023-10-15 04:22:43,535][87330] Avg episode reward: [(0, '22.940'), (1, '22.690')] -[2023-10-15 04:22:46,165][88300] Updated weights for policy 1, policy_version 52842 (0.0009) -[2023-10-15 04:22:46,529][88300] Updated weights for policy 1, policy_version 52852 (0.0008) -[2023-10-15 04:22:46,896][88300] Updated weights for policy 1, policy_version 52862 (0.0008) -[2023-10-15 04:22:47,032][88298] Updated weights for policy 0, policy_version 52550 (0.0009) -[2023-10-15 04:22:47,408][88298] Updated weights for policy 0, policy_version 52560 (0.0012) -[2023-10-15 04:22:47,780][88298] Updated weights for policy 0, policy_version 52570 (0.0010) -[2023-10-15 04:22:48,534][87330] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 107970560. Throughput: 0: 1740.7, 1: 1734.1. Samples: 26992486. Policy #0 lag: (min: 24.0, avg: 50.4, max: 56.0) -[2023-10-15 04:22:48,535][87330] Avg episode reward: [(0, '22.940'), (1, '22.600')] -[2023-10-15 04:22:50,869][88300] Updated weights for policy 1, policy_version 52872 (0.0008) -[2023-10-15 04:22:51,247][88300] Updated weights for policy 1, policy_version 52882 (0.0008) -[2023-10-15 04:22:51,610][88300] Updated weights for policy 1, policy_version 52892 (0.0008) -[2023-10-15 04:22:51,835][88298] Updated weights for policy 0, policy_version 52580 (0.0009) -[2023-10-15 04:22:52,216][88298] Updated weights for policy 0, policy_version 52590 (0.0008) -[2023-10-15 04:22:52,583][88298] Updated weights for policy 0, policy_version 52600 (0.0008) -[2023-10-15 04:22:53,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 108036096. Throughput: 0: 1744.1, 1: 1720.1. Samples: 27012986. Policy #0 lag: (min: 24.0, avg: 50.4, max: 56.0) -[2023-10-15 04:22:53,535][87330] Avg episode reward: [(0, '22.940'), (1, '22.610')] -[2023-10-15 04:22:55,379][88300] Updated weights for policy 1, policy_version 52902 (0.0007) -[2023-10-15 04:22:55,741][88300] Updated weights for policy 1, policy_version 52912 (0.0008) -[2023-10-15 04:22:56,104][88300] Updated weights for policy 1, policy_version 52922 (0.0008) -[2023-10-15 04:22:56,388][88298] Updated weights for policy 0, policy_version 52610 (0.0009) -[2023-10-15 04:22:56,760][88298] Updated weights for policy 0, policy_version 52620 (0.0009) -[2023-10-15 04:22:57,120][88298] Updated weights for policy 0, policy_version 52630 (0.0008) -[2023-10-15 04:22:57,492][88298] Updated weights for policy 0, policy_version 52640 (0.0007) -[2023-10-15 04:22:58,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 108101632. Throughput: 0: 1719.6, 1: 1728.6. Samples: 27033284. Policy #0 lag: (min: 24.0, avg: 50.4, max: 56.0) -[2023-10-15 04:22:58,534][87330] Avg episode reward: [(0, '22.940'), (1, '22.490')] -[2023-10-15 04:22:58,544][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000052928_54198272.pth... -[2023-10-15 04:22:58,544][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000052640_53903360.pth... -[2023-10-15 04:22:58,585][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000051296_52527104.pth -[2023-10-15 04:22:58,586][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000051008_52232192.pth -[2023-10-15 04:22:59,917][88300] Updated weights for policy 1, policy_version 52932 (0.0008) -[2023-10-15 04:23:00,288][88300] Updated weights for policy 1, policy_version 52942 (0.0007) -[2023-10-15 04:23:00,644][88300] Updated weights for policy 1, policy_version 52952 (0.0011) -[2023-10-15 04:23:01,449][88298] Updated weights for policy 0, policy_version 52650 (0.0008) -[2023-10-15 04:23:01,812][88298] Updated weights for policy 0, policy_version 52660 (0.0008) -[2023-10-15 04:23:02,187][88298] Updated weights for policy 0, policy_version 52670 (0.0008) -[2023-10-15 04:23:03,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 108167168. Throughput: 0: 1751.8, 1: 1722.0. Samples: 27044378. Policy #0 lag: (min: 24.0, avg: 50.4, max: 56.0) -[2023-10-15 04:23:03,534][87330] Avg episode reward: [(0, '22.890'), (1, '22.400')] -[2023-10-15 04:23:04,594][88300] Updated weights for policy 1, policy_version 52962 (0.0011) -[2023-10-15 04:23:04,962][88300] Updated weights for policy 1, policy_version 52972 (0.0010) -[2023-10-15 04:23:05,318][88300] Updated weights for policy 1, policy_version 52982 (0.0011) -[2023-10-15 04:23:05,692][88300] Updated weights for policy 1, policy_version 52992 (0.0008) -[2023-10-15 04:23:06,158][88298] Updated weights for policy 0, policy_version 52680 (0.0007) -[2023-10-15 04:23:06,532][88298] Updated weights for policy 0, policy_version 52690 (0.0009) -[2023-10-15 04:23:06,902][88298] Updated weights for policy 0, policy_version 52700 (0.0007) -[2023-10-15 04:23:08,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 108232704. Throughput: 0: 1727.3, 1: 1731.6. Samples: 27065142. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:23:08,535][87330] Avg episode reward: [(0, '22.850'), (1, '22.300')] -[2023-10-15 04:23:09,637][88300] Updated weights for policy 1, policy_version 53002 (0.0008) -[2023-10-15 04:23:10,010][88300] Updated weights for policy 1, policy_version 53012 (0.0009) -[2023-10-15 04:23:10,375][88300] Updated weights for policy 1, policy_version 53022 (0.0007) -[2023-10-15 04:23:10,832][88298] Updated weights for policy 0, policy_version 52710 (0.0008) -[2023-10-15 04:23:11,195][88298] Updated weights for policy 0, policy_version 52720 (0.0010) -[2023-10-15 04:23:11,560][88298] Updated weights for policy 0, policy_version 52730 (0.0010) -[2023-10-15 04:23:13,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 108298240. Throughput: 0: 1716.7, 1: 1758.8. Samples: 27086344. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:23:13,534][87330] Avg episode reward: [(0, '22.860'), (1, '22.420')] -[2023-10-15 04:23:14,470][88300] Updated weights for policy 1, policy_version 53032 (0.0010) -[2023-10-15 04:23:14,847][88300] Updated weights for policy 1, policy_version 53042 (0.0008) -[2023-10-15 04:23:15,211][88300] Updated weights for policy 1, policy_version 53052 (0.0008) -[2023-10-15 04:23:15,278][88298] Updated weights for policy 0, policy_version 52740 (0.0009) -[2023-10-15 04:23:15,655][88298] Updated weights for policy 0, policy_version 52750 (0.0007) -[2023-10-15 04:23:16,025][88298] Updated weights for policy 0, policy_version 52760 (0.0009) -[2023-10-15 04:23:18,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 108363776. Throughput: 0: 1735.0, 1: 1725.6. Samples: 27096476. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:23:18,535][87330] Avg episode reward: [(0, '22.850'), (1, '22.370')] -[2023-10-15 04:23:19,164][88300] Updated weights for policy 1, policy_version 53062 (0.0008) -[2023-10-15 04:23:19,529][88300] Updated weights for policy 1, policy_version 53072 (0.0007) -[2023-10-15 04:23:19,907][88300] Updated weights for policy 1, policy_version 53082 (0.0009) -[2023-10-15 04:23:19,989][88298] Updated weights for policy 0, policy_version 52770 (0.0010) -[2023-10-15 04:23:20,395][88298] Updated weights for policy 0, policy_version 52780 (0.0008) -[2023-10-15 04:23:20,756][88298] Updated weights for policy 0, policy_version 52790 (0.0009) -[2023-10-15 04:23:21,127][88298] Updated weights for policy 0, policy_version 52800 (0.0008) -[2023-10-15 04:23:23,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 108429312. Throughput: 0: 1717.7, 1: 1749.6. Samples: 27117016. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:23:23,535][87330] Avg episode reward: [(0, '22.880'), (1, '22.450')] -[2023-10-15 04:23:23,803][88300] Updated weights for policy 1, policy_version 53092 (0.0008) -[2023-10-15 04:23:24,181][88300] Updated weights for policy 1, policy_version 53102 (0.0008) -[2023-10-15 04:23:24,548][88300] Updated weights for policy 1, policy_version 53112 (0.0007) -[2023-10-15 04:23:24,944][88298] Updated weights for policy 0, policy_version 52810 (0.0009) -[2023-10-15 04:23:25,311][88298] Updated weights for policy 0, policy_version 52820 (0.0008) -[2023-10-15 04:23:25,687][88298] Updated weights for policy 0, policy_version 52830 (0.0007) -[2023-10-15 04:23:28,348][88300] Updated weights for policy 1, policy_version 53122 (0.0008) -[2023-10-15 04:23:28,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 108494848. Throughput: 0: 1728.7, 1: 1754.6. Samples: 27138352. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:23:28,535][87330] Avg episode reward: [(0, '22.900'), (1, '22.570')] -[2023-10-15 04:23:28,713][88300] Updated weights for policy 1, policy_version 53132 (0.0008) -[2023-10-15 04:23:29,088][88300] Updated weights for policy 1, policy_version 53142 (0.0007) -[2023-10-15 04:23:29,455][88300] Updated weights for policy 1, policy_version 53152 (0.0008) -[2023-10-15 04:23:29,661][88298] Updated weights for policy 0, policy_version 52840 (0.0009) -[2023-10-15 04:23:30,037][88298] Updated weights for policy 0, policy_version 52850 (0.0011) -[2023-10-15 04:23:30,411][88298] Updated weights for policy 0, policy_version 52860 (0.0007) -[2023-10-15 04:23:33,317][88300] Updated weights for policy 1, policy_version 53162 (0.0007) -[2023-10-15 04:23:33,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 108560384. Throughput: 0: 1720.0, 1: 1734.4. Samples: 27147938. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:23:33,534][87330] Avg episode reward: [(0, '22.920'), (1, '22.600')] -[2023-10-15 04:23:33,688][88300] Updated weights for policy 1, policy_version 53172 (0.0010) -[2023-10-15 04:23:34,064][88300] Updated weights for policy 1, policy_version 53182 (0.0009) -[2023-10-15 04:23:34,393][88298] Updated weights for policy 0, policy_version 52870 (0.0008) -[2023-10-15 04:23:34,765][88298] Updated weights for policy 0, policy_version 52880 (0.0008) -[2023-10-15 04:23:35,140][88298] Updated weights for policy 0, policy_version 52890 (0.0007) -[2023-10-15 04:23:38,068][88300] Updated weights for policy 1, policy_version 53192 (0.0008) -[2023-10-15 04:23:38,439][88300] Updated weights for policy 1, policy_version 53202 (0.0008) -[2023-10-15 04:23:38,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 108625920. Throughput: 0: 1722.1, 1: 1752.9. Samples: 27169360. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:23:38,534][87330] Avg episode reward: [(0, '22.990'), (1, '22.610')] -[2023-10-15 04:23:38,792][88300] Updated weights for policy 1, policy_version 53212 (0.0010) -[2023-10-15 04:23:39,115][88298] Updated weights for policy 0, policy_version 52900 (0.0007) -[2023-10-15 04:23:39,476][88298] Updated weights for policy 0, policy_version 52910 (0.0009) -[2023-10-15 04:23:39,855][88298] Updated weights for policy 0, policy_version 52920 (0.0010) -[2023-10-15 04:23:42,720][88300] Updated weights for policy 1, policy_version 53222 (0.0008) -[2023-10-15 04:23:43,085][88300] Updated weights for policy 1, policy_version 53232 (0.0007) -[2023-10-15 04:23:43,449][88300] Updated weights for policy 1, policy_version 53242 (0.0008) -[2023-10-15 04:23:43,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 108691456. Throughput: 0: 1751.2, 1: 1736.8. Samples: 27190244. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:23:43,534][87330] Avg episode reward: [(0, '23.000'), (1, '22.620')] -[2023-10-15 04:23:43,806][88298] Updated weights for policy 0, policy_version 52930 (0.0009) -[2023-10-15 04:23:44,169][88298] Updated weights for policy 0, policy_version 52940 (0.0007) -[2023-10-15 04:23:44,540][88298] Updated weights for policy 0, policy_version 52950 (0.0007) -[2023-10-15 04:23:44,915][88298] Updated weights for policy 0, policy_version 52960 (0.0009) -[2023-10-15 04:23:47,200][88300] Updated weights for policy 1, policy_version 53252 (0.0010) -[2023-10-15 04:23:47,568][88300] Updated weights for policy 1, policy_version 53262 (0.0009) -[2023-10-15 04:23:47,932][88300] Updated weights for policy 1, policy_version 53272 (0.0009) -[2023-10-15 04:23:48,534][87330] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 108789760. Throughput: 0: 1718.4, 1: 1753.6. Samples: 27200616. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-15 04:23:48,534][87330] Avg episode reward: [(0, '22.950'), (1, '22.700')] -[2023-10-15 04:23:48,873][88298] Updated weights for policy 0, policy_version 52970 (0.0011) -[2023-10-15 04:23:49,249][88298] Updated weights for policy 0, policy_version 52980 (0.0010) -[2023-10-15 04:23:49,610][88298] Updated weights for policy 0, policy_version 52990 (0.0010) -[2023-10-15 04:23:51,874][88300] Updated weights for policy 1, policy_version 53282 (0.0010) -[2023-10-15 04:23:52,246][88300] Updated weights for policy 1, policy_version 53292 (0.0007) -[2023-10-15 04:23:52,616][88300] Updated weights for policy 1, policy_version 53302 (0.0007) -[2023-10-15 04:23:52,978][88300] Updated weights for policy 1, policy_version 53312 (0.0009) -[2023-10-15 04:23:53,435][88298] Updated weights for policy 0, policy_version 53000 (0.0009) -[2023-10-15 04:23:53,534][87330] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 108855296. Throughput: 0: 1745.9, 1: 1738.6. Samples: 27221946. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-15 04:23:53,535][87330] Avg episode reward: [(0, '22.940'), (1, '22.680')] -[2023-10-15 04:23:53,806][88298] Updated weights for policy 0, policy_version 53010 (0.0008) -[2023-10-15 04:23:54,180][88298] Updated weights for policy 0, policy_version 53020 (0.0007) -[2023-10-15 04:23:56,847][88300] Updated weights for policy 1, policy_version 53322 (0.0009) -[2023-10-15 04:23:57,208][88300] Updated weights for policy 1, policy_version 53332 (0.0009) -[2023-10-15 04:23:57,576][88300] Updated weights for policy 1, policy_version 53342 (0.0010) -[2023-10-15 04:23:58,083][88298] Updated weights for policy 0, policy_version 53030 (0.0007) -[2023-10-15 04:23:58,448][88298] Updated weights for policy 0, policy_version 53040 (0.0007) -[2023-10-15 04:23:58,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 108920832. Throughput: 0: 1753.2, 1: 1720.5. Samples: 27242664. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-15 04:23:58,534][87330] Avg episode reward: [(0, '22.930'), (1, '22.700')] -[2023-10-15 04:23:58,822][88298] Updated weights for policy 0, policy_version 53050 (0.0007) -[2023-10-15 04:24:01,398][88300] Updated weights for policy 1, policy_version 53352 (0.0010) -[2023-10-15 04:24:01,774][88300] Updated weights for policy 1, policy_version 53362 (0.0011) -[2023-10-15 04:24:02,137][88300] Updated weights for policy 1, policy_version 53372 (0.0010) -[2023-10-15 04:24:02,708][88298] Updated weights for policy 0, policy_version 53060 (0.0009) -[2023-10-15 04:24:03,088][88298] Updated weights for policy 0, policy_version 53070 (0.0008) -[2023-10-15 04:24:03,461][88298] Updated weights for policy 0, policy_version 53080 (0.0007) -[2023-10-15 04:24:03,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 108986368. Throughput: 0: 1735.0, 1: 1753.0. Samples: 27253438. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-15 04:24:03,535][87330] Avg episode reward: [(0, '22.740'), (1, '22.800')] -[2023-10-15 04:24:06,094][88300] Updated weights for policy 1, policy_version 53382 (0.0007) -[2023-10-15 04:24:06,464][88300] Updated weights for policy 1, policy_version 53392 (0.0009) -[2023-10-15 04:24:06,822][88300] Updated weights for policy 1, policy_version 53402 (0.0008) -[2023-10-15 04:24:07,320][88298] Updated weights for policy 0, policy_version 53090 (0.0008) -[2023-10-15 04:24:07,741][88298] Updated weights for policy 0, policy_version 53100 (0.0011) -[2023-10-15 04:24:08,103][88298] Updated weights for policy 0, policy_version 53110 (0.0007) -[2023-10-15 04:24:08,474][88298] Updated weights for policy 0, policy_version 53120 (0.0009) -[2023-10-15 04:24:08,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 109084672. Throughput: 0: 1754.0, 1: 1725.9. Samples: 27273608. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-15 04:24:08,534][87330] Avg episode reward: [(0, '22.680'), (1, '22.700')] -[2023-10-15 04:24:10,866][88300] Updated weights for policy 1, policy_version 53412 (0.0008) -[2023-10-15 04:24:11,234][88300] Updated weights for policy 1, policy_version 53422 (0.0009) -[2023-10-15 04:24:11,595][88300] Updated weights for policy 1, policy_version 53432 (0.0010) -[2023-10-15 04:24:12,276][88298] Updated weights for policy 0, policy_version 53130 (0.0009) -[2023-10-15 04:24:12,650][88298] Updated weights for policy 0, policy_version 53140 (0.0009) -[2023-10-15 04:24:13,015][88298] Updated weights for policy 0, policy_version 53150 (0.0011) -[2023-10-15 04:24:13,534][87330] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 109150208. Throughput: 0: 1738.4, 1: 1725.7. Samples: 27294236. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-15 04:24:13,534][87330] Avg episode reward: [(0, '22.680'), (1, '22.770')] -[2023-10-15 04:24:15,376][88300] Updated weights for policy 1, policy_version 53442 (0.0009) -[2023-10-15 04:24:15,741][88300] Updated weights for policy 1, policy_version 53452 (0.0010) -[2023-10-15 04:24:16,113][88300] Updated weights for policy 1, policy_version 53462 (0.0008) -[2023-10-15 04:24:16,480][88300] Updated weights for policy 1, policy_version 53472 (0.0009) -[2023-10-15 04:24:17,188][88298] Updated weights for policy 0, policy_version 53160 (0.0007) -[2023-10-15 04:24:17,558][88298] Updated weights for policy 0, policy_version 53170 (0.0008) -[2023-10-15 04:24:17,932][88298] Updated weights for policy 0, policy_version 53180 (0.0009) -[2023-10-15 04:24:18,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 109215744. Throughput: 0: 1752.8, 1: 1734.2. Samples: 27304854. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-15 04:24:18,535][87330] Avg episode reward: [(0, '22.700'), (1, '22.840')] -[2023-10-15 04:24:20,413][88300] Updated weights for policy 1, policy_version 53482 (0.0009) -[2023-10-15 04:24:20,776][88300] Updated weights for policy 1, policy_version 53492 (0.0008) -[2023-10-15 04:24:21,150][88300] Updated weights for policy 1, policy_version 53502 (0.0009) -[2023-10-15 04:24:21,971][88298] Updated weights for policy 0, policy_version 53190 (0.0009) -[2023-10-15 04:24:22,343][88298] Updated weights for policy 0, policy_version 53200 (0.0007) -[2023-10-15 04:24:22,713][88298] Updated weights for policy 0, policy_version 53210 (0.0007) -[2023-10-15 04:24:23,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 109281280. Throughput: 0: 1749.7, 1: 1723.0. Samples: 27325634. Policy #0 lag: (min: 31.0, avg: 44.7, max: 63.0) -[2023-10-15 04:24:23,534][87330] Avg episode reward: [(0, '22.710'), (1, '22.810')] -[2023-10-15 04:24:25,079][88300] Updated weights for policy 1, policy_version 53512 (0.0008) -[2023-10-15 04:24:25,443][88300] Updated weights for policy 1, policy_version 53522 (0.0008) -[2023-10-15 04:24:25,825][88300] Updated weights for policy 1, policy_version 53532 (0.0009) -[2023-10-15 04:24:26,750][88298] Updated weights for policy 0, policy_version 53220 (0.0008) -[2023-10-15 04:24:27,112][88298] Updated weights for policy 0, policy_version 53230 (0.0010) -[2023-10-15 04:24:27,482][88298] Updated weights for policy 0, policy_version 53240 (0.0010) -[2023-10-15 04:24:28,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 109346816. Throughput: 0: 1716.7, 1: 1742.8. Samples: 27345918. Policy #0 lag: (min: 31.0, avg: 44.7, max: 63.0) -[2023-10-15 04:24:28,535][87330] Avg episode reward: [(0, '22.570'), (1, '22.830')] -[2023-10-15 04:24:29,676][88300] Updated weights for policy 1, policy_version 53542 (0.0008) -[2023-10-15 04:24:30,042][88300] Updated weights for policy 1, policy_version 53552 (0.0009) -[2023-10-15 04:24:30,423][88300] Updated weights for policy 1, policy_version 53562 (0.0008) -[2023-10-15 04:24:31,283][88298] Updated weights for policy 0, policy_version 53250 (0.0008) -[2023-10-15 04:24:31,649][88298] Updated weights for policy 0, policy_version 53260 (0.0007) -[2023-10-15 04:24:32,025][88298] Updated weights for policy 0, policy_version 53270 (0.0007) -[2023-10-15 04:24:32,394][88298] Updated weights for policy 0, policy_version 53280 (0.0007) -[2023-10-15 04:24:33,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 109412352. Throughput: 0: 1745.7, 1: 1723.2. Samples: 27356716. Policy #0 lag: (min: 31.0, avg: 44.7, max: 63.0) -[2023-10-15 04:24:33,535][87330] Avg episode reward: [(0, '22.760'), (1, '22.810')] -[2023-10-15 04:24:34,394][88300] Updated weights for policy 1, policy_version 53572 (0.0008) -[2023-10-15 04:24:34,768][88300] Updated weights for policy 1, policy_version 53582 (0.0009) -[2023-10-15 04:24:35,131][88300] Updated weights for policy 1, policy_version 53592 (0.0009) -[2023-10-15 04:24:36,321][88298] Updated weights for policy 0, policy_version 53290 (0.0008) -[2023-10-15 04:24:36,689][88298] Updated weights for policy 0, policy_version 53300 (0.0009) -[2023-10-15 04:24:37,048][88298] Updated weights for policy 0, policy_version 53310 (0.0007) -[2023-10-15 04:24:38,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 109477888. Throughput: 0: 1716.8, 1: 1741.1. Samples: 27377550. Policy #0 lag: (min: 31.0, avg: 44.7, max: 63.0) -[2023-10-15 04:24:38,535][87330] Avg episode reward: [(0, '22.770'), (1, '22.910')] -[2023-10-15 04:24:39,019][88300] Updated weights for policy 1, policy_version 53602 (0.0008) -[2023-10-15 04:24:39,383][88300] Updated weights for policy 1, policy_version 53612 (0.0010) -[2023-10-15 04:24:39,760][88300] Updated weights for policy 1, policy_version 53622 (0.0011) -[2023-10-15 04:24:40,121][88300] Updated weights for policy 1, policy_version 53632 (0.0010) -[2023-10-15 04:24:40,842][88298] Updated weights for policy 0, policy_version 53320 (0.0007) -[2023-10-15 04:24:41,216][88298] Updated weights for policy 0, policy_version 53330 (0.0009) -[2023-10-15 04:24:41,577][88298] Updated weights for policy 0, policy_version 53340 (0.0007) -[2023-10-15 04:24:43,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 109543424. Throughput: 0: 1709.6, 1: 1755.2. Samples: 27398578. Policy #0 lag: (min: 31.0, avg: 44.7, max: 63.0) -[2023-10-15 04:24:43,534][87330] Avg episode reward: [(0, '22.700'), (1, '22.910')] -[2023-10-15 04:24:44,028][88300] Updated weights for policy 1, policy_version 53642 (0.0010) -[2023-10-15 04:24:44,392][88300] Updated weights for policy 1, policy_version 53652 (0.0008) -[2023-10-15 04:24:44,766][88300] Updated weights for policy 1, policy_version 53662 (0.0008) -[2023-10-15 04:24:45,552][88298] Updated weights for policy 0, policy_version 53350 (0.0007) -[2023-10-15 04:24:45,925][88298] Updated weights for policy 0, policy_version 53360 (0.0007) -[2023-10-15 04:24:46,293][88298] Updated weights for policy 0, policy_version 53370 (0.0007) -[2023-10-15 04:24:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 109608960. Throughput: 0: 1728.7, 1: 1726.8. Samples: 27408932. Policy #0 lag: (min: 31.0, avg: 44.7, max: 63.0) -[2023-10-15 04:24:48,534][87330] Avg episode reward: [(0, '22.690'), (1, '22.700')] -[2023-10-15 04:24:48,557][88300] Updated weights for policy 1, policy_version 53672 (0.0010) -[2023-10-15 04:24:48,930][88300] Updated weights for policy 1, policy_version 53682 (0.0011) -[2023-10-15 04:24:49,294][88300] Updated weights for policy 1, policy_version 53692 (0.0010) -[2023-10-15 04:24:50,056][88298] Updated weights for policy 0, policy_version 53380 (0.0007) -[2023-10-15 04:24:50,432][88298] Updated weights for policy 0, policy_version 53390 (0.0009) -[2023-10-15 04:24:50,798][88298] Updated weights for policy 0, policy_version 53400 (0.0008) -[2023-10-15 04:24:53,011][88300] Updated weights for policy 1, policy_version 53702 (0.0009) -[2023-10-15 04:24:53,379][88300] Updated weights for policy 1, policy_version 53712 (0.0007) -[2023-10-15 04:24:53,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 109674496. Throughput: 0: 1710.9, 1: 1767.0. Samples: 27430114. Policy #0 lag: (min: 31.0, avg: 44.7, max: 63.0) -[2023-10-15 04:24:53,534][87330] Avg episode reward: [(0, '22.470'), (1, '22.570')] -[2023-10-15 04:24:53,742][88300] Updated weights for policy 1, policy_version 53722 (0.0010) -[2023-10-15 04:24:54,711][88298] Updated weights for policy 0, policy_version 53410 (0.0008) -[2023-10-15 04:24:55,122][88298] Updated weights for policy 0, policy_version 53420 (0.0007) -[2023-10-15 04:24:55,493][88298] Updated weights for policy 0, policy_version 53430 (0.0007) -[2023-10-15 04:24:55,854][88298] Updated weights for policy 0, policy_version 53440 (0.0008) -[2023-10-15 04:24:57,495][88300] Updated weights for policy 1, policy_version 53732 (0.0012) -[2023-10-15 04:24:57,862][88300] Updated weights for policy 1, policy_version 53742 (0.0012) -[2023-10-15 04:24:58,228][88300] Updated weights for policy 1, policy_version 53752 (0.0009) -[2023-10-15 04:24:58,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 109772800. Throughput: 0: 1730.5, 1: 1748.8. Samples: 27450802. Policy #0 lag: (min: 31.0, avg: 44.7, max: 63.0) -[2023-10-15 04:24:58,535][87330] Avg episode reward: [(0, '22.460'), (1, '22.520')] -[2023-10-15 04:24:58,544][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000053760_55050240.pth... -[2023-10-15 04:24:58,544][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000053440_54722560.pth... -[2023-10-15 04:24:58,580][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000051840_53084160.pth -[2023-10-15 04:24:58,583][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000052128_53379072.pth -[2023-10-15 04:24:59,726][88298] Updated weights for policy 0, policy_version 53450 (0.0009) -[2023-10-15 04:25:00,101][88298] Updated weights for policy 0, policy_version 53460 (0.0008) -[2023-10-15 04:25:00,473][88298] Updated weights for policy 0, policy_version 53470 (0.0007) -[2023-10-15 04:25:02,142][88300] Updated weights for policy 1, policy_version 53762 (0.0008) -[2023-10-15 04:25:02,508][88300] Updated weights for policy 1, policy_version 53772 (0.0007) -[2023-10-15 04:25:02,876][88300] Updated weights for policy 1, policy_version 53782 (0.0008) -[2023-10-15 04:25:03,249][88300] Updated weights for policy 1, policy_version 53792 (0.0008) -[2023-10-15 04:25:03,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 109838336. Throughput: 0: 1711.4, 1: 1763.9. Samples: 27461242. Policy #0 lag: (min: 31.0, avg: 43.5, max: 63.0) -[2023-10-15 04:25:03,534][87330] Avg episode reward: [(0, '22.600'), (1, '22.530')] -[2023-10-15 04:25:04,286][88298] Updated weights for policy 0, policy_version 53480 (0.0009) -[2023-10-15 04:25:04,654][88298] Updated weights for policy 0, policy_version 53490 (0.0008) -[2023-10-15 04:25:05,029][88298] Updated weights for policy 0, policy_version 53500 (0.0008) -[2023-10-15 04:25:07,174][88300] Updated weights for policy 1, policy_version 53802 (0.0007) -[2023-10-15 04:25:07,544][88300] Updated weights for policy 1, policy_version 53812 (0.0008) -[2023-10-15 04:25:07,914][88300] Updated weights for policy 1, policy_version 53822 (0.0008) -[2023-10-15 04:25:08,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 109903872. Throughput: 0: 1714.6, 1: 1769.7. Samples: 27482428. Policy #0 lag: (min: 31.0, avg: 43.5, max: 63.0) -[2023-10-15 04:25:08,535][87330] Avg episode reward: [(0, '22.590'), (1, '22.500')] -[2023-10-15 04:25:09,037][88298] Updated weights for policy 0, policy_version 53510 (0.0009) -[2023-10-15 04:25:09,405][88298] Updated weights for policy 0, policy_version 53520 (0.0010) -[2023-10-15 04:25:09,784][88298] Updated weights for policy 0, policy_version 53530 (0.0010) -[2023-10-15 04:25:11,741][88300] Updated weights for policy 1, policy_version 53832 (0.0009) -[2023-10-15 04:25:12,121][88300] Updated weights for policy 1, policy_version 53842 (0.0007) -[2023-10-15 04:25:12,484][88300] Updated weights for policy 1, policy_version 53852 (0.0009) -[2023-10-15 04:25:13,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 109969408. Throughput: 0: 1744.7, 1: 1745.8. Samples: 27502992. Policy #0 lag: (min: 31.0, avg: 43.5, max: 63.0) -[2023-10-15 04:25:13,535][87330] Avg episode reward: [(0, '22.720'), (1, '22.500')] -[2023-10-15 04:25:13,713][88298] Updated weights for policy 0, policy_version 53540 (0.0010) -[2023-10-15 04:25:14,070][88298] Updated weights for policy 0, policy_version 53550 (0.0011) -[2023-10-15 04:25:14,442][88298] Updated weights for policy 0, policy_version 53560 (0.0009) -[2023-10-15 04:25:16,487][88300] Updated weights for policy 1, policy_version 53862 (0.0008) -[2023-10-15 04:25:16,859][88300] Updated weights for policy 1, policy_version 53872 (0.0008) -[2023-10-15 04:25:17,225][88300] Updated weights for policy 1, policy_version 53882 (0.0007) -[2023-10-15 04:25:18,252][88298] Updated weights for policy 0, policy_version 53570 (0.0009) -[2023-10-15 04:25:18,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 110034944. Throughput: 0: 1712.9, 1: 1774.2. Samples: 27513634. Policy #0 lag: (min: 31.0, avg: 43.5, max: 63.0) -[2023-10-15 04:25:18,534][87330] Avg episode reward: [(0, '22.720'), (1, '22.440')] -[2023-10-15 04:25:18,615][88298] Updated weights for policy 0, policy_version 53580 (0.0007) -[2023-10-15 04:25:18,989][88298] Updated weights for policy 0, policy_version 53590 (0.0008) -[2023-10-15 04:25:19,359][88298] Updated weights for policy 0, policy_version 53600 (0.0011) -[2023-10-15 04:25:21,096][88300] Updated weights for policy 1, policy_version 53892 (0.0008) -[2023-10-15 04:25:21,464][88300] Updated weights for policy 1, policy_version 53902 (0.0009) -[2023-10-15 04:25:21,830][88300] Updated weights for policy 1, policy_version 53912 (0.0007) -[2023-10-15 04:25:23,319][88298] Updated weights for policy 0, policy_version 53610 (0.0010) -[2023-10-15 04:25:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 110100480. Throughput: 0: 1740.6, 1: 1738.2. Samples: 27534098. Policy #0 lag: (min: 31.0, avg: 43.5, max: 63.0) -[2023-10-15 04:25:23,535][87330] Avg episode reward: [(0, '22.900'), (1, '22.450')] -[2023-10-15 04:25:23,687][88298] Updated weights for policy 0, policy_version 53620 (0.0010) -[2023-10-15 04:25:24,064][88298] Updated weights for policy 0, policy_version 53630 (0.0009) -[2023-10-15 04:25:25,760][88300] Updated weights for policy 1, policy_version 53922 (0.0008) -[2023-10-15 04:25:26,116][88300] Updated weights for policy 1, policy_version 53932 (0.0009) -[2023-10-15 04:25:26,489][88300] Updated weights for policy 1, policy_version 53942 (0.0008) -[2023-10-15 04:25:26,861][88300] Updated weights for policy 1, policy_version 53952 (0.0008) -[2023-10-15 04:25:27,950][88298] Updated weights for policy 0, policy_version 53640 (0.0008) -[2023-10-15 04:25:28,318][88298] Updated weights for policy 0, policy_version 53650 (0.0010) -[2023-10-15 04:25:28,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 110166016. Throughput: 0: 1746.3, 1: 1744.4. Samples: 27555658. Policy #0 lag: (min: 31.0, avg: 43.5, max: 63.0) -[2023-10-15 04:25:28,535][87330] Avg episode reward: [(0, '22.930'), (1, '22.620')] -[2023-10-15 04:25:28,684][88298] Updated weights for policy 0, policy_version 53660 (0.0010) -[2023-10-15 04:25:30,730][88300] Updated weights for policy 1, policy_version 53962 (0.0007) -[2023-10-15 04:25:31,094][88300] Updated weights for policy 1, policy_version 53972 (0.0008) -[2023-10-15 04:25:31,452][88300] Updated weights for policy 1, policy_version 53982 (0.0009) -[2023-10-15 04:25:32,604][88298] Updated weights for policy 0, policy_version 53670 (0.0009) -[2023-10-15 04:25:32,973][88298] Updated weights for policy 0, policy_version 53680 (0.0010) -[2023-10-15 04:25:33,346][88298] Updated weights for policy 0, policy_version 53690 (0.0007) -[2023-10-15 04:25:33,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 110231552. Throughput: 0: 1728.8, 1: 1753.6. Samples: 27565640. Policy #0 lag: (min: 31.0, avg: 43.5, max: 63.0) -[2023-10-15 04:25:33,534][87330] Avg episode reward: [(0, '22.940'), (1, '22.640')] -[2023-10-15 04:25:35,300][88300] Updated weights for policy 1, policy_version 53992 (0.0009) -[2023-10-15 04:25:35,669][88300] Updated weights for policy 1, policy_version 54002 (0.0007) -[2023-10-15 04:25:36,035][88300] Updated weights for policy 1, policy_version 54012 (0.0008) -[2023-10-15 04:25:37,370][88298] Updated weights for policy 0, policy_version 53700 (0.0007) -[2023-10-15 04:25:37,741][88298] Updated weights for policy 0, policy_version 53710 (0.0008) -[2023-10-15 04:25:38,106][88298] Updated weights for policy 0, policy_version 53720 (0.0009) -[2023-10-15 04:25:38,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 110329856. Throughput: 0: 1748.7, 1: 1733.3. Samples: 27586802. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:25:38,534][87330] Avg episode reward: [(0, '22.960'), (1, '22.690')] -[2023-10-15 04:25:39,859][88300] Updated weights for policy 1, policy_version 54022 (0.0007) -[2023-10-15 04:25:40,230][88300] Updated weights for policy 1, policy_version 54032 (0.0007) -[2023-10-15 04:25:40,596][88300] Updated weights for policy 1, policy_version 54042 (0.0007) -[2023-10-15 04:25:42,223][88298] Updated weights for policy 0, policy_version 53730 (0.0008) -[2023-10-15 04:25:42,628][88298] Updated weights for policy 0, policy_version 53740 (0.0008) -[2023-10-15 04:25:43,008][88298] Updated weights for policy 0, policy_version 53750 (0.0008) -[2023-10-15 04:25:43,376][88298] Updated weights for policy 0, policy_version 53760 (0.0010) -[2023-10-15 04:25:43,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 110395392. Throughput: 0: 1724.4, 1: 1759.7. Samples: 27607586. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:25:43,534][87330] Avg episode reward: [(0, '22.760'), (1, '22.690')] -[2023-10-15 04:25:44,493][88300] Updated weights for policy 1, policy_version 54052 (0.0008) -[2023-10-15 04:25:44,859][88300] Updated weights for policy 1, policy_version 54062 (0.0008) -[2023-10-15 04:25:45,221][88300] Updated weights for policy 1, policy_version 54072 (0.0008) -[2023-10-15 04:25:47,206][88298] Updated weights for policy 0, policy_version 53770 (0.0009) -[2023-10-15 04:25:47,582][88298] Updated weights for policy 0, policy_version 53780 (0.0009) -[2023-10-15 04:25:47,944][88298] Updated weights for policy 0, policy_version 53790 (0.0008) -[2023-10-15 04:25:48,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 110460928. Throughput: 0: 1742.7, 1: 1737.1. Samples: 27617834. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:25:48,535][87330] Avg episode reward: [(0, '22.720'), (1, '22.820')] -[2023-10-15 04:25:49,155][88300] Updated weights for policy 1, policy_version 54082 (0.0008) -[2023-10-15 04:25:49,530][88300] Updated weights for policy 1, policy_version 54092 (0.0007) -[2023-10-15 04:25:49,902][88300] Updated weights for policy 1, policy_version 54102 (0.0007) -[2023-10-15 04:25:50,265][88300] Updated weights for policy 1, policy_version 54112 (0.0008) -[2023-10-15 04:25:51,802][88298] Updated weights for policy 0, policy_version 53800 (0.0010) -[2023-10-15 04:25:52,174][88298] Updated weights for policy 0, policy_version 53810 (0.0011) -[2023-10-15 04:25:52,539][88298] Updated weights for policy 0, policy_version 53820 (0.0010) -[2023-10-15 04:25:53,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 110526464. Throughput: 0: 1737.4, 1: 1746.4. Samples: 27639202. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:25:53,534][87330] Avg episode reward: [(0, '22.550'), (1, '22.930')] -[2023-10-15 04:25:54,026][88300] Updated weights for policy 1, policy_version 54122 (0.0009) -[2023-10-15 04:25:54,382][88300] Updated weights for policy 1, policy_version 54132 (0.0011) -[2023-10-15 04:25:54,755][88300] Updated weights for policy 1, policy_version 54142 (0.0008) -[2023-10-15 04:25:56,615][88298] Updated weights for policy 0, policy_version 53830 (0.0008) -[2023-10-15 04:25:56,991][88298] Updated weights for policy 0, policy_version 53840 (0.0009) -[2023-10-15 04:25:57,360][88298] Updated weights for policy 0, policy_version 53850 (0.0008) -[2023-10-15 04:25:58,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 110592000. Throughput: 0: 1713.2, 1: 1770.5. Samples: 27659760. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:25:58,535][87330] Avg episode reward: [(0, '22.550'), (1, '22.840')] -[2023-10-15 04:25:58,753][88300] Updated weights for policy 1, policy_version 54152 (0.0007) -[2023-10-15 04:25:59,130][88300] Updated weights for policy 1, policy_version 54162 (0.0008) -[2023-10-15 04:25:59,499][88300] Updated weights for policy 1, policy_version 54172 (0.0009) -[2023-10-15 04:26:01,175][88298] Updated weights for policy 0, policy_version 53860 (0.0008) -[2023-10-15 04:26:01,548][88298] Updated weights for policy 0, policy_version 53870 (0.0008) -[2023-10-15 04:26:01,924][88298] Updated weights for policy 0, policy_version 53880 (0.0007) -[2023-10-15 04:26:03,426][88300] Updated weights for policy 1, policy_version 54182 (0.0009) -[2023-10-15 04:26:03,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 110657536. Throughput: 0: 1746.9, 1: 1739.9. Samples: 27670544. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:26:03,535][87330] Avg episode reward: [(0, '22.550'), (1, '22.830')] -[2023-10-15 04:26:03,789][88300] Updated weights for policy 1, policy_version 54192 (0.0010) -[2023-10-15 04:26:04,162][88300] Updated weights for policy 1, policy_version 54202 (0.0011) -[2023-10-15 04:26:05,761][88298] Updated weights for policy 0, policy_version 53890 (0.0007) -[2023-10-15 04:26:06,121][88298] Updated weights for policy 0, policy_version 53900 (0.0009) -[2023-10-15 04:26:06,495][88298] Updated weights for policy 0, policy_version 53910 (0.0007) -[2023-10-15 04:26:06,864][88298] Updated weights for policy 0, policy_version 53920 (0.0008) -[2023-10-15 04:26:07,980][88300] Updated weights for policy 1, policy_version 54212 (0.0008) -[2023-10-15 04:26:08,358][88300] Updated weights for policy 1, policy_version 54222 (0.0007) -[2023-10-15 04:26:08,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 110723072. Throughput: 0: 1715.3, 1: 1769.3. Samples: 27690904. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:26:08,535][87330] Avg episode reward: [(0, '22.540'), (1, '22.670')] -[2023-10-15 04:26:08,716][88300] Updated weights for policy 1, policy_version 54232 (0.0008) -[2023-10-15 04:26:10,824][88298] Updated weights for policy 0, policy_version 53930 (0.0008) -[2023-10-15 04:26:11,196][88298] Updated weights for policy 0, policy_version 53940 (0.0007) -[2023-10-15 04:26:11,564][88298] Updated weights for policy 0, policy_version 53950 (0.0009) -[2023-10-15 04:26:12,606][88300] Updated weights for policy 1, policy_version 54242 (0.0007) -[2023-10-15 04:26:12,975][88300] Updated weights for policy 1, policy_version 54252 (0.0009) -[2023-10-15 04:26:13,359][88300] Updated weights for policy 1, policy_version 54262 (0.0008) -[2023-10-15 04:26:13,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 110788608. Throughput: 0: 1714.6, 1: 1749.1. Samples: 27711524. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:26:13,534][87330] Avg episode reward: [(0, '22.510'), (1, '22.670')] -[2023-10-15 04:26:13,717][88300] Updated weights for policy 1, policy_version 54272 (0.0008) -[2023-10-15 04:26:15,465][88298] Updated weights for policy 0, policy_version 53960 (0.0008) -[2023-10-15 04:26:15,843][88298] Updated weights for policy 0, policy_version 53970 (0.0009) -[2023-10-15 04:26:16,222][88298] Updated weights for policy 0, policy_version 53980 (0.0010) -[2023-10-15 04:26:17,500][88300] Updated weights for policy 1, policy_version 54282 (0.0009) -[2023-10-15 04:26:17,856][88300] Updated weights for policy 1, policy_version 54292 (0.0008) -[2023-10-15 04:26:18,222][88300] Updated weights for policy 1, policy_version 54302 (0.0008) -[2023-10-15 04:26:18,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 110886912. Throughput: 0: 1731.5, 1: 1755.2. Samples: 27722542. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-15 04:26:18,535][87330] Avg episode reward: [(0, '22.590'), (1, '22.610')] -[2023-10-15 04:26:20,109][88298] Updated weights for policy 0, policy_version 53990 (0.0009) -[2023-10-15 04:26:20,485][88298] Updated weights for policy 0, policy_version 54000 (0.0012) -[2023-10-15 04:26:20,857][88298] Updated weights for policy 0, policy_version 54010 (0.0007) -[2023-10-15 04:26:22,114][88300] Updated weights for policy 1, policy_version 54312 (0.0008) -[2023-10-15 04:26:22,482][88300] Updated weights for policy 1, policy_version 54322 (0.0008) -[2023-10-15 04:26:22,850][88300] Updated weights for policy 1, policy_version 54332 (0.0008) -[2023-10-15 04:26:23,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 110952448. Throughput: 0: 1713.3, 1: 1757.0. Samples: 27742964. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-15 04:26:23,534][87330] Avg episode reward: [(0, '22.740'), (1, '22.620')] -[2023-10-15 04:26:24,811][88298] Updated weights for policy 0, policy_version 54020 (0.0007) -[2023-10-15 04:26:25,170][88298] Updated weights for policy 0, policy_version 54030 (0.0008) -[2023-10-15 04:26:25,552][88298] Updated weights for policy 0, policy_version 54040 (0.0008) -[2023-10-15 04:26:26,619][88300] Updated weights for policy 1, policy_version 54342 (0.0010) -[2023-10-15 04:26:26,994][88300] Updated weights for policy 1, policy_version 54352 (0.0011) -[2023-10-15 04:26:27,362][88300] Updated weights for policy 1, policy_version 54362 (0.0010) -[2023-10-15 04:26:28,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 111017984. Throughput: 0: 1739.1, 1: 1732.5. Samples: 27763808. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-15 04:26:28,534][87330] Avg episode reward: [(0, '22.770'), (1, '22.740')] -[2023-10-15 04:26:29,443][88298] Updated weights for policy 0, policy_version 54050 (0.0008) -[2023-10-15 04:26:29,843][88298] Updated weights for policy 0, policy_version 54060 (0.0007) -[2023-10-15 04:26:30,219][88298] Updated weights for policy 0, policy_version 54070 (0.0009) -[2023-10-15 04:26:30,590][88298] Updated weights for policy 0, policy_version 54080 (0.0010) -[2023-10-15 04:26:31,371][88300] Updated weights for policy 1, policy_version 54372 (0.0009) -[2023-10-15 04:26:31,747][88300] Updated weights for policy 1, policy_version 54382 (0.0010) -[2023-10-15 04:26:32,115][88300] Updated weights for policy 1, policy_version 54392 (0.0009) -[2023-10-15 04:26:33,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 111083520. Throughput: 0: 1719.0, 1: 1762.6. Samples: 27774508. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-15 04:26:33,534][87330] Avg episode reward: [(0, '22.750'), (1, '22.750')] -[2023-10-15 04:26:34,303][88298] Updated weights for policy 0, policy_version 54090 (0.0010) -[2023-10-15 04:26:34,671][88298] Updated weights for policy 0, policy_version 54100 (0.0009) -[2023-10-15 04:26:35,045][88298] Updated weights for policy 0, policy_version 54110 (0.0007) -[2023-10-15 04:26:36,017][88300] Updated weights for policy 1, policy_version 54402 (0.0008) -[2023-10-15 04:26:36,383][88300] Updated weights for policy 1, policy_version 54412 (0.0009) -[2023-10-15 04:26:36,754][88300] Updated weights for policy 1, policy_version 54422 (0.0010) -[2023-10-15 04:26:37,124][88300] Updated weights for policy 1, policy_version 54432 (0.0009) -[2023-10-15 04:26:38,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 111149056. Throughput: 0: 1732.5, 1: 1727.2. Samples: 27794888. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-15 04:26:38,535][87330] Avg episode reward: [(0, '22.770'), (1, '22.780')] -[2023-10-15 04:26:38,842][88298] Updated weights for policy 0, policy_version 54120 (0.0008) -[2023-10-15 04:26:39,217][88298] Updated weights for policy 0, policy_version 54130 (0.0008) -[2023-10-15 04:26:39,583][88298] Updated weights for policy 0, policy_version 54140 (0.0008) -[2023-10-15 04:26:41,050][88300] Updated weights for policy 1, policy_version 54442 (0.0008) -[2023-10-15 04:26:41,415][88300] Updated weights for policy 1, policy_version 54452 (0.0008) -[2023-10-15 04:26:41,789][88300] Updated weights for policy 1, policy_version 54462 (0.0009) -[2023-10-15 04:26:43,484][88298] Updated weights for policy 0, policy_version 54150 (0.0008) -[2023-10-15 04:26:43,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 111214592. Throughput: 0: 1758.7, 1: 1722.6. Samples: 27816418. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-15 04:26:43,535][87330] Avg episode reward: [(0, '22.750'), (1, '22.830')] -[2023-10-15 04:26:43,853][88298] Updated weights for policy 0, policy_version 54160 (0.0007) -[2023-10-15 04:26:44,225][88298] Updated weights for policy 0, policy_version 54170 (0.0010) -[2023-10-15 04:26:45,879][88300] Updated weights for policy 1, policy_version 54472 (0.0009) -[2023-10-15 04:26:46,247][88300] Updated weights for policy 1, policy_version 54482 (0.0011) -[2023-10-15 04:26:46,613][88300] Updated weights for policy 1, policy_version 54492 (0.0009) -[2023-10-15 04:26:48,156][88298] Updated weights for policy 0, policy_version 54180 (0.0007) -[2023-10-15 04:26:48,517][88298] Updated weights for policy 0, policy_version 54190 (0.0008) -[2023-10-15 04:26:48,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 111280128. Throughput: 0: 1726.3, 1: 1736.0. Samples: 27826348. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-15 04:26:48,535][87330] Avg episode reward: [(0, '22.790'), (1, '22.700')] -[2023-10-15 04:26:48,893][88298] Updated weights for policy 0, policy_version 54200 (0.0008) -[2023-10-15 04:26:50,469][88300] Updated weights for policy 1, policy_version 54502 (0.0009) -[2023-10-15 04:26:50,834][88300] Updated weights for policy 1, policy_version 54512 (0.0010) -[2023-10-15 04:26:51,202][88300] Updated weights for policy 1, policy_version 54522 (0.0010) -[2023-10-15 04:26:52,707][88298] Updated weights for policy 0, policy_version 54210 (0.0008) -[2023-10-15 04:26:53,078][88298] Updated weights for policy 0, policy_version 54220 (0.0008) -[2023-10-15 04:26:53,462][88298] Updated weights for policy 0, policy_version 54230 (0.0009) -[2023-10-15 04:26:53,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 111345664. Throughput: 0: 1757.1, 1: 1720.0. Samples: 27847374. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-15 04:26:53,535][87330] Avg episode reward: [(0, '22.900'), (1, '22.670')] -[2023-10-15 04:26:53,826][88298] Updated weights for policy 0, policy_version 54240 (0.0008) -[2023-10-15 04:26:55,142][88300] Updated weights for policy 1, policy_version 54532 (0.0007) -[2023-10-15 04:26:55,503][88300] Updated weights for policy 1, policy_version 54542 (0.0009) -[2023-10-15 04:26:55,883][88300] Updated weights for policy 1, policy_version 54552 (0.0011) -[2023-10-15 04:26:57,865][88298] Updated weights for policy 0, policy_version 54250 (0.0007) -[2023-10-15 04:26:58,227][88298] Updated weights for policy 0, policy_version 54260 (0.0007) -[2023-10-15 04:26:58,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 111411200. Throughput: 0: 1754.5, 1: 1733.1. Samples: 27868468. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) -[2023-10-15 04:26:58,535][87330] Avg episode reward: [(0, '22.930'), (1, '22.620')] -[2023-10-15 04:26:58,543][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000054560_55869440.pth... -[2023-10-15 04:26:58,579][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000052928_54198272.pth -[2023-10-15 04:26:58,594][88298] Updated weights for policy 0, policy_version 54270 (0.0010) -[2023-10-15 04:26:58,668][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000054272_55574528.pth... -[2023-10-15 04:26:58,706][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000052640_53903360.pth -[2023-10-15 04:26:59,942][88300] Updated weights for policy 1, policy_version 54562 (0.0009) -[2023-10-15 04:27:00,305][88300] Updated weights for policy 1, policy_version 54572 (0.0011) -[2023-10-15 04:27:00,669][88300] Updated weights for policy 1, policy_version 54582 (0.0010) -[2023-10-15 04:27:01,039][88300] Updated weights for policy 1, policy_version 54592 (0.0008) -[2023-10-15 04:27:02,516][88298] Updated weights for policy 0, policy_version 54280 (0.0010) -[2023-10-15 04:27:02,874][88298] Updated weights for policy 0, policy_version 54290 (0.0010) -[2023-10-15 04:27:03,247][88298] Updated weights for policy 0, policy_version 54300 (0.0007) -[2023-10-15 04:27:03,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 111509504. Throughput: 0: 1746.5, 1: 1716.5. Samples: 27878380. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) -[2023-10-15 04:27:03,535][87330] Avg episode reward: [(0, '22.430'), (1, '22.600')] -[2023-10-15 04:27:04,886][88300] Updated weights for policy 1, policy_version 54602 (0.0011) -[2023-10-15 04:27:05,252][88300] Updated weights for policy 1, policy_version 54612 (0.0010) -[2023-10-15 04:27:05,619][88300] Updated weights for policy 1, policy_version 54622 (0.0010) -[2023-10-15 04:27:07,137][88298] Updated weights for policy 0, policy_version 54310 (0.0009) -[2023-10-15 04:27:07,506][88298] Updated weights for policy 0, policy_version 54320 (0.0009) -[2023-10-15 04:27:07,885][88298] Updated weights for policy 0, policy_version 54330 (0.0009) -[2023-10-15 04:27:08,534][87330] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 111575040. Throughput: 0: 1760.3, 1: 1720.8. Samples: 27899614. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) -[2023-10-15 04:27:08,534][87330] Avg episode reward: [(0, '22.370'), (1, '22.600')] -[2023-10-15 04:27:09,545][88300] Updated weights for policy 1, policy_version 54632 (0.0009) -[2023-10-15 04:27:09,913][88300] Updated weights for policy 1, policy_version 54642 (0.0011) -[2023-10-15 04:27:10,288][88300] Updated weights for policy 1, policy_version 54652 (0.0009) -[2023-10-15 04:27:11,720][88298] Updated weights for policy 0, policy_version 54340 (0.0007) -[2023-10-15 04:27:12,091][88298] Updated weights for policy 0, policy_version 54350 (0.0008) -[2023-10-15 04:27:12,467][88298] Updated weights for policy 0, policy_version 54360 (0.0007) -[2023-10-15 04:27:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 111640576. Throughput: 0: 1730.1, 1: 1743.9. Samples: 27920138. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) -[2023-10-15 04:27:13,535][87330] Avg episode reward: [(0, '22.060'), (1, '22.670')] -[2023-10-15 04:27:14,138][88300] Updated weights for policy 1, policy_version 54662 (0.0008) -[2023-10-15 04:27:14,498][88300] Updated weights for policy 1, policy_version 54672 (0.0007) -[2023-10-15 04:27:14,865][88300] Updated weights for policy 1, policy_version 54682 (0.0008) -[2023-10-15 04:27:16,294][88298] Updated weights for policy 0, policy_version 54370 (0.0008) -[2023-10-15 04:27:16,711][88298] Updated weights for policy 0, policy_version 54380 (0.0009) -[2023-10-15 04:27:17,081][88298] Updated weights for policy 0, policy_version 54390 (0.0009) -[2023-10-15 04:27:17,445][88298] Updated weights for policy 0, policy_version 54400 (0.0007) -[2023-10-15 04:27:18,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 111706112. Throughput: 0: 1764.8, 1: 1710.1. Samples: 27930876. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) -[2023-10-15 04:27:18,534][87330] Avg episode reward: [(0, '22.040'), (1, '22.670')] -[2023-10-15 04:27:18,722][88300] Updated weights for policy 1, policy_version 54692 (0.0008) -[2023-10-15 04:27:19,089][88300] Updated weights for policy 1, policy_version 54702 (0.0007) -[2023-10-15 04:27:19,459][88300] Updated weights for policy 1, policy_version 54712 (0.0009) -[2023-10-15 04:27:21,261][88298] Updated weights for policy 0, policy_version 54410 (0.0011) -[2023-10-15 04:27:21,621][88298] Updated weights for policy 0, policy_version 54420 (0.0008) -[2023-10-15 04:27:21,989][88298] Updated weights for policy 0, policy_version 54430 (0.0008) -[2023-10-15 04:27:23,182][88300] Updated weights for policy 1, policy_version 54722 (0.0010) -[2023-10-15 04:27:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 111771648. Throughput: 0: 1730.2, 1: 1752.3. Samples: 27951600. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) -[2023-10-15 04:27:23,535][87330] Avg episode reward: [(0, '22.060'), (1, '22.850')] -[2023-10-15 04:27:23,556][88300] Updated weights for policy 1, policy_version 54732 (0.0009) -[2023-10-15 04:27:23,915][88300] Updated weights for policy 1, policy_version 54742 (0.0009) -[2023-10-15 04:27:24,285][88300] Updated weights for policy 1, policy_version 54752 (0.0009) -[2023-10-15 04:27:26,042][88298] Updated weights for policy 0, policy_version 54440 (0.0009) -[2023-10-15 04:27:26,405][88298] Updated weights for policy 0, policy_version 54450 (0.0008) -[2023-10-15 04:27:26,777][88298] Updated weights for policy 0, policy_version 54460 (0.0008) -[2023-10-15 04:27:28,134][88300] Updated weights for policy 1, policy_version 54762 (0.0008) -[2023-10-15 04:27:28,517][88300] Updated weights for policy 1, policy_version 54772 (0.0009) -[2023-10-15 04:27:28,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 111837184. Throughput: 0: 1722.0, 1: 1746.3. Samples: 27972492. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) -[2023-10-15 04:27:28,535][87330] Avg episode reward: [(0, '21.560'), (1, '22.920')] -[2023-10-15 04:27:28,888][88300] Updated weights for policy 1, policy_version 54782 (0.0009) -[2023-10-15 04:27:30,519][88298] Updated weights for policy 0, policy_version 54470 (0.0007) -[2023-10-15 04:27:30,895][88298] Updated weights for policy 0, policy_version 54480 (0.0009) -[2023-10-15 04:27:31,256][88298] Updated weights for policy 0, policy_version 54490 (0.0010) -[2023-10-15 04:27:32,785][88300] Updated weights for policy 1, policy_version 54792 (0.0010) -[2023-10-15 04:27:33,160][88300] Updated weights for policy 1, policy_version 54802 (0.0010) -[2023-10-15 04:27:33,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 111902720. Throughput: 0: 1742.6, 1: 1746.8. Samples: 27983370. Policy #0 lag: (min: 30.0, avg: 36.9, max: 62.0) -[2023-10-15 04:27:33,534][87330] Avg episode reward: [(0, '21.990'), (1, '22.900')] -[2023-10-15 04:27:33,538][88300] Updated weights for policy 1, policy_version 54812 (0.0008) -[2023-10-15 04:27:35,294][88298] Updated weights for policy 0, policy_version 54500 (0.0008) -[2023-10-15 04:27:35,669][88298] Updated weights for policy 0, policy_version 54510 (0.0008) -[2023-10-15 04:27:36,043][88298] Updated weights for policy 0, policy_version 54520 (0.0008) -[2023-10-15 04:27:37,439][88300] Updated weights for policy 1, policy_version 54822 (0.0007) -[2023-10-15 04:27:37,805][88300] Updated weights for policy 1, policy_version 54832 (0.0009) -[2023-10-15 04:27:38,175][88300] Updated weights for policy 1, policy_version 54842 (0.0009) -[2023-10-15 04:27:38,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 112001024. Throughput: 0: 1723.3, 1: 1757.6. Samples: 28004016. Policy #0 lag: (min: 30.0, avg: 36.9, max: 62.0) -[2023-10-15 04:27:38,535][87330] Avg episode reward: [(0, '21.810'), (1, '22.830')] -[2023-10-15 04:27:40,146][88298] Updated weights for policy 0, policy_version 54530 (0.0007) -[2023-10-15 04:27:40,506][88298] Updated weights for policy 0, policy_version 54540 (0.0009) -[2023-10-15 04:27:40,878][88298] Updated weights for policy 0, policy_version 54550 (0.0007) -[2023-10-15 04:27:41,250][88298] Updated weights for policy 0, policy_version 54560 (0.0007) -[2023-10-15 04:27:41,981][88300] Updated weights for policy 1, policy_version 54852 (0.0008) -[2023-10-15 04:27:42,337][88300] Updated weights for policy 1, policy_version 54862 (0.0010) -[2023-10-15 04:27:42,695][88300] Updated weights for policy 1, policy_version 54872 (0.0007) -[2023-10-15 04:27:43,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 112066560. Throughput: 0: 1725.0, 1: 1735.2. Samples: 28024178. Policy #0 lag: (min: 30.0, avg: 36.9, max: 62.0) -[2023-10-15 04:27:43,535][87330] Avg episode reward: [(0, '21.960'), (1, '22.810')] -[2023-10-15 04:27:45,267][88298] Updated weights for policy 0, policy_version 54570 (0.0008) -[2023-10-15 04:27:45,636][88298] Updated weights for policy 0, policy_version 54580 (0.0008) -[2023-10-15 04:27:46,011][88298] Updated weights for policy 0, policy_version 54590 (0.0009) -[2023-10-15 04:27:46,581][88300] Updated weights for policy 1, policy_version 54882 (0.0008) -[2023-10-15 04:27:46,948][88300] Updated weights for policy 1, policy_version 54892 (0.0010) -[2023-10-15 04:27:47,324][88300] Updated weights for policy 1, policy_version 54902 (0.0009) -[2023-10-15 04:27:47,688][88300] Updated weights for policy 1, policy_version 54912 (0.0008) -[2023-10-15 04:27:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 112132096. Throughput: 0: 1722.8, 1: 1767.4. Samples: 28035436. Policy #0 lag: (min: 30.0, avg: 36.9, max: 62.0) -[2023-10-15 04:27:48,535][87330] Avg episode reward: [(0, '22.120'), (1, '22.850')] -[2023-10-15 04:27:49,918][88298] Updated weights for policy 0, policy_version 54600 (0.0009) -[2023-10-15 04:27:50,298][88298] Updated weights for policy 0, policy_version 54610 (0.0008) -[2023-10-15 04:27:50,664][88298] Updated weights for policy 0, policy_version 54620 (0.0008) -[2023-10-15 04:27:51,507][88300] Updated weights for policy 1, policy_version 54922 (0.0007) -[2023-10-15 04:27:51,877][88300] Updated weights for policy 1, policy_version 54932 (0.0007) -[2023-10-15 04:27:52,235][88300] Updated weights for policy 1, policy_version 54942 (0.0008) -[2023-10-15 04:27:53,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 112197632. Throughput: 0: 1713.7, 1: 1747.4. Samples: 28055364. Policy #0 lag: (min: 30.0, avg: 36.9, max: 62.0) -[2023-10-15 04:27:53,535][87330] Avg episode reward: [(0, '22.110'), (1, '22.720')] -[2023-10-15 04:27:54,655][88298] Updated weights for policy 0, policy_version 54630 (0.0008) -[2023-10-15 04:27:55,026][88298] Updated weights for policy 0, policy_version 54640 (0.0007) -[2023-10-15 04:27:55,401][88298] Updated weights for policy 0, policy_version 54650 (0.0007) -[2023-10-15 04:27:56,182][88300] Updated weights for policy 1, policy_version 54952 (0.0008) -[2023-10-15 04:27:56,555][88300] Updated weights for policy 1, policy_version 54962 (0.0008) -[2023-10-15 04:27:56,923][88300] Updated weights for policy 1, policy_version 54972 (0.0007) -[2023-10-15 04:27:58,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 112263168. Throughput: 0: 1743.4, 1: 1738.6. Samples: 28076828. Policy #0 lag: (min: 30.0, avg: 36.9, max: 62.0) -[2023-10-15 04:27:58,535][87330] Avg episode reward: [(0, '22.190'), (1, '22.680')] -[2023-10-15 04:27:59,362][88298] Updated weights for policy 0, policy_version 54660 (0.0007) -[2023-10-15 04:27:59,738][88298] Updated weights for policy 0, policy_version 54670 (0.0007) -[2023-10-15 04:28:00,104][88298] Updated weights for policy 0, policy_version 54680 (0.0008) -[2023-10-15 04:28:00,749][88300] Updated weights for policy 1, policy_version 54982 (0.0007) -[2023-10-15 04:28:01,108][88300] Updated weights for policy 1, policy_version 54992 (0.0008) -[2023-10-15 04:28:01,472][88300] Updated weights for policy 1, policy_version 55002 (0.0008) -[2023-10-15 04:28:03,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 112328704. Throughput: 0: 1710.4, 1: 1757.1. Samples: 28086912. Policy #0 lag: (min: 30.0, avg: 36.9, max: 62.0) -[2023-10-15 04:28:03,534][87330] Avg episode reward: [(0, '22.690'), (1, '22.650')] -[2023-10-15 04:28:03,839][88298] Updated weights for policy 0, policy_version 54690 (0.0008) -[2023-10-15 04:28:04,211][88298] Updated weights for policy 0, policy_version 54700 (0.0010) -[2023-10-15 04:28:04,582][88298] Updated weights for policy 0, policy_version 54710 (0.0010) -[2023-10-15 04:28:04,940][88298] Updated weights for policy 0, policy_version 54720 (0.0009) -[2023-10-15 04:28:05,456][88300] Updated weights for policy 1, policy_version 55012 (0.0007) -[2023-10-15 04:28:05,826][88300] Updated weights for policy 1, policy_version 55022 (0.0010) -[2023-10-15 04:28:06,191][88300] Updated weights for policy 1, policy_version 55032 (0.0009) -[2023-10-15 04:28:08,534][87330] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 112394240. Throughput: 0: 1742.6, 1: 1737.7. Samples: 28108214. Policy #0 lag: (min: 30.0, avg: 36.9, max: 62.0) -[2023-10-15 04:28:08,534][87330] Avg episode reward: [(0, '22.880'), (1, '22.660')] -[2023-10-15 04:28:08,937][88298] Updated weights for policy 0, policy_version 54730 (0.0008) -[2023-10-15 04:28:09,309][88298] Updated weights for policy 0, policy_version 54740 (0.0010) -[2023-10-15 04:28:09,673][88298] Updated weights for policy 0, policy_version 54750 (0.0009) -[2023-10-15 04:28:10,011][88300] Updated weights for policy 1, policy_version 55042 (0.0011) -[2023-10-15 04:28:10,381][88300] Updated weights for policy 1, policy_version 55052 (0.0010) -[2023-10-15 04:28:10,748][88300] Updated weights for policy 1, policy_version 55062 (0.0011) -[2023-10-15 04:28:11,115][88300] Updated weights for policy 1, policy_version 55072 (0.0010) -[2023-10-15 04:28:13,480][88298] Updated weights for policy 0, policy_version 54760 (0.0007) -[2023-10-15 04:28:13,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 112459776. Throughput: 0: 1744.2, 1: 1743.6. Samples: 28129442. Policy #0 lag: (min: 13.0, avg: 20.4, max: 45.0) -[2023-10-15 04:28:13,535][87330] Avg episode reward: [(0, '22.890'), (1, '22.660')] -[2023-10-15 04:28:13,856][88298] Updated weights for policy 0, policy_version 54770 (0.0008) -[2023-10-15 04:28:14,227][88298] Updated weights for policy 0, policy_version 54780 (0.0008) -[2023-10-15 04:28:15,065][88300] Updated weights for policy 1, policy_version 55082 (0.0008) -[2023-10-15 04:28:15,435][88300] Updated weights for policy 1, policy_version 55092 (0.0009) -[2023-10-15 04:28:15,807][88300] Updated weights for policy 1, policy_version 55102 (0.0010) -[2023-10-15 04:28:18,039][88298] Updated weights for policy 0, policy_version 54790 (0.0007) -[2023-10-15 04:28:18,415][88298] Updated weights for policy 0, policy_version 54800 (0.0008) -[2023-10-15 04:28:18,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 112525312. Throughput: 0: 1724.2, 1: 1734.0. Samples: 28138990. Policy #0 lag: (min: 13.0, avg: 20.4, max: 45.0) -[2023-10-15 04:28:18,534][87330] Avg episode reward: [(0, '22.820'), (1, '22.680')] -[2023-10-15 04:28:18,790][88298] Updated weights for policy 0, policy_version 54810 (0.0007) -[2023-10-15 04:28:19,820][88300] Updated weights for policy 1, policy_version 55112 (0.0009) -[2023-10-15 04:28:20,195][88300] Updated weights for policy 1, policy_version 55122 (0.0009) -[2023-10-15 04:28:20,564][88300] Updated weights for policy 1, policy_version 55132 (0.0009) -[2023-10-15 04:28:22,565][88298] Updated weights for policy 0, policy_version 54820 (0.0009) -[2023-10-15 04:28:22,928][88298] Updated weights for policy 0, policy_version 54830 (0.0009) -[2023-10-15 04:28:23,295][88298] Updated weights for policy 0, policy_version 54840 (0.0007) -[2023-10-15 04:28:23,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 112590848. Throughput: 0: 1743.9, 1: 1736.5. Samples: 28160630. Policy #0 lag: (min: 13.0, avg: 20.4, max: 45.0) -[2023-10-15 04:28:23,534][87330] Avg episode reward: [(0, '22.820'), (1, '22.610')] -[2023-10-15 04:28:24,384][88300] Updated weights for policy 1, policy_version 55142 (0.0008) -[2023-10-15 04:28:24,750][88300] Updated weights for policy 1, policy_version 55152 (0.0008) -[2023-10-15 04:28:25,110][88300] Updated weights for policy 1, policy_version 55162 (0.0007) -[2023-10-15 04:28:27,306][88298] Updated weights for policy 0, policy_version 54850 (0.0007) -[2023-10-15 04:28:27,673][88298] Updated weights for policy 0, policy_version 54860 (0.0010) -[2023-10-15 04:28:28,043][88298] Updated weights for policy 0, policy_version 54870 (0.0008) -[2023-10-15 04:28:28,407][88298] Updated weights for policy 0, policy_version 54880 (0.0007) -[2023-10-15 04:28:28,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 112689152. Throughput: 0: 1735.0, 1: 1771.7. Samples: 28181980. Policy #0 lag: (min: 13.0, avg: 20.4, max: 45.0) -[2023-10-15 04:28:28,535][87330] Avg episode reward: [(0, '22.840'), (1, '22.690')] -[2023-10-15 04:28:28,880][88300] Updated weights for policy 1, policy_version 55172 (0.0007) -[2023-10-15 04:28:29,251][88300] Updated weights for policy 1, policy_version 55182 (0.0008) -[2023-10-15 04:28:29,617][88300] Updated weights for policy 1, policy_version 55192 (0.0009) -[2023-10-15 04:28:32,256][88298] Updated weights for policy 0, policy_version 54890 (0.0007) -[2023-10-15 04:28:32,629][88298] Updated weights for policy 0, policy_version 54900 (0.0007) -[2023-10-15 04:28:33,002][88298] Updated weights for policy 0, policy_version 54910 (0.0007) -[2023-10-15 04:28:33,502][88300] Updated weights for policy 1, policy_version 55202 (0.0007) -[2023-10-15 04:28:33,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 112754688. Throughput: 0: 1746.0, 1: 1737.4. Samples: 28192192. Policy #0 lag: (min: 13.0, avg: 20.4, max: 45.0) -[2023-10-15 04:28:33,534][87330] Avg episode reward: [(0, '22.600'), (1, '22.710')] -[2023-10-15 04:28:33,868][88300] Updated weights for policy 1, policy_version 55212 (0.0008) -[2023-10-15 04:28:34,244][88300] Updated weights for policy 1, policy_version 55222 (0.0007) -[2023-10-15 04:28:34,607][88300] Updated weights for policy 1, policy_version 55232 (0.0007) -[2023-10-15 04:28:36,879][88298] Updated weights for policy 0, policy_version 54920 (0.0009) -[2023-10-15 04:28:37,255][88298] Updated weights for policy 0, policy_version 54930 (0.0009) -[2023-10-15 04:28:37,623][88298] Updated weights for policy 0, policy_version 54940 (0.0007) -[2023-10-15 04:28:38,407][88300] Updated weights for policy 1, policy_version 55242 (0.0007) -[2023-10-15 04:28:38,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13995.8). Total num frames: 112820224. Throughput: 0: 1752.0, 1: 1764.0. Samples: 28213582. Policy #0 lag: (min: 13.0, avg: 20.4, max: 45.0) -[2023-10-15 04:28:38,534][87330] Avg episode reward: [(0, '22.600'), (1, '22.820')] -[2023-10-15 04:28:38,772][88300] Updated weights for policy 1, policy_version 55252 (0.0008) -[2023-10-15 04:28:39,133][88300] Updated weights for policy 1, policy_version 55262 (0.0008) -[2023-10-15 04:28:41,738][88298] Updated weights for policy 0, policy_version 54950 (0.0009) -[2023-10-15 04:28:42,114][88298] Updated weights for policy 0, policy_version 54960 (0.0008) -[2023-10-15 04:28:42,482][88298] Updated weights for policy 0, policy_version 54970 (0.0010) -[2023-10-15 04:28:42,851][88300] Updated weights for policy 1, policy_version 55272 (0.0009) -[2023-10-15 04:28:43,231][88300] Updated weights for policy 1, policy_version 55282 (0.0010) -[2023-10-15 04:28:43,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 112885760. Throughput: 0: 1723.0, 1: 1761.3. Samples: 28233620. Policy #0 lag: (min: 13.0, avg: 20.4, max: 45.0) -[2023-10-15 04:28:43,534][87330] Avg episode reward: [(0, '22.490'), (1, '22.840')] -[2023-10-15 04:28:43,603][88300] Updated weights for policy 1, policy_version 55292 (0.0010) -[2023-10-15 04:28:46,294][88298] Updated weights for policy 0, policy_version 54980 (0.0008) -[2023-10-15 04:28:46,660][88298] Updated weights for policy 0, policy_version 54990 (0.0008) -[2023-10-15 04:28:47,036][88298] Updated weights for policy 0, policy_version 55000 (0.0009) -[2023-10-15 04:28:47,397][88300] Updated weights for policy 1, policy_version 55302 (0.0008) -[2023-10-15 04:28:47,763][88300] Updated weights for policy 1, policy_version 55312 (0.0007) -[2023-10-15 04:28:48,128][88300] Updated weights for policy 1, policy_version 55322 (0.0010) -[2023-10-15 04:28:48,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 112984064. Throughput: 0: 1758.1, 1: 1761.2. Samples: 28245280. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:28:48,534][87330] Avg episode reward: [(0, '22.430'), (1, '22.800')] -[2023-10-15 04:28:50,937][88298] Updated weights for policy 0, policy_version 55010 (0.0010) -[2023-10-15 04:28:51,294][88298] Updated weights for policy 0, policy_version 55020 (0.0008) -[2023-10-15 04:28:51,669][88298] Updated weights for policy 0, policy_version 55030 (0.0007) -[2023-10-15 04:28:52,033][88298] Updated weights for policy 0, policy_version 55040 (0.0007) -[2023-10-15 04:28:52,166][88300] Updated weights for policy 1, policy_version 55332 (0.0008) -[2023-10-15 04:28:52,532][88300] Updated weights for policy 1, policy_version 55342 (0.0011) -[2023-10-15 04:28:52,901][88300] Updated weights for policy 1, policy_version 55352 (0.0010) -[2023-10-15 04:28:53,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 113049600. Throughput: 0: 1732.9, 1: 1772.2. Samples: 28265944. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:28:53,534][87330] Avg episode reward: [(0, '22.280'), (1, '22.600')] -[2023-10-15 04:28:55,906][88298] Updated weights for policy 0, policy_version 55050 (0.0007) -[2023-10-15 04:28:56,273][88298] Updated weights for policy 0, policy_version 55060 (0.0009) -[2023-10-15 04:28:56,646][88298] Updated weights for policy 0, policy_version 55070 (0.0008) -[2023-10-15 04:28:56,712][88300] Updated weights for policy 1, policy_version 55362 (0.0009) -[2023-10-15 04:28:57,085][88300] Updated weights for policy 1, policy_version 55372 (0.0008) -[2023-10-15 04:28:57,443][88300] Updated weights for policy 1, policy_version 55382 (0.0007) -[2023-10-15 04:28:57,815][88300] Updated weights for policy 1, policy_version 55392 (0.0008) -[2023-10-15 04:28:58,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 113115136. Throughput: 0: 1732.0, 1: 1752.3. Samples: 28286232. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:28:58,535][87330] Avg episode reward: [(0, '22.250'), (1, '22.820')] -[2023-10-15 04:28:58,543][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000055392_56721408.pth... -[2023-10-15 04:28:58,544][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000055072_56393728.pth... -[2023-10-15 04:28:58,573][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000053760_55050240.pth -[2023-10-15 04:28:58,580][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000053440_54722560.pth -[2023-10-15 04:29:00,508][88298] Updated weights for policy 0, policy_version 55080 (0.0008) -[2023-10-15 04:29:00,888][88298] Updated weights for policy 0, policy_version 55090 (0.0008) -[2023-10-15 04:29:01,250][88298] Updated weights for policy 0, policy_version 55100 (0.0009) -[2023-10-15 04:29:01,778][88300] Updated weights for policy 1, policy_version 55402 (0.0007) -[2023-10-15 04:29:02,149][88300] Updated weights for policy 1, policy_version 55412 (0.0007) -[2023-10-15 04:29:02,510][88300] Updated weights for policy 1, policy_version 55422 (0.0007) -[2023-10-15 04:29:03,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 113180672. Throughput: 0: 1746.9, 1: 1778.9. Samples: 28297652. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:29:03,534][87330] Avg episode reward: [(0, '22.290'), (1, '22.790')] -[2023-10-15 04:29:05,029][88298] Updated weights for policy 0, policy_version 55110 (0.0007) -[2023-10-15 04:29:05,402][88298] Updated weights for policy 0, policy_version 55120 (0.0008) -[2023-10-15 04:29:05,772][88298] Updated weights for policy 0, policy_version 55130 (0.0007) -[2023-10-15 04:29:06,514][88300] Updated weights for policy 1, policy_version 55432 (0.0007) -[2023-10-15 04:29:06,886][88300] Updated weights for policy 1, policy_version 55442 (0.0007) -[2023-10-15 04:29:07,246][88300] Updated weights for policy 1, policy_version 55452 (0.0010) -[2023-10-15 04:29:08,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 113246208. Throughput: 0: 1730.8, 1: 1753.1. Samples: 28317402. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:29:08,535][87330] Avg episode reward: [(0, '22.400'), (1, '22.660')] -[2023-10-15 04:29:09,748][88298] Updated weights for policy 0, policy_version 55140 (0.0008) -[2023-10-15 04:29:10,114][88298] Updated weights for policy 0, policy_version 55150 (0.0007) -[2023-10-15 04:29:10,490][88298] Updated weights for policy 0, policy_version 55160 (0.0008) -[2023-10-15 04:29:10,922][88300] Updated weights for policy 1, policy_version 55462 (0.0008) -[2023-10-15 04:29:11,292][88300] Updated weights for policy 1, policy_version 55472 (0.0008) -[2023-10-15 04:29:11,667][88300] Updated weights for policy 1, policy_version 55482 (0.0009) -[2023-10-15 04:29:13,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 113311744. Throughput: 0: 1748.2, 1: 1738.0. Samples: 28338856. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:29:13,534][87330] Avg episode reward: [(0, '22.540'), (1, '22.640')] -[2023-10-15 04:29:14,350][88298] Updated weights for policy 0, policy_version 55170 (0.0008) -[2023-10-15 04:29:14,714][88298] Updated weights for policy 0, policy_version 55180 (0.0009) -[2023-10-15 04:29:15,089][88298] Updated weights for policy 0, policy_version 55190 (0.0011) -[2023-10-15 04:29:15,457][88298] Updated weights for policy 0, policy_version 55200 (0.0010) -[2023-10-15 04:29:15,729][88300] Updated weights for policy 1, policy_version 55492 (0.0007) -[2023-10-15 04:29:16,102][88300] Updated weights for policy 1, policy_version 55502 (0.0009) -[2023-10-15 04:29:16,477][88300] Updated weights for policy 1, policy_version 55512 (0.0009) -[2023-10-15 04:29:18,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 113377280. Throughput: 0: 1729.6, 1: 1753.4. Samples: 28348928. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:29:18,534][87330] Avg episode reward: [(0, '22.510'), (1, '22.430')] -[2023-10-15 04:29:19,485][88298] Updated weights for policy 0, policy_version 55210 (0.0009) -[2023-10-15 04:29:19,851][88298] Updated weights for policy 0, policy_version 55220 (0.0009) -[2023-10-15 04:29:20,221][88298] Updated weights for policy 0, policy_version 55230 (0.0007) -[2023-10-15 04:29:20,404][88300] Updated weights for policy 1, policy_version 55522 (0.0009) -[2023-10-15 04:29:20,768][88300] Updated weights for policy 1, policy_version 55532 (0.0007) -[2023-10-15 04:29:21,147][88300] Updated weights for policy 1, policy_version 55542 (0.0007) -[2023-10-15 04:29:21,509][88300] Updated weights for policy 1, policy_version 55552 (0.0007) -[2023-10-15 04:29:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 113442816. Throughput: 0: 1738.3, 1: 1736.1. Samples: 28369930. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:29:23,534][87330] Avg episode reward: [(0, '22.590'), (1, '22.420')] -[2023-10-15 04:29:24,101][88298] Updated weights for policy 0, policy_version 55240 (0.0010) -[2023-10-15 04:29:24,473][88298] Updated weights for policy 0, policy_version 55250 (0.0010) -[2023-10-15 04:29:24,841][88298] Updated weights for policy 0, policy_version 55260 (0.0010) -[2023-10-15 04:29:25,331][88300] Updated weights for policy 1, policy_version 55562 (0.0008) -[2023-10-15 04:29:25,704][88300] Updated weights for policy 1, policy_version 55572 (0.0008) -[2023-10-15 04:29:26,075][88300] Updated weights for policy 1, policy_version 55582 (0.0007) -[2023-10-15 04:29:28,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 113508352. Throughput: 0: 1767.0, 1: 1751.3. Samples: 28391942. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-15 04:29:28,534][87330] Avg episode reward: [(0, '22.560'), (1, '22.400')] -[2023-10-15 04:29:28,554][88298] Updated weights for policy 0, policy_version 55270 (0.0009) -[2023-10-15 04:29:28,926][88298] Updated weights for policy 0, policy_version 55280 (0.0008) -[2023-10-15 04:29:29,298][88298] Updated weights for policy 0, policy_version 55290 (0.0008) -[2023-10-15 04:29:29,708][88300] Updated weights for policy 1, policy_version 55592 (0.0008) -[2023-10-15 04:29:30,069][88300] Updated weights for policy 1, policy_version 55602 (0.0009) -[2023-10-15 04:29:30,442][88300] Updated weights for policy 1, policy_version 55612 (0.0007) -[2023-10-15 04:29:33,072][88298] Updated weights for policy 0, policy_version 55300 (0.0009) -[2023-10-15 04:29:33,446][88298] Updated weights for policy 0, policy_version 55310 (0.0010) -[2023-10-15 04:29:33,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 113573888. Throughput: 0: 1733.0, 1: 1737.8. Samples: 28401464. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-15 04:29:33,534][87330] Avg episode reward: [(0, '22.500'), (1, '22.390')] -[2023-10-15 04:29:33,807][88298] Updated weights for policy 0, policy_version 55320 (0.0008) -[2023-10-15 04:29:34,204][88300] Updated weights for policy 1, policy_version 55622 (0.0009) -[2023-10-15 04:29:34,586][88300] Updated weights for policy 1, policy_version 55632 (0.0008) -[2023-10-15 04:29:34,943][88300] Updated weights for policy 1, policy_version 55642 (0.0010) -[2023-10-15 04:29:37,792][88298] Updated weights for policy 0, policy_version 55330 (0.0007) -[2023-10-15 04:29:38,169][88298] Updated weights for policy 0, policy_version 55340 (0.0007) -[2023-10-15 04:29:38,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 113639424. Throughput: 0: 1751.7, 1: 1743.1. Samples: 28423210. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-15 04:29:38,535][87330] Avg episode reward: [(0, '22.270'), (1, '22.490')] -[2023-10-15 04:29:38,542][88298] Updated weights for policy 0, policy_version 55350 (0.0008) -[2023-10-15 04:29:38,897][88300] Updated weights for policy 1, policy_version 55652 (0.0008) -[2023-10-15 04:29:38,913][88298] Updated weights for policy 0, policy_version 55360 (0.0008) -[2023-10-15 04:29:39,274][88300] Updated weights for policy 1, policy_version 55662 (0.0008) -[2023-10-15 04:29:39,639][88300] Updated weights for policy 1, policy_version 55672 (0.0009) -[2023-10-15 04:29:42,934][88298] Updated weights for policy 0, policy_version 55370 (0.0007) -[2023-10-15 04:29:43,298][88298] Updated weights for policy 0, policy_version 55380 (0.0007) -[2023-10-15 04:29:43,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 113704960. Throughput: 0: 1746.0, 1: 1763.6. Samples: 28444164. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-15 04:29:43,534][87330] Avg episode reward: [(0, '22.220'), (1, '22.170')] -[2023-10-15 04:29:43,568][88300] Updated weights for policy 1, policy_version 55682 (0.0008) -[2023-10-15 04:29:43,675][88298] Updated weights for policy 0, policy_version 55390 (0.0008) -[2023-10-15 04:29:43,946][88300] Updated weights for policy 1, policy_version 55692 (0.0010) -[2023-10-15 04:29:44,310][88300] Updated weights for policy 1, policy_version 55702 (0.0007) -[2023-10-15 04:29:44,680][88300] Updated weights for policy 1, policy_version 55712 (0.0011) -[2023-10-15 04:29:47,578][88298] Updated weights for policy 0, policy_version 55400 (0.0008) -[2023-10-15 04:29:47,950][88298] Updated weights for policy 0, policy_version 55410 (0.0009) -[2023-10-15 04:29:48,320][88298] Updated weights for policy 0, policy_version 55420 (0.0009) -[2023-10-15 04:29:48,534][87330] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 113803264. Throughput: 0: 1737.9, 1: 1732.0. Samples: 28453800. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-15 04:29:48,534][87330] Avg episode reward: [(0, '22.260'), (1, '22.240')] -[2023-10-15 04:29:48,594][88300] Updated weights for policy 1, policy_version 55722 (0.0008) -[2023-10-15 04:29:48,954][88300] Updated weights for policy 1, policy_version 55732 (0.0007) -[2023-10-15 04:29:49,329][88300] Updated weights for policy 1, policy_version 55742 (0.0008) -[2023-10-15 04:29:52,474][88298] Updated weights for policy 0, policy_version 55430 (0.0010) -[2023-10-15 04:29:52,848][88298] Updated weights for policy 0, policy_version 55440 (0.0011) -[2023-10-15 04:29:53,224][88298] Updated weights for policy 0, policy_version 55450 (0.0008) -[2023-10-15 04:29:53,377][88300] Updated weights for policy 1, policy_version 55752 (0.0007) -[2023-10-15 04:29:53,534][87330] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 113868800. Throughput: 0: 1742.7, 1: 1765.2. Samples: 28475258. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-15 04:29:53,535][87330] Avg episode reward: [(0, '22.400'), (1, '22.310')] -[2023-10-15 04:29:53,746][88300] Updated weights for policy 1, policy_version 55762 (0.0008) -[2023-10-15 04:29:54,112][88300] Updated weights for policy 1, policy_version 55772 (0.0009) -[2023-10-15 04:29:57,053][88298] Updated weights for policy 0, policy_version 55460 (0.0007) -[2023-10-15 04:29:57,425][88298] Updated weights for policy 0, policy_version 55470 (0.0007) -[2023-10-15 04:29:57,797][88298] Updated weights for policy 0, policy_version 55480 (0.0007) -[2023-10-15 04:29:58,082][88300] Updated weights for policy 1, policy_version 55782 (0.0010) -[2023-10-15 04:29:58,450][88300] Updated weights for policy 1, policy_version 55792 (0.0010) -[2023-10-15 04:29:58,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 113934336. Throughput: 0: 1717.7, 1: 1754.4. Samples: 28495098. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-15 04:29:58,534][87330] Avg episode reward: [(0, '22.410'), (1, '22.160')] -[2023-10-15 04:29:58,823][88300] Updated weights for policy 1, policy_version 55802 (0.0008) -[2023-10-15 04:30:01,652][88298] Updated weights for policy 0, policy_version 55490 (0.0007) -[2023-10-15 04:30:02,017][88298] Updated weights for policy 0, policy_version 55500 (0.0009) -[2023-10-15 04:30:02,389][88298] Updated weights for policy 0, policy_version 55510 (0.0009) -[2023-10-15 04:30:02,734][88300] Updated weights for policy 1, policy_version 55812 (0.0007) -[2023-10-15 04:30:02,763][88298] Updated weights for policy 0, policy_version 55520 (0.0009) -[2023-10-15 04:30:03,098][88300] Updated weights for policy 1, policy_version 55822 (0.0007) -[2023-10-15 04:30:03,470][88300] Updated weights for policy 1, policy_version 55832 (0.0008) -[2023-10-15 04:30:03,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 113999872. Throughput: 0: 1741.3, 1: 1745.2. Samples: 28505818. Policy #0 lag: (min: 23.0, avg: 26.4, max: 55.0) -[2023-10-15 04:30:03,534][87330] Avg episode reward: [(0, '22.330'), (1, '22.150')] -[2023-10-15 04:30:06,659][88298] Updated weights for policy 0, policy_version 55530 (0.0007) -[2023-10-15 04:30:07,021][88298] Updated weights for policy 0, policy_version 55540 (0.0007) -[2023-10-15 04:30:07,184][88300] Updated weights for policy 1, policy_version 55842 (0.0009) -[2023-10-15 04:30:07,390][88298] Updated weights for policy 0, policy_version 55550 (0.0008) -[2023-10-15 04:30:07,550][88300] Updated weights for policy 1, policy_version 55852 (0.0008) -[2023-10-15 04:30:07,926][88300] Updated weights for policy 1, policy_version 55862 (0.0010) -[2023-10-15 04:30:08,298][88300] Updated weights for policy 1, policy_version 55872 (0.0011) -[2023-10-15 04:30:08,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 114098176. Throughput: 0: 1723.8, 1: 1759.1. Samples: 28526662. Policy #0 lag: (min: 23.0, avg: 26.4, max: 55.0) -[2023-10-15 04:30:08,534][87330] Avg episode reward: [(0, '22.680'), (1, '22.160')] -[2023-10-15 04:30:11,329][88298] Updated weights for policy 0, policy_version 55560 (0.0008) -[2023-10-15 04:30:11,701][88298] Updated weights for policy 0, policy_version 55570 (0.0008) -[2023-10-15 04:30:12,071][88298] Updated weights for policy 0, policy_version 55580 (0.0007) -[2023-10-15 04:30:12,120][88300] Updated weights for policy 1, policy_version 55882 (0.0008) -[2023-10-15 04:30:12,483][88300] Updated weights for policy 1, policy_version 55892 (0.0008) -[2023-10-15 04:30:12,848][88300] Updated weights for policy 1, policy_version 55902 (0.0011) -[2023-10-15 04:30:13,534][87330] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 114163712. Throughput: 0: 1704.7, 1: 1727.1. Samples: 28546374. Policy #0 lag: (min: 23.0, avg: 26.4, max: 55.0) -[2023-10-15 04:30:13,535][87330] Avg episode reward: [(0, '22.690'), (1, '22.260')] -[2023-10-15 04:30:15,951][88298] Updated weights for policy 0, policy_version 55590 (0.0008) -[2023-10-15 04:30:16,319][88298] Updated weights for policy 0, policy_version 55600 (0.0008) -[2023-10-15 04:30:16,673][88300] Updated weights for policy 1, policy_version 55912 (0.0008) -[2023-10-15 04:30:16,685][88298] Updated weights for policy 0, policy_version 55610 (0.0007) -[2023-10-15 04:30:17,038][88300] Updated weights for policy 1, policy_version 55922 (0.0008) -[2023-10-15 04:30:17,408][88300] Updated weights for policy 1, policy_version 55932 (0.0007) -[2023-10-15 04:30:18,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 114229248. Throughput: 0: 1734.0, 1: 1757.5. Samples: 28558582. Policy #0 lag: (min: 23.0, avg: 26.4, max: 55.0) -[2023-10-15 04:30:18,535][87330] Avg episode reward: [(0, '22.490'), (1, '22.360')] -[2023-10-15 04:30:20,516][88298] Updated weights for policy 0, policy_version 55620 (0.0009) -[2023-10-15 04:30:20,885][88298] Updated weights for policy 0, policy_version 55630 (0.0008) -[2023-10-15 04:30:21,248][88300] Updated weights for policy 1, policy_version 55942 (0.0008) -[2023-10-15 04:30:21,263][88298] Updated weights for policy 0, policy_version 55640 (0.0008) -[2023-10-15 04:30:21,619][88300] Updated weights for policy 1, policy_version 55952 (0.0007) -[2023-10-15 04:30:21,976][88300] Updated weights for policy 1, policy_version 55962 (0.0009) -[2023-10-15 04:30:23,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 114294784. Throughput: 0: 1710.5, 1: 1727.2. Samples: 28577904. Policy #0 lag: (min: 23.0, avg: 26.4, max: 55.0) -[2023-10-15 04:30:23,534][87330] Avg episode reward: [(0, '22.430'), (1, '22.350')] -[2023-10-15 04:30:25,243][88298] Updated weights for policy 0, policy_version 55650 (0.0008) -[2023-10-15 04:30:25,613][88298] Updated weights for policy 0, policy_version 55660 (0.0007) -[2023-10-15 04:30:25,984][88298] Updated weights for policy 0, policy_version 55670 (0.0007) -[2023-10-15 04:30:26,034][88300] Updated weights for policy 1, policy_version 55972 (0.0009) -[2023-10-15 04:30:26,342][88298] Updated weights for policy 0, policy_version 55680 (0.0007) -[2023-10-15 04:30:26,406][88300] Updated weights for policy 1, policy_version 55982 (0.0008) -[2023-10-15 04:30:26,774][88300] Updated weights for policy 1, policy_version 55992 (0.0010) -[2023-10-15 04:30:28,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 114360320. Throughput: 0: 1727.8, 1: 1722.4. Samples: 28599422. Policy #0 lag: (min: 23.0, avg: 26.4, max: 55.0) -[2023-10-15 04:30:28,534][87330] Avg episode reward: [(0, '22.130'), (1, '22.610')] -[2023-10-15 04:30:30,163][88298] Updated weights for policy 0, policy_version 55690 (0.0009) -[2023-10-15 04:30:30,541][88298] Updated weights for policy 0, policy_version 55700 (0.0008) -[2023-10-15 04:30:30,748][88300] Updated weights for policy 1, policy_version 56002 (0.0009) -[2023-10-15 04:30:30,909][88298] Updated weights for policy 0, policy_version 55710 (0.0008) -[2023-10-15 04:30:31,122][88300] Updated weights for policy 1, policy_version 56012 (0.0007) -[2023-10-15 04:30:31,484][88300] Updated weights for policy 1, policy_version 56022 (0.0009) -[2023-10-15 04:30:31,851][88300] Updated weights for policy 1, policy_version 56032 (0.0010) -[2023-10-15 04:30:33,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 114425856. Throughput: 0: 1724.3, 1: 1741.5. Samples: 28609760. Policy #0 lag: (min: 23.0, avg: 26.4, max: 55.0) -[2023-10-15 04:30:33,535][87330] Avg episode reward: [(0, '22.280'), (1, '22.600')] -[2023-10-15 04:30:34,706][88298] Updated weights for policy 0, policy_version 55720 (0.0010) -[2023-10-15 04:30:35,085][88298] Updated weights for policy 0, policy_version 55730 (0.0011) -[2023-10-15 04:30:35,462][88298] Updated weights for policy 0, policy_version 55740 (0.0009) -[2023-10-15 04:30:35,667][88300] Updated weights for policy 1, policy_version 56042 (0.0007) -[2023-10-15 04:30:36,027][88300] Updated weights for policy 1, policy_version 56052 (0.0007) -[2023-10-15 04:30:36,398][88300] Updated weights for policy 1, policy_version 56062 (0.0007) -[2023-10-15 04:30:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 114491392. Throughput: 0: 1727.1, 1: 1721.3. Samples: 28630434. Policy #0 lag: (min: 23.0, avg: 26.4, max: 55.0) -[2023-10-15 04:30:38,534][87330] Avg episode reward: [(0, '22.240'), (1, '22.640')] -[2023-10-15 04:30:39,534][88298] Updated weights for policy 0, policy_version 55750 (0.0008) -[2023-10-15 04:30:39,917][88298] Updated weights for policy 0, policy_version 55760 (0.0011) -[2023-10-15 04:30:40,281][88298] Updated weights for policy 0, policy_version 55770 (0.0007) -[2023-10-15 04:30:40,477][88300] Updated weights for policy 1, policy_version 56072 (0.0009) -[2023-10-15 04:30:40,840][88300] Updated weights for policy 1, policy_version 56082 (0.0009) -[2023-10-15 04:30:41,203][88300] Updated weights for policy 1, policy_version 56092 (0.0010) -[2023-10-15 04:30:43,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 114556928. Throughput: 0: 1748.2, 1: 1738.0. Samples: 28651980. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-15 04:30:43,534][87330] Avg episode reward: [(0, '22.280'), (1, '22.670')] -[2023-10-15 04:30:44,149][88298] Updated weights for policy 0, policy_version 55780 (0.0010) -[2023-10-15 04:30:44,519][88298] Updated weights for policy 0, policy_version 55790 (0.0007) -[2023-10-15 04:30:44,810][88300] Updated weights for policy 1, policy_version 56102 (0.0011) -[2023-10-15 04:30:44,883][88298] Updated weights for policy 0, policy_version 55800 (0.0009) -[2023-10-15 04:30:45,175][88300] Updated weights for policy 1, policy_version 56112 (0.0009) -[2023-10-15 04:30:45,548][88300] Updated weights for policy 1, policy_version 56122 (0.0008) -[2023-10-15 04:30:48,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 114622464. Throughput: 0: 1722.8, 1: 1734.8. Samples: 28661408. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-15 04:30:48,534][87330] Avg episode reward: [(0, '22.130'), (1, '22.690')] -[2023-10-15 04:30:48,866][88298] Updated weights for policy 0, policy_version 55810 (0.0008) -[2023-10-15 04:30:49,239][88298] Updated weights for policy 0, policy_version 55820 (0.0008) -[2023-10-15 04:30:49,398][88300] Updated weights for policy 1, policy_version 56132 (0.0009) -[2023-10-15 04:30:49,617][88298] Updated weights for policy 0, policy_version 55830 (0.0008) -[2023-10-15 04:30:49,760][88300] Updated weights for policy 1, policy_version 56142 (0.0009) -[2023-10-15 04:30:49,974][88298] Updated weights for policy 0, policy_version 55840 (0.0008) -[2023-10-15 04:30:50,130][88300] Updated weights for policy 1, policy_version 56152 (0.0008) -[2023-10-15 04:30:53,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 114688000. Throughput: 0: 1739.1, 1: 1736.9. Samples: 28683082. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-15 04:30:53,535][87330] Avg episode reward: [(0, '22.360'), (1, '22.700')] -[2023-10-15 04:30:54,098][88300] Updated weights for policy 1, policy_version 56162 (0.0009) -[2023-10-15 04:30:54,160][88298] Updated weights for policy 0, policy_version 55850 (0.0008) -[2023-10-15 04:30:54,461][88300] Updated weights for policy 1, policy_version 56172 (0.0010) -[2023-10-15 04:30:54,522][88298] Updated weights for policy 0, policy_version 55860 (0.0009) -[2023-10-15 04:30:54,831][88300] Updated weights for policy 1, policy_version 56182 (0.0009) -[2023-10-15 04:30:54,898][88298] Updated weights for policy 0, policy_version 55870 (0.0008) -[2023-10-15 04:30:55,190][88300] Updated weights for policy 1, policy_version 56192 (0.0008) -[2023-10-15 04:30:58,534][87330] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 114753536. Throughput: 0: 1751.2, 1: 1763.5. Samples: 28704532. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-15 04:30:58,535][87330] Avg episode reward: [(0, '22.360'), (1, '22.450')] -[2023-10-15 04:30:58,548][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000056192_57540608.pth... -[2023-10-15 04:30:58,579][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000054560_55869440.pth -[2023-10-15 04:30:58,905][88298] Updated weights for policy 0, policy_version 55880 (0.0008) -[2023-10-15 04:30:59,068][88300] Updated weights for policy 1, policy_version 56202 (0.0009) -[2023-10-15 04:30:59,270][88298] Updated weights for policy 0, policy_version 55890 (0.0009) -[2023-10-15 04:30:59,441][88300] Updated weights for policy 1, policy_version 56212 (0.0008) -[2023-10-15 04:30:59,635][88298] Updated weights for policy 0, policy_version 55900 (0.0008) -[2023-10-15 04:30:59,783][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000055904_57245696.pth... -[2023-10-15 04:30:59,808][88300] Updated weights for policy 1, policy_version 56222 (0.0008) -[2023-10-15 04:30:59,819][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000054272_55574528.pth -[2023-10-15 04:31:03,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 114819072. Throughput: 0: 1719.8, 1: 1730.1. Samples: 28713828. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-15 04:31:03,535][87330] Avg episode reward: [(0, '22.650'), (1, '22.090')] -[2023-10-15 04:31:03,624][88298] Updated weights for policy 0, policy_version 55910 (0.0007) -[2023-10-15 04:31:03,725][88300] Updated weights for policy 1, policy_version 56232 (0.0009) -[2023-10-15 04:31:03,995][88298] Updated weights for policy 0, policy_version 55920 (0.0008) -[2023-10-15 04:31:04,086][88300] Updated weights for policy 1, policy_version 56242 (0.0008) -[2023-10-15 04:31:04,364][88298] Updated weights for policy 0, policy_version 55930 (0.0009) -[2023-10-15 04:31:04,460][88300] Updated weights for policy 1, policy_version 56252 (0.0008) -[2023-10-15 04:31:08,345][88298] Updated weights for policy 0, policy_version 55940 (0.0010) -[2023-10-15 04:31:08,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13884.7). Total num frames: 114884608. Throughput: 0: 1738.8, 1: 1753.2. Samples: 28735046. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-15 04:31:08,535][87330] Avg episode reward: [(0, '22.570'), (1, '21.840')] -[2023-10-15 04:31:08,544][88300] Updated weights for policy 1, policy_version 56262 (0.0009) -[2023-10-15 04:31:08,717][88298] Updated weights for policy 0, policy_version 55950 (0.0008) -[2023-10-15 04:31:08,911][88300] Updated weights for policy 1, policy_version 56272 (0.0009) -[2023-10-15 04:31:09,083][88298] Updated weights for policy 0, policy_version 55960 (0.0007) -[2023-10-15 04:31:09,278][88300] Updated weights for policy 1, policy_version 56282 (0.0007) -[2023-10-15 04:31:13,050][88298] Updated weights for policy 0, policy_version 55970 (0.0008) -[2023-10-15 04:31:13,272][88300] Updated weights for policy 1, policy_version 56292 (0.0009) -[2023-10-15 04:31:13,425][88298] Updated weights for policy 0, policy_version 55980 (0.0007) -[2023-10-15 04:31:13,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 114950144. Throughput: 0: 1728.4, 1: 1755.9. Samples: 28756214. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-15 04:31:13,535][87330] Avg episode reward: [(0, '22.580'), (1, '21.530')] -[2023-10-15 04:31:13,632][88300] Updated weights for policy 1, policy_version 56302 (0.0007) -[2023-10-15 04:31:13,804][88298] Updated weights for policy 0, policy_version 55990 (0.0008) -[2023-10-15 04:31:14,008][88300] Updated weights for policy 1, policy_version 56312 (0.0007) -[2023-10-15 04:31:14,169][88298] Updated weights for policy 0, policy_version 56000 (0.0008) -[2023-10-15 04:31:17,707][88300] Updated weights for policy 1, policy_version 56322 (0.0007) -[2023-10-15 04:31:18,067][88300] Updated weights for policy 1, policy_version 56332 (0.0008) -[2023-10-15 04:31:18,185][88298] Updated weights for policy 0, policy_version 56010 (0.0009) -[2023-10-15 04:31:18,435][88300] Updated weights for policy 1, policy_version 56342 (0.0007) -[2023-10-15 04:31:18,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 115015680. Throughput: 0: 1725.1, 1: 1741.2. Samples: 28765744. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-15 04:31:18,535][87330] Avg episode reward: [(0, '22.590'), (1, '21.610')] -[2023-10-15 04:31:18,559][88298] Updated weights for policy 0, policy_version 56020 (0.0007) -[2023-10-15 04:31:18,799][88300] Updated weights for policy 1, policy_version 56352 (0.0007) -[2023-10-15 04:31:18,935][88298] Updated weights for policy 0, policy_version 56030 (0.0008) -[2023-10-15 04:31:22,619][88300] Updated weights for policy 1, policy_version 56362 (0.0009) -[2023-10-15 04:31:22,792][88298] Updated weights for policy 0, policy_version 56040 (0.0008) -[2023-10-15 04:31:22,985][88300] Updated weights for policy 1, policy_version 56372 (0.0007) -[2023-10-15 04:31:23,163][88298] Updated weights for policy 0, policy_version 56050 (0.0008) -[2023-10-15 04:31:23,345][88300] Updated weights for policy 1, policy_version 56382 (0.0007) -[2023-10-15 04:31:23,528][88298] Updated weights for policy 0, policy_version 56060 (0.0008) -[2023-10-15 04:31:23,534][87330] Fps is (10 sec: 16384.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 115113984. Throughput: 0: 1722.2, 1: 1763.2. Samples: 28787280. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:31:23,534][87330] Avg episode reward: [(0, '22.620'), (1, '21.770')] -[2023-10-15 04:31:27,438][88300] Updated weights for policy 1, policy_version 56392 (0.0007) -[2023-10-15 04:31:27,580][88298] Updated weights for policy 0, policy_version 56070 (0.0008) -[2023-10-15 04:31:27,816][88300] Updated weights for policy 1, policy_version 56402 (0.0009) -[2023-10-15 04:31:27,948][88298] Updated weights for policy 0, policy_version 56080 (0.0007) -[2023-10-15 04:31:28,189][88300] Updated weights for policy 1, policy_version 56412 (0.0009) -[2023-10-15 04:31:28,324][88298] Updated weights for policy 0, policy_version 56090 (0.0007) -[2023-10-15 04:31:28,534][87330] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 115179520. Throughput: 0: 1705.1, 1: 1731.3. Samples: 28806616. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:31:28,535][87330] Avg episode reward: [(0, '22.330'), (1, '22.000')] -[2023-10-15 04:31:32,017][88300] Updated weights for policy 1, policy_version 56422 (0.0007) -[2023-10-15 04:31:32,180][88298] Updated weights for policy 0, policy_version 56100 (0.0010) -[2023-10-15 04:31:32,391][88300] Updated weights for policy 1, policy_version 56432 (0.0007) -[2023-10-15 04:31:32,552][88298] Updated weights for policy 0, policy_version 56110 (0.0009) -[2023-10-15 04:31:32,749][88300] Updated weights for policy 1, policy_version 56442 (0.0007) -[2023-10-15 04:31:32,924][88298] Updated weights for policy 0, policy_version 56120 (0.0007) -[2023-10-15 04:31:33,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 115277824. Throughput: 0: 1718.0, 1: 1756.0. Samples: 28817734. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:31:33,534][87330] Avg episode reward: [(0, '22.300'), (1, '22.130')] -[2023-10-15 04:31:36,576][88300] Updated weights for policy 1, policy_version 56452 (0.0008) -[2023-10-15 04:31:36,788][88298] Updated weights for policy 0, policy_version 56130 (0.0009) -[2023-10-15 04:31:36,953][88300] Updated weights for policy 1, policy_version 56462 (0.0008) -[2023-10-15 04:31:37,156][88298] Updated weights for policy 0, policy_version 56140 (0.0008) -[2023-10-15 04:31:37,322][88300] Updated weights for policy 1, policy_version 56472 (0.0008) -[2023-10-15 04:31:37,517][88298] Updated weights for policy 0, policy_version 56150 (0.0008) -[2023-10-15 04:31:37,884][88298] Updated weights for policy 0, policy_version 56160 (0.0009) -[2023-10-15 04:31:38,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 115343360. Throughput: 0: 1714.1, 1: 1739.6. Samples: 28838500. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:31:38,535][87330] Avg episode reward: [(0, '22.310'), (1, '22.280')] -[2023-10-15 04:31:41,032][88300] Updated weights for policy 1, policy_version 56482 (0.0007) -[2023-10-15 04:31:41,395][88300] Updated weights for policy 1, policy_version 56492 (0.0007) -[2023-10-15 04:31:41,761][88300] Updated weights for policy 1, policy_version 56502 (0.0009) -[2023-10-15 04:31:41,843][88298] Updated weights for policy 0, policy_version 56170 (0.0008) -[2023-10-15 04:31:42,127][88300] Updated weights for policy 1, policy_version 56512 (0.0009) -[2023-10-15 04:31:42,217][88298] Updated weights for policy 0, policy_version 56180 (0.0007) -[2023-10-15 04:31:42,587][88298] Updated weights for policy 0, policy_version 56190 (0.0007) -[2023-10-15 04:31:43,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 115408896. Throughput: 0: 1692.0, 1: 1731.4. Samples: 28858582. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:31:43,535][87330] Avg episode reward: [(0, '22.350'), (1, '22.290')] -[2023-10-15 04:31:46,063][88300] Updated weights for policy 1, policy_version 56522 (0.0008) -[2023-10-15 04:31:46,431][88300] Updated weights for policy 1, policy_version 56532 (0.0009) -[2023-10-15 04:31:46,689][88298] Updated weights for policy 0, policy_version 56200 (0.0008) -[2023-10-15 04:31:46,791][88300] Updated weights for policy 1, policy_version 56542 (0.0008) -[2023-10-15 04:31:47,063][88298] Updated weights for policy 0, policy_version 56210 (0.0008) -[2023-10-15 04:31:47,447][88298] Updated weights for policy 0, policy_version 56220 (0.0009) -[2023-10-15 04:31:48,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 115474432. Throughput: 0: 1721.6, 1: 1751.2. Samples: 28870102. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:31:48,534][87330] Avg episode reward: [(0, '22.360'), (1, '22.490')] -[2023-10-15 04:31:50,620][88300] Updated weights for policy 1, policy_version 56552 (0.0007) -[2023-10-15 04:31:50,994][88300] Updated weights for policy 1, policy_version 56562 (0.0009) -[2023-10-15 04:31:51,341][88298] Updated weights for policy 0, policy_version 56230 (0.0008) -[2023-10-15 04:31:51,352][88300] Updated weights for policy 1, policy_version 56572 (0.0009) -[2023-10-15 04:31:51,705][88298] Updated weights for policy 0, policy_version 56240 (0.0007) -[2023-10-15 04:31:52,083][88298] Updated weights for policy 0, policy_version 56250 (0.0011) -[2023-10-15 04:31:53,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 115539968. Throughput: 0: 1710.5, 1: 1737.0. Samples: 28890182. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:31:53,535][87330] Avg episode reward: [(0, '22.190'), (1, '22.470')] -[2023-10-15 04:31:55,368][88300] Updated weights for policy 1, policy_version 56582 (0.0010) -[2023-10-15 04:31:55,739][88300] Updated weights for policy 1, policy_version 56592 (0.0007) -[2023-10-15 04:31:55,982][88298] Updated weights for policy 0, policy_version 56260 (0.0010) -[2023-10-15 04:31:56,100][88300] Updated weights for policy 1, policy_version 56602 (0.0007) -[2023-10-15 04:31:56,357][88298] Updated weights for policy 0, policy_version 56270 (0.0009) -[2023-10-15 04:31:56,728][88298] Updated weights for policy 0, policy_version 56280 (0.0009) -[2023-10-15 04:31:58,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 115605504. Throughput: 0: 1698.5, 1: 1736.9. Samples: 28910806. Policy #0 lag: (min: 11.0, avg: 12.3, max: 35.0) -[2023-10-15 04:31:58,534][87330] Avg episode reward: [(0, '22.390'), (1, '22.170')] -[2023-10-15 04:31:59,972][88300] Updated weights for policy 1, policy_version 56612 (0.0007) -[2023-10-15 04:32:00,351][88300] Updated weights for policy 1, policy_version 56622 (0.0009) -[2023-10-15 04:32:00,646][88298] Updated weights for policy 0, policy_version 56290 (0.0007) -[2023-10-15 04:32:00,713][88300] Updated weights for policy 1, policy_version 56632 (0.0007) -[2023-10-15 04:32:01,014][88298] Updated weights for policy 0, policy_version 56300 (0.0010) -[2023-10-15 04:32:01,383][88298] Updated weights for policy 0, policy_version 56310 (0.0009) -[2023-10-15 04:32:01,757][88298] Updated weights for policy 0, policy_version 56320 (0.0008) -[2023-10-15 04:32:03,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 115671040. Throughput: 0: 1723.1, 1: 1736.6. Samples: 28921428. Policy #0 lag: (min: 11.0, avg: 12.3, max: 35.0) -[2023-10-15 04:32:03,534][87330] Avg episode reward: [(0, '22.530'), (1, '22.370')] -[2023-10-15 04:32:04,523][88300] Updated weights for policy 1, policy_version 56642 (0.0007) -[2023-10-15 04:32:04,881][88300] Updated weights for policy 1, policy_version 56652 (0.0007) -[2023-10-15 04:32:05,251][88300] Updated weights for policy 1, policy_version 56662 (0.0008) -[2023-10-15 04:32:05,583][88298] Updated weights for policy 0, policy_version 56330 (0.0008) -[2023-10-15 04:32:05,613][88300] Updated weights for policy 1, policy_version 56672 (0.0007) -[2023-10-15 04:32:05,954][88298] Updated weights for policy 0, policy_version 56340 (0.0010) -[2023-10-15 04:32:06,313][88298] Updated weights for policy 0, policy_version 56350 (0.0008) -[2023-10-15 04:32:08,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 115736576. Throughput: 0: 1705.8, 1: 1733.7. Samples: 28942056. Policy #0 lag: (min: 11.0, avg: 12.3, max: 35.0) -[2023-10-15 04:32:08,534][87330] Avg episode reward: [(0, '22.460'), (1, '22.500')] -[2023-10-15 04:32:09,460][88300] Updated weights for policy 1, policy_version 56682 (0.0008) -[2023-10-15 04:32:09,831][88300] Updated weights for policy 1, policy_version 56692 (0.0010) -[2023-10-15 04:32:10,190][88300] Updated weights for policy 1, policy_version 56702 (0.0007) -[2023-10-15 04:32:10,364][88298] Updated weights for policy 0, policy_version 56360 (0.0009) -[2023-10-15 04:32:10,752][88298] Updated weights for policy 0, policy_version 56370 (0.0009) -[2023-10-15 04:32:11,111][88298] Updated weights for policy 0, policy_version 56380 (0.0007) -[2023-10-15 04:32:13,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 115802112. Throughput: 0: 1717.5, 1: 1768.9. Samples: 28963502. Policy #0 lag: (min: 11.0, avg: 12.3, max: 35.0) -[2023-10-15 04:32:13,535][87330] Avg episode reward: [(0, '22.400'), (1, '22.550')] -[2023-10-15 04:32:14,160][88300] Updated weights for policy 1, policy_version 56712 (0.0008) -[2023-10-15 04:32:14,542][88300] Updated weights for policy 1, policy_version 56722 (0.0007) -[2023-10-15 04:32:14,919][88300] Updated weights for policy 1, policy_version 56732 (0.0008) -[2023-10-15 04:32:15,054][88298] Updated weights for policy 0, policy_version 56390 (0.0009) -[2023-10-15 04:32:15,434][88298] Updated weights for policy 0, policy_version 56400 (0.0010) -[2023-10-15 04:32:15,808][88298] Updated weights for policy 0, policy_version 56410 (0.0008) -[2023-10-15 04:32:18,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 115867648. Throughput: 0: 1713.0, 1: 1742.3. Samples: 28973222. Policy #0 lag: (min: 11.0, avg: 12.3, max: 35.0) -[2023-10-15 04:32:18,534][87330] Avg episode reward: [(0, '22.190'), (1, '22.540')] -[2023-10-15 04:32:18,668][88300] Updated weights for policy 1, policy_version 56742 (0.0008) -[2023-10-15 04:32:19,045][88300] Updated weights for policy 1, policy_version 56752 (0.0009) -[2023-10-15 04:32:19,416][88300] Updated weights for policy 1, policy_version 56762 (0.0007) -[2023-10-15 04:32:19,675][88298] Updated weights for policy 0, policy_version 56420 (0.0009) -[2023-10-15 04:32:20,042][88298] Updated weights for policy 0, policy_version 56430 (0.0009) -[2023-10-15 04:32:20,415][88298] Updated weights for policy 0, policy_version 56440 (0.0007) -[2023-10-15 04:32:23,365][88300] Updated weights for policy 1, policy_version 56772 (0.0010) -[2023-10-15 04:32:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 115933184. Throughput: 0: 1703.9, 1: 1759.2. Samples: 28994342. Policy #0 lag: (min: 11.0, avg: 12.3, max: 35.0) -[2023-10-15 04:32:23,534][87330] Avg episode reward: [(0, '22.200'), (1, '22.470')] -[2023-10-15 04:32:23,735][88300] Updated weights for policy 1, policy_version 56782 (0.0010) -[2023-10-15 04:32:24,106][88300] Updated weights for policy 1, policy_version 56792 (0.0007) -[2023-10-15 04:32:24,365][88298] Updated weights for policy 0, policy_version 56450 (0.0009) -[2023-10-15 04:32:24,741][88298] Updated weights for policy 0, policy_version 56460 (0.0007) -[2023-10-15 04:32:25,112][88298] Updated weights for policy 0, policy_version 56470 (0.0007) -[2023-10-15 04:32:25,489][88298] Updated weights for policy 0, policy_version 56480 (0.0009) -[2023-10-15 04:32:27,842][88300] Updated weights for policy 1, policy_version 56802 (0.0007) -[2023-10-15 04:32:28,202][88300] Updated weights for policy 1, policy_version 56812 (0.0008) -[2023-10-15 04:32:28,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 115998720. Throughput: 0: 1733.0, 1: 1759.1. Samples: 29015728. Policy #0 lag: (min: 11.0, avg: 12.3, max: 35.0) -[2023-10-15 04:32:28,534][87330] Avg episode reward: [(0, '22.450'), (1, '22.750')] -[2023-10-15 04:32:28,570][88300] Updated weights for policy 1, policy_version 56822 (0.0007) -[2023-10-15 04:32:28,938][88300] Updated weights for policy 1, policy_version 56832 (0.0009) -[2023-10-15 04:32:29,361][88298] Updated weights for policy 0, policy_version 56490 (0.0011) -[2023-10-15 04:32:29,724][88298] Updated weights for policy 0, policy_version 56500 (0.0009) -[2023-10-15 04:32:30,094][88298] Updated weights for policy 0, policy_version 56510 (0.0008) -[2023-10-15 04:32:32,880][88300] Updated weights for policy 1, policy_version 56842 (0.0009) -[2023-10-15 04:32:33,244][88300] Updated weights for policy 1, policy_version 56852 (0.0008) -[2023-10-15 04:32:33,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 116064256. Throughput: 0: 1704.3, 1: 1752.6. Samples: 29025664. Policy #0 lag: (min: 11.0, avg: 12.3, max: 35.0) -[2023-10-15 04:32:33,534][87330] Avg episode reward: [(0, '22.450'), (1, '22.790')] -[2023-10-15 04:32:33,597][88300] Updated weights for policy 1, policy_version 56862 (0.0007) -[2023-10-15 04:32:33,985][88298] Updated weights for policy 0, policy_version 56520 (0.0009) -[2023-10-15 04:32:34,359][88298] Updated weights for policy 0, policy_version 56530 (0.0010) -[2023-10-15 04:32:34,722][88298] Updated weights for policy 0, policy_version 56540 (0.0011) -[2023-10-15 04:32:37,466][88300] Updated weights for policy 1, policy_version 56872 (0.0009) -[2023-10-15 04:32:37,829][88300] Updated weights for policy 1, policy_version 56882 (0.0008) -[2023-10-15 04:32:38,204][88300] Updated weights for policy 1, policy_version 56892 (0.0009) -[2023-10-15 04:32:38,534][87330] Fps is (10 sec: 16384.2, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 116162560. Throughput: 0: 1721.2, 1: 1771.9. Samples: 29047370. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:32:38,534][87330] Avg episode reward: [(0, '22.460'), (1, '22.790')] -[2023-10-15 04:32:38,745][88298] Updated weights for policy 0, policy_version 56550 (0.0010) -[2023-10-15 04:32:39,120][88298] Updated weights for policy 0, policy_version 56560 (0.0009) -[2023-10-15 04:32:39,491][88298] Updated weights for policy 0, policy_version 56570 (0.0009) -[2023-10-15 04:32:42,072][88300] Updated weights for policy 1, policy_version 56902 (0.0009) -[2023-10-15 04:32:42,454][88300] Updated weights for policy 1, policy_version 56912 (0.0007) -[2023-10-15 04:32:42,828][88300] Updated weights for policy 1, policy_version 56922 (0.0008) -[2023-10-15 04:32:43,411][88298] Updated weights for policy 0, policy_version 56580 (0.0007) -[2023-10-15 04:32:43,534][87330] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 116228096. Throughput: 0: 1736.8, 1: 1746.0. Samples: 29067534. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:32:43,534][87330] Avg episode reward: [(0, '22.320'), (1, '22.830')] -[2023-10-15 04:32:43,774][88298] Updated weights for policy 0, policy_version 56590 (0.0008) -[2023-10-15 04:32:44,145][88298] Updated weights for policy 0, policy_version 56600 (0.0008) -[2023-10-15 04:32:46,642][88300] Updated weights for policy 1, policy_version 56932 (0.0010) -[2023-10-15 04:32:47,005][88300] Updated weights for policy 1, policy_version 56942 (0.0010) -[2023-10-15 04:32:47,375][88300] Updated weights for policy 1, policy_version 56952 (0.0008) -[2023-10-15 04:32:48,248][88298] Updated weights for policy 0, policy_version 56610 (0.0009) -[2023-10-15 04:32:48,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 116293632. Throughput: 0: 1707.3, 1: 1780.4. Samples: 29078372. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:32:48,534][87330] Avg episode reward: [(0, '22.480'), (1, '22.650')] -[2023-10-15 04:32:48,611][88298] Updated weights for policy 0, policy_version 56620 (0.0010) -[2023-10-15 04:32:48,982][88298] Updated weights for policy 0, policy_version 56630 (0.0007) -[2023-10-15 04:32:49,357][88298] Updated weights for policy 0, policy_version 56640 (0.0007) -[2023-10-15 04:32:51,286][88300] Updated weights for policy 1, policy_version 56962 (0.0009) -[2023-10-15 04:32:51,646][88300] Updated weights for policy 1, policy_version 56972 (0.0011) -[2023-10-15 04:32:52,021][88300] Updated weights for policy 1, policy_version 56982 (0.0008) -[2023-10-15 04:32:52,385][88300] Updated weights for policy 1, policy_version 56992 (0.0008) -[2023-10-15 04:32:53,195][88298] Updated weights for policy 0, policy_version 56650 (0.0008) -[2023-10-15 04:32:53,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 116359168. Throughput: 0: 1731.6, 1: 1748.4. Samples: 29098658. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:32:53,535][87330] Avg episode reward: [(0, '22.680'), (1, '22.650')] -[2023-10-15 04:32:53,566][88298] Updated weights for policy 0, policy_version 56660 (0.0009) -[2023-10-15 04:32:53,939][88298] Updated weights for policy 0, policy_version 56670 (0.0011) -[2023-10-15 04:32:56,229][88300] Updated weights for policy 1, policy_version 57002 (0.0010) -[2023-10-15 04:32:56,602][88300] Updated weights for policy 1, policy_version 57012 (0.0009) -[2023-10-15 04:32:56,964][88300] Updated weights for policy 1, policy_version 57022 (0.0009) -[2023-10-15 04:32:57,916][88298] Updated weights for policy 0, policy_version 56680 (0.0010) -[2023-10-15 04:32:58,299][88298] Updated weights for policy 0, policy_version 56690 (0.0009) -[2023-10-15 04:32:58,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 116424704. Throughput: 0: 1733.9, 1: 1746.8. Samples: 29120132. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:32:58,534][87330] Avg episode reward: [(0, '22.550'), (1, '22.750')] -[2023-10-15 04:32:58,541][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000057024_58392576.pth... -[2023-10-15 04:32:58,578][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000055392_56721408.pth -[2023-10-15 04:32:58,583][88033] Saving a milestone ./train_atari/atari_seaquest_APPO/checkpoint_p1/milestones/checkpoint_000057024_58392576.pth -[2023-10-15 04:32:58,671][88298] Updated weights for policy 0, policy_version 56700 (0.0008) -[2023-10-15 04:32:58,811][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000056704_58064896.pth... -[2023-10-15 04:32:58,850][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000055072_56393728.pth -[2023-10-15 04:32:58,855][87905] Saving a milestone ./train_atari/atari_seaquest_APPO/checkpoint_p0/milestones/checkpoint_000056704_58064896.pth -[2023-10-15 04:33:00,919][88300] Updated weights for policy 1, policy_version 57032 (0.0009) -[2023-10-15 04:33:01,285][88300] Updated weights for policy 1, policy_version 57042 (0.0010) -[2023-10-15 04:33:01,647][88300] Updated weights for policy 1, policy_version 57052 (0.0009) -[2023-10-15 04:33:02,405][88298] Updated weights for policy 0, policy_version 56710 (0.0008) -[2023-10-15 04:33:02,771][88298] Updated weights for policy 0, policy_version 56720 (0.0009) -[2023-10-15 04:33:03,148][88298] Updated weights for policy 0, policy_version 56730 (0.0007) -[2023-10-15 04:33:03,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 116523008. Throughput: 0: 1731.9, 1: 1762.4. Samples: 29130470. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:33:03,535][87330] Avg episode reward: [(0, '22.400'), (1, '22.810')] -[2023-10-15 04:33:05,578][88300] Updated weights for policy 1, policy_version 57062 (0.0009) -[2023-10-15 04:33:05,935][88300] Updated weights for policy 1, policy_version 57072 (0.0010) -[2023-10-15 04:33:06,296][88300] Updated weights for policy 1, policy_version 57082 (0.0009) -[2023-10-15 04:33:07,064][88298] Updated weights for policy 0, policy_version 56740 (0.0007) -[2023-10-15 04:33:07,421][88298] Updated weights for policy 0, policy_version 56750 (0.0008) -[2023-10-15 04:33:07,791][88298] Updated weights for policy 0, policy_version 56760 (0.0009) -[2023-10-15 04:33:08,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 116588544. Throughput: 0: 1744.4, 1: 1740.6. Samples: 29151164. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:33:08,535][87330] Avg episode reward: [(0, '22.340'), (1, '22.710')] -[2023-10-15 04:33:10,333][88300] Updated weights for policy 1, policy_version 57092 (0.0010) -[2023-10-15 04:33:10,705][88300] Updated weights for policy 1, policy_version 57102 (0.0007) -[2023-10-15 04:33:11,071][88300] Updated weights for policy 1, policy_version 57112 (0.0008) -[2023-10-15 04:33:11,761][88298] Updated weights for policy 0, policy_version 56770 (0.0009) -[2023-10-15 04:33:12,126][88298] Updated weights for policy 0, policy_version 56780 (0.0011) -[2023-10-15 04:33:12,492][88298] Updated weights for policy 0, policy_version 56790 (0.0011) -[2023-10-15 04:33:12,863][88298] Updated weights for policy 0, policy_version 56800 (0.0009) -[2023-10-15 04:33:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 116654080. Throughput: 0: 1718.8, 1: 1745.4. Samples: 29171614. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-15 04:33:13,535][87330] Avg episode reward: [(0, '22.610'), (1, '22.690')] -[2023-10-15 04:33:14,818][88300] Updated weights for policy 1, policy_version 57122 (0.0008) -[2023-10-15 04:33:15,186][88300] Updated weights for policy 1, policy_version 57132 (0.0008) -[2023-10-15 04:33:15,555][88300] Updated weights for policy 1, policy_version 57142 (0.0012) -[2023-10-15 04:33:15,915][88300] Updated weights for policy 1, policy_version 57152 (0.0010) -[2023-10-15 04:33:16,783][88298] Updated weights for policy 0, policy_version 56810 (0.0008) -[2023-10-15 04:33:17,150][88298] Updated weights for policy 0, policy_version 56820 (0.0007) -[2023-10-15 04:33:17,525][88298] Updated weights for policy 0, policy_version 56830 (0.0008) -[2023-10-15 04:33:18,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 116719616. Throughput: 0: 1751.9, 1: 1730.1. Samples: 29182356. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-15 04:33:18,534][87330] Avg episode reward: [(0, '22.570'), (1, '22.840')] -[2023-10-15 04:33:19,878][88300] Updated weights for policy 1, policy_version 57162 (0.0012) -[2023-10-15 04:33:20,247][88300] Updated weights for policy 1, policy_version 57172 (0.0011) -[2023-10-15 04:33:20,628][88300] Updated weights for policy 1, policy_version 57182 (0.0008) -[2023-10-15 04:33:21,493][88298] Updated weights for policy 0, policy_version 56840 (0.0010) -[2023-10-15 04:33:21,870][88298] Updated weights for policy 0, policy_version 56850 (0.0009) -[2023-10-15 04:33:22,233][88298] Updated weights for policy 0, policy_version 56860 (0.0009) -[2023-10-15 04:33:23,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 116785152. Throughput: 0: 1740.2, 1: 1727.2. Samples: 29203404. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-15 04:33:23,534][87330] Avg episode reward: [(0, '22.560'), (1, '22.850')] -[2023-10-15 04:33:24,465][88300] Updated weights for policy 1, policy_version 57192 (0.0008) -[2023-10-15 04:33:24,832][88300] Updated weights for policy 1, policy_version 57202 (0.0008) -[2023-10-15 04:33:25,198][88300] Updated weights for policy 1, policy_version 57212 (0.0009) -[2023-10-15 04:33:25,943][88298] Updated weights for policy 0, policy_version 56870 (0.0007) -[2023-10-15 04:33:26,313][88298] Updated weights for policy 0, policy_version 56880 (0.0011) -[2023-10-15 04:33:26,683][88298] Updated weights for policy 0, policy_version 56890 (0.0010) -[2023-10-15 04:33:28,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 116850688. Throughput: 0: 1733.0, 1: 1762.5. Samples: 29224834. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-15 04:33:28,535][87330] Avg episode reward: [(0, '22.690'), (1, '22.770')] -[2023-10-15 04:33:29,018][88300] Updated weights for policy 1, policy_version 57222 (0.0008) -[2023-10-15 04:33:29,383][88300] Updated weights for policy 1, policy_version 57232 (0.0009) -[2023-10-15 04:33:29,760][88300] Updated weights for policy 1, policy_version 57242 (0.0009) -[2023-10-15 04:33:30,496][88298] Updated weights for policy 0, policy_version 56900 (0.0008) -[2023-10-15 04:33:30,856][88298] Updated weights for policy 0, policy_version 56910 (0.0007) -[2023-10-15 04:33:31,228][88298] Updated weights for policy 0, policy_version 56920 (0.0010) -[2023-10-15 04:33:33,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 116916224. Throughput: 0: 1761.7, 1: 1728.5. Samples: 29235430. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-15 04:33:33,534][87330] Avg episode reward: [(0, '22.860'), (1, '22.750')] -[2023-10-15 04:33:33,564][88300] Updated weights for policy 1, policy_version 57252 (0.0010) -[2023-10-15 04:33:33,925][88300] Updated weights for policy 1, policy_version 57262 (0.0008) -[2023-10-15 04:33:34,294][88300] Updated weights for policy 1, policy_version 57272 (0.0008) -[2023-10-15 04:33:35,147][88298] Updated weights for policy 0, policy_version 56930 (0.0010) -[2023-10-15 04:33:35,516][88298] Updated weights for policy 0, policy_version 56940 (0.0007) -[2023-10-15 04:33:35,887][88298] Updated weights for policy 0, policy_version 56950 (0.0007) -[2023-10-15 04:33:36,258][88298] Updated weights for policy 0, policy_version 56960 (0.0010) -[2023-10-15 04:33:38,224][88300] Updated weights for policy 1, policy_version 57282 (0.0010) -[2023-10-15 04:33:38,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 116981760. Throughput: 0: 1743.3, 1: 1760.1. Samples: 29256312. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-15 04:33:38,535][87330] Avg episode reward: [(0, '22.850'), (1, '22.730')] -[2023-10-15 04:33:38,582][88300] Updated weights for policy 1, policy_version 57292 (0.0010) -[2023-10-15 04:33:38,951][88300] Updated weights for policy 1, policy_version 57302 (0.0007) -[2023-10-15 04:33:39,322][88300] Updated weights for policy 1, policy_version 57312 (0.0007) -[2023-10-15 04:33:39,927][88298] Updated weights for policy 0, policy_version 56970 (0.0009) -[2023-10-15 04:33:40,297][88298] Updated weights for policy 0, policy_version 56980 (0.0009) -[2023-10-15 04:33:40,670][88298] Updated weights for policy 0, policy_version 56990 (0.0009) -[2023-10-15 04:33:43,326][88300] Updated weights for policy 1, policy_version 57322 (0.0008) -[2023-10-15 04:33:43,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 117047296. Throughput: 0: 1748.5, 1: 1753.7. Samples: 29277732. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-15 04:33:43,534][87330] Avg episode reward: [(0, '22.860'), (1, '22.760')] -[2023-10-15 04:33:43,689][88300] Updated weights for policy 1, policy_version 57332 (0.0008) -[2023-10-15 04:33:44,065][88300] Updated weights for policy 1, policy_version 57342 (0.0008) -[2023-10-15 04:33:44,496][88298] Updated weights for policy 0, policy_version 57000 (0.0010) -[2023-10-15 04:33:44,860][88298] Updated weights for policy 0, policy_version 57010 (0.0010) -[2023-10-15 04:33:45,231][88298] Updated weights for policy 0, policy_version 57020 (0.0010) -[2023-10-15 04:33:48,049][88300] Updated weights for policy 1, policy_version 57352 (0.0008) -[2023-10-15 04:33:48,425][88300] Updated weights for policy 1, policy_version 57362 (0.0011) -[2023-10-15 04:33:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 117112832. Throughput: 0: 1745.5, 1: 1745.5. Samples: 29287564. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-15 04:33:48,535][87330] Avg episode reward: [(0, '22.910'), (1, '22.800')] -[2023-10-15 04:33:48,789][88300] Updated weights for policy 1, policy_version 57372 (0.0007) -[2023-10-15 04:33:49,220][88298] Updated weights for policy 0, policy_version 57030 (0.0009) -[2023-10-15 04:33:49,588][88298] Updated weights for policy 0, policy_version 57040 (0.0009) -[2023-10-15 04:33:49,961][88298] Updated weights for policy 0, policy_version 57050 (0.0009) -[2023-10-15 04:33:52,584][88300] Updated weights for policy 1, policy_version 57382 (0.0007) -[2023-10-15 04:33:52,957][88300] Updated weights for policy 1, policy_version 57392 (0.0007) -[2023-10-15 04:33:53,318][88300] Updated weights for policy 1, policy_version 57402 (0.0007) -[2023-10-15 04:33:53,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 117211136. Throughput: 0: 1740.8, 1: 1761.0. Samples: 29308742. Policy #0 lag: (min: 16.0, avg: 32.9, max: 48.0) -[2023-10-15 04:33:53,534][87330] Avg episode reward: [(0, '22.960'), (1, '22.840')] -[2023-10-15 04:33:53,985][88298] Updated weights for policy 0, policy_version 57060 (0.0009) -[2023-10-15 04:33:54,369][88298] Updated weights for policy 0, policy_version 57070 (0.0009) -[2023-10-15 04:33:54,738][88298] Updated weights for policy 0, policy_version 57080 (0.0009) -[2023-10-15 04:33:57,353][88300] Updated weights for policy 1, policy_version 57412 (0.0008) -[2023-10-15 04:33:57,713][88300] Updated weights for policy 1, policy_version 57422 (0.0011) -[2023-10-15 04:33:58,078][88300] Updated weights for policy 1, policy_version 57432 (0.0008) -[2023-10-15 04:33:58,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 117276672. Throughput: 0: 1758.4, 1: 1729.0. Samples: 29328546. Policy #0 lag: (min: 16.0, avg: 32.9, max: 48.0) -[2023-10-15 04:33:58,535][87330] Avg episode reward: [(0, '22.750'), (1, '22.660')] -[2023-10-15 04:33:58,782][88298] Updated weights for policy 0, policy_version 57090 (0.0008) -[2023-10-15 04:33:59,157][88298] Updated weights for policy 0, policy_version 57100 (0.0008) -[2023-10-15 04:33:59,532][88298] Updated weights for policy 0, policy_version 57110 (0.0009) -[2023-10-15 04:33:59,894][88298] Updated weights for policy 0, policy_version 57120 (0.0007) -[2023-10-15 04:34:01,973][88300] Updated weights for policy 1, policy_version 57442 (0.0009) -[2023-10-15 04:34:02,344][88300] Updated weights for policy 1, policy_version 57452 (0.0007) -[2023-10-15 04:34:02,701][88300] Updated weights for policy 1, policy_version 57462 (0.0009) -[2023-10-15 04:34:03,070][88300] Updated weights for policy 1, policy_version 57472 (0.0008) -[2023-10-15 04:34:03,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 117342208. Throughput: 0: 1724.4, 1: 1758.0. Samples: 29339068. Policy #0 lag: (min: 16.0, avg: 32.9, max: 48.0) -[2023-10-15 04:34:03,534][87330] Avg episode reward: [(0, '22.760'), (1, '22.610')] -[2023-10-15 04:34:03,909][88298] Updated weights for policy 0, policy_version 57130 (0.0007) -[2023-10-15 04:34:04,278][88298] Updated weights for policy 0, policy_version 57140 (0.0009) -[2023-10-15 04:34:04,647][88298] Updated weights for policy 0, policy_version 57150 (0.0007) -[2023-10-15 04:34:07,020][88300] Updated weights for policy 1, policy_version 57482 (0.0007) -[2023-10-15 04:34:07,390][88300] Updated weights for policy 1, policy_version 57492 (0.0008) -[2023-10-15 04:34:07,758][88300] Updated weights for policy 1, policy_version 57502 (0.0009) -[2023-10-15 04:34:08,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 117407744. Throughput: 0: 1732.8, 1: 1740.7. Samples: 29359716. Policy #0 lag: (min: 16.0, avg: 32.9, max: 48.0) -[2023-10-15 04:34:08,535][87330] Avg episode reward: [(0, '22.760'), (1, '22.370')] -[2023-10-15 04:34:08,547][88298] Updated weights for policy 0, policy_version 57160 (0.0008) -[2023-10-15 04:34:08,907][88298] Updated weights for policy 0, policy_version 57170 (0.0008) -[2023-10-15 04:34:09,283][88298] Updated weights for policy 0, policy_version 57180 (0.0009) -[2023-10-15 04:34:11,592][88300] Updated weights for policy 1, policy_version 57512 (0.0007) -[2023-10-15 04:34:11,964][88300] Updated weights for policy 1, policy_version 57522 (0.0009) -[2023-10-15 04:34:12,337][88300] Updated weights for policy 1, policy_version 57532 (0.0008) -[2023-10-15 04:34:13,215][88298] Updated weights for policy 0, policy_version 57190 (0.0009) -[2023-10-15 04:34:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 117473280. Throughput: 0: 1744.1, 1: 1716.5. Samples: 29380562. Policy #0 lag: (min: 16.0, avg: 32.9, max: 48.0) -[2023-10-15 04:34:13,534][87330] Avg episode reward: [(0, '22.780'), (1, '22.430')] -[2023-10-15 04:34:13,584][88298] Updated weights for policy 0, policy_version 57200 (0.0010) -[2023-10-15 04:34:13,950][88298] Updated weights for policy 0, policy_version 57210 (0.0009) -[2023-10-15 04:34:16,269][88300] Updated weights for policy 1, policy_version 57542 (0.0008) -[2023-10-15 04:34:16,645][88300] Updated weights for policy 1, policy_version 57552 (0.0010) -[2023-10-15 04:34:17,006][88300] Updated weights for policy 1, policy_version 57562 (0.0010) -[2023-10-15 04:34:17,841][88298] Updated weights for policy 0, policy_version 57220 (0.0009) -[2023-10-15 04:34:18,203][88298] Updated weights for policy 0, policy_version 57230 (0.0008) -[2023-10-15 04:34:18,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 117538816. Throughput: 0: 1718.3, 1: 1743.8. Samples: 29391224. Policy #0 lag: (min: 16.0, avg: 32.9, max: 48.0) -[2023-10-15 04:34:18,534][87330] Avg episode reward: [(0, '22.780'), (1, '22.320')] -[2023-10-15 04:34:18,577][88298] Updated weights for policy 0, policy_version 57240 (0.0007) -[2023-10-15 04:34:20,789][88300] Updated weights for policy 1, policy_version 57572 (0.0009) -[2023-10-15 04:34:21,150][88300] Updated weights for policy 1, policy_version 57582 (0.0008) -[2023-10-15 04:34:21,518][88300] Updated weights for policy 1, policy_version 57592 (0.0007) -[2023-10-15 04:34:22,538][88298] Updated weights for policy 0, policy_version 57250 (0.0008) -[2023-10-15 04:34:22,901][88298] Updated weights for policy 0, policy_version 57260 (0.0007) -[2023-10-15 04:34:23,283][88298] Updated weights for policy 0, policy_version 57270 (0.0008) -[2023-10-15 04:34:23,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 117604352. Throughput: 0: 1738.6, 1: 1718.7. Samples: 29411892. Policy #0 lag: (min: 16.0, avg: 32.9, max: 48.0) -[2023-10-15 04:34:23,534][87330] Avg episode reward: [(0, '22.700'), (1, '22.150')] -[2023-10-15 04:34:23,646][88298] Updated weights for policy 0, policy_version 57280 (0.0007) -[2023-10-15 04:34:25,236][88300] Updated weights for policy 1, policy_version 57602 (0.0008) -[2023-10-15 04:34:25,610][88300] Updated weights for policy 1, policy_version 57612 (0.0008) -[2023-10-15 04:34:25,978][88300] Updated weights for policy 1, policy_version 57622 (0.0007) -[2023-10-15 04:34:26,343][88300] Updated weights for policy 1, policy_version 57632 (0.0008) -[2023-10-15 04:34:27,492][88298] Updated weights for policy 0, policy_version 57290 (0.0011) -[2023-10-15 04:34:27,857][88298] Updated weights for policy 0, policy_version 57300 (0.0011) -[2023-10-15 04:34:28,235][88298] Updated weights for policy 0, policy_version 57310 (0.0007) -[2023-10-15 04:34:28,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 117702656. Throughput: 0: 1720.0, 1: 1731.6. Samples: 29433054. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:34:28,534][87330] Avg episode reward: [(0, '22.650'), (1, '22.200')] -[2023-10-15 04:34:30,320][88300] Updated weights for policy 1, policy_version 57642 (0.0009) -[2023-10-15 04:34:30,699][88300] Updated weights for policy 1, policy_version 57652 (0.0009) -[2023-10-15 04:34:31,061][88300] Updated weights for policy 1, policy_version 57662 (0.0007) -[2023-10-15 04:34:32,172][88298] Updated weights for policy 0, policy_version 57320 (0.0007) -[2023-10-15 04:34:32,558][88298] Updated weights for policy 0, policy_version 57330 (0.0009) -[2023-10-15 04:34:32,922][88298] Updated weights for policy 0, policy_version 57340 (0.0009) -[2023-10-15 04:34:33,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 117768192. Throughput: 0: 1739.3, 1: 1726.8. Samples: 29443538. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:34:33,534][87330] Avg episode reward: [(0, '22.860'), (1, '22.270')] -[2023-10-15 04:34:34,961][88300] Updated weights for policy 1, policy_version 57672 (0.0008) -[2023-10-15 04:34:35,329][88300] Updated weights for policy 1, policy_version 57682 (0.0009) -[2023-10-15 04:34:35,706][88300] Updated weights for policy 1, policy_version 57692 (0.0009) -[2023-10-15 04:34:36,727][88298] Updated weights for policy 0, policy_version 57350 (0.0010) -[2023-10-15 04:34:37,098][88298] Updated weights for policy 0, policy_version 57360 (0.0008) -[2023-10-15 04:34:37,466][88298] Updated weights for policy 0, policy_version 57370 (0.0009) -[2023-10-15 04:34:38,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 117833728. Throughput: 0: 1732.9, 1: 1731.0. Samples: 29464618. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:34:38,535][87330] Avg episode reward: [(0, '22.840'), (1, '22.500')] -[2023-10-15 04:34:39,546][88300] Updated weights for policy 1, policy_version 57702 (0.0009) -[2023-10-15 04:34:39,932][88300] Updated weights for policy 1, policy_version 57712 (0.0009) -[2023-10-15 04:34:40,299][88300] Updated weights for policy 1, policy_version 57722 (0.0009) -[2023-10-15 04:34:41,365][88298] Updated weights for policy 0, policy_version 57380 (0.0010) -[2023-10-15 04:34:41,740][88298] Updated weights for policy 0, policy_version 57390 (0.0008) -[2023-10-15 04:34:42,106][88298] Updated weights for policy 0, policy_version 57400 (0.0007) -[2023-10-15 04:34:43,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 117899264. Throughput: 0: 1715.2, 1: 1766.5. Samples: 29485224. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:34:43,534][87330] Avg episode reward: [(0, '22.630'), (1, '22.490')] -[2023-10-15 04:34:44,111][88300] Updated weights for policy 1, policy_version 57732 (0.0010) -[2023-10-15 04:34:44,479][88300] Updated weights for policy 1, policy_version 57742 (0.0009) -[2023-10-15 04:34:44,839][88300] Updated weights for policy 1, policy_version 57752 (0.0007) -[2023-10-15 04:34:46,094][88298] Updated weights for policy 0, policy_version 57410 (0.0007) -[2023-10-15 04:34:46,475][88298] Updated weights for policy 0, policy_version 57420 (0.0007) -[2023-10-15 04:34:46,848][88298] Updated weights for policy 0, policy_version 57430 (0.0007) -[2023-10-15 04:34:47,222][88298] Updated weights for policy 0, policy_version 57440 (0.0009) -[2023-10-15 04:34:48,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 117964800. Throughput: 0: 1752.4, 1: 1736.3. Samples: 29496058. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:34:48,534][87330] Avg episode reward: [(0, '22.610'), (1, '22.620')] -[2023-10-15 04:34:48,790][88300] Updated weights for policy 1, policy_version 57762 (0.0010) -[2023-10-15 04:34:49,162][88300] Updated weights for policy 1, policy_version 57772 (0.0008) -[2023-10-15 04:34:49,524][88300] Updated weights for policy 1, policy_version 57782 (0.0007) -[2023-10-15 04:34:49,896][88300] Updated weights for policy 1, policy_version 57792 (0.0008) -[2023-10-15 04:34:51,167][88298] Updated weights for policy 0, policy_version 57450 (0.0009) -[2023-10-15 04:34:51,526][88298] Updated weights for policy 0, policy_version 57460 (0.0008) -[2023-10-15 04:34:51,902][88298] Updated weights for policy 0, policy_version 57470 (0.0008) -[2023-10-15 04:34:53,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 118030336. Throughput: 0: 1730.5, 1: 1754.7. Samples: 29516552. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:34:53,534][87330] Avg episode reward: [(0, '22.650'), (1, '22.780')] -[2023-10-15 04:34:53,895][88300] Updated weights for policy 1, policy_version 57802 (0.0010) -[2023-10-15 04:34:54,263][88300] Updated weights for policy 1, policy_version 57812 (0.0010) -[2023-10-15 04:34:54,627][88300] Updated weights for policy 1, policy_version 57822 (0.0010) -[2023-10-15 04:34:55,852][88298] Updated weights for policy 0, policy_version 57480 (0.0010) -[2023-10-15 04:34:56,216][88298] Updated weights for policy 0, policy_version 57490 (0.0010) -[2023-10-15 04:34:56,586][88298] Updated weights for policy 0, policy_version 57500 (0.0010) -[2023-10-15 04:34:58,492][88300] Updated weights for policy 1, policy_version 57832 (0.0007) -[2023-10-15 04:34:58,534][87330] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 118095872. Throughput: 0: 1718.7, 1: 1774.3. Samples: 29537746. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:34:58,535][87330] Avg episode reward: [(0, '22.700'), (1, '22.900')] -[2023-10-15 04:34:58,545][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000057504_58884096.pth... -[2023-10-15 04:34:58,576][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000055904_57245696.pth -[2023-10-15 04:34:58,867][88300] Updated weights for policy 1, policy_version 57842 (0.0009) -[2023-10-15 04:34:59,225][88300] Updated weights for policy 1, policy_version 57852 (0.0008) -[2023-10-15 04:34:59,367][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000057856_59244544.pth... -[2023-10-15 04:34:59,396][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000056192_57540608.pth -[2023-10-15 04:35:00,314][88298] Updated weights for policy 0, policy_version 57510 (0.0008) -[2023-10-15 04:35:00,691][88298] Updated weights for policy 0, policy_version 57520 (0.0008) -[2023-10-15 04:35:01,057][88298] Updated weights for policy 0, policy_version 57530 (0.0008) -[2023-10-15 04:35:03,125][88300] Updated weights for policy 1, policy_version 57862 (0.0009) -[2023-10-15 04:35:03,501][88300] Updated weights for policy 1, policy_version 57872 (0.0010) -[2023-10-15 04:35:03,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 118161408. Throughput: 0: 1736.6, 1: 1743.8. Samples: 29547840. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:35:03,535][87330] Avg episode reward: [(0, '22.690'), (1, '22.940')] -[2023-10-15 04:35:03,864][88300] Updated weights for policy 1, policy_version 57882 (0.0010) -[2023-10-15 04:35:04,908][88298] Updated weights for policy 0, policy_version 57540 (0.0007) -[2023-10-15 04:35:05,273][88298] Updated weights for policy 0, policy_version 57550 (0.0009) -[2023-10-15 04:35:05,643][88298] Updated weights for policy 0, policy_version 57560 (0.0008) -[2023-10-15 04:35:07,713][88300] Updated weights for policy 1, policy_version 57892 (0.0008) -[2023-10-15 04:35:08,083][88300] Updated weights for policy 1, policy_version 57902 (0.0007) -[2023-10-15 04:35:08,444][88300] Updated weights for policy 1, policy_version 57912 (0.0007) -[2023-10-15 04:35:08,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 118226944. Throughput: 0: 1724.7, 1: 1766.7. Samples: 29569002. Policy #0 lag: (min: 31.0, avg: 31.2, max: 42.0) -[2023-10-15 04:35:08,534][87330] Avg episode reward: [(0, '22.730'), (1, '22.860')] -[2023-10-15 04:35:09,364][88298] Updated weights for policy 0, policy_version 57570 (0.0009) -[2023-10-15 04:35:09,738][88298] Updated weights for policy 0, policy_version 57580 (0.0008) -[2023-10-15 04:35:10,101][88298] Updated weights for policy 0, policy_version 57590 (0.0007) -[2023-10-15 04:35:10,479][88298] Updated weights for policy 0, policy_version 57600 (0.0007) -[2023-10-15 04:35:12,216][88300] Updated weights for policy 1, policy_version 57922 (0.0007) -[2023-10-15 04:35:12,591][88300] Updated weights for policy 1, policy_version 57932 (0.0010) -[2023-10-15 04:35:12,948][88300] Updated weights for policy 1, policy_version 57942 (0.0009) -[2023-10-15 04:35:13,312][88300] Updated weights for policy 1, policy_version 57952 (0.0010) -[2023-10-15 04:35:13,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 118325248. Throughput: 0: 1742.0, 1: 1734.1. Samples: 29589480. Policy #0 lag: (min: 31.0, avg: 31.2, max: 42.0) -[2023-10-15 04:35:13,535][87330] Avg episode reward: [(0, '22.650'), (1, '22.890')] -[2023-10-15 04:35:14,530][88298] Updated weights for policy 0, policy_version 57610 (0.0008) -[2023-10-15 04:35:14,895][88298] Updated weights for policy 0, policy_version 57620 (0.0008) -[2023-10-15 04:35:15,266][88298] Updated weights for policy 0, policy_version 57630 (0.0008) -[2023-10-15 04:35:17,141][88300] Updated weights for policy 1, policy_version 57962 (0.0008) -[2023-10-15 04:35:17,501][88300] Updated weights for policy 1, policy_version 57972 (0.0008) -[2023-10-15 04:35:17,871][88300] Updated weights for policy 1, policy_version 57982 (0.0007) -[2023-10-15 04:35:18,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 118390784. Throughput: 0: 1719.6, 1: 1759.3. Samples: 29600088. Policy #0 lag: (min: 31.0, avg: 31.2, max: 42.0) -[2023-10-15 04:35:18,535][87330] Avg episode reward: [(0, '22.890'), (1, '22.880')] -[2023-10-15 04:35:19,258][88298] Updated weights for policy 0, policy_version 57640 (0.0007) -[2023-10-15 04:35:19,630][88298] Updated weights for policy 0, policy_version 57650 (0.0009) -[2023-10-15 04:35:20,009][88298] Updated weights for policy 0, policy_version 57660 (0.0010) -[2023-10-15 04:35:21,596][88300] Updated weights for policy 1, policy_version 57992 (0.0011) -[2023-10-15 04:35:21,964][88300] Updated weights for policy 1, policy_version 58002 (0.0008) -[2023-10-15 04:35:22,336][88300] Updated weights for policy 1, policy_version 58012 (0.0007) -[2023-10-15 04:35:23,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 118456320. Throughput: 0: 1726.5, 1: 1740.1. Samples: 29620616. Policy #0 lag: (min: 31.0, avg: 31.2, max: 42.0) -[2023-10-15 04:35:23,534][87330] Avg episode reward: [(0, '22.910'), (1, '22.880')] -[2023-10-15 04:35:23,972][88298] Updated weights for policy 0, policy_version 57670 (0.0010) -[2023-10-15 04:35:24,348][88298] Updated weights for policy 0, policy_version 57680 (0.0007) -[2023-10-15 04:35:24,710][88298] Updated weights for policy 0, policy_version 57690 (0.0008) -[2023-10-15 04:35:26,271][88300] Updated weights for policy 1, policy_version 58022 (0.0008) -[2023-10-15 04:35:26,666][88300] Updated weights for policy 1, policy_version 58032 (0.0008) -[2023-10-15 04:35:27,027][88300] Updated weights for policy 1, policy_version 58042 (0.0009) -[2023-10-15 04:35:28,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 118521856. Throughput: 0: 1750.6, 1: 1731.1. Samples: 29641902. Policy #0 lag: (min: 31.0, avg: 31.2, max: 42.0) -[2023-10-15 04:35:28,535][87330] Avg episode reward: [(0, '22.920'), (1, '22.880')] -[2023-10-15 04:35:28,641][88298] Updated weights for policy 0, policy_version 57700 (0.0008) -[2023-10-15 04:35:29,017][88298] Updated weights for policy 0, policy_version 57710 (0.0009) -[2023-10-15 04:35:29,377][88298] Updated weights for policy 0, policy_version 57720 (0.0010) -[2023-10-15 04:35:30,816][88300] Updated weights for policy 1, policy_version 58052 (0.0008) -[2023-10-15 04:35:31,187][88300] Updated weights for policy 1, policy_version 58062 (0.0008) -[2023-10-15 04:35:31,549][88300] Updated weights for policy 1, policy_version 58072 (0.0008) -[2023-10-15 04:35:33,286][88298] Updated weights for policy 0, policy_version 57730 (0.0009) -[2023-10-15 04:35:33,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 118587392. Throughput: 0: 1716.4, 1: 1755.5. Samples: 29652294. Policy #0 lag: (min: 31.0, avg: 31.2, max: 42.0) -[2023-10-15 04:35:33,534][87330] Avg episode reward: [(0, '22.910'), (1, '22.900')] -[2023-10-15 04:35:33,657][88298] Updated weights for policy 0, policy_version 57740 (0.0008) -[2023-10-15 04:35:34,028][88298] Updated weights for policy 0, policy_version 57750 (0.0010) -[2023-10-15 04:35:34,406][88298] Updated weights for policy 0, policy_version 57760 (0.0009) -[2023-10-15 04:35:35,531][88300] Updated weights for policy 1, policy_version 58082 (0.0007) -[2023-10-15 04:35:35,898][88300] Updated weights for policy 1, policy_version 58092 (0.0010) -[2023-10-15 04:35:36,255][88300] Updated weights for policy 1, policy_version 58102 (0.0010) -[2023-10-15 04:35:36,618][88300] Updated weights for policy 1, policy_version 58112 (0.0009) -[2023-10-15 04:35:38,229][88298] Updated weights for policy 0, policy_version 57770 (0.0007) -[2023-10-15 04:35:38,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 118652928. Throughput: 0: 1739.8, 1: 1731.6. Samples: 29672764. Policy #0 lag: (min: 31.0, avg: 31.2, max: 42.0) -[2023-10-15 04:35:38,534][87330] Avg episode reward: [(0, '22.930'), (1, '22.700')] -[2023-10-15 04:35:38,599][88298] Updated weights for policy 0, policy_version 57780 (0.0009) -[2023-10-15 04:35:38,968][88298] Updated weights for policy 0, policy_version 57790 (0.0009) -[2023-10-15 04:35:40,546][88300] Updated weights for policy 1, policy_version 58122 (0.0008) -[2023-10-15 04:35:40,909][88300] Updated weights for policy 1, policy_version 58132 (0.0007) -[2023-10-15 04:35:41,287][88300] Updated weights for policy 1, policy_version 58142 (0.0007) -[2023-10-15 04:35:42,807][88298] Updated weights for policy 0, policy_version 57800 (0.0007) -[2023-10-15 04:35:43,179][88298] Updated weights for policy 0, policy_version 57810 (0.0007) -[2023-10-15 04:35:43,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 118718464. Throughput: 0: 1744.6, 1: 1738.5. Samples: 29694486. Policy #0 lag: (min: 31.0, avg: 31.2, max: 42.0) -[2023-10-15 04:35:43,534][87330] Avg episode reward: [(0, '22.920'), (1, '22.730')] -[2023-10-15 04:35:43,537][88298] Updated weights for policy 0, policy_version 57820 (0.0007) -[2023-10-15 04:35:45,052][88300] Updated weights for policy 1, policy_version 58152 (0.0009) -[2023-10-15 04:35:45,423][88300] Updated weights for policy 1, policy_version 58162 (0.0010) -[2023-10-15 04:35:45,801][88300] Updated weights for policy 1, policy_version 58172 (0.0010) -[2023-10-15 04:35:47,523][88298] Updated weights for policy 0, policy_version 57830 (0.0009) -[2023-10-15 04:35:47,900][88298] Updated weights for policy 0, policy_version 57840 (0.0010) -[2023-10-15 04:35:48,264][88298] Updated weights for policy 0, policy_version 57850 (0.0009) -[2023-10-15 04:35:48,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 118816768. Throughput: 0: 1735.8, 1: 1739.4. Samples: 29704222. Policy #0 lag: (min: 21.0, avg: 24.1, max: 53.0) -[2023-10-15 04:35:48,534][87330] Avg episode reward: [(0, '22.970'), (1, '22.720')] -[2023-10-15 04:35:49,726][88300] Updated weights for policy 1, policy_version 58182 (0.0009) -[2023-10-15 04:35:50,089][88300] Updated weights for policy 1, policy_version 58192 (0.0009) -[2023-10-15 04:35:50,459][88300] Updated weights for policy 1, policy_version 58202 (0.0009) -[2023-10-15 04:35:51,954][88298] Updated weights for policy 0, policy_version 57860 (0.0008) -[2023-10-15 04:35:52,328][88298] Updated weights for policy 0, policy_version 57870 (0.0009) -[2023-10-15 04:35:52,697][88298] Updated weights for policy 0, policy_version 57880 (0.0010) -[2023-10-15 04:35:53,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 118882304. Throughput: 0: 1750.6, 1: 1740.0. Samples: 29726076. Policy #0 lag: (min: 21.0, avg: 24.1, max: 53.0) -[2023-10-15 04:35:53,534][87330] Avg episode reward: [(0, '22.940'), (1, '22.730')] -[2023-10-15 04:35:54,381][88300] Updated weights for policy 1, policy_version 58212 (0.0010) -[2023-10-15 04:35:54,747][88300] Updated weights for policy 1, policy_version 58222 (0.0011) -[2023-10-15 04:35:55,111][88300] Updated weights for policy 1, policy_version 58232 (0.0010) -[2023-10-15 04:35:56,647][88298] Updated weights for policy 0, policy_version 57890 (0.0009) -[2023-10-15 04:35:57,018][88298] Updated weights for policy 0, policy_version 57900 (0.0007) -[2023-10-15 04:35:57,395][88298] Updated weights for policy 0, policy_version 57910 (0.0007) -[2023-10-15 04:35:57,766][88298] Updated weights for policy 0, policy_version 57920 (0.0010) -[2023-10-15 04:35:58,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 118947840. Throughput: 0: 1721.6, 1: 1767.6. Samples: 29746496. Policy #0 lag: (min: 21.0, avg: 24.1, max: 53.0) -[2023-10-15 04:35:58,534][87330] Avg episode reward: [(0, '22.970'), (1, '22.700')] -[2023-10-15 04:35:58,977][88300] Updated weights for policy 1, policy_version 58242 (0.0009) -[2023-10-15 04:35:59,350][88300] Updated weights for policy 1, policy_version 58252 (0.0009) -[2023-10-15 04:35:59,720][88300] Updated weights for policy 1, policy_version 58262 (0.0009) -[2023-10-15 04:36:00,092][88300] Updated weights for policy 1, policy_version 58272 (0.0008) -[2023-10-15 04:36:01,644][88298] Updated weights for policy 0, policy_version 57930 (0.0012) -[2023-10-15 04:36:02,009][88298] Updated weights for policy 0, policy_version 57940 (0.0008) -[2023-10-15 04:36:02,389][88298] Updated weights for policy 0, policy_version 57950 (0.0008) -[2023-10-15 04:36:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 119013376. Throughput: 0: 1760.2, 1: 1738.4. Samples: 29757522. Policy #0 lag: (min: 21.0, avg: 24.1, max: 53.0) -[2023-10-15 04:36:03,534][87330] Avg episode reward: [(0, '22.790'), (1, '22.660')] -[2023-10-15 04:36:03,862][88300] Updated weights for policy 1, policy_version 58282 (0.0008) -[2023-10-15 04:36:04,234][88300] Updated weights for policy 1, policy_version 58292 (0.0007) -[2023-10-15 04:36:04,613][88300] Updated weights for policy 1, policy_version 58302 (0.0007) -[2023-10-15 04:36:06,528][88298] Updated weights for policy 0, policy_version 57960 (0.0008) -[2023-10-15 04:36:06,897][88298] Updated weights for policy 0, policy_version 57970 (0.0007) -[2023-10-15 04:36:07,268][88298] Updated weights for policy 0, policy_version 57980 (0.0007) -[2023-10-15 04:36:08,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 119078912. Throughput: 0: 1745.1, 1: 1762.3. Samples: 29778448. Policy #0 lag: (min: 21.0, avg: 24.1, max: 53.0) -[2023-10-15 04:36:08,535][87330] Avg episode reward: [(0, '22.800'), (1, '22.850')] -[2023-10-15 04:36:08,541][88300] Updated weights for policy 1, policy_version 58312 (0.0008) -[2023-10-15 04:36:08,914][88300] Updated weights for policy 1, policy_version 58322 (0.0007) -[2023-10-15 04:36:09,273][88300] Updated weights for policy 1, policy_version 58332 (0.0007) -[2023-10-15 04:36:11,244][88298] Updated weights for policy 0, policy_version 57990 (0.0010) -[2023-10-15 04:36:11,620][88298] Updated weights for policy 0, policy_version 58000 (0.0007) -[2023-10-15 04:36:11,986][88298] Updated weights for policy 0, policy_version 58010 (0.0009) -[2023-10-15 04:36:13,306][88300] Updated weights for policy 1, policy_version 58342 (0.0008) -[2023-10-15 04:36:13,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 119144448. Throughput: 0: 1724.0, 1: 1764.7. Samples: 29798892. Policy #0 lag: (min: 21.0, avg: 24.1, max: 53.0) -[2023-10-15 04:36:13,535][87330] Avg episode reward: [(0, '22.760'), (1, '22.890')] -[2023-10-15 04:36:13,697][88300] Updated weights for policy 1, policy_version 58352 (0.0008) -[2023-10-15 04:36:14,064][88300] Updated weights for policy 1, policy_version 58362 (0.0009) -[2023-10-15 04:36:15,807][88298] Updated weights for policy 0, policy_version 58020 (0.0008) -[2023-10-15 04:36:16,179][88298] Updated weights for policy 0, policy_version 58030 (0.0007) -[2023-10-15 04:36:16,546][88298] Updated weights for policy 0, policy_version 58040 (0.0008) -[2023-10-15 04:36:17,967][88300] Updated weights for policy 1, policy_version 58372 (0.0008) -[2023-10-15 04:36:18,340][88300] Updated weights for policy 1, policy_version 58382 (0.0007) -[2023-10-15 04:36:18,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 119209984. Throughput: 0: 1753.3, 1: 1744.2. Samples: 29809680. Policy #0 lag: (min: 21.0, avg: 24.1, max: 53.0) -[2023-10-15 04:36:18,534][87330] Avg episode reward: [(0, '22.790'), (1, '22.820')] -[2023-10-15 04:36:18,706][88300] Updated weights for policy 1, policy_version 58392 (0.0008) -[2023-10-15 04:36:20,394][88298] Updated weights for policy 0, policy_version 58050 (0.0008) -[2023-10-15 04:36:20,778][88298] Updated weights for policy 0, policy_version 58060 (0.0010) -[2023-10-15 04:36:21,141][88298] Updated weights for policy 0, policy_version 58070 (0.0010) -[2023-10-15 04:36:21,520][88298] Updated weights for policy 0, policy_version 58080 (0.0011) -[2023-10-15 04:36:22,612][88300] Updated weights for policy 1, policy_version 58402 (0.0009) -[2023-10-15 04:36:22,978][88300] Updated weights for policy 1, policy_version 58412 (0.0008) -[2023-10-15 04:36:23,354][88300] Updated weights for policy 1, policy_version 58422 (0.0008) -[2023-10-15 04:36:23,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 119275520. Throughput: 0: 1726.8, 1: 1769.2. Samples: 29830084. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-15 04:36:23,534][87330] Avg episode reward: [(0, '22.830'), (1, '22.810')] -[2023-10-15 04:36:23,710][88300] Updated weights for policy 1, policy_version 58432 (0.0008) -[2023-10-15 04:36:25,577][88298] Updated weights for policy 0, policy_version 58090 (0.0007) -[2023-10-15 04:36:25,954][88298] Updated weights for policy 0, policy_version 58100 (0.0010) -[2023-10-15 04:36:26,332][88298] Updated weights for policy 0, policy_version 58110 (0.0008) -[2023-10-15 04:36:27,589][88300] Updated weights for policy 1, policy_version 58442 (0.0009) -[2023-10-15 04:36:27,956][88300] Updated weights for policy 1, policy_version 58452 (0.0011) -[2023-10-15 04:36:28,332][88300] Updated weights for policy 1, policy_version 58462 (0.0009) -[2023-10-15 04:36:28,534][87330] Fps is (10 sec: 16383.5, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 119373824. Throughput: 0: 1730.3, 1: 1739.0. Samples: 29850606. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-15 04:36:28,535][87330] Avg episode reward: [(0, '22.810'), (1, '22.800')] -[2023-10-15 04:36:30,135][88298] Updated weights for policy 0, policy_version 58120 (0.0010) -[2023-10-15 04:36:30,510][88298] Updated weights for policy 0, policy_version 58130 (0.0008) -[2023-10-15 04:36:30,892][88298] Updated weights for policy 0, policy_version 58140 (0.0009) -[2023-10-15 04:36:32,364][88300] Updated weights for policy 1, policy_version 58472 (0.0010) -[2023-10-15 04:36:32,731][88300] Updated weights for policy 1, policy_version 58482 (0.0010) -[2023-10-15 04:36:33,105][88300] Updated weights for policy 1, policy_version 58492 (0.0010) -[2023-10-15 04:36:33,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 119439360. Throughput: 0: 1729.2, 1: 1763.2. Samples: 29861384. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-15 04:36:33,535][87330] Avg episode reward: [(0, '22.850'), (1, '22.840')] -[2023-10-15 04:36:34,830][88298] Updated weights for policy 0, policy_version 58150 (0.0008) -[2023-10-15 04:36:35,202][88298] Updated weights for policy 0, policy_version 58160 (0.0008) -[2023-10-15 04:36:35,573][88298] Updated weights for policy 0, policy_version 58170 (0.0007) -[2023-10-15 04:36:37,005][88300] Updated weights for policy 1, policy_version 58502 (0.0009) -[2023-10-15 04:36:37,368][88300] Updated weights for policy 1, policy_version 58512 (0.0009) -[2023-10-15 04:36:37,739][88300] Updated weights for policy 1, policy_version 58522 (0.0010) -[2023-10-15 04:36:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 119504896. Throughput: 0: 1718.1, 1: 1747.7. Samples: 29882036. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-15 04:36:38,535][87330] Avg episode reward: [(0, '23.010'), (1, '22.700')] -[2023-10-15 04:36:39,411][88298] Updated weights for policy 0, policy_version 58180 (0.0008) -[2023-10-15 04:36:39,779][88298] Updated weights for policy 0, policy_version 58190 (0.0008) -[2023-10-15 04:36:40,150][88298] Updated weights for policy 0, policy_version 58200 (0.0007) -[2023-10-15 04:36:41,614][88300] Updated weights for policy 1, policy_version 58532 (0.0009) -[2023-10-15 04:36:41,989][88300] Updated weights for policy 1, policy_version 58542 (0.0008) -[2023-10-15 04:36:42,351][88300] Updated weights for policy 1, policy_version 58552 (0.0008) -[2023-10-15 04:36:43,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 119570432. Throughput: 0: 1748.9, 1: 1725.2. Samples: 29902832. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-15 04:36:43,534][87330] Avg episode reward: [(0, '22.830'), (1, '22.380')] -[2023-10-15 04:36:44,001][88298] Updated weights for policy 0, policy_version 58210 (0.0007) -[2023-10-15 04:36:44,386][88298] Updated weights for policy 0, policy_version 58220 (0.0007) -[2023-10-15 04:36:44,752][88298] Updated weights for policy 0, policy_version 58230 (0.0011) -[2023-10-15 04:36:45,124][88298] Updated weights for policy 0, policy_version 58240 (0.0010) -[2023-10-15 04:36:46,351][88300] Updated weights for policy 1, policy_version 58562 (0.0008) -[2023-10-15 04:36:46,719][88300] Updated weights for policy 1, policy_version 58572 (0.0008) -[2023-10-15 04:36:47,079][88300] Updated weights for policy 1, policy_version 58582 (0.0007) -[2023-10-15 04:36:47,453][88300] Updated weights for policy 1, policy_version 58592 (0.0008) -[2023-10-15 04:36:48,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 119635968. Throughput: 0: 1709.2, 1: 1753.6. Samples: 29913344. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-15 04:36:48,534][87330] Avg episode reward: [(0, '22.850'), (1, '22.390')] -[2023-10-15 04:36:49,050][88298] Updated weights for policy 0, policy_version 58250 (0.0007) -[2023-10-15 04:36:49,425][88298] Updated weights for policy 0, policy_version 58260 (0.0008) -[2023-10-15 04:36:49,784][88298] Updated weights for policy 0, policy_version 58270 (0.0009) -[2023-10-15 04:36:51,275][88300] Updated weights for policy 1, policy_version 58602 (0.0010) -[2023-10-15 04:36:51,647][88300] Updated weights for policy 1, policy_version 58612 (0.0008) -[2023-10-15 04:36:52,010][88300] Updated weights for policy 1, policy_version 58622 (0.0007) -[2023-10-15 04:36:53,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 119701504. Throughput: 0: 1737.4, 1: 1722.1. Samples: 29934126. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-15 04:36:53,534][87330] Avg episode reward: [(0, '22.660'), (1, '22.400')] -[2023-10-15 04:36:53,683][88298] Updated weights for policy 0, policy_version 58280 (0.0008) -[2023-10-15 04:36:54,056][88298] Updated weights for policy 0, policy_version 58290 (0.0010) -[2023-10-15 04:36:54,424][88298] Updated weights for policy 0, policy_version 58300 (0.0008) -[2023-10-15 04:36:55,943][88300] Updated weights for policy 1, policy_version 58632 (0.0007) -[2023-10-15 04:36:56,314][88300] Updated weights for policy 1, policy_version 58642 (0.0011) -[2023-10-15 04:36:56,685][88300] Updated weights for policy 1, policy_version 58652 (0.0011) -[2023-10-15 04:36:58,279][88298] Updated weights for policy 0, policy_version 58310 (0.0007) -[2023-10-15 04:36:58,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 119767040. Throughput: 0: 1757.9, 1: 1727.6. Samples: 29955740. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-15 04:36:58,534][87330] Avg episode reward: [(0, '22.680'), (1, '22.420')] -[2023-10-15 04:36:58,543][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000058656_60063744.pth... -[2023-10-15 04:36:58,581][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000057024_58392576.pth -[2023-10-15 04:36:58,652][88298] Updated weights for policy 0, policy_version 58320 (0.0009) -[2023-10-15 04:36:59,023][88298] Updated weights for policy 0, policy_version 58330 (0.0008) -[2023-10-15 04:36:59,239][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000058336_59736064.pth... -[2023-10-15 04:36:59,267][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000056704_58064896.pth -[2023-10-15 04:37:00,706][88300] Updated weights for policy 1, policy_version 58662 (0.0011) -[2023-10-15 04:37:01,097][88300] Updated weights for policy 1, policy_version 58672 (0.0008) -[2023-10-15 04:37:01,463][88300] Updated weights for policy 1, policy_version 58682 (0.0008) -[2023-10-15 04:37:02,921][88298] Updated weights for policy 0, policy_version 58340 (0.0007) -[2023-10-15 04:37:03,287][88298] Updated weights for policy 0, policy_version 58350 (0.0009) -[2023-10-15 04:37:03,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 119832576. Throughput: 0: 1726.6, 1: 1739.4. Samples: 29965648. Policy #0 lag: (min: 7.0, avg: 9.4, max: 39.0) -[2023-10-15 04:37:03,534][87330] Avg episode reward: [(0, '22.690'), (1, '22.450')] -[2023-10-15 04:37:03,664][88298] Updated weights for policy 0, policy_version 58360 (0.0008) -[2023-10-15 04:37:05,073][88300] Updated weights for policy 1, policy_version 58692 (0.0008) -[2023-10-15 04:37:05,452][88300] Updated weights for policy 1, policy_version 58702 (0.0007) -[2023-10-15 04:37:05,815][88300] Updated weights for policy 1, policy_version 58712 (0.0007) -[2023-10-15 04:37:07,643][88298] Updated weights for policy 0, policy_version 58370 (0.0009) -[2023-10-15 04:37:08,002][88298] Updated weights for policy 0, policy_version 58380 (0.0010) -[2023-10-15 04:37:08,370][88298] Updated weights for policy 0, policy_version 58390 (0.0010) -[2023-10-15 04:37:08,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 119898112. Throughput: 0: 1752.8, 1: 1727.7. Samples: 29986706. Policy #0 lag: (min: 7.0, avg: 9.4, max: 39.0) -[2023-10-15 04:37:08,534][87330] Avg episode reward: [(0, '22.690'), (1, '22.530')] -[2023-10-15 04:37:08,740][88298] Updated weights for policy 0, policy_version 58400 (0.0009) -[2023-10-15 04:37:09,602][88300] Updated weights for policy 1, policy_version 58722 (0.0009) -[2023-10-15 04:37:09,962][88300] Updated weights for policy 1, policy_version 58732 (0.0009) -[2023-10-15 04:37:10,335][88300] Updated weights for policy 1, policy_version 58742 (0.0007) -[2023-10-15 04:37:10,695][88300] Updated weights for policy 1, policy_version 58752 (0.0007) -[2023-10-15 04:37:12,633][88298] Updated weights for policy 0, policy_version 58410 (0.0007) -[2023-10-15 04:37:12,998][88298] Updated weights for policy 0, policy_version 58420 (0.0008) -[2023-10-15 04:37:13,367][88298] Updated weights for policy 0, policy_version 58430 (0.0008) -[2023-10-15 04:37:13,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 119996416. Throughput: 0: 1738.9, 1: 1756.9. Samples: 30007912. Policy #0 lag: (min: 7.0, avg: 9.4, max: 39.0) -[2023-10-15 04:37:13,534][87330] Avg episode reward: [(0, '22.650'), (1, '22.730')] -[2023-10-15 04:37:14,584][88300] Updated weights for policy 1, policy_version 58762 (0.0007) -[2023-10-15 04:37:14,949][88300] Updated weights for policy 1, policy_version 58772 (0.0011) -[2023-10-15 04:37:15,320][88300] Updated weights for policy 1, policy_version 58782 (0.0010) -[2023-10-15 04:37:17,363][88298] Updated weights for policy 0, policy_version 58440 (0.0008) -[2023-10-15 04:37:17,721][88298] Updated weights for policy 0, policy_version 58450 (0.0011) -[2023-10-15 04:37:18,099][88298] Updated weights for policy 0, policy_version 58460 (0.0007) -[2023-10-15 04:37:18,534][87330] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 120061952. Throughput: 0: 1743.9, 1: 1736.9. Samples: 30018022. Policy #0 lag: (min: 7.0, avg: 9.4, max: 39.0) -[2023-10-15 04:37:18,535][87330] Avg episode reward: [(0, '22.780'), (1, '22.860')] -[2023-10-15 04:37:19,056][88300] Updated weights for policy 1, policy_version 58792 (0.0007) -[2023-10-15 04:37:19,431][88300] Updated weights for policy 1, policy_version 58802 (0.0009) -[2023-10-15 04:37:19,794][88300] Updated weights for policy 1, policy_version 58812 (0.0009) -[2023-10-15 04:37:22,097][88298] Updated weights for policy 0, policy_version 58470 (0.0009) -[2023-10-15 04:37:22,466][88298] Updated weights for policy 0, policy_version 58480 (0.0008) -[2023-10-15 04:37:22,829][88298] Updated weights for policy 0, policy_version 58490 (0.0007) -[2023-10-15 04:37:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 120127488. Throughput: 0: 1749.6, 1: 1759.1. Samples: 30039924. Policy #0 lag: (min: 7.0, avg: 9.4, max: 39.0) -[2023-10-15 04:37:23,534][87330] Avg episode reward: [(0, '22.790'), (1, '22.900')] -[2023-10-15 04:37:23,586][88300] Updated weights for policy 1, policy_version 58822 (0.0009) -[2023-10-15 04:37:23,948][88300] Updated weights for policy 1, policy_version 58832 (0.0008) -[2023-10-15 04:37:24,323][88300] Updated weights for policy 1, policy_version 58842 (0.0007) -[2023-10-15 04:37:26,666][88298] Updated weights for policy 0, policy_version 58500 (0.0008) -[2023-10-15 04:37:27,045][88298] Updated weights for policy 0, policy_version 58510 (0.0008) -[2023-10-15 04:37:27,413][88298] Updated weights for policy 0, policy_version 58520 (0.0008) -[2023-10-15 04:37:28,119][88300] Updated weights for policy 1, policy_version 58852 (0.0007) -[2023-10-15 04:37:28,490][88300] Updated weights for policy 1, policy_version 58862 (0.0008) -[2023-10-15 04:37:28,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 120193024. Throughput: 0: 1716.0, 1: 1777.4. Samples: 30060038. Policy #0 lag: (min: 7.0, avg: 9.4, max: 39.0) -[2023-10-15 04:37:28,535][87330] Avg episode reward: [(0, '22.930'), (1, '22.700')] -[2023-10-15 04:37:28,848][88300] Updated weights for policy 1, policy_version 58872 (0.0010) -[2023-10-15 04:37:31,265][88298] Updated weights for policy 0, policy_version 58530 (0.0008) -[2023-10-15 04:37:31,640][88298] Updated weights for policy 0, policy_version 58540 (0.0009) -[2023-10-15 04:37:32,014][88298] Updated weights for policy 0, policy_version 58550 (0.0007) -[2023-10-15 04:37:32,375][88298] Updated weights for policy 0, policy_version 58560 (0.0007) -[2023-10-15 04:37:32,847][88300] Updated weights for policy 1, policy_version 58882 (0.0010) -[2023-10-15 04:37:33,203][88300] Updated weights for policy 1, policy_version 58892 (0.0009) -[2023-10-15 04:37:33,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 120258560. Throughput: 0: 1754.4, 1: 1753.3. Samples: 30071188. Policy #0 lag: (min: 7.0, avg: 9.4, max: 39.0) -[2023-10-15 04:37:33,534][87330] Avg episode reward: [(0, '22.910'), (1, '22.640')] -[2023-10-15 04:37:33,572][88300] Updated weights for policy 1, policy_version 58902 (0.0011) -[2023-10-15 04:37:33,937][88300] Updated weights for policy 1, policy_version 58912 (0.0010) -[2023-10-15 04:37:36,285][88298] Updated weights for policy 0, policy_version 58570 (0.0010) -[2023-10-15 04:37:36,662][88298] Updated weights for policy 0, policy_version 58580 (0.0010) -[2023-10-15 04:37:37,036][88298] Updated weights for policy 0, policy_version 58590 (0.0007) -[2023-10-15 04:37:37,804][88300] Updated weights for policy 1, policy_version 58922 (0.0007) -[2023-10-15 04:37:38,170][88300] Updated weights for policy 1, policy_version 58932 (0.0008) -[2023-10-15 04:37:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 120324096. Throughput: 0: 1726.0, 1: 1781.9. Samples: 30091982. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 04:37:38,535][87330] Avg episode reward: [(0, '22.910'), (1, '22.680')] -[2023-10-15 04:37:38,539][88300] Updated weights for policy 1, policy_version 58942 (0.0007) -[2023-10-15 04:37:40,972][88298] Updated weights for policy 0, policy_version 58600 (0.0009) -[2023-10-15 04:37:41,354][88298] Updated weights for policy 0, policy_version 58610 (0.0008) -[2023-10-15 04:37:41,718][88298] Updated weights for policy 0, policy_version 58620 (0.0007) -[2023-10-15 04:37:42,417][88300] Updated weights for policy 1, policy_version 58952 (0.0007) -[2023-10-15 04:37:42,780][88300] Updated weights for policy 1, policy_version 58962 (0.0009) -[2023-10-15 04:37:43,148][88300] Updated weights for policy 1, policy_version 58972 (0.0008) -[2023-10-15 04:37:43,534][87330] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 120422400. Throughput: 0: 1715.9, 1: 1755.8. Samples: 30111968. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 04:37:43,535][87330] Avg episode reward: [(0, '22.930'), (1, '22.500')] -[2023-10-15 04:37:45,576][88298] Updated weights for policy 0, policy_version 58630 (0.0007) -[2023-10-15 04:37:45,947][88298] Updated weights for policy 0, policy_version 58640 (0.0007) -[2023-10-15 04:37:46,313][88298] Updated weights for policy 0, policy_version 58650 (0.0008) -[2023-10-15 04:37:47,136][88300] Updated weights for policy 1, policy_version 58982 (0.0009) -[2023-10-15 04:37:47,520][88300] Updated weights for policy 1, policy_version 58992 (0.0007) -[2023-10-15 04:37:47,879][88300] Updated weights for policy 1, policy_version 59002 (0.0008) -[2023-10-15 04:37:48,534][87330] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 120487936. Throughput: 0: 1739.5, 1: 1769.6. Samples: 30123556. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 04:37:48,534][87330] Avg episode reward: [(0, '22.870'), (1, '22.530')] -[2023-10-15 04:37:50,120][88298] Updated weights for policy 0, policy_version 58660 (0.0008) -[2023-10-15 04:37:50,494][88298] Updated weights for policy 0, policy_version 58670 (0.0010) -[2023-10-15 04:37:50,862][88298] Updated weights for policy 0, policy_version 58680 (0.0010) -[2023-10-15 04:37:51,600][88300] Updated weights for policy 1, policy_version 59012 (0.0007) -[2023-10-15 04:37:51,959][88300] Updated weights for policy 1, policy_version 59022 (0.0007) -[2023-10-15 04:37:52,326][88300] Updated weights for policy 1, policy_version 59032 (0.0008) -[2023-10-15 04:37:53,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 120553472. Throughput: 0: 1722.6, 1: 1762.1. Samples: 30143516. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 04:37:53,535][87330] Avg episode reward: [(0, '22.850'), (1, '22.470')] -[2023-10-15 04:37:54,893][88298] Updated weights for policy 0, policy_version 58690 (0.0009) -[2023-10-15 04:37:55,275][88298] Updated weights for policy 0, policy_version 58700 (0.0009) -[2023-10-15 04:37:55,641][88298] Updated weights for policy 0, policy_version 58710 (0.0009) -[2023-10-15 04:37:55,911][88300] Updated weights for policy 1, policy_version 59042 (0.0009) -[2023-10-15 04:37:56,012][88298] Updated weights for policy 0, policy_version 58720 (0.0010) -[2023-10-15 04:37:56,273][88300] Updated weights for policy 1, policy_version 59052 (0.0011) -[2023-10-15 04:37:56,636][88300] Updated weights for policy 1, policy_version 59062 (0.0010) -[2023-10-15 04:37:57,002][88300] Updated weights for policy 1, policy_version 59072 (0.0007) -[2023-10-15 04:37:58,534][87330] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 120619008. Throughput: 0: 1735.4, 1: 1748.8. Samples: 30164700. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 04:37:58,535][87330] Avg episode reward: [(0, '22.860'), (1, '22.330')] -[2023-10-15 04:37:59,857][88298] Updated weights for policy 0, policy_version 58730 (0.0007) -[2023-10-15 04:38:00,228][88298] Updated weights for policy 0, policy_version 58740 (0.0008) -[2023-10-15 04:38:00,597][88298] Updated weights for policy 0, policy_version 58750 (0.0008) -[2023-10-15 04:38:00,880][88300] Updated weights for policy 1, policy_version 59082 (0.0008) -[2023-10-15 04:38:01,240][88300] Updated weights for policy 1, policy_version 59092 (0.0009) -[2023-10-15 04:38:01,606][88300] Updated weights for policy 1, policy_version 59102 (0.0008) -[2023-10-15 04:38:03,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 120684544. Throughput: 0: 1725.4, 1: 1761.2. Samples: 30174920. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 04:38:03,535][87330] Avg episode reward: [(0, '22.840'), (1, '22.090')] -[2023-10-15 04:38:04,404][88298] Updated weights for policy 0, policy_version 58760 (0.0008) -[2023-10-15 04:38:04,773][88298] Updated weights for policy 0, policy_version 58770 (0.0011) -[2023-10-15 04:38:05,150][88298] Updated weights for policy 0, policy_version 58780 (0.0010) -[2023-10-15 04:38:05,569][88300] Updated weights for policy 1, policy_version 59112 (0.0009) -[2023-10-15 04:38:05,946][88300] Updated weights for policy 1, policy_version 59122 (0.0009) -[2023-10-15 04:38:06,319][88300] Updated weights for policy 1, policy_version 59132 (0.0007) -[2023-10-15 04:38:08,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 120750080. Throughput: 0: 1735.7, 1: 1737.4. Samples: 30196212. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 04:38:08,535][87330] Avg episode reward: [(0, '22.850'), (1, '22.110')] -[2023-10-15 04:38:08,944][88298] Updated weights for policy 0, policy_version 58790 (0.0008) -[2023-10-15 04:38:09,318][88298] Updated weights for policy 0, policy_version 58800 (0.0007) -[2023-10-15 04:38:09,689][88298] Updated weights for policy 0, policy_version 58810 (0.0008) -[2023-10-15 04:38:10,218][88300] Updated weights for policy 1, policy_version 59142 (0.0008) -[2023-10-15 04:38:10,590][88300] Updated weights for policy 1, policy_version 59152 (0.0009) -[2023-10-15 04:38:10,966][88300] Updated weights for policy 1, policy_version 59162 (0.0007) -[2023-10-15 04:38:13,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 120815616. Throughput: 0: 1769.6, 1: 1738.5. Samples: 30217902. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 04:38:13,534][87330] Avg episode reward: [(0, '22.840'), (1, '22.210')] -[2023-10-15 04:38:13,613][88298] Updated weights for policy 0, policy_version 58820 (0.0008) -[2023-10-15 04:38:13,991][88298] Updated weights for policy 0, policy_version 58830 (0.0007) -[2023-10-15 04:38:14,354][88298] Updated weights for policy 0, policy_version 58840 (0.0007) -[2023-10-15 04:38:14,910][88300] Updated weights for policy 1, policy_version 59172 (0.0009) -[2023-10-15 04:38:15,275][88300] Updated weights for policy 1, policy_version 59182 (0.0009) -[2023-10-15 04:38:15,646][88300] Updated weights for policy 1, policy_version 59192 (0.0009) -[2023-10-15 04:38:18,027][88298] Updated weights for policy 0, policy_version 58850 (0.0009) -[2023-10-15 04:38:18,389][88298] Updated weights for policy 0, policy_version 58860 (0.0008) -[2023-10-15 04:38:18,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 120881152. Throughput: 0: 1738.5, 1: 1733.4. Samples: 30227426. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:38:18,534][87330] Avg episode reward: [(0, '22.890'), (1, '22.270')] -[2023-10-15 04:38:18,761][88298] Updated weights for policy 0, policy_version 58870 (0.0009) -[2023-10-15 04:38:19,123][88298] Updated weights for policy 0, policy_version 58880 (0.0007) -[2023-10-15 04:38:19,632][88300] Updated weights for policy 1, policy_version 59202 (0.0007) -[2023-10-15 04:38:20,004][88300] Updated weights for policy 1, policy_version 59212 (0.0008) -[2023-10-15 04:38:20,363][88300] Updated weights for policy 1, policy_version 59222 (0.0007) -[2023-10-15 04:38:20,733][88300] Updated weights for policy 1, policy_version 59232 (0.0008) -[2023-10-15 04:38:23,059][88298] Updated weights for policy 0, policy_version 58890 (0.0009) -[2023-10-15 04:38:23,429][88298] Updated weights for policy 0, policy_version 58900 (0.0009) -[2023-10-15 04:38:23,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 120946688. Throughput: 0: 1761.6, 1: 1732.9. Samples: 30249234. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:38:23,535][87330] Avg episode reward: [(0, '23.000'), (1, '22.160')] -[2023-10-15 04:38:23,798][88298] Updated weights for policy 0, policy_version 58910 (0.0007) -[2023-10-15 04:38:24,606][88300] Updated weights for policy 1, policy_version 59242 (0.0007) -[2023-10-15 04:38:24,970][88300] Updated weights for policy 1, policy_version 59252 (0.0007) -[2023-10-15 04:38:25,333][88300] Updated weights for policy 1, policy_version 59262 (0.0007) -[2023-10-15 04:38:27,856][88298] Updated weights for policy 0, policy_version 58920 (0.0007) -[2023-10-15 04:38:28,244][88298] Updated weights for policy 0, policy_version 58930 (0.0010) -[2023-10-15 04:38:28,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 121012224. Throughput: 0: 1762.6, 1: 1761.0. Samples: 30270532. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:38:28,535][87330] Avg episode reward: [(0, '22.970'), (1, '22.270')] -[2023-10-15 04:38:28,614][88298] Updated weights for policy 0, policy_version 58940 (0.0007) -[2023-10-15 04:38:29,251][88300] Updated weights for policy 1, policy_version 59272 (0.0009) -[2023-10-15 04:38:29,612][88300] Updated weights for policy 1, policy_version 59282 (0.0007) -[2023-10-15 04:38:29,990][88300] Updated weights for policy 1, policy_version 59292 (0.0008) -[2023-10-15 04:38:32,298][88298] Updated weights for policy 0, policy_version 58950 (0.0007) -[2023-10-15 04:38:32,663][88298] Updated weights for policy 0, policy_version 58960 (0.0007) -[2023-10-15 04:38:33,033][88298] Updated weights for policy 0, policy_version 58970 (0.0007) -[2023-10-15 04:38:33,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 121110528. Throughput: 0: 1748.3, 1: 1736.1. Samples: 30280356. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:38:33,535][87330] Avg episode reward: [(0, '22.860'), (1, '22.370')] -[2023-10-15 04:38:33,985][88300] Updated weights for policy 1, policy_version 59302 (0.0009) -[2023-10-15 04:38:34,359][88300] Updated weights for policy 1, policy_version 59312 (0.0008) -[2023-10-15 04:38:34,729][88300] Updated weights for policy 1, policy_version 59322 (0.0008) -[2023-10-15 04:38:37,088][88298] Updated weights for policy 0, policy_version 58980 (0.0007) -[2023-10-15 04:38:37,451][88298] Updated weights for policy 0, policy_version 58990 (0.0008) -[2023-10-15 04:38:37,821][88298] Updated weights for policy 0, policy_version 59000 (0.0009) -[2023-10-15 04:38:38,534][87330] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 121176064. Throughput: 0: 1765.3, 1: 1750.0. Samples: 30301702. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:38:38,534][87330] Avg episode reward: [(0, '22.840'), (1, '22.330')] -[2023-10-15 04:38:38,551][88300] Updated weights for policy 1, policy_version 59332 (0.0008) -[2023-10-15 04:38:38,923][88300] Updated weights for policy 1, policy_version 59342 (0.0007) -[2023-10-15 04:38:39,280][88300] Updated weights for policy 1, policy_version 59352 (0.0008) -[2023-10-15 04:38:41,565][88298] Updated weights for policy 0, policy_version 59010 (0.0009) -[2023-10-15 04:38:41,931][88298] Updated weights for policy 0, policy_version 59020 (0.0011) -[2023-10-15 04:38:42,309][88298] Updated weights for policy 0, policy_version 59030 (0.0009) -[2023-10-15 04:38:42,670][88298] Updated weights for policy 0, policy_version 59040 (0.0008) -[2023-10-15 04:38:43,318][88300] Updated weights for policy 1, policy_version 59362 (0.0008) -[2023-10-15 04:38:43,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13995.8). Total num frames: 121241600. Throughput: 0: 1738.6, 1: 1757.5. Samples: 30322024. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:38:43,534][87330] Avg episode reward: [(0, '22.820'), (1, '22.190')] -[2023-10-15 04:38:43,689][88300] Updated weights for policy 1, policy_version 59372 (0.0008) -[2023-10-15 04:38:44,060][88300] Updated weights for policy 1, policy_version 59382 (0.0008) -[2023-10-15 04:38:44,429][88300] Updated weights for policy 1, policy_version 59392 (0.0008) -[2023-10-15 04:38:46,640][88298] Updated weights for policy 0, policy_version 59050 (0.0009) -[2023-10-15 04:38:47,001][88298] Updated weights for policy 0, policy_version 59060 (0.0009) -[2023-10-15 04:38:47,372][88298] Updated weights for policy 0, policy_version 59070 (0.0010) -[2023-10-15 04:38:48,359][88300] Updated weights for policy 1, policy_version 59402 (0.0008) -[2023-10-15 04:38:48,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 121307136. Throughput: 0: 1768.6, 1: 1739.9. Samples: 30332802. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:38:48,534][87330] Avg episode reward: [(0, '22.670'), (1, '22.190')] -[2023-10-15 04:38:48,721][88300] Updated weights for policy 1, policy_version 59412 (0.0008) -[2023-10-15 04:38:49,085][88300] Updated weights for policy 1, policy_version 59422 (0.0008) -[2023-10-15 04:38:51,249][88298] Updated weights for policy 0, policy_version 59080 (0.0008) -[2023-10-15 04:38:51,609][88298] Updated weights for policy 0, policy_version 59090 (0.0008) -[2023-10-15 04:38:51,983][88298] Updated weights for policy 0, policy_version 59100 (0.0008) -[2023-10-15 04:38:52,951][88300] Updated weights for policy 1, policy_version 59432 (0.0007) -[2023-10-15 04:38:53,322][88300] Updated weights for policy 1, policy_version 59442 (0.0009) -[2023-10-15 04:38:53,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 121372672. Throughput: 0: 1738.4, 1: 1757.3. Samples: 30353520. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:38:53,534][87330] Avg episode reward: [(0, '22.660'), (1, '22.220')] -[2023-10-15 04:38:53,695][88300] Updated weights for policy 1, policy_version 59452 (0.0010) -[2023-10-15 04:38:56,017][88298] Updated weights for policy 0, policy_version 59110 (0.0009) -[2023-10-15 04:38:56,387][88298] Updated weights for policy 0, policy_version 59120 (0.0007) -[2023-10-15 04:38:56,757][88298] Updated weights for policy 0, policy_version 59130 (0.0008) -[2023-10-15 04:38:57,619][88300] Updated weights for policy 1, policy_version 59462 (0.0010) -[2023-10-15 04:38:57,984][88300] Updated weights for policy 1, policy_version 59472 (0.0011) -[2023-10-15 04:38:58,342][88300] Updated weights for policy 1, policy_version 59482 (0.0010) -[2023-10-15 04:38:58,534][87330] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 121438208. Throughput: 0: 1723.8, 1: 1738.9. Samples: 30373722. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:38:58,535][87330] Avg episode reward: [(0, '22.630'), (1, '22.330')] -[2023-10-15 04:38:58,548][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000059136_60555264.pth... -[2023-10-15 04:38:58,555][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000059488_60915712.pth... -[2023-10-15 04:38:58,584][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000057856_59244544.pth -[2023-10-15 04:38:58,586][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000057504_58884096.pth -[2023-10-15 04:39:00,651][88298] Updated weights for policy 0, policy_version 59140 (0.0007) -[2023-10-15 04:39:01,012][88298] Updated weights for policy 0, policy_version 59150 (0.0008) -[2023-10-15 04:39:01,383][88298] Updated weights for policy 0, policy_version 59160 (0.0008) -[2023-10-15 04:39:02,293][88300] Updated weights for policy 1, policy_version 59492 (0.0009) -[2023-10-15 04:39:02,659][88300] Updated weights for policy 1, policy_version 59502 (0.0011) -[2023-10-15 04:39:03,032][88300] Updated weights for policy 1, policy_version 59512 (0.0010) -[2023-10-15 04:39:03,534][87330] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 121536512. Throughput: 0: 1741.8, 1: 1757.6. Samples: 30384898. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:39:03,535][87330] Avg episode reward: [(0, '22.750'), (1, '22.440')] -[2023-10-15 04:39:05,140][88298] Updated weights for policy 0, policy_version 59170 (0.0007) -[2023-10-15 04:39:05,522][88298] Updated weights for policy 0, policy_version 59180 (0.0008) -[2023-10-15 04:39:05,894][88298] Updated weights for policy 0, policy_version 59190 (0.0007) -[2023-10-15 04:39:06,271][88298] Updated weights for policy 0, policy_version 59200 (0.0009) -[2023-10-15 04:39:06,855][88300] Updated weights for policy 1, policy_version 59522 (0.0009) -[2023-10-15 04:39:07,218][88300] Updated weights for policy 1, policy_version 59532 (0.0007) -[2023-10-15 04:39:07,584][88300] Updated weights for policy 1, policy_version 59542 (0.0008) -[2023-10-15 04:39:07,957][88300] Updated weights for policy 1, policy_version 59552 (0.0008) -[2023-10-15 04:39:08,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 121602048. Throughput: 0: 1718.7, 1: 1743.0. Samples: 30405010. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:39:08,535][87330] Avg episode reward: [(0, '22.800'), (1, '22.540')] -[2023-10-15 04:39:10,095][88298] Updated weights for policy 0, policy_version 59210 (0.0009) -[2023-10-15 04:39:10,460][88298] Updated weights for policy 0, policy_version 59220 (0.0009) -[2023-10-15 04:39:10,831][88298] Updated weights for policy 0, policy_version 59230 (0.0008) -[2023-10-15 04:39:11,825][88300] Updated weights for policy 1, policy_version 59562 (0.0007) -[2023-10-15 04:39:12,184][88300] Updated weights for policy 1, policy_version 59572 (0.0008) -[2023-10-15 04:39:12,555][88300] Updated weights for policy 1, policy_version 59582 (0.0007) -[2023-10-15 04:39:13,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 121667584. Throughput: 0: 1731.0, 1: 1723.3. Samples: 30425976. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:39:13,534][87330] Avg episode reward: [(0, '22.820'), (1, '22.850')] -[2023-10-15 04:39:14,913][88298] Updated weights for policy 0, policy_version 59240 (0.0009) -[2023-10-15 04:39:15,290][88298] Updated weights for policy 0, policy_version 59250 (0.0009) -[2023-10-15 04:39:15,663][88298] Updated weights for policy 0, policy_version 59260 (0.0007) -[2023-10-15 04:39:16,263][88300] Updated weights for policy 1, policy_version 59592 (0.0008) -[2023-10-15 04:39:16,636][88300] Updated weights for policy 1, policy_version 59602 (0.0008) -[2023-10-15 04:39:16,998][88300] Updated weights for policy 1, policy_version 59612 (0.0008) -[2023-10-15 04:39:18,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 121733120. Throughput: 0: 1720.5, 1: 1750.1. Samples: 30436534. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:39:18,535][87330] Avg episode reward: [(0, '22.940'), (1, '22.840')] -[2023-10-15 04:39:19,700][88298] Updated weights for policy 0, policy_version 59270 (0.0008) -[2023-10-15 04:39:20,066][88298] Updated weights for policy 0, policy_version 59280 (0.0009) -[2023-10-15 04:39:20,439][88298] Updated weights for policy 0, policy_version 59290 (0.0009) -[2023-10-15 04:39:20,974][88300] Updated weights for policy 1, policy_version 59622 (0.0007) -[2023-10-15 04:39:21,365][88300] Updated weights for policy 1, policy_version 59632 (0.0008) -[2023-10-15 04:39:21,731][88300] Updated weights for policy 1, policy_version 59642 (0.0012) -[2023-10-15 04:39:23,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 121798656. Throughput: 0: 1714.9, 1: 1727.3. Samples: 30456600. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:39:23,535][87330] Avg episode reward: [(0, '22.950'), (1, '22.720')] -[2023-10-15 04:39:24,407][88298] Updated weights for policy 0, policy_version 59300 (0.0008) -[2023-10-15 04:39:24,781][88298] Updated weights for policy 0, policy_version 59310 (0.0007) -[2023-10-15 04:39:25,154][88298] Updated weights for policy 0, policy_version 59320 (0.0007) -[2023-10-15 04:39:25,442][88300] Updated weights for policy 1, policy_version 59652 (0.0008) -[2023-10-15 04:39:25,800][88300] Updated weights for policy 1, policy_version 59662 (0.0008) -[2023-10-15 04:39:26,165][88300] Updated weights for policy 1, policy_version 59672 (0.0010) -[2023-10-15 04:39:28,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 121864192. Throughput: 0: 1746.2, 1: 1731.1. Samples: 30478504. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:39:28,535][87330] Avg episode reward: [(0, '22.990'), (1, '22.740')] -[2023-10-15 04:39:29,005][88298] Updated weights for policy 0, policy_version 59330 (0.0007) -[2023-10-15 04:39:29,375][88298] Updated weights for policy 0, policy_version 59340 (0.0009) -[2023-10-15 04:39:29,739][88298] Updated weights for policy 0, policy_version 59350 (0.0011) -[2023-10-15 04:39:30,103][88298] Updated weights for policy 0, policy_version 59360 (0.0009) -[2023-10-15 04:39:30,182][88300] Updated weights for policy 1, policy_version 59682 (0.0009) -[2023-10-15 04:39:30,552][88300] Updated weights for policy 1, policy_version 59692 (0.0007) -[2023-10-15 04:39:30,912][88300] Updated weights for policy 1, policy_version 59702 (0.0009) -[2023-10-15 04:39:31,282][88300] Updated weights for policy 1, policy_version 59712 (0.0010) -[2023-10-15 04:39:33,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 121929728. Throughput: 0: 1714.4, 1: 1737.6. Samples: 30488142. Policy #0 lag: (min: 5.0, avg: 12.6, max: 37.0) -[2023-10-15 04:39:33,534][87330] Avg episode reward: [(0, '22.990'), (1, '22.700')] -[2023-10-15 04:39:33,953][88298] Updated weights for policy 0, policy_version 59370 (0.0010) -[2023-10-15 04:39:34,313][88298] Updated weights for policy 0, policy_version 59380 (0.0008) -[2023-10-15 04:39:34,690][88298] Updated weights for policy 0, policy_version 59390 (0.0010) -[2023-10-15 04:39:35,103][88300] Updated weights for policy 1, policy_version 59722 (0.0009) -[2023-10-15 04:39:35,461][88300] Updated weights for policy 1, policy_version 59732 (0.0008) -[2023-10-15 04:39:35,832][88300] Updated weights for policy 1, policy_version 59742 (0.0009) -[2023-10-15 04:39:38,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 121995264. Throughput: 0: 1741.0, 1: 1733.3. Samples: 30509866. Policy #0 lag: (min: 5.0, avg: 12.6, max: 37.0) -[2023-10-15 04:39:38,535][87330] Avg episode reward: [(0, '22.980'), (1, '22.660')] -[2023-10-15 04:39:38,635][88298] Updated weights for policy 0, policy_version 59400 (0.0007) -[2023-10-15 04:39:39,002][88298] Updated weights for policy 0, policy_version 59410 (0.0008) -[2023-10-15 04:39:39,384][88298] Updated weights for policy 0, policy_version 59420 (0.0008) -[2023-10-15 04:39:39,664][88300] Updated weights for policy 1, policy_version 59752 (0.0009) -[2023-10-15 04:39:40,029][88300] Updated weights for policy 1, policy_version 59762 (0.0008) -[2023-10-15 04:39:40,396][88300] Updated weights for policy 1, policy_version 59772 (0.0007) -[2023-10-15 04:39:43,230][88298] Updated weights for policy 0, policy_version 59430 (0.0007) -[2023-10-15 04:39:43,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 122060800. Throughput: 0: 1752.0, 1: 1755.7. Samples: 30531568. Policy #0 lag: (min: 5.0, avg: 12.6, max: 37.0) -[2023-10-15 04:39:43,535][87330] Avg episode reward: [(0, '22.900'), (1, '22.650')] -[2023-10-15 04:39:43,588][88298] Updated weights for policy 0, policy_version 59440 (0.0007) -[2023-10-15 04:39:43,958][88298] Updated weights for policy 0, policy_version 59450 (0.0007) -[2023-10-15 04:39:44,304][88300] Updated weights for policy 1, policy_version 59782 (0.0007) -[2023-10-15 04:39:44,666][88300] Updated weights for policy 1, policy_version 59792 (0.0007) -[2023-10-15 04:39:45,035][88300] Updated weights for policy 1, policy_version 59802 (0.0009) -[2023-10-15 04:39:47,780][88298] Updated weights for policy 0, policy_version 59460 (0.0007) -[2023-10-15 04:39:48,146][88298] Updated weights for policy 0, policy_version 59470 (0.0008) -[2023-10-15 04:39:48,512][88298] Updated weights for policy 0, policy_version 59480 (0.0009) -[2023-10-15 04:39:48,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 122126336. Throughput: 0: 1732.5, 1: 1737.9. Samples: 30541068. Policy #0 lag: (min: 5.0, avg: 12.6, max: 37.0) -[2023-10-15 04:39:48,534][87330] Avg episode reward: [(0, '22.910'), (1, '22.640')] -[2023-10-15 04:39:49,026][88300] Updated weights for policy 1, policy_version 59812 (0.0007) -[2023-10-15 04:39:49,391][88300] Updated weights for policy 1, policy_version 59822 (0.0008) -[2023-10-15 04:39:49,762][88300] Updated weights for policy 1, policy_version 59832 (0.0008) -[2023-10-15 04:39:52,494][88298] Updated weights for policy 0, policy_version 59490 (0.0010) -[2023-10-15 04:39:52,865][88298] Updated weights for policy 0, policy_version 59500 (0.0008) -[2023-10-15 04:39:53,244][88298] Updated weights for policy 0, policy_version 59510 (0.0007) -[2023-10-15 04:39:53,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 122191872. Throughput: 0: 1753.3, 1: 1748.5. Samples: 30562592. Policy #0 lag: (min: 5.0, avg: 12.6, max: 37.0) -[2023-10-15 04:39:53,535][87330] Avg episode reward: [(0, '22.950'), (1, '22.760')] -[2023-10-15 04:39:53,577][88300] Updated weights for policy 1, policy_version 59842 (0.0009) -[2023-10-15 04:39:53,606][88298] Updated weights for policy 0, policy_version 59520 (0.0007) -[2023-10-15 04:39:53,943][88300] Updated weights for policy 1, policy_version 59852 (0.0007) -[2023-10-15 04:39:54,305][88300] Updated weights for policy 1, policy_version 59862 (0.0009) -[2023-10-15 04:39:54,674][88300] Updated weights for policy 1, policy_version 59872 (0.0011) -[2023-10-15 04:39:57,463][88298] Updated weights for policy 0, policy_version 59530 (0.0008) -[2023-10-15 04:39:57,835][88298] Updated weights for policy 0, policy_version 59540 (0.0009) -[2023-10-15 04:39:58,211][88298] Updated weights for policy 0, policy_version 59550 (0.0007) -[2023-10-15 04:39:58,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 122290176. Throughput: 0: 1733.5, 1: 1767.9. Samples: 30583540. Policy #0 lag: (min: 5.0, avg: 12.6, max: 37.0) -[2023-10-15 04:39:58,535][87330] Avg episode reward: [(0, '22.960'), (1, '22.760')] -[2023-10-15 04:39:58,607][88300] Updated weights for policy 1, policy_version 59882 (0.0010) -[2023-10-15 04:39:58,986][88300] Updated weights for policy 1, policy_version 59892 (0.0007) -[2023-10-15 04:39:59,353][88300] Updated weights for policy 1, policy_version 59902 (0.0007) -[2023-10-15 04:40:02,317][88298] Updated weights for policy 0, policy_version 59560 (0.0011) -[2023-10-15 04:40:02,697][88298] Updated weights for policy 0, policy_version 59570 (0.0007) -[2023-10-15 04:40:02,936][88300] Updated weights for policy 1, policy_version 59912 (0.0007) -[2023-10-15 04:40:03,071][88298] Updated weights for policy 0, policy_version 59580 (0.0008) -[2023-10-15 04:40:03,314][88300] Updated weights for policy 1, policy_version 59922 (0.0008) -[2023-10-15 04:40:03,534][87330] Fps is (10 sec: 16384.2, 60 sec: 13653.4, 300 sec: 13995.8). Total num frames: 122355712. Throughput: 0: 1751.8, 1: 1741.7. Samples: 30593744. Policy #0 lag: (min: 5.0, avg: 12.6, max: 37.0) -[2023-10-15 04:40:03,534][87330] Avg episode reward: [(0, '22.920'), (1, '22.740')] -[2023-10-15 04:40:03,668][88300] Updated weights for policy 1, policy_version 59932 (0.0011) -[2023-10-15 04:40:06,869][88298] Updated weights for policy 0, policy_version 59590 (0.0010) -[2023-10-15 04:40:07,236][88298] Updated weights for policy 0, policy_version 59600 (0.0008) -[2023-10-15 04:40:07,600][88298] Updated weights for policy 0, policy_version 59610 (0.0008) -[2023-10-15 04:40:07,785][88300] Updated weights for policy 1, policy_version 59942 (0.0010) -[2023-10-15 04:40:08,161][88300] Updated weights for policy 1, policy_version 59952 (0.0010) -[2023-10-15 04:40:08,527][88300] Updated weights for policy 1, policy_version 59962 (0.0010) -[2023-10-15 04:40:08,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 122421248. Throughput: 0: 1745.2, 1: 1768.0. Samples: 30614694. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:40:08,535][87330] Avg episode reward: [(0, '22.940'), (1, '22.850')] -[2023-10-15 04:40:11,520][88298] Updated weights for policy 0, policy_version 59620 (0.0008) -[2023-10-15 04:40:11,893][88298] Updated weights for policy 0, policy_version 59630 (0.0009) -[2023-10-15 04:40:12,256][88298] Updated weights for policy 0, policy_version 59640 (0.0008) -[2023-10-15 04:40:12,470][88300] Updated weights for policy 1, policy_version 59972 (0.0009) -[2023-10-15 04:40:12,837][88300] Updated weights for policy 1, policy_version 59982 (0.0008) -[2023-10-15 04:40:13,207][88300] Updated weights for policy 1, policy_version 59992 (0.0008) -[2023-10-15 04:40:13,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 122519552. Throughput: 0: 1718.9, 1: 1736.7. Samples: 30634006. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:40:13,534][87330] Avg episode reward: [(0, '22.940'), (1, '22.770')] -[2023-10-15 04:40:16,164][88298] Updated weights for policy 0, policy_version 59650 (0.0009) -[2023-10-15 04:40:16,526][88298] Updated weights for policy 0, policy_version 59660 (0.0010) -[2023-10-15 04:40:16,894][88298] Updated weights for policy 0, policy_version 59670 (0.0008) -[2023-10-15 04:40:17,115][88300] Updated weights for policy 1, policy_version 60002 (0.0008) -[2023-10-15 04:40:17,265][88298] Updated weights for policy 0, policy_version 59680 (0.0007) -[2023-10-15 04:40:17,477][88300] Updated weights for policy 1, policy_version 60012 (0.0007) -[2023-10-15 04:40:17,845][88300] Updated weights for policy 1, policy_version 60022 (0.0008) -[2023-10-15 04:40:18,218][88300] Updated weights for policy 1, policy_version 60032 (0.0007) -[2023-10-15 04:40:18,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 122585088. Throughput: 0: 1750.0, 1: 1755.0. Samples: 30645868. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:40:18,535][87330] Avg episode reward: [(0, '22.990'), (1, '22.730')] -[2023-10-15 04:40:21,253][88298] Updated weights for policy 0, policy_version 59690 (0.0008) -[2023-10-15 04:40:21,621][88298] Updated weights for policy 0, policy_version 59700 (0.0009) -[2023-10-15 04:40:21,994][88298] Updated weights for policy 0, policy_version 59710 (0.0007) -[2023-10-15 04:40:22,068][88300] Updated weights for policy 1, policy_version 60042 (0.0009) -[2023-10-15 04:40:22,435][88300] Updated weights for policy 1, policy_version 60052 (0.0008) -[2023-10-15 04:40:22,801][88300] Updated weights for policy 1, policy_version 60062 (0.0008) -[2023-10-15 04:40:23,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 122650624. Throughput: 0: 1723.2, 1: 1748.8. Samples: 30666104. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:40:23,535][87330] Avg episode reward: [(0, '22.990'), (1, '22.460')] -[2023-10-15 04:40:25,814][88298] Updated weights for policy 0, policy_version 59720 (0.0007) -[2023-10-15 04:40:26,190][88298] Updated weights for policy 0, policy_version 59730 (0.0007) -[2023-10-15 04:40:26,559][88298] Updated weights for policy 0, policy_version 59740 (0.0008) -[2023-10-15 04:40:26,718][88300] Updated weights for policy 1, policy_version 60072 (0.0007) -[2023-10-15 04:40:27,085][88300] Updated weights for policy 1, policy_version 60082 (0.0008) -[2023-10-15 04:40:27,451][88300] Updated weights for policy 1, policy_version 60092 (0.0008) -[2023-10-15 04:40:28,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 122716160. Throughput: 0: 1714.6, 1: 1732.0. Samples: 30686668. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:40:28,535][87330] Avg episode reward: [(0, '22.790'), (1, '22.410')] -[2023-10-15 04:40:30,636][88298] Updated weights for policy 0, policy_version 59750 (0.0010) -[2023-10-15 04:40:31,011][88298] Updated weights for policy 0, policy_version 59760 (0.0010) -[2023-10-15 04:40:31,280][88300] Updated weights for policy 1, policy_version 60102 (0.0009) -[2023-10-15 04:40:31,369][88298] Updated weights for policy 0, policy_version 59770 (0.0008) -[2023-10-15 04:40:31,646][88300] Updated weights for policy 1, policy_version 60112 (0.0009) -[2023-10-15 04:40:32,022][88300] Updated weights for policy 1, policy_version 60122 (0.0009) -[2023-10-15 04:40:33,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 122781696. Throughput: 0: 1728.1, 1: 1764.2. Samples: 30698224. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:40:33,534][87330] Avg episode reward: [(0, '22.810'), (1, '22.390')] -[2023-10-15 04:40:35,257][88298] Updated weights for policy 0, policy_version 59780 (0.0007) -[2023-10-15 04:40:35,629][88298] Updated weights for policy 0, policy_version 59790 (0.0008) -[2023-10-15 04:40:35,872][88300] Updated weights for policy 1, policy_version 60132 (0.0009) -[2023-10-15 04:40:35,992][88298] Updated weights for policy 0, policy_version 59800 (0.0008) -[2023-10-15 04:40:36,235][88300] Updated weights for policy 1, policy_version 60142 (0.0010) -[2023-10-15 04:40:36,598][88300] Updated weights for policy 1, policy_version 60152 (0.0009) -[2023-10-15 04:40:38,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 122847232. Throughput: 0: 1706.5, 1: 1741.3. Samples: 30717746. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:40:38,534][87330] Avg episode reward: [(0, '22.660'), (1, '22.420')] -[2023-10-15 04:40:40,055][88298] Updated weights for policy 0, policy_version 59810 (0.0009) -[2023-10-15 04:40:40,418][88298] Updated weights for policy 0, policy_version 59820 (0.0008) -[2023-10-15 04:40:40,461][88300] Updated weights for policy 1, policy_version 60162 (0.0008) -[2023-10-15 04:40:40,792][88298] Updated weights for policy 0, policy_version 59830 (0.0007) -[2023-10-15 04:40:40,827][88300] Updated weights for policy 1, policy_version 60172 (0.0009) -[2023-10-15 04:40:41,163][88298] Updated weights for policy 0, policy_version 59840 (0.0009) -[2023-10-15 04:40:41,181][88300] Updated weights for policy 1, policy_version 60182 (0.0008) -[2023-10-15 04:40:41,556][88300] Updated weights for policy 1, policy_version 60192 (0.0008) -[2023-10-15 04:40:43,534][87330] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 122912768. Throughput: 0: 1719.6, 1: 1739.2. Samples: 30739184. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:40:43,535][87330] Avg episode reward: [(0, '22.610'), (1, '22.330')] -[2023-10-15 04:40:45,153][88298] Updated weights for policy 0, policy_version 59850 (0.0008) -[2023-10-15 04:40:45,494][88300] Updated weights for policy 1, policy_version 60202 (0.0007) -[2023-10-15 04:40:45,525][88298] Updated weights for policy 0, policy_version 59860 (0.0009) -[2023-10-15 04:40:45,852][88300] Updated weights for policy 1, policy_version 60212 (0.0009) -[2023-10-15 04:40:45,895][88298] Updated weights for policy 0, policy_version 59870 (0.0009) -[2023-10-15 04:40:46,231][88300] Updated weights for policy 1, policy_version 60222 (0.0010) -[2023-10-15 04:40:48,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 122978304. Throughput: 0: 1707.6, 1: 1742.0. Samples: 30748980. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:40:48,534][87330] Avg episode reward: [(0, '22.620'), (1, '22.270')] -[2023-10-15 04:40:49,853][88298] Updated weights for policy 0, policy_version 59880 (0.0009) -[2023-10-15 04:40:50,232][88300] Updated weights for policy 1, policy_version 60232 (0.0009) -[2023-10-15 04:40:50,234][88298] Updated weights for policy 0, policy_version 59890 (0.0007) -[2023-10-15 04:40:50,595][88298] Updated weights for policy 0, policy_version 59900 (0.0008) -[2023-10-15 04:40:50,603][88300] Updated weights for policy 1, policy_version 60242 (0.0009) -[2023-10-15 04:40:50,971][88300] Updated weights for policy 1, policy_version 60252 (0.0007) -[2023-10-15 04:40:53,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 123043840. Throughput: 0: 1712.7, 1: 1736.7. Samples: 30769916. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:40:53,535][87330] Avg episode reward: [(0, '22.360'), (1, '22.550')] -[2023-10-15 04:40:54,627][88298] Updated weights for policy 0, policy_version 59910 (0.0009) -[2023-10-15 04:40:54,748][88300] Updated weights for policy 1, policy_version 60262 (0.0009) -[2023-10-15 04:40:54,990][88298] Updated weights for policy 0, policy_version 59920 (0.0009) -[2023-10-15 04:40:55,130][88300] Updated weights for policy 1, policy_version 60272 (0.0008) -[2023-10-15 04:40:55,368][88298] Updated weights for policy 0, policy_version 59930 (0.0008) -[2023-10-15 04:40:55,498][88300] Updated weights for policy 1, policy_version 60282 (0.0007) -[2023-10-15 04:40:58,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 123109376. Throughput: 0: 1735.6, 1: 1761.6. Samples: 30791380. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:40:58,535][87330] Avg episode reward: [(0, '22.550'), (1, '22.590')] -[2023-10-15 04:40:58,544][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000060288_61734912.pth... -[2023-10-15 04:40:58,544][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000059936_61374464.pth... -[2023-10-15 04:40:58,574][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000058656_60063744.pth -[2023-10-15 04:40:58,580][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000058336_59736064.pth -[2023-10-15 04:40:59,248][88298] Updated weights for policy 0, policy_version 59940 (0.0008) -[2023-10-15 04:40:59,415][88300] Updated weights for policy 1, policy_version 60292 (0.0007) -[2023-10-15 04:40:59,610][88298] Updated weights for policy 0, policy_version 59950 (0.0007) -[2023-10-15 04:40:59,791][88300] Updated weights for policy 1, policy_version 60302 (0.0009) -[2023-10-15 04:40:59,982][88298] Updated weights for policy 0, policy_version 59960 (0.0008) -[2023-10-15 04:41:00,153][88300] Updated weights for policy 1, policy_version 60312 (0.0008) -[2023-10-15 04:41:03,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 123174912. Throughput: 0: 1706.8, 1: 1739.1. Samples: 30800932. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:41:03,534][87330] Avg episode reward: [(0, '22.560'), (1, '22.540')] -[2023-10-15 04:41:03,848][88298] Updated weights for policy 0, policy_version 59970 (0.0009) -[2023-10-15 04:41:03,956][88300] Updated weights for policy 1, policy_version 60322 (0.0009) -[2023-10-15 04:41:04,230][88298] Updated weights for policy 0, policy_version 59980 (0.0007) -[2023-10-15 04:41:04,318][88300] Updated weights for policy 1, policy_version 60332 (0.0007) -[2023-10-15 04:41:04,597][88298] Updated weights for policy 0, policy_version 59990 (0.0007) -[2023-10-15 04:41:04,688][88300] Updated weights for policy 1, policy_version 60342 (0.0007) -[2023-10-15 04:41:04,958][88298] Updated weights for policy 0, policy_version 60000 (0.0011) -[2023-10-15 04:41:05,055][88300] Updated weights for policy 1, policy_version 60352 (0.0009) -[2023-10-15 04:41:08,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 123240448. Throughput: 0: 1732.7, 1: 1753.4. Samples: 30822978. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:41:08,535][87330] Avg episode reward: [(0, '22.660'), (1, '22.500')] -[2023-10-15 04:41:08,579][88298] Updated weights for policy 0, policy_version 60010 (0.0007) -[2023-10-15 04:41:08,902][88300] Updated weights for policy 1, policy_version 60362 (0.0007) -[2023-10-15 04:41:08,940][88298] Updated weights for policy 0, policy_version 60020 (0.0008) -[2023-10-15 04:41:09,263][88300] Updated weights for policy 1, policy_version 60372 (0.0007) -[2023-10-15 04:41:09,306][88298] Updated weights for policy 0, policy_version 60030 (0.0008) -[2023-10-15 04:41:09,638][88300] Updated weights for policy 1, policy_version 60382 (0.0008) -[2023-10-15 04:41:13,257][88298] Updated weights for policy 0, policy_version 60040 (0.0008) -[2023-10-15 04:41:13,467][88300] Updated weights for policy 1, policy_version 60392 (0.0008) -[2023-10-15 04:41:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13884.7). Total num frames: 123305984. Throughput: 0: 1742.3, 1: 1766.9. Samples: 30844584. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:41:13,534][87330] Avg episode reward: [(0, '22.700'), (1, '22.370')] -[2023-10-15 04:41:13,616][88298] Updated weights for policy 0, policy_version 60050 (0.0009) -[2023-10-15 04:41:13,833][88300] Updated weights for policy 1, policy_version 60402 (0.0008) -[2023-10-15 04:41:13,982][88298] Updated weights for policy 0, policy_version 60060 (0.0007) -[2023-10-15 04:41:14,202][88300] Updated weights for policy 1, policy_version 60412 (0.0008) -[2023-10-15 04:41:17,830][88298] Updated weights for policy 0, policy_version 60070 (0.0007) -[2023-10-15 04:41:18,202][88298] Updated weights for policy 0, policy_version 60080 (0.0008) -[2023-10-15 04:41:18,312][88300] Updated weights for policy 1, policy_version 60422 (0.0010) -[2023-10-15 04:41:18,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13884.7). Total num frames: 123371520. Throughput: 0: 1727.0, 1: 1734.5. Samples: 30853994. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:41:18,534][87330] Avg episode reward: [(0, '22.700'), (1, '22.480')] -[2023-10-15 04:41:18,569][88298] Updated weights for policy 0, policy_version 60090 (0.0007) -[2023-10-15 04:41:18,670][88300] Updated weights for policy 1, policy_version 60432 (0.0008) -[2023-10-15 04:41:19,031][88300] Updated weights for policy 1, policy_version 60442 (0.0007) -[2023-10-15 04:41:22,522][88298] Updated weights for policy 0, policy_version 60100 (0.0007) -[2023-10-15 04:41:22,895][88298] Updated weights for policy 0, policy_version 60110 (0.0007) -[2023-10-15 04:41:22,951][88300] Updated weights for policy 1, policy_version 60452 (0.0009) -[2023-10-15 04:41:23,270][88298] Updated weights for policy 0, policy_version 60120 (0.0007) -[2023-10-15 04:41:23,321][88300] Updated weights for policy 1, policy_version 60462 (0.0007) -[2023-10-15 04:41:23,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 123437056. Throughput: 0: 1744.3, 1: 1757.6. Samples: 30875332. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:41:23,535][87330] Avg episode reward: [(0, '22.590'), (1, '22.330')] -[2023-10-15 04:41:23,683][88300] Updated weights for policy 1, policy_version 60472 (0.0008) -[2023-10-15 04:41:27,231][88298] Updated weights for policy 0, policy_version 60130 (0.0008) -[2023-10-15 04:41:27,445][88300] Updated weights for policy 1, policy_version 60482 (0.0008) -[2023-10-15 04:41:27,606][88298] Updated weights for policy 0, policy_version 60140 (0.0008) -[2023-10-15 04:41:27,812][88300] Updated weights for policy 1, policy_version 60492 (0.0007) -[2023-10-15 04:41:27,970][88298] Updated weights for policy 0, policy_version 60150 (0.0009) -[2023-10-15 04:41:28,189][88300] Updated weights for policy 1, policy_version 60502 (0.0008) -[2023-10-15 04:41:28,342][88298] Updated weights for policy 0, policy_version 60160 (0.0008) -[2023-10-15 04:41:28,534][87330] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 123535360. Throughput: 0: 1732.7, 1: 1734.8. Samples: 30895220. Policy #0 lag: (min: 8.0, avg: 32.3, max: 40.0) -[2023-10-15 04:41:28,535][87330] Avg episode reward: [(0, '22.760'), (1, '22.270')] -[2023-10-15 04:41:28,551][88300] Updated weights for policy 1, policy_version 60512 (0.0008) -[2023-10-15 04:41:32,243][88298] Updated weights for policy 0, policy_version 60170 (0.0008) -[2023-10-15 04:41:32,358][88300] Updated weights for policy 1, policy_version 60522 (0.0008) -[2023-10-15 04:41:32,605][88298] Updated weights for policy 0, policy_version 60180 (0.0008) -[2023-10-15 04:41:32,719][88300] Updated weights for policy 1, policy_version 60532 (0.0009) -[2023-10-15 04:41:32,976][88298] Updated weights for policy 0, policy_version 60190 (0.0008) -[2023-10-15 04:41:33,091][88300] Updated weights for policy 1, policy_version 60542 (0.0008) -[2023-10-15 04:41:33,534][87330] Fps is (10 sec: 19660.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 123633664. Throughput: 0: 1747.0, 1: 1752.9. Samples: 30906476. Policy #0 lag: (min: 8.0, avg: 32.3, max: 40.0) -[2023-10-15 04:41:33,534][87330] Avg episode reward: [(0, '22.740'), (1, '22.320')] -[2023-10-15 04:41:37,105][88300] Updated weights for policy 1, policy_version 60552 (0.0007) -[2023-10-15 04:41:37,140][88298] Updated weights for policy 0, policy_version 60200 (0.0008) -[2023-10-15 04:41:37,474][88300] Updated weights for policy 1, policy_version 60562 (0.0008) -[2023-10-15 04:41:37,512][88298] Updated weights for policy 0, policy_version 60210 (0.0008) -[2023-10-15 04:41:37,842][88300] Updated weights for policy 1, policy_version 60572 (0.0007) -[2023-10-15 04:41:37,878][88298] Updated weights for policy 0, policy_version 60220 (0.0008) -[2023-10-15 04:41:38,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 123699200. Throughput: 0: 1751.5, 1: 1750.3. Samples: 30927494. Policy #0 lag: (min: 8.0, avg: 32.3, max: 40.0) -[2023-10-15 04:41:38,535][87330] Avg episode reward: [(0, '22.430'), (1, '22.320')] -[2023-10-15 04:41:41,626][88300] Updated weights for policy 1, policy_version 60582 (0.0008) -[2023-10-15 04:41:41,652][88298] Updated weights for policy 0, policy_version 60230 (0.0009) -[2023-10-15 04:41:42,011][88300] Updated weights for policy 1, policy_version 60592 (0.0008) -[2023-10-15 04:41:42,028][88298] Updated weights for policy 0, policy_version 60240 (0.0008) -[2023-10-15 04:41:42,379][88300] Updated weights for policy 1, policy_version 60602 (0.0007) -[2023-10-15 04:41:42,390][88298] Updated weights for policy 0, policy_version 60250 (0.0010) -[2023-10-15 04:41:43,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 123764736. Throughput: 0: 1721.4, 1: 1732.2. Samples: 30946794. Policy #0 lag: (min: 8.0, avg: 32.3, max: 40.0) -[2023-10-15 04:41:43,535][87330] Avg episode reward: [(0, '22.370'), (1, '22.390')] -[2023-10-15 04:41:46,197][88300] Updated weights for policy 1, policy_version 60612 (0.0007) -[2023-10-15 04:41:46,298][88298] Updated weights for policy 0, policy_version 60260 (0.0009) -[2023-10-15 04:41:46,560][88300] Updated weights for policy 1, policy_version 60622 (0.0007) -[2023-10-15 04:41:46,664][88298] Updated weights for policy 0, policy_version 60270 (0.0008) -[2023-10-15 04:41:46,925][88300] Updated weights for policy 1, policy_version 60632 (0.0007) -[2023-10-15 04:41:47,029][88298] Updated weights for policy 0, policy_version 60280 (0.0007) -[2023-10-15 04:41:48,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 123830272. Throughput: 0: 1752.7, 1: 1762.2. Samples: 30959102. Policy #0 lag: (min: 8.0, avg: 32.3, max: 40.0) -[2023-10-15 04:41:48,534][87330] Avg episode reward: [(0, '22.340'), (1, '22.420')] -[2023-10-15 04:41:50,870][88300] Updated weights for policy 1, policy_version 60642 (0.0007) -[2023-10-15 04:41:50,939][88298] Updated weights for policy 0, policy_version 60290 (0.0007) -[2023-10-15 04:41:51,229][88300] Updated weights for policy 1, policy_version 60652 (0.0009) -[2023-10-15 04:41:51,303][88298] Updated weights for policy 0, policy_version 60300 (0.0008) -[2023-10-15 04:41:51,602][88300] Updated weights for policy 1, policy_version 60662 (0.0007) -[2023-10-15 04:41:51,664][88298] Updated weights for policy 0, policy_version 60310 (0.0008) -[2023-10-15 04:41:51,967][88300] Updated weights for policy 1, policy_version 60672 (0.0008) -[2023-10-15 04:41:52,029][88298] Updated weights for policy 0, policy_version 60320 (0.0008) -[2023-10-15 04:41:53,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 123895808. Throughput: 0: 1729.0, 1: 1729.5. Samples: 30978612. Policy #0 lag: (min: 8.0, avg: 32.3, max: 40.0) -[2023-10-15 04:41:53,534][87330] Avg episode reward: [(0, '22.400'), (1, '22.230')] -[2023-10-15 04:41:55,859][88298] Updated weights for policy 0, policy_version 60330 (0.0010) -[2023-10-15 04:41:55,964][88300] Updated weights for policy 1, policy_version 60682 (0.0010) -[2023-10-15 04:41:56,225][88298] Updated weights for policy 0, policy_version 60340 (0.0009) -[2023-10-15 04:41:56,330][88300] Updated weights for policy 1, policy_version 60692 (0.0009) -[2023-10-15 04:41:56,590][88298] Updated weights for policy 0, policy_version 60350 (0.0007) -[2023-10-15 04:41:56,694][88300] Updated weights for policy 1, policy_version 60702 (0.0008) -[2023-10-15 04:41:58,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 123961344. Throughput: 0: 1724.7, 1: 1730.1. Samples: 31000050. Policy #0 lag: (min: 8.0, avg: 32.3, max: 40.0) -[2023-10-15 04:41:58,535][87330] Avg episode reward: [(0, '22.520'), (1, '22.380')] -[2023-10-15 04:42:00,420][88298] Updated weights for policy 0, policy_version 60360 (0.0008) -[2023-10-15 04:42:00,532][88300] Updated weights for policy 1, policy_version 60712 (0.0008) -[2023-10-15 04:42:00,781][88298] Updated weights for policy 0, policy_version 60370 (0.0007) -[2023-10-15 04:42:00,892][88300] Updated weights for policy 1, policy_version 60722 (0.0008) -[2023-10-15 04:42:01,150][88298] Updated weights for policy 0, policy_version 60380 (0.0007) -[2023-10-15 04:42:01,254][88300] Updated weights for policy 1, policy_version 60732 (0.0009) -[2023-10-15 04:42:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 124026880. Throughput: 0: 1739.8, 1: 1739.4. Samples: 31010556. Policy #0 lag: (min: 8.0, avg: 32.3, max: 40.0) -[2023-10-15 04:42:03,534][87330] Avg episode reward: [(0, '22.510'), (1, '22.420')] -[2023-10-15 04:42:05,243][88300] Updated weights for policy 1, policy_version 60742 (0.0010) -[2023-10-15 04:42:05,273][88298] Updated weights for policy 0, policy_version 60390 (0.0009) -[2023-10-15 04:42:05,610][88300] Updated weights for policy 1, policy_version 60752 (0.0007) -[2023-10-15 04:42:05,634][88298] Updated weights for policy 0, policy_version 60400 (0.0009) -[2023-10-15 04:42:05,983][88300] Updated weights for policy 1, policy_version 60762 (0.0008) -[2023-10-15 04:42:06,009][88298] Updated weights for policy 0, policy_version 60410 (0.0009) -[2023-10-15 04:42:08,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 124092416. Throughput: 0: 1724.2, 1: 1734.3. Samples: 31030966. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:42:08,535][87330] Avg episode reward: [(0, '22.800'), (1, '22.180')] -[2023-10-15 04:42:09,687][88300] Updated weights for policy 1, policy_version 60772 (0.0009) -[2023-10-15 04:42:09,948][88298] Updated weights for policy 0, policy_version 60420 (0.0007) -[2023-10-15 04:42:10,063][88300] Updated weights for policy 1, policy_version 60782 (0.0009) -[2023-10-15 04:42:10,320][88298] Updated weights for policy 0, policy_version 60430 (0.0008) -[2023-10-15 04:42:10,434][88300] Updated weights for policy 1, policy_version 60792 (0.0008) -[2023-10-15 04:42:10,683][88298] Updated weights for policy 0, policy_version 60440 (0.0007) -[2023-10-15 04:42:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 124157952. Throughput: 0: 1735.0, 1: 1759.8. Samples: 31052486. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:42:13,534][87330] Avg episode reward: [(0, '22.900'), (1, '22.390')] -[2023-10-15 04:42:14,262][88300] Updated weights for policy 1, policy_version 60802 (0.0010) -[2023-10-15 04:42:14,629][88300] Updated weights for policy 1, policy_version 60812 (0.0007) -[2023-10-15 04:42:14,708][88298] Updated weights for policy 0, policy_version 60450 (0.0008) -[2023-10-15 04:42:14,984][88300] Updated weights for policy 1, policy_version 60822 (0.0008) -[2023-10-15 04:42:15,078][88298] Updated weights for policy 0, policy_version 60460 (0.0009) -[2023-10-15 04:42:15,356][88300] Updated weights for policy 1, policy_version 60832 (0.0008) -[2023-10-15 04:42:15,436][88298] Updated weights for policy 0, policy_version 60470 (0.0007) -[2023-10-15 04:42:15,810][88298] Updated weights for policy 0, policy_version 60480 (0.0009) -[2023-10-15 04:42:18,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 124223488. Throughput: 0: 1718.8, 1: 1738.8. Samples: 31062068. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:42:18,535][87330] Avg episode reward: [(0, '22.880'), (1, '22.430')] -[2023-10-15 04:42:19,316][88300] Updated weights for policy 1, policy_version 60842 (0.0008) -[2023-10-15 04:42:19,683][88300] Updated weights for policy 1, policy_version 60852 (0.0010) -[2023-10-15 04:42:19,832][88298] Updated weights for policy 0, policy_version 60490 (0.0008) -[2023-10-15 04:42:20,046][88300] Updated weights for policy 1, policy_version 60862 (0.0007) -[2023-10-15 04:42:20,204][88298] Updated weights for policy 0, policy_version 60500 (0.0008) -[2023-10-15 04:42:20,566][88298] Updated weights for policy 0, policy_version 60510 (0.0009) -[2023-10-15 04:42:23,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 124289024. Throughput: 0: 1716.8, 1: 1747.8. Samples: 31083402. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:42:23,535][87330] Avg episode reward: [(0, '22.730'), (1, '22.610')] -[2023-10-15 04:42:23,910][88300] Updated weights for policy 1, policy_version 60872 (0.0009) -[2023-10-15 04:42:24,280][88300] Updated weights for policy 1, policy_version 60882 (0.0010) -[2023-10-15 04:42:24,499][88298] Updated weights for policy 0, policy_version 60520 (0.0009) -[2023-10-15 04:42:24,651][88300] Updated weights for policy 1, policy_version 60892 (0.0009) -[2023-10-15 04:42:24,867][88298] Updated weights for policy 0, policy_version 60530 (0.0009) -[2023-10-15 04:42:25,229][88298] Updated weights for policy 0, policy_version 60540 (0.0011) -[2023-10-15 04:42:28,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 124354560. Throughput: 0: 1749.3, 1: 1770.1. Samples: 31105162. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:42:28,534][87330] Avg episode reward: [(0, '22.730'), (1, '22.460')] -[2023-10-15 04:42:28,569][88300] Updated weights for policy 1, policy_version 60902 (0.0010) -[2023-10-15 04:42:28,944][88300] Updated weights for policy 1, policy_version 60912 (0.0008) -[2023-10-15 04:42:29,020][88298] Updated weights for policy 0, policy_version 60550 (0.0008) -[2023-10-15 04:42:29,311][88300] Updated weights for policy 1, policy_version 60922 (0.0008) -[2023-10-15 04:42:29,383][88298] Updated weights for policy 0, policy_version 60560 (0.0007) -[2023-10-15 04:42:29,761][88298] Updated weights for policy 0, policy_version 60570 (0.0010) -[2023-10-15 04:42:33,108][88300] Updated weights for policy 1, policy_version 60932 (0.0009) -[2023-10-15 04:42:33,480][88300] Updated weights for policy 1, policy_version 60942 (0.0007) -[2023-10-15 04:42:33,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13884.8). Total num frames: 124420096. Throughput: 0: 1714.6, 1: 1741.9. Samples: 31114644. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:42:33,534][87330] Avg episode reward: [(0, '22.690'), (1, '22.440')] -[2023-10-15 04:42:33,842][88300] Updated weights for policy 1, policy_version 60952 (0.0008) -[2023-10-15 04:42:33,869][88298] Updated weights for policy 0, policy_version 60580 (0.0008) -[2023-10-15 04:42:34,234][88298] Updated weights for policy 0, policy_version 60590 (0.0009) -[2023-10-15 04:42:34,600][88298] Updated weights for policy 0, policy_version 60600 (0.0010) -[2023-10-15 04:42:37,631][88300] Updated weights for policy 1, policy_version 60962 (0.0008) -[2023-10-15 04:42:37,986][88300] Updated weights for policy 1, policy_version 60972 (0.0008) -[2023-10-15 04:42:38,351][88300] Updated weights for policy 1, policy_version 60982 (0.0008) -[2023-10-15 04:42:38,435][88298] Updated weights for policy 0, policy_version 60610 (0.0011) -[2023-10-15 04:42:38,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 124485632. Throughput: 0: 1726.0, 1: 1765.3. Samples: 31135720. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:42:38,535][87330] Avg episode reward: [(0, '22.650'), (1, '22.650')] -[2023-10-15 04:42:38,720][88300] Updated weights for policy 1, policy_version 60992 (0.0008) -[2023-10-15 04:42:38,812][88298] Updated weights for policy 0, policy_version 60620 (0.0010) -[2023-10-15 04:42:39,175][88298] Updated weights for policy 0, policy_version 60630 (0.0010) -[2023-10-15 04:42:39,545][88298] Updated weights for policy 0, policy_version 60640 (0.0007) -[2023-10-15 04:42:42,622][88300] Updated weights for policy 1, policy_version 61002 (0.0009) -[2023-10-15 04:42:42,991][88300] Updated weights for policy 1, policy_version 61012 (0.0007) -[2023-10-15 04:42:43,361][88300] Updated weights for policy 1, policy_version 61022 (0.0008) -[2023-10-15 04:42:43,403][88298] Updated weights for policy 0, policy_version 60650 (0.0008) -[2023-10-15 04:42:43,534][87330] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 124583936. Throughput: 0: 1730.2, 1: 1743.3. Samples: 31156358. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:42:43,534][87330] Avg episode reward: [(0, '22.630'), (1, '22.410')] -[2023-10-15 04:42:43,762][88298] Updated weights for policy 0, policy_version 60660 (0.0010) -[2023-10-15 04:42:44,138][88298] Updated weights for policy 0, policy_version 60670 (0.0011) -[2023-10-15 04:42:47,332][88300] Updated weights for policy 1, policy_version 61032 (0.0008) -[2023-10-15 04:42:47,703][88300] Updated weights for policy 1, policy_version 61042 (0.0007) -[2023-10-15 04:42:48,065][88300] Updated weights for policy 1, policy_version 61052 (0.0007) -[2023-10-15 04:42:48,077][88298] Updated weights for policy 0, policy_version 60680 (0.0008) -[2023-10-15 04:42:48,444][88298] Updated weights for policy 0, policy_version 60690 (0.0009) -[2023-10-15 04:42:48,534][87330] Fps is (10 sec: 16384.3, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 124649472. Throughput: 0: 1713.6, 1: 1759.0. Samples: 31166820. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:42:48,534][87330] Avg episode reward: [(0, '22.610'), (1, '22.240')] -[2023-10-15 04:42:48,816][88298] Updated weights for policy 0, policy_version 60700 (0.0009) -[2023-10-15 04:42:52,011][88300] Updated weights for policy 1, policy_version 61062 (0.0008) -[2023-10-15 04:42:52,370][88300] Updated weights for policy 1, policy_version 61072 (0.0010) -[2023-10-15 04:42:52,732][88300] Updated weights for policy 1, policy_version 61082 (0.0007) -[2023-10-15 04:42:52,797][88298] Updated weights for policy 0, policy_version 60710 (0.0007) -[2023-10-15 04:42:53,174][88298] Updated weights for policy 0, policy_version 60720 (0.0008) -[2023-10-15 04:42:53,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 124715008. Throughput: 0: 1730.7, 1: 1755.1. Samples: 31187826. Policy #0 lag: (min: 3.0, avg: 5.8, max: 35.0) -[2023-10-15 04:42:53,535][87330] Avg episode reward: [(0, '22.790'), (1, '22.190')] -[2023-10-15 04:42:53,543][88298] Updated weights for policy 0, policy_version 60730 (0.0008) -[2023-10-15 04:42:56,535][88300] Updated weights for policy 1, policy_version 61092 (0.0007) -[2023-10-15 04:42:56,899][88300] Updated weights for policy 1, policy_version 61102 (0.0007) -[2023-10-15 04:42:57,274][88300] Updated weights for policy 1, policy_version 61112 (0.0008) -[2023-10-15 04:42:57,499][88298] Updated weights for policy 0, policy_version 60740 (0.0008) -[2023-10-15 04:42:57,870][88298] Updated weights for policy 0, policy_version 60750 (0.0007) -[2023-10-15 04:42:58,241][88298] Updated weights for policy 0, policy_version 60760 (0.0007) -[2023-10-15 04:42:58,534][87330] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 124780544. Throughput: 0: 1724.7, 1: 1734.0. Samples: 31208128. Policy #0 lag: (min: 3.0, avg: 5.8, max: 35.0) -[2023-10-15 04:42:58,535][87330] Avg episode reward: [(0, '22.870'), (1, '22.240')] -[2023-10-15 04:42:58,545][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000060768_62226432.pth... -[2023-10-15 04:42:58,545][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000061120_62586880.pth... -[2023-10-15 04:42:58,575][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000059136_60555264.pth -[2023-10-15 04:42:58,587][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000059488_60915712.pth -[2023-10-15 04:43:01,195][88300] Updated weights for policy 1, policy_version 61122 (0.0007) -[2023-10-15 04:43:01,571][88300] Updated weights for policy 1, policy_version 61132 (0.0009) -[2023-10-15 04:43:01,941][88300] Updated weights for policy 1, policy_version 61142 (0.0010) -[2023-10-15 04:43:02,094][88298] Updated weights for policy 0, policy_version 60770 (0.0008) -[2023-10-15 04:43:02,305][88300] Updated weights for policy 1, policy_version 61152 (0.0008) -[2023-10-15 04:43:02,468][88298] Updated weights for policy 0, policy_version 60780 (0.0011) -[2023-10-15 04:43:02,838][88298] Updated weights for policy 0, policy_version 60790 (0.0008) -[2023-10-15 04:43:03,211][88298] Updated weights for policy 0, policy_version 60800 (0.0007) -[2023-10-15 04:43:03,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 124878848. Throughput: 0: 1731.0, 1: 1761.6. Samples: 31219236. Policy #0 lag: (min: 3.0, avg: 5.8, max: 35.0) -[2023-10-15 04:43:03,534][87330] Avg episode reward: [(0, '22.900'), (1, '22.410')] -[2023-10-15 04:43:06,156][88300] Updated weights for policy 1, policy_version 61162 (0.0010) -[2023-10-15 04:43:06,518][88300] Updated weights for policy 1, policy_version 61172 (0.0009) -[2023-10-15 04:43:06,894][88300] Updated weights for policy 1, policy_version 61182 (0.0009) -[2023-10-15 04:43:07,206][88298] Updated weights for policy 0, policy_version 60810 (0.0007) -[2023-10-15 04:43:07,576][88298] Updated weights for policy 0, policy_version 60820 (0.0009) -[2023-10-15 04:43:07,948][88298] Updated weights for policy 0, policy_version 60830 (0.0009) -[2023-10-15 04:43:08,534][87330] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 124944384. Throughput: 0: 1741.1, 1: 1728.4. Samples: 31239530. Policy #0 lag: (min: 3.0, avg: 5.8, max: 35.0) -[2023-10-15 04:43:08,534][87330] Avg episode reward: [(0, '22.840'), (1, '22.340')] -[2023-10-15 04:43:10,869][88300] Updated weights for policy 1, policy_version 61192 (0.0010) -[2023-10-15 04:43:11,231][88300] Updated weights for policy 1, policy_version 61202 (0.0011) -[2023-10-15 04:43:11,605][88300] Updated weights for policy 1, policy_version 61212 (0.0009) -[2023-10-15 04:43:11,797][88298] Updated weights for policy 0, policy_version 60840 (0.0010) -[2023-10-15 04:43:12,166][88298] Updated weights for policy 0, policy_version 60850 (0.0008) -[2023-10-15 04:43:12,540][88298] Updated weights for policy 0, policy_version 60860 (0.0007) -[2023-10-15 04:43:13,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 125009920. Throughput: 0: 1708.4, 1: 1726.6. Samples: 31259738. Policy #0 lag: (min: 3.0, avg: 5.8, max: 35.0) -[2023-10-15 04:43:13,535][87330] Avg episode reward: [(0, '22.910'), (1, '22.100')] -[2023-10-15 04:43:15,426][88300] Updated weights for policy 1, policy_version 61222 (0.0007) -[2023-10-15 04:43:15,819][88300] Updated weights for policy 1, policy_version 61232 (0.0009) -[2023-10-15 04:43:16,182][88300] Updated weights for policy 1, policy_version 61242 (0.0008) -[2023-10-15 04:43:16,427][88298] Updated weights for policy 0, policy_version 60870 (0.0008) -[2023-10-15 04:43:16,797][88298] Updated weights for policy 0, policy_version 60880 (0.0009) -[2023-10-15 04:43:17,168][88298] Updated weights for policy 0, policy_version 60890 (0.0009) -[2023-10-15 04:43:18,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 125075456. Throughput: 0: 1739.8, 1: 1731.6. Samples: 31270856. Policy #0 lag: (min: 3.0, avg: 5.8, max: 35.0) -[2023-10-15 04:43:18,535][87330] Avg episode reward: [(0, '22.910'), (1, '22.360')] -[2023-10-15 04:43:20,103][88300] Updated weights for policy 1, policy_version 61252 (0.0010) -[2023-10-15 04:43:20,476][88300] Updated weights for policy 1, policy_version 61262 (0.0008) -[2023-10-15 04:43:20,835][88300] Updated weights for policy 1, policy_version 61272 (0.0007) -[2023-10-15 04:43:21,031][88298] Updated weights for policy 0, policy_version 60900 (0.0008) -[2023-10-15 04:43:21,398][88298] Updated weights for policy 0, policy_version 60910 (0.0007) -[2023-10-15 04:43:21,773][88298] Updated weights for policy 0, policy_version 60920 (0.0008) -[2023-10-15 04:43:23,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 125140992. Throughput: 0: 1731.2, 1: 1724.9. Samples: 31291244. Policy #0 lag: (min: 3.0, avg: 5.8, max: 35.0) -[2023-10-15 04:43:23,535][87330] Avg episode reward: [(0, '22.620'), (1, '22.390')] -[2023-10-15 04:43:24,778][88300] Updated weights for policy 1, policy_version 61282 (0.0008) -[2023-10-15 04:43:25,145][88300] Updated weights for policy 1, policy_version 61292 (0.0010) -[2023-10-15 04:43:25,519][88300] Updated weights for policy 1, policy_version 61302 (0.0008) -[2023-10-15 04:43:25,700][88298] Updated weights for policy 0, policy_version 60930 (0.0008) -[2023-10-15 04:43:25,881][88300] Updated weights for policy 1, policy_version 61312 (0.0008) -[2023-10-15 04:43:26,071][88298] Updated weights for policy 0, policy_version 60940 (0.0009) -[2023-10-15 04:43:26,429][88298] Updated weights for policy 0, policy_version 60950 (0.0009) -[2023-10-15 04:43:26,807][88298] Updated weights for policy 0, policy_version 60960 (0.0009) -[2023-10-15 04:43:28,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 125206528. Throughput: 0: 1722.0, 1: 1749.1. Samples: 31312558. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 04:43:28,534][87330] Avg episode reward: [(0, '22.510'), (1, '22.410')] -[2023-10-15 04:43:29,805][88300] Updated weights for policy 1, policy_version 61322 (0.0008) -[2023-10-15 04:43:30,168][88300] Updated weights for policy 1, policy_version 61332 (0.0008) -[2023-10-15 04:43:30,536][88300] Updated weights for policy 1, policy_version 61342 (0.0007) -[2023-10-15 04:43:30,823][88298] Updated weights for policy 0, policy_version 60970 (0.0009) -[2023-10-15 04:43:31,191][88298] Updated weights for policy 0, policy_version 60980 (0.0009) -[2023-10-15 04:43:31,564][88298] Updated weights for policy 0, policy_version 60990 (0.0011) -[2023-10-15 04:43:33,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 125272064. Throughput: 0: 1744.7, 1: 1723.9. Samples: 31322908. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 04:43:33,535][87330] Avg episode reward: [(0, '22.480'), (1, '22.420')] -[2023-10-15 04:43:34,358][88300] Updated weights for policy 1, policy_version 61352 (0.0008) -[2023-10-15 04:43:34,722][88300] Updated weights for policy 1, policy_version 61362 (0.0008) -[2023-10-15 04:43:35,086][88300] Updated weights for policy 1, policy_version 61372 (0.0009) -[2023-10-15 04:43:35,328][88298] Updated weights for policy 0, policy_version 61000 (0.0007) -[2023-10-15 04:43:35,697][88298] Updated weights for policy 0, policy_version 61010 (0.0007) -[2023-10-15 04:43:36,072][88298] Updated weights for policy 0, policy_version 61020 (0.0008) -[2023-10-15 04:43:38,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 125337600. Throughput: 0: 1725.5, 1: 1739.3. Samples: 31343740. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 04:43:38,535][87330] Avg episode reward: [(0, '22.510'), (1, '22.410')] -[2023-10-15 04:43:39,025][88300] Updated weights for policy 1, policy_version 61382 (0.0008) -[2023-10-15 04:43:39,392][88300] Updated weights for policy 1, policy_version 61392 (0.0008) -[2023-10-15 04:43:39,750][88300] Updated weights for policy 1, policy_version 61402 (0.0008) -[2023-10-15 04:43:39,999][88298] Updated weights for policy 0, policy_version 61030 (0.0008) -[2023-10-15 04:43:40,361][88298] Updated weights for policy 0, policy_version 61040 (0.0007) -[2023-10-15 04:43:40,724][88298] Updated weights for policy 0, policy_version 61050 (0.0007) -[2023-10-15 04:43:43,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 125403136. Throughput: 0: 1735.0, 1: 1757.6. Samples: 31365294. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 04:43:43,535][87330] Avg episode reward: [(0, '22.400'), (1, '22.260')] -[2023-10-15 04:43:43,656][88300] Updated weights for policy 1, policy_version 61412 (0.0008) -[2023-10-15 04:43:44,030][88300] Updated weights for policy 1, policy_version 61422 (0.0009) -[2023-10-15 04:43:44,399][88300] Updated weights for policy 1, policy_version 61432 (0.0008) -[2023-10-15 04:43:44,639][88298] Updated weights for policy 0, policy_version 61060 (0.0007) -[2023-10-15 04:43:45,012][88298] Updated weights for policy 0, policy_version 61070 (0.0007) -[2023-10-15 04:43:45,381][88298] Updated weights for policy 0, policy_version 61080 (0.0007) -[2023-10-15 04:43:48,117][88300] Updated weights for policy 1, policy_version 61442 (0.0008) -[2023-10-15 04:43:48,473][88300] Updated weights for policy 1, policy_version 61452 (0.0008) -[2023-10-15 04:43:48,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 125468672. Throughput: 0: 1727.8, 1: 1731.7. Samples: 31374912. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 04:43:48,534][87330] Avg episode reward: [(0, '22.400'), (1, '22.600')] -[2023-10-15 04:43:48,842][88300] Updated weights for policy 1, policy_version 61462 (0.0011) -[2023-10-15 04:43:49,211][88300] Updated weights for policy 1, policy_version 61472 (0.0008) -[2023-10-15 04:43:49,433][88298] Updated weights for policy 0, policy_version 61090 (0.0009) -[2023-10-15 04:43:49,807][88298] Updated weights for policy 0, policy_version 61100 (0.0010) -[2023-10-15 04:43:50,179][88298] Updated weights for policy 0, policy_version 61110 (0.0012) -[2023-10-15 04:43:50,554][88298] Updated weights for policy 0, policy_version 61120 (0.0010) -[2023-10-15 04:43:53,187][88300] Updated weights for policy 1, policy_version 61482 (0.0008) -[2023-10-15 04:43:53,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 125534208. Throughput: 0: 1725.7, 1: 1758.2. Samples: 31396306. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 04:43:53,535][87330] Avg episode reward: [(0, '22.640'), (1, '22.620')] -[2023-10-15 04:43:53,561][88300] Updated weights for policy 1, policy_version 61492 (0.0007) -[2023-10-15 04:43:53,935][88300] Updated weights for policy 1, policy_version 61502 (0.0009) -[2023-10-15 04:43:54,520][88298] Updated weights for policy 0, policy_version 61130 (0.0007) -[2023-10-15 04:43:54,893][88298] Updated weights for policy 0, policy_version 61140 (0.0009) -[2023-10-15 04:43:55,268][88298] Updated weights for policy 0, policy_version 61150 (0.0008) -[2023-10-15 04:43:58,022][88300] Updated weights for policy 1, policy_version 61512 (0.0008) -[2023-10-15 04:43:58,391][88300] Updated weights for policy 1, policy_version 61522 (0.0007) -[2023-10-15 04:43:58,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 125599744. Throughput: 0: 1751.6, 1: 1741.8. Samples: 31416938. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 04:43:58,534][87330] Avg episode reward: [(0, '22.660'), (1, '22.630')] -[2023-10-15 04:43:58,763][88300] Updated weights for policy 1, policy_version 61532 (0.0008) -[2023-10-15 04:43:59,263][88298] Updated weights for policy 0, policy_version 61160 (0.0009) -[2023-10-15 04:43:59,633][88298] Updated weights for policy 0, policy_version 61170 (0.0007) -[2023-10-15 04:43:59,997][88298] Updated weights for policy 0, policy_version 61180 (0.0008) -[2023-10-15 04:44:02,928][88300] Updated weights for policy 1, policy_version 61542 (0.0007) -[2023-10-15 04:44:03,318][88300] Updated weights for policy 1, policy_version 61552 (0.0009) -[2023-10-15 04:44:03,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 125665280. Throughput: 0: 1720.5, 1: 1746.5. Samples: 31426870. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 04:44:03,534][87330] Avg episode reward: [(0, '22.810'), (1, '22.640')] -[2023-10-15 04:44:03,692][88300] Updated weights for policy 1, policy_version 61562 (0.0008) -[2023-10-15 04:44:03,802][88298] Updated weights for policy 0, policy_version 61190 (0.0009) -[2023-10-15 04:44:04,159][88298] Updated weights for policy 0, policy_version 61200 (0.0009) -[2023-10-15 04:44:04,524][88298] Updated weights for policy 0, policy_version 61210 (0.0007) -[2023-10-15 04:44:07,438][88300] Updated weights for policy 1, policy_version 61572 (0.0008) -[2023-10-15 04:44:07,803][88300] Updated weights for policy 1, policy_version 61582 (0.0011) -[2023-10-15 04:44:08,169][88300] Updated weights for policy 1, policy_version 61592 (0.0008) -[2023-10-15 04:44:08,454][88298] Updated weights for policy 0, policy_version 61220 (0.0009) -[2023-10-15 04:44:08,534][87330] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 125763584. Throughput: 0: 1740.0, 1: 1752.4. Samples: 31448400. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 04:44:08,534][87330] Avg episode reward: [(0, '22.860'), (1, '22.640')] -[2023-10-15 04:44:08,823][88298] Updated weights for policy 0, policy_version 61230 (0.0009) -[2023-10-15 04:44:09,199][88298] Updated weights for policy 0, policy_version 61240 (0.0007) -[2023-10-15 04:44:12,138][88300] Updated weights for policy 1, policy_version 61602 (0.0008) -[2023-10-15 04:44:12,513][88300] Updated weights for policy 1, policy_version 61612 (0.0008) -[2023-10-15 04:44:12,889][88300] Updated weights for policy 1, policy_version 61622 (0.0008) -[2023-10-15 04:44:13,009][88298] Updated weights for policy 0, policy_version 61250 (0.0009) -[2023-10-15 04:44:13,254][88300] Updated weights for policy 1, policy_version 61632 (0.0008) -[2023-10-15 04:44:13,380][88298] Updated weights for policy 0, policy_version 61260 (0.0008) -[2023-10-15 04:44:13,534][87330] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 125829120. Throughput: 0: 1752.4, 1: 1721.1. Samples: 31468866. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-15 04:44:13,534][87330] Avg episode reward: [(0, '22.830'), (1, '22.720')] -[2023-10-15 04:44:13,754][88298] Updated weights for policy 0, policy_version 61270 (0.0009) -[2023-10-15 04:44:14,121][88298] Updated weights for policy 0, policy_version 61280 (0.0008) -[2023-10-15 04:44:17,023][88300] Updated weights for policy 1, policy_version 61642 (0.0009) -[2023-10-15 04:44:17,389][88300] Updated weights for policy 1, policy_version 61652 (0.0009) -[2023-10-15 04:44:17,752][88300] Updated weights for policy 1, policy_version 61662 (0.0009) -[2023-10-15 04:44:17,878][88298] Updated weights for policy 0, policy_version 61290 (0.0008) -[2023-10-15 04:44:18,245][88298] Updated weights for policy 0, policy_version 61300 (0.0007) -[2023-10-15 04:44:18,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 125894656. Throughput: 0: 1731.6, 1: 1750.0. Samples: 31479576. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-15 04:44:18,535][87330] Avg episode reward: [(0, '22.950'), (1, '22.980')] -[2023-10-15 04:44:18,536][88033] Saving new best policy, reward=22.980! -[2023-10-15 04:44:18,612][88298] Updated weights for policy 0, policy_version 61310 (0.0007) -[2023-10-15 04:44:21,669][88300] Updated weights for policy 1, policy_version 61672 (0.0009) -[2023-10-15 04:44:22,035][88300] Updated weights for policy 1, policy_version 61682 (0.0007) -[2023-10-15 04:44:22,403][88300] Updated weights for policy 1, policy_version 61692 (0.0008) -[2023-10-15 04:44:22,493][88298] Updated weights for policy 0, policy_version 61320 (0.0007) -[2023-10-15 04:44:22,871][88298] Updated weights for policy 0, policy_version 61330 (0.0008) -[2023-10-15 04:44:23,232][88298] Updated weights for policy 0, policy_version 61340 (0.0007) -[2023-10-15 04:44:23,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 125992960. Throughput: 0: 1753.3, 1: 1724.5. Samples: 31500244. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-15 04:44:23,534][87330] Avg episode reward: [(0, '22.990'), (1, '22.940')] -[2023-10-15 04:44:26,396][88300] Updated weights for policy 1, policy_version 61702 (0.0009) -[2023-10-15 04:44:26,757][88300] Updated weights for policy 1, policy_version 61712 (0.0009) -[2023-10-15 04:44:27,052][88298] Updated weights for policy 0, policy_version 61350 (0.0007) -[2023-10-15 04:44:27,134][88300] Updated weights for policy 1, policy_version 61722 (0.0008) -[2023-10-15 04:44:27,422][88298] Updated weights for policy 0, policy_version 61360 (0.0009) -[2023-10-15 04:44:27,791][88298] Updated weights for policy 0, policy_version 61370 (0.0009) -[2023-10-15 04:44:28,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 126058496. Throughput: 0: 1732.2, 1: 1709.3. Samples: 31520164. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-15 04:44:28,535][87330] Avg episode reward: [(0, '22.910'), (1, '22.580')] -[2023-10-15 04:44:31,110][88300] Updated weights for policy 1, policy_version 61732 (0.0010) -[2023-10-15 04:44:31,477][88300] Updated weights for policy 1, policy_version 61742 (0.0010) -[2023-10-15 04:44:31,627][88298] Updated weights for policy 0, policy_version 61380 (0.0007) -[2023-10-15 04:44:31,845][88300] Updated weights for policy 1, policy_version 61752 (0.0008) -[2023-10-15 04:44:31,988][88298] Updated weights for policy 0, policy_version 61390 (0.0007) -[2023-10-15 04:44:32,357][88298] Updated weights for policy 0, policy_version 61400 (0.0008) -[2023-10-15 04:44:33,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 126124032. Throughput: 0: 1757.1, 1: 1734.6. Samples: 31532040. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-15 04:44:33,535][87330] Avg episode reward: [(0, '22.710'), (1, '22.560')] -[2023-10-15 04:44:35,769][88300] Updated weights for policy 1, policy_version 61762 (0.0008) -[2023-10-15 04:44:36,134][88300] Updated weights for policy 1, policy_version 61772 (0.0009) -[2023-10-15 04:44:36,405][88298] Updated weights for policy 0, policy_version 61410 (0.0007) -[2023-10-15 04:44:36,509][88300] Updated weights for policy 1, policy_version 61782 (0.0008) -[2023-10-15 04:44:36,782][88298] Updated weights for policy 0, policy_version 61420 (0.0008) -[2023-10-15 04:44:36,865][88300] Updated weights for policy 1, policy_version 61792 (0.0009) -[2023-10-15 04:44:37,158][88298] Updated weights for policy 0, policy_version 61430 (0.0007) -[2023-10-15 04:44:37,527][88298] Updated weights for policy 0, policy_version 61440 (0.0007) -[2023-10-15 04:44:38,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 126189568. Throughput: 0: 1746.3, 1: 1713.8. Samples: 31552008. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-15 04:44:38,534][87330] Avg episode reward: [(0, '22.690'), (1, '22.570')] -[2023-10-15 04:44:40,634][88300] Updated weights for policy 1, policy_version 61802 (0.0007) -[2023-10-15 04:44:41,008][88300] Updated weights for policy 1, policy_version 61812 (0.0007) -[2023-10-15 04:44:41,364][88300] Updated weights for policy 1, policy_version 61822 (0.0007) -[2023-10-15 04:44:41,446][88298] Updated weights for policy 0, policy_version 61450 (0.0007) -[2023-10-15 04:44:41,817][88298] Updated weights for policy 0, policy_version 61460 (0.0007) -[2023-10-15 04:44:42,193][88298] Updated weights for policy 0, policy_version 61470 (0.0008) -[2023-10-15 04:44:43,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 126255104. Throughput: 0: 1732.6, 1: 1737.9. Samples: 31573112. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-15 04:44:43,534][87330] Avg episode reward: [(0, '22.700'), (1, '22.580')] -[2023-10-15 04:44:45,017][88300] Updated weights for policy 1, policy_version 61832 (0.0008) -[2023-10-15 04:44:45,380][88300] Updated weights for policy 1, policy_version 61842 (0.0008) -[2023-10-15 04:44:45,744][88300] Updated weights for policy 1, policy_version 61852 (0.0008) -[2023-10-15 04:44:46,118][88298] Updated weights for policy 0, policy_version 61480 (0.0009) -[2023-10-15 04:44:46,494][88298] Updated weights for policy 0, policy_version 61490 (0.0008) -[2023-10-15 04:44:46,871][88298] Updated weights for policy 0, policy_version 61500 (0.0010) -[2023-10-15 04:44:48,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 126320640. Throughput: 0: 1764.3, 1: 1723.9. Samples: 31583840. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-15 04:44:48,534][87330] Avg episode reward: [(0, '22.670'), (1, '22.570')] -[2023-10-15 04:44:49,797][88300] Updated weights for policy 1, policy_version 61862 (0.0009) -[2023-10-15 04:44:50,181][88300] Updated weights for policy 1, policy_version 61872 (0.0008) -[2023-10-15 04:44:50,550][88300] Updated weights for policy 1, policy_version 61882 (0.0007) -[2023-10-15 04:44:50,785][88298] Updated weights for policy 0, policy_version 61510 (0.0008) -[2023-10-15 04:44:51,156][88298] Updated weights for policy 0, policy_version 61520 (0.0007) -[2023-10-15 04:44:51,530][88298] Updated weights for policy 0, policy_version 61530 (0.0008) -[2023-10-15 04:44:53,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 126386176. Throughput: 0: 1728.7, 1: 1726.9. Samples: 31603904. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:44:53,535][87330] Avg episode reward: [(0, '22.650'), (1, '22.580')] -[2023-10-15 04:44:54,351][88300] Updated weights for policy 1, policy_version 61892 (0.0007) -[2023-10-15 04:44:54,722][88300] Updated weights for policy 1, policy_version 61902 (0.0008) -[2023-10-15 04:44:55,083][88300] Updated weights for policy 1, policy_version 61912 (0.0009) -[2023-10-15 04:44:55,345][88298] Updated weights for policy 0, policy_version 61540 (0.0007) -[2023-10-15 04:44:55,713][88298] Updated weights for policy 0, policy_version 61550 (0.0008) -[2023-10-15 04:44:56,086][88298] Updated weights for policy 0, policy_version 61560 (0.0009) -[2023-10-15 04:44:58,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 126451712. Throughput: 0: 1724.6, 1: 1757.2. Samples: 31625548. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:44:58,535][87330] Avg episode reward: [(0, '22.410'), (1, '22.720')] -[2023-10-15 04:44:58,546][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000061568_63045632.pth... -[2023-10-15 04:44:58,547][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000061920_63406080.pth... -[2023-10-15 04:44:58,579][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000060288_61734912.pth -[2023-10-15 04:44:58,586][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000059936_61374464.pth -[2023-10-15 04:44:58,921][88300] Updated weights for policy 1, policy_version 61922 (0.0008) -[2023-10-15 04:44:59,287][88300] Updated weights for policy 1, policy_version 61932 (0.0007) -[2023-10-15 04:44:59,655][88300] Updated weights for policy 1, policy_version 61942 (0.0007) -[2023-10-15 04:44:59,970][88298] Updated weights for policy 0, policy_version 61570 (0.0007) -[2023-10-15 04:45:00,030][88300] Updated weights for policy 1, policy_version 61952 (0.0008) -[2023-10-15 04:45:00,335][88298] Updated weights for policy 0, policy_version 61580 (0.0007) -[2023-10-15 04:45:00,707][88298] Updated weights for policy 0, policy_version 61590 (0.0008) -[2023-10-15 04:45:01,073][88298] Updated weights for policy 0, policy_version 61600 (0.0009) -[2023-10-15 04:45:03,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 13884.8). Total num frames: 126517248. Throughput: 0: 1733.4, 1: 1733.3. Samples: 31635578. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:45:03,534][87330] Avg episode reward: [(0, '22.690'), (1, '22.780')] -[2023-10-15 04:45:03,922][88300] Updated weights for policy 1, policy_version 61962 (0.0007) -[2023-10-15 04:45:04,293][88300] Updated weights for policy 1, policy_version 61972 (0.0007) -[2023-10-15 04:45:04,653][88300] Updated weights for policy 1, policy_version 61982 (0.0008) -[2023-10-15 04:45:04,985][88298] Updated weights for policy 0, policy_version 61610 (0.0008) -[2023-10-15 04:45:05,355][88298] Updated weights for policy 0, policy_version 61620 (0.0009) -[2023-10-15 04:45:05,739][88298] Updated weights for policy 0, policy_version 61630 (0.0008) -[2023-10-15 04:45:08,380][88300] Updated weights for policy 1, policy_version 61992 (0.0008) -[2023-10-15 04:45:08,534][87330] Fps is (10 sec: 13107.6, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 126582784. Throughput: 0: 1721.3, 1: 1757.2. Samples: 31656780. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:45:08,534][87330] Avg episode reward: [(0, '22.710'), (1, '22.500')] -[2023-10-15 04:45:08,755][88300] Updated weights for policy 1, policy_version 62002 (0.0008) -[2023-10-15 04:45:09,115][88300] Updated weights for policy 1, policy_version 62012 (0.0009) -[2023-10-15 04:45:09,697][88298] Updated weights for policy 0, policy_version 61640 (0.0009) -[2023-10-15 04:45:10,057][88298] Updated weights for policy 0, policy_version 61650 (0.0009) -[2023-10-15 04:45:10,423][88298] Updated weights for policy 0, policy_version 61660 (0.0008) -[2023-10-15 04:45:12,937][88300] Updated weights for policy 1, policy_version 62022 (0.0009) -[2023-10-15 04:45:13,299][88300] Updated weights for policy 1, policy_version 62032 (0.0007) -[2023-10-15 04:45:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 126648320. Throughput: 0: 1746.7, 1: 1764.8. Samples: 31678180. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:45:13,534][87330] Avg episode reward: [(0, '22.720'), (1, '22.450')] -[2023-10-15 04:45:13,667][88300] Updated weights for policy 1, policy_version 62042 (0.0007) -[2023-10-15 04:45:14,267][88298] Updated weights for policy 0, policy_version 61670 (0.0008) -[2023-10-15 04:45:14,634][88298] Updated weights for policy 0, policy_version 61680 (0.0007) -[2023-10-15 04:45:15,021][88298] Updated weights for policy 0, policy_version 61690 (0.0009) -[2023-10-15 04:45:17,552][88300] Updated weights for policy 1, policy_version 62052 (0.0009) -[2023-10-15 04:45:17,918][88300] Updated weights for policy 1, policy_version 62062 (0.0008) -[2023-10-15 04:45:18,283][88300] Updated weights for policy 1, policy_version 62072 (0.0008) -[2023-10-15 04:45:18,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 126713856. Throughput: 0: 1721.1, 1: 1752.9. Samples: 31688370. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:45:18,535][87330] Avg episode reward: [(0, '22.760'), (1, '22.290')] -[2023-10-15 04:45:18,914][88298] Updated weights for policy 0, policy_version 61700 (0.0009) -[2023-10-15 04:45:19,277][88298] Updated weights for policy 0, policy_version 61710 (0.0007) -[2023-10-15 04:45:19,640][88298] Updated weights for policy 0, policy_version 61720 (0.0008) -[2023-10-15 04:45:22,107][88300] Updated weights for policy 1, policy_version 62082 (0.0008) -[2023-10-15 04:45:22,472][88300] Updated weights for policy 1, policy_version 62092 (0.0007) -[2023-10-15 04:45:22,848][88300] Updated weights for policy 1, policy_version 62102 (0.0010) -[2023-10-15 04:45:23,218][88300] Updated weights for policy 1, policy_version 62112 (0.0010) -[2023-10-15 04:45:23,521][88298] Updated weights for policy 0, policy_version 61730 (0.0007) -[2023-10-15 04:45:23,534][87330] Fps is (10 sec: 16383.5, 60 sec: 13653.2, 300 sec: 13884.7). Total num frames: 126812160. Throughput: 0: 1731.8, 1: 1777.9. Samples: 31709942. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:45:23,535][87330] Avg episode reward: [(0, '22.770'), (1, '22.130')] -[2023-10-15 04:45:23,899][88298] Updated weights for policy 0, policy_version 61740 (0.0008) -[2023-10-15 04:45:24,272][88298] Updated weights for policy 0, policy_version 61750 (0.0009) -[2023-10-15 04:45:24,646][88298] Updated weights for policy 0, policy_version 61760 (0.0009) -[2023-10-15 04:45:27,153][88300] Updated weights for policy 1, policy_version 62122 (0.0007) -[2023-10-15 04:45:27,521][88300] Updated weights for policy 1, policy_version 62132 (0.0009) -[2023-10-15 04:45:27,893][88300] Updated weights for policy 1, policy_version 62142 (0.0007) -[2023-10-15 04:45:28,534][87330] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 126877696. Throughput: 0: 1753.2, 1: 1741.9. Samples: 31730390. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:45:28,535][87330] Avg episode reward: [(0, '22.770'), (1, '22.200')] -[2023-10-15 04:45:28,597][88298] Updated weights for policy 0, policy_version 61770 (0.0010) -[2023-10-15 04:45:28,974][88298] Updated weights for policy 0, policy_version 61780 (0.0008) -[2023-10-15 04:45:29,342][88298] Updated weights for policy 0, policy_version 61790 (0.0009) -[2023-10-15 04:45:31,775][88300] Updated weights for policy 1, policy_version 62152 (0.0009) -[2023-10-15 04:45:32,145][88300] Updated weights for policy 1, policy_version 62162 (0.0008) -[2023-10-15 04:45:32,508][88300] Updated weights for policy 1, policy_version 62172 (0.0008) -[2023-10-15 04:45:33,349][88298] Updated weights for policy 0, policy_version 61800 (0.0007) -[2023-10-15 04:45:33,534][87330] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 126943232. Throughput: 0: 1719.8, 1: 1779.7. Samples: 31741318. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:45:33,534][87330] Avg episode reward: [(0, '23.000'), (1, '22.270')] -[2023-10-15 04:45:33,727][88298] Updated weights for policy 0, policy_version 61810 (0.0008) -[2023-10-15 04:45:34,096][88298] Updated weights for policy 0, policy_version 61820 (0.0009) -[2023-10-15 04:45:36,540][88300] Updated weights for policy 1, policy_version 62182 (0.0009) -[2023-10-15 04:45:36,927][88300] Updated weights for policy 1, policy_version 62192 (0.0009) -[2023-10-15 04:45:37,299][88300] Updated weights for policy 1, policy_version 62202 (0.0008) -[2023-10-15 04:45:38,152][88298] Updated weights for policy 0, policy_version 61830 (0.0007) -[2023-10-15 04:45:38,517][88298] Updated weights for policy 0, policy_version 61840 (0.0008) -[2023-10-15 04:45:38,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 127008768. Throughput: 0: 1744.9, 1: 1757.3. Samples: 31761502. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-15 04:45:38,534][87330] Avg episode reward: [(0, '22.990'), (1, '22.480')] -[2023-10-15 04:45:38,885][88298] Updated weights for policy 0, policy_version 61850 (0.0008) -[2023-10-15 04:45:41,199][88300] Updated weights for policy 1, policy_version 62212 (0.0007) -[2023-10-15 04:45:41,554][88300] Updated weights for policy 1, policy_version 62222 (0.0010) -[2023-10-15 04:45:41,925][88300] Updated weights for policy 1, policy_version 62232 (0.0009) -[2023-10-15 04:45:42,778][88298] Updated weights for policy 0, policy_version 61860 (0.0007) -[2023-10-15 04:45:43,155][88298] Updated weights for policy 0, policy_version 61870 (0.0007) -[2023-10-15 04:45:43,523][88298] Updated weights for policy 0, policy_version 61880 (0.0007) -[2023-10-15 04:45:43,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 127074304. Throughput: 0: 1742.8, 1: 1747.1. Samples: 31782594. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-15 04:45:43,534][87330] Avg episode reward: [(0, '22.970'), (1, '22.460')] -[2023-10-15 04:45:45,697][88300] Updated weights for policy 1, policy_version 62242 (0.0010) -[2023-10-15 04:45:46,060][88300] Updated weights for policy 1, policy_version 62252 (0.0010) -[2023-10-15 04:45:46,437][88300] Updated weights for policy 1, policy_version 62262 (0.0010) -[2023-10-15 04:45:46,801][88300] Updated weights for policy 1, policy_version 62272 (0.0008) -[2023-10-15 04:45:47,205][88298] Updated weights for policy 0, policy_version 61890 (0.0008) -[2023-10-15 04:45:47,569][88298] Updated weights for policy 0, policy_version 61900 (0.0008) -[2023-10-15 04:45:47,941][88298] Updated weights for policy 0, policy_version 61910 (0.0007) -[2023-10-15 04:45:48,312][88298] Updated weights for policy 0, policy_version 61920 (0.0009) -[2023-10-15 04:45:48,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 127172608. Throughput: 0: 1735.8, 1: 1758.3. Samples: 31792814. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-15 04:45:48,534][87330] Avg episode reward: [(0, '22.940'), (1, '22.620')] -[2023-10-15 04:45:50,618][88300] Updated weights for policy 1, policy_version 62282 (0.0009) -[2023-10-15 04:45:50,990][88300] Updated weights for policy 1, policy_version 62292 (0.0008) -[2023-10-15 04:45:51,359][88300] Updated weights for policy 1, policy_version 62302 (0.0009) -[2023-10-15 04:45:52,328][88298] Updated weights for policy 0, policy_version 61930 (0.0008) -[2023-10-15 04:45:52,707][88298] Updated weights for policy 0, policy_version 61940 (0.0009) -[2023-10-15 04:45:53,079][88298] Updated weights for policy 0, policy_version 61950 (0.0009) -[2023-10-15 04:45:53,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 127238144. Throughput: 0: 1750.5, 1: 1739.8. Samples: 31813844. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-15 04:45:53,535][87330] Avg episode reward: [(0, '22.820'), (1, '22.680')] -[2023-10-15 04:45:55,223][88300] Updated weights for policy 1, policy_version 62312 (0.0011) -[2023-10-15 04:45:55,590][88300] Updated weights for policy 1, policy_version 62322 (0.0010) -[2023-10-15 04:45:55,959][88300] Updated weights for policy 1, policy_version 62332 (0.0008) -[2023-10-15 04:45:57,003][88298] Updated weights for policy 0, policy_version 61960 (0.0007) -[2023-10-15 04:45:57,367][88298] Updated weights for policy 0, policy_version 61970 (0.0009) -[2023-10-15 04:45:57,740][88298] Updated weights for policy 0, policy_version 61980 (0.0010) -[2023-10-15 04:45:58,534][87330] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 127303680. Throughput: 0: 1719.4, 1: 1749.4. Samples: 31834274. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-15 04:45:58,535][87330] Avg episode reward: [(0, '22.830'), (1, '22.660')] -[2023-10-15 04:45:59,926][88300] Updated weights for policy 1, policy_version 62342 (0.0009) -[2023-10-15 04:46:00,293][88300] Updated weights for policy 1, policy_version 62352 (0.0009) -[2023-10-15 04:46:00,656][88300] Updated weights for policy 1, policy_version 62362 (0.0009) -[2023-10-15 04:46:01,500][88298] Updated weights for policy 0, policy_version 61990 (0.0007) -[2023-10-15 04:46:01,873][88298] Updated weights for policy 0, policy_version 62000 (0.0007) -[2023-10-15 04:46:02,243][88298] Updated weights for policy 0, policy_version 62010 (0.0008) -[2023-10-15 04:46:03,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 127369216. Throughput: 0: 1747.7, 1: 1731.8. Samples: 31844948. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-15 04:46:03,534][87330] Avg episode reward: [(0, '22.800'), (1, '22.620')] -[2023-10-15 04:46:04,503][88300] Updated weights for policy 1, policy_version 62372 (0.0008) -[2023-10-15 04:46:04,866][88300] Updated weights for policy 1, policy_version 62382 (0.0008) -[2023-10-15 04:46:05,235][88300] Updated weights for policy 1, policy_version 62392 (0.0008) -[2023-10-15 04:46:06,146][88298] Updated weights for policy 0, policy_version 62020 (0.0009) -[2023-10-15 04:46:06,524][88298] Updated weights for policy 0, policy_version 62030 (0.0009) -[2023-10-15 04:46:06,893][88298] Updated weights for policy 0, policy_version 62040 (0.0008) -[2023-10-15 04:46:08,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 127434752. Throughput: 0: 1729.1, 1: 1731.4. Samples: 31865664. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-15 04:46:08,535][87330] Avg episode reward: [(0, '22.810'), (1, '22.710')] -[2023-10-15 04:46:09,357][88300] Updated weights for policy 1, policy_version 62402 (0.0010) -[2023-10-15 04:46:09,718][88300] Updated weights for policy 1, policy_version 62412 (0.0010) -[2023-10-15 04:46:10,091][88300] Updated weights for policy 1, policy_version 62422 (0.0008) -[2023-10-15 04:46:10,453][88300] Updated weights for policy 1, policy_version 62432 (0.0008) -[2023-10-15 04:46:10,701][88298] Updated weights for policy 0, policy_version 62050 (0.0008) -[2023-10-15 04:46:11,072][88298] Updated weights for policy 0, policy_version 62060 (0.0010) -[2023-10-15 04:46:11,440][88298] Updated weights for policy 0, policy_version 62070 (0.0009) -[2023-10-15 04:46:11,811][88298] Updated weights for policy 0, policy_version 62080 (0.0008) -[2023-10-15 04:46:13,534][87330] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 127500288. Throughput: 0: 1721.1, 1: 1760.2. Samples: 31887048. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-15 04:46:13,535][87330] Avg episode reward: [(0, '22.730'), (1, '22.750')] -[2023-10-15 04:46:14,266][88300] Updated weights for policy 1, policy_version 62442 (0.0009) -[2023-10-15 04:46:14,638][88300] Updated weights for policy 1, policy_version 62452 (0.0008) -[2023-10-15 04:46:15,010][88300] Updated weights for policy 1, policy_version 62462 (0.0010) -[2023-10-15 04:46:15,808][88298] Updated weights for policy 0, policy_version 62090 (0.0010) -[2023-10-15 04:46:16,182][88298] Updated weights for policy 0, policy_version 62100 (0.0008) -[2023-10-15 04:46:16,551][88298] Updated weights for policy 0, policy_version 62110 (0.0008) -[2023-10-15 04:46:18,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 127565824. Throughput: 0: 1744.9, 1: 1723.2. Samples: 31897384. Policy #0 lag: (min: 4.0, avg: 11.9, max: 36.0) -[2023-10-15 04:46:18,534][87330] Avg episode reward: [(0, '22.680'), (1, '22.740')] -[2023-10-15 04:46:18,879][88300] Updated weights for policy 1, policy_version 62472 (0.0007) -[2023-10-15 04:46:19,251][88300] Updated weights for policy 1, policy_version 62482 (0.0007) -[2023-10-15 04:46:19,614][88300] Updated weights for policy 1, policy_version 62492 (0.0007) -[2023-10-15 04:46:20,512][88298] Updated weights for policy 0, policy_version 62120 (0.0008) -[2023-10-15 04:46:20,888][88298] Updated weights for policy 0, policy_version 62130 (0.0010) -[2023-10-15 04:46:21,260][88298] Updated weights for policy 0, policy_version 62140 (0.0008) -[2023-10-15 04:46:23,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 127631360. Throughput: 0: 1728.4, 1: 1747.4. Samples: 31917912. Policy #0 lag: (min: 4.0, avg: 11.9, max: 36.0) -[2023-10-15 04:46:23,536][87330] Avg episode reward: [(0, '22.830'), (1, '22.740')] -[2023-10-15 04:46:23,635][88300] Updated weights for policy 1, policy_version 62502 (0.0009) -[2023-10-15 04:46:24,014][88300] Updated weights for policy 1, policy_version 62512 (0.0008) -[2023-10-15 04:46:24,385][88300] Updated weights for policy 1, policy_version 62522 (0.0008) -[2023-10-15 04:46:25,120][88298] Updated weights for policy 0, policy_version 62150 (0.0009) -[2023-10-15 04:46:25,494][88298] Updated weights for policy 0, policy_version 62160 (0.0009) -[2023-10-15 04:46:25,853][88298] Updated weights for policy 0, policy_version 62170 (0.0007) -[2023-10-15 04:46:28,287][88300] Updated weights for policy 1, policy_version 62532 (0.0008) -[2023-10-15 04:46:28,534][87330] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 127696896. Throughput: 0: 1727.7, 1: 1753.8. Samples: 31939264. Policy #0 lag: (min: 4.0, avg: 11.9, max: 36.0) -[2023-10-15 04:46:28,535][87330] Avg episode reward: [(0, '22.810'), (1, '22.760')] -[2023-10-15 04:46:28,651][88300] Updated weights for policy 1, policy_version 62542 (0.0007) -[2023-10-15 04:46:29,008][88300] Updated weights for policy 1, policy_version 62552 (0.0008) -[2023-10-15 04:46:29,825][88298] Updated weights for policy 0, policy_version 62180 (0.0008) -[2023-10-15 04:46:30,201][88298] Updated weights for policy 0, policy_version 62190 (0.0008) -[2023-10-15 04:46:30,561][88298] Updated weights for policy 0, policy_version 62200 (0.0010) -[2023-10-15 04:46:32,850][88300] Updated weights for policy 1, policy_version 62562 (0.0008) -[2023-10-15 04:46:33,211][88300] Updated weights for policy 1, policy_version 62572 (0.0007) -[2023-10-15 04:46:33,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 127762432. Throughput: 0: 1731.1, 1: 1739.1. Samples: 31948972. Policy #0 lag: (min: 4.0, avg: 11.9, max: 36.0) -[2023-10-15 04:46:33,535][87330] Avg episode reward: [(0, '22.840'), (1, '22.760')] -[2023-10-15 04:46:33,577][88300] Updated weights for policy 1, policy_version 62582 (0.0010) -[2023-10-15 04:46:33,946][88300] Updated weights for policy 1, policy_version 62592 (0.0010) -[2023-10-15 04:46:34,442][88298] Updated weights for policy 0, policy_version 62210 (0.0010) -[2023-10-15 04:46:34,814][88298] Updated weights for policy 0, policy_version 62220 (0.0009) -[2023-10-15 04:46:35,185][88298] Updated weights for policy 0, policy_version 62230 (0.0008) -[2023-10-15 04:46:35,548][88298] Updated weights for policy 0, policy_version 62240 (0.0008) -[2023-10-15 04:46:37,736][88300] Updated weights for policy 1, policy_version 62602 (0.0009) -[2023-10-15 04:46:38,112][88300] Updated weights for policy 1, policy_version 62612 (0.0008) -[2023-10-15 04:46:38,477][88300] Updated weights for policy 1, policy_version 62622 (0.0008) -[2023-10-15 04:46:38,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 127827968. Throughput: 0: 1723.6, 1: 1756.0. Samples: 31970424. Policy #0 lag: (min: 4.0, avg: 11.9, max: 36.0) -[2023-10-15 04:46:38,534][87330] Avg episode reward: [(0, '22.820'), (1, '22.790')] -[2023-10-15 04:46:39,388][88298] Updated weights for policy 0, policy_version 62250 (0.0009) -[2023-10-15 04:46:39,754][88298] Updated weights for policy 0, policy_version 62260 (0.0009) -[2023-10-15 04:46:40,123][88298] Updated weights for policy 0, policy_version 62270 (0.0007) -[2023-10-15 04:46:42,241][88300] Updated weights for policy 1, policy_version 62632 (0.0009) -[2023-10-15 04:46:42,597][88300] Updated weights for policy 1, policy_version 62642 (0.0008) -[2023-10-15 04:46:42,978][88300] Updated weights for policy 1, policy_version 62652 (0.0007) -[2023-10-15 04:46:43,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 127926272. Throughput: 0: 1752.3, 1: 1728.5. Samples: 31990910. Policy #0 lag: (min: 4.0, avg: 11.9, max: 36.0) -[2023-10-15 04:46:43,535][87330] Avg episode reward: [(0, '22.840'), (1, '22.590')] -[2023-10-15 04:46:44,008][88298] Updated weights for policy 0, policy_version 62280 (0.0009) -[2023-10-15 04:46:44,382][88298] Updated weights for policy 0, policy_version 62290 (0.0012) -[2023-10-15 04:46:44,760][88298] Updated weights for policy 0, policy_version 62300 (0.0010) -[2023-10-15 04:46:46,875][88300] Updated weights for policy 1, policy_version 62662 (0.0008) -[2023-10-15 04:46:47,253][88300] Updated weights for policy 1, policy_version 62672 (0.0009) -[2023-10-15 04:46:47,619][88300] Updated weights for policy 1, policy_version 62682 (0.0007) -[2023-10-15 04:46:48,534][87330] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 127991808. Throughput: 0: 1724.3, 1: 1761.8. Samples: 32001822. Policy #0 lag: (min: 4.0, avg: 11.9, max: 36.0) -[2023-10-15 04:46:48,534][87330] Avg episode reward: [(0, '22.870'), (1, '22.620')] -[2023-10-15 04:46:48,718][88298] Updated weights for policy 0, policy_version 62310 (0.0007) -[2023-10-15 04:46:49,088][88298] Updated weights for policy 0, policy_version 62320 (0.0010) -[2023-10-15 04:46:49,452][88298] Updated weights for policy 0, policy_version 62330 (0.0010) -[2023-10-15 04:46:51,335][88300] Updated weights for policy 1, policy_version 62692 (0.0008) -[2023-10-15 04:46:51,714][88300] Updated weights for policy 1, policy_version 62702 (0.0009) -[2023-10-15 04:46:52,082][88300] Updated weights for policy 1, policy_version 62712 (0.0009) -[2023-10-15 04:46:53,233][88298] Updated weights for policy 0, policy_version 62340 (0.0008) -[2023-10-15 04:46:53,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 128057344. Throughput: 0: 1739.5, 1: 1741.2. Samples: 32022294. Policy #0 lag: (min: 4.0, avg: 11.9, max: 36.0) -[2023-10-15 04:46:53,534][87330] Avg episode reward: [(0, '22.870'), (1, '22.650')] -[2023-10-15 04:46:53,605][88298] Updated weights for policy 0, policy_version 62350 (0.0008) -[2023-10-15 04:46:53,982][88298] Updated weights for policy 0, policy_version 62360 (0.0007) -[2023-10-15 04:46:56,125][88300] Updated weights for policy 1, policy_version 62722 (0.0010) -[2023-10-15 04:46:56,485][88300] Updated weights for policy 1, policy_version 62732 (0.0007) -[2023-10-15 04:46:56,850][88300] Updated weights for policy 1, policy_version 62742 (0.0007) -[2023-10-15 04:46:57,213][88300] Updated weights for policy 1, policy_version 62752 (0.0008) -[2023-10-15 04:46:57,920][88298] Updated weights for policy 0, policy_version 62370 (0.0010) -[2023-10-15 04:46:58,294][88298] Updated weights for policy 0, policy_version 62380 (0.0008) -[2023-10-15 04:46:58,534][87330] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 128122880. Throughput: 0: 1746.2, 1: 1731.3. Samples: 32043538. Policy #0 lag: (min: 4.0, avg: 11.9, max: 36.0) -[2023-10-15 04:46:58,535][87330] Avg episode reward: [(0, '22.890'), (1, '22.640')] -[2023-10-15 04:46:58,547][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000062752_64258048.pth... -[2023-10-15 04:46:58,582][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000061120_62586880.pth -[2023-10-15 04:46:58,658][88298] Updated weights for policy 0, policy_version 62390 (0.0007) -[2023-10-15 04:46:59,029][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000062400_63897600.pth... -[2023-10-15 04:46:59,030][88298] Updated weights for policy 0, policy_version 62400 (0.0007) -[2023-10-15 04:46:59,059][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000060768_62226432.pth -[2023-10-15 04:47:01,078][88300] Updated weights for policy 1, policy_version 62762 (0.0008) -[2023-10-15 04:47:01,440][88300] Updated weights for policy 1, policy_version 62772 (0.0008) -[2023-10-15 04:47:01,806][88300] Updated weights for policy 1, policy_version 62782 (0.0008) -[2023-10-15 04:47:02,940][88298] Updated weights for policy 0, policy_version 62410 (0.0013) -[2023-10-15 04:47:03,311][88298] Updated weights for policy 0, policy_version 62420 (0.0009) -[2023-10-15 04:47:03,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 128188416. Throughput: 0: 1725.0, 1: 1753.9. Samples: 32053934. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-10-15 04:47:03,534][87330] Avg episode reward: [(0, '22.870'), (1, '22.690')] -[2023-10-15 04:47:03,685][88298] Updated weights for policy 0, policy_version 62430 (0.0009) -[2023-10-15 04:47:05,684][88300] Updated weights for policy 1, policy_version 62792 (0.0010) -[2023-10-15 04:47:06,043][88300] Updated weights for policy 1, policy_version 62802 (0.0010) -[2023-10-15 04:47:06,419][88300] Updated weights for policy 1, policy_version 62812 (0.0009) -[2023-10-15 04:47:07,846][88298] Updated weights for policy 0, policy_version 62440 (0.0009) -[2023-10-15 04:47:08,230][88298] Updated weights for policy 0, policy_version 62450 (0.0008) -[2023-10-15 04:47:08,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 128253952. Throughput: 0: 1749.7, 1: 1735.4. Samples: 32074744. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-10-15 04:47:08,535][87330] Avg episode reward: [(0, '22.860'), (1, '22.550')] -[2023-10-15 04:47:08,599][88298] Updated weights for policy 0, policy_version 62460 (0.0008) -[2023-10-15 04:47:10,399][88300] Updated weights for policy 1, policy_version 62822 (0.0010) -[2023-10-15 04:47:10,782][88300] Updated weights for policy 1, policy_version 62832 (0.0009) -[2023-10-15 04:47:11,149][88300] Updated weights for policy 1, policy_version 62842 (0.0009) -[2023-10-15 04:47:12,540][88298] Updated weights for policy 0, policy_version 62470 (0.0009) -[2023-10-15 04:47:12,905][88298] Updated weights for policy 0, policy_version 62480 (0.0007) -[2023-10-15 04:47:13,280][88298] Updated weights for policy 0, policy_version 62490 (0.0009) -[2023-10-15 04:47:13,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 128352256. Throughput: 0: 1738.2, 1: 1738.8. Samples: 32095730. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-10-15 04:47:13,534][87330] Avg episode reward: [(0, '22.890'), (1, '22.640')] -[2023-10-15 04:47:14,898][88300] Updated weights for policy 1, policy_version 62852 (0.0008) -[2023-10-15 04:47:15,263][88300] Updated weights for policy 1, policy_version 62862 (0.0008) -[2023-10-15 04:47:15,637][88300] Updated weights for policy 1, policy_version 62872 (0.0008) -[2023-10-15 04:47:17,030][88298] Updated weights for policy 0, policy_version 62500 (0.0010) -[2023-10-15 04:47:17,398][88298] Updated weights for policy 0, policy_version 62510 (0.0010) -[2023-10-15 04:47:17,765][88298] Updated weights for policy 0, policy_version 62520 (0.0010) -[2023-10-15 04:47:18,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 128417792. Throughput: 0: 1748.2, 1: 1741.6. Samples: 32106014. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-10-15 04:47:18,535][87330] Avg episode reward: [(0, '22.890'), (1, '22.620')] -[2023-10-15 04:47:19,458][88300] Updated weights for policy 1, policy_version 62882 (0.0008) -[2023-10-15 04:47:19,830][88300] Updated weights for policy 1, policy_version 62892 (0.0011) -[2023-10-15 04:47:20,189][88300] Updated weights for policy 1, policy_version 62902 (0.0009) -[2023-10-15 04:47:20,561][88300] Updated weights for policy 1, policy_version 62912 (0.0007) -[2023-10-15 04:47:21,759][88298] Updated weights for policy 0, policy_version 62530 (0.0010) -[2023-10-15 04:47:22,134][88298] Updated weights for policy 0, policy_version 62540 (0.0010) -[2023-10-15 04:47:22,495][88298] Updated weights for policy 0, policy_version 62550 (0.0009) -[2023-10-15 04:47:22,861][88298] Updated weights for policy 0, policy_version 62560 (0.0009) -[2023-10-15 04:47:23,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 128483328. Throughput: 0: 1744.1, 1: 1744.1. Samples: 32127394. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-10-15 04:47:23,534][87330] Avg episode reward: [(0, '22.490'), (1, '22.400')] -[2023-10-15 04:47:24,381][88300] Updated weights for policy 1, policy_version 62922 (0.0007) -[2023-10-15 04:47:24,744][88300] Updated weights for policy 1, policy_version 62932 (0.0009) -[2023-10-15 04:47:25,112][88300] Updated weights for policy 1, policy_version 62942 (0.0008) -[2023-10-15 04:47:26,768][88298] Updated weights for policy 0, policy_version 62570 (0.0010) -[2023-10-15 04:47:27,133][88298] Updated weights for policy 0, policy_version 62580 (0.0009) -[2023-10-15 04:47:27,496][88298] Updated weights for policy 0, policy_version 62590 (0.0009) -[2023-10-15 04:47:28,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 128548864. Throughput: 0: 1713.7, 1: 1775.3. Samples: 32147918. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-10-15 04:47:28,534][87330] Avg episode reward: [(0, '22.280'), (1, '22.430')] -[2023-10-15 04:47:28,994][88300] Updated weights for policy 1, policy_version 62952 (0.0007) -[2023-10-15 04:47:29,357][88300] Updated weights for policy 1, policy_version 62962 (0.0007) -[2023-10-15 04:47:29,724][88300] Updated weights for policy 1, policy_version 62972 (0.0007) -[2023-10-15 04:47:31,358][88298] Updated weights for policy 0, policy_version 62600 (0.0010) -[2023-10-15 04:47:31,729][88298] Updated weights for policy 0, policy_version 62610 (0.0009) -[2023-10-15 04:47:32,091][88298] Updated weights for policy 0, policy_version 62620 (0.0008) -[2023-10-15 04:47:33,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 128614400. Throughput: 0: 1745.8, 1: 1746.9. Samples: 32158994. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-10-15 04:47:33,535][87330] Avg episode reward: [(0, '22.270'), (1, '22.480')] -[2023-10-15 04:47:33,641][88300] Updated weights for policy 1, policy_version 62982 (0.0007) -[2023-10-15 04:47:34,004][88300] Updated weights for policy 1, policy_version 62992 (0.0008) -[2023-10-15 04:47:34,361][88300] Updated weights for policy 1, policy_version 63002 (0.0008) -[2023-10-15 04:47:35,960][88298] Updated weights for policy 0, policy_version 62630 (0.0007) -[2023-10-15 04:47:36,326][88298] Updated weights for policy 0, policy_version 62640 (0.0007) -[2023-10-15 04:47:36,695][88298] Updated weights for policy 0, policy_version 62650 (0.0009) -[2023-10-15 04:47:38,225][88300] Updated weights for policy 1, policy_version 63012 (0.0010) -[2023-10-15 04:47:38,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 128679936. Throughput: 0: 1725.9, 1: 1769.0. Samples: 32179564. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-10-15 04:47:38,534][87330] Avg episode reward: [(0, '22.100'), (1, '22.620')] -[2023-10-15 04:47:38,604][88300] Updated weights for policy 1, policy_version 63022 (0.0009) -[2023-10-15 04:47:38,973][88300] Updated weights for policy 1, policy_version 63032 (0.0008) -[2023-10-15 04:47:40,562][88298] Updated weights for policy 0, policy_version 62660 (0.0007) -[2023-10-15 04:47:40,929][88298] Updated weights for policy 0, policy_version 62670 (0.0009) -[2023-10-15 04:47:41,295][88298] Updated weights for policy 0, policy_version 62680 (0.0009) -[2023-10-15 04:47:42,736][88300] Updated weights for policy 1, policy_version 63042 (0.0007) -[2023-10-15 04:47:43,105][88300] Updated weights for policy 1, policy_version 63052 (0.0008) -[2023-10-15 04:47:43,464][88300] Updated weights for policy 1, policy_version 63062 (0.0008) -[2023-10-15 04:47:43,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 128745472. Throughput: 0: 1717.9, 1: 1768.1. Samples: 32200406. Policy #0 lag: (min: 8.0, avg: 35.2, max: 40.0) -[2023-10-15 04:47:43,534][87330] Avg episode reward: [(0, '22.090'), (1, '22.540')] -[2023-10-15 04:47:43,830][88300] Updated weights for policy 1, policy_version 63072 (0.0009) -[2023-10-15 04:47:45,306][88298] Updated weights for policy 0, policy_version 62690 (0.0008) -[2023-10-15 04:47:45,670][88298] Updated weights for policy 0, policy_version 62700 (0.0010) -[2023-10-15 04:47:46,043][88298] Updated weights for policy 0, policy_version 62710 (0.0009) -[2023-10-15 04:47:46,415][88298] Updated weights for policy 0, policy_version 62720 (0.0009) -[2023-10-15 04:47:47,577][88300] Updated weights for policy 1, policy_version 63082 (0.0009) -[2023-10-15 04:47:47,943][88300] Updated weights for policy 1, policy_version 63092 (0.0009) -[2023-10-15 04:47:48,312][88300] Updated weights for policy 1, policy_version 63102 (0.0008) -[2023-10-15 04:47:48,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 128843776. Throughput: 0: 1734.4, 1: 1760.8. Samples: 32211216. Policy #0 lag: (min: 8.0, avg: 35.2, max: 40.0) -[2023-10-15 04:47:48,534][87330] Avg episode reward: [(0, '22.050'), (1, '22.590')] -[2023-10-15 04:47:50,377][88298] Updated weights for policy 0, policy_version 62730 (0.0007) -[2023-10-15 04:47:50,750][88298] Updated weights for policy 0, policy_version 62740 (0.0007) -[2023-10-15 04:47:51,116][88298] Updated weights for policy 0, policy_version 62750 (0.0008) -[2023-10-15 04:47:52,315][88300] Updated weights for policy 1, policy_version 63112 (0.0008) -[2023-10-15 04:47:52,682][88300] Updated weights for policy 1, policy_version 63122 (0.0008) -[2023-10-15 04:47:53,054][88300] Updated weights for policy 1, policy_version 63132 (0.0007) -[2023-10-15 04:47:53,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 128909312. Throughput: 0: 1714.8, 1: 1772.0. Samples: 32231650. Policy #0 lag: (min: 8.0, avg: 35.2, max: 40.0) -[2023-10-15 04:47:53,534][87330] Avg episode reward: [(0, '22.460'), (1, '22.830')] -[2023-10-15 04:47:55,116][88298] Updated weights for policy 0, policy_version 62760 (0.0010) -[2023-10-15 04:47:55,488][88298] Updated weights for policy 0, policy_version 62770 (0.0008) -[2023-10-15 04:47:55,864][88298] Updated weights for policy 0, policy_version 62780 (0.0007) -[2023-10-15 04:47:57,035][88300] Updated weights for policy 1, policy_version 63142 (0.0010) -[2023-10-15 04:47:57,423][88300] Updated weights for policy 1, policy_version 63152 (0.0010) -[2023-10-15 04:47:57,784][88300] Updated weights for policy 1, policy_version 63162 (0.0008) -[2023-10-15 04:47:58,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 128974848. Throughput: 0: 1732.9, 1: 1741.5. Samples: 32252080. Policy #0 lag: (min: 8.0, avg: 35.2, max: 40.0) -[2023-10-15 04:47:58,535][87330] Avg episode reward: [(0, '22.630'), (1, '22.820')] -[2023-10-15 04:47:59,547][88298] Updated weights for policy 0, policy_version 62790 (0.0008) -[2023-10-15 04:47:59,910][88298] Updated weights for policy 0, policy_version 62800 (0.0010) -[2023-10-15 04:48:00,284][88298] Updated weights for policy 0, policy_version 62810 (0.0009) -[2023-10-15 04:48:01,555][88300] Updated weights for policy 1, policy_version 63172 (0.0008) -[2023-10-15 04:48:01,933][88300] Updated weights for policy 1, policy_version 63182 (0.0009) -[2023-10-15 04:48:02,296][88300] Updated weights for policy 1, policy_version 63192 (0.0010) -[2023-10-15 04:48:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 129040384. Throughput: 0: 1714.2, 1: 1774.6. Samples: 32263012. Policy #0 lag: (min: 8.0, avg: 35.2, max: 40.0) -[2023-10-15 04:48:03,534][87330] Avg episode reward: [(0, '22.650'), (1, '22.850')] -[2023-10-15 04:48:04,215][88298] Updated weights for policy 0, policy_version 62820 (0.0008) -[2023-10-15 04:48:04,581][88298] Updated weights for policy 0, policy_version 62830 (0.0008) -[2023-10-15 04:48:04,947][88298] Updated weights for policy 0, policy_version 62840 (0.0008) -[2023-10-15 04:48:06,052][88300] Updated weights for policy 1, policy_version 63202 (0.0007) -[2023-10-15 04:48:06,416][88300] Updated weights for policy 1, policy_version 63212 (0.0007) -[2023-10-15 04:48:06,785][88300] Updated weights for policy 1, policy_version 63222 (0.0007) -[2023-10-15 04:48:07,149][88300] Updated weights for policy 1, policy_version 63232 (0.0007) -[2023-10-15 04:48:08,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 129105920. Throughput: 0: 1723.7, 1: 1742.3. Samples: 32283364. Policy #0 lag: (min: 8.0, avg: 35.2, max: 40.0) -[2023-10-15 04:48:08,534][87330] Avg episode reward: [(0, '22.470'), (1, '22.860')] -[2023-10-15 04:48:08,680][88298] Updated weights for policy 0, policy_version 62850 (0.0008) -[2023-10-15 04:48:09,051][88298] Updated weights for policy 0, policy_version 62860 (0.0009) -[2023-10-15 04:48:09,421][88298] Updated weights for policy 0, policy_version 62870 (0.0008) -[2023-10-15 04:48:09,799][88298] Updated weights for policy 0, policy_version 62880 (0.0009) -[2023-10-15 04:48:11,084][88300] Updated weights for policy 1, policy_version 63242 (0.0010) -[2023-10-15 04:48:11,454][88300] Updated weights for policy 1, policy_version 63252 (0.0007) -[2023-10-15 04:48:11,814][88300] Updated weights for policy 1, policy_version 63262 (0.0011) -[2023-10-15 04:48:13,534][87330] Fps is (10 sec: 13106.7, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 129171456. Throughput: 0: 1755.2, 1: 1734.9. Samples: 32304974. Policy #0 lag: (min: 8.0, avg: 35.2, max: 40.0) -[2023-10-15 04:48:13,536][87330] Avg episode reward: [(0, '22.600'), (1, '22.650')] -[2023-10-15 04:48:13,889][88298] Updated weights for policy 0, policy_version 62890 (0.0007) -[2023-10-15 04:48:14,253][88298] Updated weights for policy 0, policy_version 62900 (0.0010) -[2023-10-15 04:48:14,625][88298] Updated weights for policy 0, policy_version 62910 (0.0008) -[2023-10-15 04:48:15,729][88300] Updated weights for policy 1, policy_version 63272 (0.0009) -[2023-10-15 04:48:16,098][88300] Updated weights for policy 1, policy_version 63282 (0.0010) -[2023-10-15 04:48:16,463][88300] Updated weights for policy 1, policy_version 63292 (0.0007) -[2023-10-15 04:48:18,531][88298] Updated weights for policy 0, policy_version 62920 (0.0008) -[2023-10-15 04:48:18,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 129236992. Throughput: 0: 1720.7, 1: 1745.9. Samples: 32314992. Policy #0 lag: (min: 8.0, avg: 35.2, max: 40.0) -[2023-10-15 04:48:18,534][87330] Avg episode reward: [(0, '22.720'), (1, '22.700')] -[2023-10-15 04:48:18,890][88298] Updated weights for policy 0, policy_version 62930 (0.0008) -[2023-10-15 04:48:19,259][88298] Updated weights for policy 0, policy_version 62940 (0.0009) -[2023-10-15 04:48:20,237][88300] Updated weights for policy 1, policy_version 63302 (0.0008) -[2023-10-15 04:48:20,602][88300] Updated weights for policy 1, policy_version 63312 (0.0007) -[2023-10-15 04:48:20,970][88300] Updated weights for policy 1, policy_version 63322 (0.0007) -[2023-10-15 04:48:23,247][88298] Updated weights for policy 0, policy_version 62950 (0.0009) -[2023-10-15 04:48:23,534][87330] Fps is (10 sec: 13107.8, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 129302528. Throughput: 0: 1738.4, 1: 1741.0. Samples: 32336134. Policy #0 lag: (min: 8.0, avg: 35.2, max: 40.0) -[2023-10-15 04:48:23,534][87330] Avg episode reward: [(0, '22.670'), (1, '22.740')] -[2023-10-15 04:48:23,623][88298] Updated weights for policy 0, policy_version 62960 (0.0011) -[2023-10-15 04:48:23,990][88298] Updated weights for policy 0, policy_version 62970 (0.0010) -[2023-10-15 04:48:24,679][88300] Updated weights for policy 1, policy_version 63332 (0.0010) -[2023-10-15 04:48:25,047][88300] Updated weights for policy 1, policy_version 63342 (0.0010) -[2023-10-15 04:48:25,403][88300] Updated weights for policy 1, policy_version 63352 (0.0009) -[2023-10-15 04:48:28,024][88298] Updated weights for policy 0, policy_version 62980 (0.0010) -[2023-10-15 04:48:28,388][88298] Updated weights for policy 0, policy_version 62990 (0.0007) -[2023-10-15 04:48:28,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 129368064. Throughput: 0: 1743.9, 1: 1758.4. Samples: 32358008. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-15 04:48:28,535][87330] Avg episode reward: [(0, '22.660'), (1, '22.710')] -[2023-10-15 04:48:28,766][88298] Updated weights for policy 0, policy_version 63000 (0.0009) -[2023-10-15 04:48:29,241][88300] Updated weights for policy 1, policy_version 63362 (0.0008) -[2023-10-15 04:48:29,607][88300] Updated weights for policy 1, policy_version 63372 (0.0009) -[2023-10-15 04:48:29,969][88300] Updated weights for policy 1, policy_version 63382 (0.0007) -[2023-10-15 04:48:30,324][88300] Updated weights for policy 1, policy_version 63392 (0.0007) -[2023-10-15 04:48:32,505][88298] Updated weights for policy 0, policy_version 63010 (0.0008) -[2023-10-15 04:48:32,866][88298] Updated weights for policy 0, policy_version 63020 (0.0008) -[2023-10-15 04:48:33,247][88298] Updated weights for policy 0, policy_version 63030 (0.0011) -[2023-10-15 04:48:33,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 129433600. Throughput: 0: 1731.5, 1: 1747.7. Samples: 32367784. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-15 04:48:33,535][87330] Avg episode reward: [(0, '22.670'), (1, '22.680')] -[2023-10-15 04:48:33,622][88298] Updated weights for policy 0, policy_version 63040 (0.0009) -[2023-10-15 04:48:34,135][88300] Updated weights for policy 1, policy_version 63402 (0.0009) -[2023-10-15 04:48:34,509][88300] Updated weights for policy 1, policy_version 63412 (0.0008) -[2023-10-15 04:48:34,881][88300] Updated weights for policy 1, policy_version 63422 (0.0008) -[2023-10-15 04:48:37,475][88298] Updated weights for policy 0, policy_version 63050 (0.0009) -[2023-10-15 04:48:37,840][88298] Updated weights for policy 0, policy_version 63060 (0.0008) -[2023-10-15 04:48:38,212][88298] Updated weights for policy 0, policy_version 63070 (0.0007) -[2023-10-15 04:48:38,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 129531904. Throughput: 0: 1751.0, 1: 1755.2. Samples: 32389428. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-15 04:48:38,535][87330] Avg episode reward: [(0, '22.490'), (1, '22.680')] -[2023-10-15 04:48:38,683][88300] Updated weights for policy 1, policy_version 63432 (0.0010) -[2023-10-15 04:48:39,045][88300] Updated weights for policy 1, policy_version 63442 (0.0008) -[2023-10-15 04:48:39,426][88300] Updated weights for policy 1, policy_version 63452 (0.0009) -[2023-10-15 04:48:42,476][88298] Updated weights for policy 0, policy_version 63080 (0.0008) -[2023-10-15 04:48:42,857][88298] Updated weights for policy 0, policy_version 63090 (0.0008) -[2023-10-15 04:48:43,225][88298] Updated weights for policy 0, policy_version 63100 (0.0009) -[2023-10-15 04:48:43,361][88300] Updated weights for policy 1, policy_version 63462 (0.0007) -[2023-10-15 04:48:43,534][87330] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 129597440. Throughput: 0: 1728.0, 1: 1785.3. Samples: 32410176. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-15 04:48:43,534][87330] Avg episode reward: [(0, '22.660'), (1, '22.700')] -[2023-10-15 04:48:43,751][88300] Updated weights for policy 1, policy_version 63472 (0.0010) -[2023-10-15 04:48:44,117][88300] Updated weights for policy 1, policy_version 63482 (0.0010) -[2023-10-15 04:48:47,183][88298] Updated weights for policy 0, policy_version 63110 (0.0008) -[2023-10-15 04:48:47,562][88298] Updated weights for policy 0, policy_version 63120 (0.0009) -[2023-10-15 04:48:47,930][88298] Updated weights for policy 0, policy_version 63130 (0.0010) -[2023-10-15 04:48:48,002][88300] Updated weights for policy 1, policy_version 63492 (0.0010) -[2023-10-15 04:48:48,374][88300] Updated weights for policy 1, policy_version 63502 (0.0010) -[2023-10-15 04:48:48,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 129662976. Throughput: 0: 1746.9, 1: 1750.4. Samples: 32420392. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-15 04:48:48,535][87330] Avg episode reward: [(0, '22.640'), (1, '22.900')] -[2023-10-15 04:48:48,732][88300] Updated weights for policy 1, policy_version 63512 (0.0009) -[2023-10-15 04:48:51,705][88298] Updated weights for policy 0, policy_version 63140 (0.0009) -[2023-10-15 04:48:52,073][88298] Updated weights for policy 0, policy_version 63150 (0.0010) -[2023-10-15 04:48:52,449][88298] Updated weights for policy 0, policy_version 63160 (0.0008) -[2023-10-15 04:48:52,634][88300] Updated weights for policy 1, policy_version 63522 (0.0007) -[2023-10-15 04:48:52,999][88300] Updated weights for policy 1, policy_version 63532 (0.0007) -[2023-10-15 04:48:53,369][88300] Updated weights for policy 1, policy_version 63542 (0.0007) -[2023-10-15 04:48:53,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 129728512. Throughput: 0: 1738.5, 1: 1780.9. Samples: 32441738. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-15 04:48:53,534][87330] Avg episode reward: [(0, '22.620'), (1, '22.950')] -[2023-10-15 04:48:53,731][88300] Updated weights for policy 1, policy_version 63552 (0.0007) -[2023-10-15 04:48:56,360][88298] Updated weights for policy 0, policy_version 63170 (0.0007) -[2023-10-15 04:48:56,728][88298] Updated weights for policy 0, policy_version 63180 (0.0008) -[2023-10-15 04:48:57,093][88298] Updated weights for policy 0, policy_version 63190 (0.0008) -[2023-10-15 04:48:57,461][88298] Updated weights for policy 0, policy_version 63200 (0.0008) -[2023-10-15 04:48:57,611][88300] Updated weights for policy 1, policy_version 63562 (0.0009) -[2023-10-15 04:48:57,993][88300] Updated weights for policy 1, policy_version 63572 (0.0009) -[2023-10-15 04:48:58,360][88300] Updated weights for policy 1, policy_version 63582 (0.0007) -[2023-10-15 04:48:58,534][87330] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 129826816. Throughput: 0: 1707.0, 1: 1767.5. Samples: 32461324. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-15 04:48:58,535][87330] Avg episode reward: [(0, '22.650'), (1, '22.920')] -[2023-10-15 04:48:58,548][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000063200_64716800.pth... -[2023-10-15 04:48:58,548][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000063584_65110016.pth... -[2023-10-15 04:48:58,584][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000061568_63045632.pth -[2023-10-15 04:48:58,586][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000061920_63406080.pth -[2023-10-15 04:49:01,413][88298] Updated weights for policy 0, policy_version 63210 (0.0007) -[2023-10-15 04:49:01,785][88298] Updated weights for policy 0, policy_version 63220 (0.0009) -[2023-10-15 04:49:02,153][88298] Updated weights for policy 0, policy_version 63230 (0.0007) -[2023-10-15 04:49:02,195][88300] Updated weights for policy 1, policy_version 63592 (0.0007) -[2023-10-15 04:49:02,557][88300] Updated weights for policy 1, policy_version 63602 (0.0007) -[2023-10-15 04:49:02,931][88300] Updated weights for policy 1, policy_version 63612 (0.0010) -[2023-10-15 04:49:03,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 129892352. Throughput: 0: 1738.4, 1: 1778.7. Samples: 32473262. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-15 04:49:03,535][87330] Avg episode reward: [(0, '22.650'), (1, '22.820')] -[2023-10-15 04:49:06,037][88298] Updated weights for policy 0, policy_version 63240 (0.0009) -[2023-10-15 04:49:06,407][88298] Updated weights for policy 0, policy_version 63250 (0.0008) -[2023-10-15 04:49:06,756][88300] Updated weights for policy 1, policy_version 63622 (0.0008) -[2023-10-15 04:49:06,783][88298] Updated weights for policy 0, policy_version 63260 (0.0008) -[2023-10-15 04:49:07,118][88300] Updated weights for policy 1, policy_version 63632 (0.0010) -[2023-10-15 04:49:07,488][88300] Updated weights for policy 1, policy_version 63642 (0.0009) -[2023-10-15 04:49:08,534][87330] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 129957888. Throughput: 0: 1721.1, 1: 1766.3. Samples: 32493066. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:49:08,534][87330] Avg episode reward: [(0, '22.600'), (1, '22.840')] -[2023-10-15 04:49:10,726][88298] Updated weights for policy 0, policy_version 63270 (0.0010) -[2023-10-15 04:49:11,099][88298] Updated weights for policy 0, policy_version 63280 (0.0009) -[2023-10-15 04:49:11,283][88300] Updated weights for policy 1, policy_version 63652 (0.0007) -[2023-10-15 04:49:11,473][88298] Updated weights for policy 0, policy_version 63290 (0.0008) -[2023-10-15 04:49:11,657][88300] Updated weights for policy 1, policy_version 63662 (0.0009) -[2023-10-15 04:49:12,021][88300] Updated weights for policy 1, policy_version 63672 (0.0010) -[2023-10-15 04:49:13,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.6, 300 sec: 13995.8). Total num frames: 130023424. Throughput: 0: 1718.5, 1: 1747.1. Samples: 32513958. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:49:13,534][87330] Avg episode reward: [(0, '22.780'), (1, '22.830')] -[2023-10-15 04:49:15,354][88298] Updated weights for policy 0, policy_version 63300 (0.0008) -[2023-10-15 04:49:15,730][88298] Updated weights for policy 0, policy_version 63310 (0.0007) -[2023-10-15 04:49:16,000][88300] Updated weights for policy 1, policy_version 63682 (0.0008) -[2023-10-15 04:49:16,099][88298] Updated weights for policy 0, policy_version 63320 (0.0008) -[2023-10-15 04:49:16,360][88300] Updated weights for policy 1, policy_version 63692 (0.0007) -[2023-10-15 04:49:16,735][88300] Updated weights for policy 1, policy_version 63702 (0.0008) -[2023-10-15 04:49:17,096][88300] Updated weights for policy 1, policy_version 63712 (0.0007) -[2023-10-15 04:49:18,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 130088960. Throughput: 0: 1732.4, 1: 1768.1. Samples: 32525308. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:49:18,535][87330] Avg episode reward: [(0, '22.810'), (1, '22.800')] -[2023-10-15 04:49:19,950][88298] Updated weights for policy 0, policy_version 63330 (0.0008) -[2023-10-15 04:49:20,327][88298] Updated weights for policy 0, policy_version 63340 (0.0007) -[2023-10-15 04:49:20,692][88298] Updated weights for policy 0, policy_version 63350 (0.0008) -[2023-10-15 04:49:21,066][88298] Updated weights for policy 0, policy_version 63360 (0.0009) -[2023-10-15 04:49:21,074][88300] Updated weights for policy 1, policy_version 63722 (0.0008) -[2023-10-15 04:49:21,434][88300] Updated weights for policy 1, policy_version 63732 (0.0008) -[2023-10-15 04:49:21,804][88300] Updated weights for policy 1, policy_version 63742 (0.0009) -[2023-10-15 04:49:23,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 130154496. Throughput: 0: 1718.8, 1: 1736.4. Samples: 32544916. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:49:23,535][87330] Avg episode reward: [(0, '22.890'), (1, '22.670')] -[2023-10-15 04:49:24,926][88298] Updated weights for policy 0, policy_version 63370 (0.0008) -[2023-10-15 04:49:25,294][88298] Updated weights for policy 0, policy_version 63380 (0.0008) -[2023-10-15 04:49:25,673][88298] Updated weights for policy 0, policy_version 63390 (0.0008) -[2023-10-15 04:49:25,853][88300] Updated weights for policy 1, policy_version 63752 (0.0007) -[2023-10-15 04:49:26,226][88300] Updated weights for policy 1, policy_version 63762 (0.0007) -[2023-10-15 04:49:26,585][88300] Updated weights for policy 1, policy_version 63772 (0.0010) -[2023-10-15 04:49:28,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 130220032. Throughput: 0: 1739.5, 1: 1737.5. Samples: 32566642. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:49:28,535][87330] Avg episode reward: [(0, '22.880'), (1, '22.530')] -[2023-10-15 04:49:29,571][88298] Updated weights for policy 0, policy_version 63400 (0.0008) -[2023-10-15 04:49:29,949][88298] Updated weights for policy 0, policy_version 63410 (0.0008) -[2023-10-15 04:49:30,322][88298] Updated weights for policy 0, policy_version 63420 (0.0008) -[2023-10-15 04:49:30,412][88300] Updated weights for policy 1, policy_version 63782 (0.0010) -[2023-10-15 04:49:30,807][88300] Updated weights for policy 1, policy_version 63792 (0.0008) -[2023-10-15 04:49:31,169][88300] Updated weights for policy 1, policy_version 63802 (0.0010) -[2023-10-15 04:49:33,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 130285568. Throughput: 0: 1721.1, 1: 1743.9. Samples: 32576316. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:49:33,534][87330] Avg episode reward: [(0, '22.850'), (1, '22.540')] -[2023-10-15 04:49:34,362][88298] Updated weights for policy 0, policy_version 63430 (0.0008) -[2023-10-15 04:49:34,735][88298] Updated weights for policy 0, policy_version 63440 (0.0009) -[2023-10-15 04:49:35,088][88300] Updated weights for policy 1, policy_version 63812 (0.0008) -[2023-10-15 04:49:35,100][88298] Updated weights for policy 0, policy_version 63450 (0.0010) -[2023-10-15 04:49:35,448][88300] Updated weights for policy 1, policy_version 63822 (0.0009) -[2023-10-15 04:49:35,824][88300] Updated weights for policy 1, policy_version 63832 (0.0011) -[2023-10-15 04:49:38,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 130351104. Throughput: 0: 1727.0, 1: 1734.9. Samples: 32597526. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:49:38,534][87330] Avg episode reward: [(0, '22.880'), (1, '22.500')] -[2023-10-15 04:49:38,959][88298] Updated weights for policy 0, policy_version 63460 (0.0009) -[2023-10-15 04:49:39,324][88298] Updated weights for policy 0, policy_version 63470 (0.0008) -[2023-10-15 04:49:39,580][88300] Updated weights for policy 1, policy_version 63842 (0.0007) -[2023-10-15 04:49:39,696][88298] Updated weights for policy 0, policy_version 63480 (0.0008) -[2023-10-15 04:49:39,952][88300] Updated weights for policy 1, policy_version 63852 (0.0007) -[2023-10-15 04:49:40,324][88300] Updated weights for policy 1, policy_version 63862 (0.0008) -[2023-10-15 04:49:40,690][88300] Updated weights for policy 1, policy_version 63872 (0.0008) -[2023-10-15 04:49:43,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 130416640. Throughput: 0: 1760.5, 1: 1750.5. Samples: 32619318. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:49:43,534][87330] Avg episode reward: [(0, '22.900'), (1, '22.170')] -[2023-10-15 04:49:43,586][88298] Updated weights for policy 0, policy_version 63490 (0.0008) -[2023-10-15 04:49:43,950][88298] Updated weights for policy 0, policy_version 63500 (0.0008) -[2023-10-15 04:49:44,321][88298] Updated weights for policy 0, policy_version 63510 (0.0008) -[2023-10-15 04:49:44,610][88300] Updated weights for policy 1, policy_version 63882 (0.0008) -[2023-10-15 04:49:44,685][88298] Updated weights for policy 0, policy_version 63520 (0.0008) -[2023-10-15 04:49:44,975][88300] Updated weights for policy 1, policy_version 63892 (0.0009) -[2023-10-15 04:49:45,339][88300] Updated weights for policy 1, policy_version 63902 (0.0007) -[2023-10-15 04:49:48,532][88298] Updated weights for policy 0, policy_version 63530 (0.0009) -[2023-10-15 04:49:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 130482176. Throughput: 0: 1733.3, 1: 1727.7. Samples: 32629010. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:49:48,534][87330] Avg episode reward: [(0, '22.920'), (1, '22.200')] -[2023-10-15 04:49:48,893][88298] Updated weights for policy 0, policy_version 63540 (0.0008) -[2023-10-15 04:49:49,165][88300] Updated weights for policy 1, policy_version 63912 (0.0008) -[2023-10-15 04:49:49,261][88298] Updated weights for policy 0, policy_version 63550 (0.0007) -[2023-10-15 04:49:49,529][88300] Updated weights for policy 1, policy_version 63922 (0.0010) -[2023-10-15 04:49:49,892][88300] Updated weights for policy 1, policy_version 63932 (0.0009) -[2023-10-15 04:49:53,208][88298] Updated weights for policy 0, policy_version 63560 (0.0008) -[2023-10-15 04:49:53,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 130547712. Throughput: 0: 1753.0, 1: 1741.6. Samples: 32650320. Policy #0 lag: (min: 31.0, avg: 46.0, max: 63.0) -[2023-10-15 04:49:53,534][87330] Avg episode reward: [(0, '22.930'), (1, '22.280')] -[2023-10-15 04:49:53,587][88298] Updated weights for policy 0, policy_version 63570 (0.0007) -[2023-10-15 04:49:53,792][88300] Updated weights for policy 1, policy_version 63942 (0.0009) -[2023-10-15 04:49:53,948][88298] Updated weights for policy 0, policy_version 63580 (0.0009) -[2023-10-15 04:49:54,153][88300] Updated weights for policy 1, policy_version 63952 (0.0007) -[2023-10-15 04:49:54,530][88300] Updated weights for policy 1, policy_version 63962 (0.0007) -[2023-10-15 04:49:57,647][88298] Updated weights for policy 0, policy_version 63590 (0.0010) -[2023-10-15 04:49:58,016][88298] Updated weights for policy 0, policy_version 63600 (0.0009) -[2023-10-15 04:49:58,392][88298] Updated weights for policy 0, policy_version 63610 (0.0008) -[2023-10-15 04:49:58,453][88300] Updated weights for policy 1, policy_version 63972 (0.0008) -[2023-10-15 04:49:58,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 13884.7). Total num frames: 130613248. Throughput: 0: 1749.0, 1: 1755.6. Samples: 32671666. Policy #0 lag: (min: 31.0, avg: 46.0, max: 63.0) -[2023-10-15 04:49:58,534][87330] Avg episode reward: [(0, '22.950'), (1, '22.030')] -[2023-10-15 04:49:58,825][88300] Updated weights for policy 1, policy_version 63982 (0.0009) -[2023-10-15 04:49:59,196][88300] Updated weights for policy 1, policy_version 63992 (0.0008) -[2023-10-15 04:50:02,329][88298] Updated weights for policy 0, policy_version 63620 (0.0008) -[2023-10-15 04:50:02,698][88298] Updated weights for policy 0, policy_version 63630 (0.0007) -[2023-10-15 04:50:03,064][88298] Updated weights for policy 0, policy_version 63640 (0.0007) -[2023-10-15 04:50:03,113][88300] Updated weights for policy 1, policy_version 64002 (0.0009) -[2023-10-15 04:50:03,479][88300] Updated weights for policy 1, policy_version 64012 (0.0007) -[2023-10-15 04:50:03,534][87330] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13995.8). Total num frames: 130711552. Throughput: 0: 1740.1, 1: 1728.8. Samples: 32681406. Policy #0 lag: (min: 31.0, avg: 46.0, max: 63.0) -[2023-10-15 04:50:03,534][87330] Avg episode reward: [(0, '22.970'), (1, '22.160')] -[2023-10-15 04:50:03,836][88300] Updated weights for policy 1, policy_version 64022 (0.0009) -[2023-10-15 04:50:04,202][88300] Updated weights for policy 1, policy_version 64032 (0.0009) -[2023-10-15 04:50:07,013][88298] Updated weights for policy 0, policy_version 63650 (0.0009) -[2023-10-15 04:50:07,378][88298] Updated weights for policy 0, policy_version 63660 (0.0009) -[2023-10-15 04:50:07,757][88298] Updated weights for policy 0, policy_version 63670 (0.0010) -[2023-10-15 04:50:08,112][88298] Updated weights for policy 0, policy_version 63680 (0.0008) -[2023-10-15 04:50:08,184][88300] Updated weights for policy 1, policy_version 64042 (0.0008) -[2023-10-15 04:50:08,534][87330] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 130777088. Throughput: 0: 1750.2, 1: 1759.6. Samples: 32702858. Policy #0 lag: (min: 31.0, avg: 46.0, max: 63.0) -[2023-10-15 04:50:08,534][87330] Avg episode reward: [(0, '23.000'), (1, '22.190')] -[2023-10-15 04:50:08,551][88300] Updated weights for policy 1, policy_version 64052 (0.0008) -[2023-10-15 04:50:08,908][88300] Updated weights for policy 1, policy_version 64062 (0.0008) -[2023-10-15 04:50:11,916][88298] Updated weights for policy 0, policy_version 63690 (0.0008) -[2023-10-15 04:50:12,270][88298] Updated weights for policy 0, policy_version 63700 (0.0008) -[2023-10-15 04:50:12,631][88298] Updated weights for policy 0, policy_version 63710 (0.0008) -[2023-10-15 04:50:12,813][88300] Updated weights for policy 1, policy_version 64072 (0.0010) -[2023-10-15 04:50:13,168][88300] Updated weights for policy 1, policy_version 64082 (0.0007) -[2023-10-15 04:50:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 130842624. Throughput: 0: 1722.3, 1: 1740.0. Samples: 32722442. Policy #0 lag: (min: 31.0, avg: 46.0, max: 63.0) -[2023-10-15 04:50:13,534][87330] Avg episode reward: [(0, '22.980'), (1, '22.490')] -[2023-10-15 04:50:13,542][88300] Updated weights for policy 1, policy_version 64092 (0.0010) -[2023-10-15 04:50:16,805][88298] Updated weights for policy 0, policy_version 63720 (0.0009) -[2023-10-15 04:50:17,181][88298] Updated weights for policy 0, policy_version 63730 (0.0009) -[2023-10-15 04:50:17,481][88300] Updated weights for policy 1, policy_version 64102 (0.0008) -[2023-10-15 04:50:17,553][88298] Updated weights for policy 0, policy_version 63740 (0.0008) -[2023-10-15 04:50:17,866][88300] Updated weights for policy 1, policy_version 64112 (0.0009) -[2023-10-15 04:50:18,233][88300] Updated weights for policy 1, policy_version 64122 (0.0008) -[2023-10-15 04:50:18,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 130940928. Throughput: 0: 1758.0, 1: 1751.3. Samples: 32734236. Policy #0 lag: (min: 31.0, avg: 46.0, max: 63.0) -[2023-10-15 04:50:18,535][87330] Avg episode reward: [(0, '22.970'), (1, '22.620')] -[2023-10-15 04:50:21,510][88298] Updated weights for policy 0, policy_version 63750 (0.0009) -[2023-10-15 04:50:21,876][88298] Updated weights for policy 0, policy_version 63760 (0.0010) -[2023-10-15 04:50:22,049][88300] Updated weights for policy 1, policy_version 64132 (0.0009) -[2023-10-15 04:50:22,251][88298] Updated weights for policy 0, policy_version 63770 (0.0008) -[2023-10-15 04:50:22,420][88300] Updated weights for policy 1, policy_version 64142 (0.0007) -[2023-10-15 04:50:22,770][88300] Updated weights for policy 1, policy_version 64152 (0.0011) -[2023-10-15 04:50:23,534][87330] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 131006464. Throughput: 0: 1739.4, 1: 1753.4. Samples: 32754702. Policy #0 lag: (min: 31.0, avg: 46.0, max: 63.0) -[2023-10-15 04:50:23,535][87330] Avg episode reward: [(0, '22.970'), (1, '22.630')] -[2023-10-15 04:50:26,021][88298] Updated weights for policy 0, policy_version 63780 (0.0010) -[2023-10-15 04:50:26,390][88298] Updated weights for policy 0, policy_version 63790 (0.0010) -[2023-10-15 04:50:26,760][88298] Updated weights for policy 0, policy_version 63800 (0.0008) -[2023-10-15 04:50:26,801][88300] Updated weights for policy 1, policy_version 64162 (0.0010) -[2023-10-15 04:50:27,178][88300] Updated weights for policy 1, policy_version 64172 (0.0009) -[2023-10-15 04:50:27,543][88300] Updated weights for policy 1, policy_version 64182 (0.0007) -[2023-10-15 04:50:27,910][88300] Updated weights for policy 1, policy_version 64192 (0.0007) -[2023-10-15 04:50:28,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 131072000. Throughput: 0: 1719.5, 1: 1726.5. Samples: 32774388. Policy #0 lag: (min: 31.0, avg: 46.0, max: 63.0) -[2023-10-15 04:50:28,535][87330] Avg episode reward: [(0, '22.840'), (1, '22.800')] -[2023-10-15 04:50:30,616][88298] Updated weights for policy 0, policy_version 63810 (0.0009) -[2023-10-15 04:50:30,994][88298] Updated weights for policy 0, policy_version 63820 (0.0008) -[2023-10-15 04:50:31,361][88298] Updated weights for policy 0, policy_version 63830 (0.0008) -[2023-10-15 04:50:31,726][88298] Updated weights for policy 0, policy_version 63840 (0.0010) -[2023-10-15 04:50:31,752][88300] Updated weights for policy 1, policy_version 64202 (0.0007) -[2023-10-15 04:50:32,113][88300] Updated weights for policy 1, policy_version 64212 (0.0008) -[2023-10-15 04:50:32,486][88300] Updated weights for policy 1, policy_version 64222 (0.0007) -[2023-10-15 04:50:33,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 131137536. Throughput: 0: 1741.0, 1: 1754.9. Samples: 32786328. Policy #0 lag: (min: 17.0, avg: 28.6, max: 49.0) -[2023-10-15 04:50:33,534][87330] Avg episode reward: [(0, '22.830'), (1, '22.940')] -[2023-10-15 04:50:35,624][88298] Updated weights for policy 0, policy_version 63850 (0.0007) -[2023-10-15 04:50:36,003][88298] Updated weights for policy 0, policy_version 63860 (0.0007) -[2023-10-15 04:50:36,248][88300] Updated weights for policy 1, policy_version 64232 (0.0008) -[2023-10-15 04:50:36,369][88298] Updated weights for policy 0, policy_version 63870 (0.0007) -[2023-10-15 04:50:36,617][88300] Updated weights for policy 1, policy_version 64242 (0.0008) -[2023-10-15 04:50:36,989][88300] Updated weights for policy 1, policy_version 64252 (0.0008) -[2023-10-15 04:50:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 131203072. Throughput: 0: 1717.2, 1: 1736.7. Samples: 32805744. Policy #0 lag: (min: 17.0, avg: 28.6, max: 49.0) -[2023-10-15 04:50:38,534][87330] Avg episode reward: [(0, '22.790'), (1, '22.940')] -[2023-10-15 04:50:40,284][88298] Updated weights for policy 0, policy_version 63880 (0.0007) -[2023-10-15 04:50:40,655][88298] Updated weights for policy 0, policy_version 63890 (0.0007) -[2023-10-15 04:50:40,874][88300] Updated weights for policy 1, policy_version 64262 (0.0009) -[2023-10-15 04:50:41,030][88298] Updated weights for policy 0, policy_version 63900 (0.0007) -[2023-10-15 04:50:41,243][88300] Updated weights for policy 1, policy_version 64272 (0.0009) -[2023-10-15 04:50:41,621][88300] Updated weights for policy 1, policy_version 64282 (0.0009) -[2023-10-15 04:50:43,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 131268608. Throughput: 0: 1725.1, 1: 1736.3. Samples: 32827426. Policy #0 lag: (min: 17.0, avg: 28.6, max: 49.0) -[2023-10-15 04:50:43,534][87330] Avg episode reward: [(0, '22.780'), (1, '22.950')] -[2023-10-15 04:50:44,920][88298] Updated weights for policy 0, policy_version 63910 (0.0010) -[2023-10-15 04:50:45,294][88298] Updated weights for policy 0, policy_version 63920 (0.0008) -[2023-10-15 04:50:45,338][88300] Updated weights for policy 1, policy_version 64292 (0.0009) -[2023-10-15 04:50:45,661][88298] Updated weights for policy 0, policy_version 63930 (0.0007) -[2023-10-15 04:50:45,698][88300] Updated weights for policy 1, policy_version 64302 (0.0009) -[2023-10-15 04:50:46,056][88300] Updated weights for policy 1, policy_version 64312 (0.0007) -[2023-10-15 04:50:48,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 131334144. Throughput: 0: 1722.5, 1: 1744.3. Samples: 32837414. Policy #0 lag: (min: 17.0, avg: 28.6, max: 49.0) -[2023-10-15 04:50:48,534][87330] Avg episode reward: [(0, '22.730'), (1, '22.930')] -[2023-10-15 04:50:49,662][88298] Updated weights for policy 0, policy_version 63940 (0.0010) -[2023-10-15 04:50:49,850][88300] Updated weights for policy 1, policy_version 64322 (0.0009) -[2023-10-15 04:50:50,036][88298] Updated weights for policy 0, policy_version 63950 (0.0008) -[2023-10-15 04:50:50,210][88300] Updated weights for policy 1, policy_version 64332 (0.0009) -[2023-10-15 04:50:50,406][88298] Updated weights for policy 0, policy_version 63960 (0.0007) -[2023-10-15 04:50:50,573][88300] Updated weights for policy 1, policy_version 64342 (0.0008) -[2023-10-15 04:50:50,943][88300] Updated weights for policy 1, policy_version 64352 (0.0008) -[2023-10-15 04:50:53,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 131399680. Throughput: 0: 1717.9, 1: 1738.5. Samples: 32858396. Policy #0 lag: (min: 17.0, avg: 28.6, max: 49.0) -[2023-10-15 04:50:53,535][87330] Avg episode reward: [(0, '22.730'), (1, '22.920')] -[2023-10-15 04:50:54,388][88298] Updated weights for policy 0, policy_version 63970 (0.0008) -[2023-10-15 04:50:54,754][88298] Updated weights for policy 0, policy_version 63980 (0.0008) -[2023-10-15 04:50:54,857][88300] Updated weights for policy 1, policy_version 64362 (0.0007) -[2023-10-15 04:50:55,130][88298] Updated weights for policy 0, policy_version 63990 (0.0008) -[2023-10-15 04:50:55,229][88300] Updated weights for policy 1, policy_version 64372 (0.0007) -[2023-10-15 04:50:55,496][88298] Updated weights for policy 0, policy_version 64000 (0.0008) -[2023-10-15 04:50:55,596][88300] Updated weights for policy 1, policy_version 64382 (0.0009) -[2023-10-15 04:50:58,534][87330] Fps is (10 sec: 13106.6, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 131465216. Throughput: 0: 1741.9, 1: 1753.4. Samples: 32879732. Policy #0 lag: (min: 17.0, avg: 28.6, max: 49.0) -[2023-10-15 04:50:58,535][87330] Avg episode reward: [(0, '22.790'), (1, '22.930')] -[2023-10-15 04:50:58,548][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000064000_65536000.pth... -[2023-10-15 04:50:58,548][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000064384_65929216.pth... -[2023-10-15 04:50:58,580][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000062400_63897600.pth -[2023-10-15 04:50:58,582][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000062752_64258048.pth -[2023-10-15 04:50:59,501][88298] Updated weights for policy 0, policy_version 64010 (0.0008) -[2023-10-15 04:50:59,589][88300] Updated weights for policy 1, policy_version 64392 (0.0008) -[2023-10-15 04:50:59,874][88298] Updated weights for policy 0, policy_version 64020 (0.0007) -[2023-10-15 04:50:59,951][88300] Updated weights for policy 1, policy_version 64402 (0.0007) -[2023-10-15 04:51:00,247][88298] Updated weights for policy 0, policy_version 64030 (0.0007) -[2023-10-15 04:51:00,322][88300] Updated weights for policy 1, policy_version 64412 (0.0007) -[2023-10-15 04:51:03,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 131530752. Throughput: 0: 1706.9, 1: 1731.5. Samples: 32888962. Policy #0 lag: (min: 17.0, avg: 28.6, max: 49.0) -[2023-10-15 04:51:03,534][87330] Avg episode reward: [(0, '22.750'), (1, '22.890')] -[2023-10-15 04:51:04,225][88298] Updated weights for policy 0, policy_version 64040 (0.0008) -[2023-10-15 04:51:04,381][88300] Updated weights for policy 1, policy_version 64422 (0.0008) -[2023-10-15 04:51:04,594][88298] Updated weights for policy 0, policy_version 64050 (0.0007) -[2023-10-15 04:51:04,747][88300] Updated weights for policy 1, policy_version 64432 (0.0007) -[2023-10-15 04:51:04,960][88298] Updated weights for policy 0, policy_version 64060 (0.0008) -[2023-10-15 04:51:05,125][88300] Updated weights for policy 1, policy_version 64442 (0.0010) -[2023-10-15 04:51:08,534][87330] Fps is (10 sec: 13107.7, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 131596288. Throughput: 0: 1719.4, 1: 1734.9. Samples: 32910146. Policy #0 lag: (min: 17.0, avg: 28.6, max: 49.0) -[2023-10-15 04:51:08,535][87330] Avg episode reward: [(0, '22.790'), (1, '22.870')] -[2023-10-15 04:51:08,848][88298] Updated weights for policy 0, policy_version 64070 (0.0008) -[2023-10-15 04:51:09,141][88300] Updated weights for policy 1, policy_version 64452 (0.0009) -[2023-10-15 04:51:09,222][88298] Updated weights for policy 0, policy_version 64080 (0.0010) -[2023-10-15 04:51:09,538][88300] Updated weights for policy 1, policy_version 64462 (0.0008) -[2023-10-15 04:51:09,584][88298] Updated weights for policy 0, policy_version 64090 (0.0009) -[2023-10-15 04:51:09,899][88300] Updated weights for policy 1, policy_version 64472 (0.0008) -[2023-10-15 04:51:13,478][88298] Updated weights for policy 0, policy_version 64100 (0.0010) -[2023-10-15 04:51:13,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 131661824. Throughput: 0: 1739.0, 1: 1756.8. Samples: 32931700. Policy #0 lag: (min: 17.0, avg: 28.6, max: 49.0) -[2023-10-15 04:51:13,535][87330] Avg episode reward: [(0, '22.790'), (1, '22.880')] -[2023-10-15 04:51:13,785][88300] Updated weights for policy 1, policy_version 64482 (0.0009) -[2023-10-15 04:51:13,844][88298] Updated weights for policy 0, policy_version 64110 (0.0009) -[2023-10-15 04:51:14,157][88300] Updated weights for policy 1, policy_version 64492 (0.0009) -[2023-10-15 04:51:14,220][88298] Updated weights for policy 0, policy_version 64120 (0.0007) -[2023-10-15 04:51:14,524][88300] Updated weights for policy 1, policy_version 64502 (0.0007) -[2023-10-15 04:51:14,895][88300] Updated weights for policy 1, policy_version 64512 (0.0009) -[2023-10-15 04:51:18,242][88298] Updated weights for policy 0, policy_version 64130 (0.0007) -[2023-10-15 04:51:18,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13107.3, 300 sec: 13884.8). Total num frames: 131727360. Throughput: 0: 1714.6, 1: 1725.5. Samples: 32941130. Policy #0 lag: (min: 31.0, avg: 32.9, max: 61.0) -[2023-10-15 04:51:18,534][87330] Avg episode reward: [(0, '22.760'), (1, '22.850')] -[2023-10-15 04:51:18,615][88298] Updated weights for policy 0, policy_version 64140 (0.0009) -[2023-10-15 04:51:18,848][88300] Updated weights for policy 1, policy_version 64522 (0.0007) -[2023-10-15 04:51:18,974][88298] Updated weights for policy 0, policy_version 64150 (0.0009) -[2023-10-15 04:51:19,213][88300] Updated weights for policy 1, policy_version 64532 (0.0007) -[2023-10-15 04:51:19,347][88298] Updated weights for policy 0, policy_version 64160 (0.0009) -[2023-10-15 04:51:19,578][88300] Updated weights for policy 1, policy_version 64542 (0.0009) -[2023-10-15 04:51:23,335][88298] Updated weights for policy 0, policy_version 64170 (0.0007) -[2023-10-15 04:51:23,454][88300] Updated weights for policy 1, policy_version 64552 (0.0008) -[2023-10-15 04:51:23,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13884.8). Total num frames: 131792896. Throughput: 0: 1737.5, 1: 1745.1. Samples: 32962462. Policy #0 lag: (min: 31.0, avg: 32.9, max: 61.0) -[2023-10-15 04:51:23,534][87330] Avg episode reward: [(0, '22.850'), (1, '22.870')] -[2023-10-15 04:51:23,706][88298] Updated weights for policy 0, policy_version 64180 (0.0007) -[2023-10-15 04:51:23,814][88300] Updated weights for policy 1, policy_version 64562 (0.0008) -[2023-10-15 04:51:24,064][88298] Updated weights for policy 0, policy_version 64190 (0.0008) -[2023-10-15 04:51:24,178][88300] Updated weights for policy 1, policy_version 64572 (0.0008) -[2023-10-15 04:51:28,045][88298] Updated weights for policy 0, policy_version 64200 (0.0007) -[2023-10-15 04:51:28,155][88300] Updated weights for policy 1, policy_version 64582 (0.0008) -[2023-10-15 04:51:28,416][88298] Updated weights for policy 0, policy_version 64210 (0.0009) -[2023-10-15 04:51:28,522][88300] Updated weights for policy 1, policy_version 64592 (0.0008) -[2023-10-15 04:51:28,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13884.8). Total num frames: 131858432. Throughput: 0: 1734.4, 1: 1735.3. Samples: 32983560. Policy #0 lag: (min: 31.0, avg: 32.9, max: 61.0) -[2023-10-15 04:51:28,534][87330] Avg episode reward: [(0, '22.760'), (1, '22.820')] -[2023-10-15 04:51:28,782][88298] Updated weights for policy 0, policy_version 64220 (0.0010) -[2023-10-15 04:51:28,891][88300] Updated weights for policy 1, policy_version 64602 (0.0009) -[2023-10-15 04:51:32,450][88298] Updated weights for policy 0, policy_version 64230 (0.0009) -[2023-10-15 04:51:32,820][88298] Updated weights for policy 0, policy_version 64240 (0.0010) -[2023-10-15 04:51:32,845][88300] Updated weights for policy 1, policy_version 64612 (0.0007) -[2023-10-15 04:51:33,180][88298] Updated weights for policy 0, policy_version 64250 (0.0007) -[2023-10-15 04:51:33,212][88300] Updated weights for policy 1, policy_version 64622 (0.0008) -[2023-10-15 04:51:33,534][87330] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 131956736. Throughput: 0: 1731.6, 1: 1734.3. Samples: 32993380. Policy #0 lag: (min: 31.0, avg: 32.9, max: 61.0) -[2023-10-15 04:51:33,534][87330] Avg episode reward: [(0, '22.790'), (1, '22.750')] -[2023-10-15 04:51:33,576][88300] Updated weights for policy 1, policy_version 64632 (0.0008) -[2023-10-15 04:51:37,129][88298] Updated weights for policy 0, policy_version 64260 (0.0007) -[2023-10-15 04:51:37,464][88300] Updated weights for policy 1, policy_version 64642 (0.0009) -[2023-10-15 04:51:37,495][88298] Updated weights for policy 0, policy_version 64270 (0.0009) -[2023-10-15 04:51:37,835][88300] Updated weights for policy 1, policy_version 64652 (0.0008) -[2023-10-15 04:51:37,869][88298] Updated weights for policy 0, policy_version 64280 (0.0010) -[2023-10-15 04:51:38,199][88300] Updated weights for policy 1, policy_version 64662 (0.0007) -[2023-10-15 04:51:38,534][87330] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 132022272. Throughput: 0: 1738.8, 1: 1737.7. Samples: 33014838. Policy #0 lag: (min: 31.0, avg: 32.9, max: 61.0) -[2023-10-15 04:51:38,534][87330] Avg episode reward: [(0, '22.820'), (1, '22.520')] -[2023-10-15 04:51:38,562][88300] Updated weights for policy 1, policy_version 64672 (0.0007) -[2023-10-15 04:51:41,698][88298] Updated weights for policy 0, policy_version 64290 (0.0008) -[2023-10-15 04:51:42,075][88298] Updated weights for policy 0, policy_version 64300 (0.0010) -[2023-10-15 04:51:42,437][88298] Updated weights for policy 0, policy_version 64310 (0.0008) -[2023-10-15 04:51:42,480][88300] Updated weights for policy 1, policy_version 64682 (0.0008) -[2023-10-15 04:51:42,803][88298] Updated weights for policy 0, policy_version 64320 (0.0008) -[2023-10-15 04:51:42,850][88300] Updated weights for policy 1, policy_version 64692 (0.0007) -[2023-10-15 04:51:43,216][88300] Updated weights for policy 1, policy_version 64702 (0.0010) -[2023-10-15 04:51:43,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 132120576. Throughput: 0: 1711.4, 1: 1710.2. Samples: 33033706. Policy #0 lag: (min: 31.0, avg: 32.9, max: 61.0) -[2023-10-15 04:51:43,534][87330] Avg episode reward: [(0, '22.820'), (1, '22.430')] -[2023-10-15 04:51:46,849][88298] Updated weights for policy 0, policy_version 64330 (0.0009) -[2023-10-15 04:51:47,218][88298] Updated weights for policy 0, policy_version 64340 (0.0009) -[2023-10-15 04:51:47,263][88300] Updated weights for policy 1, policy_version 64712 (0.0007) -[2023-10-15 04:51:47,583][88298] Updated weights for policy 0, policy_version 64350 (0.0008) -[2023-10-15 04:51:47,630][88300] Updated weights for policy 1, policy_version 64722 (0.0008) -[2023-10-15 04:51:48,000][88300] Updated weights for policy 1, policy_version 64732 (0.0008) -[2023-10-15 04:51:48,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 132186112. Throughput: 0: 1739.4, 1: 1739.9. Samples: 33045528. Policy #0 lag: (min: 31.0, avg: 32.9, max: 61.0) -[2023-10-15 04:51:48,534][87330] Avg episode reward: [(0, '22.850'), (1, '22.380')] -[2023-10-15 04:51:51,593][88298] Updated weights for policy 0, policy_version 64360 (0.0009) -[2023-10-15 04:51:51,853][88300] Updated weights for policy 1, policy_version 64742 (0.0008) -[2023-10-15 04:51:51,964][88298] Updated weights for policy 0, policy_version 64370 (0.0007) -[2023-10-15 04:51:52,222][88300] Updated weights for policy 1, policy_version 64752 (0.0007) -[2023-10-15 04:51:52,325][88298] Updated weights for policy 0, policy_version 64380 (0.0008) -[2023-10-15 04:51:52,594][88300] Updated weights for policy 1, policy_version 64762 (0.0007) -[2023-10-15 04:51:53,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 132251648. Throughput: 0: 1730.5, 1: 1727.8. Samples: 33065770. Policy #0 lag: (min: 31.0, avg: 32.9, max: 61.0) -[2023-10-15 04:51:53,534][87330] Avg episode reward: [(0, '22.740'), (1, '22.310')] -[2023-10-15 04:51:56,205][88298] Updated weights for policy 0, policy_version 64390 (0.0007) -[2023-10-15 04:51:56,243][88300] Updated weights for policy 1, policy_version 64772 (0.0007) -[2023-10-15 04:51:56,571][88298] Updated weights for policy 0, policy_version 64400 (0.0007) -[2023-10-15 04:51:56,628][88300] Updated weights for policy 1, policy_version 64782 (0.0009) -[2023-10-15 04:51:56,932][88298] Updated weights for policy 0, policy_version 64410 (0.0007) -[2023-10-15 04:51:56,997][88300] Updated weights for policy 1, policy_version 64792 (0.0008) -[2023-10-15 04:51:58,534][87330] Fps is (10 sec: 13106.7, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 132317184. Throughput: 0: 1709.2, 1: 1718.8. Samples: 33085962. Policy #0 lag: (min: 12.0, avg: 24.3, max: 44.0) -[2023-10-15 04:51:58,535][87330] Avg episode reward: [(0, '22.680'), (1, '22.380')] -[2023-10-15 04:52:00,871][88298] Updated weights for policy 0, policy_version 64420 (0.0008) -[2023-10-15 04:52:00,898][88300] Updated weights for policy 1, policy_version 64802 (0.0008) -[2023-10-15 04:52:01,244][88298] Updated weights for policy 0, policy_version 64430 (0.0007) -[2023-10-15 04:52:01,262][88300] Updated weights for policy 1, policy_version 64812 (0.0008) -[2023-10-15 04:52:01,607][88298] Updated weights for policy 0, policy_version 64440 (0.0007) -[2023-10-15 04:52:01,632][88300] Updated weights for policy 1, policy_version 64822 (0.0008) -[2023-10-15 04:52:01,987][88300] Updated weights for policy 1, policy_version 64832 (0.0009) -[2023-10-15 04:52:03,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 132382720. Throughput: 0: 1739.3, 1: 1739.9. Samples: 33097696. Policy #0 lag: (min: 12.0, avg: 24.3, max: 44.0) -[2023-10-15 04:52:03,535][87330] Avg episode reward: [(0, '22.810'), (1, '22.240')] -[2023-10-15 04:52:05,439][88298] Updated weights for policy 0, policy_version 64450 (0.0010) -[2023-10-15 04:52:05,804][88298] Updated weights for policy 0, policy_version 64460 (0.0007) -[2023-10-15 04:52:05,998][88300] Updated weights for policy 1, policy_version 64842 (0.0008) -[2023-10-15 04:52:06,167][88298] Updated weights for policy 0, policy_version 64470 (0.0008) -[2023-10-15 04:52:06,365][88300] Updated weights for policy 1, policy_version 64852 (0.0007) -[2023-10-15 04:52:06,542][88298] Updated weights for policy 0, policy_version 64480 (0.0008) -[2023-10-15 04:52:06,728][88300] Updated weights for policy 1, policy_version 64862 (0.0008) -[2023-10-15 04:52:08,534][87330] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 132448256. Throughput: 0: 1716.3, 1: 1720.4. Samples: 33117112. Policy #0 lag: (min: 12.0, avg: 24.3, max: 44.0) -[2023-10-15 04:52:08,535][87330] Avg episode reward: [(0, '22.820'), (1, '22.460')] -[2023-10-15 04:52:10,473][88300] Updated weights for policy 1, policy_version 64872 (0.0008) -[2023-10-15 04:52:10,512][88298] Updated weights for policy 0, policy_version 64490 (0.0009) -[2023-10-15 04:52:10,849][88300] Updated weights for policy 1, policy_version 64882 (0.0009) -[2023-10-15 04:52:10,890][88298] Updated weights for policy 0, policy_version 64500 (0.0008) -[2023-10-15 04:52:11,214][88300] Updated weights for policy 1, policy_version 64892 (0.0008) -[2023-10-15 04:52:11,254][88298] Updated weights for policy 0, policy_version 64510 (0.0008) -[2023-10-15 04:52:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 132513792. Throughput: 0: 1718.7, 1: 1725.6. Samples: 33138556. Policy #0 lag: (min: 12.0, avg: 24.3, max: 44.0) -[2023-10-15 04:52:13,535][87330] Avg episode reward: [(0, '22.820'), (1, '22.450')] -[2023-10-15 04:52:15,179][88298] Updated weights for policy 0, policy_version 64520 (0.0007) -[2023-10-15 04:52:15,315][88300] Updated weights for policy 1, policy_version 64902 (0.0009) -[2023-10-15 04:52:15,547][88298] Updated weights for policy 0, policy_version 64530 (0.0007) -[2023-10-15 04:52:15,690][88300] Updated weights for policy 1, policy_version 64912 (0.0008) -[2023-10-15 04:52:15,923][88298] Updated weights for policy 0, policy_version 64540 (0.0008) -[2023-10-15 04:52:16,056][88300] Updated weights for policy 1, policy_version 64922 (0.0007) -[2023-10-15 04:52:18,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 132579328. Throughput: 0: 1724.7, 1: 1724.7. Samples: 33148602. Policy #0 lag: (min: 12.0, avg: 24.3, max: 44.0) -[2023-10-15 04:52:18,535][87330] Avg episode reward: [(0, '22.830'), (1, '22.650')] -[2023-10-15 04:52:19,774][88298] Updated weights for policy 0, policy_version 64550 (0.0010) -[2023-10-15 04:52:20,025][88300] Updated weights for policy 1, policy_version 64932 (0.0009) -[2023-10-15 04:52:20,137][88298] Updated weights for policy 0, policy_version 64560 (0.0007) -[2023-10-15 04:52:20,389][88300] Updated weights for policy 1, policy_version 64942 (0.0008) -[2023-10-15 04:52:20,514][88298] Updated weights for policy 0, policy_version 64570 (0.0007) -[2023-10-15 04:52:20,752][88300] Updated weights for policy 1, policy_version 64952 (0.0007) -[2023-10-15 04:52:23,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 132644864. Throughput: 0: 1711.4, 1: 1719.9. Samples: 33169246. Policy #0 lag: (min: 12.0, avg: 24.3, max: 44.0) -[2023-10-15 04:52:23,535][87330] Avg episode reward: [(0, '22.730'), (1, '22.600')] -[2023-10-15 04:52:24,413][88298] Updated weights for policy 0, policy_version 64580 (0.0010) -[2023-10-15 04:52:24,782][88298] Updated weights for policy 0, policy_version 64590 (0.0008) -[2023-10-15 04:52:24,785][88300] Updated weights for policy 1, policy_version 64962 (0.0009) -[2023-10-15 04:52:25,155][88298] Updated weights for policy 0, policy_version 64600 (0.0007) -[2023-10-15 04:52:25,157][88300] Updated weights for policy 1, policy_version 64972 (0.0007) -[2023-10-15 04:52:25,517][88300] Updated weights for policy 1, policy_version 64982 (0.0007) -[2023-10-15 04:52:25,885][88300] Updated weights for policy 1, policy_version 64992 (0.0009) -[2023-10-15 04:52:28,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 132710400. Throughput: 0: 1743.1, 1: 1752.2. Samples: 33190994. Policy #0 lag: (min: 12.0, avg: 24.3, max: 44.0) -[2023-10-15 04:52:28,535][87330] Avg episode reward: [(0, '22.830'), (1, '22.570')] -[2023-10-15 04:52:29,445][88298] Updated weights for policy 0, policy_version 64610 (0.0007) -[2023-10-15 04:52:29,625][88300] Updated weights for policy 1, policy_version 65002 (0.0010) -[2023-10-15 04:52:29,813][88298] Updated weights for policy 0, policy_version 64620 (0.0008) -[2023-10-15 04:52:29,978][88300] Updated weights for policy 1, policy_version 65012 (0.0010) -[2023-10-15 04:52:30,179][88298] Updated weights for policy 0, policy_version 64630 (0.0010) -[2023-10-15 04:52:30,350][88300] Updated weights for policy 1, policy_version 65022 (0.0008) -[2023-10-15 04:52:30,542][88298] Updated weights for policy 0, policy_version 64640 (0.0010) -[2023-10-15 04:52:33,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 132775936. Throughput: 0: 1715.3, 1: 1726.5. Samples: 33200410. Policy #0 lag: (min: 12.0, avg: 24.3, max: 44.0) -[2023-10-15 04:52:33,535][87330] Avg episode reward: [(0, '22.840'), (1, '22.800')] -[2023-10-15 04:52:34,220][88300] Updated weights for policy 1, policy_version 65032 (0.0009) -[2023-10-15 04:52:34,430][88298] Updated weights for policy 0, policy_version 64650 (0.0007) -[2023-10-15 04:52:34,587][88300] Updated weights for policy 1, policy_version 65042 (0.0008) -[2023-10-15 04:52:34,797][88298] Updated weights for policy 0, policy_version 64660 (0.0008) -[2023-10-15 04:52:34,951][88300] Updated weights for policy 1, policy_version 65052 (0.0010) -[2023-10-15 04:52:35,167][88298] Updated weights for policy 0, policy_version 64670 (0.0007) -[2023-10-15 04:52:38,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 132841472. Throughput: 0: 1728.8, 1: 1744.8. Samples: 33222080. Policy #0 lag: (min: 12.0, avg: 24.3, max: 44.0) -[2023-10-15 04:52:38,535][87330] Avg episode reward: [(0, '22.850'), (1, '22.790')] -[2023-10-15 04:52:38,791][88300] Updated weights for policy 1, policy_version 65062 (0.0007) -[2023-10-15 04:52:39,159][88300] Updated weights for policy 1, policy_version 65072 (0.0009) -[2023-10-15 04:52:39,172][88298] Updated weights for policy 0, policy_version 64680 (0.0007) -[2023-10-15 04:52:39,516][88300] Updated weights for policy 1, policy_version 65082 (0.0008) -[2023-10-15 04:52:39,547][88298] Updated weights for policy 0, policy_version 64690 (0.0007) -[2023-10-15 04:52:39,911][88298] Updated weights for policy 0, policy_version 64700 (0.0009) -[2023-10-15 04:52:43,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 132907008. Throughput: 0: 1744.2, 1: 1759.0. Samples: 33243606. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-15 04:52:43,535][87330] Avg episode reward: [(0, '22.830'), (1, '22.790')] -[2023-10-15 04:52:43,541][88300] Updated weights for policy 1, policy_version 65092 (0.0010) -[2023-10-15 04:52:43,939][88300] Updated weights for policy 1, policy_version 65102 (0.0007) -[2023-10-15 04:52:43,967][88298] Updated weights for policy 0, policy_version 64710 (0.0008) -[2023-10-15 04:52:44,300][88300] Updated weights for policy 1, policy_version 65112 (0.0007) -[2023-10-15 04:52:44,338][88298] Updated weights for policy 0, policy_version 64720 (0.0007) -[2023-10-15 04:52:44,705][88298] Updated weights for policy 0, policy_version 64730 (0.0009) -[2023-10-15 04:52:48,174][88300] Updated weights for policy 1, policy_version 65122 (0.0009) -[2023-10-15 04:52:48,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 132972544. Throughput: 0: 1715.7, 1: 1734.7. Samples: 33252966. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-15 04:52:48,534][87330] Avg episode reward: [(0, '22.780'), (1, '22.670')] -[2023-10-15 04:52:48,540][88300] Updated weights for policy 1, policy_version 65132 (0.0009) -[2023-10-15 04:52:48,690][88298] Updated weights for policy 0, policy_version 64740 (0.0008) -[2023-10-15 04:52:48,912][88300] Updated weights for policy 1, policy_version 65142 (0.0008) -[2023-10-15 04:52:49,070][88298] Updated weights for policy 0, policy_version 64750 (0.0007) -[2023-10-15 04:52:49,282][88300] Updated weights for policy 1, policy_version 65152 (0.0009) -[2023-10-15 04:52:49,441][88298] Updated weights for policy 0, policy_version 64760 (0.0009) -[2023-10-15 04:52:53,140][88298] Updated weights for policy 0, policy_version 64770 (0.0008) -[2023-10-15 04:52:53,164][88300] Updated weights for policy 1, policy_version 65162 (0.0007) -[2023-10-15 04:52:53,503][88298] Updated weights for policy 0, policy_version 64780 (0.0008) -[2023-10-15 04:52:53,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 133038080. Throughput: 0: 1740.1, 1: 1756.8. Samples: 33274476. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-15 04:52:53,535][87330] Avg episode reward: [(0, '22.770'), (1, '22.800')] -[2023-10-15 04:52:53,537][88300] Updated weights for policy 1, policy_version 65172 (0.0007) -[2023-10-15 04:52:53,877][88298] Updated weights for policy 0, policy_version 64790 (0.0008) -[2023-10-15 04:52:53,902][88300] Updated weights for policy 1, policy_version 65182 (0.0008) -[2023-10-15 04:52:54,240][88298] Updated weights for policy 0, policy_version 64800 (0.0007) -[2023-10-15 04:52:57,927][88300] Updated weights for policy 1, policy_version 65192 (0.0008) -[2023-10-15 04:52:58,133][88298] Updated weights for policy 0, policy_version 64810 (0.0007) -[2023-10-15 04:52:58,288][88300] Updated weights for policy 1, policy_version 65202 (0.0009) -[2023-10-15 04:52:58,506][88298] Updated weights for policy 0, policy_version 64820 (0.0007) -[2023-10-15 04:52:58,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.3, 300 sec: 13773.7). Total num frames: 133103616. Throughput: 0: 1741.8, 1: 1744.9. Samples: 33295460. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-15 04:52:58,534][87330] Avg episode reward: [(0, '22.870'), (1, '22.580')] -[2023-10-15 04:52:58,652][88300] Updated weights for policy 1, policy_version 65212 (0.0008) -[2023-10-15 04:52:58,796][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000065216_66781184.pth... -[2023-10-15 04:52:58,828][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000063584_65110016.pth -[2023-10-15 04:52:58,834][88033] Saving a milestone ./train_atari/atari_seaquest_APPO/checkpoint_p1/milestones/checkpoint_000065216_66781184.pth -[2023-10-15 04:52:58,873][88298] Updated weights for policy 0, policy_version 64830 (0.0010) -[2023-10-15 04:52:58,944][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000064832_66387968.pth... -[2023-10-15 04:52:58,972][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000063200_64716800.pth -[2023-10-15 04:52:58,976][87905] Saving a milestone ./train_atari/atari_seaquest_APPO/checkpoint_p0/milestones/checkpoint_000064832_66387968.pth -[2023-10-15 04:53:02,660][88300] Updated weights for policy 1, policy_version 65222 (0.0008) -[2023-10-15 04:53:02,708][88298] Updated weights for policy 0, policy_version 64840 (0.0009) -[2023-10-15 04:53:03,030][88300] Updated weights for policy 1, policy_version 65232 (0.0007) -[2023-10-15 04:53:03,074][88298] Updated weights for policy 0, policy_version 64850 (0.0007) -[2023-10-15 04:53:03,389][88300] Updated weights for policy 1, policy_version 65242 (0.0007) -[2023-10-15 04:53:03,446][88298] Updated weights for policy 0, policy_version 64860 (0.0007) -[2023-10-15 04:53:03,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 133169152. Throughput: 0: 1732.2, 1: 1752.1. Samples: 33305396. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-15 04:53:03,535][87330] Avg episode reward: [(0, '22.860'), (1, '22.600')] -[2023-10-15 04:53:07,375][88298] Updated weights for policy 0, policy_version 64870 (0.0008) -[2023-10-15 04:53:07,420][88300] Updated weights for policy 1, policy_version 65252 (0.0009) -[2023-10-15 04:53:07,749][88298] Updated weights for policy 0, policy_version 64880 (0.0008) -[2023-10-15 04:53:07,788][88300] Updated weights for policy 1, policy_version 65262 (0.0007) -[2023-10-15 04:53:08,119][88298] Updated weights for policy 0, policy_version 64890 (0.0008) -[2023-10-15 04:53:08,147][88300] Updated weights for policy 1, policy_version 65272 (0.0008) -[2023-10-15 04:53:08,534][87330] Fps is (10 sec: 19660.6, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 133300224. Throughput: 0: 1743.4, 1: 1754.8. Samples: 33326664. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-15 04:53:08,535][87330] Avg episode reward: [(0, '22.860'), (1, '22.600')] -[2023-10-15 04:53:11,948][88300] Updated weights for policy 1, policy_version 65282 (0.0007) -[2023-10-15 04:53:12,060][88298] Updated weights for policy 0, policy_version 64900 (0.0008) -[2023-10-15 04:53:12,313][88300] Updated weights for policy 1, policy_version 65292 (0.0008) -[2023-10-15 04:53:12,424][88298] Updated weights for policy 0, policy_version 64910 (0.0008) -[2023-10-15 04:53:12,686][88300] Updated weights for policy 1, policy_version 65302 (0.0007) -[2023-10-15 04:53:12,781][88298] Updated weights for policy 0, policy_version 64920 (0.0009) -[2023-10-15 04:53:13,047][88300] Updated weights for policy 1, policy_version 65312 (0.0007) -[2023-10-15 04:53:13,534][87330] Fps is (10 sec: 19660.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 133365760. Throughput: 0: 1719.2, 1: 1721.7. Samples: 33345834. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-15 04:53:13,535][87330] Avg episode reward: [(0, '22.760'), (1, '22.610')] -[2023-10-15 04:53:16,727][88298] Updated weights for policy 0, policy_version 64930 (0.0007) -[2023-10-15 04:53:16,887][88300] Updated weights for policy 1, policy_version 65322 (0.0008) -[2023-10-15 04:53:17,095][88298] Updated weights for policy 0, policy_version 64940 (0.0007) -[2023-10-15 04:53:17,251][88300] Updated weights for policy 1, policy_version 65332 (0.0007) -[2023-10-15 04:53:17,466][88298] Updated weights for policy 0, policy_version 64950 (0.0007) -[2023-10-15 04:53:17,616][88300] Updated weights for policy 1, policy_version 65342 (0.0008) -[2023-10-15 04:53:17,839][88298] Updated weights for policy 0, policy_version 64960 (0.0008) -[2023-10-15 04:53:18,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 133431296. Throughput: 0: 1741.6, 1: 1753.9. Samples: 33357710. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-15 04:53:18,535][87330] Avg episode reward: [(0, '22.800'), (1, '22.620')] -[2023-10-15 04:53:21,616][88300] Updated weights for policy 1, policy_version 65352 (0.0007) -[2023-10-15 04:53:21,727][88298] Updated weights for policy 0, policy_version 64970 (0.0008) -[2023-10-15 04:53:21,984][88300] Updated weights for policy 1, policy_version 65362 (0.0008) -[2023-10-15 04:53:22,098][88298] Updated weights for policy 0, policy_version 64980 (0.0007) -[2023-10-15 04:53:22,349][88300] Updated weights for policy 1, policy_version 65372 (0.0007) -[2023-10-15 04:53:22,468][88298] Updated weights for policy 0, policy_version 64990 (0.0007) -[2023-10-15 04:53:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 133496832. Throughput: 0: 1734.9, 1: 1725.6. Samples: 33377804. Policy #0 lag: (min: 9.0, avg: 22.7, max: 41.0) -[2023-10-15 04:53:23,535][87330] Avg episode reward: [(0, '22.800'), (1, '22.720')] -[2023-10-15 04:53:26,259][88300] Updated weights for policy 1, policy_version 65382 (0.0007) -[2023-10-15 04:53:26,507][88298] Updated weights for policy 0, policy_version 65000 (0.0008) -[2023-10-15 04:53:26,617][88300] Updated weights for policy 1, policy_version 65392 (0.0008) -[2023-10-15 04:53:26,872][88298] Updated weights for policy 0, policy_version 65010 (0.0007) -[2023-10-15 04:53:26,984][88300] Updated weights for policy 1, policy_version 65402 (0.0010) -[2023-10-15 04:53:27,241][88298] Updated weights for policy 0, policy_version 65020 (0.0009) -[2023-10-15 04:53:28,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 133562368. Throughput: 0: 1710.5, 1: 1716.9. Samples: 33397838. Policy #0 lag: (min: 9.0, avg: 22.7, max: 41.0) -[2023-10-15 04:53:28,535][87330] Avg episode reward: [(0, '22.820'), (1, '22.680')] -[2023-10-15 04:53:31,146][88300] Updated weights for policy 1, policy_version 65412 (0.0007) -[2023-10-15 04:53:31,255][88298] Updated weights for policy 0, policy_version 65030 (0.0009) -[2023-10-15 04:53:31,548][88300] Updated weights for policy 1, policy_version 65422 (0.0009) -[2023-10-15 04:53:31,621][88298] Updated weights for policy 0, policy_version 65040 (0.0009) -[2023-10-15 04:53:31,919][88300] Updated weights for policy 1, policy_version 65432 (0.0007) -[2023-10-15 04:53:31,981][88298] Updated weights for policy 0, policy_version 65050 (0.0007) -[2023-10-15 04:53:33,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 133627904. Throughput: 0: 1739.5, 1: 1737.2. Samples: 33409414. Policy #0 lag: (min: 9.0, avg: 22.7, max: 41.0) -[2023-10-15 04:53:33,534][87330] Avg episode reward: [(0, '22.820'), (1, '22.680')] -[2023-10-15 04:53:35,716][88300] Updated weights for policy 1, policy_version 65442 (0.0008) -[2023-10-15 04:53:35,903][88298] Updated weights for policy 0, policy_version 65060 (0.0008) -[2023-10-15 04:53:36,080][88300] Updated weights for policy 1, policy_version 65452 (0.0008) -[2023-10-15 04:53:36,266][88298] Updated weights for policy 0, policy_version 65070 (0.0010) -[2023-10-15 04:53:36,450][88300] Updated weights for policy 1, policy_version 65462 (0.0008) -[2023-10-15 04:53:36,628][88298] Updated weights for policy 0, policy_version 65080 (0.0008) -[2023-10-15 04:53:36,815][88300] Updated weights for policy 1, policy_version 65472 (0.0008) -[2023-10-15 04:53:38,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 133693440. Throughput: 0: 1712.6, 1: 1706.3. Samples: 33428328. Policy #0 lag: (min: 9.0, avg: 22.7, max: 41.0) -[2023-10-15 04:53:38,534][87330] Avg episode reward: [(0, '22.660'), (1, '22.530')] -[2023-10-15 04:53:40,444][88298] Updated weights for policy 0, policy_version 65090 (0.0008) -[2023-10-15 04:53:40,776][88300] Updated weights for policy 1, policy_version 65482 (0.0008) -[2023-10-15 04:53:40,817][88298] Updated weights for policy 0, policy_version 65100 (0.0009) -[2023-10-15 04:53:41,141][88300] Updated weights for policy 1, policy_version 65492 (0.0008) -[2023-10-15 04:53:41,185][88298] Updated weights for policy 0, policy_version 65110 (0.0007) -[2023-10-15 04:53:41,508][88300] Updated weights for policy 1, policy_version 65502 (0.0009) -[2023-10-15 04:53:41,547][88298] Updated weights for policy 0, policy_version 65120 (0.0008) -[2023-10-15 04:53:43,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 133758976. Throughput: 0: 1707.4, 1: 1722.4. Samples: 33449798. Policy #0 lag: (min: 9.0, avg: 22.7, max: 41.0) -[2023-10-15 04:53:43,535][87330] Avg episode reward: [(0, '22.580'), (1, '22.520')] -[2023-10-15 04:53:45,326][88300] Updated weights for policy 1, policy_version 65512 (0.0007) -[2023-10-15 04:53:45,358][88298] Updated weights for policy 0, policy_version 65130 (0.0009) -[2023-10-15 04:53:45,690][88300] Updated weights for policy 1, policy_version 65522 (0.0008) -[2023-10-15 04:53:45,725][88298] Updated weights for policy 0, policy_version 65140 (0.0009) -[2023-10-15 04:53:46,063][88300] Updated weights for policy 1, policy_version 65532 (0.0007) -[2023-10-15 04:53:46,100][88298] Updated weights for policy 0, policy_version 65150 (0.0007) -[2023-10-15 04:53:48,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 133824512. Throughput: 0: 1721.1, 1: 1713.4. Samples: 33459948. Policy #0 lag: (min: 9.0, avg: 22.7, max: 41.0) -[2023-10-15 04:53:48,534][87330] Avg episode reward: [(0, '22.590'), (1, '22.480')] -[2023-10-15 04:53:50,029][88300] Updated weights for policy 1, policy_version 65542 (0.0007) -[2023-10-15 04:53:50,059][88298] Updated weights for policy 0, policy_version 65160 (0.0007) -[2023-10-15 04:53:50,393][88300] Updated weights for policy 1, policy_version 65552 (0.0009) -[2023-10-15 04:53:50,428][88298] Updated weights for policy 0, policy_version 65170 (0.0007) -[2023-10-15 04:53:50,773][88300] Updated weights for policy 1, policy_version 65562 (0.0008) -[2023-10-15 04:53:50,808][88298] Updated weights for policy 0, policy_version 65180 (0.0009) -[2023-10-15 04:53:53,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 133890048. Throughput: 0: 1706.1, 1: 1710.1. Samples: 33480394. Policy #0 lag: (min: 9.0, avg: 22.7, max: 41.0) -[2023-10-15 04:53:53,535][87330] Avg episode reward: [(0, '22.600'), (1, '22.460')] -[2023-10-15 04:53:54,649][88300] Updated weights for policy 1, policy_version 65572 (0.0008) -[2023-10-15 04:53:54,810][88298] Updated weights for policy 0, policy_version 65190 (0.0009) -[2023-10-15 04:53:55,003][88300] Updated weights for policy 1, policy_version 65582 (0.0007) -[2023-10-15 04:53:55,176][88298] Updated weights for policy 0, policy_version 65200 (0.0010) -[2023-10-15 04:53:55,369][88300] Updated weights for policy 1, policy_version 65592 (0.0008) -[2023-10-15 04:53:55,550][88298] Updated weights for policy 0, policy_version 65210 (0.0008) -[2023-10-15 04:53:58,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 133955584. Throughput: 0: 1725.4, 1: 1741.5. Samples: 33501844. Policy #0 lag: (min: 9.0, avg: 22.7, max: 41.0) -[2023-10-15 04:53:58,534][87330] Avg episode reward: [(0, '22.350'), (1, '22.610')] -[2023-10-15 04:53:59,305][88300] Updated weights for policy 1, policy_version 65602 (0.0008) -[2023-10-15 04:53:59,527][88298] Updated weights for policy 0, policy_version 65220 (0.0008) -[2023-10-15 04:53:59,670][88300] Updated weights for policy 1, policy_version 65612 (0.0007) -[2023-10-15 04:53:59,895][88298] Updated weights for policy 0, policy_version 65230 (0.0008) -[2023-10-15 04:54:00,046][88300] Updated weights for policy 1, policy_version 65622 (0.0009) -[2023-10-15 04:54:00,265][88298] Updated weights for policy 0, policy_version 65240 (0.0008) -[2023-10-15 04:54:00,410][88300] Updated weights for policy 1, policy_version 65632 (0.0007) -[2023-10-15 04:54:03,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 134021120. Throughput: 0: 1704.8, 1: 1707.7. Samples: 33511274. Policy #0 lag: (min: 9.0, avg: 22.7, max: 41.0) -[2023-10-15 04:54:03,535][87330] Avg episode reward: [(0, '22.280'), (1, '22.680')] -[2023-10-15 04:54:04,166][88298] Updated weights for policy 0, policy_version 65250 (0.0009) -[2023-10-15 04:54:04,300][88300] Updated weights for policy 1, policy_version 65642 (0.0008) -[2023-10-15 04:54:04,539][88298] Updated weights for policy 0, policy_version 65260 (0.0007) -[2023-10-15 04:54:04,675][88300] Updated weights for policy 1, policy_version 65652 (0.0007) -[2023-10-15 04:54:04,903][88298] Updated weights for policy 0, policy_version 65270 (0.0009) -[2023-10-15 04:54:05,033][88300] Updated weights for policy 1, policy_version 65662 (0.0009) -[2023-10-15 04:54:05,268][88298] Updated weights for policy 0, policy_version 65280 (0.0007) -[2023-10-15 04:54:08,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 134086656. Throughput: 0: 1715.3, 1: 1732.4. Samples: 33532946. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:54:08,534][87330] Avg episode reward: [(0, '22.500'), (1, '22.700')] -[2023-10-15 04:54:08,977][88298] Updated weights for policy 0, policy_version 65290 (0.0008) -[2023-10-15 04:54:08,980][88300] Updated weights for policy 1, policy_version 65672 (0.0010) -[2023-10-15 04:54:09,343][88298] Updated weights for policy 0, policy_version 65300 (0.0007) -[2023-10-15 04:54:09,358][88300] Updated weights for policy 1, policy_version 65682 (0.0007) -[2023-10-15 04:54:09,713][88298] Updated weights for policy 0, policy_version 65310 (0.0008) -[2023-10-15 04:54:09,721][88300] Updated weights for policy 1, policy_version 65692 (0.0008) -[2023-10-15 04:54:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 134152192. Throughput: 0: 1750.8, 1: 1737.5. Samples: 33554808. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:54:13,535][87330] Avg episode reward: [(0, '22.580'), (1, '22.680')] -[2023-10-15 04:54:13,715][88300] Updated weights for policy 1, policy_version 65702 (0.0007) -[2023-10-15 04:54:13,757][88298] Updated weights for policy 0, policy_version 65320 (0.0008) -[2023-10-15 04:54:14,091][88300] Updated weights for policy 1, policy_version 65712 (0.0007) -[2023-10-15 04:54:14,126][88298] Updated weights for policy 0, policy_version 65330 (0.0010) -[2023-10-15 04:54:14,456][88300] Updated weights for policy 1, policy_version 65722 (0.0008) -[2023-10-15 04:54:14,495][88298] Updated weights for policy 0, policy_version 65340 (0.0008) -[2023-10-15 04:54:18,311][88298] Updated weights for policy 0, policy_version 65350 (0.0009) -[2023-10-15 04:54:18,375][88300] Updated weights for policy 1, policy_version 65732 (0.0008) -[2023-10-15 04:54:18,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.3, 300 sec: 13773.7). Total num frames: 134217728. Throughput: 0: 1715.6, 1: 1720.8. Samples: 33564050. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:54:18,534][87330] Avg episode reward: [(0, '22.410'), (1, '22.670')] -[2023-10-15 04:54:18,675][88298] Updated weights for policy 0, policy_version 65360 (0.0009) -[2023-10-15 04:54:18,750][88300] Updated weights for policy 1, policy_version 65742 (0.0007) -[2023-10-15 04:54:19,033][88298] Updated weights for policy 0, policy_version 65370 (0.0009) -[2023-10-15 04:54:19,116][88300] Updated weights for policy 1, policy_version 65752 (0.0007) -[2023-10-15 04:54:23,073][88300] Updated weights for policy 1, policy_version 65762 (0.0010) -[2023-10-15 04:54:23,087][88298] Updated weights for policy 0, policy_version 65380 (0.0008) -[2023-10-15 04:54:23,433][88300] Updated weights for policy 1, policy_version 65772 (0.0008) -[2023-10-15 04:54:23,465][88298] Updated weights for policy 0, policy_version 65390 (0.0009) -[2023-10-15 04:54:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 134283264. Throughput: 0: 1744.8, 1: 1750.4. Samples: 33585616. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:54:23,535][87330] Avg episode reward: [(0, '22.390'), (1, '22.480')] -[2023-10-15 04:54:23,798][88300] Updated weights for policy 1, policy_version 65782 (0.0008) -[2023-10-15 04:54:23,838][88298] Updated weights for policy 0, policy_version 65400 (0.0008) -[2023-10-15 04:54:24,166][88300] Updated weights for policy 1, policy_version 65792 (0.0008) -[2023-10-15 04:54:27,868][88298] Updated weights for policy 0, policy_version 65410 (0.0007) -[2023-10-15 04:54:28,056][88300] Updated weights for policy 1, policy_version 65802 (0.0008) -[2023-10-15 04:54:28,236][88298] Updated weights for policy 0, policy_version 65420 (0.0009) -[2023-10-15 04:54:28,426][88300] Updated weights for policy 1, policy_version 65812 (0.0007) -[2023-10-15 04:54:28,534][87330] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 134348800. Throughput: 0: 1746.0, 1: 1735.6. Samples: 33606474. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:54:28,535][87330] Avg episode reward: [(0, '22.400'), (1, '22.510')] -[2023-10-15 04:54:28,599][88298] Updated weights for policy 0, policy_version 65430 (0.0007) -[2023-10-15 04:54:28,783][88300] Updated weights for policy 1, policy_version 65822 (0.0007) -[2023-10-15 04:54:28,967][88298] Updated weights for policy 0, policy_version 65440 (0.0008) -[2023-10-15 04:54:32,689][88300] Updated weights for policy 1, policy_version 65832 (0.0008) -[2023-10-15 04:54:32,912][88298] Updated weights for policy 0, policy_version 65450 (0.0007) -[2023-10-15 04:54:33,062][88300] Updated weights for policy 1, policy_version 65842 (0.0009) -[2023-10-15 04:54:33,277][88298] Updated weights for policy 0, policy_version 65460 (0.0010) -[2023-10-15 04:54:33,435][88300] Updated weights for policy 1, policy_version 65852 (0.0008) -[2023-10-15 04:54:33,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 134414336. Throughput: 0: 1731.1, 1: 1747.6. Samples: 33616488. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:54:33,534][87330] Avg episode reward: [(0, '22.640'), (1, '22.440')] -[2023-10-15 04:54:33,648][88298] Updated weights for policy 0, policy_version 65470 (0.0007) -[2023-10-15 04:54:37,306][88300] Updated weights for policy 1, policy_version 65862 (0.0009) -[2023-10-15 04:54:37,550][88298] Updated weights for policy 0, policy_version 65480 (0.0007) -[2023-10-15 04:54:37,674][88300] Updated weights for policy 1, policy_version 65872 (0.0008) -[2023-10-15 04:54:37,922][88298] Updated weights for policy 0, policy_version 65490 (0.0007) -[2023-10-15 04:54:38,031][88300] Updated weights for policy 1, policy_version 65882 (0.0010) -[2023-10-15 04:54:38,284][88298] Updated weights for policy 0, policy_version 65500 (0.0008) -[2023-10-15 04:54:38,534][87330] Fps is (10 sec: 19661.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 134545408. Throughput: 0: 1748.7, 1: 1757.0. Samples: 33638152. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:54:38,534][87330] Avg episode reward: [(0, '22.680'), (1, '22.630')] -[2023-10-15 04:54:41,792][88300] Updated weights for policy 1, policy_version 65892 (0.0009) -[2023-10-15 04:54:42,156][88300] Updated weights for policy 1, policy_version 65902 (0.0010) -[2023-10-15 04:54:42,269][88298] Updated weights for policy 0, policy_version 65510 (0.0007) -[2023-10-15 04:54:42,519][88300] Updated weights for policy 1, policy_version 65912 (0.0007) -[2023-10-15 04:54:42,632][88298] Updated weights for policy 0, policy_version 65520 (0.0007) -[2023-10-15 04:54:43,005][88298] Updated weights for policy 0, policy_version 65530 (0.0007) -[2023-10-15 04:54:43,534][87330] Fps is (10 sec: 19660.6, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 134610944. Throughput: 0: 1732.6, 1: 1733.6. Samples: 33657826. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:54:43,534][87330] Avg episode reward: [(0, '22.670'), (1, '22.600')] -[2023-10-15 04:54:46,153][88300] Updated weights for policy 1, policy_version 65922 (0.0007) -[2023-10-15 04:54:46,521][88300] Updated weights for policy 1, policy_version 65932 (0.0008) -[2023-10-15 04:54:46,683][88298] Updated weights for policy 0, policy_version 65540 (0.0007) -[2023-10-15 04:54:46,885][88300] Updated weights for policy 1, policy_version 65942 (0.0008) -[2023-10-15 04:54:47,057][88298] Updated weights for policy 0, policy_version 65550 (0.0008) -[2023-10-15 04:54:47,248][88300] Updated weights for policy 1, policy_version 65952 (0.0009) -[2023-10-15 04:54:47,416][88298] Updated weights for policy 0, policy_version 65560 (0.0009) -[2023-10-15 04:54:48,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 134676480. Throughput: 0: 1749.1, 1: 1766.9. Samples: 33669494. Policy #0 lag: (min: 31.0, avg: 32.0, max: 52.0) -[2023-10-15 04:54:48,535][87330] Avg episode reward: [(0, '22.690'), (1, '22.620')] -[2023-10-15 04:54:51,105][88300] Updated weights for policy 1, policy_version 65962 (0.0008) -[2023-10-15 04:54:51,442][88298] Updated weights for policy 0, policy_version 65570 (0.0008) -[2023-10-15 04:54:51,472][88300] Updated weights for policy 1, policy_version 65972 (0.0009) -[2023-10-15 04:54:51,814][88298] Updated weights for policy 0, policy_version 65580 (0.0009) -[2023-10-15 04:54:51,838][88300] Updated weights for policy 1, policy_version 65982 (0.0008) -[2023-10-15 04:54:52,194][88298] Updated weights for policy 0, policy_version 65590 (0.0008) -[2023-10-15 04:54:52,563][88298] Updated weights for policy 0, policy_version 65600 (0.0009) -[2023-10-15 04:54:53,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 134742016. Throughput: 0: 1732.5, 1: 1740.8. Samples: 33689248. Policy #0 lag: (min: 31.0, avg: 32.0, max: 52.0) -[2023-10-15 04:54:53,535][87330] Avg episode reward: [(0, '22.790'), (1, '22.600')] -[2023-10-15 04:54:55,622][88300] Updated weights for policy 1, policy_version 65992 (0.0008) -[2023-10-15 04:54:55,986][88300] Updated weights for policy 1, policy_version 66002 (0.0009) -[2023-10-15 04:54:56,361][88300] Updated weights for policy 1, policy_version 66012 (0.0010) -[2023-10-15 04:54:56,393][88298] Updated weights for policy 0, policy_version 65610 (0.0009) -[2023-10-15 04:54:56,761][88298] Updated weights for policy 0, policy_version 65620 (0.0011) -[2023-10-15 04:54:57,129][88298] Updated weights for policy 0, policy_version 65630 (0.0010) -[2023-10-15 04:54:58,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 134807552. Throughput: 0: 1700.4, 1: 1747.0. Samples: 33709938. Policy #0 lag: (min: 31.0, avg: 32.0, max: 52.0) -[2023-10-15 04:54:58,535][87330] Avg episode reward: [(0, '22.690'), (1, '22.820')] -[2023-10-15 04:54:58,545][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000065632_67207168.pth... -[2023-10-15 04:54:58,546][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000066016_67600384.pth... -[2023-10-15 04:54:58,576][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000064000_65536000.pth -[2023-10-15 04:54:58,581][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000064384_65929216.pth -[2023-10-15 04:55:00,434][88300] Updated weights for policy 1, policy_version 66022 (0.0008) -[2023-10-15 04:55:00,793][88300] Updated weights for policy 1, policy_version 66032 (0.0009) -[2023-10-15 04:55:01,156][88300] Updated weights for policy 1, policy_version 66042 (0.0009) -[2023-10-15 04:55:01,247][88298] Updated weights for policy 0, policy_version 65640 (0.0007) -[2023-10-15 04:55:01,626][88298] Updated weights for policy 0, policy_version 65650 (0.0007) -[2023-10-15 04:55:01,991][88298] Updated weights for policy 0, policy_version 65660 (0.0009) -[2023-10-15 04:55:03,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 134873088. Throughput: 0: 1737.2, 1: 1752.7. Samples: 33721096. Policy #0 lag: (min: 31.0, avg: 32.0, max: 52.0) -[2023-10-15 04:55:03,535][87330] Avg episode reward: [(0, '22.630'), (1, '22.850')] -[2023-10-15 04:55:05,041][88300] Updated weights for policy 1, policy_version 66052 (0.0008) -[2023-10-15 04:55:05,418][88300] Updated weights for policy 1, policy_version 66062 (0.0009) -[2023-10-15 04:55:05,779][88300] Updated weights for policy 1, policy_version 66072 (0.0009) -[2023-10-15 04:55:06,119][88298] Updated weights for policy 0, policy_version 65670 (0.0008) -[2023-10-15 04:55:06,489][88298] Updated weights for policy 0, policy_version 65680 (0.0007) -[2023-10-15 04:55:06,855][88298] Updated weights for policy 0, policy_version 65690 (0.0008) -[2023-10-15 04:55:08,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 134938624. Throughput: 0: 1710.7, 1: 1748.5. Samples: 33741278. Policy #0 lag: (min: 31.0, avg: 32.0, max: 52.0) -[2023-10-15 04:55:08,535][87330] Avg episode reward: [(0, '22.620'), (1, '22.670')] -[2023-10-15 04:55:09,697][88300] Updated weights for policy 1, policy_version 66082 (0.0008) -[2023-10-15 04:55:10,090][88300] Updated weights for policy 1, policy_version 66092 (0.0009) -[2023-10-15 04:55:10,471][88300] Updated weights for policy 1, policy_version 66102 (0.0009) -[2023-10-15 04:55:10,832][88300] Updated weights for policy 1, policy_version 66112 (0.0008) -[2023-10-15 04:55:10,874][88298] Updated weights for policy 0, policy_version 65700 (0.0008) -[2023-10-15 04:55:11,252][88298] Updated weights for policy 0, policy_version 65710 (0.0008) -[2023-10-15 04:55:11,612][88298] Updated weights for policy 0, policy_version 65720 (0.0010) -[2023-10-15 04:55:13,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 135004160. Throughput: 0: 1707.3, 1: 1759.1. Samples: 33762462. Policy #0 lag: (min: 31.0, avg: 32.0, max: 52.0) -[2023-10-15 04:55:13,534][87330] Avg episode reward: [(0, '22.600'), (1, '22.710')] -[2023-10-15 04:55:14,501][88300] Updated weights for policy 1, policy_version 66122 (0.0007) -[2023-10-15 04:55:14,859][88300] Updated weights for policy 1, policy_version 66132 (0.0009) -[2023-10-15 04:55:15,227][88300] Updated weights for policy 1, policy_version 66142 (0.0008) -[2023-10-15 04:55:15,518][88298] Updated weights for policy 0, policy_version 65730 (0.0009) -[2023-10-15 04:55:15,882][88298] Updated weights for policy 0, policy_version 65740 (0.0007) -[2023-10-15 04:55:16,260][88298] Updated weights for policy 0, policy_version 65750 (0.0007) -[2023-10-15 04:55:16,623][88298] Updated weights for policy 0, policy_version 65760 (0.0009) -[2023-10-15 04:55:18,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 135069696. Throughput: 0: 1734.2, 1: 1745.3. Samples: 33773066. Policy #0 lag: (min: 31.0, avg: 32.0, max: 52.0) -[2023-10-15 04:55:18,534][87330] Avg episode reward: [(0, '22.550'), (1, '22.730')] -[2023-10-15 04:55:19,129][88300] Updated weights for policy 1, policy_version 66152 (0.0010) -[2023-10-15 04:55:19,494][88300] Updated weights for policy 1, policy_version 66162 (0.0008) -[2023-10-15 04:55:19,852][88300] Updated weights for policy 1, policy_version 66172 (0.0009) -[2023-10-15 04:55:20,602][88298] Updated weights for policy 0, policy_version 65770 (0.0007) -[2023-10-15 04:55:20,967][88298] Updated weights for policy 0, policy_version 65780 (0.0009) -[2023-10-15 04:55:21,337][88298] Updated weights for policy 0, policy_version 65790 (0.0010) -[2023-10-15 04:55:23,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 135135232. Throughput: 0: 1708.3, 1: 1744.0. Samples: 33793502. Policy #0 lag: (min: 31.0, avg: 32.0, max: 52.0) -[2023-10-15 04:55:23,534][87330] Avg episode reward: [(0, '22.490'), (1, '22.740')] -[2023-10-15 04:55:23,701][88300] Updated weights for policy 1, policy_version 66182 (0.0008) -[2023-10-15 04:55:24,057][88300] Updated weights for policy 1, policy_version 66192 (0.0010) -[2023-10-15 04:55:24,423][88300] Updated weights for policy 1, policy_version 66202 (0.0009) -[2023-10-15 04:55:25,143][88298] Updated weights for policy 0, policy_version 65800 (0.0008) -[2023-10-15 04:55:25,515][88298] Updated weights for policy 0, policy_version 65810 (0.0008) -[2023-10-15 04:55:25,891][88298] Updated weights for policy 0, policy_version 65820 (0.0007) -[2023-10-15 04:55:28,362][88300] Updated weights for policy 1, policy_version 66212 (0.0008) -[2023-10-15 04:55:28,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.6, 300 sec: 13773.7). Total num frames: 135200768. Throughput: 0: 1726.5, 1: 1768.5. Samples: 33815102. Policy #0 lag: (min: 31.0, avg: 32.0, max: 52.0) -[2023-10-15 04:55:28,534][87330] Avg episode reward: [(0, '22.670'), (1, '22.780')] -[2023-10-15 04:55:28,724][88300] Updated weights for policy 1, policy_version 66222 (0.0009) -[2023-10-15 04:55:29,098][88300] Updated weights for policy 1, policy_version 66232 (0.0010) -[2023-10-15 04:55:29,589][88298] Updated weights for policy 0, policy_version 65830 (0.0009) -[2023-10-15 04:55:29,967][88298] Updated weights for policy 0, policy_version 65840 (0.0008) -[2023-10-15 04:55:30,329][88298] Updated weights for policy 0, policy_version 65850 (0.0007) -[2023-10-15 04:55:32,912][88300] Updated weights for policy 1, policy_version 66242 (0.0009) -[2023-10-15 04:55:33,285][88300] Updated weights for policy 1, policy_version 66252 (0.0008) -[2023-10-15 04:55:33,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 135266304. Throughput: 0: 1711.6, 1: 1735.9. Samples: 33824632. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-15 04:55:33,534][87330] Avg episode reward: [(0, '22.710'), (1, '22.760')] -[2023-10-15 04:55:33,649][88300] Updated weights for policy 1, policy_version 66262 (0.0008) -[2023-10-15 04:55:34,013][88300] Updated weights for policy 1, policy_version 66272 (0.0008) -[2023-10-15 04:55:34,393][88298] Updated weights for policy 0, policy_version 65860 (0.0008) -[2023-10-15 04:55:34,768][88298] Updated weights for policy 0, policy_version 65870 (0.0010) -[2023-10-15 04:55:35,146][88298] Updated weights for policy 0, policy_version 65880 (0.0009) -[2023-10-15 04:55:37,918][88300] Updated weights for policy 1, policy_version 66282 (0.0009) -[2023-10-15 04:55:38,292][88300] Updated weights for policy 1, policy_version 66292 (0.0008) -[2023-10-15 04:55:38,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 135331840. Throughput: 0: 1724.9, 1: 1763.2. Samples: 33846212. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-15 04:55:38,534][87330] Avg episode reward: [(0, '22.360'), (1, '22.720')] -[2023-10-15 04:55:38,659][88300] Updated weights for policy 1, policy_version 66302 (0.0007) -[2023-10-15 04:55:39,171][88298] Updated weights for policy 0, policy_version 65890 (0.0008) -[2023-10-15 04:55:39,540][88298] Updated weights for policy 0, policy_version 65900 (0.0008) -[2023-10-15 04:55:39,907][88298] Updated weights for policy 0, policy_version 65910 (0.0008) -[2023-10-15 04:55:40,275][88298] Updated weights for policy 0, policy_version 65920 (0.0007) -[2023-10-15 04:55:42,542][88300] Updated weights for policy 1, policy_version 66312 (0.0007) -[2023-10-15 04:55:42,910][88300] Updated weights for policy 1, policy_version 66322 (0.0008) -[2023-10-15 04:55:43,281][88300] Updated weights for policy 1, policy_version 66332 (0.0008) -[2023-10-15 04:55:43,534][87330] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 135430144. Throughput: 0: 1751.2, 1: 1738.4. Samples: 33866970. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-15 04:55:43,535][87330] Avg episode reward: [(0, '22.330'), (1, '22.900')] -[2023-10-15 04:55:44,212][88298] Updated weights for policy 0, policy_version 65930 (0.0008) -[2023-10-15 04:55:44,578][88298] Updated weights for policy 0, policy_version 65940 (0.0010) -[2023-10-15 04:55:44,956][88298] Updated weights for policy 0, policy_version 65950 (0.0011) -[2023-10-15 04:55:47,291][88300] Updated weights for policy 1, policy_version 66342 (0.0009) -[2023-10-15 04:55:47,660][88300] Updated weights for policy 1, policy_version 66352 (0.0007) -[2023-10-15 04:55:48,022][88300] Updated weights for policy 1, policy_version 66362 (0.0007) -[2023-10-15 04:55:48,534][87330] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 135495680. Throughput: 0: 1718.4, 1: 1755.0. Samples: 33877398. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-15 04:55:48,535][87330] Avg episode reward: [(0, '22.360'), (1, '22.900')] -[2023-10-15 04:55:48,968][88298] Updated weights for policy 0, policy_version 65960 (0.0009) -[2023-10-15 04:55:49,343][88298] Updated weights for policy 0, policy_version 65970 (0.0007) -[2023-10-15 04:55:49,708][88298] Updated weights for policy 0, policy_version 65980 (0.0007) -[2023-10-15 04:55:51,898][88300] Updated weights for policy 1, policy_version 66372 (0.0007) -[2023-10-15 04:55:52,263][88300] Updated weights for policy 1, policy_version 66382 (0.0008) -[2023-10-15 04:55:52,628][88300] Updated weights for policy 1, policy_version 66392 (0.0008) -[2023-10-15 04:55:53,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 135561216. Throughput: 0: 1742.6, 1: 1750.7. Samples: 33898474. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-15 04:55:53,535][87330] Avg episode reward: [(0, '22.350'), (1, '22.780')] -[2023-10-15 04:55:53,545][88298] Updated weights for policy 0, policy_version 65990 (0.0009) -[2023-10-15 04:55:53,915][88298] Updated weights for policy 0, policy_version 66000 (0.0007) -[2023-10-15 04:55:54,282][88298] Updated weights for policy 0, policy_version 66010 (0.0008) -[2023-10-15 04:55:56,572][88300] Updated weights for policy 1, policy_version 66402 (0.0009) -[2023-10-15 04:55:56,952][88300] Updated weights for policy 1, policy_version 66412 (0.0011) -[2023-10-15 04:55:57,318][88300] Updated weights for policy 1, policy_version 66422 (0.0011) -[2023-10-15 04:55:57,689][88300] Updated weights for policy 1, policy_version 66432 (0.0010) -[2023-10-15 04:55:58,036][88298] Updated weights for policy 0, policy_version 66020 (0.0008) -[2023-10-15 04:55:58,409][88298] Updated weights for policy 0, policy_version 66030 (0.0009) -[2023-10-15 04:55:58,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 135626752. Throughput: 0: 1750.2, 1: 1733.9. Samples: 33919246. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-15 04:55:58,534][87330] Avg episode reward: [(0, '22.340'), (1, '22.760')] -[2023-10-15 04:55:58,778][88298] Updated weights for policy 0, policy_version 66040 (0.0010) -[2023-10-15 04:56:01,496][88300] Updated weights for policy 1, policy_version 66442 (0.0011) -[2023-10-15 04:56:01,859][88300] Updated weights for policy 1, policy_version 66452 (0.0010) -[2023-10-15 04:56:02,232][88300] Updated weights for policy 1, policy_version 66462 (0.0009) -[2023-10-15 04:56:02,668][88298] Updated weights for policy 0, policy_version 66050 (0.0009) -[2023-10-15 04:56:03,039][88298] Updated weights for policy 0, policy_version 66060 (0.0009) -[2023-10-15 04:56:03,402][88298] Updated weights for policy 0, policy_version 66070 (0.0010) -[2023-10-15 04:56:03,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 135692288. Throughput: 0: 1721.5, 1: 1764.2. Samples: 33929920. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-15 04:56:03,534][87330] Avg episode reward: [(0, '22.290'), (1, '22.800')] -[2023-10-15 04:56:03,778][88298] Updated weights for policy 0, policy_version 66080 (0.0010) -[2023-10-15 04:56:06,254][88300] Updated weights for policy 1, policy_version 66472 (0.0010) -[2023-10-15 04:56:06,620][88300] Updated weights for policy 1, policy_version 66482 (0.0011) -[2023-10-15 04:56:06,994][88300] Updated weights for policy 1, policy_version 66492 (0.0008) -[2023-10-15 04:56:07,668][88298] Updated weights for policy 0, policy_version 66090 (0.0009) -[2023-10-15 04:56:08,033][88298] Updated weights for policy 0, policy_version 66100 (0.0007) -[2023-10-15 04:56:08,402][88298] Updated weights for policy 0, policy_version 66110 (0.0010) -[2023-10-15 04:56:08,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 135790592. Throughput: 0: 1747.0, 1: 1732.6. Samples: 33950086. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-15 04:56:08,534][87330] Avg episode reward: [(0, '22.430'), (1, '22.830')] -[2023-10-15 04:56:10,671][88300] Updated weights for policy 1, policy_version 66502 (0.0008) -[2023-10-15 04:56:11,047][88300] Updated weights for policy 1, policy_version 66512 (0.0008) -[2023-10-15 04:56:11,413][88300] Updated weights for policy 1, policy_version 66522 (0.0008) -[2023-10-15 04:56:12,287][88298] Updated weights for policy 0, policy_version 66120 (0.0007) -[2023-10-15 04:56:12,664][88298] Updated weights for policy 0, policy_version 66130 (0.0007) -[2023-10-15 04:56:13,037][88298] Updated weights for policy 0, policy_version 66140 (0.0008) -[2023-10-15 04:56:13,534][87330] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 135856128. Throughput: 0: 1732.6, 1: 1738.3. Samples: 33971290. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:56:13,535][87330] Avg episode reward: [(0, '22.690'), (1, '22.860')] -[2023-10-15 04:56:15,226][88300] Updated weights for policy 1, policy_version 66532 (0.0009) -[2023-10-15 04:56:15,597][88300] Updated weights for policy 1, policy_version 66542 (0.0010) -[2023-10-15 04:56:15,953][88300] Updated weights for policy 1, policy_version 66552 (0.0010) -[2023-10-15 04:56:16,685][88298] Updated weights for policy 0, policy_version 66150 (0.0010) -[2023-10-15 04:56:17,049][88298] Updated weights for policy 0, policy_version 66160 (0.0008) -[2023-10-15 04:56:17,412][88298] Updated weights for policy 0, policy_version 66170 (0.0010) -[2023-10-15 04:56:18,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 135921664. Throughput: 0: 1752.2, 1: 1741.9. Samples: 33981866. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:56:18,534][87330] Avg episode reward: [(0, '22.710'), (1, '22.890')] -[2023-10-15 04:56:19,841][88300] Updated weights for policy 1, policy_version 66562 (0.0010) -[2023-10-15 04:56:20,214][88300] Updated weights for policy 1, policy_version 66572 (0.0009) -[2023-10-15 04:56:20,590][88300] Updated weights for policy 1, policy_version 66582 (0.0009) -[2023-10-15 04:56:20,954][88300] Updated weights for policy 1, policy_version 66592 (0.0008) -[2023-10-15 04:56:21,400][88298] Updated weights for policy 0, policy_version 66180 (0.0008) -[2023-10-15 04:56:21,778][88298] Updated weights for policy 0, policy_version 66190 (0.0007) -[2023-10-15 04:56:22,139][88298] Updated weights for policy 0, policy_version 66200 (0.0010) -[2023-10-15 04:56:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 135987200. Throughput: 0: 1743.6, 1: 1737.3. Samples: 34002850. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:56:23,535][87330] Avg episode reward: [(0, '22.730'), (1, '22.930')] -[2023-10-15 04:56:24,906][88300] Updated weights for policy 1, policy_version 66602 (0.0010) -[2023-10-15 04:56:25,273][88300] Updated weights for policy 1, policy_version 66612 (0.0007) -[2023-10-15 04:56:25,649][88300] Updated weights for policy 1, policy_version 66622 (0.0008) -[2023-10-15 04:56:26,085][88298] Updated weights for policy 0, policy_version 66210 (0.0007) -[2023-10-15 04:56:26,461][88298] Updated weights for policy 0, policy_version 66220 (0.0009) -[2023-10-15 04:56:26,820][88298] Updated weights for policy 0, policy_version 66230 (0.0008) -[2023-10-15 04:56:27,189][88298] Updated weights for policy 0, policy_version 66240 (0.0007) -[2023-10-15 04:56:28,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 136052736. Throughput: 0: 1720.1, 1: 1759.4. Samples: 34023548. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:56:28,535][87330] Avg episode reward: [(0, '22.680'), (1, '23.000')] -[2023-10-15 04:56:28,549][88033] Saving new best policy, reward=23.000! -[2023-10-15 04:56:29,597][88300] Updated weights for policy 1, policy_version 66632 (0.0008) -[2023-10-15 04:56:29,965][88300] Updated weights for policy 1, policy_version 66642 (0.0009) -[2023-10-15 04:56:30,333][88300] Updated weights for policy 1, policy_version 66652 (0.0009) -[2023-10-15 04:56:31,136][88298] Updated weights for policy 0, policy_version 66250 (0.0009) -[2023-10-15 04:56:31,516][88298] Updated weights for policy 0, policy_version 66260 (0.0008) -[2023-10-15 04:56:31,880][88298] Updated weights for policy 0, policy_version 66270 (0.0007) -[2023-10-15 04:56:33,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 136118272. Throughput: 0: 1751.3, 1: 1736.1. Samples: 34034332. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:56:33,534][87330] Avg episode reward: [(0, '22.730'), (1, '22.970')] -[2023-10-15 04:56:34,141][88300] Updated weights for policy 1, policy_version 66662 (0.0009) -[2023-10-15 04:56:34,514][88300] Updated weights for policy 1, policy_version 66672 (0.0011) -[2023-10-15 04:56:34,883][88300] Updated weights for policy 1, policy_version 66682 (0.0011) -[2023-10-15 04:56:35,778][88298] Updated weights for policy 0, policy_version 66280 (0.0008) -[2023-10-15 04:56:36,153][88298] Updated weights for policy 0, policy_version 66290 (0.0007) -[2023-10-15 04:56:36,530][88298] Updated weights for policy 0, policy_version 66300 (0.0009) -[2023-10-15 04:56:38,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 136183808. Throughput: 0: 1724.4, 1: 1742.5. Samples: 34054488. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:56:38,535][87330] Avg episode reward: [(0, '22.780'), (1, '22.980')] -[2023-10-15 04:56:38,829][88300] Updated weights for policy 1, policy_version 66692 (0.0008) -[2023-10-15 04:56:39,197][88300] Updated weights for policy 1, policy_version 66702 (0.0008) -[2023-10-15 04:56:39,562][88300] Updated weights for policy 1, policy_version 66712 (0.0009) -[2023-10-15 04:56:40,700][88298] Updated weights for policy 0, policy_version 66310 (0.0007) -[2023-10-15 04:56:41,070][88298] Updated weights for policy 0, policy_version 66320 (0.0007) -[2023-10-15 04:56:41,435][88298] Updated weights for policy 0, policy_version 66330 (0.0007) -[2023-10-15 04:56:43,338][88300] Updated weights for policy 1, policy_version 66722 (0.0008) -[2023-10-15 04:56:43,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 136249344. Throughput: 0: 1718.0, 1: 1765.4. Samples: 34076000. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:56:43,534][87330] Avg episode reward: [(0, '22.760'), (1, '22.890')] -[2023-10-15 04:56:43,772][88300] Updated weights for policy 1, policy_version 66732 (0.0008) -[2023-10-15 04:56:44,143][88300] Updated weights for policy 1, policy_version 66742 (0.0007) -[2023-10-15 04:56:44,510][88300] Updated weights for policy 1, policy_version 66752 (0.0008) -[2023-10-15 04:56:45,301][88298] Updated weights for policy 0, policy_version 66340 (0.0008) -[2023-10-15 04:56:45,677][88298] Updated weights for policy 0, policy_version 66350 (0.0007) -[2023-10-15 04:56:46,040][88298] Updated weights for policy 0, policy_version 66360 (0.0008) -[2023-10-15 04:56:48,387][88300] Updated weights for policy 1, policy_version 66762 (0.0008) -[2023-10-15 04:56:48,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 136314880. Throughput: 0: 1737.2, 1: 1730.7. Samples: 34085978. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:56:48,534][87330] Avg episode reward: [(0, '22.770'), (1, '22.520')] -[2023-10-15 04:56:48,761][88300] Updated weights for policy 1, policy_version 66772 (0.0007) -[2023-10-15 04:56:49,122][88300] Updated weights for policy 1, policy_version 66782 (0.0008) -[2023-10-15 04:56:50,000][88298] Updated weights for policy 0, policy_version 66370 (0.0008) -[2023-10-15 04:56:50,361][88298] Updated weights for policy 0, policy_version 66380 (0.0008) -[2023-10-15 04:56:50,738][88298] Updated weights for policy 0, policy_version 66390 (0.0009) -[2023-10-15 04:56:51,105][88298] Updated weights for policy 0, policy_version 66400 (0.0010) -[2023-10-15 04:56:53,154][88300] Updated weights for policy 1, policy_version 66792 (0.0008) -[2023-10-15 04:56:53,521][88300] Updated weights for policy 1, policy_version 66802 (0.0007) -[2023-10-15 04:56:53,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 136380416. Throughput: 0: 1724.0, 1: 1760.2. Samples: 34106878. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:56:53,534][87330] Avg episode reward: [(0, '22.770'), (1, '22.530')] -[2023-10-15 04:56:53,888][88300] Updated weights for policy 1, policy_version 66812 (0.0008) -[2023-10-15 04:56:54,905][88298] Updated weights for policy 0, policy_version 66410 (0.0011) -[2023-10-15 04:56:55,277][88298] Updated weights for policy 0, policy_version 66420 (0.0009) -[2023-10-15 04:56:55,653][88298] Updated weights for policy 0, policy_version 66430 (0.0010) -[2023-10-15 04:56:57,737][88300] Updated weights for policy 1, policy_version 66822 (0.0009) -[2023-10-15 04:56:58,099][88300] Updated weights for policy 1, policy_version 66832 (0.0007) -[2023-10-15 04:56:58,463][88300] Updated weights for policy 1, policy_version 66842 (0.0007) -[2023-10-15 04:56:58,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 136445952. Throughput: 0: 1740.4, 1: 1736.0. Samples: 34127728. Policy #0 lag: (min: 6.0, avg: 13.8, max: 38.0) -[2023-10-15 04:56:58,535][87330] Avg episode reward: [(0, '22.920'), (1, '22.550')] -[2023-10-15 04:56:58,542][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000066432_68026368.pth... -[2023-10-15 04:56:58,581][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000064832_66387968.pth -[2023-10-15 04:56:58,677][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000066848_68452352.pth... -[2023-10-15 04:56:58,714][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000065216_66781184.pth -[2023-10-15 04:56:59,394][88298] Updated weights for policy 0, policy_version 66440 (0.0007) -[2023-10-15 04:56:59,767][88298] Updated weights for policy 0, policy_version 66450 (0.0008) -[2023-10-15 04:57:00,134][88298] Updated weights for policy 0, policy_version 66460 (0.0007) -[2023-10-15 04:57:02,256][88300] Updated weights for policy 1, policy_version 66852 (0.0007) -[2023-10-15 04:57:02,621][88300] Updated weights for policy 1, policy_version 66862 (0.0008) -[2023-10-15 04:57:02,980][88300] Updated weights for policy 1, policy_version 66872 (0.0008) -[2023-10-15 04:57:03,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 136544256. Throughput: 0: 1721.2, 1: 1753.6. Samples: 34138232. Policy #0 lag: (min: 6.0, avg: 13.8, max: 38.0) -[2023-10-15 04:57:03,534][87330] Avg episode reward: [(0, '22.890'), (1, '22.540')] -[2023-10-15 04:57:03,954][88298] Updated weights for policy 0, policy_version 66470 (0.0007) -[2023-10-15 04:57:04,323][88298] Updated weights for policy 0, policy_version 66480 (0.0009) -[2023-10-15 04:57:04,704][88298] Updated weights for policy 0, policy_version 66490 (0.0010) -[2023-10-15 04:57:06,926][88300] Updated weights for policy 1, policy_version 66882 (0.0009) -[2023-10-15 04:57:07,288][88300] Updated weights for policy 1, policy_version 66892 (0.0007) -[2023-10-15 04:57:07,664][88300] Updated weights for policy 1, policy_version 66902 (0.0010) -[2023-10-15 04:57:08,038][88300] Updated weights for policy 1, policy_version 66912 (0.0010) -[2023-10-15 04:57:08,534][87330] Fps is (10 sec: 16384.2, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 136609792. Throughput: 0: 1728.4, 1: 1747.5. Samples: 34159262. Policy #0 lag: (min: 6.0, avg: 13.8, max: 38.0) -[2023-10-15 04:57:08,534][87330] Avg episode reward: [(0, '22.850'), (1, '22.560')] -[2023-10-15 04:57:08,536][88298] Updated weights for policy 0, policy_version 66500 (0.0010) -[2023-10-15 04:57:08,903][88298] Updated weights for policy 0, policy_version 66510 (0.0011) -[2023-10-15 04:57:09,271][88298] Updated weights for policy 0, policy_version 66520 (0.0008) -[2023-10-15 04:57:11,793][88300] Updated weights for policy 1, policy_version 66922 (0.0008) -[2023-10-15 04:57:12,166][88300] Updated weights for policy 1, policy_version 66932 (0.0007) -[2023-10-15 04:57:12,529][88300] Updated weights for policy 1, policy_version 66942 (0.0008) -[2023-10-15 04:57:13,284][88298] Updated weights for policy 0, policy_version 66530 (0.0008) -[2023-10-15 04:57:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 136675328. Throughput: 0: 1748.0, 1: 1727.8. Samples: 34179958. Policy #0 lag: (min: 6.0, avg: 13.8, max: 38.0) -[2023-10-15 04:57:13,534][87330] Avg episode reward: [(0, '22.860'), (1, '22.680')] -[2023-10-15 04:57:13,652][88298] Updated weights for policy 0, policy_version 66540 (0.0010) -[2023-10-15 04:57:14,027][88298] Updated weights for policy 0, policy_version 66550 (0.0008) -[2023-10-15 04:57:14,387][88298] Updated weights for policy 0, policy_version 66560 (0.0009) -[2023-10-15 04:57:16,442][88300] Updated weights for policy 1, policy_version 66952 (0.0010) -[2023-10-15 04:57:16,810][88300] Updated weights for policy 1, policy_version 66962 (0.0010) -[2023-10-15 04:57:17,185][88300] Updated weights for policy 1, policy_version 66972 (0.0008) -[2023-10-15 04:57:18,425][88298] Updated weights for policy 0, policy_version 66570 (0.0010) -[2023-10-15 04:57:18,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 136740864. Throughput: 0: 1714.7, 1: 1757.9. Samples: 34190600. Policy #0 lag: (min: 6.0, avg: 13.8, max: 38.0) -[2023-10-15 04:57:18,535][87330] Avg episode reward: [(0, '22.720'), (1, '22.690')] -[2023-10-15 04:57:18,794][88298] Updated weights for policy 0, policy_version 66580 (0.0010) -[2023-10-15 04:57:19,157][88298] Updated weights for policy 0, policy_version 66590 (0.0009) -[2023-10-15 04:57:21,053][88300] Updated weights for policy 1, policy_version 66982 (0.0007) -[2023-10-15 04:57:21,417][88300] Updated weights for policy 1, policy_version 66992 (0.0009) -[2023-10-15 04:57:21,786][88300] Updated weights for policy 1, policy_version 67002 (0.0011) -[2023-10-15 04:57:23,310][88298] Updated weights for policy 0, policy_version 66600 (0.0008) -[2023-10-15 04:57:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 136806400. Throughput: 0: 1737.9, 1: 1728.6. Samples: 34210480. Policy #0 lag: (min: 6.0, avg: 13.8, max: 38.0) -[2023-10-15 04:57:23,534][87330] Avg episode reward: [(0, '22.720'), (1, '22.840')] -[2023-10-15 04:57:23,677][88298] Updated weights for policy 0, policy_version 66610 (0.0008) -[2023-10-15 04:57:24,054][88298] Updated weights for policy 0, policy_version 66620 (0.0007) -[2023-10-15 04:57:25,579][88300] Updated weights for policy 1, policy_version 67012 (0.0008) -[2023-10-15 04:57:25,947][88300] Updated weights for policy 1, policy_version 67022 (0.0009) -[2023-10-15 04:57:26,326][88300] Updated weights for policy 1, policy_version 67032 (0.0008) -[2023-10-15 04:57:28,160][88298] Updated weights for policy 0, policy_version 66630 (0.0007) -[2023-10-15 04:57:28,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 136871936. Throughput: 0: 1738.4, 1: 1730.7. Samples: 34232114. Policy #0 lag: (min: 6.0, avg: 13.8, max: 38.0) -[2023-10-15 04:57:28,535][87330] Avg episode reward: [(0, '22.690'), (1, '22.720')] -[2023-10-15 04:57:28,542][88298] Updated weights for policy 0, policy_version 66640 (0.0007) -[2023-10-15 04:57:28,914][88298] Updated weights for policy 0, policy_version 66650 (0.0007) -[2023-10-15 04:57:30,230][88300] Updated weights for policy 1, policy_version 67042 (0.0007) -[2023-10-15 04:57:30,651][88300] Updated weights for policy 1, policy_version 67052 (0.0009) -[2023-10-15 04:57:31,021][88300] Updated weights for policy 1, policy_version 67062 (0.0009) -[2023-10-15 04:57:31,386][88300] Updated weights for policy 1, policy_version 67072 (0.0008) -[2023-10-15 04:57:32,832][88298] Updated weights for policy 0, policy_version 66660 (0.0007) -[2023-10-15 04:57:33,193][88298] Updated weights for policy 0, policy_version 66670 (0.0007) -[2023-10-15 04:57:33,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 136937472. Throughput: 0: 1720.7, 1: 1737.7. Samples: 34241608. Policy #0 lag: (min: 6.0, avg: 13.8, max: 38.0) -[2023-10-15 04:57:33,534][87330] Avg episode reward: [(0, '22.650'), (1, '22.690')] -[2023-10-15 04:57:33,577][88298] Updated weights for policy 0, policy_version 66680 (0.0010) -[2023-10-15 04:57:35,390][88300] Updated weights for policy 1, policy_version 67082 (0.0007) -[2023-10-15 04:57:35,754][88300] Updated weights for policy 1, policy_version 67092 (0.0008) -[2023-10-15 04:57:36,123][88300] Updated weights for policy 1, policy_version 67102 (0.0008) -[2023-10-15 04:57:37,509][88298] Updated weights for policy 0, policy_version 66690 (0.0010) -[2023-10-15 04:57:37,883][88298] Updated weights for policy 0, policy_version 66700 (0.0011) -[2023-10-15 04:57:38,249][88298] Updated weights for policy 0, policy_version 66710 (0.0010) -[2023-10-15 04:57:38,534][87330] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 137003008. Throughput: 0: 1732.4, 1: 1729.9. Samples: 34262684. Policy #0 lag: (min: 6.0, avg: 13.8, max: 38.0) -[2023-10-15 04:57:38,534][87330] Avg episode reward: [(0, '22.640'), (1, '22.490')] -[2023-10-15 04:57:38,618][88298] Updated weights for policy 0, policy_version 66720 (0.0009) -[2023-10-15 04:57:40,012][88300] Updated weights for policy 1, policy_version 67112 (0.0008) -[2023-10-15 04:57:40,379][88300] Updated weights for policy 1, policy_version 67122 (0.0009) -[2023-10-15 04:57:40,745][88300] Updated weights for policy 1, policy_version 67132 (0.0008) -[2023-10-15 04:57:42,301][88298] Updated weights for policy 0, policy_version 66730 (0.0007) -[2023-10-15 04:57:42,676][88298] Updated weights for policy 0, policy_version 66740 (0.0007) -[2023-10-15 04:57:43,033][88298] Updated weights for policy 0, policy_version 66750 (0.0007) -[2023-10-15 04:57:43,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 137101312. Throughput: 0: 1707.9, 1: 1753.0. Samples: 34283470. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:57:43,534][87330] Avg episode reward: [(0, '22.670'), (1, '22.460')] -[2023-10-15 04:57:44,658][88300] Updated weights for policy 1, policy_version 67142 (0.0009) -[2023-10-15 04:57:45,026][88300] Updated weights for policy 1, policy_version 67152 (0.0011) -[2023-10-15 04:57:45,397][88300] Updated weights for policy 1, policy_version 67162 (0.0009) -[2023-10-15 04:57:47,088][88298] Updated weights for policy 0, policy_version 66760 (0.0010) -[2023-10-15 04:57:47,462][88298] Updated weights for policy 0, policy_version 66770 (0.0008) -[2023-10-15 04:57:47,820][88298] Updated weights for policy 0, policy_version 66780 (0.0010) -[2023-10-15 04:57:48,534][87330] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 137166848. Throughput: 0: 1726.0, 1: 1729.9. Samples: 34293746. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:57:48,535][87330] Avg episode reward: [(0, '22.780'), (1, '22.310')] -[2023-10-15 04:57:49,274][88300] Updated weights for policy 1, policy_version 67172 (0.0008) -[2023-10-15 04:57:49,646][88300] Updated weights for policy 1, policy_version 67182 (0.0009) -[2023-10-15 04:57:50,008][88300] Updated weights for policy 1, policy_version 67192 (0.0008) -[2023-10-15 04:57:51,816][88298] Updated weights for policy 0, policy_version 66790 (0.0007) -[2023-10-15 04:57:52,186][88298] Updated weights for policy 0, policy_version 66800 (0.0007) -[2023-10-15 04:57:52,557][88298] Updated weights for policy 0, policy_version 66810 (0.0007) -[2023-10-15 04:57:53,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 137232384. Throughput: 0: 1724.5, 1: 1738.8. Samples: 34315110. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:57:53,534][87330] Avg episode reward: [(0, '22.740'), (1, '22.510')] -[2023-10-15 04:57:53,827][88300] Updated weights for policy 1, policy_version 67202 (0.0008) -[2023-10-15 04:57:54,189][88300] Updated weights for policy 1, policy_version 67212 (0.0008) -[2023-10-15 04:57:54,560][88300] Updated weights for policy 1, policy_version 67222 (0.0009) -[2023-10-15 04:57:54,933][88300] Updated weights for policy 1, policy_version 67232 (0.0010) -[2023-10-15 04:57:56,408][88298] Updated weights for policy 0, policy_version 66820 (0.0007) -[2023-10-15 04:57:56,787][88298] Updated weights for policy 0, policy_version 66830 (0.0010) -[2023-10-15 04:57:57,159][88298] Updated weights for policy 0, policy_version 66840 (0.0009) -[2023-10-15 04:57:58,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 137297920. Throughput: 0: 1700.1, 1: 1759.5. Samples: 34335640. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:57:58,534][87330] Avg episode reward: [(0, '22.800'), (1, '22.640')] -[2023-10-15 04:57:58,761][88300] Updated weights for policy 1, policy_version 67242 (0.0007) -[2023-10-15 04:57:59,122][88300] Updated weights for policy 1, policy_version 67252 (0.0007) -[2023-10-15 04:57:59,491][88300] Updated weights for policy 1, policy_version 67262 (0.0008) -[2023-10-15 04:58:00,967][88298] Updated weights for policy 0, policy_version 66850 (0.0008) -[2023-10-15 04:58:01,344][88298] Updated weights for policy 0, policy_version 66860 (0.0009) -[2023-10-15 04:58:01,708][88298] Updated weights for policy 0, policy_version 66870 (0.0009) -[2023-10-15 04:58:02,077][88298] Updated weights for policy 0, policy_version 66880 (0.0007) -[2023-10-15 04:58:03,310][88300] Updated weights for policy 1, policy_version 67272 (0.0008) -[2023-10-15 04:58:03,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 137363456. Throughput: 0: 1738.7, 1: 1732.6. Samples: 34346810. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:58:03,534][87330] Avg episode reward: [(0, '22.820'), (1, '22.600')] -[2023-10-15 04:58:03,680][88300] Updated weights for policy 1, policy_version 67282 (0.0008) -[2023-10-15 04:58:04,048][88300] Updated weights for policy 1, policy_version 67292 (0.0007) -[2023-10-15 04:58:06,010][88298] Updated weights for policy 0, policy_version 66890 (0.0009) -[2023-10-15 04:58:06,382][88298] Updated weights for policy 0, policy_version 66900 (0.0009) -[2023-10-15 04:58:06,751][88298] Updated weights for policy 0, policy_version 66910 (0.0009) -[2023-10-15 04:58:07,891][88300] Updated weights for policy 1, policy_version 67302 (0.0008) -[2023-10-15 04:58:08,260][88300] Updated weights for policy 1, policy_version 67312 (0.0010) -[2023-10-15 04:58:08,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 137428992. Throughput: 0: 1716.0, 1: 1770.8. Samples: 34367388. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:58:08,534][87330] Avg episode reward: [(0, '22.880'), (1, '22.630')] -[2023-10-15 04:58:08,645][88300] Updated weights for policy 1, policy_version 67322 (0.0009) -[2023-10-15 04:58:10,687][88298] Updated weights for policy 0, policy_version 66920 (0.0007) -[2023-10-15 04:58:11,066][88298] Updated weights for policy 0, policy_version 66930 (0.0007) -[2023-10-15 04:58:11,430][88298] Updated weights for policy 0, policy_version 66940 (0.0009) -[2023-10-15 04:58:12,309][88300] Updated weights for policy 1, policy_version 67332 (0.0010) -[2023-10-15 04:58:12,682][88300] Updated weights for policy 1, policy_version 67342 (0.0009) -[2023-10-15 04:58:13,045][88300] Updated weights for policy 1, policy_version 67352 (0.0009) -[2023-10-15 04:58:13,534][87330] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 13884.8). Total num frames: 137527296. Throughput: 0: 1720.0, 1: 1746.0. Samples: 34388084. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:58:13,535][87330] Avg episode reward: [(0, '22.890'), (1, '22.820')] -[2023-10-15 04:58:15,460][88298] Updated weights for policy 0, policy_version 66950 (0.0008) -[2023-10-15 04:58:15,834][88298] Updated weights for policy 0, policy_version 66960 (0.0008) -[2023-10-15 04:58:16,207][88298] Updated weights for policy 0, policy_version 66970 (0.0008) -[2023-10-15 04:58:17,091][88300] Updated weights for policy 1, policy_version 67362 (0.0008) -[2023-10-15 04:58:17,510][88300] Updated weights for policy 1, policy_version 67372 (0.0009) -[2023-10-15 04:58:17,877][88300] Updated weights for policy 1, policy_version 67382 (0.0009) -[2023-10-15 04:58:18,239][88300] Updated weights for policy 1, policy_version 67392 (0.0008) -[2023-10-15 04:58:18,534][87330] Fps is (10 sec: 16383.5, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 137592832. Throughput: 0: 1731.5, 1: 1769.1. Samples: 34399136. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:58:18,535][87330] Avg episode reward: [(0, '22.870'), (1, '22.950')] -[2023-10-15 04:58:20,239][88298] Updated weights for policy 0, policy_version 66980 (0.0009) -[2023-10-15 04:58:20,614][88298] Updated weights for policy 0, policy_version 66990 (0.0009) -[2023-10-15 04:58:20,988][88298] Updated weights for policy 0, policy_version 67000 (0.0007) -[2023-10-15 04:58:22,019][88300] Updated weights for policy 1, policy_version 67402 (0.0007) -[2023-10-15 04:58:22,392][88300] Updated weights for policy 1, policy_version 67412 (0.0009) -[2023-10-15 04:58:22,763][88300] Updated weights for policy 1, policy_version 67422 (0.0009) -[2023-10-15 04:58:23,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 137658368. Throughput: 0: 1710.1, 1: 1760.5. Samples: 34418864. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-15 04:58:23,535][87330] Avg episode reward: [(0, '22.880'), (1, '22.950')] -[2023-10-15 04:58:24,818][88298] Updated weights for policy 0, policy_version 67010 (0.0008) -[2023-10-15 04:58:25,186][88298] Updated weights for policy 0, policy_version 67020 (0.0007) -[2023-10-15 04:58:25,561][88298] Updated weights for policy 0, policy_version 67030 (0.0007) -[2023-10-15 04:58:25,920][88298] Updated weights for policy 0, policy_version 67040 (0.0010) -[2023-10-15 04:58:26,689][88300] Updated weights for policy 1, policy_version 67432 (0.0008) -[2023-10-15 04:58:27,052][88300] Updated weights for policy 1, policy_version 67442 (0.0007) -[2023-10-15 04:58:27,414][88300] Updated weights for policy 1, policy_version 67452 (0.0008) -[2023-10-15 04:58:28,534][87330] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 137723904. Throughput: 0: 1737.8, 1: 1738.4. Samples: 34439900. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-15 04:58:28,534][87330] Avg episode reward: [(0, '22.910'), (1, '22.830')] -[2023-10-15 04:58:29,693][88298] Updated weights for policy 0, policy_version 67050 (0.0007) -[2023-10-15 04:58:30,070][88298] Updated weights for policy 0, policy_version 67060 (0.0007) -[2023-10-15 04:58:30,441][88298] Updated weights for policy 0, policy_version 67070 (0.0007) -[2023-10-15 04:58:31,465][88300] Updated weights for policy 1, policy_version 67462 (0.0009) -[2023-10-15 04:58:31,825][88300] Updated weights for policy 1, policy_version 67472 (0.0008) -[2023-10-15 04:58:32,192][88300] Updated weights for policy 1, policy_version 67482 (0.0010) -[2023-10-15 04:58:33,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 137789440. Throughput: 0: 1720.9, 1: 1773.6. Samples: 34450998. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-15 04:58:33,535][87330] Avg episode reward: [(0, '22.900'), (1, '22.840')] -[2023-10-15 04:58:34,355][88298] Updated weights for policy 0, policy_version 67080 (0.0007) -[2023-10-15 04:58:34,724][88298] Updated weights for policy 0, policy_version 67090 (0.0009) -[2023-10-15 04:58:35,102][88298] Updated weights for policy 0, policy_version 67100 (0.0008) -[2023-10-15 04:58:36,012][88300] Updated weights for policy 1, policy_version 67492 (0.0009) -[2023-10-15 04:58:36,384][88300] Updated weights for policy 1, policy_version 67502 (0.0010) -[2023-10-15 04:58:36,750][88300] Updated weights for policy 1, policy_version 67512 (0.0009) -[2023-10-15 04:58:38,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 137854976. Throughput: 0: 1724.4, 1: 1741.2. Samples: 34471064. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-15 04:58:38,535][87330] Avg episode reward: [(0, '22.920'), (1, '22.770')] -[2023-10-15 04:58:39,106][88298] Updated weights for policy 0, policy_version 67110 (0.0008) -[2023-10-15 04:58:39,476][88298] Updated weights for policy 0, policy_version 67120 (0.0007) -[2023-10-15 04:58:39,845][88298] Updated weights for policy 0, policy_version 67130 (0.0007) -[2023-10-15 04:58:40,505][88300] Updated weights for policy 1, policy_version 67522 (0.0011) -[2023-10-15 04:58:40,875][88300] Updated weights for policy 1, policy_version 67532 (0.0009) -[2023-10-15 04:58:41,250][88300] Updated weights for policy 1, policy_version 67542 (0.0008) -[2023-10-15 04:58:41,612][88300] Updated weights for policy 1, policy_version 67552 (0.0007) -[2023-10-15 04:58:43,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 137920512. Throughput: 0: 1752.8, 1: 1741.8. Samples: 34492898. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-15 04:58:43,535][87330] Avg episode reward: [(0, '22.960'), (1, '22.710')] -[2023-10-15 04:58:43,694][88298] Updated weights for policy 0, policy_version 67140 (0.0008) -[2023-10-15 04:58:44,074][88298] Updated weights for policy 0, policy_version 67150 (0.0009) -[2023-10-15 04:58:44,436][88298] Updated weights for policy 0, policy_version 67160 (0.0010) -[2023-10-15 04:58:45,510][88300] Updated weights for policy 1, policy_version 67562 (0.0008) -[2023-10-15 04:58:45,880][88300] Updated weights for policy 1, policy_version 67572 (0.0010) -[2023-10-15 04:58:46,250][88300] Updated weights for policy 1, policy_version 67582 (0.0007) -[2023-10-15 04:58:48,276][88298] Updated weights for policy 0, policy_version 67170 (0.0010) -[2023-10-15 04:58:48,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 137986048. Throughput: 0: 1714.3, 1: 1745.5. Samples: 34502504. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-15 04:58:48,535][87330] Avg episode reward: [(0, '22.940'), (1, '22.740')] -[2023-10-15 04:58:48,640][88298] Updated weights for policy 0, policy_version 67180 (0.0008) -[2023-10-15 04:58:49,012][88298] Updated weights for policy 0, policy_version 67190 (0.0008) -[2023-10-15 04:58:49,383][88298] Updated weights for policy 0, policy_version 67200 (0.0009) -[2023-10-15 04:58:50,188][88300] Updated weights for policy 1, policy_version 67592 (0.0010) -[2023-10-15 04:58:50,557][88300] Updated weights for policy 1, policy_version 67602 (0.0008) -[2023-10-15 04:58:50,926][88300] Updated weights for policy 1, policy_version 67612 (0.0010) -[2023-10-15 04:58:53,396][88298] Updated weights for policy 0, policy_version 67210 (0.0007) -[2023-10-15 04:58:53,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 138051584. Throughput: 0: 1746.2, 1: 1732.6. Samples: 34523934. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-15 04:58:53,535][87330] Avg episode reward: [(0, '22.960'), (1, '22.740')] -[2023-10-15 04:58:53,764][88298] Updated weights for policy 0, policy_version 67220 (0.0007) -[2023-10-15 04:58:54,133][88298] Updated weights for policy 0, policy_version 67230 (0.0009) -[2023-10-15 04:58:55,010][88300] Updated weights for policy 1, policy_version 67622 (0.0008) -[2023-10-15 04:58:55,378][88300] Updated weights for policy 1, policy_version 67632 (0.0008) -[2023-10-15 04:58:55,744][88300] Updated weights for policy 1, policy_version 67642 (0.0008) -[2023-10-15 04:58:58,156][88298] Updated weights for policy 0, policy_version 67240 (0.0010) -[2023-10-15 04:58:58,526][88298] Updated weights for policy 0, policy_version 67250 (0.0007) -[2023-10-15 04:58:58,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 138117120. Throughput: 0: 1740.7, 1: 1745.6. Samples: 34544968. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-15 04:58:58,535][87330] Avg episode reward: [(0, '22.910'), (1, '22.660')] -[2023-10-15 04:58:58,544][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000067648_69271552.pth... -[2023-10-15 04:58:58,584][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000066016_67600384.pth -[2023-10-15 04:58:58,896][88298] Updated weights for policy 0, policy_version 67260 (0.0010) -[2023-10-15 04:58:59,045][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000067264_68878336.pth... -[2023-10-15 04:58:59,083][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000065632_67207168.pth -[2023-10-15 04:58:59,517][88300] Updated weights for policy 1, policy_version 67652 (0.0008) -[2023-10-15 04:58:59,882][88300] Updated weights for policy 1, policy_version 67662 (0.0007) -[2023-10-15 04:59:00,254][88300] Updated weights for policy 1, policy_version 67672 (0.0008) -[2023-10-15 04:59:02,812][88298] Updated weights for policy 0, policy_version 67270 (0.0009) -[2023-10-15 04:59:03,193][88298] Updated weights for policy 0, policy_version 67280 (0.0009) -[2023-10-15 04:59:03,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 138182656. Throughput: 0: 1728.5, 1: 1719.5. Samples: 34554296. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-15 04:59:03,534][87330] Avg episode reward: [(0, '22.930'), (1, '22.680')] -[2023-10-15 04:59:03,574][88298] Updated weights for policy 0, policy_version 67290 (0.0008) -[2023-10-15 04:59:04,188][88300] Updated weights for policy 1, policy_version 67682 (0.0010) -[2023-10-15 04:59:04,553][88300] Updated weights for policy 1, policy_version 67692 (0.0008) -[2023-10-15 04:59:04,929][88300] Updated weights for policy 1, policy_version 67702 (0.0009) -[2023-10-15 04:59:05,288][88300] Updated weights for policy 1, policy_version 67712 (0.0009) -[2023-10-15 04:59:07,389][88298] Updated weights for policy 0, policy_version 67300 (0.0008) -[2023-10-15 04:59:07,751][88298] Updated weights for policy 0, policy_version 67310 (0.0007) -[2023-10-15 04:59:08,123][88298] Updated weights for policy 0, policy_version 67320 (0.0007) -[2023-10-15 04:59:08,534][87330] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 138280960. Throughput: 0: 1750.0, 1: 1741.5. Samples: 34575982. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-10-15 04:59:08,535][87330] Avg episode reward: [(0, '22.840'), (1, '22.790')] -[2023-10-15 04:59:09,210][88300] Updated weights for policy 1, policy_version 67722 (0.0007) -[2023-10-15 04:59:09,577][88300] Updated weights for policy 1, policy_version 67732 (0.0008) -[2023-10-15 04:59:09,937][88300] Updated weights for policy 1, policy_version 67742 (0.0009) -[2023-10-15 04:59:12,030][88298] Updated weights for policy 0, policy_version 67330 (0.0007) -[2023-10-15 04:59:12,392][88298] Updated weights for policy 0, policy_version 67340 (0.0009) -[2023-10-15 04:59:12,767][88298] Updated weights for policy 0, policy_version 67350 (0.0007) -[2023-10-15 04:59:13,132][88298] Updated weights for policy 0, policy_version 67360 (0.0007) -[2023-10-15 04:59:13,534][87330] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13995.8). Total num frames: 138346496. Throughput: 0: 1725.4, 1: 1763.6. Samples: 34596908. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-10-15 04:59:13,534][87330] Avg episode reward: [(0, '23.080'), (1, '22.830')] -[2023-10-15 04:59:13,543][87905] Saving new best policy, reward=23.080! -[2023-10-15 04:59:13,731][88300] Updated weights for policy 1, policy_version 67752 (0.0011) -[2023-10-15 04:59:14,101][88300] Updated weights for policy 1, policy_version 67762 (0.0008) -[2023-10-15 04:59:14,467][88300] Updated weights for policy 1, policy_version 67772 (0.0009) -[2023-10-15 04:59:17,119][88298] Updated weights for policy 0, policy_version 67370 (0.0011) -[2023-10-15 04:59:17,490][88298] Updated weights for policy 0, policy_version 67380 (0.0007) -[2023-10-15 04:59:17,865][88298] Updated weights for policy 0, policy_version 67390 (0.0007) -[2023-10-15 04:59:18,309][88300] Updated weights for policy 1, policy_version 67782 (0.0008) -[2023-10-15 04:59:18,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13995.8). Total num frames: 138412032. Throughput: 0: 1742.7, 1: 1730.6. Samples: 34607296. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-10-15 04:59:18,534][87330] Avg episode reward: [(0, '23.230'), (1, '22.850')] -[2023-10-15 04:59:18,535][87905] Saving new best policy, reward=23.230! -[2023-10-15 04:59:18,672][88300] Updated weights for policy 1, policy_version 67792 (0.0008) -[2023-10-15 04:59:19,036][88300] Updated weights for policy 1, policy_version 67802 (0.0008) -[2023-10-15 04:59:21,812][88298] Updated weights for policy 0, policy_version 67400 (0.0007) -[2023-10-15 04:59:22,177][88298] Updated weights for policy 0, policy_version 67410 (0.0007) -[2023-10-15 04:59:22,544][88298] Updated weights for policy 0, policy_version 67420 (0.0007) -[2023-10-15 04:59:22,949][88300] Updated weights for policy 1, policy_version 67812 (0.0008) -[2023-10-15 04:59:23,313][88300] Updated weights for policy 1, policy_version 67822 (0.0007) -[2023-10-15 04:59:23,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 138477568. Throughput: 0: 1733.8, 1: 1761.2. Samples: 34628336. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-10-15 04:59:23,535][87330] Avg episode reward: [(0, '23.150'), (1, '22.830')] -[2023-10-15 04:59:23,677][88300] Updated weights for policy 1, policy_version 67832 (0.0008) -[2023-10-15 04:59:26,486][88298] Updated weights for policy 0, policy_version 67430 (0.0009) -[2023-10-15 04:59:26,855][88298] Updated weights for policy 0, policy_version 67440 (0.0009) -[2023-10-15 04:59:27,224][88298] Updated weights for policy 0, policy_version 67450 (0.0008) -[2023-10-15 04:59:27,571][88300] Updated weights for policy 1, policy_version 67842 (0.0010) -[2023-10-15 04:59:27,934][88300] Updated weights for policy 1, policy_version 67852 (0.0010) -[2023-10-15 04:59:28,296][88300] Updated weights for policy 1, policy_version 67862 (0.0009) -[2023-10-15 04:59:28,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 138543104. Throughput: 0: 1707.8, 1: 1743.1. Samples: 34648190. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-10-15 04:59:28,534][87330] Avg episode reward: [(0, '23.190'), (1, '23.040')] -[2023-10-15 04:59:28,664][88033] Saving new best policy, reward=23.040! -[2023-10-15 04:59:28,668][88300] Updated weights for policy 1, policy_version 67872 (0.0008) -[2023-10-15 04:59:31,160][88298] Updated weights for policy 0, policy_version 67460 (0.0009) -[2023-10-15 04:59:31,530][88298] Updated weights for policy 0, policy_version 67470 (0.0008) -[2023-10-15 04:59:31,897][88298] Updated weights for policy 0, policy_version 67480 (0.0008) -[2023-10-15 04:59:32,651][88300] Updated weights for policy 1, policy_version 67882 (0.0008) -[2023-10-15 04:59:33,017][88300] Updated weights for policy 1, policy_version 67892 (0.0008) -[2023-10-15 04:59:33,383][88300] Updated weights for policy 1, policy_version 67902 (0.0007) -[2023-10-15 04:59:33,534][87330] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 138641408. Throughput: 0: 1742.9, 1: 1754.4. Samples: 34659884. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-10-15 04:59:33,534][87330] Avg episode reward: [(0, '22.950'), (1, '23.040')] -[2023-10-15 04:59:35,734][88298] Updated weights for policy 0, policy_version 67490 (0.0008) -[2023-10-15 04:59:36,100][88298] Updated weights for policy 0, policy_version 67500 (0.0008) -[2023-10-15 04:59:36,469][88298] Updated weights for policy 0, policy_version 67510 (0.0007) -[2023-10-15 04:59:36,834][88298] Updated weights for policy 0, policy_version 67520 (0.0008) -[2023-10-15 04:59:37,203][88300] Updated weights for policy 1, policy_version 67912 (0.0008) -[2023-10-15 04:59:37,567][88300] Updated weights for policy 1, policy_version 67922 (0.0009) -[2023-10-15 04:59:37,937][88300] Updated weights for policy 1, policy_version 67932 (0.0009) -[2023-10-15 04:59:38,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 138706944. Throughput: 0: 1712.6, 1: 1757.3. Samples: 34680080. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-10-15 04:59:38,535][87330] Avg episode reward: [(0, '22.690'), (1, '23.040')] -[2023-10-15 04:59:40,718][88298] Updated weights for policy 0, policy_version 67530 (0.0007) -[2023-10-15 04:59:41,101][88298] Updated weights for policy 0, policy_version 67540 (0.0009) -[2023-10-15 04:59:41,465][88298] Updated weights for policy 0, policy_version 67550 (0.0010) -[2023-10-15 04:59:41,757][88300] Updated weights for policy 1, policy_version 67942 (0.0007) -[2023-10-15 04:59:42,131][88300] Updated weights for policy 1, policy_version 67952 (0.0007) -[2023-10-15 04:59:42,497][88300] Updated weights for policy 1, policy_version 67962 (0.0008) -[2023-10-15 04:59:43,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 138772480. Throughput: 0: 1716.2, 1: 1739.9. Samples: 34700494. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-10-15 04:59:43,535][87330] Avg episode reward: [(0, '22.450'), (1, '22.960')] -[2023-10-15 04:59:45,342][88298] Updated weights for policy 0, policy_version 67560 (0.0007) -[2023-10-15 04:59:45,713][88298] Updated weights for policy 0, policy_version 67570 (0.0007) -[2023-10-15 04:59:46,083][88298] Updated weights for policy 0, policy_version 67580 (0.0009) -[2023-10-15 04:59:46,349][88300] Updated weights for policy 1, policy_version 67972 (0.0007) -[2023-10-15 04:59:46,711][88300] Updated weights for policy 1, policy_version 67982 (0.0010) -[2023-10-15 04:59:47,082][88300] Updated weights for policy 1, policy_version 67992 (0.0008) -[2023-10-15 04:59:48,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 138838016. Throughput: 0: 1729.1, 1: 1771.4. Samples: 34711820. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:59:48,534][87330] Avg episode reward: [(0, '22.320'), (1, '22.980')] -[2023-10-15 04:59:50,110][88298] Updated weights for policy 0, policy_version 67590 (0.0010) -[2023-10-15 04:59:50,475][88298] Updated weights for policy 0, policy_version 67600 (0.0009) -[2023-10-15 04:59:50,841][88298] Updated weights for policy 0, policy_version 67610 (0.0008) -[2023-10-15 04:59:50,947][88300] Updated weights for policy 1, policy_version 68002 (0.0008) -[2023-10-15 04:59:51,316][88300] Updated weights for policy 1, policy_version 68012 (0.0010) -[2023-10-15 04:59:51,685][88300] Updated weights for policy 1, policy_version 68022 (0.0008) -[2023-10-15 04:59:52,058][88300] Updated weights for policy 1, policy_version 68032 (0.0010) -[2023-10-15 04:59:53,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 138903552. Throughput: 0: 1714.0, 1: 1739.4. Samples: 34731386. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:59:53,534][87330] Avg episode reward: [(0, '22.210'), (1, '23.010')] -[2023-10-15 04:59:54,926][88298] Updated weights for policy 0, policy_version 67620 (0.0009) -[2023-10-15 04:59:55,299][88298] Updated weights for policy 0, policy_version 67630 (0.0008) -[2023-10-15 04:59:55,679][88298] Updated weights for policy 0, policy_version 67640 (0.0009) -[2023-10-15 04:59:55,968][88300] Updated weights for policy 1, policy_version 68042 (0.0008) -[2023-10-15 04:59:56,344][88300] Updated weights for policy 1, policy_version 68052 (0.0009) -[2023-10-15 04:59:56,722][88300] Updated weights for policy 1, policy_version 68062 (0.0007) -[2023-10-15 04:59:58,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.6, 300 sec: 13884.8). Total num frames: 138969088. Throughput: 0: 1734.1, 1: 1740.3. Samples: 34753254. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 04:59:58,534][87330] Avg episode reward: [(0, '22.420'), (1, '22.970')] -[2023-10-15 04:59:59,708][88298] Updated weights for policy 0, policy_version 67650 (0.0008) -[2023-10-15 05:00:00,085][88298] Updated weights for policy 0, policy_version 67660 (0.0008) -[2023-10-15 05:00:00,441][88298] Updated weights for policy 0, policy_version 67670 (0.0008) -[2023-10-15 05:00:00,525][88300] Updated weights for policy 1, policy_version 68072 (0.0008) -[2023-10-15 05:00:00,813][88298] Updated weights for policy 0, policy_version 67680 (0.0008) -[2023-10-15 05:00:00,881][88300] Updated weights for policy 1, policy_version 68082 (0.0008) -[2023-10-15 05:00:01,244][88300] Updated weights for policy 1, policy_version 68092 (0.0009) -[2023-10-15 05:00:03,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 139034624. Throughput: 0: 1713.6, 1: 1743.3. Samples: 34762858. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:00:03,534][87330] Avg episode reward: [(0, '22.670'), (1, '22.970')] -[2023-10-15 05:00:04,536][88298] Updated weights for policy 0, policy_version 67690 (0.0009) -[2023-10-15 05:00:04,917][88298] Updated weights for policy 0, policy_version 67700 (0.0011) -[2023-10-15 05:00:05,274][88298] Updated weights for policy 0, policy_version 67710 (0.0009) -[2023-10-15 05:00:05,311][88300] Updated weights for policy 1, policy_version 68102 (0.0009) -[2023-10-15 05:00:05,681][88300] Updated weights for policy 1, policy_version 68112 (0.0010) -[2023-10-15 05:00:06,056][88300] Updated weights for policy 1, policy_version 68122 (0.0010) -[2023-10-15 05:00:08,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 139100160. Throughput: 0: 1730.3, 1: 1733.5. Samples: 34784204. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:00:08,534][87330] Avg episode reward: [(0, '22.950'), (1, '22.950')] -[2023-10-15 05:00:09,021][88298] Updated weights for policy 0, policy_version 67720 (0.0007) -[2023-10-15 05:00:09,394][88298] Updated weights for policy 0, policy_version 67730 (0.0007) -[2023-10-15 05:00:09,764][88298] Updated weights for policy 0, policy_version 67740 (0.0008) -[2023-10-15 05:00:09,905][88300] Updated weights for policy 1, policy_version 68132 (0.0009) -[2023-10-15 05:00:10,270][88300] Updated weights for policy 1, policy_version 68142 (0.0011) -[2023-10-15 05:00:10,643][88300] Updated weights for policy 1, policy_version 68152 (0.0010) -[2023-10-15 05:00:13,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 139165696. Throughput: 0: 1755.7, 1: 1755.0. Samples: 34806170. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:00:13,534][87330] Avg episode reward: [(0, '22.990'), (1, '23.020')] -[2023-10-15 05:00:13,713][88298] Updated weights for policy 0, policy_version 67750 (0.0009) -[2023-10-15 05:00:14,088][88298] Updated weights for policy 0, policy_version 67760 (0.0011) -[2023-10-15 05:00:14,444][88300] Updated weights for policy 1, policy_version 68162 (0.0010) -[2023-10-15 05:00:14,463][88298] Updated weights for policy 0, policy_version 67770 (0.0009) -[2023-10-15 05:00:14,808][88300] Updated weights for policy 1, policy_version 68172 (0.0010) -[2023-10-15 05:00:15,181][88300] Updated weights for policy 1, policy_version 68182 (0.0010) -[2023-10-15 05:00:15,541][88300] Updated weights for policy 1, policy_version 68192 (0.0011) -[2023-10-15 05:00:18,390][88298] Updated weights for policy 0, policy_version 67780 (0.0007) -[2023-10-15 05:00:18,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 139231232. Throughput: 0: 1722.4, 1: 1738.5. Samples: 34815624. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:00:18,534][87330] Avg episode reward: [(0, '23.000'), (1, '23.030')] -[2023-10-15 05:00:18,757][88298] Updated weights for policy 0, policy_version 67790 (0.0007) -[2023-10-15 05:00:19,127][88298] Updated weights for policy 0, policy_version 67800 (0.0010) -[2023-10-15 05:00:19,343][88300] Updated weights for policy 1, policy_version 68202 (0.0007) -[2023-10-15 05:00:19,709][88300] Updated weights for policy 1, policy_version 68212 (0.0010) -[2023-10-15 05:00:20,087][88300] Updated weights for policy 1, policy_version 68222 (0.0008) -[2023-10-15 05:00:23,224][88298] Updated weights for policy 0, policy_version 67810 (0.0009) -[2023-10-15 05:00:23,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 139296768. Throughput: 0: 1741.8, 1: 1745.0. Samples: 34836986. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:00:23,535][87330] Avg episode reward: [(0, '23.030'), (1, '23.050')] -[2023-10-15 05:00:23,537][88033] Saving new best policy, reward=23.050! -[2023-10-15 05:00:23,597][88298] Updated weights for policy 0, policy_version 67820 (0.0011) -[2023-10-15 05:00:23,969][88300] Updated weights for policy 1, policy_version 68232 (0.0008) -[2023-10-15 05:00:23,972][88298] Updated weights for policy 0, policy_version 67830 (0.0009) -[2023-10-15 05:00:24,337][88300] Updated weights for policy 1, policy_version 68242 (0.0009) -[2023-10-15 05:00:24,345][88298] Updated weights for policy 0, policy_version 67840 (0.0008) -[2023-10-15 05:00:24,703][88300] Updated weights for policy 1, policy_version 68252 (0.0007) -[2023-10-15 05:00:28,316][88298] Updated weights for policy 0, policy_version 67850 (0.0009) -[2023-10-15 05:00:28,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 139362304. Throughput: 0: 1740.3, 1: 1769.3. Samples: 34858426. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:00:28,535][87330] Avg episode reward: [(0, '23.030'), (1, '23.030')] -[2023-10-15 05:00:28,620][88300] Updated weights for policy 1, policy_version 68262 (0.0009) -[2023-10-15 05:00:28,688][88298] Updated weights for policy 0, policy_version 67860 (0.0008) -[2023-10-15 05:00:28,986][88300] Updated weights for policy 1, policy_version 68272 (0.0007) -[2023-10-15 05:00:29,047][88298] Updated weights for policy 0, policy_version 67870 (0.0008) -[2023-10-15 05:00:29,356][88300] Updated weights for policy 1, policy_version 68282 (0.0008) -[2023-10-15 05:00:33,034][88298] Updated weights for policy 0, policy_version 67880 (0.0008) -[2023-10-15 05:00:33,370][88300] Updated weights for policy 1, policy_version 68292 (0.0009) -[2023-10-15 05:00:33,404][88298] Updated weights for policy 0, policy_version 67890 (0.0008) -[2023-10-15 05:00:33,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13884.7). Total num frames: 139427840. Throughput: 0: 1727.2, 1: 1735.1. Samples: 34867622. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:00:33,534][87330] Avg episode reward: [(0, '23.020'), (1, '23.070')] -[2023-10-15 05:00:33,742][88300] Updated weights for policy 1, policy_version 68302 (0.0008) -[2023-10-15 05:00:33,777][88298] Updated weights for policy 0, policy_version 67900 (0.0007) -[2023-10-15 05:00:34,111][88300] Updated weights for policy 1, policy_version 68312 (0.0009) -[2023-10-15 05:00:34,400][88033] Saving new best policy, reward=23.070! -[2023-10-15 05:00:37,702][88298] Updated weights for policy 0, policy_version 67910 (0.0008) -[2023-10-15 05:00:38,074][88300] Updated weights for policy 1, policy_version 68322 (0.0007) -[2023-10-15 05:00:38,094][88298] Updated weights for policy 0, policy_version 67920 (0.0007) -[2023-10-15 05:00:38,430][88300] Updated weights for policy 1, policy_version 68332 (0.0008) -[2023-10-15 05:00:38,462][88298] Updated weights for policy 0, policy_version 67930 (0.0007) -[2023-10-15 05:00:38,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 139493376. Throughput: 0: 1745.6, 1: 1761.0. Samples: 34889186. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:00:38,534][87330] Avg episode reward: [(0, '22.980'), (1, '23.080')] -[2023-10-15 05:00:38,805][88300] Updated weights for policy 1, policy_version 68342 (0.0008) -[2023-10-15 05:00:39,168][88033] Saving new best policy, reward=23.080! -[2023-10-15 05:00:39,172][88300] Updated weights for policy 1, policy_version 68352 (0.0008) -[2023-10-15 05:00:42,455][88298] Updated weights for policy 0, policy_version 67940 (0.0008) -[2023-10-15 05:00:42,821][88298] Updated weights for policy 0, policy_version 67950 (0.0009) -[2023-10-15 05:00:43,066][88300] Updated weights for policy 1, policy_version 68362 (0.0008) -[2023-10-15 05:00:43,184][88298] Updated weights for policy 0, policy_version 67960 (0.0007) -[2023-10-15 05:00:43,422][88300] Updated weights for policy 1, policy_version 68372 (0.0007) -[2023-10-15 05:00:43,534][87330] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 139591680. Throughput: 0: 1726.9, 1: 1742.3. Samples: 34909370. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:00:43,534][87330] Avg episode reward: [(0, '22.960'), (1, '23.050')] -[2023-10-15 05:00:43,784][88300] Updated weights for policy 1, policy_version 68382 (0.0008) -[2023-10-15 05:00:46,985][88298] Updated weights for policy 0, policy_version 67970 (0.0007) -[2023-10-15 05:00:47,362][88298] Updated weights for policy 0, policy_version 67980 (0.0007) -[2023-10-15 05:00:47,585][88300] Updated weights for policy 1, policy_version 68392 (0.0010) -[2023-10-15 05:00:47,721][88298] Updated weights for policy 0, policy_version 67990 (0.0008) -[2023-10-15 05:00:47,950][88300] Updated weights for policy 1, policy_version 68402 (0.0008) -[2023-10-15 05:00:48,093][88298] Updated weights for policy 0, policy_version 68000 (0.0008) -[2023-10-15 05:00:48,312][88300] Updated weights for policy 1, policy_version 68412 (0.0009) -[2023-10-15 05:00:48,534][87330] Fps is (10 sec: 19660.6, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 139689984. Throughput: 0: 1740.5, 1: 1753.6. Samples: 34920094. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:00:48,535][87330] Avg episode reward: [(0, '22.930'), (1, '23.010')] -[2023-10-15 05:00:52,036][88298] Updated weights for policy 0, policy_version 68010 (0.0008) -[2023-10-15 05:00:52,210][88300] Updated weights for policy 1, policy_version 68422 (0.0007) -[2023-10-15 05:00:52,410][88298] Updated weights for policy 0, policy_version 68020 (0.0007) -[2023-10-15 05:00:52,576][88300] Updated weights for policy 1, policy_version 68432 (0.0007) -[2023-10-15 05:00:52,777][88298] Updated weights for policy 0, policy_version 68030 (0.0007) -[2023-10-15 05:00:52,949][88300] Updated weights for policy 1, policy_version 68442 (0.0009) -[2023-10-15 05:00:53,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 139755520. Throughput: 0: 1733.4, 1: 1765.2. Samples: 34941640. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:00:53,534][87330] Avg episode reward: [(0, '22.790'), (1, '23.050')] -[2023-10-15 05:00:56,765][88298] Updated weights for policy 0, policy_version 68040 (0.0009) -[2023-10-15 05:00:56,962][88300] Updated weights for policy 1, policy_version 68452 (0.0008) -[2023-10-15 05:00:57,133][88298] Updated weights for policy 0, policy_version 68050 (0.0007) -[2023-10-15 05:00:57,329][88300] Updated weights for policy 1, policy_version 68462 (0.0008) -[2023-10-15 05:00:57,504][88298] Updated weights for policy 0, policy_version 68060 (0.0008) -[2023-10-15 05:00:57,695][88300] Updated weights for policy 1, policy_version 68472 (0.0007) -[2023-10-15 05:00:58,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 139821056. Throughput: 0: 1700.4, 1: 1733.1. Samples: 34960678. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:00:58,534][87330] Avg episode reward: [(0, '22.750'), (1, '22.980')] -[2023-10-15 05:00:58,544][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000068480_70123520.pth... -[2023-10-15 05:00:58,545][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000068064_69697536.pth... -[2023-10-15 05:00:58,574][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000066848_68452352.pth -[2023-10-15 05:00:58,591][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000066432_68026368.pth -[2023-10-15 05:01:01,504][88300] Updated weights for policy 1, policy_version 68482 (0.0009) -[2023-10-15 05:01:01,550][88298] Updated weights for policy 0, policy_version 68070 (0.0008) -[2023-10-15 05:01:01,877][88300] Updated weights for policy 1, policy_version 68492 (0.0008) -[2023-10-15 05:01:01,914][88298] Updated weights for policy 0, policy_version 68080 (0.0008) -[2023-10-15 05:01:02,238][88300] Updated weights for policy 1, policy_version 68502 (0.0007) -[2023-10-15 05:01:02,291][88298] Updated weights for policy 0, policy_version 68090 (0.0008) -[2023-10-15 05:01:02,606][88300] Updated weights for policy 1, policy_version 68512 (0.0008) -[2023-10-15 05:01:03,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 139886592. Throughput: 0: 1728.6, 1: 1759.3. Samples: 34972578. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:01:03,534][87330] Avg episode reward: [(0, '22.700'), (1, '22.970')] -[2023-10-15 05:01:06,331][88298] Updated weights for policy 0, policy_version 68100 (0.0008) -[2023-10-15 05:01:06,467][88300] Updated weights for policy 1, policy_version 68522 (0.0007) -[2023-10-15 05:01:06,698][88298] Updated weights for policy 0, policy_version 68110 (0.0009) -[2023-10-15 05:01:06,827][88300] Updated weights for policy 1, policy_version 68532 (0.0007) -[2023-10-15 05:01:07,070][88298] Updated weights for policy 0, policy_version 68120 (0.0007) -[2023-10-15 05:01:07,188][88300] Updated weights for policy 1, policy_version 68542 (0.0008) -[2023-10-15 05:01:08,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 139952128. Throughput: 0: 1717.6, 1: 1731.2. Samples: 34992180. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:01:08,535][87330] Avg episode reward: [(0, '22.530'), (1, '22.900')] -[2023-10-15 05:01:11,038][88298] Updated weights for policy 0, policy_version 68130 (0.0008) -[2023-10-15 05:01:11,143][88300] Updated weights for policy 1, policy_version 68552 (0.0009) -[2023-10-15 05:01:11,401][88298] Updated weights for policy 0, policy_version 68140 (0.0007) -[2023-10-15 05:01:11,504][88300] Updated weights for policy 1, policy_version 68562 (0.0009) -[2023-10-15 05:01:11,778][88298] Updated weights for policy 0, policy_version 68150 (0.0007) -[2023-10-15 05:01:11,866][88300] Updated weights for policy 1, policy_version 68572 (0.0007) -[2023-10-15 05:01:12,151][88298] Updated weights for policy 0, policy_version 68160 (0.0007) -[2023-10-15 05:01:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 140017664. Throughput: 0: 1703.1, 1: 1727.6. Samples: 35012808. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) -[2023-10-15 05:01:13,534][87330] Avg episode reward: [(0, '22.530'), (1, '22.900')] -[2023-10-15 05:01:15,798][88300] Updated weights for policy 1, policy_version 68582 (0.0008) -[2023-10-15 05:01:15,955][88298] Updated weights for policy 0, policy_version 68170 (0.0010) -[2023-10-15 05:01:16,167][88300] Updated weights for policy 1, policy_version 68592 (0.0008) -[2023-10-15 05:01:16,319][88298] Updated weights for policy 0, policy_version 68180 (0.0007) -[2023-10-15 05:01:16,542][88300] Updated weights for policy 1, policy_version 68602 (0.0008) -[2023-10-15 05:01:16,693][88298] Updated weights for policy 0, policy_version 68190 (0.0009) -[2023-10-15 05:01:18,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 140083200. Throughput: 0: 1729.2, 1: 1745.2. Samples: 35023972. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) -[2023-10-15 05:01:18,534][87330] Avg episode reward: [(0, '22.590'), (1, '22.960')] -[2023-10-15 05:01:20,442][88300] Updated weights for policy 1, policy_version 68612 (0.0008) -[2023-10-15 05:01:20,633][88298] Updated weights for policy 0, policy_version 68200 (0.0008) -[2023-10-15 05:01:20,822][88300] Updated weights for policy 1, policy_version 68622 (0.0008) -[2023-10-15 05:01:20,995][88298] Updated weights for policy 0, policy_version 68210 (0.0009) -[2023-10-15 05:01:21,190][88300] Updated weights for policy 1, policy_version 68632 (0.0010) -[2023-10-15 05:01:21,372][88298] Updated weights for policy 0, policy_version 68220 (0.0008) -[2023-10-15 05:01:23,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 140148736. Throughput: 0: 1701.5, 1: 1731.9. Samples: 35043686. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) -[2023-10-15 05:01:23,534][87330] Avg episode reward: [(0, '22.650'), (1, '22.870')] -[2023-10-15 05:01:25,205][88298] Updated weights for policy 0, policy_version 68230 (0.0007) -[2023-10-15 05:01:25,227][88300] Updated weights for policy 1, policy_version 68642 (0.0008) -[2023-10-15 05:01:25,583][88298] Updated weights for policy 0, policy_version 68240 (0.0007) -[2023-10-15 05:01:25,602][88300] Updated weights for policy 1, policy_version 68652 (0.0009) -[2023-10-15 05:01:25,954][88298] Updated weights for policy 0, policy_version 68250 (0.0007) -[2023-10-15 05:01:25,964][88300] Updated weights for policy 1, policy_version 68662 (0.0009) -[2023-10-15 05:01:26,328][88300] Updated weights for policy 1, policy_version 68672 (0.0007) -[2023-10-15 05:01:28,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 140214272. Throughput: 0: 1718.9, 1: 1742.3. Samples: 35065124. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) -[2023-10-15 05:01:28,535][87330] Avg episode reward: [(0, '22.700'), (1, '22.750')] -[2023-10-15 05:01:29,815][88298] Updated weights for policy 0, policy_version 68260 (0.0008) -[2023-10-15 05:01:30,190][88298] Updated weights for policy 0, policy_version 68270 (0.0009) -[2023-10-15 05:01:30,213][88300] Updated weights for policy 1, policy_version 68682 (0.0009) -[2023-10-15 05:01:30,559][88298] Updated weights for policy 0, policy_version 68280 (0.0008) -[2023-10-15 05:01:30,572][88300] Updated weights for policy 1, policy_version 68692 (0.0009) -[2023-10-15 05:01:30,937][88300] Updated weights for policy 1, policy_version 68702 (0.0007) -[2023-10-15 05:01:33,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13884.8). Total num frames: 140279808. Throughput: 0: 1708.1, 1: 1725.7. Samples: 35074618. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) -[2023-10-15 05:01:33,534][87330] Avg episode reward: [(0, '22.510'), (1, '22.660')] -[2023-10-15 05:01:34,486][88298] Updated weights for policy 0, policy_version 68290 (0.0007) -[2023-10-15 05:01:34,814][88300] Updated weights for policy 1, policy_version 68712 (0.0008) -[2023-10-15 05:01:34,846][88298] Updated weights for policy 0, policy_version 68300 (0.0008) -[2023-10-15 05:01:35,182][88300] Updated weights for policy 1, policy_version 68722 (0.0009) -[2023-10-15 05:01:35,217][88298] Updated weights for policy 0, policy_version 68310 (0.0007) -[2023-10-15 05:01:35,543][88300] Updated weights for policy 1, policy_version 68732 (0.0009) -[2023-10-15 05:01:35,585][88298] Updated weights for policy 0, policy_version 68320 (0.0008) -[2023-10-15 05:01:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 140345344. Throughput: 0: 1701.3, 1: 1727.5. Samples: 35095940. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) -[2023-10-15 05:01:38,535][87330] Avg episode reward: [(0, '22.760'), (1, '22.650')] -[2023-10-15 05:01:39,324][88300] Updated weights for policy 1, policy_version 68742 (0.0009) -[2023-10-15 05:01:39,606][88298] Updated weights for policy 0, policy_version 68330 (0.0008) -[2023-10-15 05:01:39,693][88300] Updated weights for policy 1, policy_version 68752 (0.0009) -[2023-10-15 05:01:39,979][88298] Updated weights for policy 0, policy_version 68340 (0.0008) -[2023-10-15 05:01:40,051][88300] Updated weights for policy 1, policy_version 68762 (0.0008) -[2023-10-15 05:01:40,347][88298] Updated weights for policy 0, policy_version 68350 (0.0008) -[2023-10-15 05:01:43,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 140410880. Throughput: 0: 1731.1, 1: 1754.0. Samples: 35117508. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) -[2023-10-15 05:01:43,535][87330] Avg episode reward: [(0, '22.620'), (1, '22.520')] -[2023-10-15 05:01:43,940][88300] Updated weights for policy 1, policy_version 68772 (0.0008) -[2023-10-15 05:01:44,214][88298] Updated weights for policy 0, policy_version 68360 (0.0008) -[2023-10-15 05:01:44,296][88300] Updated weights for policy 1, policy_version 68782 (0.0007) -[2023-10-15 05:01:44,598][88298] Updated weights for policy 0, policy_version 68370 (0.0008) -[2023-10-15 05:01:44,658][88300] Updated weights for policy 1, policy_version 68792 (0.0008) -[2023-10-15 05:01:44,962][88298] Updated weights for policy 0, policy_version 68380 (0.0008) -[2023-10-15 05:01:48,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13884.7). Total num frames: 140476416. Throughput: 0: 1703.1, 1: 1728.7. Samples: 35127006. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) -[2023-10-15 05:01:48,534][87330] Avg episode reward: [(0, '22.620'), (1, '22.500')] -[2023-10-15 05:01:48,610][88300] Updated weights for policy 1, policy_version 68802 (0.0008) -[2023-10-15 05:01:48,958][88298] Updated weights for policy 0, policy_version 68390 (0.0008) -[2023-10-15 05:01:48,967][88300] Updated weights for policy 1, policy_version 68812 (0.0007) -[2023-10-15 05:01:49,327][88298] Updated weights for policy 0, policy_version 68400 (0.0007) -[2023-10-15 05:01:49,332][88300] Updated weights for policy 1, policy_version 68822 (0.0007) -[2023-10-15 05:01:49,692][88298] Updated weights for policy 0, policy_version 68410 (0.0007) -[2023-10-15 05:01:49,701][88300] Updated weights for policy 1, policy_version 68832 (0.0008) -[2023-10-15 05:01:53,521][88300] Updated weights for policy 1, policy_version 68842 (0.0008) -[2023-10-15 05:01:53,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13884.7). Total num frames: 140541952. Throughput: 0: 1719.6, 1: 1754.4. Samples: 35148508. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) -[2023-10-15 05:01:53,534][87330] Avg episode reward: [(0, '22.560'), (1, '22.550')] -[2023-10-15 05:01:53,654][88298] Updated weights for policy 0, policy_version 68420 (0.0008) -[2023-10-15 05:01:53,893][88300] Updated weights for policy 1, policy_version 68852 (0.0009) -[2023-10-15 05:01:54,029][88298] Updated weights for policy 0, policy_version 68430 (0.0007) -[2023-10-15 05:01:54,260][88300] Updated weights for policy 1, policy_version 68862 (0.0009) -[2023-10-15 05:01:54,396][88298] Updated weights for policy 0, policy_version 68440 (0.0008) -[2023-10-15 05:01:58,085][88300] Updated weights for policy 1, policy_version 68872 (0.0007) -[2023-10-15 05:01:58,286][88298] Updated weights for policy 0, policy_version 68450 (0.0010) -[2023-10-15 05:01:58,449][88300] Updated weights for policy 1, policy_version 68882 (0.0008) -[2023-10-15 05:01:58,534][87330] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 140607488. Throughput: 0: 1737.3, 1: 1751.6. Samples: 35169812. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 05:01:58,535][87330] Avg episode reward: [(0, '22.560'), (1, '22.550')] -[2023-10-15 05:01:58,651][88298] Updated weights for policy 0, policy_version 68460 (0.0008) -[2023-10-15 05:01:58,807][88300] Updated weights for policy 1, policy_version 68892 (0.0007) -[2023-10-15 05:01:59,023][88298] Updated weights for policy 0, policy_version 68470 (0.0007) -[2023-10-15 05:01:59,388][88298] Updated weights for policy 0, policy_version 68480 (0.0009) -[2023-10-15 05:02:02,770][88300] Updated weights for policy 1, policy_version 68902 (0.0008) -[2023-10-15 05:02:03,141][88300] Updated weights for policy 1, policy_version 68912 (0.0007) -[2023-10-15 05:02:03,279][88298] Updated weights for policy 0, policy_version 68490 (0.0007) -[2023-10-15 05:02:03,507][88300] Updated weights for policy 1, policy_version 68922 (0.0007) -[2023-10-15 05:02:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 140673024. Throughput: 0: 1717.1, 1: 1747.1. Samples: 35179858. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 05:02:03,534][87330] Avg episode reward: [(0, '22.480'), (1, '22.440')] -[2023-10-15 05:02:03,646][88298] Updated weights for policy 0, policy_version 68500 (0.0007) -[2023-10-15 05:02:04,018][88298] Updated weights for policy 0, policy_version 68510 (0.0008) -[2023-10-15 05:02:07,260][88300] Updated weights for policy 1, policy_version 68932 (0.0007) -[2023-10-15 05:02:07,622][88300] Updated weights for policy 1, policy_version 68942 (0.0009) -[2023-10-15 05:02:07,983][88300] Updated weights for policy 1, policy_version 68952 (0.0009) -[2023-10-15 05:02:08,103][88298] Updated weights for policy 0, policy_version 68520 (0.0008) -[2023-10-15 05:02:08,472][88298] Updated weights for policy 0, policy_version 68530 (0.0008) -[2023-10-15 05:02:08,534][87330] Fps is (10 sec: 16384.4, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 140771328. Throughput: 0: 1736.1, 1: 1761.7. Samples: 35201088. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 05:02:08,534][87330] Avg episode reward: [(0, '22.640'), (1, '22.390')] -[2023-10-15 05:02:08,841][88298] Updated weights for policy 0, policy_version 68540 (0.0008) -[2023-10-15 05:02:11,957][88300] Updated weights for policy 1, policy_version 68962 (0.0007) -[2023-10-15 05:02:12,325][88300] Updated weights for policy 1, policy_version 68972 (0.0007) -[2023-10-15 05:02:12,691][88300] Updated weights for policy 1, policy_version 68982 (0.0009) -[2023-10-15 05:02:12,749][88298] Updated weights for policy 0, policy_version 68550 (0.0009) -[2023-10-15 05:02:13,053][88300] Updated weights for policy 1, policy_version 68992 (0.0008) -[2023-10-15 05:02:13,138][88298] Updated weights for policy 0, policy_version 68560 (0.0009) -[2023-10-15 05:02:13,507][88298] Updated weights for policy 0, policy_version 68570 (0.0007) -[2023-10-15 05:02:13,534][87330] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 140836864. Throughput: 0: 1732.3, 1: 1735.5. Samples: 35221174. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 05:02:13,535][87330] Avg episode reward: [(0, '22.590'), (1, '22.430')] -[2023-10-15 05:02:16,950][88300] Updated weights for policy 1, policy_version 69002 (0.0009) -[2023-10-15 05:02:17,321][88300] Updated weights for policy 1, policy_version 69012 (0.0007) -[2023-10-15 05:02:17,434][88298] Updated weights for policy 0, policy_version 68580 (0.0007) -[2023-10-15 05:02:17,692][88300] Updated weights for policy 1, policy_version 69022 (0.0009) -[2023-10-15 05:02:17,803][88298] Updated weights for policy 0, policy_version 68590 (0.0009) -[2023-10-15 05:02:18,183][88298] Updated weights for policy 0, policy_version 68600 (0.0009) -[2023-10-15 05:02:18,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 140935168. Throughput: 0: 1731.6, 1: 1773.3. Samples: 35232338. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 05:02:18,535][87330] Avg episode reward: [(0, '22.540'), (1, '22.410')] -[2023-10-15 05:02:21,590][88300] Updated weights for policy 1, policy_version 69032 (0.0010) -[2023-10-15 05:02:21,958][88300] Updated weights for policy 1, policy_version 69042 (0.0008) -[2023-10-15 05:02:22,087][88298] Updated weights for policy 0, policy_version 68610 (0.0007) -[2023-10-15 05:02:22,323][88300] Updated weights for policy 1, policy_version 69052 (0.0007) -[2023-10-15 05:02:22,455][88298] Updated weights for policy 0, policy_version 68620 (0.0007) -[2023-10-15 05:02:22,822][88298] Updated weights for policy 0, policy_version 68630 (0.0009) -[2023-10-15 05:02:23,192][88298] Updated weights for policy 0, policy_version 68640 (0.0010) -[2023-10-15 05:02:23,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 141000704. Throughput: 0: 1737.8, 1: 1747.5. Samples: 35252778. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 05:02:23,534][87330] Avg episode reward: [(0, '22.500'), (1, '22.480')] -[2023-10-15 05:02:26,214][88300] Updated weights for policy 1, policy_version 69062 (0.0008) -[2023-10-15 05:02:26,579][88300] Updated weights for policy 1, policy_version 69072 (0.0008) -[2023-10-15 05:02:26,950][88300] Updated weights for policy 1, policy_version 69082 (0.0009) -[2023-10-15 05:02:27,119][88298] Updated weights for policy 0, policy_version 68650 (0.0007) -[2023-10-15 05:02:27,491][88298] Updated weights for policy 0, policy_version 68660 (0.0008) -[2023-10-15 05:02:27,856][88298] Updated weights for policy 0, policy_version 68670 (0.0008) -[2023-10-15 05:02:28,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 141066240. Throughput: 0: 1712.8, 1: 1737.4. Samples: 35272770. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 05:02:28,535][87330] Avg episode reward: [(0, '22.450'), (1, '22.500')] -[2023-10-15 05:02:31,040][88300] Updated weights for policy 1, policy_version 69092 (0.0008) -[2023-10-15 05:02:31,401][88300] Updated weights for policy 1, policy_version 69102 (0.0007) -[2023-10-15 05:02:31,656][88298] Updated weights for policy 0, policy_version 68680 (0.0007) -[2023-10-15 05:02:31,769][88300] Updated weights for policy 1, policy_version 69112 (0.0009) -[2023-10-15 05:02:32,026][88298] Updated weights for policy 0, policy_version 68690 (0.0009) -[2023-10-15 05:02:32,408][88298] Updated weights for policy 0, policy_version 68700 (0.0010) -[2023-10-15 05:02:33,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 141131776. Throughput: 0: 1743.4, 1: 1750.8. Samples: 35284242. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 05:02:33,534][87330] Avg episode reward: [(0, '22.530'), (1, '22.600')] -[2023-10-15 05:02:35,638][88300] Updated weights for policy 1, policy_version 69122 (0.0008) -[2023-10-15 05:02:36,010][88300] Updated weights for policy 1, policy_version 69132 (0.0009) -[2023-10-15 05:02:36,304][88298] Updated weights for policy 0, policy_version 68710 (0.0011) -[2023-10-15 05:02:36,383][88300] Updated weights for policy 1, policy_version 69142 (0.0007) -[2023-10-15 05:02:36,676][88298] Updated weights for policy 0, policy_version 68720 (0.0008) -[2023-10-15 05:02:36,744][88300] Updated weights for policy 1, policy_version 69152 (0.0008) -[2023-10-15 05:02:37,048][88298] Updated weights for policy 0, policy_version 68730 (0.0009) -[2023-10-15 05:02:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 141197312. Throughput: 0: 1728.1, 1: 1725.6. Samples: 35303926. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-15 05:02:38,534][87330] Avg episode reward: [(0, '22.520'), (1, '22.860')] -[2023-10-15 05:02:40,647][88300] Updated weights for policy 1, policy_version 69162 (0.0009) -[2023-10-15 05:02:40,892][88298] Updated weights for policy 0, policy_version 68740 (0.0007) -[2023-10-15 05:02:41,019][88300] Updated weights for policy 1, policy_version 69172 (0.0008) -[2023-10-15 05:02:41,263][88298] Updated weights for policy 0, policy_version 68750 (0.0008) -[2023-10-15 05:02:41,386][88300] Updated weights for policy 1, policy_version 69182 (0.0010) -[2023-10-15 05:02:41,630][88298] Updated weights for policy 0, policy_version 68760 (0.0011) -[2023-10-15 05:02:43,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 141262848. Throughput: 0: 1715.2, 1: 1728.1. Samples: 35324758. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-15 05:02:43,535][87330] Avg episode reward: [(0, '22.690'), (1, '23.070')] -[2023-10-15 05:02:45,387][88300] Updated weights for policy 1, policy_version 69192 (0.0007) -[2023-10-15 05:02:45,696][88298] Updated weights for policy 0, policy_version 68770 (0.0010) -[2023-10-15 05:02:45,750][88300] Updated weights for policy 1, policy_version 69202 (0.0007) -[2023-10-15 05:02:46,062][88298] Updated weights for policy 0, policy_version 68780 (0.0008) -[2023-10-15 05:02:46,118][88300] Updated weights for policy 1, policy_version 69212 (0.0011) -[2023-10-15 05:02:46,433][88298] Updated weights for policy 0, policy_version 68790 (0.0010) -[2023-10-15 05:02:46,797][88298] Updated weights for policy 0, policy_version 68800 (0.0008) -[2023-10-15 05:02:48,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 141328384. Throughput: 0: 1737.2, 1: 1718.7. Samples: 35335376. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-15 05:02:48,535][87330] Avg episode reward: [(0, '22.690'), (1, '23.050')] -[2023-10-15 05:02:50,106][88300] Updated weights for policy 1, policy_version 69222 (0.0007) -[2023-10-15 05:02:50,477][88300] Updated weights for policy 1, policy_version 69232 (0.0007) -[2023-10-15 05:02:50,627][88298] Updated weights for policy 0, policy_version 68810 (0.0008) -[2023-10-15 05:02:50,836][88300] Updated weights for policy 1, policy_version 69242 (0.0007) -[2023-10-15 05:02:51,000][88298] Updated weights for policy 0, policy_version 68820 (0.0008) -[2023-10-15 05:02:51,374][88298] Updated weights for policy 0, policy_version 68830 (0.0009) -[2023-10-15 05:02:53,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 141393920. Throughput: 0: 1719.3, 1: 1711.3. Samples: 35355466. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-15 05:02:53,535][87330] Avg episode reward: [(0, '22.710'), (1, '23.080')] -[2023-10-15 05:02:54,778][88300] Updated weights for policy 1, policy_version 69252 (0.0009) -[2023-10-15 05:02:55,147][88300] Updated weights for policy 1, policy_version 69262 (0.0007) -[2023-10-15 05:02:55,227][88298] Updated weights for policy 0, policy_version 68840 (0.0008) -[2023-10-15 05:02:55,504][88300] Updated weights for policy 1, policy_version 69272 (0.0008) -[2023-10-15 05:02:55,600][88298] Updated weights for policy 0, policy_version 68850 (0.0009) -[2023-10-15 05:02:55,962][88298] Updated weights for policy 0, policy_version 68860 (0.0009) -[2023-10-15 05:02:58,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 141459456. Throughput: 0: 1721.1, 1: 1740.5. Samples: 35376944. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-15 05:02:58,535][87330] Avg episode reward: [(0, '22.740'), (1, '23.120')] -[2023-10-15 05:02:58,547][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000068864_70516736.pth... -[2023-10-15 05:02:58,548][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000069280_70942720.pth... -[2023-10-15 05:02:58,580][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000067648_69271552.pth -[2023-10-15 05:02:58,583][88033] Saving new best policy, reward=23.120! -[2023-10-15 05:02:58,586][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000067264_68878336.pth -[2023-10-15 05:02:59,591][88300] Updated weights for policy 1, policy_version 69282 (0.0009) -[2023-10-15 05:02:59,943][88298] Updated weights for policy 0, policy_version 68870 (0.0007) -[2023-10-15 05:02:59,963][88300] Updated weights for policy 1, policy_version 69292 (0.0008) -[2023-10-15 05:03:00,326][88298] Updated weights for policy 0, policy_version 68880 (0.0007) -[2023-10-15 05:03:00,330][88300] Updated weights for policy 1, policy_version 69302 (0.0007) -[2023-10-15 05:03:00,698][88300] Updated weights for policy 1, policy_version 69312 (0.0007) -[2023-10-15 05:03:00,698][88298] Updated weights for policy 0, policy_version 68890 (0.0007) -[2023-10-15 05:03:03,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 141524992. Throughput: 0: 1719.3, 1: 1701.3. Samples: 35386268. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-15 05:03:03,535][87330] Avg episode reward: [(0, '22.840'), (1, '22.920')] -[2023-10-15 05:03:04,494][88298] Updated weights for policy 0, policy_version 68900 (0.0007) -[2023-10-15 05:03:04,563][88300] Updated weights for policy 1, policy_version 69322 (0.0008) -[2023-10-15 05:03:04,859][88298] Updated weights for policy 0, policy_version 68910 (0.0009) -[2023-10-15 05:03:04,937][88300] Updated weights for policy 1, policy_version 69332 (0.0009) -[2023-10-15 05:03:05,226][88298] Updated weights for policy 0, policy_version 68920 (0.0009) -[2023-10-15 05:03:05,298][88300] Updated weights for policy 1, policy_version 69342 (0.0008) -[2023-10-15 05:03:08,534][87330] Fps is (10 sec: 13107.6, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 141590528. Throughput: 0: 1717.9, 1: 1726.3. Samples: 35407766. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-15 05:03:08,534][87330] Avg episode reward: [(0, '22.840'), (1, '22.880')] -[2023-10-15 05:03:09,161][88298] Updated weights for policy 0, policy_version 68930 (0.0008) -[2023-10-15 05:03:09,278][88300] Updated weights for policy 1, policy_version 69352 (0.0007) -[2023-10-15 05:03:09,534][88298] Updated weights for policy 0, policy_version 68940 (0.0008) -[2023-10-15 05:03:09,648][88300] Updated weights for policy 1, policy_version 69362 (0.0008) -[2023-10-15 05:03:09,897][88298] Updated weights for policy 0, policy_version 68950 (0.0008) -[2023-10-15 05:03:10,022][88300] Updated weights for policy 1, policy_version 69372 (0.0008) -[2023-10-15 05:03:10,268][88298] Updated weights for policy 0, policy_version 68960 (0.0007) -[2023-10-15 05:03:13,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 141656064. Throughput: 0: 1741.8, 1: 1734.0. Samples: 35429178. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-15 05:03:13,534][87330] Avg episode reward: [(0, '22.810'), (1, '22.840')] -[2023-10-15 05:03:13,747][88300] Updated weights for policy 1, policy_version 69382 (0.0008) -[2023-10-15 05:03:14,113][88300] Updated weights for policy 1, policy_version 69392 (0.0008) -[2023-10-15 05:03:14,213][88298] Updated weights for policy 0, policy_version 68970 (0.0007) -[2023-10-15 05:03:14,473][88300] Updated weights for policy 1, policy_version 69402 (0.0007) -[2023-10-15 05:03:14,582][88298] Updated weights for policy 0, policy_version 68980 (0.0007) -[2023-10-15 05:03:14,951][88298] Updated weights for policy 0, policy_version 68990 (0.0008) -[2023-10-15 05:03:18,406][88300] Updated weights for policy 1, policy_version 69412 (0.0008) -[2023-10-15 05:03:18,534][87330] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 141721600. Throughput: 0: 1715.8, 1: 1716.3. Samples: 35438688. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-15 05:03:18,535][87330] Avg episode reward: [(0, '22.550'), (1, '22.860')] -[2023-10-15 05:03:18,768][88300] Updated weights for policy 1, policy_version 69422 (0.0009) -[2023-10-15 05:03:18,931][88298] Updated weights for policy 0, policy_version 69000 (0.0008) -[2023-10-15 05:03:19,137][88300] Updated weights for policy 1, policy_version 69432 (0.0009) -[2023-10-15 05:03:19,294][88298] Updated weights for policy 0, policy_version 69010 (0.0008) -[2023-10-15 05:03:19,670][88298] Updated weights for policy 0, policy_version 69020 (0.0009) -[2023-10-15 05:03:23,235][88300] Updated weights for policy 1, policy_version 69442 (0.0008) -[2023-10-15 05:03:23,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 13773.7). Total num frames: 141787136. Throughput: 0: 1729.3, 1: 1737.9. Samples: 35459950. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-15 05:03:23,535][87330] Avg episode reward: [(0, '22.500'), (1, '22.870')] -[2023-10-15 05:03:23,594][88300] Updated weights for policy 1, policy_version 69452 (0.0008) -[2023-10-15 05:03:23,813][88298] Updated weights for policy 0, policy_version 69030 (0.0009) -[2023-10-15 05:03:23,955][88300] Updated weights for policy 1, policy_version 69462 (0.0008) -[2023-10-15 05:03:24,173][88298] Updated weights for policy 0, policy_version 69040 (0.0008) -[2023-10-15 05:03:24,318][88300] Updated weights for policy 1, policy_version 69472 (0.0009) -[2023-10-15 05:03:24,551][88298] Updated weights for policy 0, policy_version 69050 (0.0009) -[2023-10-15 05:03:28,259][88300] Updated weights for policy 1, policy_version 69482 (0.0007) -[2023-10-15 05:03:28,488][88298] Updated weights for policy 0, policy_version 69060 (0.0009) -[2023-10-15 05:03:28,534][87330] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 141852672. Throughput: 0: 1739.0, 1: 1731.6. Samples: 35480932. Policy #0 lag: (min: 31.0, avg: 31.2, max: 41.0) -[2023-10-15 05:03:28,534][87330] Avg episode reward: [(0, '22.490'), (1, '22.850')] -[2023-10-15 05:03:28,626][88300] Updated weights for policy 1, policy_version 69492 (0.0008) -[2023-10-15 05:03:28,864][88298] Updated weights for policy 0, policy_version 69070 (0.0008) -[2023-10-15 05:03:28,992][88300] Updated weights for policy 1, policy_version 69502 (0.0008) -[2023-10-15 05:03:29,228][88298] Updated weights for policy 0, policy_version 69080 (0.0009) -[2023-10-15 05:03:32,803][88300] Updated weights for policy 1, policy_version 69512 (0.0008) -[2023-10-15 05:03:33,124][88298] Updated weights for policy 0, policy_version 69090 (0.0007) -[2023-10-15 05:03:33,168][88300] Updated weights for policy 1, policy_version 69522 (0.0007) -[2023-10-15 05:03:33,496][88298] Updated weights for policy 0, policy_version 69100 (0.0007) -[2023-10-15 05:03:33,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 141918208. Throughput: 0: 1713.7, 1: 1737.8. Samples: 35490692. Policy #0 lag: (min: 31.0, avg: 31.2, max: 41.0) -[2023-10-15 05:03:33,534][87330] Avg episode reward: [(0, '22.400'), (1, '22.790')] -[2023-10-15 05:03:33,536][88300] Updated weights for policy 1, policy_version 69532 (0.0007) -[2023-10-15 05:03:33,862][88298] Updated weights for policy 0, policy_version 69110 (0.0008) -[2023-10-15 05:03:34,231][88298] Updated weights for policy 0, policy_version 69120 (0.0011) -[2023-10-15 05:03:37,559][88300] Updated weights for policy 1, policy_version 69542 (0.0008) -[2023-10-15 05:03:37,927][88300] Updated weights for policy 1, policy_version 69552 (0.0007) -[2023-10-15 05:03:38,105][88298] Updated weights for policy 0, policy_version 69130 (0.0009) -[2023-10-15 05:03:38,299][88300] Updated weights for policy 1, policy_version 69562 (0.0008) -[2023-10-15 05:03:38,480][88298] Updated weights for policy 0, policy_version 69140 (0.0009) -[2023-10-15 05:03:38,534][87330] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 142016512. Throughput: 0: 1738.2, 1: 1742.5. Samples: 35512096. Policy #0 lag: (min: 31.0, avg: 31.2, max: 41.0) -[2023-10-15 05:03:38,534][87330] Avg episode reward: [(0, '22.410'), (1, '23.060')] -[2023-10-15 05:03:38,848][88298] Updated weights for policy 0, policy_version 69150 (0.0007) -[2023-10-15 05:03:42,262][88300] Updated weights for policy 1, policy_version 69572 (0.0008) -[2023-10-15 05:03:42,631][88300] Updated weights for policy 1, policy_version 69582 (0.0007) -[2023-10-15 05:03:42,828][88298] Updated weights for policy 0, policy_version 69160 (0.0007) -[2023-10-15 05:03:42,992][88300] Updated weights for policy 1, policy_version 69592 (0.0007) -[2023-10-15 05:03:43,205][88298] Updated weights for policy 0, policy_version 69170 (0.0009) -[2023-10-15 05:03:43,534][87330] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 142082048. Throughput: 0: 1738.2, 1: 1712.9. Samples: 35532242. Policy #0 lag: (min: 31.0, avg: 31.2, max: 41.0) -[2023-10-15 05:03:43,535][87330] Avg episode reward: [(0, '22.400'), (1, '23.040')] -[2023-10-15 05:03:43,569][88298] Updated weights for policy 0, policy_version 69180 (0.0010) -[2023-10-15 05:03:46,834][88300] Updated weights for policy 1, policy_version 69602 (0.0007) -[2023-10-15 05:03:47,197][88300] Updated weights for policy 1, policy_version 69612 (0.0010) -[2023-10-15 05:03:47,564][88300] Updated weights for policy 1, policy_version 69622 (0.0008) -[2023-10-15 05:03:47,680][88298] Updated weights for policy 0, policy_version 69190 (0.0009) -[2023-10-15 05:03:47,932][88300] Updated weights for policy 1, policy_version 69632 (0.0007) -[2023-10-15 05:03:48,064][88298] Updated weights for policy 0, policy_version 69200 (0.0009) -[2023-10-15 05:03:48,429][88298] Updated weights for policy 0, policy_version 69210 (0.0008) -[2023-10-15 05:03:48,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 142147584. Throughput: 0: 1740.3, 1: 1739.5. Samples: 35542860. Policy #0 lag: (min: 31.0, avg: 31.2, max: 41.0) -[2023-10-15 05:03:48,534][87330] Avg episode reward: [(0, '22.400'), (1, '23.060')] -[2023-10-15 05:03:51,838][88300] Updated weights for policy 1, policy_version 69642 (0.0008) -[2023-10-15 05:03:52,211][88300] Updated weights for policy 1, policy_version 69652 (0.0008) -[2023-10-15 05:03:52,226][88298] Updated weights for policy 0, policy_version 69220 (0.0007) -[2023-10-15 05:03:52,575][88300] Updated weights for policy 1, policy_version 69662 (0.0008) -[2023-10-15 05:03:52,592][88298] Updated weights for policy 0, policy_version 69230 (0.0007) -[2023-10-15 05:03:52,973][88298] Updated weights for policy 0, policy_version 69240 (0.0009) -[2023-10-15 05:03:53,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 142245888. Throughput: 0: 1738.6, 1: 1721.0. Samples: 35563446. Policy #0 lag: (min: 31.0, avg: 31.2, max: 41.0) -[2023-10-15 05:03:53,535][87330] Avg episode reward: [(0, '22.530'), (1, '22.850')] -[2023-10-15 05:03:56,647][88300] Updated weights for policy 1, policy_version 69672 (0.0010) -[2023-10-15 05:03:56,872][88298] Updated weights for policy 0, policy_version 69250 (0.0010) -[2023-10-15 05:03:57,009][88300] Updated weights for policy 1, policy_version 69682 (0.0009) -[2023-10-15 05:03:57,238][88298] Updated weights for policy 0, policy_version 69260 (0.0008) -[2023-10-15 05:03:57,386][88300] Updated weights for policy 1, policy_version 69692 (0.0008) -[2023-10-15 05:03:57,602][88298] Updated weights for policy 0, policy_version 69270 (0.0008) -[2023-10-15 05:03:57,966][88298] Updated weights for policy 0, policy_version 69280 (0.0008) -[2023-10-15 05:03:58,534][87330] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 142311424. Throughput: 0: 1715.6, 1: 1705.3. Samples: 35583118. Policy #0 lag: (min: 31.0, avg: 31.2, max: 41.0) -[2023-10-15 05:03:58,535][87330] Avg episode reward: [(0, '22.300'), (1, '22.900')] -[2023-10-15 05:04:01,208][88300] Updated weights for policy 1, policy_version 69702 (0.0009) -[2023-10-15 05:04:01,583][88300] Updated weights for policy 1, policy_version 69712 (0.0008) -[2023-10-15 05:04:01,954][88300] Updated weights for policy 1, policy_version 69722 (0.0009) -[2023-10-15 05:04:02,024][88298] Updated weights for policy 0, policy_version 69290 (0.0009) -[2023-10-15 05:04:02,404][88298] Updated weights for policy 0, policy_version 69300 (0.0008) -[2023-10-15 05:04:02,772][88298] Updated weights for policy 0, policy_version 69310 (0.0009) -[2023-10-15 05:04:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 142376960. Throughput: 0: 1732.8, 1: 1734.6. Samples: 35594720. Policy #0 lag: (min: 31.0, avg: 31.2, max: 41.0) -[2023-10-15 05:04:03,535][87330] Avg episode reward: [(0, '22.130'), (1, '22.900')] -[2023-10-15 05:04:05,934][88300] Updated weights for policy 1, policy_version 69732 (0.0008) -[2023-10-15 05:04:06,304][88300] Updated weights for policy 1, policy_version 69742 (0.0009) -[2023-10-15 05:04:06,675][88300] Updated weights for policy 1, policy_version 69752 (0.0007) -[2023-10-15 05:04:06,734][88298] Updated weights for policy 0, policy_version 69320 (0.0008) -[2023-10-15 05:04:07,108][88298] Updated weights for policy 0, policy_version 69330 (0.0008) -[2023-10-15 05:04:07,484][88298] Updated weights for policy 0, policy_version 69340 (0.0011) -[2023-10-15 05:04:08,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 142442496. Throughput: 0: 1727.5, 1: 1707.5. Samples: 35614524. Policy #0 lag: (min: 31.0, avg: 31.2, max: 41.0) -[2023-10-15 05:04:08,534][87330] Avg episode reward: [(0, '22.180'), (1, '22.800')] -[2023-10-15 05:04:10,546][88300] Updated weights for policy 1, policy_version 69762 (0.0007) -[2023-10-15 05:04:10,913][88300] Updated weights for policy 1, policy_version 69772 (0.0010) -[2023-10-15 05:04:11,241][88298] Updated weights for policy 0, policy_version 69350 (0.0009) -[2023-10-15 05:04:11,288][88300] Updated weights for policy 1, policy_version 69782 (0.0008) -[2023-10-15 05:04:11,609][88298] Updated weights for policy 0, policy_version 69360 (0.0008) -[2023-10-15 05:04:11,646][88300] Updated weights for policy 1, policy_version 69792 (0.0009) -[2023-10-15 05:04:11,983][88298] Updated weights for policy 0, policy_version 69370 (0.0009) -[2023-10-15 05:04:13,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 142508032. Throughput: 0: 1713.3, 1: 1720.8. Samples: 35635464. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-15 05:04:13,535][87330] Avg episode reward: [(0, '21.730'), (1, '22.790')] -[2023-10-15 05:04:15,481][88300] Updated weights for policy 1, policy_version 69802 (0.0009) -[2023-10-15 05:04:15,845][88300] Updated weights for policy 1, policy_version 69812 (0.0008) -[2023-10-15 05:04:15,880][88298] Updated weights for policy 0, policy_version 69380 (0.0008) -[2023-10-15 05:04:16,208][88300] Updated weights for policy 1, policy_version 69822 (0.0008) -[2023-10-15 05:04:16,250][88298] Updated weights for policy 0, policy_version 69390 (0.0008) -[2023-10-15 05:04:16,611][88298] Updated weights for policy 0, policy_version 69400 (0.0008) -[2023-10-15 05:04:18,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 142573568. Throughput: 0: 1741.0, 1: 1716.8. Samples: 35646294. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-15 05:04:18,535][87330] Avg episode reward: [(0, '21.840'), (1, '22.730')] -[2023-10-15 05:04:20,257][88300] Updated weights for policy 1, policy_version 69832 (0.0008) -[2023-10-15 05:04:20,482][88298] Updated weights for policy 0, policy_version 69410 (0.0010) -[2023-10-15 05:04:20,632][88300] Updated weights for policy 1, policy_version 69842 (0.0008) -[2023-10-15 05:04:20,859][88298] Updated weights for policy 0, policy_version 69420 (0.0008) -[2023-10-15 05:04:20,999][88300] Updated weights for policy 1, policy_version 69852 (0.0008) -[2023-10-15 05:04:21,227][88298] Updated weights for policy 0, policy_version 69430 (0.0009) -[2023-10-15 05:04:21,600][88298] Updated weights for policy 0, policy_version 69440 (0.0007) -[2023-10-15 05:04:23,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 142639104. Throughput: 0: 1715.0, 1: 1712.1. Samples: 35666316. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-15 05:04:23,535][87330] Avg episode reward: [(0, '21.900'), (1, '22.630')] -[2023-10-15 05:04:24,763][88300] Updated weights for policy 1, policy_version 69862 (0.0010) -[2023-10-15 05:04:25,132][88300] Updated weights for policy 1, policy_version 69872 (0.0009) -[2023-10-15 05:04:25,487][88298] Updated weights for policy 0, policy_version 69450 (0.0008) -[2023-10-15 05:04:25,497][88300] Updated weights for policy 1, policy_version 69882 (0.0008) -[2023-10-15 05:04:25,855][88298] Updated weights for policy 0, policy_version 69460 (0.0008) -[2023-10-15 05:04:26,226][88298] Updated weights for policy 0, policy_version 69470 (0.0010) -[2023-10-15 05:04:28,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 142704640. Throughput: 0: 1715.7, 1: 1747.3. Samples: 35688078. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-15 05:04:28,535][87330] Avg episode reward: [(0, '22.080'), (1, '22.820')] -[2023-10-15 05:04:29,281][88300] Updated weights for policy 1, policy_version 69892 (0.0008) -[2023-10-15 05:04:29,651][88300] Updated weights for policy 1, policy_version 69902 (0.0010) -[2023-10-15 05:04:30,028][88300] Updated weights for policy 1, policy_version 69912 (0.0009) -[2023-10-15 05:04:30,274][88298] Updated weights for policy 0, policy_version 69480 (0.0007) -[2023-10-15 05:04:30,643][88298] Updated weights for policy 0, policy_version 69490 (0.0008) -[2023-10-15 05:04:31,011][88298] Updated weights for policy 0, policy_version 69500 (0.0009) -[2023-10-15 05:04:33,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 142770176. Throughput: 0: 1723.5, 1: 1726.2. Samples: 35698094. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-15 05:04:33,534][87330] Avg episode reward: [(0, '22.190'), (1, '22.840')] -[2023-10-15 05:04:33,954][88300] Updated weights for policy 1, policy_version 69922 (0.0008) -[2023-10-15 05:04:34,326][88300] Updated weights for policy 1, policy_version 69932 (0.0009) -[2023-10-15 05:04:34,697][88300] Updated weights for policy 1, policy_version 69942 (0.0010) -[2023-10-15 05:04:34,953][88298] Updated weights for policy 0, policy_version 69510 (0.0008) -[2023-10-15 05:04:35,059][88300] Updated weights for policy 1, policy_version 69952 (0.0008) -[2023-10-15 05:04:35,331][88298] Updated weights for policy 0, policy_version 69520 (0.0009) -[2023-10-15 05:04:35,701][88298] Updated weights for policy 0, policy_version 69530 (0.0007) -[2023-10-15 05:04:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 142835712. Throughput: 0: 1713.7, 1: 1741.2. Samples: 35718920. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-15 05:04:38,535][87330] Avg episode reward: [(0, '22.300'), (1, '22.920')] -[2023-10-15 05:04:39,191][88300] Updated weights for policy 1, policy_version 69962 (0.0008) -[2023-10-15 05:04:39,554][88300] Updated weights for policy 1, policy_version 69972 (0.0009) -[2023-10-15 05:04:39,726][88298] Updated weights for policy 0, policy_version 69540 (0.0008) -[2023-10-15 05:04:39,915][88300] Updated weights for policy 1, policy_version 69982 (0.0008) -[2023-10-15 05:04:40,107][88298] Updated weights for policy 0, policy_version 69550 (0.0008) -[2023-10-15 05:04:40,484][88298] Updated weights for policy 0, policy_version 69560 (0.0008) -[2023-10-15 05:04:43,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 142901248. Throughput: 0: 1738.1, 1: 1758.3. Samples: 35740454. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-15 05:04:43,535][87330] Avg episode reward: [(0, '22.760'), (1, '22.760')] -[2023-10-15 05:04:43,812][88300] Updated weights for policy 1, policy_version 69992 (0.0008) -[2023-10-15 05:04:44,165][88300] Updated weights for policy 1, policy_version 70002 (0.0009) -[2023-10-15 05:04:44,188][88298] Updated weights for policy 0, policy_version 69570 (0.0010) -[2023-10-15 05:04:44,530][88300] Updated weights for policy 1, policy_version 70012 (0.0009) -[2023-10-15 05:04:44,559][88298] Updated weights for policy 0, policy_version 69580 (0.0008) -[2023-10-15 05:04:44,925][88298] Updated weights for policy 0, policy_version 69590 (0.0009) -[2023-10-15 05:04:45,297][88298] Updated weights for policy 0, policy_version 69600 (0.0007) -[2023-10-15 05:04:48,453][88300] Updated weights for policy 1, policy_version 70022 (0.0010) -[2023-10-15 05:04:48,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 142966784. Throughput: 0: 1718.8, 1: 1732.1. Samples: 35750008. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-15 05:04:48,534][87330] Avg episode reward: [(0, '22.720'), (1, '22.690')] -[2023-10-15 05:04:48,811][88300] Updated weights for policy 1, policy_version 70032 (0.0009) -[2023-10-15 05:04:49,083][88298] Updated weights for policy 0, policy_version 69610 (0.0007) -[2023-10-15 05:04:49,181][88300] Updated weights for policy 1, policy_version 70042 (0.0007) -[2023-10-15 05:04:49,459][88298] Updated weights for policy 0, policy_version 69620 (0.0007) -[2023-10-15 05:04:49,831][88298] Updated weights for policy 0, policy_version 69630 (0.0008) -[2023-10-15 05:04:53,095][88300] Updated weights for policy 1, policy_version 70052 (0.0007) -[2023-10-15 05:04:53,458][88300] Updated weights for policy 1, policy_version 70062 (0.0009) -[2023-10-15 05:04:53,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 143032320. Throughput: 0: 1728.6, 1: 1759.0. Samples: 35771466. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-15 05:04:53,534][87330] Avg episode reward: [(0, '22.700'), (1, '22.680')] -[2023-10-15 05:04:53,726][88298] Updated weights for policy 0, policy_version 69640 (0.0009) -[2023-10-15 05:04:53,823][88300] Updated weights for policy 1, policy_version 70072 (0.0008) -[2023-10-15 05:04:54,094][88298] Updated weights for policy 0, policy_version 69650 (0.0008) -[2023-10-15 05:04:54,465][88298] Updated weights for policy 0, policy_version 69660 (0.0009) -[2023-10-15 05:04:57,584][88300] Updated weights for policy 1, policy_version 70082 (0.0008) -[2023-10-15 05:04:57,938][88300] Updated weights for policy 1, policy_version 70092 (0.0008) -[2023-10-15 05:04:58,306][88300] Updated weights for policy 1, policy_version 70102 (0.0007) -[2023-10-15 05:04:58,503][88298] Updated weights for policy 0, policy_version 69670 (0.0008) -[2023-10-15 05:04:58,534][87330] Fps is (10 sec: 13106.7, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 143097856. Throughput: 0: 1745.4, 1: 1740.8. Samples: 35792342. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-15 05:04:58,535][87330] Avg episode reward: [(0, '22.540'), (1, '22.610')] -[2023-10-15 05:04:58,665][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000070112_71794688.pth... -[2023-10-15 05:04:58,666][88300] Updated weights for policy 1, policy_version 70112 (0.0007) -[2023-10-15 05:04:58,703][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000068480_70123520.pth -[2023-10-15 05:04:58,878][88298] Updated weights for policy 0, policy_version 69680 (0.0007) -[2023-10-15 05:04:59,259][88298] Updated weights for policy 0, policy_version 69690 (0.0008) -[2023-10-15 05:04:59,486][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000069696_71368704.pth... -[2023-10-15 05:04:59,530][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000068064_69697536.pth -[2023-10-15 05:05:02,545][88300] Updated weights for policy 1, policy_version 70122 (0.0008) -[2023-10-15 05:05:02,907][88300] Updated weights for policy 1, policy_version 70132 (0.0007) -[2023-10-15 05:05:03,206][88298] Updated weights for policy 0, policy_version 69700 (0.0009) -[2023-10-15 05:05:03,282][88300] Updated weights for policy 1, policy_version 70142 (0.0008) -[2023-10-15 05:05:03,534][87330] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 143196160. Throughput: 0: 1716.2, 1: 1755.4. Samples: 35802516. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:05:03,534][87330] Avg episode reward: [(0, '22.510'), (1, '22.420')] -[2023-10-15 05:05:03,572][88298] Updated weights for policy 0, policy_version 69710 (0.0009) -[2023-10-15 05:05:03,935][88298] Updated weights for policy 0, policy_version 69720 (0.0011) -[2023-10-15 05:05:07,242][88300] Updated weights for policy 1, policy_version 70152 (0.0011) -[2023-10-15 05:05:07,614][88300] Updated weights for policy 1, policy_version 70162 (0.0009) -[2023-10-15 05:05:07,922][88298] Updated weights for policy 0, policy_version 69730 (0.0009) -[2023-10-15 05:05:07,968][88300] Updated weights for policy 1, policy_version 70172 (0.0008) -[2023-10-15 05:05:08,299][88298] Updated weights for policy 0, policy_version 69740 (0.0009) -[2023-10-15 05:05:08,534][87330] Fps is (10 sec: 16384.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 143261696. Throughput: 0: 1744.8, 1: 1756.6. Samples: 35823878. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:05:08,535][87330] Avg episode reward: [(0, '22.570'), (1, '22.310')] -[2023-10-15 05:05:08,671][88298] Updated weights for policy 0, policy_version 69750 (0.0007) -[2023-10-15 05:05:09,041][88298] Updated weights for policy 0, policy_version 69760 (0.0008) -[2023-10-15 05:05:11,686][88300] Updated weights for policy 1, policy_version 70182 (0.0008) -[2023-10-15 05:05:12,060][88300] Updated weights for policy 1, policy_version 70192 (0.0008) -[2023-10-15 05:05:12,425][88300] Updated weights for policy 1, policy_version 70202 (0.0008) -[2023-10-15 05:05:13,028][88298] Updated weights for policy 0, policy_version 69770 (0.0007) -[2023-10-15 05:05:13,400][88298] Updated weights for policy 0, policy_version 69780 (0.0007) -[2023-10-15 05:05:13,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 143327232. Throughput: 0: 1746.9, 1: 1730.7. Samples: 35844570. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:05:13,534][87330] Avg episode reward: [(0, '22.560'), (1, '22.390')] -[2023-10-15 05:05:13,761][88298] Updated weights for policy 0, policy_version 69790 (0.0007) -[2023-10-15 05:05:16,387][88300] Updated weights for policy 1, policy_version 70212 (0.0009) -[2023-10-15 05:05:16,747][88300] Updated weights for policy 1, policy_version 70222 (0.0010) -[2023-10-15 05:05:17,130][88300] Updated weights for policy 1, policy_version 70232 (0.0009) -[2023-10-15 05:05:17,829][88298] Updated weights for policy 0, policy_version 69800 (0.0009) -[2023-10-15 05:05:18,188][88298] Updated weights for policy 0, policy_version 69810 (0.0010) -[2023-10-15 05:05:18,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 143392768. Throughput: 0: 1733.8, 1: 1761.2. Samples: 35855370. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:05:18,535][87330] Avg episode reward: [(0, '22.560'), (1, '22.260')] -[2023-10-15 05:05:18,558][88298] Updated weights for policy 0, policy_version 69820 (0.0010) -[2023-10-15 05:05:20,950][88300] Updated weights for policy 1, policy_version 70242 (0.0008) -[2023-10-15 05:05:21,325][88300] Updated weights for policy 1, policy_version 70252 (0.0009) -[2023-10-15 05:05:21,683][88300] Updated weights for policy 1, policy_version 70262 (0.0008) -[2023-10-15 05:05:22,058][88300] Updated weights for policy 1, policy_version 70272 (0.0008) -[2023-10-15 05:05:22,375][88298] Updated weights for policy 0, policy_version 69830 (0.0008) -[2023-10-15 05:05:22,742][88298] Updated weights for policy 0, policy_version 69840 (0.0007) -[2023-10-15 05:05:23,118][88298] Updated weights for policy 0, policy_version 69850 (0.0008) -[2023-10-15 05:05:23,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 143491072. Throughput: 0: 1751.5, 1: 1735.0. Samples: 35875810. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:05:23,535][87330] Avg episode reward: [(0, '22.620'), (1, '22.370')] -[2023-10-15 05:05:25,820][88300] Updated weights for policy 1, policy_version 70282 (0.0008) -[2023-10-15 05:05:26,190][88300] Updated weights for policy 1, policy_version 70292 (0.0008) -[2023-10-15 05:05:26,561][88300] Updated weights for policy 1, policy_version 70302 (0.0008) -[2023-10-15 05:05:26,938][88298] Updated weights for policy 0, policy_version 69860 (0.0009) -[2023-10-15 05:05:27,331][88298] Updated weights for policy 0, policy_version 69870 (0.0009) -[2023-10-15 05:05:27,691][88298] Updated weights for policy 0, policy_version 69880 (0.0009) -[2023-10-15 05:05:28,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 143556608. Throughput: 0: 1729.2, 1: 1742.1. Samples: 35896664. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:05:28,535][87330] Avg episode reward: [(0, '22.640'), (1, '22.260')] -[2023-10-15 05:05:30,700][88300] Updated weights for policy 1, policy_version 70312 (0.0008) -[2023-10-15 05:05:31,075][88300] Updated weights for policy 1, policy_version 70322 (0.0008) -[2023-10-15 05:05:31,439][88300] Updated weights for policy 1, policy_version 70332 (0.0009) -[2023-10-15 05:05:31,526][88298] Updated weights for policy 0, policy_version 69890 (0.0008) -[2023-10-15 05:05:31,895][88298] Updated weights for policy 0, policy_version 69900 (0.0008) -[2023-10-15 05:05:32,256][88298] Updated weights for policy 0, policy_version 69910 (0.0007) -[2023-10-15 05:05:32,633][88298] Updated weights for policy 0, policy_version 69920 (0.0008) -[2023-10-15 05:05:33,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 143622144. Throughput: 0: 1752.9, 1: 1746.0. Samples: 35907458. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:05:33,535][87330] Avg episode reward: [(0, '22.810'), (1, '22.150')] -[2023-10-15 05:05:35,307][88300] Updated weights for policy 1, policy_version 70342 (0.0007) -[2023-10-15 05:05:35,679][88300] Updated weights for policy 1, policy_version 70352 (0.0008) -[2023-10-15 05:05:36,046][88300] Updated weights for policy 1, policy_version 70362 (0.0010) -[2023-10-15 05:05:36,389][88298] Updated weights for policy 0, policy_version 69930 (0.0007) -[2023-10-15 05:05:36,750][88298] Updated weights for policy 0, policy_version 69940 (0.0008) -[2023-10-15 05:05:37,118][88298] Updated weights for policy 0, policy_version 69950 (0.0010) -[2023-10-15 05:05:38,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 143687680. Throughput: 0: 1738.5, 1: 1737.9. Samples: 35927904. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:05:38,534][87330] Avg episode reward: [(0, '22.740'), (1, '22.250')] -[2023-10-15 05:05:39,978][88300] Updated weights for policy 1, policy_version 70372 (0.0009) -[2023-10-15 05:05:40,349][88300] Updated weights for policy 1, policy_version 70382 (0.0011) -[2023-10-15 05:05:40,710][88300] Updated weights for policy 1, policy_version 70392 (0.0010) -[2023-10-15 05:05:41,205][88298] Updated weights for policy 0, policy_version 69960 (0.0009) -[2023-10-15 05:05:41,573][88298] Updated weights for policy 0, policy_version 69970 (0.0010) -[2023-10-15 05:05:41,953][88298] Updated weights for policy 0, policy_version 69980 (0.0010) -[2023-10-15 05:05:43,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 143753216. Throughput: 0: 1721.5, 1: 1750.8. Samples: 35948592. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:05:43,534][87330] Avg episode reward: [(0, '22.760'), (1, '22.030')] -[2023-10-15 05:05:44,501][88300] Updated weights for policy 1, policy_version 70402 (0.0010) -[2023-10-15 05:05:44,868][88300] Updated weights for policy 1, policy_version 70412 (0.0007) -[2023-10-15 05:05:45,235][88300] Updated weights for policy 1, policy_version 70422 (0.0009) -[2023-10-15 05:05:45,602][88300] Updated weights for policy 1, policy_version 70432 (0.0008) -[2023-10-15 05:05:45,936][88298] Updated weights for policy 0, policy_version 69990 (0.0008) -[2023-10-15 05:05:46,302][88298] Updated weights for policy 0, policy_version 70000 (0.0007) -[2023-10-15 05:05:46,671][88298] Updated weights for policy 0, policy_version 70010 (0.0010) -[2023-10-15 05:05:48,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 143818752. Throughput: 0: 1748.3, 1: 1735.8. Samples: 35959302. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-15 05:05:48,535][87330] Avg episode reward: [(0, '22.750'), (1, '22.230')] -[2023-10-15 05:05:49,322][88300] Updated weights for policy 1, policy_version 70442 (0.0008) -[2023-10-15 05:05:49,687][88300] Updated weights for policy 1, policy_version 70452 (0.0008) -[2023-10-15 05:05:50,049][88300] Updated weights for policy 1, policy_version 70462 (0.0009) -[2023-10-15 05:05:50,583][88298] Updated weights for policy 0, policy_version 70020 (0.0009) -[2023-10-15 05:05:50,957][88298] Updated weights for policy 0, policy_version 70030 (0.0009) -[2023-10-15 05:05:51,327][88298] Updated weights for policy 0, policy_version 70040 (0.0008) -[2023-10-15 05:05:53,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 143884288. Throughput: 0: 1717.5, 1: 1744.3. Samples: 35979658. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-15 05:05:53,534][87330] Avg episode reward: [(0, '22.780'), (1, '22.020')] -[2023-10-15 05:05:54,235][88300] Updated weights for policy 1, policy_version 70472 (0.0008) -[2023-10-15 05:05:54,602][88300] Updated weights for policy 1, policy_version 70482 (0.0008) -[2023-10-15 05:05:54,969][88300] Updated weights for policy 1, policy_version 70492 (0.0009) -[2023-10-15 05:05:55,065][88298] Updated weights for policy 0, policy_version 70050 (0.0007) -[2023-10-15 05:05:55,432][88298] Updated weights for policy 0, policy_version 70060 (0.0010) -[2023-10-15 05:05:55,797][88298] Updated weights for policy 0, policy_version 70070 (0.0010) -[2023-10-15 05:05:56,162][88298] Updated weights for policy 0, policy_version 70080 (0.0009) -[2023-10-15 05:05:58,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 143949824. Throughput: 0: 1723.9, 1: 1757.6. Samples: 36001238. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-15 05:05:58,535][87330] Avg episode reward: [(0, '22.760'), (1, '22.170')] -[2023-10-15 05:05:58,959][88300] Updated weights for policy 1, policy_version 70502 (0.0008) -[2023-10-15 05:05:59,326][88300] Updated weights for policy 1, policy_version 70512 (0.0007) -[2023-10-15 05:05:59,691][88300] Updated weights for policy 1, policy_version 70522 (0.0009) -[2023-10-15 05:05:59,902][88298] Updated weights for policy 0, policy_version 70090 (0.0009) -[2023-10-15 05:06:00,272][88298] Updated weights for policy 0, policy_version 70100 (0.0010) -[2023-10-15 05:06:00,637][88298] Updated weights for policy 0, policy_version 70110 (0.0008) -[2023-10-15 05:06:03,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 144015360. Throughput: 0: 1727.2, 1: 1729.6. Samples: 36010926. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-15 05:06:03,535][87330] Avg episode reward: [(0, '22.760'), (1, '22.370')] -[2023-10-15 05:06:03,578][88300] Updated weights for policy 1, policy_version 70532 (0.0010) -[2023-10-15 05:06:03,941][88300] Updated weights for policy 1, policy_version 70542 (0.0009) -[2023-10-15 05:06:04,306][88300] Updated weights for policy 1, policy_version 70552 (0.0011) -[2023-10-15 05:06:04,802][88298] Updated weights for policy 0, policy_version 70120 (0.0007) -[2023-10-15 05:06:05,173][88298] Updated weights for policy 0, policy_version 70130 (0.0008) -[2023-10-15 05:06:05,541][88298] Updated weights for policy 0, policy_version 70140 (0.0010) -[2023-10-15 05:06:08,161][88300] Updated weights for policy 1, policy_version 70562 (0.0010) -[2023-10-15 05:06:08,524][88300] Updated weights for policy 1, policy_version 70572 (0.0007) -[2023-10-15 05:06:08,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 144080896. Throughput: 0: 1721.9, 1: 1759.1. Samples: 36032454. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-15 05:06:08,535][87330] Avg episode reward: [(0, '22.830'), (1, '22.310')] -[2023-10-15 05:06:08,898][88300] Updated weights for policy 1, policy_version 70582 (0.0008) -[2023-10-15 05:06:09,265][88300] Updated weights for policy 1, policy_version 70592 (0.0009) -[2023-10-15 05:06:09,531][88298] Updated weights for policy 0, policy_version 70150 (0.0008) -[2023-10-15 05:06:09,907][88298] Updated weights for policy 0, policy_version 70160 (0.0008) -[2023-10-15 05:06:10,278][88298] Updated weights for policy 0, policy_version 70170 (0.0007) -[2023-10-15 05:06:13,088][88300] Updated weights for policy 1, policy_version 70602 (0.0009) -[2023-10-15 05:06:13,454][88300] Updated weights for policy 1, policy_version 70612 (0.0008) -[2023-10-15 05:06:13,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 144146432. Throughput: 0: 1740.6, 1: 1742.2. Samples: 36053392. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-15 05:06:13,534][87330] Avg episode reward: [(0, '22.670'), (1, '22.430')] -[2023-10-15 05:06:13,832][88300] Updated weights for policy 1, policy_version 70622 (0.0007) -[2023-10-15 05:06:14,166][88298] Updated weights for policy 0, policy_version 70180 (0.0008) -[2023-10-15 05:06:14,553][88298] Updated weights for policy 0, policy_version 70190 (0.0008) -[2023-10-15 05:06:14,925][88298] Updated weights for policy 0, policy_version 70200 (0.0007) -[2023-10-15 05:06:17,580][88300] Updated weights for policy 1, policy_version 70632 (0.0008) -[2023-10-15 05:06:17,938][88300] Updated weights for policy 1, policy_version 70642 (0.0008) -[2023-10-15 05:06:18,290][88300] Updated weights for policy 1, policy_version 70652 (0.0008) -[2023-10-15 05:06:18,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 144244736. Throughput: 0: 1715.7, 1: 1750.8. Samples: 36063450. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-15 05:06:18,534][87330] Avg episode reward: [(0, '22.620'), (1, '22.540')] -[2023-10-15 05:06:18,781][88298] Updated weights for policy 0, policy_version 70210 (0.0007) -[2023-10-15 05:06:19,156][88298] Updated weights for policy 0, policy_version 70220 (0.0008) -[2023-10-15 05:06:19,513][88298] Updated weights for policy 0, policy_version 70230 (0.0010) -[2023-10-15 05:06:19,876][88298] Updated weights for policy 0, policy_version 70240 (0.0010) -[2023-10-15 05:06:22,284][88300] Updated weights for policy 1, policy_version 70662 (0.0007) -[2023-10-15 05:06:22,647][88300] Updated weights for policy 1, policy_version 70672 (0.0008) -[2023-10-15 05:06:23,007][88300] Updated weights for policy 1, policy_version 70682 (0.0007) -[2023-10-15 05:06:23,534][87330] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 144310272. Throughput: 0: 1727.9, 1: 1755.6. Samples: 36084662. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-15 05:06:23,535][87330] Avg episode reward: [(0, '22.660'), (1, '22.750')] -[2023-10-15 05:06:23,681][88298] Updated weights for policy 0, policy_version 70250 (0.0009) -[2023-10-15 05:06:24,050][88298] Updated weights for policy 0, policy_version 70260 (0.0009) -[2023-10-15 05:06:24,417][88298] Updated weights for policy 0, policy_version 70270 (0.0008) -[2023-10-15 05:06:26,700][88300] Updated weights for policy 1, policy_version 70692 (0.0008) -[2023-10-15 05:06:27,064][88300] Updated weights for policy 1, policy_version 70702 (0.0009) -[2023-10-15 05:06:27,425][88300] Updated weights for policy 1, policy_version 70712 (0.0010) -[2023-10-15 05:06:28,454][88298] Updated weights for policy 0, policy_version 70280 (0.0007) -[2023-10-15 05:06:28,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 144375808. Throughput: 0: 1748.4, 1: 1734.7. Samples: 36105334. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-15 05:06:28,535][87330] Avg episode reward: [(0, '22.660'), (1, '22.720')] -[2023-10-15 05:06:28,816][88298] Updated weights for policy 0, policy_version 70290 (0.0007) -[2023-10-15 05:06:29,180][88298] Updated weights for policy 0, policy_version 70300 (0.0007) -[2023-10-15 05:06:31,331][88300] Updated weights for policy 1, policy_version 70722 (0.0007) -[2023-10-15 05:06:31,697][88300] Updated weights for policy 1, policy_version 70732 (0.0009) -[2023-10-15 05:06:32,067][88300] Updated weights for policy 1, policy_version 70742 (0.0008) -[2023-10-15 05:06:32,425][88300] Updated weights for policy 1, policy_version 70752 (0.0009) -[2023-10-15 05:06:32,992][88298] Updated weights for policy 0, policy_version 70310 (0.0008) -[2023-10-15 05:06:33,369][88298] Updated weights for policy 0, policy_version 70320 (0.0009) -[2023-10-15 05:06:33,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 144441344. Throughput: 0: 1722.9, 1: 1766.9. Samples: 36116340. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-15 05:06:33,534][87330] Avg episode reward: [(0, '22.680'), (1, '22.720')] -[2023-10-15 05:06:33,747][88298] Updated weights for policy 0, policy_version 70330 (0.0008) -[2023-10-15 05:06:36,312][88300] Updated weights for policy 1, policy_version 70762 (0.0011) -[2023-10-15 05:06:36,668][88300] Updated weights for policy 1, policy_version 70772 (0.0010) -[2023-10-15 05:06:37,039][88300] Updated weights for policy 1, policy_version 70782 (0.0010) -[2023-10-15 05:06:37,839][88298] Updated weights for policy 0, policy_version 70340 (0.0007) -[2023-10-15 05:06:38,205][88298] Updated weights for policy 0, policy_version 70350 (0.0008) -[2023-10-15 05:06:38,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 144506880. Throughput: 0: 1752.6, 1: 1737.9. Samples: 36136732. Policy #0 lag: (min: 11.0, avg: 18.5, max: 43.0) -[2023-10-15 05:06:38,534][87330] Avg episode reward: [(0, '22.640'), (1, '22.890')] -[2023-10-15 05:06:38,571][88298] Updated weights for policy 0, policy_version 70360 (0.0008) -[2023-10-15 05:06:40,869][88300] Updated weights for policy 1, policy_version 70792 (0.0008) -[2023-10-15 05:06:41,237][88300] Updated weights for policy 1, policy_version 70802 (0.0009) -[2023-10-15 05:06:41,607][88300] Updated weights for policy 1, policy_version 70812 (0.0009) -[2023-10-15 05:06:42,413][88298] Updated weights for policy 0, policy_version 70370 (0.0007) -[2023-10-15 05:06:42,785][88298] Updated weights for policy 0, policy_version 70380 (0.0007) -[2023-10-15 05:06:43,151][88298] Updated weights for policy 0, policy_version 70390 (0.0007) -[2023-10-15 05:06:43,516][88298] Updated weights for policy 0, policy_version 70400 (0.0009) -[2023-10-15 05:06:43,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 144605184. Throughput: 0: 1739.3, 1: 1746.9. Samples: 36158116. Policy #0 lag: (min: 11.0, avg: 18.5, max: 43.0) -[2023-10-15 05:06:43,535][87330] Avg episode reward: [(0, '22.680'), (1, '22.900')] -[2023-10-15 05:06:45,349][88300] Updated weights for policy 1, policy_version 70822 (0.0007) -[2023-10-15 05:06:45,708][88300] Updated weights for policy 1, policy_version 70832 (0.0007) -[2023-10-15 05:06:46,073][88300] Updated weights for policy 1, policy_version 70842 (0.0010) -[2023-10-15 05:06:47,386][88298] Updated weights for policy 0, policy_version 70410 (0.0007) -[2023-10-15 05:06:47,758][88298] Updated weights for policy 0, policy_version 70420 (0.0009) -[2023-10-15 05:06:48,133][88298] Updated weights for policy 0, policy_version 70430 (0.0008) -[2023-10-15 05:06:48,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 144670720. Throughput: 0: 1748.4, 1: 1750.1. Samples: 36168360. Policy #0 lag: (min: 11.0, avg: 18.5, max: 43.0) -[2023-10-15 05:06:48,534][87330] Avg episode reward: [(0, '22.520'), (1, '22.900')] -[2023-10-15 05:06:49,983][88300] Updated weights for policy 1, policy_version 70852 (0.0008) -[2023-10-15 05:06:50,355][88300] Updated weights for policy 1, policy_version 70862 (0.0008) -[2023-10-15 05:06:50,721][88300] Updated weights for policy 1, policy_version 70872 (0.0008) -[2023-10-15 05:06:52,039][88298] Updated weights for policy 0, policy_version 70440 (0.0007) -[2023-10-15 05:06:52,406][88298] Updated weights for policy 0, policy_version 70450 (0.0007) -[2023-10-15 05:06:52,769][88298] Updated weights for policy 0, policy_version 70460 (0.0007) -[2023-10-15 05:06:53,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 144736256. Throughput: 0: 1748.2, 1: 1742.0. Samples: 36189514. Policy #0 lag: (min: 11.0, avg: 18.5, max: 43.0) -[2023-10-15 05:06:53,535][87330] Avg episode reward: [(0, '22.520'), (1, '22.780')] -[2023-10-15 05:06:54,647][88300] Updated weights for policy 1, policy_version 70882 (0.0009) -[2023-10-15 05:06:55,013][88300] Updated weights for policy 1, policy_version 70892 (0.0007) -[2023-10-15 05:06:55,382][88300] Updated weights for policy 1, policy_version 70902 (0.0007) -[2023-10-15 05:06:55,744][88300] Updated weights for policy 1, policy_version 70912 (0.0011) -[2023-10-15 05:06:56,548][88298] Updated weights for policy 0, policy_version 70470 (0.0008) -[2023-10-15 05:06:56,922][88298] Updated weights for policy 0, policy_version 70480 (0.0011) -[2023-10-15 05:06:57,296][88298] Updated weights for policy 0, policy_version 70490 (0.0008) -[2023-10-15 05:06:58,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 144801792. Throughput: 0: 1725.7, 1: 1751.3. Samples: 36209856. Policy #0 lag: (min: 11.0, avg: 18.5, max: 43.0) -[2023-10-15 05:06:58,534][87330] Avg episode reward: [(0, '22.400'), (1, '22.820')] -[2023-10-15 05:06:58,543][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000070496_72187904.pth... -[2023-10-15 05:06:58,544][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000070912_72613888.pth... -[2023-10-15 05:06:58,575][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000068864_70516736.pth -[2023-10-15 05:06:58,582][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000069280_70942720.pth -[2023-10-15 05:06:59,691][88300] Updated weights for policy 1, policy_version 70922 (0.0008) -[2023-10-15 05:07:00,049][88300] Updated weights for policy 1, policy_version 70932 (0.0008) -[2023-10-15 05:07:00,418][88300] Updated weights for policy 1, policy_version 70942 (0.0008) -[2023-10-15 05:07:01,291][88298] Updated weights for policy 0, policy_version 70500 (0.0010) -[2023-10-15 05:07:01,684][88298] Updated weights for policy 0, policy_version 70510 (0.0007) -[2023-10-15 05:07:02,056][88298] Updated weights for policy 0, policy_version 70520 (0.0008) -[2023-10-15 05:07:03,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 144867328. Throughput: 0: 1757.1, 1: 1733.5. Samples: 36220530. Policy #0 lag: (min: 11.0, avg: 18.5, max: 43.0) -[2023-10-15 05:07:03,535][87330] Avg episode reward: [(0, '22.420'), (1, '22.870')] -[2023-10-15 05:07:04,324][88300] Updated weights for policy 1, policy_version 70952 (0.0008) -[2023-10-15 05:07:04,688][88300] Updated weights for policy 1, policy_version 70962 (0.0008) -[2023-10-15 05:07:05,064][88300] Updated weights for policy 1, policy_version 70972 (0.0008) -[2023-10-15 05:07:05,980][88298] Updated weights for policy 0, policy_version 70530 (0.0009) -[2023-10-15 05:07:06,349][88298] Updated weights for policy 0, policy_version 70540 (0.0007) -[2023-10-15 05:07:06,713][88298] Updated weights for policy 0, policy_version 70550 (0.0009) -[2023-10-15 05:07:07,082][88298] Updated weights for policy 0, policy_version 70560 (0.0010) -[2023-10-15 05:07:08,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 144932864. Throughput: 0: 1733.4, 1: 1744.0. Samples: 36241146. Policy #0 lag: (min: 11.0, avg: 18.5, max: 43.0) -[2023-10-15 05:07:08,535][87330] Avg episode reward: [(0, '22.460'), (1, '22.830')] -[2023-10-15 05:07:09,039][88300] Updated weights for policy 1, policy_version 70982 (0.0009) -[2023-10-15 05:07:09,428][88300] Updated weights for policy 1, policy_version 70992 (0.0010) -[2023-10-15 05:07:09,791][88300] Updated weights for policy 1, policy_version 71002 (0.0010) -[2023-10-15 05:07:10,987][88298] Updated weights for policy 0, policy_version 70570 (0.0008) -[2023-10-15 05:07:11,349][88298] Updated weights for policy 0, policy_version 70580 (0.0009) -[2023-10-15 05:07:11,725][88298] Updated weights for policy 0, policy_version 70590 (0.0010) -[2023-10-15 05:07:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 144998400. Throughput: 0: 1720.8, 1: 1760.4. Samples: 36261988. Policy #0 lag: (min: 11.0, avg: 18.5, max: 43.0) -[2023-10-15 05:07:13,535][87330] Avg episode reward: [(0, '22.440'), (1, '22.640')] -[2023-10-15 05:07:13,609][88300] Updated weights for policy 1, policy_version 71012 (0.0009) -[2023-10-15 05:07:13,974][88300] Updated weights for policy 1, policy_version 71022 (0.0009) -[2023-10-15 05:07:14,346][88300] Updated weights for policy 1, policy_version 71032 (0.0009) -[2023-10-15 05:07:15,658][88298] Updated weights for policy 0, policy_version 70600 (0.0009) -[2023-10-15 05:07:16,034][88298] Updated weights for policy 0, policy_version 70610 (0.0007) -[2023-10-15 05:07:16,402][88298] Updated weights for policy 0, policy_version 70620 (0.0007) -[2023-10-15 05:07:18,164][88300] Updated weights for policy 1, policy_version 71042 (0.0008) -[2023-10-15 05:07:18,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 145063936. Throughput: 0: 1741.3, 1: 1730.0. Samples: 36272548. Policy #0 lag: (min: 11.0, avg: 18.5, max: 43.0) -[2023-10-15 05:07:18,535][87330] Avg episode reward: [(0, '22.660'), (1, '22.620')] -[2023-10-15 05:07:18,537][88300] Updated weights for policy 1, policy_version 71052 (0.0008) -[2023-10-15 05:07:18,913][88300] Updated weights for policy 1, policy_version 71062 (0.0008) -[2023-10-15 05:07:19,278][88300] Updated weights for policy 1, policy_version 71072 (0.0009) -[2023-10-15 05:07:20,355][88298] Updated weights for policy 0, policy_version 70630 (0.0008) -[2023-10-15 05:07:20,730][88298] Updated weights for policy 0, policy_version 70640 (0.0009) -[2023-10-15 05:07:21,092][88298] Updated weights for policy 0, policy_version 70650 (0.0009) -[2023-10-15 05:07:23,248][88300] Updated weights for policy 1, policy_version 71082 (0.0010) -[2023-10-15 05:07:23,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 145129472. Throughput: 0: 1722.0, 1: 1760.6. Samples: 36293448. Policy #0 lag: (min: 3.0, avg: 12.9, max: 35.0) -[2023-10-15 05:07:23,535][87330] Avg episode reward: [(0, '22.730'), (1, '22.690')] -[2023-10-15 05:07:23,623][88300] Updated weights for policy 1, policy_version 71092 (0.0007) -[2023-10-15 05:07:23,991][88300] Updated weights for policy 1, policy_version 71102 (0.0009) -[2023-10-15 05:07:24,862][88298] Updated weights for policy 0, policy_version 70660 (0.0009) -[2023-10-15 05:07:25,242][88298] Updated weights for policy 0, policy_version 70670 (0.0008) -[2023-10-15 05:07:25,603][88298] Updated weights for policy 0, policy_version 70680 (0.0008) -[2023-10-15 05:07:27,822][88300] Updated weights for policy 1, policy_version 71112 (0.0007) -[2023-10-15 05:07:28,183][88300] Updated weights for policy 1, policy_version 71122 (0.0007) -[2023-10-15 05:07:28,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 145195008. Throughput: 0: 1727.5, 1: 1743.5. Samples: 36314310. Policy #0 lag: (min: 3.0, avg: 12.9, max: 35.0) -[2023-10-15 05:07:28,534][87330] Avg episode reward: [(0, '22.650'), (1, '22.700')] -[2023-10-15 05:07:28,553][88300] Updated weights for policy 1, policy_version 71132 (0.0008) -[2023-10-15 05:07:29,569][88298] Updated weights for policy 0, policy_version 70690 (0.0007) -[2023-10-15 05:07:29,946][88298] Updated weights for policy 0, policy_version 70700 (0.0008) -[2023-10-15 05:07:30,305][88298] Updated weights for policy 0, policy_version 70710 (0.0007) -[2023-10-15 05:07:30,676][88298] Updated weights for policy 0, policy_version 70720 (0.0007) -[2023-10-15 05:07:32,305][88300] Updated weights for policy 1, policy_version 71142 (0.0007) -[2023-10-15 05:07:32,674][88300] Updated weights for policy 1, policy_version 71152 (0.0007) -[2023-10-15 05:07:33,034][88300] Updated weights for policy 1, policy_version 71162 (0.0007) -[2023-10-15 05:07:33,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 145293312. Throughput: 0: 1721.7, 1: 1756.0. Samples: 36324856. Policy #0 lag: (min: 3.0, avg: 12.9, max: 35.0) -[2023-10-15 05:07:33,534][87330] Avg episode reward: [(0, '22.790'), (1, '22.680')] -[2023-10-15 05:07:34,441][88298] Updated weights for policy 0, policy_version 70730 (0.0007) -[2023-10-15 05:07:34,810][88298] Updated weights for policy 0, policy_version 70740 (0.0008) -[2023-10-15 05:07:35,173][88298] Updated weights for policy 0, policy_version 70750 (0.0010) -[2023-10-15 05:07:36,967][88300] Updated weights for policy 1, policy_version 71172 (0.0008) -[2023-10-15 05:07:37,327][88300] Updated weights for policy 1, policy_version 71182 (0.0007) -[2023-10-15 05:07:37,696][88300] Updated weights for policy 1, policy_version 71192 (0.0007) -[2023-10-15 05:07:38,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.4, 300 sec: 13884.8). Total num frames: 145358848. Throughput: 0: 1724.0, 1: 1751.8. Samples: 36345924. Policy #0 lag: (min: 3.0, avg: 12.9, max: 35.0) -[2023-10-15 05:07:38,534][87330] Avg episode reward: [(0, '22.720'), (1, '22.750')] -[2023-10-15 05:07:39,088][88298] Updated weights for policy 0, policy_version 70760 (0.0009) -[2023-10-15 05:07:39,454][88298] Updated weights for policy 0, policy_version 70770 (0.0008) -[2023-10-15 05:07:39,819][88298] Updated weights for policy 0, policy_version 70780 (0.0009) -[2023-10-15 05:07:41,674][88300] Updated weights for policy 1, policy_version 71202 (0.0009) -[2023-10-15 05:07:42,044][88300] Updated weights for policy 1, policy_version 71212 (0.0008) -[2023-10-15 05:07:42,411][88300] Updated weights for policy 1, policy_version 71222 (0.0008) -[2023-10-15 05:07:42,778][88300] Updated weights for policy 1, policy_version 71232 (0.0008) -[2023-10-15 05:07:43,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 145424384. Throughput: 0: 1751.7, 1: 1731.6. Samples: 36366608. Policy #0 lag: (min: 3.0, avg: 12.9, max: 35.0) -[2023-10-15 05:07:43,534][87330] Avg episode reward: [(0, '22.670'), (1, '22.730')] -[2023-10-15 05:07:43,806][88298] Updated weights for policy 0, policy_version 70790 (0.0008) -[2023-10-15 05:07:44,180][88298] Updated weights for policy 0, policy_version 70800 (0.0008) -[2023-10-15 05:07:44,547][88298] Updated weights for policy 0, policy_version 70810 (0.0009) -[2023-10-15 05:07:46,481][88300] Updated weights for policy 1, policy_version 71242 (0.0009) -[2023-10-15 05:07:46,854][88300] Updated weights for policy 1, policy_version 71252 (0.0011) -[2023-10-15 05:07:47,225][88300] Updated weights for policy 1, policy_version 71262 (0.0010) -[2023-10-15 05:07:48,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 145489920. Throughput: 0: 1718.9, 1: 1768.6. Samples: 36377464. Policy #0 lag: (min: 3.0, avg: 12.9, max: 35.0) -[2023-10-15 05:07:48,534][87330] Avg episode reward: [(0, '22.620'), (1, '23.040')] -[2023-10-15 05:07:48,566][88298] Updated weights for policy 0, policy_version 70820 (0.0008) -[2023-10-15 05:07:48,965][88298] Updated weights for policy 0, policy_version 70830 (0.0007) -[2023-10-15 05:07:49,331][88298] Updated weights for policy 0, policy_version 70840 (0.0007) -[2023-10-15 05:07:51,168][88300] Updated weights for policy 1, policy_version 71272 (0.0008) -[2023-10-15 05:07:51,531][88300] Updated weights for policy 1, policy_version 71282 (0.0009) -[2023-10-15 05:07:51,895][88300] Updated weights for policy 1, policy_version 71292 (0.0007) -[2023-10-15 05:07:53,139][88298] Updated weights for policy 0, policy_version 70850 (0.0007) -[2023-10-15 05:07:53,522][88298] Updated weights for policy 0, policy_version 70860 (0.0008) -[2023-10-15 05:07:53,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 145555456. Throughput: 0: 1744.4, 1: 1735.8. Samples: 36397758. Policy #0 lag: (min: 3.0, avg: 12.9, max: 35.0) -[2023-10-15 05:07:53,535][87330] Avg episode reward: [(0, '22.630'), (1, '22.840')] -[2023-10-15 05:07:53,896][88298] Updated weights for policy 0, policy_version 70870 (0.0009) -[2023-10-15 05:07:54,265][88298] Updated weights for policy 0, policy_version 70880 (0.0007) -[2023-10-15 05:07:55,825][88300] Updated weights for policy 1, policy_version 71302 (0.0008) -[2023-10-15 05:07:56,194][88300] Updated weights for policy 1, policy_version 71312 (0.0009) -[2023-10-15 05:07:56,566][88300] Updated weights for policy 1, policy_version 71322 (0.0010) -[2023-10-15 05:07:57,982][88298] Updated weights for policy 0, policy_version 70890 (0.0008) -[2023-10-15 05:07:58,360][88298] Updated weights for policy 0, policy_version 70900 (0.0008) -[2023-10-15 05:07:58,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 145620992. Throughput: 0: 1759.7, 1: 1738.7. Samples: 36419414. Policy #0 lag: (min: 3.0, avg: 12.9, max: 35.0) -[2023-10-15 05:07:58,534][87330] Avg episode reward: [(0, '22.610'), (1, '22.810')] -[2023-10-15 05:07:58,719][88298] Updated weights for policy 0, policy_version 70910 (0.0011) -[2023-10-15 05:08:00,445][88300] Updated weights for policy 1, policy_version 71332 (0.0010) -[2023-10-15 05:08:00,809][88300] Updated weights for policy 1, policy_version 71342 (0.0008) -[2023-10-15 05:08:01,180][88300] Updated weights for policy 1, policy_version 71352 (0.0008) -[2023-10-15 05:08:02,630][88298] Updated weights for policy 0, policy_version 70920 (0.0008) -[2023-10-15 05:08:03,002][88298] Updated weights for policy 0, policy_version 70930 (0.0007) -[2023-10-15 05:08:03,366][88298] Updated weights for policy 0, policy_version 70940 (0.0008) -[2023-10-15 05:08:03,534][87330] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 145719296. Throughput: 0: 1745.2, 1: 1743.8. Samples: 36429556. Policy #0 lag: (min: 3.0, avg: 12.9, max: 35.0) -[2023-10-15 05:08:03,534][87330] Avg episode reward: [(0, '22.690'), (1, '22.810')] -[2023-10-15 05:08:05,042][88300] Updated weights for policy 1, policy_version 71362 (0.0009) -[2023-10-15 05:08:05,416][88300] Updated weights for policy 1, policy_version 71372 (0.0008) -[2023-10-15 05:08:05,781][88300] Updated weights for policy 1, policy_version 71382 (0.0007) -[2023-10-15 05:08:06,149][88300] Updated weights for policy 1, policy_version 71392 (0.0008) -[2023-10-15 05:08:07,300][88298] Updated weights for policy 0, policy_version 70950 (0.0008) -[2023-10-15 05:08:07,674][88298] Updated weights for policy 0, policy_version 70960 (0.0008) -[2023-10-15 05:08:08,033][88298] Updated weights for policy 0, policy_version 70970 (0.0007) -[2023-10-15 05:08:08,534][87330] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 145784832. Throughput: 0: 1763.4, 1: 1739.1. Samples: 36451060. Policy #0 lag: (min: 7.0, avg: 11.8, max: 39.0) -[2023-10-15 05:08:08,535][87330] Avg episode reward: [(0, '22.540'), (1, '22.830')] -[2023-10-15 05:08:10,079][88300] Updated weights for policy 1, policy_version 71402 (0.0008) -[2023-10-15 05:08:10,450][88300] Updated weights for policy 1, policy_version 71412 (0.0007) -[2023-10-15 05:08:10,807][88300] Updated weights for policy 1, policy_version 71422 (0.0009) -[2023-10-15 05:08:11,928][88298] Updated weights for policy 0, policy_version 70980 (0.0008) -[2023-10-15 05:08:12,304][88298] Updated weights for policy 0, policy_version 70990 (0.0009) -[2023-10-15 05:08:12,674][88298] Updated weights for policy 0, policy_version 71000 (0.0008) -[2023-10-15 05:08:13,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 145850368. Throughput: 0: 1740.5, 1: 1749.0. Samples: 36471336. Policy #0 lag: (min: 7.0, avg: 11.8, max: 39.0) -[2023-10-15 05:08:13,534][87330] Avg episode reward: [(0, '22.610'), (1, '22.750')] -[2023-10-15 05:08:14,742][88300] Updated weights for policy 1, policy_version 71432 (0.0009) -[2023-10-15 05:08:15,104][88300] Updated weights for policy 1, policy_version 71442 (0.0007) -[2023-10-15 05:08:15,471][88300] Updated weights for policy 1, policy_version 71452 (0.0007) -[2023-10-15 05:08:16,482][88298] Updated weights for policy 0, policy_version 71010 (0.0007) -[2023-10-15 05:08:16,848][88298] Updated weights for policy 0, policy_version 71020 (0.0009) -[2023-10-15 05:08:17,221][88298] Updated weights for policy 0, policy_version 71030 (0.0007) -[2023-10-15 05:08:17,581][88298] Updated weights for policy 0, policy_version 71040 (0.0007) -[2023-10-15 05:08:18,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 145915904. Throughput: 0: 1762.6, 1: 1728.5. Samples: 36481956. Policy #0 lag: (min: 7.0, avg: 11.8, max: 39.0) -[2023-10-15 05:08:18,535][87330] Avg episode reward: [(0, '22.490'), (1, '22.600')] -[2023-10-15 05:08:19,321][88300] Updated weights for policy 1, policy_version 71462 (0.0009) -[2023-10-15 05:08:19,687][88300] Updated weights for policy 1, policy_version 71472 (0.0010) -[2023-10-15 05:08:20,058][88300] Updated weights for policy 1, policy_version 71482 (0.0011) -[2023-10-15 05:08:21,413][88298] Updated weights for policy 0, policy_version 71050 (0.0010) -[2023-10-15 05:08:21,787][88298] Updated weights for policy 0, policy_version 71060 (0.0007) -[2023-10-15 05:08:22,155][88298] Updated weights for policy 0, policy_version 71070 (0.0009) -[2023-10-15 05:08:23,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 145981440. Throughput: 0: 1745.5, 1: 1739.0. Samples: 36502728. Policy #0 lag: (min: 7.0, avg: 11.8, max: 39.0) -[2023-10-15 05:08:23,535][87330] Avg episode reward: [(0, '22.590'), (1, '22.560')] -[2023-10-15 05:08:23,847][88300] Updated weights for policy 1, policy_version 71492 (0.0010) -[2023-10-15 05:08:24,222][88300] Updated weights for policy 1, policy_version 71502 (0.0007) -[2023-10-15 05:08:24,596][88300] Updated weights for policy 1, policy_version 71512 (0.0009) -[2023-10-15 05:08:26,142][88298] Updated weights for policy 0, policy_version 71080 (0.0011) -[2023-10-15 05:08:26,501][88298] Updated weights for policy 0, policy_version 71090 (0.0007) -[2023-10-15 05:08:26,873][88298] Updated weights for policy 0, policy_version 71100 (0.0007) -[2023-10-15 05:08:28,417][88300] Updated weights for policy 1, policy_version 71522 (0.0007) -[2023-10-15 05:08:28,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 146046976. Throughput: 0: 1728.6, 1: 1769.5. Samples: 36524020. Policy #0 lag: (min: 7.0, avg: 11.8, max: 39.0) -[2023-10-15 05:08:28,534][87330] Avg episode reward: [(0, '22.580'), (1, '22.740')] -[2023-10-15 05:08:28,789][88300] Updated weights for policy 1, policy_version 71532 (0.0010) -[2023-10-15 05:08:29,156][88300] Updated weights for policy 1, policy_version 71542 (0.0009) -[2023-10-15 05:08:29,520][88300] Updated weights for policy 1, policy_version 71552 (0.0008) -[2023-10-15 05:08:30,767][88298] Updated weights for policy 0, policy_version 71110 (0.0009) -[2023-10-15 05:08:31,141][88298] Updated weights for policy 0, policy_version 71120 (0.0010) -[2023-10-15 05:08:31,513][88298] Updated weights for policy 0, policy_version 71130 (0.0008) -[2023-10-15 05:08:33,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 146112512. Throughput: 0: 1760.2, 1: 1738.3. Samples: 36534896. Policy #0 lag: (min: 7.0, avg: 11.8, max: 39.0) -[2023-10-15 05:08:33,535][87330] Avg episode reward: [(0, '22.640'), (1, '22.730')] -[2023-10-15 05:08:33,574][88300] Updated weights for policy 1, policy_version 71562 (0.0010) -[2023-10-15 05:08:33,947][88300] Updated weights for policy 1, policy_version 71572 (0.0009) -[2023-10-15 05:08:34,308][88300] Updated weights for policy 1, policy_version 71582 (0.0007) -[2023-10-15 05:08:35,504][88298] Updated weights for policy 0, policy_version 71140 (0.0007) -[2023-10-15 05:08:35,874][88298] Updated weights for policy 0, policy_version 71150 (0.0007) -[2023-10-15 05:08:36,247][88298] Updated weights for policy 0, policy_version 71160 (0.0008) -[2023-10-15 05:08:38,094][88300] Updated weights for policy 1, policy_version 71592 (0.0007) -[2023-10-15 05:08:38,463][88300] Updated weights for policy 1, policy_version 71602 (0.0007) -[2023-10-15 05:08:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 146178048. Throughput: 0: 1735.0, 1: 1765.0. Samples: 36555258. Policy #0 lag: (min: 7.0, avg: 11.8, max: 39.0) -[2023-10-15 05:08:38,534][87330] Avg episode reward: [(0, '22.650'), (1, '22.480')] -[2023-10-15 05:08:38,833][88300] Updated weights for policy 1, policy_version 71612 (0.0008) -[2023-10-15 05:08:40,089][88298] Updated weights for policy 0, policy_version 71170 (0.0008) -[2023-10-15 05:08:40,463][88298] Updated weights for policy 0, policy_version 71180 (0.0011) -[2023-10-15 05:08:40,828][88298] Updated weights for policy 0, policy_version 71190 (0.0007) -[2023-10-15 05:08:41,195][88298] Updated weights for policy 0, policy_version 71200 (0.0010) -[2023-10-15 05:08:42,783][88300] Updated weights for policy 1, policy_version 71622 (0.0008) -[2023-10-15 05:08:43,167][88300] Updated weights for policy 1, policy_version 71632 (0.0009) -[2023-10-15 05:08:43,530][88300] Updated weights for policy 1, policy_version 71642 (0.0009) -[2023-10-15 05:08:43,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 146243584. Throughput: 0: 1736.3, 1: 1750.5. Samples: 36576322. Policy #0 lag: (min: 7.0, avg: 11.8, max: 39.0) -[2023-10-15 05:08:43,534][87330] Avg episode reward: [(0, '22.610'), (1, '22.520')] -[2023-10-15 05:08:44,850][88298] Updated weights for policy 0, policy_version 71210 (0.0009) -[2023-10-15 05:08:45,219][88298] Updated weights for policy 0, policy_version 71220 (0.0008) -[2023-10-15 05:08:45,584][88298] Updated weights for policy 0, policy_version 71230 (0.0008) -[2023-10-15 05:08:47,355][88300] Updated weights for policy 1, policy_version 71652 (0.0008) -[2023-10-15 05:08:47,727][88300] Updated weights for policy 1, policy_version 71662 (0.0010) -[2023-10-15 05:08:48,087][88300] Updated weights for policy 1, policy_version 71672 (0.0009) -[2023-10-15 05:08:48,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 146341888. Throughput: 0: 1731.1, 1: 1759.3. Samples: 36586624. Policy #0 lag: (min: 7.0, avg: 11.8, max: 39.0) -[2023-10-15 05:08:48,534][87330] Avg episode reward: [(0, '22.730'), (1, '22.660')] -[2023-10-15 05:08:49,501][88298] Updated weights for policy 0, policy_version 71240 (0.0008) -[2023-10-15 05:08:49,872][88298] Updated weights for policy 0, policy_version 71250 (0.0007) -[2023-10-15 05:08:50,241][88298] Updated weights for policy 0, policy_version 71260 (0.0007) -[2023-10-15 05:08:52,081][88300] Updated weights for policy 1, policy_version 71682 (0.0008) -[2023-10-15 05:08:52,446][88300] Updated weights for policy 1, policy_version 71692 (0.0007) -[2023-10-15 05:08:52,807][88300] Updated weights for policy 1, policy_version 71702 (0.0007) -[2023-10-15 05:08:53,173][88300] Updated weights for policy 1, policy_version 71712 (0.0008) -[2023-10-15 05:08:53,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 146407424. Throughput: 0: 1726.4, 1: 1755.5. Samples: 36607746. Policy #0 lag: (min: 7.0, avg: 11.8, max: 39.0) -[2023-10-15 05:08:53,534][87330] Avg episode reward: [(0, '22.610'), (1, '22.700')] -[2023-10-15 05:08:54,167][88298] Updated weights for policy 0, policy_version 71270 (0.0008) -[2023-10-15 05:08:54,539][88298] Updated weights for policy 0, policy_version 71280 (0.0008) -[2023-10-15 05:08:54,909][88298] Updated weights for policy 0, policy_version 71290 (0.0008) -[2023-10-15 05:08:57,167][88300] Updated weights for policy 1, policy_version 71722 (0.0007) -[2023-10-15 05:08:57,533][88300] Updated weights for policy 1, policy_version 71732 (0.0010) -[2023-10-15 05:08:57,903][88300] Updated weights for policy 1, policy_version 71742 (0.0007) -[2023-10-15 05:08:58,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 146472960. Throughput: 0: 1753.0, 1: 1735.1. Samples: 36628298. Policy #0 lag: (min: 16.0, avg: 33.5, max: 48.0) -[2023-10-15 05:08:58,534][87330] Avg episode reward: [(0, '22.480'), (1, '22.730')] -[2023-10-15 05:08:58,543][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000071296_73007104.pth... -[2023-10-15 05:08:58,544][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000071744_73465856.pth... -[2023-10-15 05:08:58,589][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000070112_71794688.pth -[2023-10-15 05:08:58,590][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000069696_71368704.pth -[2023-10-15 05:08:58,920][88298] Updated weights for policy 0, policy_version 71300 (0.0010) -[2023-10-15 05:08:59,296][88298] Updated weights for policy 0, policy_version 71310 (0.0008) -[2023-10-15 05:08:59,671][88298] Updated weights for policy 0, policy_version 71320 (0.0007) -[2023-10-15 05:09:01,643][88300] Updated weights for policy 1, policy_version 71752 (0.0007) -[2023-10-15 05:09:02,012][88300] Updated weights for policy 1, policy_version 71762 (0.0009) -[2023-10-15 05:09:02,390][88300] Updated weights for policy 1, policy_version 71772 (0.0011) -[2023-10-15 05:09:03,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 146538496. Throughput: 0: 1725.5, 1: 1768.2. Samples: 36639170. Policy #0 lag: (min: 16.0, avg: 33.5, max: 48.0) -[2023-10-15 05:09:03,535][87330] Avg episode reward: [(0, '22.430'), (1, '22.790')] -[2023-10-15 05:09:03,565][88298] Updated weights for policy 0, policy_version 71330 (0.0010) -[2023-10-15 05:09:03,936][88298] Updated weights for policy 0, policy_version 71340 (0.0010) -[2023-10-15 05:09:04,307][88298] Updated weights for policy 0, policy_version 71350 (0.0008) -[2023-10-15 05:09:04,670][88298] Updated weights for policy 0, policy_version 71360 (0.0007) -[2023-10-15 05:09:06,278][88300] Updated weights for policy 1, policy_version 71782 (0.0010) -[2023-10-15 05:09:06,635][88300] Updated weights for policy 1, policy_version 71792 (0.0009) -[2023-10-15 05:09:07,008][88300] Updated weights for policy 1, policy_version 71802 (0.0010) -[2023-10-15 05:09:08,484][88298] Updated weights for policy 0, policy_version 71370 (0.0007) -[2023-10-15 05:09:08,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 146604032. Throughput: 0: 1741.9, 1: 1741.9. Samples: 36659500. Policy #0 lag: (min: 16.0, avg: 33.5, max: 48.0) -[2023-10-15 05:09:08,534][87330] Avg episode reward: [(0, '22.530'), (1, '23.040')] -[2023-10-15 05:09:08,845][88298] Updated weights for policy 0, policy_version 71380 (0.0007) -[2023-10-15 05:09:09,212][88298] Updated weights for policy 0, policy_version 71390 (0.0007) -[2023-10-15 05:09:10,664][88300] Updated weights for policy 1, policy_version 71812 (0.0009) -[2023-10-15 05:09:11,043][88300] Updated weights for policy 1, policy_version 71822 (0.0009) -[2023-10-15 05:09:11,411][88300] Updated weights for policy 1, policy_version 71832 (0.0009) -[2023-10-15 05:09:13,098][88298] Updated weights for policy 0, policy_version 71400 (0.0007) -[2023-10-15 05:09:13,461][88298] Updated weights for policy 0, policy_version 71410 (0.0009) -[2023-10-15 05:09:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 146669568. Throughput: 0: 1760.7, 1: 1738.4. Samples: 36681480. Policy #0 lag: (min: 16.0, avg: 33.5, max: 48.0) -[2023-10-15 05:09:13,535][87330] Avg episode reward: [(0, '22.600'), (1, '23.100')] -[2023-10-15 05:09:13,835][88298] Updated weights for policy 0, policy_version 71420 (0.0010) -[2023-10-15 05:09:15,261][88300] Updated weights for policy 1, policy_version 71842 (0.0010) -[2023-10-15 05:09:15,618][88300] Updated weights for policy 1, policy_version 71852 (0.0009) -[2023-10-15 05:09:15,980][88300] Updated weights for policy 1, policy_version 71862 (0.0007) -[2023-10-15 05:09:16,342][88300] Updated weights for policy 1, policy_version 71872 (0.0008) -[2023-10-15 05:09:17,854][88298] Updated weights for policy 0, policy_version 71430 (0.0009) -[2023-10-15 05:09:18,215][88298] Updated weights for policy 0, policy_version 71440 (0.0007) -[2023-10-15 05:09:18,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 146735104. Throughput: 0: 1725.1, 1: 1743.8. Samples: 36690996. Policy #0 lag: (min: 16.0, avg: 33.5, max: 48.0) -[2023-10-15 05:09:18,534][87330] Avg episode reward: [(0, '22.570'), (1, '23.040')] -[2023-10-15 05:09:18,583][88298] Updated weights for policy 0, policy_version 71450 (0.0008) -[2023-10-15 05:09:20,068][88300] Updated weights for policy 1, policy_version 71882 (0.0007) -[2023-10-15 05:09:20,439][88300] Updated weights for policy 1, policy_version 71892 (0.0007) -[2023-10-15 05:09:20,808][88300] Updated weights for policy 1, policy_version 71902 (0.0008) -[2023-10-15 05:09:22,622][88298] Updated weights for policy 0, policy_version 71460 (0.0008) -[2023-10-15 05:09:23,024][88298] Updated weights for policy 0, policy_version 71470 (0.0007) -[2023-10-15 05:09:23,397][88298] Updated weights for policy 0, policy_version 71480 (0.0007) -[2023-10-15 05:09:23,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 146800640. Throughput: 0: 1749.1, 1: 1743.9. Samples: 36712446. Policy #0 lag: (min: 16.0, avg: 33.5, max: 48.0) -[2023-10-15 05:09:23,534][87330] Avg episode reward: [(0, '22.620'), (1, '23.040')] -[2023-10-15 05:09:24,801][88300] Updated weights for policy 1, policy_version 71912 (0.0008) -[2023-10-15 05:09:25,168][88300] Updated weights for policy 1, policy_version 71922 (0.0009) -[2023-10-15 05:09:25,542][88300] Updated weights for policy 1, policy_version 71932 (0.0010) -[2023-10-15 05:09:27,517][88298] Updated weights for policy 0, policy_version 71490 (0.0009) -[2023-10-15 05:09:27,890][88298] Updated weights for policy 0, policy_version 71500 (0.0009) -[2023-10-15 05:09:28,262][88298] Updated weights for policy 0, policy_version 71510 (0.0007) -[2023-10-15 05:09:28,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 146866176. Throughput: 0: 1730.5, 1: 1757.4. Samples: 36733280. Policy #0 lag: (min: 16.0, avg: 33.5, max: 48.0) -[2023-10-15 05:09:28,535][87330] Avg episode reward: [(0, '22.680'), (1, '22.950')] -[2023-10-15 05:09:28,626][88298] Updated weights for policy 0, policy_version 71520 (0.0007) -[2023-10-15 05:09:29,681][88300] Updated weights for policy 1, policy_version 71942 (0.0009) -[2023-10-15 05:09:30,065][88300] Updated weights for policy 1, policy_version 71952 (0.0009) -[2023-10-15 05:09:30,437][88300] Updated weights for policy 1, policy_version 71962 (0.0007) -[2023-10-15 05:09:32,469][88298] Updated weights for policy 0, policy_version 71530 (0.0010) -[2023-10-15 05:09:32,834][88298] Updated weights for policy 0, policy_version 71540 (0.0009) -[2023-10-15 05:09:33,211][88298] Updated weights for policy 0, policy_version 71550 (0.0007) -[2023-10-15 05:09:33,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 146964480. Throughput: 0: 1737.9, 1: 1736.8. Samples: 36742984. Policy #0 lag: (min: 16.0, avg: 33.5, max: 48.0) -[2023-10-15 05:09:33,534][87330] Avg episode reward: [(0, '22.740'), (1, '22.820')] -[2023-10-15 05:09:34,305][88300] Updated weights for policy 1, policy_version 71972 (0.0009) -[2023-10-15 05:09:34,671][88300] Updated weights for policy 1, policy_version 71982 (0.0010) -[2023-10-15 05:09:35,049][88300] Updated weights for policy 1, policy_version 71992 (0.0009) -[2023-10-15 05:09:37,044][88298] Updated weights for policy 0, policy_version 71560 (0.0009) -[2023-10-15 05:09:37,424][88298] Updated weights for policy 0, policy_version 71570 (0.0009) -[2023-10-15 05:09:37,781][88298] Updated weights for policy 0, policy_version 71580 (0.0009) -[2023-10-15 05:09:38,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 147030016. Throughput: 0: 1739.5, 1: 1745.6. Samples: 36764576. Policy #0 lag: (min: 16.0, avg: 33.5, max: 48.0) -[2023-10-15 05:09:38,535][87330] Avg episode reward: [(0, '22.780'), (1, '22.810')] -[2023-10-15 05:09:38,761][88300] Updated weights for policy 1, policy_version 72002 (0.0008) -[2023-10-15 05:09:39,131][88300] Updated weights for policy 1, policy_version 72012 (0.0008) -[2023-10-15 05:09:39,491][88300] Updated weights for policy 1, policy_version 72022 (0.0010) -[2023-10-15 05:09:39,857][88300] Updated weights for policy 1, policy_version 72032 (0.0009) -[2023-10-15 05:09:41,697][88298] Updated weights for policy 0, policy_version 71590 (0.0010) -[2023-10-15 05:09:42,070][88298] Updated weights for policy 0, policy_version 71600 (0.0011) -[2023-10-15 05:09:42,449][88298] Updated weights for policy 0, policy_version 71610 (0.0007) -[2023-10-15 05:09:43,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 147095552. Throughput: 0: 1708.3, 1: 1773.7. Samples: 36784988. Policy #0 lag: (min: 18.0, avg: 27.1, max: 50.0) -[2023-10-15 05:09:43,535][87330] Avg episode reward: [(0, '22.620'), (1, '22.830')] -[2023-10-15 05:09:43,708][88300] Updated weights for policy 1, policy_version 72042 (0.0008) -[2023-10-15 05:09:44,077][88300] Updated weights for policy 1, policy_version 72052 (0.0008) -[2023-10-15 05:09:44,450][88300] Updated weights for policy 1, policy_version 72062 (0.0008) -[2023-10-15 05:09:46,468][88298] Updated weights for policy 0, policy_version 71620 (0.0008) -[2023-10-15 05:09:46,843][88298] Updated weights for policy 0, policy_version 71630 (0.0008) -[2023-10-15 05:09:47,216][88298] Updated weights for policy 0, policy_version 71640 (0.0009) -[2023-10-15 05:09:48,157][88300] Updated weights for policy 1, policy_version 72072 (0.0008) -[2023-10-15 05:09:48,520][88300] Updated weights for policy 1, policy_version 72082 (0.0009) -[2023-10-15 05:09:48,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 147161088. Throughput: 0: 1736.5, 1: 1742.5. Samples: 36795726. Policy #0 lag: (min: 18.0, avg: 27.1, max: 50.0) -[2023-10-15 05:09:48,535][87330] Avg episode reward: [(0, '22.660'), (1, '22.830')] -[2023-10-15 05:09:48,880][88300] Updated weights for policy 1, policy_version 72092 (0.0010) -[2023-10-15 05:09:50,983][88298] Updated weights for policy 0, policy_version 71650 (0.0009) -[2023-10-15 05:09:51,350][88298] Updated weights for policy 0, policy_version 71660 (0.0010) -[2023-10-15 05:09:51,719][88298] Updated weights for policy 0, policy_version 71670 (0.0007) -[2023-10-15 05:09:52,092][88298] Updated weights for policy 0, policy_version 71680 (0.0008) -[2023-10-15 05:09:52,798][88300] Updated weights for policy 1, policy_version 72102 (0.0008) -[2023-10-15 05:09:53,170][88300] Updated weights for policy 1, policy_version 72112 (0.0009) -[2023-10-15 05:09:53,530][88300] Updated weights for policy 1, policy_version 72122 (0.0009) -[2023-10-15 05:09:53,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 147226624. Throughput: 0: 1714.6, 1: 1772.1. Samples: 36816402. Policy #0 lag: (min: 18.0, avg: 27.1, max: 50.0) -[2023-10-15 05:09:53,535][87330] Avg episode reward: [(0, '22.640'), (1, '22.900')] -[2023-10-15 05:09:55,812][88298] Updated weights for policy 0, policy_version 71690 (0.0007) -[2023-10-15 05:09:56,183][88298] Updated weights for policy 0, policy_version 71700 (0.0009) -[2023-10-15 05:09:56,551][88298] Updated weights for policy 0, policy_version 71710 (0.0007) -[2023-10-15 05:09:57,466][88300] Updated weights for policy 1, policy_version 72132 (0.0009) -[2023-10-15 05:09:57,833][88300] Updated weights for policy 1, policy_version 72142 (0.0009) -[2023-10-15 05:09:58,203][88300] Updated weights for policy 1, policy_version 72152 (0.0009) -[2023-10-15 05:09:58,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 147324928. Throughput: 0: 1705.8, 1: 1742.8. Samples: 36836664. Policy #0 lag: (min: 18.0, avg: 27.1, max: 50.0) -[2023-10-15 05:09:58,534][87330] Avg episode reward: [(0, '22.630'), (1, '22.870')] -[2023-10-15 05:10:00,435][88298] Updated weights for policy 0, policy_version 71720 (0.0008) -[2023-10-15 05:10:00,801][88298] Updated weights for policy 0, policy_version 71730 (0.0008) -[2023-10-15 05:10:01,172][88298] Updated weights for policy 0, policy_version 71740 (0.0010) -[2023-10-15 05:10:02,244][88300] Updated weights for policy 1, policy_version 72162 (0.0007) -[2023-10-15 05:10:02,606][88300] Updated weights for policy 1, policy_version 72172 (0.0007) -[2023-10-15 05:10:02,976][88300] Updated weights for policy 1, policy_version 72182 (0.0008) -[2023-10-15 05:10:03,339][88300] Updated weights for policy 1, policy_version 72192 (0.0009) -[2023-10-15 05:10:03,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 147390464. Throughput: 0: 1726.4, 1: 1760.5. Samples: 36847906. Policy #0 lag: (min: 18.0, avg: 27.1, max: 50.0) -[2023-10-15 05:10:03,534][87330] Avg episode reward: [(0, '22.710'), (1, '23.120')] -[2023-10-15 05:10:05,225][88298] Updated weights for policy 0, policy_version 71750 (0.0009) -[2023-10-15 05:10:05,599][88298] Updated weights for policy 0, policy_version 71760 (0.0007) -[2023-10-15 05:10:05,974][88298] Updated weights for policy 0, policy_version 71770 (0.0008) -[2023-10-15 05:10:07,255][88300] Updated weights for policy 1, policy_version 72202 (0.0011) -[2023-10-15 05:10:07,623][88300] Updated weights for policy 1, policy_version 72212 (0.0011) -[2023-10-15 05:10:07,999][88300] Updated weights for policy 1, policy_version 72222 (0.0010) -[2023-10-15 05:10:08,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 147456000. Throughput: 0: 1709.7, 1: 1755.1. Samples: 36868362. Policy #0 lag: (min: 18.0, avg: 27.1, max: 50.0) -[2023-10-15 05:10:08,534][87330] Avg episode reward: [(0, '22.740'), (1, '23.080')] -[2023-10-15 05:10:10,129][88298] Updated weights for policy 0, policy_version 71780 (0.0009) -[2023-10-15 05:10:10,526][88298] Updated weights for policy 0, policy_version 71790 (0.0008) -[2023-10-15 05:10:10,898][88298] Updated weights for policy 0, policy_version 71800 (0.0009) -[2023-10-15 05:10:11,747][88300] Updated weights for policy 1, policy_version 72232 (0.0008) -[2023-10-15 05:10:12,110][88300] Updated weights for policy 1, policy_version 72242 (0.0009) -[2023-10-15 05:10:12,477][88300] Updated weights for policy 1, policy_version 72252 (0.0008) -[2023-10-15 05:10:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 147521536. Throughput: 0: 1720.6, 1: 1744.4. Samples: 36889204. Policy #0 lag: (min: 18.0, avg: 27.1, max: 50.0) -[2023-10-15 05:10:13,534][87330] Avg episode reward: [(0, '22.720'), (1, '23.060')] -[2023-10-15 05:10:14,663][88298] Updated weights for policy 0, policy_version 71810 (0.0008) -[2023-10-15 05:10:15,033][88298] Updated weights for policy 0, policy_version 71820 (0.0011) -[2023-10-15 05:10:15,407][88298] Updated weights for policy 0, policy_version 71830 (0.0008) -[2023-10-15 05:10:15,768][88298] Updated weights for policy 0, policy_version 71840 (0.0007) -[2023-10-15 05:10:16,407][88300] Updated weights for policy 1, policy_version 72262 (0.0009) -[2023-10-15 05:10:16,773][88300] Updated weights for policy 1, policy_version 72272 (0.0011) -[2023-10-15 05:10:17,142][88300] Updated weights for policy 1, policy_version 72282 (0.0010) -[2023-10-15 05:10:18,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 147587072. Throughput: 0: 1714.7, 1: 1778.2. Samples: 36900164. Policy #0 lag: (min: 18.0, avg: 27.1, max: 50.0) -[2023-10-15 05:10:18,534][87330] Avg episode reward: [(0, '22.920'), (1, '22.990')] -[2023-10-15 05:10:19,725][88298] Updated weights for policy 0, policy_version 71850 (0.0009) -[2023-10-15 05:10:20,093][88298] Updated weights for policy 0, policy_version 71860 (0.0009) -[2023-10-15 05:10:20,465][88298] Updated weights for policy 0, policy_version 71870 (0.0008) -[2023-10-15 05:10:21,055][88300] Updated weights for policy 1, policy_version 72292 (0.0010) -[2023-10-15 05:10:21,425][88300] Updated weights for policy 1, policy_version 72302 (0.0010) -[2023-10-15 05:10:21,779][88300] Updated weights for policy 1, policy_version 72312 (0.0008) -[2023-10-15 05:10:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 147652608. Throughput: 0: 1721.5, 1: 1743.3. Samples: 36920490. Policy #0 lag: (min: 18.0, avg: 27.1, max: 50.0) -[2023-10-15 05:10:23,534][87330] Avg episode reward: [(0, '22.860'), (1, '22.920')] -[2023-10-15 05:10:24,364][88298] Updated weights for policy 0, policy_version 71880 (0.0007) -[2023-10-15 05:10:24,726][88298] Updated weights for policy 0, policy_version 71890 (0.0007) -[2023-10-15 05:10:25,105][88298] Updated weights for policy 0, policy_version 71900 (0.0007) -[2023-10-15 05:10:25,691][88300] Updated weights for policy 1, policy_version 72322 (0.0007) -[2023-10-15 05:10:26,051][88300] Updated weights for policy 1, policy_version 72332 (0.0009) -[2023-10-15 05:10:26,425][88300] Updated weights for policy 1, policy_version 72342 (0.0008) -[2023-10-15 05:10:26,785][88300] Updated weights for policy 1, policy_version 72352 (0.0009) -[2023-10-15 05:10:28,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 147718144. Throughput: 0: 1752.8, 1: 1741.7. Samples: 36942242. Policy #0 lag: (min: 18.0, avg: 27.1, max: 50.0) -[2023-10-15 05:10:28,535][87330] Avg episode reward: [(0, '22.880'), (1, '22.920')] -[2023-10-15 05:10:28,954][88298] Updated weights for policy 0, policy_version 71910 (0.0007) -[2023-10-15 05:10:29,324][88298] Updated weights for policy 0, policy_version 71920 (0.0007) -[2023-10-15 05:10:29,706][88298] Updated weights for policy 0, policy_version 71930 (0.0007) -[2023-10-15 05:10:30,556][88300] Updated weights for policy 1, policy_version 72362 (0.0008) -[2023-10-15 05:10:30,932][88300] Updated weights for policy 1, policy_version 72372 (0.0008) -[2023-10-15 05:10:31,300][88300] Updated weights for policy 1, policy_version 72382 (0.0008) -[2023-10-15 05:10:33,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 147783680. Throughput: 0: 1722.9, 1: 1749.4. Samples: 36951978. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:10:33,534][87330] Avg episode reward: [(0, '22.690'), (1, '22.920')] -[2023-10-15 05:10:33,720][88298] Updated weights for policy 0, policy_version 71940 (0.0008) -[2023-10-15 05:10:34,088][88298] Updated weights for policy 0, policy_version 71950 (0.0007) -[2023-10-15 05:10:34,459][88298] Updated weights for policy 0, policy_version 71960 (0.0007) -[2023-10-15 05:10:34,941][88300] Updated weights for policy 1, policy_version 72392 (0.0007) -[2023-10-15 05:10:35,304][88300] Updated weights for policy 1, policy_version 72402 (0.0010) -[2023-10-15 05:10:35,662][88300] Updated weights for policy 1, policy_version 72412 (0.0008) -[2023-10-15 05:10:38,331][88298] Updated weights for policy 0, policy_version 71970 (0.0007) -[2023-10-15 05:10:38,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 147849216. Throughput: 0: 1745.5, 1: 1745.3. Samples: 36973486. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:10:38,534][87330] Avg episode reward: [(0, '22.710'), (1, '22.800')] -[2023-10-15 05:10:38,693][88298] Updated weights for policy 0, policy_version 71980 (0.0008) -[2023-10-15 05:10:39,067][88298] Updated weights for policy 0, policy_version 71990 (0.0007) -[2023-10-15 05:10:39,440][88298] Updated weights for policy 0, policy_version 72000 (0.0008) -[2023-10-15 05:10:39,689][88300] Updated weights for policy 1, policy_version 72422 (0.0010) -[2023-10-15 05:10:40,054][88300] Updated weights for policy 1, policy_version 72432 (0.0011) -[2023-10-15 05:10:40,429][88300] Updated weights for policy 1, policy_version 72442 (0.0008) -[2023-10-15 05:10:43,204][88298] Updated weights for policy 0, policy_version 72010 (0.0008) -[2023-10-15 05:10:43,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 147914752. Throughput: 0: 1754.2, 1: 1767.2. Samples: 36995124. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:10:43,534][87330] Avg episode reward: [(0, '22.620'), (1, '22.860')] -[2023-10-15 05:10:43,566][88298] Updated weights for policy 0, policy_version 72020 (0.0010) -[2023-10-15 05:10:43,944][88298] Updated weights for policy 0, policy_version 72030 (0.0009) -[2023-10-15 05:10:44,340][88300] Updated weights for policy 1, policy_version 72452 (0.0009) -[2023-10-15 05:10:44,711][88300] Updated weights for policy 1, policy_version 72462 (0.0008) -[2023-10-15 05:10:45,067][88300] Updated weights for policy 1, policy_version 72472 (0.0007) -[2023-10-15 05:10:47,886][88298] Updated weights for policy 0, policy_version 72040 (0.0009) -[2023-10-15 05:10:48,250][88298] Updated weights for policy 0, policy_version 72050 (0.0007) -[2023-10-15 05:10:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 147980288. Throughput: 0: 1736.4, 1: 1744.4. Samples: 37004546. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:10:48,534][87330] Avg episode reward: [(0, '22.450'), (1, '22.930')] -[2023-10-15 05:10:48,620][88298] Updated weights for policy 0, policy_version 72060 (0.0007) -[2023-10-15 05:10:49,006][88300] Updated weights for policy 1, policy_version 72482 (0.0007) -[2023-10-15 05:10:49,361][88300] Updated weights for policy 1, policy_version 72492 (0.0009) -[2023-10-15 05:10:49,734][88300] Updated weights for policy 1, policy_version 72502 (0.0010) -[2023-10-15 05:10:50,106][88300] Updated weights for policy 1, policy_version 72512 (0.0010) -[2023-10-15 05:10:52,461][88298] Updated weights for policy 0, policy_version 72070 (0.0008) -[2023-10-15 05:10:52,843][88298] Updated weights for policy 0, policy_version 72080 (0.0009) -[2023-10-15 05:10:53,206][88298] Updated weights for policy 0, policy_version 72090 (0.0008) -[2023-10-15 05:10:53,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 148078592. Throughput: 0: 1761.3, 1: 1749.1. Samples: 37026328. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:10:53,535][87330] Avg episode reward: [(0, '22.230'), (1, '22.850')] -[2023-10-15 05:10:54,011][88300] Updated weights for policy 1, policy_version 72522 (0.0009) -[2023-10-15 05:10:54,379][88300] Updated weights for policy 1, policy_version 72532 (0.0009) -[2023-10-15 05:10:54,740][88300] Updated weights for policy 1, policy_version 72542 (0.0008) -[2023-10-15 05:10:57,162][88298] Updated weights for policy 0, policy_version 72100 (0.0008) -[2023-10-15 05:10:57,570][88298] Updated weights for policy 0, policy_version 72110 (0.0010) -[2023-10-15 05:10:57,936][88298] Updated weights for policy 0, policy_version 72120 (0.0008) -[2023-10-15 05:10:58,520][88300] Updated weights for policy 1, policy_version 72552 (0.0010) -[2023-10-15 05:10:58,534][87330] Fps is (10 sec: 16383.6, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 148144128. Throughput: 0: 1741.5, 1: 1771.3. Samples: 37047280. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:10:58,535][87330] Avg episode reward: [(0, '22.140'), (1, '22.650')] -[2023-10-15 05:10:58,544][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000072128_73859072.pth... -[2023-10-15 05:10:58,582][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000070496_72187904.pth -[2023-10-15 05:10:58,891][88300] Updated weights for policy 1, policy_version 72562 (0.0011) -[2023-10-15 05:10:59,262][88300] Updated weights for policy 1, policy_version 72572 (0.0011) -[2023-10-15 05:10:59,404][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000072576_74317824.pth... -[2023-10-15 05:10:59,433][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000070912_72613888.pth -[2023-10-15 05:11:01,940][88298] Updated weights for policy 0, policy_version 72130 (0.0010) -[2023-10-15 05:11:02,313][88298] Updated weights for policy 0, policy_version 72140 (0.0011) -[2023-10-15 05:11:02,685][88298] Updated weights for policy 0, policy_version 72150 (0.0008) -[2023-10-15 05:11:03,052][88298] Updated weights for policy 0, policy_version 72160 (0.0009) -[2023-10-15 05:11:03,129][88300] Updated weights for policy 1, policy_version 72582 (0.0007) -[2023-10-15 05:11:03,498][88300] Updated weights for policy 1, policy_version 72592 (0.0008) -[2023-10-15 05:11:03,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13995.8). Total num frames: 148209664. Throughput: 0: 1757.4, 1: 1741.0. Samples: 37057592. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:11:03,534][87330] Avg episode reward: [(0, '22.080'), (1, '22.660')] -[2023-10-15 05:11:03,861][88300] Updated weights for policy 1, policy_version 72602 (0.0007) -[2023-10-15 05:11:07,005][88298] Updated weights for policy 0, policy_version 72170 (0.0008) -[2023-10-15 05:11:07,373][88298] Updated weights for policy 0, policy_version 72180 (0.0009) -[2023-10-15 05:11:07,731][88298] Updated weights for policy 0, policy_version 72190 (0.0009) -[2023-10-15 05:11:07,760][88300] Updated weights for policy 1, policy_version 72612 (0.0008) -[2023-10-15 05:11:08,121][88300] Updated weights for policy 1, policy_version 72622 (0.0008) -[2023-10-15 05:11:08,496][88300] Updated weights for policy 1, policy_version 72632 (0.0010) -[2023-10-15 05:11:08,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 148275200. Throughput: 0: 1745.5, 1: 1771.0. Samples: 37078734. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:11:08,534][87330] Avg episode reward: [(0, '22.300'), (1, '22.550')] -[2023-10-15 05:11:11,410][88298] Updated weights for policy 0, policy_version 72200 (0.0011) -[2023-10-15 05:11:11,785][88298] Updated weights for policy 0, policy_version 72210 (0.0008) -[2023-10-15 05:11:12,156][88298] Updated weights for policy 0, policy_version 72220 (0.0007) -[2023-10-15 05:11:12,399][88300] Updated weights for policy 1, policy_version 72642 (0.0009) -[2023-10-15 05:11:12,768][88300] Updated weights for policy 1, policy_version 72652 (0.0008) -[2023-10-15 05:11:13,139][88300] Updated weights for policy 1, policy_version 72662 (0.0007) -[2023-10-15 05:11:13,500][88300] Updated weights for policy 1, policy_version 72672 (0.0009) -[2023-10-15 05:11:13,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 148373504. Throughput: 0: 1722.0, 1: 1748.2. Samples: 37098400. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:11:13,535][87330] Avg episode reward: [(0, '22.270'), (1, '22.490')] -[2023-10-15 05:11:15,997][88298] Updated weights for policy 0, policy_version 72230 (0.0009) -[2023-10-15 05:11:16,363][88298] Updated weights for policy 0, policy_version 72240 (0.0010) -[2023-10-15 05:11:16,739][88298] Updated weights for policy 0, policy_version 72250 (0.0010) -[2023-10-15 05:11:17,304][88300] Updated weights for policy 1, policy_version 72682 (0.0007) -[2023-10-15 05:11:17,670][88300] Updated weights for policy 1, policy_version 72692 (0.0008) -[2023-10-15 05:11:18,031][88300] Updated weights for policy 1, policy_version 72702 (0.0009) -[2023-10-15 05:11:18,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 148439040. Throughput: 0: 1757.0, 1: 1759.2. Samples: 37110208. Policy #0 lag: (min: 6.0, avg: 7.0, max: 27.0) -[2023-10-15 05:11:18,534][87330] Avg episode reward: [(0, '22.340'), (1, '22.460')] -[2023-10-15 05:11:20,765][88298] Updated weights for policy 0, policy_version 72260 (0.0010) -[2023-10-15 05:11:21,131][88298] Updated weights for policy 0, policy_version 72270 (0.0009) -[2023-10-15 05:11:21,505][88298] Updated weights for policy 0, policy_version 72280 (0.0010) -[2023-10-15 05:11:21,848][88300] Updated weights for policy 1, policy_version 72712 (0.0009) -[2023-10-15 05:11:22,213][88300] Updated weights for policy 1, policy_version 72722 (0.0009) -[2023-10-15 05:11:22,585][88300] Updated weights for policy 1, policy_version 72732 (0.0010) -[2023-10-15 05:11:23,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 148504576. Throughput: 0: 1728.8, 1: 1747.5. Samples: 37129918. Policy #0 lag: (min: 6.0, avg: 7.0, max: 27.0) -[2023-10-15 05:11:23,534][87330] Avg episode reward: [(0, '22.720'), (1, '22.580')] -[2023-10-15 05:11:25,403][88298] Updated weights for policy 0, policy_version 72290 (0.0009) -[2023-10-15 05:11:25,780][88298] Updated weights for policy 0, policy_version 72300 (0.0010) -[2023-10-15 05:11:26,151][88298] Updated weights for policy 0, policy_version 72310 (0.0007) -[2023-10-15 05:11:26,454][88300] Updated weights for policy 1, policy_version 72742 (0.0008) -[2023-10-15 05:11:26,524][88298] Updated weights for policy 0, policy_version 72320 (0.0007) -[2023-10-15 05:11:26,820][88300] Updated weights for policy 1, policy_version 72752 (0.0009) -[2023-10-15 05:11:27,199][88300] Updated weights for policy 1, policy_version 72762 (0.0008) -[2023-10-15 05:11:28,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 148570112. Throughput: 0: 1730.6, 1: 1737.4. Samples: 37151182. Policy #0 lag: (min: 6.0, avg: 7.0, max: 27.0) -[2023-10-15 05:11:28,534][87330] Avg episode reward: [(0, '22.780'), (1, '22.810')] -[2023-10-15 05:11:30,290][88298] Updated weights for policy 0, policy_version 72330 (0.0008) -[2023-10-15 05:11:30,664][88298] Updated weights for policy 0, policy_version 72340 (0.0007) -[2023-10-15 05:11:31,028][88298] Updated weights for policy 0, policy_version 72350 (0.0007) -[2023-10-15 05:11:31,065][88300] Updated weights for policy 1, policy_version 72772 (0.0010) -[2023-10-15 05:11:31,434][88300] Updated weights for policy 1, policy_version 72782 (0.0010) -[2023-10-15 05:11:31,800][88300] Updated weights for policy 1, policy_version 72792 (0.0011) -[2023-10-15 05:11:33,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 148635648. Throughput: 0: 1743.4, 1: 1764.8. Samples: 37162418. Policy #0 lag: (min: 6.0, avg: 7.0, max: 27.0) -[2023-10-15 05:11:33,535][87330] Avg episode reward: [(0, '22.830'), (1, '22.760')] -[2023-10-15 05:11:35,065][88298] Updated weights for policy 0, policy_version 72360 (0.0011) -[2023-10-15 05:11:35,431][88298] Updated weights for policy 0, policy_version 72370 (0.0009) -[2023-10-15 05:11:35,783][88300] Updated weights for policy 1, policy_version 72802 (0.0007) -[2023-10-15 05:11:35,802][88298] Updated weights for policy 0, policy_version 72380 (0.0009) -[2023-10-15 05:11:36,155][88300] Updated weights for policy 1, policy_version 72812 (0.0008) -[2023-10-15 05:11:36,515][88300] Updated weights for policy 1, policy_version 72822 (0.0007) -[2023-10-15 05:11:36,887][88300] Updated weights for policy 1, policy_version 72832 (0.0010) -[2023-10-15 05:11:38,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 148701184. Throughput: 0: 1723.6, 1: 1745.3. Samples: 37182426. Policy #0 lag: (min: 6.0, avg: 7.0, max: 27.0) -[2023-10-15 05:11:38,534][87330] Avg episode reward: [(0, '22.830'), (1, '22.950')] -[2023-10-15 05:11:39,651][88298] Updated weights for policy 0, policy_version 72390 (0.0008) -[2023-10-15 05:11:40,022][88298] Updated weights for policy 0, policy_version 72400 (0.0008) -[2023-10-15 05:11:40,384][88298] Updated weights for policy 0, policy_version 72410 (0.0008) -[2023-10-15 05:11:40,532][88300] Updated weights for policy 1, policy_version 72842 (0.0008) -[2023-10-15 05:11:40,899][88300] Updated weights for policy 1, policy_version 72852 (0.0009) -[2023-10-15 05:11:41,264][88300] Updated weights for policy 1, policy_version 72862 (0.0010) -[2023-10-15 05:11:43,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 148766720. Throughput: 0: 1749.9, 1: 1741.5. Samples: 37204392. Policy #0 lag: (min: 6.0, avg: 7.0, max: 27.0) -[2023-10-15 05:11:43,534][87330] Avg episode reward: [(0, '22.720'), (1, '23.030')] -[2023-10-15 05:11:44,259][88298] Updated weights for policy 0, policy_version 72420 (0.0008) -[2023-10-15 05:11:44,647][88298] Updated weights for policy 0, policy_version 72430 (0.0009) -[2023-10-15 05:11:45,023][88298] Updated weights for policy 0, policy_version 72440 (0.0007) -[2023-10-15 05:11:45,030][88300] Updated weights for policy 1, policy_version 72872 (0.0007) -[2023-10-15 05:11:45,398][88300] Updated weights for policy 1, policy_version 72882 (0.0007) -[2023-10-15 05:11:45,766][88300] Updated weights for policy 1, policy_version 72892 (0.0010) -[2023-10-15 05:11:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 148832256. Throughput: 0: 1728.0, 1: 1743.1. Samples: 37213788. Policy #0 lag: (min: 6.0, avg: 7.0, max: 27.0) -[2023-10-15 05:11:48,534][87330] Avg episode reward: [(0, '22.750'), (1, '22.980')] -[2023-10-15 05:11:48,899][88298] Updated weights for policy 0, policy_version 72450 (0.0007) -[2023-10-15 05:11:49,271][88298] Updated weights for policy 0, policy_version 72460 (0.0008) -[2023-10-15 05:11:49,643][88298] Updated weights for policy 0, policy_version 72470 (0.0008) -[2023-10-15 05:11:49,677][88300] Updated weights for policy 1, policy_version 72902 (0.0009) -[2023-10-15 05:11:50,008][88298] Updated weights for policy 0, policy_version 72480 (0.0008) -[2023-10-15 05:11:50,054][88300] Updated weights for policy 1, policy_version 72912 (0.0008) -[2023-10-15 05:11:50,430][88300] Updated weights for policy 1, policy_version 72922 (0.0009) -[2023-10-15 05:11:53,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 148897792. Throughput: 0: 1735.9, 1: 1741.3. Samples: 37235208. Policy #0 lag: (min: 6.0, avg: 7.0, max: 27.0) -[2023-10-15 05:11:53,535][87330] Avg episode reward: [(0, '22.770'), (1, '22.960')] -[2023-10-15 05:11:53,764][88298] Updated weights for policy 0, policy_version 72490 (0.0007) -[2023-10-15 05:11:54,133][88298] Updated weights for policy 0, policy_version 72500 (0.0011) -[2023-10-15 05:11:54,407][88300] Updated weights for policy 1, policy_version 72932 (0.0010) -[2023-10-15 05:11:54,510][88298] Updated weights for policy 0, policy_version 72510 (0.0007) -[2023-10-15 05:11:54,775][88300] Updated weights for policy 1, policy_version 72942 (0.0008) -[2023-10-15 05:11:55,145][88300] Updated weights for policy 1, policy_version 72952 (0.0009) -[2023-10-15 05:11:58,476][88298] Updated weights for policy 0, policy_version 72520 (0.0007) -[2023-10-15 05:11:58,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 148963328. Throughput: 0: 1759.7, 1: 1760.8. Samples: 37256822. Policy #0 lag: (min: 6.0, avg: 7.0, max: 27.0) -[2023-10-15 05:11:58,535][87330] Avg episode reward: [(0, '22.770'), (1, '22.940')] -[2023-10-15 05:11:58,847][88298] Updated weights for policy 0, policy_version 72530 (0.0008) -[2023-10-15 05:11:58,983][88300] Updated weights for policy 1, policy_version 72962 (0.0010) -[2023-10-15 05:11:59,226][88298] Updated weights for policy 0, policy_version 72540 (0.0007) -[2023-10-15 05:11:59,349][88300] Updated weights for policy 1, policy_version 72972 (0.0007) -[2023-10-15 05:11:59,721][88300] Updated weights for policy 1, policy_version 72982 (0.0009) -[2023-10-15 05:12:00,085][88300] Updated weights for policy 1, policy_version 72992 (0.0008) -[2023-10-15 05:12:03,011][88298] Updated weights for policy 0, policy_version 72550 (0.0007) -[2023-10-15 05:12:03,378][88298] Updated weights for policy 0, policy_version 72560 (0.0007) -[2023-10-15 05:12:03,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 149028864. Throughput: 0: 1732.9, 1: 1740.4. Samples: 37266506. Policy #0 lag: (min: 6.0, avg: 7.0, max: 27.0) -[2023-10-15 05:12:03,534][87330] Avg episode reward: [(0, '22.860'), (1, '22.940')] -[2023-10-15 05:12:03,750][88298] Updated weights for policy 0, policy_version 72570 (0.0007) -[2023-10-15 05:12:03,896][88300] Updated weights for policy 1, policy_version 73002 (0.0007) -[2023-10-15 05:12:04,264][88300] Updated weights for policy 1, policy_version 73012 (0.0009) -[2023-10-15 05:12:04,633][88300] Updated weights for policy 1, policy_version 73022 (0.0008) -[2023-10-15 05:12:07,624][88298] Updated weights for policy 0, policy_version 72580 (0.0009) -[2023-10-15 05:12:08,003][88298] Updated weights for policy 0, policy_version 72590 (0.0009) -[2023-10-15 05:12:08,373][88298] Updated weights for policy 0, policy_version 72600 (0.0010) -[2023-10-15 05:12:08,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 149094400. Throughput: 0: 1766.9, 1: 1751.0. Samples: 37288222. Policy #0 lag: (min: 31.0, avg: 32.3, max: 55.0) -[2023-10-15 05:12:08,534][87330] Avg episode reward: [(0, '22.870'), (1, '23.010')] -[2023-10-15 05:12:08,617][88300] Updated weights for policy 1, policy_version 73032 (0.0009) -[2023-10-15 05:12:08,980][88300] Updated weights for policy 1, policy_version 73042 (0.0009) -[2023-10-15 05:12:09,351][88300] Updated weights for policy 1, policy_version 73052 (0.0007) -[2023-10-15 05:12:12,221][88298] Updated weights for policy 0, policy_version 72610 (0.0009) -[2023-10-15 05:12:12,595][88298] Updated weights for policy 0, policy_version 72620 (0.0008) -[2023-10-15 05:12:12,961][88298] Updated weights for policy 0, policy_version 72630 (0.0008) -[2023-10-15 05:12:13,328][88298] Updated weights for policy 0, policy_version 72640 (0.0007) -[2023-10-15 05:12:13,494][88300] Updated weights for policy 1, policy_version 73062 (0.0009) -[2023-10-15 05:12:13,534][87330] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 149192704. Throughput: 0: 1743.7, 1: 1766.6. Samples: 37309146. Policy #0 lag: (min: 31.0, avg: 32.3, max: 55.0) -[2023-10-15 05:12:13,535][87330] Avg episode reward: [(0, '22.990'), (1, '22.650')] -[2023-10-15 05:12:13,861][88300] Updated weights for policy 1, policy_version 73072 (0.0008) -[2023-10-15 05:12:14,234][88300] Updated weights for policy 1, policy_version 73082 (0.0008) -[2023-10-15 05:12:17,260][88298] Updated weights for policy 0, policy_version 72650 (0.0008) -[2023-10-15 05:12:17,625][88298] Updated weights for policy 0, policy_version 72660 (0.0007) -[2023-10-15 05:12:17,999][88298] Updated weights for policy 0, policy_version 72670 (0.0008) -[2023-10-15 05:12:18,150][88300] Updated weights for policy 1, policy_version 73092 (0.0009) -[2023-10-15 05:12:18,516][88300] Updated weights for policy 1, policy_version 73102 (0.0008) -[2023-10-15 05:12:18,534][87330] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13995.8). Total num frames: 149258240. Throughput: 0: 1749.8, 1: 1735.3. Samples: 37319246. Policy #0 lag: (min: 31.0, avg: 32.3, max: 55.0) -[2023-10-15 05:12:18,534][87330] Avg episode reward: [(0, '22.990'), (1, '22.590')] -[2023-10-15 05:12:18,887][88300] Updated weights for policy 1, policy_version 73112 (0.0007) -[2023-10-15 05:12:22,120][88298] Updated weights for policy 0, policy_version 72680 (0.0009) -[2023-10-15 05:12:22,501][88298] Updated weights for policy 0, policy_version 72690 (0.0009) -[2023-10-15 05:12:22,806][88300] Updated weights for policy 1, policy_version 73122 (0.0007) -[2023-10-15 05:12:22,868][88298] Updated weights for policy 0, policy_version 72700 (0.0008) -[2023-10-15 05:12:23,179][88300] Updated weights for policy 1, policy_version 73132 (0.0008) -[2023-10-15 05:12:23,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 149323776. Throughput: 0: 1763.1, 1: 1758.7. Samples: 37340904. Policy #0 lag: (min: 31.0, avg: 32.3, max: 55.0) -[2023-10-15 05:12:23,535][87330] Avg episode reward: [(0, '22.950'), (1, '22.510')] -[2023-10-15 05:12:23,539][88300] Updated weights for policy 1, policy_version 73142 (0.0007) -[2023-10-15 05:12:23,903][88300] Updated weights for policy 1, policy_version 73152 (0.0009) -[2023-10-15 05:12:26,693][88298] Updated weights for policy 0, policy_version 72710 (0.0009) -[2023-10-15 05:12:27,069][88298] Updated weights for policy 0, policy_version 72720 (0.0011) -[2023-10-15 05:12:27,428][88298] Updated weights for policy 0, policy_version 72730 (0.0009) -[2023-10-15 05:12:27,570][88300] Updated weights for policy 1, policy_version 73162 (0.0009) -[2023-10-15 05:12:27,939][88300] Updated weights for policy 1, policy_version 73172 (0.0011) -[2023-10-15 05:12:28,300][88300] Updated weights for policy 1, policy_version 73182 (0.0010) -[2023-10-15 05:12:28,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 149422080. Throughput: 0: 1727.0, 1: 1736.9. Samples: 37360270. Policy #0 lag: (min: 31.0, avg: 32.3, max: 55.0) -[2023-10-15 05:12:28,534][87330] Avg episode reward: [(0, '22.970'), (1, '22.450')] -[2023-10-15 05:12:31,184][88298] Updated weights for policy 0, policy_version 72740 (0.0010) -[2023-10-15 05:12:31,563][88298] Updated weights for policy 0, policy_version 72750 (0.0010) -[2023-10-15 05:12:31,932][88298] Updated weights for policy 0, policy_version 72760 (0.0008) -[2023-10-15 05:12:32,336][88300] Updated weights for policy 1, policy_version 73192 (0.0008) -[2023-10-15 05:12:32,703][88300] Updated weights for policy 1, policy_version 73202 (0.0007) -[2023-10-15 05:12:33,066][88300] Updated weights for policy 1, policy_version 73212 (0.0008) -[2023-10-15 05:12:33,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 149487616. Throughput: 0: 1766.7, 1: 1756.1. Samples: 37372312. Policy #0 lag: (min: 31.0, avg: 32.3, max: 55.0) -[2023-10-15 05:12:33,535][87330] Avg episode reward: [(0, '22.960'), (1, '22.230')] -[2023-10-15 05:12:35,797][88298] Updated weights for policy 0, policy_version 72770 (0.0008) -[2023-10-15 05:12:36,160][88298] Updated weights for policy 0, policy_version 72780 (0.0008) -[2023-10-15 05:12:36,541][88298] Updated weights for policy 0, policy_version 72790 (0.0008) -[2023-10-15 05:12:36,901][88298] Updated weights for policy 0, policy_version 72800 (0.0010) -[2023-10-15 05:12:36,988][88300] Updated weights for policy 1, policy_version 73222 (0.0010) -[2023-10-15 05:12:37,360][88300] Updated weights for policy 1, policy_version 73232 (0.0010) -[2023-10-15 05:12:37,733][88300] Updated weights for policy 1, policy_version 73242 (0.0009) -[2023-10-15 05:12:38,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 149553152. Throughput: 0: 1739.5, 1: 1747.6. Samples: 37392124. Policy #0 lag: (min: 31.0, avg: 32.3, max: 55.0) -[2023-10-15 05:12:38,534][87330] Avg episode reward: [(0, '22.940'), (1, '22.190')] -[2023-10-15 05:12:40,970][88298] Updated weights for policy 0, policy_version 72810 (0.0007) -[2023-10-15 05:12:41,340][88298] Updated weights for policy 0, policy_version 72820 (0.0009) -[2023-10-15 05:12:41,530][88300] Updated weights for policy 1, policy_version 73252 (0.0007) -[2023-10-15 05:12:41,714][88298] Updated weights for policy 0, policy_version 72830 (0.0007) -[2023-10-15 05:12:41,906][88300] Updated weights for policy 1, policy_version 73262 (0.0009) -[2023-10-15 05:12:42,284][88300] Updated weights for policy 1, policy_version 73272 (0.0007) -[2023-10-15 05:12:43,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 149618688. Throughput: 0: 1730.3, 1: 1731.2. Samples: 37412590. Policy #0 lag: (min: 31.0, avg: 32.3, max: 55.0) -[2023-10-15 05:12:43,534][87330] Avg episode reward: [(0, '22.910'), (1, '22.330')] -[2023-10-15 05:12:45,650][88298] Updated weights for policy 0, policy_version 72840 (0.0008) -[2023-10-15 05:12:46,017][88298] Updated weights for policy 0, policy_version 72850 (0.0007) -[2023-10-15 05:12:46,075][88300] Updated weights for policy 1, policy_version 73282 (0.0008) -[2023-10-15 05:12:46,385][88298] Updated weights for policy 0, policy_version 72860 (0.0009) -[2023-10-15 05:12:46,443][88300] Updated weights for policy 1, policy_version 73292 (0.0009) -[2023-10-15 05:12:46,816][88300] Updated weights for policy 1, policy_version 73302 (0.0010) -[2023-10-15 05:12:47,171][88300] Updated weights for policy 1, policy_version 73312 (0.0009) -[2023-10-15 05:12:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 149684224. Throughput: 0: 1742.5, 1: 1758.0. Samples: 37424028. Policy #0 lag: (min: 31.0, avg: 32.3, max: 55.0) -[2023-10-15 05:12:48,534][87330] Avg episode reward: [(0, '22.890'), (1, '22.500')] -[2023-10-15 05:12:50,361][88298] Updated weights for policy 0, policy_version 72870 (0.0007) -[2023-10-15 05:12:50,731][88298] Updated weights for policy 0, policy_version 72880 (0.0008) -[2023-10-15 05:12:51,110][88298] Updated weights for policy 0, policy_version 72890 (0.0008) -[2023-10-15 05:12:51,156][88300] Updated weights for policy 1, policy_version 73322 (0.0008) -[2023-10-15 05:12:51,524][88300] Updated weights for policy 1, policy_version 73332 (0.0009) -[2023-10-15 05:12:51,890][88300] Updated weights for policy 1, policy_version 73342 (0.0008) -[2023-10-15 05:12:53,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 149749760. Throughput: 0: 1714.3, 1: 1731.5. Samples: 37443280. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:12:53,534][87330] Avg episode reward: [(0, '22.910'), (1, '22.550')] -[2023-10-15 05:12:54,966][88298] Updated weights for policy 0, policy_version 72900 (0.0009) -[2023-10-15 05:12:55,328][88298] Updated weights for policy 0, policy_version 72910 (0.0008) -[2023-10-15 05:12:55,692][88298] Updated weights for policy 0, policy_version 72920 (0.0010) -[2023-10-15 05:12:55,756][88300] Updated weights for policy 1, policy_version 73352 (0.0008) -[2023-10-15 05:12:56,128][88300] Updated weights for policy 1, policy_version 73362 (0.0007) -[2023-10-15 05:12:56,494][88300] Updated weights for policy 1, policy_version 73372 (0.0008) -[2023-10-15 05:12:58,534][87330] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 149815296. Throughput: 0: 1732.6, 1: 1725.5. Samples: 37464762. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:12:58,535][87330] Avg episode reward: [(0, '22.880'), (1, '22.660')] -[2023-10-15 05:12:58,544][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000072928_74678272.pth... -[2023-10-15 05:12:58,545][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000073376_75137024.pth... -[2023-10-15 05:12:58,578][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000071744_73465856.pth -[2023-10-15 05:12:58,582][88033] Saving a milestone ./train_atari/atari_seaquest_APPO/checkpoint_p1/milestones/checkpoint_000073376_75137024.pth -[2023-10-15 05:12:58,585][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000071296_73007104.pth -[2023-10-15 05:12:58,590][87905] Saving a milestone ./train_atari/atari_seaquest_APPO/checkpoint_p0/milestones/checkpoint_000072928_74678272.pth -[2023-10-15 05:12:59,519][88298] Updated weights for policy 0, policy_version 72930 (0.0009) -[2023-10-15 05:12:59,886][88298] Updated weights for policy 0, policy_version 72940 (0.0011) -[2023-10-15 05:13:00,251][88298] Updated weights for policy 0, policy_version 72950 (0.0008) -[2023-10-15 05:13:00,529][88300] Updated weights for policy 1, policy_version 73382 (0.0008) -[2023-10-15 05:13:00,627][88298] Updated weights for policy 0, policy_version 72960 (0.0008) -[2023-10-15 05:13:00,892][88300] Updated weights for policy 1, policy_version 73392 (0.0008) -[2023-10-15 05:13:01,256][88300] Updated weights for policy 1, policy_version 73402 (0.0009) -[2023-10-15 05:13:03,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 149880832. Throughput: 0: 1717.6, 1: 1731.7. Samples: 37474468. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:13:03,535][87330] Avg episode reward: [(0, '22.850'), (1, '22.720')] -[2023-10-15 05:13:04,526][88298] Updated weights for policy 0, policy_version 72970 (0.0008) -[2023-10-15 05:13:04,902][88298] Updated weights for policy 0, policy_version 72980 (0.0009) -[2023-10-15 05:13:05,178][88300] Updated weights for policy 1, policy_version 73412 (0.0008) -[2023-10-15 05:13:05,271][88298] Updated weights for policy 0, policy_version 72990 (0.0007) -[2023-10-15 05:13:05,542][88300] Updated weights for policy 1, policy_version 73422 (0.0009) -[2023-10-15 05:13:05,920][88300] Updated weights for policy 1, policy_version 73432 (0.0008) -[2023-10-15 05:13:08,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 149946368. Throughput: 0: 1717.7, 1: 1719.8. Samples: 37495594. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:13:08,535][87330] Avg episode reward: [(0, '22.860'), (1, '22.790')] -[2023-10-15 05:13:09,207][88298] Updated weights for policy 0, policy_version 73000 (0.0008) -[2023-10-15 05:13:09,574][88298] Updated weights for policy 0, policy_version 73010 (0.0009) -[2023-10-15 05:13:09,853][88300] Updated weights for policy 1, policy_version 73442 (0.0008) -[2023-10-15 05:13:09,938][88298] Updated weights for policy 0, policy_version 73020 (0.0007) -[2023-10-15 05:13:10,216][88300] Updated weights for policy 1, policy_version 73452 (0.0007) -[2023-10-15 05:13:10,587][88300] Updated weights for policy 1, policy_version 73462 (0.0007) -[2023-10-15 05:13:10,948][88300] Updated weights for policy 1, policy_version 73472 (0.0007) -[2023-10-15 05:13:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 150011904. Throughput: 0: 1744.5, 1: 1742.0. Samples: 37517162. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:13:13,535][87330] Avg episode reward: [(0, '22.800'), (1, '22.840')] -[2023-10-15 05:13:13,925][88298] Updated weights for policy 0, policy_version 73030 (0.0008) -[2023-10-15 05:13:14,295][88298] Updated weights for policy 0, policy_version 73040 (0.0008) -[2023-10-15 05:13:14,662][88298] Updated weights for policy 0, policy_version 73050 (0.0007) -[2023-10-15 05:13:14,823][88300] Updated weights for policy 1, policy_version 73482 (0.0008) -[2023-10-15 05:13:15,197][88300] Updated weights for policy 1, policy_version 73492 (0.0007) -[2023-10-15 05:13:15,569][88300] Updated weights for policy 1, policy_version 73502 (0.0007) -[2023-10-15 05:13:18,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 150077440. Throughput: 0: 1707.1, 1: 1719.1. Samples: 37526488. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:13:18,534][87330] Avg episode reward: [(0, '22.600'), (1, '22.870')] -[2023-10-15 05:13:18,725][88298] Updated weights for policy 0, policy_version 73060 (0.0008) -[2023-10-15 05:13:19,111][88298] Updated weights for policy 0, policy_version 73070 (0.0007) -[2023-10-15 05:13:19,355][88300] Updated weights for policy 1, policy_version 73512 (0.0007) -[2023-10-15 05:13:19,493][88298] Updated weights for policy 0, policy_version 73080 (0.0009) -[2023-10-15 05:13:19,728][88300] Updated weights for policy 1, policy_version 73522 (0.0008) -[2023-10-15 05:13:20,103][88300] Updated weights for policy 1, policy_version 73532 (0.0010) -[2023-10-15 05:13:23,340][88298] Updated weights for policy 0, policy_version 73090 (0.0008) -[2023-10-15 05:13:23,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 150142976. Throughput: 0: 1729.8, 1: 1733.4. Samples: 37547968. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:13:23,535][87330] Avg episode reward: [(0, '22.580'), (1, '22.880')] -[2023-10-15 05:13:23,707][88298] Updated weights for policy 0, policy_version 73100 (0.0008) -[2023-10-15 05:13:23,959][88300] Updated weights for policy 1, policy_version 73542 (0.0009) -[2023-10-15 05:13:24,077][88298] Updated weights for policy 0, policy_version 73110 (0.0008) -[2023-10-15 05:13:24,335][88300] Updated weights for policy 1, policy_version 73552 (0.0007) -[2023-10-15 05:13:24,441][88298] Updated weights for policy 0, policy_version 73120 (0.0008) -[2023-10-15 05:13:24,699][88300] Updated weights for policy 1, policy_version 73562 (0.0008) -[2023-10-15 05:13:28,343][88298] Updated weights for policy 0, policy_version 73130 (0.0009) -[2023-10-15 05:13:28,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13884.8). Total num frames: 150208512. Throughput: 0: 1733.8, 1: 1749.9. Samples: 37569354. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:13:28,534][87330] Avg episode reward: [(0, '22.450'), (1, '22.940')] -[2023-10-15 05:13:28,629][88300] Updated weights for policy 1, policy_version 73572 (0.0010) -[2023-10-15 05:13:28,713][88298] Updated weights for policy 0, policy_version 73140 (0.0007) -[2023-10-15 05:13:29,000][88300] Updated weights for policy 1, policy_version 73582 (0.0008) -[2023-10-15 05:13:29,088][88298] Updated weights for policy 0, policy_version 73150 (0.0007) -[2023-10-15 05:13:29,360][88300] Updated weights for policy 1, policy_version 73592 (0.0009) -[2023-10-15 05:13:33,163][88298] Updated weights for policy 0, policy_version 73160 (0.0009) -[2023-10-15 05:13:33,319][88300] Updated weights for policy 1, policy_version 73602 (0.0011) -[2023-10-15 05:13:33,527][88298] Updated weights for policy 0, policy_version 73170 (0.0009) -[2023-10-15 05:13:33,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13884.7). Total num frames: 150274048. Throughput: 0: 1716.2, 1: 1722.9. Samples: 37578786. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:13:33,534][87330] Avg episode reward: [(0, '22.470'), (1, '22.980')] -[2023-10-15 05:13:33,687][88300] Updated weights for policy 1, policy_version 73612 (0.0007) -[2023-10-15 05:13:33,900][88298] Updated weights for policy 0, policy_version 73180 (0.0007) -[2023-10-15 05:13:34,055][88300] Updated weights for policy 1, policy_version 73622 (0.0009) -[2023-10-15 05:13:34,429][88300] Updated weights for policy 1, policy_version 73632 (0.0008) -[2023-10-15 05:13:37,818][88298] Updated weights for policy 0, policy_version 73190 (0.0010) -[2023-10-15 05:13:38,184][88298] Updated weights for policy 0, policy_version 73200 (0.0007) -[2023-10-15 05:13:38,396][88300] Updated weights for policy 1, policy_version 73642 (0.0007) -[2023-10-15 05:13:38,534][87330] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 13884.7). Total num frames: 150339584. Throughput: 0: 1736.5, 1: 1753.7. Samples: 37600342. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:13:38,535][87330] Avg episode reward: [(0, '22.470'), (1, '23.130')] -[2023-10-15 05:13:38,561][88298] Updated weights for policy 0, policy_version 73210 (0.0008) -[2023-10-15 05:13:38,752][88300] Updated weights for policy 1, policy_version 73652 (0.0009) -[2023-10-15 05:13:39,112][88300] Updated weights for policy 1, policy_version 73662 (0.0011) -[2023-10-15 05:13:39,185][88033] Saving new best policy, reward=23.130! -[2023-10-15 05:13:42,370][88298] Updated weights for policy 0, policy_version 73220 (0.0008) -[2023-10-15 05:13:42,743][88298] Updated weights for policy 0, policy_version 73230 (0.0010) -[2023-10-15 05:13:43,028][88300] Updated weights for policy 1, policy_version 73672 (0.0008) -[2023-10-15 05:13:43,114][88298] Updated weights for policy 0, policy_version 73240 (0.0007) -[2023-10-15 05:13:43,405][88300] Updated weights for policy 1, policy_version 73682 (0.0008) -[2023-10-15 05:13:43,534][87330] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 150437888. Throughput: 0: 1719.9, 1: 1745.5. Samples: 37620704. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) -[2023-10-15 05:13:43,534][87330] Avg episode reward: [(0, '22.480'), (1, '23.050')] -[2023-10-15 05:13:43,764][88300] Updated weights for policy 1, policy_version 73692 (0.0007) -[2023-10-15 05:13:47,002][88298] Updated weights for policy 0, policy_version 73250 (0.0007) -[2023-10-15 05:13:47,369][88298] Updated weights for policy 0, policy_version 73260 (0.0007) -[2023-10-15 05:13:47,613][88300] Updated weights for policy 1, policy_version 73702 (0.0008) -[2023-10-15 05:13:47,731][88298] Updated weights for policy 0, policy_version 73270 (0.0010) -[2023-10-15 05:13:47,977][88300] Updated weights for policy 1, policy_version 73712 (0.0008) -[2023-10-15 05:13:48,095][88298] Updated weights for policy 0, policy_version 73280 (0.0008) -[2023-10-15 05:13:48,351][88300] Updated weights for policy 1, policy_version 73722 (0.0009) -[2023-10-15 05:13:48,534][87330] Fps is (10 sec: 16384.4, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 150503424. Throughput: 0: 1732.5, 1: 1756.0. Samples: 37631452. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) -[2023-10-15 05:13:48,534][87330] Avg episode reward: [(0, '22.560'), (1, '23.020')] -[2023-10-15 05:13:52,184][88300] Updated weights for policy 1, policy_version 73732 (0.0011) -[2023-10-15 05:13:52,186][88298] Updated weights for policy 0, policy_version 73290 (0.0008) -[2023-10-15 05:13:52,545][88300] Updated weights for policy 1, policy_version 73742 (0.0009) -[2023-10-15 05:13:52,556][88298] Updated weights for policy 0, policy_version 73300 (0.0008) -[2023-10-15 05:13:52,918][88300] Updated weights for policy 1, policy_version 73752 (0.0008) -[2023-10-15 05:13:52,931][88298] Updated weights for policy 0, policy_version 73310 (0.0009) -[2023-10-15 05:13:53,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 150601728. Throughput: 0: 1730.0, 1: 1761.3. Samples: 37652700. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) -[2023-10-15 05:13:53,534][87330] Avg episode reward: [(0, '22.770'), (1, '23.070')] -[2023-10-15 05:13:56,683][88300] Updated weights for policy 1, policy_version 73762 (0.0008) -[2023-10-15 05:13:56,774][88298] Updated weights for policy 0, policy_version 73320 (0.0007) -[2023-10-15 05:13:57,043][88300] Updated weights for policy 1, policy_version 73772 (0.0007) -[2023-10-15 05:13:57,149][88298] Updated weights for policy 0, policy_version 73330 (0.0007) -[2023-10-15 05:13:57,411][88300] Updated weights for policy 1, policy_version 73782 (0.0009) -[2023-10-15 05:13:57,519][88298] Updated weights for policy 0, policy_version 73340 (0.0007) -[2023-10-15 05:13:57,776][88300] Updated weights for policy 1, policy_version 73792 (0.0007) -[2023-10-15 05:13:58,534][87330] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 150667264. Throughput: 0: 1706.1, 1: 1729.6. Samples: 37671770. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) -[2023-10-15 05:13:58,535][87330] Avg episode reward: [(0, '22.820'), (1, '23.070')] -[2023-10-15 05:14:01,477][88298] Updated weights for policy 0, policy_version 73350 (0.0008) -[2023-10-15 05:14:01,665][88300] Updated weights for policy 1, policy_version 73802 (0.0008) -[2023-10-15 05:14:01,845][88298] Updated weights for policy 0, policy_version 73360 (0.0007) -[2023-10-15 05:14:02,035][88300] Updated weights for policy 1, policy_version 73812 (0.0008) -[2023-10-15 05:14:02,221][88298] Updated weights for policy 0, policy_version 73370 (0.0008) -[2023-10-15 05:14:02,400][88300] Updated weights for policy 1, policy_version 73822 (0.0009) -[2023-10-15 05:14:03,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 150732800. Throughput: 0: 1738.0, 1: 1762.1. Samples: 37683994. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) -[2023-10-15 05:14:03,535][87330] Avg episode reward: [(0, '22.820'), (1, '23.060')] -[2023-10-15 05:14:06,216][88298] Updated weights for policy 0, policy_version 73380 (0.0009) -[2023-10-15 05:14:06,417][88300] Updated weights for policy 1, policy_version 73832 (0.0007) -[2023-10-15 05:14:06,605][88298] Updated weights for policy 0, policy_version 73390 (0.0007) -[2023-10-15 05:14:06,787][88300] Updated weights for policy 1, policy_version 73842 (0.0007) -[2023-10-15 05:14:06,972][88298] Updated weights for policy 0, policy_version 73400 (0.0008) -[2023-10-15 05:14:07,151][88300] Updated weights for policy 1, policy_version 73852 (0.0008) -[2023-10-15 05:14:08,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 150798336. Throughput: 0: 1721.3, 1: 1733.0. Samples: 37703410. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) -[2023-10-15 05:14:08,534][87330] Avg episode reward: [(0, '22.810'), (1, '23.070')] -[2023-10-15 05:14:10,941][88298] Updated weights for policy 0, policy_version 73410 (0.0007) -[2023-10-15 05:14:11,102][88300] Updated weights for policy 1, policy_version 73862 (0.0009) -[2023-10-15 05:14:11,314][88298] Updated weights for policy 0, policy_version 73420 (0.0008) -[2023-10-15 05:14:11,493][88300] Updated weights for policy 1, policy_version 73872 (0.0009) -[2023-10-15 05:14:11,677][88298] Updated weights for policy 0, policy_version 73430 (0.0008) -[2023-10-15 05:14:11,861][88300] Updated weights for policy 1, policy_version 73882 (0.0009) -[2023-10-15 05:14:12,042][88298] Updated weights for policy 0, policy_version 73440 (0.0008) -[2023-10-15 05:14:13,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 150863872. Throughput: 0: 1707.9, 1: 1724.6. Samples: 37723818. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) -[2023-10-15 05:14:13,534][87330] Avg episode reward: [(0, '22.830'), (1, '23.090')] -[2023-10-15 05:14:15,777][88300] Updated weights for policy 1, policy_version 73892 (0.0008) -[2023-10-15 05:14:15,972][88298] Updated weights for policy 0, policy_version 73450 (0.0008) -[2023-10-15 05:14:16,143][88300] Updated weights for policy 1, policy_version 73902 (0.0009) -[2023-10-15 05:14:16,346][88298] Updated weights for policy 0, policy_version 73460 (0.0008) -[2023-10-15 05:14:16,508][88300] Updated weights for policy 1, policy_version 73912 (0.0009) -[2023-10-15 05:14:16,718][88298] Updated weights for policy 0, policy_version 73470 (0.0009) -[2023-10-15 05:14:18,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 150929408. Throughput: 0: 1732.0, 1: 1741.1. Samples: 37735078. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) -[2023-10-15 05:14:18,535][87330] Avg episode reward: [(0, '22.800'), (1, '23.140')] -[2023-10-15 05:14:18,537][88033] Saving new best policy, reward=23.140! -[2023-10-15 05:14:20,463][88300] Updated weights for policy 1, policy_version 73922 (0.0007) -[2023-10-15 05:14:20,561][88298] Updated weights for policy 0, policy_version 73480 (0.0007) -[2023-10-15 05:14:20,828][88300] Updated weights for policy 1, policy_version 73932 (0.0007) -[2023-10-15 05:14:20,932][88298] Updated weights for policy 0, policy_version 73490 (0.0007) -[2023-10-15 05:14:21,189][88300] Updated weights for policy 1, policy_version 73942 (0.0008) -[2023-10-15 05:14:21,303][88298] Updated weights for policy 0, policy_version 73500 (0.0009) -[2023-10-15 05:14:21,561][88300] Updated weights for policy 1, policy_version 73952 (0.0008) -[2023-10-15 05:14:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 150994944. Throughput: 0: 1711.6, 1: 1722.2. Samples: 37754864. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) -[2023-10-15 05:14:23,534][87330] Avg episode reward: [(0, '22.720'), (1, '23.080')] -[2023-10-15 05:14:25,074][88298] Updated weights for policy 0, policy_version 73510 (0.0008) -[2023-10-15 05:14:25,434][88298] Updated weights for policy 0, policy_version 73520 (0.0008) -[2023-10-15 05:14:25,530][88300] Updated weights for policy 1, policy_version 73962 (0.0007) -[2023-10-15 05:14:25,807][88298] Updated weights for policy 0, policy_version 73530 (0.0009) -[2023-10-15 05:14:25,889][88300] Updated weights for policy 1, policy_version 73972 (0.0007) -[2023-10-15 05:14:26,262][88300] Updated weights for policy 1, policy_version 73982 (0.0010) -[2023-10-15 05:14:28,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 151060480. Throughput: 0: 1731.2, 1: 1730.0. Samples: 37776456. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-15 05:14:28,535][87330] Avg episode reward: [(0, '22.680'), (1, '23.070')] -[2023-10-15 05:14:29,768][88298] Updated weights for policy 0, policy_version 73540 (0.0007) -[2023-10-15 05:14:30,147][88298] Updated weights for policy 0, policy_version 73550 (0.0008) -[2023-10-15 05:14:30,187][88300] Updated weights for policy 1, policy_version 73992 (0.0008) -[2023-10-15 05:14:30,512][88298] Updated weights for policy 0, policy_version 73560 (0.0008) -[2023-10-15 05:14:30,553][88300] Updated weights for policy 1, policy_version 74002 (0.0007) -[2023-10-15 05:14:30,918][88300] Updated weights for policy 1, policy_version 74012 (0.0007) -[2023-10-15 05:14:33,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 151126016. Throughput: 0: 1716.8, 1: 1716.1. Samples: 37785932. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-15 05:14:33,534][87330] Avg episode reward: [(0, '22.860'), (1, '23.040')] -[2023-10-15 05:14:34,358][88298] Updated weights for policy 0, policy_version 73570 (0.0007) -[2023-10-15 05:14:34,718][88298] Updated weights for policy 0, policy_version 73580 (0.0008) -[2023-10-15 05:14:34,833][88300] Updated weights for policy 1, policy_version 74022 (0.0008) -[2023-10-15 05:14:35,094][88298] Updated weights for policy 0, policy_version 73590 (0.0008) -[2023-10-15 05:14:35,194][88300] Updated weights for policy 1, policy_version 74032 (0.0008) -[2023-10-15 05:14:35,459][88298] Updated weights for policy 0, policy_version 73600 (0.0008) -[2023-10-15 05:14:35,559][88300] Updated weights for policy 1, policy_version 74042 (0.0007) -[2023-10-15 05:14:38,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 151191552. Throughput: 0: 1716.0, 1: 1720.7. Samples: 37807350. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-15 05:14:38,534][87330] Avg episode reward: [(0, '22.860'), (1, '23.020')] -[2023-10-15 05:14:39,407][88298] Updated weights for policy 0, policy_version 73610 (0.0007) -[2023-10-15 05:14:39,409][88300] Updated weights for policy 1, policy_version 74052 (0.0007) -[2023-10-15 05:14:39,770][88298] Updated weights for policy 0, policy_version 73620 (0.0007) -[2023-10-15 05:14:39,776][88300] Updated weights for policy 1, policy_version 74062 (0.0007) -[2023-10-15 05:14:40,140][88298] Updated weights for policy 0, policy_version 73630 (0.0007) -[2023-10-15 05:14:40,141][88300] Updated weights for policy 1, policy_version 74072 (0.0007) -[2023-10-15 05:14:43,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 151257088. Throughput: 0: 1743.6, 1: 1750.8. Samples: 37829018. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-15 05:14:43,534][87330] Avg episode reward: [(0, '22.860'), (1, '23.000')] -[2023-10-15 05:14:43,967][88300] Updated weights for policy 1, policy_version 74082 (0.0009) -[2023-10-15 05:14:44,040][88298] Updated weights for policy 0, policy_version 73640 (0.0009) -[2023-10-15 05:14:44,324][88300] Updated weights for policy 1, policy_version 74092 (0.0009) -[2023-10-15 05:14:44,399][88298] Updated weights for policy 0, policy_version 73650 (0.0008) -[2023-10-15 05:14:44,687][88300] Updated weights for policy 1, policy_version 74102 (0.0008) -[2023-10-15 05:14:44,766][88298] Updated weights for policy 0, policy_version 73660 (0.0008) -[2023-10-15 05:14:45,057][88300] Updated weights for policy 1, policy_version 74112 (0.0007) -[2023-10-15 05:14:48,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 151322624. Throughput: 0: 1714.5, 1: 1718.9. Samples: 37838494. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-15 05:14:48,534][87330] Avg episode reward: [(0, '22.870'), (1, '23.020')] -[2023-10-15 05:14:48,812][88298] Updated weights for policy 0, policy_version 73670 (0.0008) -[2023-10-15 05:14:48,853][88300] Updated weights for policy 1, policy_version 74122 (0.0009) -[2023-10-15 05:14:49,179][88298] Updated weights for policy 0, policy_version 73680 (0.0007) -[2023-10-15 05:14:49,222][88300] Updated weights for policy 1, policy_version 74132 (0.0009) -[2023-10-15 05:14:49,556][88298] Updated weights for policy 0, policy_version 73690 (0.0009) -[2023-10-15 05:14:49,586][88300] Updated weights for policy 1, policy_version 74142 (0.0008) -[2023-10-15 05:14:53,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 151388160. Throughput: 0: 1732.8, 1: 1746.0. Samples: 37859956. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-15 05:14:53,535][87330] Avg episode reward: [(0, '22.970'), (1, '23.080')] -[2023-10-15 05:14:53,668][88298] Updated weights for policy 0, policy_version 73700 (0.0008) -[2023-10-15 05:14:53,761][88300] Updated weights for policy 1, policy_version 74152 (0.0009) -[2023-10-15 05:14:54,052][88298] Updated weights for policy 0, policy_version 73710 (0.0007) -[2023-10-15 05:14:54,122][88300] Updated weights for policy 1, policy_version 74162 (0.0009) -[2023-10-15 05:14:54,424][88298] Updated weights for policy 0, policy_version 73720 (0.0008) -[2023-10-15 05:14:54,493][88300] Updated weights for policy 1, policy_version 74172 (0.0007) -[2023-10-15 05:14:58,377][88298] Updated weights for policy 0, policy_version 73730 (0.0009) -[2023-10-15 05:14:58,472][88300] Updated weights for policy 1, policy_version 74182 (0.0007) -[2023-10-15 05:14:58,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 151453696. Throughput: 0: 1744.4, 1: 1756.4. Samples: 37881354. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-15 05:14:58,534][87330] Avg episode reward: [(0, '22.760'), (1, '23.040')] -[2023-10-15 05:14:58,736][88298] Updated weights for policy 0, policy_version 73740 (0.0009) -[2023-10-15 05:14:58,865][88300] Updated weights for policy 1, policy_version 74192 (0.0007) -[2023-10-15 05:14:59,115][88298] Updated weights for policy 0, policy_version 73750 (0.0008) -[2023-10-15 05:14:59,230][88300] Updated weights for policy 1, policy_version 74202 (0.0007) -[2023-10-15 05:14:59,446][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000074208_75988992.pth... -[2023-10-15 05:14:59,473][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000073760_75530240.pth... -[2023-10-15 05:14:59,473][88298] Updated weights for policy 0, policy_version 73760 (0.0008) -[2023-10-15 05:14:59,475][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000072576_74317824.pth -[2023-10-15 05:14:59,505][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000072128_73859072.pth -[2023-10-15 05:15:02,876][88300] Updated weights for policy 1, policy_version 74212 (0.0007) -[2023-10-15 05:15:03,234][88300] Updated weights for policy 1, policy_version 74222 (0.0007) -[2023-10-15 05:15:03,434][88298] Updated weights for policy 0, policy_version 73770 (0.0009) -[2023-10-15 05:15:03,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 151519232. Throughput: 0: 1719.0, 1: 1739.0. Samples: 37890688. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-15 05:15:03,534][87330] Avg episode reward: [(0, '22.770'), (1, '23.090')] -[2023-10-15 05:15:03,605][88300] Updated weights for policy 1, policy_version 74232 (0.0009) -[2023-10-15 05:15:03,801][88298] Updated weights for policy 0, policy_version 73780 (0.0007) -[2023-10-15 05:15:04,176][88298] Updated weights for policy 0, policy_version 73790 (0.0009) -[2023-10-15 05:15:07,531][88300] Updated weights for policy 1, policy_version 74242 (0.0007) -[2023-10-15 05:15:07,894][88300] Updated weights for policy 1, policy_version 74252 (0.0007) -[2023-10-15 05:15:08,038][88298] Updated weights for policy 0, policy_version 73800 (0.0007) -[2023-10-15 05:15:08,253][88300] Updated weights for policy 1, policy_version 74262 (0.0009) -[2023-10-15 05:15:08,418][88298] Updated weights for policy 0, policy_version 73810 (0.0007) -[2023-10-15 05:15:08,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 151584768. Throughput: 0: 1740.6, 1: 1760.1. Samples: 37912394. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-15 05:15:08,535][87330] Avg episode reward: [(0, '22.750'), (1, '23.070')] -[2023-10-15 05:15:08,619][88300] Updated weights for policy 1, policy_version 74272 (0.0007) -[2023-10-15 05:15:08,776][88298] Updated weights for policy 0, policy_version 73820 (0.0008) -[2023-10-15 05:15:12,580][88298] Updated weights for policy 0, policy_version 73830 (0.0007) -[2023-10-15 05:15:12,608][88300] Updated weights for policy 1, policy_version 74282 (0.0010) -[2023-10-15 05:15:12,953][88298] Updated weights for policy 0, policy_version 73840 (0.0009) -[2023-10-15 05:15:12,973][88300] Updated weights for policy 1, policy_version 74292 (0.0008) -[2023-10-15 05:15:13,314][88298] Updated weights for policy 0, policy_version 73850 (0.0009) -[2023-10-15 05:15:13,337][88300] Updated weights for policy 1, policy_version 74302 (0.0008) -[2023-10-15 05:15:13,538][87330] Fps is (10 sec: 19651.3, 60 sec: 14198.3, 300 sec: 13995.6). Total num frames: 151715840. Throughput: 0: 1728.7, 1: 1736.5. Samples: 37932406. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:15:13,540][87330] Avg episode reward: [(0, '22.760'), (1, '23.070')] -[2023-10-15 05:15:17,262][88300] Updated weights for policy 1, policy_version 74312 (0.0008) -[2023-10-15 05:15:17,278][88298] Updated weights for policy 0, policy_version 73860 (0.0008) -[2023-10-15 05:15:17,629][88300] Updated weights for policy 1, policy_version 74322 (0.0009) -[2023-10-15 05:15:17,643][88298] Updated weights for policy 0, policy_version 73870 (0.0010) -[2023-10-15 05:15:18,002][88300] Updated weights for policy 1, policy_version 74332 (0.0008) -[2023-10-15 05:15:18,015][88298] Updated weights for policy 0, policy_version 73880 (0.0008) -[2023-10-15 05:15:18,534][87330] Fps is (10 sec: 19660.7, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 151781376. Throughput: 0: 1741.5, 1: 1757.1. Samples: 37943372. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:15:18,535][87330] Avg episode reward: [(0, '22.570'), (1, '23.090')] -[2023-10-15 05:15:21,753][88300] Updated weights for policy 1, policy_version 74342 (0.0007) -[2023-10-15 05:15:21,977][88298] Updated weights for policy 0, policy_version 73890 (0.0008) -[2023-10-15 05:15:22,117][88300] Updated weights for policy 1, policy_version 74352 (0.0008) -[2023-10-15 05:15:22,343][88298] Updated weights for policy 0, policy_version 73900 (0.0010) -[2023-10-15 05:15:22,476][88300] Updated weights for policy 1, policy_version 74362 (0.0007) -[2023-10-15 05:15:22,717][88298] Updated weights for policy 0, policy_version 73910 (0.0007) -[2023-10-15 05:15:23,077][88298] Updated weights for policy 0, policy_version 73920 (0.0007) -[2023-10-15 05:15:23,534][87330] Fps is (10 sec: 13113.3, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 151846912. Throughput: 0: 1743.3, 1: 1741.1. Samples: 37964150. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:15:23,535][87330] Avg episode reward: [(0, '22.400'), (1, '22.970')] -[2023-10-15 05:15:26,543][88300] Updated weights for policy 1, policy_version 74372 (0.0009) -[2023-10-15 05:15:26,873][88298] Updated weights for policy 0, policy_version 73930 (0.0008) -[2023-10-15 05:15:26,910][88300] Updated weights for policy 1, policy_version 74382 (0.0009) -[2023-10-15 05:15:27,242][88298] Updated weights for policy 0, policy_version 73940 (0.0007) -[2023-10-15 05:15:27,285][88300] Updated weights for policy 1, policy_version 74392 (0.0007) -[2023-10-15 05:15:27,608][88298] Updated weights for policy 0, policy_version 73950 (0.0007) -[2023-10-15 05:15:28,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 151912448. Throughput: 0: 1713.5, 1: 1719.1. Samples: 37983488. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:15:28,535][87330] Avg episode reward: [(0, '22.200'), (1, '22.900')] -[2023-10-15 05:15:31,146][88300] Updated weights for policy 1, policy_version 74402 (0.0008) -[2023-10-15 05:15:31,513][88300] Updated weights for policy 1, policy_version 74412 (0.0008) -[2023-10-15 05:15:31,625][88298] Updated weights for policy 0, policy_version 73960 (0.0009) -[2023-10-15 05:15:31,879][88300] Updated weights for policy 1, policy_version 74422 (0.0007) -[2023-10-15 05:15:32,007][88298] Updated weights for policy 0, policy_version 73970 (0.0007) -[2023-10-15 05:15:32,243][88300] Updated weights for policy 1, policy_version 74432 (0.0007) -[2023-10-15 05:15:32,383][88298] Updated weights for policy 0, policy_version 73980 (0.0008) -[2023-10-15 05:15:33,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 151977984. Throughput: 0: 1743.4, 1: 1748.7. Samples: 37995638. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:15:33,534][87330] Avg episode reward: [(0, '22.440'), (1, '22.900')] -[2023-10-15 05:15:36,103][88300] Updated weights for policy 1, policy_version 74442 (0.0010) -[2023-10-15 05:15:36,381][88298] Updated weights for policy 0, policy_version 73990 (0.0010) -[2023-10-15 05:15:36,481][88300] Updated weights for policy 1, policy_version 74452 (0.0008) -[2023-10-15 05:15:36,752][88298] Updated weights for policy 0, policy_version 74000 (0.0007) -[2023-10-15 05:15:36,843][88300] Updated weights for policy 1, policy_version 74462 (0.0007) -[2023-10-15 05:15:37,121][88298] Updated weights for policy 0, policy_version 74010 (0.0009) -[2023-10-15 05:15:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 152043520. Throughput: 0: 1726.4, 1: 1722.5. Samples: 38015156. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:15:38,535][87330] Avg episode reward: [(0, '22.220'), (1, '22.790')] -[2023-10-15 05:15:40,698][88300] Updated weights for policy 1, policy_version 74472 (0.0009) -[2023-10-15 05:15:40,946][88298] Updated weights for policy 0, policy_version 74020 (0.0008) -[2023-10-15 05:15:41,051][88300] Updated weights for policy 1, policy_version 74482 (0.0007) -[2023-10-15 05:15:41,349][88298] Updated weights for policy 0, policy_version 74030 (0.0008) -[2023-10-15 05:15:41,419][88300] Updated weights for policy 1, policy_version 74492 (0.0009) -[2023-10-15 05:15:41,720][88298] Updated weights for policy 0, policy_version 74040 (0.0009) -[2023-10-15 05:15:43,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 152109056. Throughput: 0: 1718.2, 1: 1721.3. Samples: 38036132. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:15:43,535][87330] Avg episode reward: [(0, '22.230'), (1, '22.630')] -[2023-10-15 05:15:45,418][88300] Updated weights for policy 1, policy_version 74502 (0.0009) -[2023-10-15 05:15:45,608][88298] Updated weights for policy 0, policy_version 74050 (0.0010) -[2023-10-15 05:15:45,791][88300] Updated weights for policy 1, policy_version 74512 (0.0008) -[2023-10-15 05:15:45,974][88298] Updated weights for policy 0, policy_version 74060 (0.0008) -[2023-10-15 05:15:46,152][88300] Updated weights for policy 1, policy_version 74522 (0.0008) -[2023-10-15 05:15:46,335][88298] Updated weights for policy 0, policy_version 74070 (0.0008) -[2023-10-15 05:15:46,705][88298] Updated weights for policy 0, policy_version 74080 (0.0010) -[2023-10-15 05:15:48,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 152174592. Throughput: 0: 1740.8, 1: 1721.6. Samples: 38046498. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:15:48,535][87330] Avg episode reward: [(0, '22.210'), (1, '22.610')] -[2023-10-15 05:15:50,206][88300] Updated weights for policy 1, policy_version 74532 (0.0010) -[2023-10-15 05:15:50,567][88300] Updated weights for policy 1, policy_version 74542 (0.0008) -[2023-10-15 05:15:50,643][88298] Updated weights for policy 0, policy_version 74090 (0.0008) -[2023-10-15 05:15:50,929][88300] Updated weights for policy 1, policy_version 74552 (0.0009) -[2023-10-15 05:15:51,008][88298] Updated weights for policy 0, policy_version 74100 (0.0009) -[2023-10-15 05:15:51,379][88298] Updated weights for policy 0, policy_version 74110 (0.0009) -[2023-10-15 05:15:53,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 152240128. Throughput: 0: 1719.5, 1: 1710.0. Samples: 38066718. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:15:53,535][87330] Avg episode reward: [(0, '22.600'), (1, '22.610')] -[2023-10-15 05:15:54,836][88300] Updated weights for policy 1, policy_version 74562 (0.0009) -[2023-10-15 05:15:55,196][88300] Updated weights for policy 1, policy_version 74572 (0.0008) -[2023-10-15 05:15:55,328][88298] Updated weights for policy 0, policy_version 74120 (0.0009) -[2023-10-15 05:15:55,566][88300] Updated weights for policy 1, policy_version 74582 (0.0008) -[2023-10-15 05:15:55,701][88298] Updated weights for policy 0, policy_version 74130 (0.0007) -[2023-10-15 05:15:55,929][88300] Updated weights for policy 1, policy_version 74592 (0.0008) -[2023-10-15 05:15:56,058][88298] Updated weights for policy 0, policy_version 74140 (0.0008) -[2023-10-15 05:15:58,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 152305664. Throughput: 0: 1724.6, 1: 1734.8. Samples: 38088066. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:15:58,535][87330] Avg episode reward: [(0, '22.770'), (1, '22.470')] -[2023-10-15 05:15:59,937][88300] Updated weights for policy 1, policy_version 74602 (0.0007) -[2023-10-15 05:15:59,985][88298] Updated weights for policy 0, policy_version 74150 (0.0008) -[2023-10-15 05:16:00,309][88300] Updated weights for policy 1, policy_version 74612 (0.0008) -[2023-10-15 05:16:00,347][88298] Updated weights for policy 0, policy_version 74160 (0.0008) -[2023-10-15 05:16:00,674][88300] Updated weights for policy 1, policy_version 74622 (0.0007) -[2023-10-15 05:16:00,716][88298] Updated weights for policy 0, policy_version 74170 (0.0007) -[2023-10-15 05:16:03,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 152371200. Throughput: 0: 1719.2, 1: 1713.4. Samples: 38097838. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:16:03,534][87330] Avg episode reward: [(0, '22.740'), (1, '22.300')] -[2023-10-15 05:16:04,536][88300] Updated weights for policy 1, policy_version 74632 (0.0008) -[2023-10-15 05:16:04,617][88298] Updated weights for policy 0, policy_version 74180 (0.0009) -[2023-10-15 05:16:04,906][88300] Updated weights for policy 1, policy_version 74642 (0.0008) -[2023-10-15 05:16:04,985][88298] Updated weights for policy 0, policy_version 74190 (0.0008) -[2023-10-15 05:16:05,261][88300] Updated weights for policy 1, policy_version 74652 (0.0009) -[2023-10-15 05:16:05,360][88298] Updated weights for policy 0, policy_version 74200 (0.0007) -[2023-10-15 05:16:08,534][87330] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 152436736. Throughput: 0: 1712.6, 1: 1727.9. Samples: 38118972. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:16:08,534][87330] Avg episode reward: [(0, '22.920'), (1, '22.250')] -[2023-10-15 05:16:09,252][88298] Updated weights for policy 0, policy_version 74210 (0.0008) -[2023-10-15 05:16:09,308][88300] Updated weights for policy 1, policy_version 74662 (0.0008) -[2023-10-15 05:16:09,620][88298] Updated weights for policy 0, policy_version 74220 (0.0008) -[2023-10-15 05:16:09,676][88300] Updated weights for policy 1, policy_version 74672 (0.0008) -[2023-10-15 05:16:09,993][88298] Updated weights for policy 0, policy_version 74230 (0.0008) -[2023-10-15 05:16:10,042][88300] Updated weights for policy 1, policy_version 74682 (0.0009) -[2023-10-15 05:16:10,366][88298] Updated weights for policy 0, policy_version 74240 (0.0008) -[2023-10-15 05:16:13,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13108.2, 300 sec: 13773.7). Total num frames: 152502272. Throughput: 0: 1742.2, 1: 1747.0. Samples: 38140502. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:16:13,535][87330] Avg episode reward: [(0, '22.910'), (1, '22.320')] -[2023-10-15 05:16:13,947][88300] Updated weights for policy 1, policy_version 74692 (0.0007) -[2023-10-15 05:16:14,318][88300] Updated weights for policy 1, policy_version 74702 (0.0009) -[2023-10-15 05:16:14,462][88298] Updated weights for policy 0, policy_version 74250 (0.0007) -[2023-10-15 05:16:14,690][88300] Updated weights for policy 1, policy_version 74712 (0.0008) -[2023-10-15 05:16:14,833][88298] Updated weights for policy 0, policy_version 74260 (0.0008) -[2023-10-15 05:16:15,206][88298] Updated weights for policy 0, policy_version 74270 (0.0009) -[2023-10-15 05:16:18,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 152567808. Throughput: 0: 1706.3, 1: 1717.8. Samples: 38149722. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:16:18,534][87330] Avg episode reward: [(0, '22.680'), (1, '22.370')] -[2023-10-15 05:16:18,633][88300] Updated weights for policy 1, policy_version 74722 (0.0007) -[2023-10-15 05:16:19,006][88300] Updated weights for policy 1, policy_version 74732 (0.0007) -[2023-10-15 05:16:19,114][88298] Updated weights for policy 0, policy_version 74280 (0.0007) -[2023-10-15 05:16:19,378][88300] Updated weights for policy 1, policy_version 74742 (0.0007) -[2023-10-15 05:16:19,492][88298] Updated weights for policy 0, policy_version 74290 (0.0007) -[2023-10-15 05:16:19,738][88300] Updated weights for policy 1, policy_version 74752 (0.0007) -[2023-10-15 05:16:19,856][88298] Updated weights for policy 0, policy_version 74300 (0.0007) -[2023-10-15 05:16:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 152633344. Throughput: 0: 1725.0, 1: 1743.3. Samples: 38171230. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:16:23,535][87330] Avg episode reward: [(0, '22.640'), (1, '22.370')] -[2023-10-15 05:16:23,557][88300] Updated weights for policy 1, policy_version 74762 (0.0010) -[2023-10-15 05:16:23,817][88298] Updated weights for policy 0, policy_version 74310 (0.0008) -[2023-10-15 05:16:23,925][88300] Updated weights for policy 1, policy_version 74772 (0.0008) -[2023-10-15 05:16:24,191][88298] Updated weights for policy 0, policy_version 74320 (0.0008) -[2023-10-15 05:16:24,299][88300] Updated weights for policy 1, policy_version 74782 (0.0007) -[2023-10-15 05:16:24,568][88298] Updated weights for policy 0, policy_version 74330 (0.0010) -[2023-10-15 05:16:28,300][88300] Updated weights for policy 1, policy_version 74792 (0.0010) -[2023-10-15 05:16:28,516][88298] Updated weights for policy 0, policy_version 74340 (0.0007) -[2023-10-15 05:16:28,534][87330] Fps is (10 sec: 13106.7, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 152698880. Throughput: 0: 1735.2, 1: 1737.3. Samples: 38192398. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:16:28,535][87330] Avg episode reward: [(0, '22.670'), (1, '22.490')] -[2023-10-15 05:16:28,676][88300] Updated weights for policy 1, policy_version 74802 (0.0008) -[2023-10-15 05:16:28,919][88298] Updated weights for policy 0, policy_version 74350 (0.0007) -[2023-10-15 05:16:29,032][88300] Updated weights for policy 1, policy_version 74812 (0.0008) -[2023-10-15 05:16:29,283][88298] Updated weights for policy 0, policy_version 74360 (0.0007) -[2023-10-15 05:16:33,104][88298] Updated weights for policy 0, policy_version 74370 (0.0008) -[2023-10-15 05:16:33,104][88300] Updated weights for policy 1, policy_version 74822 (0.0009) -[2023-10-15 05:16:33,471][88298] Updated weights for policy 0, policy_version 74380 (0.0008) -[2023-10-15 05:16:33,491][88300] Updated weights for policy 1, policy_version 74832 (0.0007) -[2023-10-15 05:16:33,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 152764416. Throughput: 0: 1710.8, 1: 1740.9. Samples: 38201824. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:16:33,534][87330] Avg episode reward: [(0, '22.690'), (1, '22.640')] -[2023-10-15 05:16:33,830][88298] Updated weights for policy 0, policy_version 74390 (0.0007) -[2023-10-15 05:16:33,860][88300] Updated weights for policy 1, policy_version 74842 (0.0008) -[2023-10-15 05:16:34,204][88298] Updated weights for policy 0, policy_version 74400 (0.0007) -[2023-10-15 05:16:37,813][88300] Updated weights for policy 1, policy_version 74852 (0.0007) -[2023-10-15 05:16:38,158][88298] Updated weights for policy 0, policy_version 74410 (0.0007) -[2023-10-15 05:16:38,186][88300] Updated weights for policy 1, policy_version 74862 (0.0007) -[2023-10-15 05:16:38,526][88298] Updated weights for policy 0, policy_version 74420 (0.0009) -[2023-10-15 05:16:38,534][87330] Fps is (10 sec: 13107.8, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 152829952. Throughput: 0: 1733.2, 1: 1743.7. Samples: 38223176. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:16:38,534][87330] Avg episode reward: [(0, '22.720'), (1, '22.620')] -[2023-10-15 05:16:38,541][88300] Updated weights for policy 1, policy_version 74872 (0.0007) -[2023-10-15 05:16:38,903][88298] Updated weights for policy 0, policy_version 74430 (0.0008) -[2023-10-15 05:16:42,462][88300] Updated weights for policy 1, policy_version 74882 (0.0008) -[2023-10-15 05:16:42,776][88298] Updated weights for policy 0, policy_version 74440 (0.0008) -[2023-10-15 05:16:42,824][88300] Updated weights for policy 1, policy_version 74892 (0.0009) -[2023-10-15 05:16:43,155][88298] Updated weights for policy 0, policy_version 74450 (0.0007) -[2023-10-15 05:16:43,197][88300] Updated weights for policy 1, policy_version 74902 (0.0009) -[2023-10-15 05:16:43,526][88298] Updated weights for policy 0, policy_version 74460 (0.0009) -[2023-10-15 05:16:43,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 152895488. Throughput: 0: 1723.2, 1: 1725.6. Samples: 38243264. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:16:43,535][87330] Avg episode reward: [(0, '22.450'), (1, '22.880')] -[2023-10-15 05:16:43,558][88300] Updated weights for policy 1, policy_version 74912 (0.0009) -[2023-10-15 05:16:47,416][88300] Updated weights for policy 1, policy_version 74922 (0.0009) -[2023-10-15 05:16:47,659][88298] Updated weights for policy 0, policy_version 74470 (0.0009) -[2023-10-15 05:16:47,775][88300] Updated weights for policy 1, policy_version 74932 (0.0009) -[2023-10-15 05:16:48,029][88298] Updated weights for policy 0, policy_version 74480 (0.0008) -[2023-10-15 05:16:48,145][88300] Updated weights for policy 1, policy_version 74942 (0.0007) -[2023-10-15 05:16:48,396][88298] Updated weights for policy 0, policy_version 74490 (0.0009) -[2023-10-15 05:16:48,534][87330] Fps is (10 sec: 16383.5, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 152993792. Throughput: 0: 1721.9, 1: 1748.3. Samples: 38254002. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:16:48,535][87330] Avg episode reward: [(0, '22.680'), (1, '22.890')] -[2023-10-15 05:16:51,820][88300] Updated weights for policy 1, policy_version 74952 (0.0007) -[2023-10-15 05:16:52,183][88300] Updated weights for policy 1, policy_version 74962 (0.0007) -[2023-10-15 05:16:52,195][88298] Updated weights for policy 0, policy_version 74500 (0.0008) -[2023-10-15 05:16:52,550][88300] Updated weights for policy 1, policy_version 74972 (0.0007) -[2023-10-15 05:16:52,566][88298] Updated weights for policy 0, policy_version 74510 (0.0008) -[2023-10-15 05:16:52,932][88298] Updated weights for policy 0, policy_version 74520 (0.0008) -[2023-10-15 05:16:53,534][87330] Fps is (10 sec: 19661.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 153092096. Throughput: 0: 1731.2, 1: 1730.5. Samples: 38274752. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-15 05:16:53,534][87330] Avg episode reward: [(0, '22.290'), (1, '22.860')] -[2023-10-15 05:16:56,527][88300] Updated weights for policy 1, policy_version 74982 (0.0008) -[2023-10-15 05:16:56,871][88298] Updated weights for policy 0, policy_version 74530 (0.0008) -[2023-10-15 05:16:56,899][88300] Updated weights for policy 1, policy_version 74992 (0.0008) -[2023-10-15 05:16:57,241][88298] Updated weights for policy 0, policy_version 74540 (0.0008) -[2023-10-15 05:16:57,265][88300] Updated weights for policy 1, policy_version 75002 (0.0009) -[2023-10-15 05:16:57,615][88298] Updated weights for policy 0, policy_version 74550 (0.0007) -[2023-10-15 05:16:57,977][88298] Updated weights for policy 0, policy_version 74560 (0.0007) -[2023-10-15 05:16:58,534][87330] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 153157632. Throughput: 0: 1705.9, 1: 1716.8. Samples: 38294524. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-15 05:16:58,534][87330] Avg episode reward: [(0, '22.230'), (1, '22.850')] -[2023-10-15 05:16:58,543][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000074560_76349440.pth... -[2023-10-15 05:16:58,543][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000075008_76808192.pth... -[2023-10-15 05:16:58,580][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000073376_75137024.pth -[2023-10-15 05:16:58,585][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000072928_74678272.pth -[2023-10-15 05:17:01,129][88300] Updated weights for policy 1, policy_version 75012 (0.0008) -[2023-10-15 05:17:01,487][88300] Updated weights for policy 1, policy_version 75022 (0.0007) -[2023-10-15 05:17:01,854][88300] Updated weights for policy 1, policy_version 75032 (0.0009) -[2023-10-15 05:17:01,933][88298] Updated weights for policy 0, policy_version 74570 (0.0007) -[2023-10-15 05:17:02,306][88298] Updated weights for policy 0, policy_version 74580 (0.0009) -[2023-10-15 05:17:02,678][88298] Updated weights for policy 0, policy_version 74590 (0.0009) -[2023-10-15 05:17:03,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 153223168. Throughput: 0: 1739.6, 1: 1738.4. Samples: 38306234. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-15 05:17:03,534][87330] Avg episode reward: [(0, '22.200'), (1, '22.850')] -[2023-10-15 05:17:05,818][88300] Updated weights for policy 1, policy_version 75042 (0.0009) -[2023-10-15 05:17:06,183][88300] Updated weights for policy 1, policy_version 75052 (0.0010) -[2023-10-15 05:17:06,560][88300] Updated weights for policy 1, policy_version 75062 (0.0007) -[2023-10-15 05:17:06,635][88298] Updated weights for policy 0, policy_version 74600 (0.0007) -[2023-10-15 05:17:06,925][88300] Updated weights for policy 1, policy_version 75072 (0.0008) -[2023-10-15 05:17:07,007][88298] Updated weights for policy 0, policy_version 74610 (0.0008) -[2023-10-15 05:17:07,383][88298] Updated weights for policy 0, policy_version 74620 (0.0008) -[2023-10-15 05:17:08,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 153288704. Throughput: 0: 1729.3, 1: 1715.5. Samples: 38326248. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-15 05:17:08,535][87330] Avg episode reward: [(0, '22.180'), (1, '22.970')] -[2023-10-15 05:17:10,887][88300] Updated weights for policy 1, policy_version 75082 (0.0008) -[2023-10-15 05:17:11,216][88298] Updated weights for policy 0, policy_version 74630 (0.0008) -[2023-10-15 05:17:11,256][88300] Updated weights for policy 1, policy_version 75092 (0.0009) -[2023-10-15 05:17:11,586][88298] Updated weights for policy 0, policy_version 74640 (0.0009) -[2023-10-15 05:17:11,620][88300] Updated weights for policy 1, policy_version 75102 (0.0008) -[2023-10-15 05:17:11,961][88298] Updated weights for policy 0, policy_version 74650 (0.0009) -[2023-10-15 05:17:13,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 153354240. Throughput: 0: 1715.7, 1: 1719.9. Samples: 38347002. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-15 05:17:13,535][87330] Avg episode reward: [(0, '22.410'), (1, '22.980')] -[2023-10-15 05:17:15,565][88300] Updated weights for policy 1, policy_version 75112 (0.0009) -[2023-10-15 05:17:15,802][88298] Updated weights for policy 0, policy_version 74660 (0.0007) -[2023-10-15 05:17:15,942][88300] Updated weights for policy 1, policy_version 75122 (0.0007) -[2023-10-15 05:17:16,189][88298] Updated weights for policy 0, policy_version 74670 (0.0007) -[2023-10-15 05:17:16,311][88300] Updated weights for policy 1, policy_version 75132 (0.0007) -[2023-10-15 05:17:16,564][88298] Updated weights for policy 0, policy_version 74680 (0.0009) -[2023-10-15 05:17:18,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 153419776. Throughput: 0: 1748.6, 1: 1724.8. Samples: 38358128. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-15 05:17:18,535][87330] Avg episode reward: [(0, '22.420'), (1, '22.990')] -[2023-10-15 05:17:20,180][88300] Updated weights for policy 1, policy_version 75142 (0.0008) -[2023-10-15 05:17:20,469][88298] Updated weights for policy 0, policy_version 74690 (0.0009) -[2023-10-15 05:17:20,567][88300] Updated weights for policy 1, policy_version 75152 (0.0008) -[2023-10-15 05:17:20,832][88298] Updated weights for policy 0, policy_version 74700 (0.0007) -[2023-10-15 05:17:20,936][88300] Updated weights for policy 1, policy_version 75162 (0.0008) -[2023-10-15 05:17:21,198][88298] Updated weights for policy 0, policy_version 74710 (0.0008) -[2023-10-15 05:17:21,568][88298] Updated weights for policy 0, policy_version 74720 (0.0008) -[2023-10-15 05:17:23,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 153485312. Throughput: 0: 1721.0, 1: 1715.3. Samples: 38377812. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-15 05:17:23,534][87330] Avg episode reward: [(0, '22.750'), (1, '23.010')] -[2023-10-15 05:17:24,998][88300] Updated weights for policy 1, policy_version 75172 (0.0009) -[2023-10-15 05:17:25,361][88300] Updated weights for policy 1, policy_version 75182 (0.0010) -[2023-10-15 05:17:25,405][88298] Updated weights for policy 0, policy_version 74730 (0.0007) -[2023-10-15 05:17:25,731][88300] Updated weights for policy 1, policy_version 75192 (0.0008) -[2023-10-15 05:17:25,776][88298] Updated weights for policy 0, policy_version 74740 (0.0008) -[2023-10-15 05:17:26,142][88298] Updated weights for policy 0, policy_version 74750 (0.0010) -[2023-10-15 05:17:28,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 153550848. Throughput: 0: 1738.4, 1: 1732.4. Samples: 38399448. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-15 05:17:28,535][87330] Avg episode reward: [(0, '22.830'), (1, '23.030')] -[2023-10-15 05:17:29,625][88300] Updated weights for policy 1, policy_version 75202 (0.0007) -[2023-10-15 05:17:29,917][88298] Updated weights for policy 0, policy_version 74760 (0.0007) -[2023-10-15 05:17:29,997][88300] Updated weights for policy 1, policy_version 75212 (0.0007) -[2023-10-15 05:17:30,289][88298] Updated weights for policy 0, policy_version 74770 (0.0008) -[2023-10-15 05:17:30,356][88300] Updated weights for policy 1, policy_version 75222 (0.0007) -[2023-10-15 05:17:30,653][88298] Updated weights for policy 0, policy_version 74780 (0.0007) -[2023-10-15 05:17:30,726][88300] Updated weights for policy 1, policy_version 75232 (0.0007) -[2023-10-15 05:17:33,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 153616384. Throughput: 0: 1734.0, 1: 1706.6. Samples: 38408832. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-15 05:17:33,535][87330] Avg episode reward: [(0, '22.830'), (1, '23.030')] -[2023-10-15 05:17:34,527][88298] Updated weights for policy 0, policy_version 74790 (0.0010) -[2023-10-15 05:17:34,758][88300] Updated weights for policy 1, policy_version 75242 (0.0008) -[2023-10-15 05:17:34,895][88298] Updated weights for policy 0, policy_version 74800 (0.0010) -[2023-10-15 05:17:35,122][88300] Updated weights for policy 1, policy_version 75252 (0.0007) -[2023-10-15 05:17:35,264][88298] Updated weights for policy 0, policy_version 74810 (0.0007) -[2023-10-15 05:17:35,491][88300] Updated weights for policy 1, policy_version 75262 (0.0007) -[2023-10-15 05:17:38,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 153681920. Throughput: 0: 1730.1, 1: 1725.3. Samples: 38430244. Policy #0 lag: (min: 18.0, avg: 26.4, max: 50.0) -[2023-10-15 05:17:38,535][87330] Avg episode reward: [(0, '22.900'), (1, '23.010')] -[2023-10-15 05:17:39,200][88298] Updated weights for policy 0, policy_version 74820 (0.0008) -[2023-10-15 05:17:39,368][88300] Updated weights for policy 1, policy_version 75272 (0.0008) -[2023-10-15 05:17:39,561][88298] Updated weights for policy 0, policy_version 74830 (0.0008) -[2023-10-15 05:17:39,732][88300] Updated weights for policy 1, policy_version 75282 (0.0009) -[2023-10-15 05:17:39,933][88298] Updated weights for policy 0, policy_version 74840 (0.0009) -[2023-10-15 05:17:40,097][88300] Updated weights for policy 1, policy_version 75292 (0.0009) -[2023-10-15 05:17:43,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 153747456. Throughput: 0: 1752.8, 1: 1741.8. Samples: 38451780. Policy #0 lag: (min: 18.0, avg: 26.4, max: 50.0) -[2023-10-15 05:17:43,534][87330] Avg episode reward: [(0, '22.880'), (1, '23.100')] -[2023-10-15 05:17:43,917][88298] Updated weights for policy 0, policy_version 74850 (0.0007) -[2023-10-15 05:17:44,049][88300] Updated weights for policy 1, policy_version 75302 (0.0007) -[2023-10-15 05:17:44,298][88298] Updated weights for policy 0, policy_version 74860 (0.0007) -[2023-10-15 05:17:44,416][88300] Updated weights for policy 1, policy_version 75312 (0.0007) -[2023-10-15 05:17:44,669][88298] Updated weights for policy 0, policy_version 74870 (0.0007) -[2023-10-15 05:17:44,784][88300] Updated weights for policy 1, policy_version 75322 (0.0008) -[2023-10-15 05:17:45,036][88298] Updated weights for policy 0, policy_version 74880 (0.0009) -[2023-10-15 05:17:48,534][87330] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 153812992. Throughput: 0: 1721.9, 1: 1723.4. Samples: 38461270. Policy #0 lag: (min: 18.0, avg: 26.4, max: 50.0) -[2023-10-15 05:17:48,534][87330] Avg episode reward: [(0, '23.000'), (1, '22.880')] -[2023-10-15 05:17:48,634][88300] Updated weights for policy 1, policy_version 75332 (0.0007) -[2023-10-15 05:17:48,938][88298] Updated weights for policy 0, policy_version 74890 (0.0008) -[2023-10-15 05:17:48,995][88300] Updated weights for policy 1, policy_version 75342 (0.0007) -[2023-10-15 05:17:49,309][88298] Updated weights for policy 0, policy_version 74900 (0.0007) -[2023-10-15 05:17:49,362][88300] Updated weights for policy 1, policy_version 75352 (0.0007) -[2023-10-15 05:17:49,682][88298] Updated weights for policy 0, policy_version 74910 (0.0007) -[2023-10-15 05:17:53,247][88300] Updated weights for policy 1, policy_version 75362 (0.0007) -[2023-10-15 05:17:53,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 153878528. Throughput: 0: 1732.4, 1: 1745.6. Samples: 38482756. Policy #0 lag: (min: 18.0, avg: 26.4, max: 50.0) -[2023-10-15 05:17:53,534][87330] Avg episode reward: [(0, '23.000'), (1, '22.890')] -[2023-10-15 05:17:53,555][88298] Updated weights for policy 0, policy_version 74920 (0.0008) -[2023-10-15 05:17:53,614][88300] Updated weights for policy 1, policy_version 75372 (0.0008) -[2023-10-15 05:17:53,928][88298] Updated weights for policy 0, policy_version 74930 (0.0009) -[2023-10-15 05:17:53,980][88300] Updated weights for policy 1, policy_version 75382 (0.0007) -[2023-10-15 05:17:54,298][88298] Updated weights for policy 0, policy_version 74940 (0.0008) -[2023-10-15 05:17:54,341][88300] Updated weights for policy 1, policy_version 75392 (0.0010) -[2023-10-15 05:17:58,228][88300] Updated weights for policy 1, policy_version 75402 (0.0010) -[2023-10-15 05:17:58,377][88298] Updated weights for policy 0, policy_version 74950 (0.0007) -[2023-10-15 05:17:58,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 153944064. Throughput: 0: 1747.6, 1: 1738.8. Samples: 38503888. Policy #0 lag: (min: 18.0, avg: 26.4, max: 50.0) -[2023-10-15 05:17:58,534][87330] Avg episode reward: [(0, '23.030'), (1, '22.790')] -[2023-10-15 05:17:58,596][88300] Updated weights for policy 1, policy_version 75412 (0.0007) -[2023-10-15 05:17:58,739][88298] Updated weights for policy 0, policy_version 74960 (0.0009) -[2023-10-15 05:17:58,948][88300] Updated weights for policy 1, policy_version 75422 (0.0007) -[2023-10-15 05:17:59,106][88298] Updated weights for policy 0, policy_version 74970 (0.0007) -[2023-10-15 05:18:02,796][88300] Updated weights for policy 1, policy_version 75432 (0.0009) -[2023-10-15 05:18:03,157][88300] Updated weights for policy 1, policy_version 75442 (0.0007) -[2023-10-15 05:18:03,174][88298] Updated weights for policy 0, policy_version 74980 (0.0008) -[2023-10-15 05:18:03,528][88300] Updated weights for policy 1, policy_version 75452 (0.0007) -[2023-10-15 05:18:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 154009600. Throughput: 0: 1719.7, 1: 1742.1. Samples: 38513906. Policy #0 lag: (min: 18.0, avg: 26.4, max: 50.0) -[2023-10-15 05:18:03,534][87330] Avg episode reward: [(0, '22.990'), (1, '22.800')] -[2023-10-15 05:18:03,565][88298] Updated weights for policy 0, policy_version 74990 (0.0008) -[2023-10-15 05:18:03,938][88298] Updated weights for policy 0, policy_version 75000 (0.0007) -[2023-10-15 05:18:07,653][88300] Updated weights for policy 1, policy_version 75462 (0.0008) -[2023-10-15 05:18:07,924][88298] Updated weights for policy 0, policy_version 75010 (0.0007) -[2023-10-15 05:18:08,040][88300] Updated weights for policy 1, policy_version 75472 (0.0007) -[2023-10-15 05:18:08,295][88298] Updated weights for policy 0, policy_version 75020 (0.0008) -[2023-10-15 05:18:08,405][88300] Updated weights for policy 1, policy_version 75482 (0.0007) -[2023-10-15 05:18:08,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 154075136. Throughput: 0: 1740.2, 1: 1757.0. Samples: 38535186. Policy #0 lag: (min: 18.0, avg: 26.4, max: 50.0) -[2023-10-15 05:18:08,535][87330] Avg episode reward: [(0, '22.900'), (1, '22.700')] -[2023-10-15 05:18:08,662][88298] Updated weights for policy 0, policy_version 75030 (0.0007) -[2023-10-15 05:18:09,029][88298] Updated weights for policy 0, policy_version 75040 (0.0007) -[2023-10-15 05:18:12,160][88300] Updated weights for policy 1, policy_version 75492 (0.0007) -[2023-10-15 05:18:12,525][88300] Updated weights for policy 1, policy_version 75502 (0.0008) -[2023-10-15 05:18:12,892][88300] Updated weights for policy 1, policy_version 75512 (0.0007) -[2023-10-15 05:18:12,909][88298] Updated weights for policy 0, policy_version 75050 (0.0007) -[2023-10-15 05:18:13,277][88298] Updated weights for policy 0, policy_version 75060 (0.0009) -[2023-10-15 05:18:13,534][87330] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 154173440. Throughput: 0: 1732.1, 1: 1726.4. Samples: 38555084. Policy #0 lag: (min: 18.0, avg: 26.4, max: 50.0) -[2023-10-15 05:18:13,535][87330] Avg episode reward: [(0, '22.900'), (1, '22.710')] -[2023-10-15 05:18:13,650][88298] Updated weights for policy 0, policy_version 75070 (0.0009) -[2023-10-15 05:18:16,756][88300] Updated weights for policy 1, policy_version 75522 (0.0007) -[2023-10-15 05:18:17,113][88300] Updated weights for policy 1, policy_version 75532 (0.0007) -[2023-10-15 05:18:17,483][88300] Updated weights for policy 1, policy_version 75542 (0.0008) -[2023-10-15 05:18:17,616][88298] Updated weights for policy 0, policy_version 75080 (0.0008) -[2023-10-15 05:18:17,844][88300] Updated weights for policy 1, policy_version 75552 (0.0009) -[2023-10-15 05:18:17,997][88298] Updated weights for policy 0, policy_version 75090 (0.0008) -[2023-10-15 05:18:18,365][88298] Updated weights for policy 0, policy_version 75100 (0.0008) -[2023-10-15 05:18:18,534][87330] Fps is (10 sec: 19660.8, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 154271744. Throughput: 0: 1733.8, 1: 1759.4. Samples: 38566028. Policy #0 lag: (min: 18.0, avg: 26.4, max: 50.0) -[2023-10-15 05:18:18,535][87330] Avg episode reward: [(0, '22.900'), (1, '22.940')] -[2023-10-15 05:18:21,903][88300] Updated weights for policy 1, policy_version 75562 (0.0010) -[2023-10-15 05:18:22,269][88300] Updated weights for policy 1, policy_version 75572 (0.0008) -[2023-10-15 05:18:22,363][88298] Updated weights for policy 0, policy_version 75110 (0.0008) -[2023-10-15 05:18:22,626][88300] Updated weights for policy 1, policy_version 75582 (0.0009) -[2023-10-15 05:18:22,738][88298] Updated weights for policy 0, policy_version 75120 (0.0007) -[2023-10-15 05:18:23,105][88298] Updated weights for policy 0, policy_version 75130 (0.0007) -[2023-10-15 05:18:23,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 154337280. Throughput: 0: 1733.3, 1: 1741.7. Samples: 38586618. Policy #0 lag: (min: 2.0, avg: 10.6, max: 34.0) -[2023-10-15 05:18:23,534][87330] Avg episode reward: [(0, '22.860'), (1, '22.920')] -[2023-10-15 05:18:26,445][88300] Updated weights for policy 1, policy_version 75592 (0.0011) -[2023-10-15 05:18:26,816][88300] Updated weights for policy 1, policy_version 75602 (0.0009) -[2023-10-15 05:18:27,149][88298] Updated weights for policy 0, policy_version 75140 (0.0008) -[2023-10-15 05:18:27,174][88300] Updated weights for policy 1, policy_version 75612 (0.0008) -[2023-10-15 05:18:27,525][88298] Updated weights for policy 0, policy_version 75150 (0.0010) -[2023-10-15 05:18:27,888][88298] Updated weights for policy 0, policy_version 75160 (0.0009) -[2023-10-15 05:18:28,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 154402816. Throughput: 0: 1716.5, 1: 1733.1. Samples: 38607012. Policy #0 lag: (min: 2.0, avg: 10.6, max: 34.0) -[2023-10-15 05:18:28,534][87330] Avg episode reward: [(0, '22.760'), (1, '22.970')] -[2023-10-15 05:18:30,895][88300] Updated weights for policy 1, policy_version 75622 (0.0008) -[2023-10-15 05:18:31,257][88300] Updated weights for policy 1, policy_version 75632 (0.0009) -[2023-10-15 05:18:31,633][88300] Updated weights for policy 1, policy_version 75642 (0.0009) -[2023-10-15 05:18:31,823][88298] Updated weights for policy 0, policy_version 75170 (0.0008) -[2023-10-15 05:18:32,186][88298] Updated weights for policy 0, policy_version 75180 (0.0009) -[2023-10-15 05:18:32,555][88298] Updated weights for policy 0, policy_version 75190 (0.0009) -[2023-10-15 05:18:32,913][88298] Updated weights for policy 0, policy_version 75200 (0.0007) -[2023-10-15 05:18:33,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 154468352. Throughput: 0: 1734.5, 1: 1750.4. Samples: 38618092. Policy #0 lag: (min: 2.0, avg: 10.6, max: 34.0) -[2023-10-15 05:18:33,535][87330] Avg episode reward: [(0, '22.710'), (1, '23.000')] -[2023-10-15 05:18:35,429][88300] Updated weights for policy 1, policy_version 75652 (0.0009) -[2023-10-15 05:18:35,791][88300] Updated weights for policy 1, policy_version 75662 (0.0009) -[2023-10-15 05:18:36,162][88300] Updated weights for policy 1, policy_version 75672 (0.0008) -[2023-10-15 05:18:36,769][88298] Updated weights for policy 0, policy_version 75210 (0.0009) -[2023-10-15 05:18:37,146][88298] Updated weights for policy 0, policy_version 75220 (0.0008) -[2023-10-15 05:18:37,511][88298] Updated weights for policy 0, policy_version 75230 (0.0007) -[2023-10-15 05:18:38,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 154533888. Throughput: 0: 1726.5, 1: 1735.6. Samples: 38638550. Policy #0 lag: (min: 2.0, avg: 10.6, max: 34.0) -[2023-10-15 05:18:38,534][87330] Avg episode reward: [(0, '22.820'), (1, '23.100')] -[2023-10-15 05:18:40,072][88300] Updated weights for policy 1, policy_version 75682 (0.0009) -[2023-10-15 05:18:40,437][88300] Updated weights for policy 1, policy_version 75692 (0.0009) -[2023-10-15 05:18:40,804][88300] Updated weights for policy 1, policy_version 75702 (0.0007) -[2023-10-15 05:18:41,172][88300] Updated weights for policy 1, policy_version 75712 (0.0008) -[2023-10-15 05:18:41,343][88298] Updated weights for policy 0, policy_version 75240 (0.0009) -[2023-10-15 05:18:41,710][88298] Updated weights for policy 0, policy_version 75250 (0.0010) -[2023-10-15 05:18:42,081][88298] Updated weights for policy 0, policy_version 75260 (0.0009) -[2023-10-15 05:18:43,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 154599424. Throughput: 0: 1706.5, 1: 1749.9. Samples: 38659424. Policy #0 lag: (min: 2.0, avg: 10.6, max: 34.0) -[2023-10-15 05:18:43,534][87330] Avg episode reward: [(0, '22.800'), (1, '23.050')] -[2023-10-15 05:18:45,155][88300] Updated weights for policy 1, policy_version 75722 (0.0010) -[2023-10-15 05:18:45,525][88300] Updated weights for policy 1, policy_version 75732 (0.0008) -[2023-10-15 05:18:45,885][88298] Updated weights for policy 0, policy_version 75270 (0.0010) -[2023-10-15 05:18:45,894][88300] Updated weights for policy 1, policy_version 75742 (0.0007) -[2023-10-15 05:18:46,258][88298] Updated weights for policy 0, policy_version 75280 (0.0007) -[2023-10-15 05:18:46,624][88298] Updated weights for policy 0, policy_version 75290 (0.0008) -[2023-10-15 05:18:48,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 154664960. Throughput: 0: 1734.5, 1: 1736.9. Samples: 38670122. Policy #0 lag: (min: 2.0, avg: 10.6, max: 34.0) -[2023-10-15 05:18:48,534][87330] Avg episode reward: [(0, '22.780'), (1, '23.070')] -[2023-10-15 05:18:49,904][88300] Updated weights for policy 1, policy_version 75752 (0.0008) -[2023-10-15 05:18:50,281][88300] Updated weights for policy 1, policy_version 75762 (0.0007) -[2023-10-15 05:18:50,594][88298] Updated weights for policy 0, policy_version 75300 (0.0009) -[2023-10-15 05:18:50,651][88300] Updated weights for policy 1, policy_version 75772 (0.0007) -[2023-10-15 05:18:50,982][88298] Updated weights for policy 0, policy_version 75310 (0.0008) -[2023-10-15 05:18:51,344][88298] Updated weights for policy 0, policy_version 75320 (0.0010) -[2023-10-15 05:18:53,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 154730496. Throughput: 0: 1712.7, 1: 1732.2. Samples: 38690204. Policy #0 lag: (min: 2.0, avg: 10.6, max: 34.0) -[2023-10-15 05:18:53,535][87330] Avg episode reward: [(0, '22.790'), (1, '22.900')] -[2023-10-15 05:18:54,446][88300] Updated weights for policy 1, policy_version 75782 (0.0008) -[2023-10-15 05:18:54,826][88300] Updated weights for policy 1, policy_version 75792 (0.0008) -[2023-10-15 05:18:55,193][88300] Updated weights for policy 1, policy_version 75802 (0.0007) -[2023-10-15 05:18:55,383][88298] Updated weights for policy 0, policy_version 75330 (0.0008) -[2023-10-15 05:18:55,761][88298] Updated weights for policy 0, policy_version 75340 (0.0010) -[2023-10-15 05:18:56,131][88298] Updated weights for policy 0, policy_version 75350 (0.0008) -[2023-10-15 05:18:56,506][88298] Updated weights for policy 0, policy_version 75360 (0.0008) -[2023-10-15 05:18:58,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 154796032. Throughput: 0: 1713.9, 1: 1763.6. Samples: 38711570. Policy #0 lag: (min: 2.0, avg: 10.6, max: 34.0) -[2023-10-15 05:18:58,534][87330] Avg episode reward: [(0, '22.500'), (1, '22.920')] -[2023-10-15 05:18:58,543][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000075808_77627392.pth... -[2023-10-15 05:18:58,543][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000075360_77168640.pth... -[2023-10-15 05:18:58,583][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000074208_75988992.pth -[2023-10-15 05:18:58,583][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000073760_75530240.pth -[2023-10-15 05:18:59,157][88300] Updated weights for policy 1, policy_version 75812 (0.0008) -[2023-10-15 05:18:59,516][88300] Updated weights for policy 1, policy_version 75822 (0.0010) -[2023-10-15 05:18:59,893][88300] Updated weights for policy 1, policy_version 75832 (0.0010) -[2023-10-15 05:19:00,297][88298] Updated weights for policy 0, policy_version 75370 (0.0007) -[2023-10-15 05:19:00,665][88298] Updated weights for policy 0, policy_version 75380 (0.0008) -[2023-10-15 05:19:01,033][88298] Updated weights for policy 0, policy_version 75390 (0.0009) -[2023-10-15 05:19:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 154861568. Throughput: 0: 1719.1, 1: 1731.3. Samples: 38721296. Policy #0 lag: (min: 2.0, avg: 10.6, max: 34.0) -[2023-10-15 05:19:03,535][87330] Avg episode reward: [(0, '22.600'), (1, '22.910')] -[2023-10-15 05:19:03,799][88300] Updated weights for policy 1, policy_version 75842 (0.0008) -[2023-10-15 05:19:04,166][88300] Updated weights for policy 1, policy_version 75852 (0.0007) -[2023-10-15 05:19:04,544][88300] Updated weights for policy 1, policy_version 75862 (0.0008) -[2023-10-15 05:19:04,899][88298] Updated weights for policy 0, policy_version 75400 (0.0008) -[2023-10-15 05:19:04,904][88300] Updated weights for policy 1, policy_version 75872 (0.0009) -[2023-10-15 05:19:05,278][88298] Updated weights for policy 0, policy_version 75410 (0.0007) -[2023-10-15 05:19:05,637][88298] Updated weights for policy 0, policy_version 75420 (0.0007) -[2023-10-15 05:19:08,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 154927104. Throughput: 0: 1715.6, 1: 1749.3. Samples: 38742536. Policy #0 lag: (min: 2.0, avg: 10.6, max: 34.0) -[2023-10-15 05:19:08,534][87330] Avg episode reward: [(0, '22.690'), (1, '22.870')] -[2023-10-15 05:19:08,815][88300] Updated weights for policy 1, policy_version 75882 (0.0007) -[2023-10-15 05:19:09,178][88300] Updated weights for policy 1, policy_version 75892 (0.0007) -[2023-10-15 05:19:09,416][88298] Updated weights for policy 0, policy_version 75430 (0.0008) -[2023-10-15 05:19:09,550][88300] Updated weights for policy 1, policy_version 75902 (0.0007) -[2023-10-15 05:19:09,777][88298] Updated weights for policy 0, policy_version 75440 (0.0008) -[2023-10-15 05:19:10,157][88298] Updated weights for policy 0, policy_version 75450 (0.0008) -[2023-10-15 05:19:13,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 154992640. Throughput: 0: 1739.9, 1: 1752.8. Samples: 38764182. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-15 05:19:13,534][87330] Avg episode reward: [(0, '22.680'), (1, '22.870')] -[2023-10-15 05:19:13,553][88300] Updated weights for policy 1, policy_version 75912 (0.0008) -[2023-10-15 05:19:13,916][88300] Updated weights for policy 1, policy_version 75922 (0.0007) -[2023-10-15 05:19:14,129][88298] Updated weights for policy 0, policy_version 75460 (0.0007) -[2023-10-15 05:19:14,286][88300] Updated weights for policy 1, policy_version 75932 (0.0008) -[2023-10-15 05:19:14,501][88298] Updated weights for policy 0, policy_version 75470 (0.0008) -[2023-10-15 05:19:14,871][88298] Updated weights for policy 0, policy_version 75480 (0.0009) -[2023-10-15 05:19:18,159][88300] Updated weights for policy 1, policy_version 75942 (0.0007) -[2023-10-15 05:19:18,522][88300] Updated weights for policy 1, policy_version 75952 (0.0008) -[2023-10-15 05:19:18,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 155058176. Throughput: 0: 1726.4, 1: 1729.9. Samples: 38773622. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-15 05:19:18,534][87330] Avg episode reward: [(0, '22.710'), (1, '22.890')] -[2023-10-15 05:19:18,729][88298] Updated weights for policy 0, policy_version 75490 (0.0007) -[2023-10-15 05:19:18,885][88300] Updated weights for policy 1, policy_version 75962 (0.0008) -[2023-10-15 05:19:19,100][88298] Updated weights for policy 0, policy_version 75500 (0.0008) -[2023-10-15 05:19:19,460][88298] Updated weights for policy 0, policy_version 75510 (0.0008) -[2023-10-15 05:19:19,827][88298] Updated weights for policy 0, policy_version 75520 (0.0008) -[2023-10-15 05:19:22,695][88300] Updated weights for policy 1, policy_version 75972 (0.0008) -[2023-10-15 05:19:23,061][88300] Updated weights for policy 1, policy_version 75982 (0.0007) -[2023-10-15 05:19:23,423][88300] Updated weights for policy 1, policy_version 75992 (0.0009) -[2023-10-15 05:19:23,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 155123712. Throughput: 0: 1734.2, 1: 1748.0. Samples: 38795250. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-15 05:19:23,534][87330] Avg episode reward: [(0, '22.610'), (1, '22.870')] -[2023-10-15 05:19:23,669][88298] Updated weights for policy 0, policy_version 75530 (0.0008) -[2023-10-15 05:19:24,030][88298] Updated weights for policy 0, policy_version 75540 (0.0011) -[2023-10-15 05:19:24,393][88298] Updated weights for policy 0, policy_version 75550 (0.0008) -[2023-10-15 05:19:27,346][88300] Updated weights for policy 1, policy_version 76002 (0.0010) -[2023-10-15 05:19:27,703][88300] Updated weights for policy 1, policy_version 76012 (0.0010) -[2023-10-15 05:19:28,076][88300] Updated weights for policy 1, policy_version 76022 (0.0008) -[2023-10-15 05:19:28,339][88298] Updated weights for policy 0, policy_version 75560 (0.0009) -[2023-10-15 05:19:28,439][88300] Updated weights for policy 1, policy_version 76032 (0.0007) -[2023-10-15 05:19:28,534][87330] Fps is (10 sec: 16383.6, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 155222016. Throughput: 0: 1751.0, 1: 1722.3. Samples: 38815722. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-15 05:19:28,535][87330] Avg episode reward: [(0, '22.490'), (1, '22.880')] -[2023-10-15 05:19:28,695][88298] Updated weights for policy 0, policy_version 75570 (0.0009) -[2023-10-15 05:19:29,076][88298] Updated weights for policy 0, policy_version 75580 (0.0008) -[2023-10-15 05:19:32,182][88300] Updated weights for policy 1, policy_version 76042 (0.0008) -[2023-10-15 05:19:32,551][88300] Updated weights for policy 1, policy_version 76052 (0.0008) -[2023-10-15 05:19:32,924][88300] Updated weights for policy 1, policy_version 76062 (0.0007) -[2023-10-15 05:19:33,228][88298] Updated weights for policy 0, policy_version 75590 (0.0009) -[2023-10-15 05:19:33,534][87330] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 155287552. Throughput: 0: 1719.0, 1: 1751.2. Samples: 38826284. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-15 05:19:33,535][87330] Avg episode reward: [(0, '22.580'), (1, '22.840')] -[2023-10-15 05:19:33,598][88298] Updated weights for policy 0, policy_version 75600 (0.0011) -[2023-10-15 05:19:33,961][88298] Updated weights for policy 0, policy_version 75610 (0.0010) -[2023-10-15 05:19:36,810][88300] Updated weights for policy 1, policy_version 76072 (0.0008) -[2023-10-15 05:19:37,172][88300] Updated weights for policy 1, policy_version 76082 (0.0007) -[2023-10-15 05:19:37,548][88300] Updated weights for policy 1, policy_version 76092 (0.0009) -[2023-10-15 05:19:38,067][88298] Updated weights for policy 0, policy_version 75620 (0.0010) -[2023-10-15 05:19:38,468][88298] Updated weights for policy 0, policy_version 75630 (0.0008) -[2023-10-15 05:19:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 155353088. Throughput: 0: 1744.0, 1: 1740.5. Samples: 38847006. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-15 05:19:38,535][87330] Avg episode reward: [(0, '22.530'), (1, '22.830')] -[2023-10-15 05:19:38,838][88298] Updated weights for policy 0, policy_version 75640 (0.0007) -[2023-10-15 05:19:41,634][88300] Updated weights for policy 1, policy_version 76102 (0.0009) -[2023-10-15 05:19:42,015][88300] Updated weights for policy 1, policy_version 76112 (0.0008) -[2023-10-15 05:19:42,385][88300] Updated weights for policy 1, policy_version 76122 (0.0009) -[2023-10-15 05:19:42,842][88298] Updated weights for policy 0, policy_version 75650 (0.0008) -[2023-10-15 05:19:43,206][88298] Updated weights for policy 0, policy_version 75660 (0.0007) -[2023-10-15 05:19:43,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 155418624. Throughput: 0: 1741.0, 1: 1723.7. Samples: 38867482. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-15 05:19:43,534][87330] Avg episode reward: [(0, '22.510'), (1, '22.860')] -[2023-10-15 05:19:43,575][88298] Updated weights for policy 0, policy_version 75670 (0.0010) -[2023-10-15 05:19:43,936][88298] Updated weights for policy 0, policy_version 75680 (0.0008) -[2023-10-15 05:19:46,362][88300] Updated weights for policy 1, policy_version 76132 (0.0010) -[2023-10-15 05:19:46,726][88300] Updated weights for policy 1, policy_version 76142 (0.0010) -[2023-10-15 05:19:47,095][88300] Updated weights for policy 1, policy_version 76152 (0.0009) -[2023-10-15 05:19:47,973][88298] Updated weights for policy 0, policy_version 75690 (0.0009) -[2023-10-15 05:19:48,348][88298] Updated weights for policy 0, policy_version 75700 (0.0011) -[2023-10-15 05:19:48,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 155484160. Throughput: 0: 1730.5, 1: 1757.1. Samples: 38878240. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-15 05:19:48,535][87330] Avg episode reward: [(0, '22.450'), (1, '22.820')] -[2023-10-15 05:19:48,713][88298] Updated weights for policy 0, policy_version 75710 (0.0007) -[2023-10-15 05:19:50,945][88300] Updated weights for policy 1, policy_version 76162 (0.0009) -[2023-10-15 05:19:51,309][88300] Updated weights for policy 1, policy_version 76172 (0.0008) -[2023-10-15 05:19:51,676][88300] Updated weights for policy 1, policy_version 76182 (0.0011) -[2023-10-15 05:19:52,036][88300] Updated weights for policy 1, policy_version 76192 (0.0010) -[2023-10-15 05:19:52,516][88298] Updated weights for policy 0, policy_version 75720 (0.0009) -[2023-10-15 05:19:52,886][88298] Updated weights for policy 0, policy_version 75730 (0.0009) -[2023-10-15 05:19:53,267][88298] Updated weights for policy 0, policy_version 75740 (0.0009) -[2023-10-15 05:19:53,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 155582464. Throughput: 0: 1734.4, 1: 1726.0. Samples: 38898256. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-15 05:19:53,535][87330] Avg episode reward: [(0, '22.490'), (1, '22.930')] -[2023-10-15 05:19:55,851][88300] Updated weights for policy 1, policy_version 76202 (0.0008) -[2023-10-15 05:19:56,211][88300] Updated weights for policy 1, policy_version 76212 (0.0008) -[2023-10-15 05:19:56,579][88300] Updated weights for policy 1, policy_version 76222 (0.0008) -[2023-10-15 05:19:57,233][88298] Updated weights for policy 0, policy_version 75750 (0.0009) -[2023-10-15 05:19:57,599][88298] Updated weights for policy 0, policy_version 75760 (0.0008) -[2023-10-15 05:19:57,976][88298] Updated weights for policy 0, policy_version 75770 (0.0007) -[2023-10-15 05:19:58,534][87330] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 155648000. Throughput: 0: 1710.0, 1: 1730.3. Samples: 38918996. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:19:58,534][87330] Avg episode reward: [(0, '22.660'), (1, '22.760')] -[2023-10-15 05:20:00,680][88300] Updated weights for policy 1, policy_version 76232 (0.0008) -[2023-10-15 05:20:01,042][88300] Updated weights for policy 1, policy_version 76242 (0.0008) -[2023-10-15 05:20:01,408][88300] Updated weights for policy 1, policy_version 76252 (0.0009) -[2023-10-15 05:20:01,837][88298] Updated weights for policy 0, policy_version 75780 (0.0007) -[2023-10-15 05:20:02,209][88298] Updated weights for policy 0, policy_version 75790 (0.0007) -[2023-10-15 05:20:02,583][88298] Updated weights for policy 0, policy_version 75800 (0.0007) -[2023-10-15 05:20:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 155713536. Throughput: 0: 1728.6, 1: 1743.3. Samples: 38929858. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:20:03,535][87330] Avg episode reward: [(0, '22.800'), (1, '22.690')] -[2023-10-15 05:20:05,181][88300] Updated weights for policy 1, policy_version 76262 (0.0008) -[2023-10-15 05:20:05,550][88300] Updated weights for policy 1, policy_version 76272 (0.0009) -[2023-10-15 05:20:05,923][88300] Updated weights for policy 1, policy_version 76282 (0.0008) -[2023-10-15 05:20:06,425][88298] Updated weights for policy 0, policy_version 75810 (0.0007) -[2023-10-15 05:20:06,793][88298] Updated weights for policy 0, policy_version 75820 (0.0009) -[2023-10-15 05:20:07,158][88298] Updated weights for policy 0, policy_version 75830 (0.0008) -[2023-10-15 05:20:07,529][88298] Updated weights for policy 0, policy_version 75840 (0.0008) -[2023-10-15 05:20:08,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13773.9). Total num frames: 155779072. Throughput: 0: 1718.8, 1: 1734.6. Samples: 38950654. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:20:08,534][87330] Avg episode reward: [(0, '22.860'), (1, '22.670')] -[2023-10-15 05:20:09,755][88300] Updated weights for policy 1, policy_version 76292 (0.0009) -[2023-10-15 05:20:10,118][88300] Updated weights for policy 1, policy_version 76302 (0.0007) -[2023-10-15 05:20:10,483][88300] Updated weights for policy 1, policy_version 76312 (0.0008) -[2023-10-15 05:20:11,457][88298] Updated weights for policy 0, policy_version 75850 (0.0009) -[2023-10-15 05:20:11,832][88298] Updated weights for policy 0, policy_version 75860 (0.0008) -[2023-10-15 05:20:12,205][88298] Updated weights for policy 0, policy_version 75870 (0.0009) -[2023-10-15 05:20:13,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 155844608. Throughput: 0: 1702.4, 1: 1760.6. Samples: 38971560. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:20:13,534][87330] Avg episode reward: [(0, '22.790'), (1, '22.580')] -[2023-10-15 05:20:14,270][88300] Updated weights for policy 1, policy_version 76322 (0.0007) -[2023-10-15 05:20:14,634][88300] Updated weights for policy 1, policy_version 76332 (0.0008) -[2023-10-15 05:20:15,008][88300] Updated weights for policy 1, policy_version 76342 (0.0009) -[2023-10-15 05:20:15,380][88300] Updated weights for policy 1, policy_version 76352 (0.0007) -[2023-10-15 05:20:16,065][88298] Updated weights for policy 0, policy_version 75880 (0.0009) -[2023-10-15 05:20:16,433][88298] Updated weights for policy 0, policy_version 75890 (0.0007) -[2023-10-15 05:20:16,804][88298] Updated weights for policy 0, policy_version 75900 (0.0010) -[2023-10-15 05:20:18,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 155910144. Throughput: 0: 1734.8, 1: 1734.3. Samples: 38982390. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:20:18,535][87330] Avg episode reward: [(0, '22.800'), (1, '22.580')] -[2023-10-15 05:20:19,060][88300] Updated weights for policy 1, policy_version 76362 (0.0010) -[2023-10-15 05:20:19,432][88300] Updated weights for policy 1, policy_version 76372 (0.0008) -[2023-10-15 05:20:19,795][88300] Updated weights for policy 1, policy_version 76382 (0.0007) -[2023-10-15 05:20:20,852][88298] Updated weights for policy 0, policy_version 75910 (0.0010) -[2023-10-15 05:20:21,212][88298] Updated weights for policy 0, policy_version 75920 (0.0008) -[2023-10-15 05:20:21,584][88298] Updated weights for policy 0, policy_version 75930 (0.0009) -[2023-10-15 05:20:23,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 155975680. Throughput: 0: 1706.3, 1: 1755.5. Samples: 39002786. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:20:23,535][87330] Avg episode reward: [(0, '22.770'), (1, '22.610')] -[2023-10-15 05:20:23,595][88300] Updated weights for policy 1, policy_version 76392 (0.0010) -[2023-10-15 05:20:23,965][88300] Updated weights for policy 1, policy_version 76402 (0.0009) -[2023-10-15 05:20:24,340][88300] Updated weights for policy 1, policy_version 76412 (0.0009) -[2023-10-15 05:20:25,470][88298] Updated weights for policy 0, policy_version 75940 (0.0008) -[2023-10-15 05:20:25,863][88298] Updated weights for policy 0, policy_version 75950 (0.0009) -[2023-10-15 05:20:26,227][88298] Updated weights for policy 0, policy_version 75960 (0.0009) -[2023-10-15 05:20:28,382][88300] Updated weights for policy 1, policy_version 76422 (0.0007) -[2023-10-15 05:20:28,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 156041216. Throughput: 0: 1706.4, 1: 1775.2. Samples: 39024158. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:20:28,535][87330] Avg episode reward: [(0, '22.760'), (1, '22.540')] -[2023-10-15 05:20:28,756][88300] Updated weights for policy 1, policy_version 76432 (0.0007) -[2023-10-15 05:20:29,121][88300] Updated weights for policy 1, policy_version 76442 (0.0008) -[2023-10-15 05:20:30,207][88298] Updated weights for policy 0, policy_version 75970 (0.0007) -[2023-10-15 05:20:30,570][88298] Updated weights for policy 0, policy_version 75980 (0.0007) -[2023-10-15 05:20:30,931][88298] Updated weights for policy 0, policy_version 75990 (0.0008) -[2023-10-15 05:20:31,302][88298] Updated weights for policy 0, policy_version 76000 (0.0011) -[2023-10-15 05:20:33,022][88300] Updated weights for policy 1, policy_version 76452 (0.0010) -[2023-10-15 05:20:33,394][88300] Updated weights for policy 1, policy_version 76462 (0.0011) -[2023-10-15 05:20:33,534][87330] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 156106752. Throughput: 0: 1724.0, 1: 1745.3. Samples: 39034360. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:20:33,535][87330] Avg episode reward: [(0, '22.760'), (1, '22.730')] -[2023-10-15 05:20:33,753][88300] Updated weights for policy 1, policy_version 76472 (0.0010) -[2023-10-15 05:20:35,041][88298] Updated weights for policy 0, policy_version 76010 (0.0008) -[2023-10-15 05:20:35,409][88298] Updated weights for policy 0, policy_version 76020 (0.0008) -[2023-10-15 05:20:35,773][88298] Updated weights for policy 0, policy_version 76030 (0.0008) -[2023-10-15 05:20:37,724][88300] Updated weights for policy 1, policy_version 76482 (0.0008) -[2023-10-15 05:20:38,084][88300] Updated weights for policy 1, policy_version 76492 (0.0008) -[2023-10-15 05:20:38,447][88300] Updated weights for policy 1, policy_version 76502 (0.0009) -[2023-10-15 05:20:38,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 156172288. Throughput: 0: 1715.1, 1: 1774.2. Samples: 39055272. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:20:38,535][87330] Avg episode reward: [(0, '22.750'), (1, '22.760')] -[2023-10-15 05:20:38,819][88300] Updated weights for policy 1, policy_version 76512 (0.0010) -[2023-10-15 05:20:39,762][88298] Updated weights for policy 0, policy_version 76040 (0.0008) -[2023-10-15 05:20:40,133][88298] Updated weights for policy 0, policy_version 76050 (0.0007) -[2023-10-15 05:20:40,506][88298] Updated weights for policy 0, policy_version 76060 (0.0009) -[2023-10-15 05:20:42,775][88300] Updated weights for policy 1, policy_version 76522 (0.0007) -[2023-10-15 05:20:43,153][88300] Updated weights for policy 1, policy_version 76532 (0.0008) -[2023-10-15 05:20:43,509][88300] Updated weights for policy 1, policy_version 76542 (0.0008) -[2023-10-15 05:20:43,534][87330] Fps is (10 sec: 13107.7, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 156237824. Throughput: 0: 1740.0, 1: 1753.9. Samples: 39076218. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:20:43,534][87330] Avg episode reward: [(0, '22.750'), (1, '22.890')] -[2023-10-15 05:20:44,269][88298] Updated weights for policy 0, policy_version 76070 (0.0008) -[2023-10-15 05:20:44,641][88298] Updated weights for policy 0, policy_version 76080 (0.0008) -[2023-10-15 05:20:45,018][88298] Updated weights for policy 0, policy_version 76090 (0.0007) -[2023-10-15 05:20:47,378][88300] Updated weights for policy 1, policy_version 76552 (0.0008) -[2023-10-15 05:20:47,734][88300] Updated weights for policy 1, policy_version 76562 (0.0009) -[2023-10-15 05:20:48,098][88300] Updated weights for policy 1, policy_version 76572 (0.0009) -[2023-10-15 05:20:48,534][87330] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 156336128. Throughput: 0: 1719.9, 1: 1762.9. Samples: 39086586. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:20:48,534][87330] Avg episode reward: [(0, '22.730'), (1, '22.790')] -[2023-10-15 05:20:48,967][88298] Updated weights for policy 0, policy_version 76100 (0.0007) -[2023-10-15 05:20:49,336][88298] Updated weights for policy 0, policy_version 76110 (0.0007) -[2023-10-15 05:20:49,712][88298] Updated weights for policy 0, policy_version 76120 (0.0009) -[2023-10-15 05:20:51,982][88300] Updated weights for policy 1, policy_version 76582 (0.0009) -[2023-10-15 05:20:52,352][88300] Updated weights for policy 1, policy_version 76592 (0.0007) -[2023-10-15 05:20:52,725][88300] Updated weights for policy 1, policy_version 76602 (0.0008) -[2023-10-15 05:20:53,534][87330] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 156401664. Throughput: 0: 1728.5, 1: 1756.9. Samples: 39107498. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-15 05:20:53,534][87330] Avg episode reward: [(0, '22.860'), (1, '22.570')] -[2023-10-15 05:20:53,566][88298] Updated weights for policy 0, policy_version 76130 (0.0008) -[2023-10-15 05:20:53,938][88298] Updated weights for policy 0, policy_version 76140 (0.0009) -[2023-10-15 05:20:54,304][88298] Updated weights for policy 0, policy_version 76150 (0.0009) -[2023-10-15 05:20:54,679][88298] Updated weights for policy 0, policy_version 76160 (0.0008) -[2023-10-15 05:20:56,525][88300] Updated weights for policy 1, policy_version 76612 (0.0009) -[2023-10-15 05:20:56,889][88300] Updated weights for policy 1, policy_version 76622 (0.0007) -[2023-10-15 05:20:57,259][88300] Updated weights for policy 1, policy_version 76632 (0.0008) -[2023-10-15 05:20:58,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 156467200. Throughput: 0: 1754.5, 1: 1728.2. Samples: 39128282. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-15 05:20:58,534][87330] Avg episode reward: [(0, '22.850'), (1, '22.420')] -[2023-10-15 05:20:58,542][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000076640_78479360.pth... -[2023-10-15 05:20:58,571][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000075008_76808192.pth -[2023-10-15 05:20:58,627][88298] Updated weights for policy 0, policy_version 76170 (0.0007) -[2023-10-15 05:20:58,996][88298] Updated weights for policy 0, policy_version 76180 (0.0007) -[2023-10-15 05:20:59,359][88298] Updated weights for policy 0, policy_version 76190 (0.0007) -[2023-10-15 05:20:59,431][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000076192_78020608.pth... -[2023-10-15 05:20:59,460][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000074560_76349440.pth -[2023-10-15 05:21:01,142][88300] Updated weights for policy 1, policy_version 76642 (0.0009) -[2023-10-15 05:21:01,502][88300] Updated weights for policy 1, policy_version 76652 (0.0010) -[2023-10-15 05:21:01,879][88300] Updated weights for policy 1, policy_version 76662 (0.0009) -[2023-10-15 05:21:02,247][88300] Updated weights for policy 1, policy_version 76672 (0.0008) -[2023-10-15 05:21:03,320][88298] Updated weights for policy 0, policy_version 76200 (0.0007) -[2023-10-15 05:21:03,534][87330] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 156532736. Throughput: 0: 1720.8, 1: 1755.2. Samples: 39138808. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-15 05:21:03,535][87330] Avg episode reward: [(0, '22.740'), (1, '22.610')] -[2023-10-15 05:21:03,684][88298] Updated weights for policy 0, policy_version 76210 (0.0009) -[2023-10-15 05:21:04,059][88298] Updated weights for policy 0, policy_version 76220 (0.0008) -[2023-10-15 05:21:06,076][88300] Updated weights for policy 1, policy_version 76682 (0.0009) -[2023-10-15 05:21:06,445][88300] Updated weights for policy 1, policy_version 76692 (0.0010) -[2023-10-15 05:21:06,804][88300] Updated weights for policy 1, policy_version 76702 (0.0010) -[2023-10-15 05:21:08,268][88298] Updated weights for policy 0, policy_version 76230 (0.0009) -[2023-10-15 05:21:08,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 156598272. Throughput: 0: 1752.8, 1: 1721.8. Samples: 39159142. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-15 05:21:08,534][87330] Avg episode reward: [(0, '22.730'), (1, '22.570')] -[2023-10-15 05:21:08,643][88298] Updated weights for policy 0, policy_version 76240 (0.0009) -[2023-10-15 05:21:09,018][88298] Updated weights for policy 0, policy_version 76250 (0.0007) -[2023-10-15 05:21:10,705][88300] Updated weights for policy 1, policy_version 76712 (0.0008) -[2023-10-15 05:21:11,065][88300] Updated weights for policy 1, policy_version 76722 (0.0008) -[2023-10-15 05:21:11,426][88300] Updated weights for policy 1, policy_version 76732 (0.0010) -[2023-10-15 05:21:12,890][88298] Updated weights for policy 0, policy_version 76260 (0.0007) -[2023-10-15 05:21:13,257][88298] Updated weights for policy 0, policy_version 76270 (0.0008) -[2023-10-15 05:21:13,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 156663808. Throughput: 0: 1761.5, 1: 1718.2. Samples: 39180744. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-15 05:21:13,534][87330] Avg episode reward: [(0, '22.810'), (1, '22.520')] -[2023-10-15 05:21:13,623][88298] Updated weights for policy 0, policy_version 76280 (0.0008) -[2023-10-15 05:21:15,591][88300] Updated weights for policy 1, policy_version 76742 (0.0009) -[2023-10-15 05:21:15,983][88300] Updated weights for policy 1, policy_version 76752 (0.0009) -[2023-10-15 05:21:16,352][88300] Updated weights for policy 1, policy_version 76762 (0.0009) -[2023-10-15 05:21:17,386][88298] Updated weights for policy 0, policy_version 76290 (0.0008) -[2023-10-15 05:21:17,761][88298] Updated weights for policy 0, policy_version 76300 (0.0008) -[2023-10-15 05:21:18,127][88298] Updated weights for policy 0, policy_version 76310 (0.0009) -[2023-10-15 05:21:18,495][88298] Updated weights for policy 0, policy_version 76320 (0.0008) -[2023-10-15 05:21:18,534][87330] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 156762112. Throughput: 0: 1747.7, 1: 1724.2. Samples: 39190598. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-15 05:21:18,535][87330] Avg episode reward: [(0, '22.830'), (1, '22.500')] -[2023-10-15 05:21:20,155][88300] Updated weights for policy 1, policy_version 76772 (0.0009) -[2023-10-15 05:21:20,520][88300] Updated weights for policy 1, policy_version 76782 (0.0008) -[2023-10-15 05:21:20,902][88300] Updated weights for policy 1, policy_version 76792 (0.0009) -[2023-10-15 05:21:22,282][88298] Updated weights for policy 0, policy_version 76330 (0.0008) -[2023-10-15 05:21:22,647][88298] Updated weights for policy 0, policy_version 76340 (0.0008) -[2023-10-15 05:21:23,025][88298] Updated weights for policy 0, policy_version 76350 (0.0008) -[2023-10-15 05:21:23,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 156827648. Throughput: 0: 1761.9, 1: 1718.5. Samples: 39211890. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-15 05:21:23,534][87330] Avg episode reward: [(0, '22.840'), (1, '22.660')] -[2023-10-15 05:21:24,702][88300] Updated weights for policy 1, policy_version 76802 (0.0008) -[2023-10-15 05:21:25,076][88300] Updated weights for policy 1, policy_version 76812 (0.0008) -[2023-10-15 05:21:25,450][88300] Updated weights for policy 1, policy_version 76822 (0.0009) -[2023-10-15 05:21:25,826][88300] Updated weights for policy 1, policy_version 76832 (0.0008) -[2023-10-15 05:21:26,855][88298] Updated weights for policy 0, policy_version 76360 (0.0008) -[2023-10-15 05:21:27,232][88298] Updated weights for policy 0, policy_version 76370 (0.0007) -[2023-10-15 05:21:27,590][88298] Updated weights for policy 0, policy_version 76380 (0.0007) -[2023-10-15 05:21:28,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 156893184. Throughput: 0: 1727.8, 1: 1739.9. Samples: 39232264. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-15 05:21:28,534][87330] Avg episode reward: [(0, '22.870'), (1, '22.650')] -[2023-10-15 05:21:29,646][88300] Updated weights for policy 1, policy_version 76842 (0.0007) -[2023-10-15 05:21:30,012][88300] Updated weights for policy 1, policy_version 76852 (0.0007) -[2023-10-15 05:21:30,377][88300] Updated weights for policy 1, policy_version 76862 (0.0007) -[2023-10-15 05:21:31,519][88298] Updated weights for policy 0, policy_version 76390 (0.0009) -[2023-10-15 05:21:31,898][88298] Updated weights for policy 0, policy_version 76400 (0.0007) -[2023-10-15 05:21:32,268][88298] Updated weights for policy 0, policy_version 76410 (0.0009) -[2023-10-15 05:21:33,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 156958720. Throughput: 0: 1755.2, 1: 1721.2. Samples: 39243024. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-15 05:21:33,535][87330] Avg episode reward: [(0, '22.760'), (1, '22.830')] -[2023-10-15 05:21:34,403][88300] Updated weights for policy 1, policy_version 76872 (0.0007) -[2023-10-15 05:21:34,771][88300] Updated weights for policy 1, policy_version 76882 (0.0009) -[2023-10-15 05:21:35,144][88300] Updated weights for policy 1, policy_version 76892 (0.0009) -[2023-10-15 05:21:36,332][88298] Updated weights for policy 0, policy_version 76420 (0.0008) -[2023-10-15 05:21:36,702][88298] Updated weights for policy 0, policy_version 76430 (0.0008) -[2023-10-15 05:21:37,067][88298] Updated weights for policy 0, policy_version 76440 (0.0007) -[2023-10-15 05:21:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 157024256. Throughput: 0: 1738.1, 1: 1736.0. Samples: 39263836. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-15 05:21:38,534][87330] Avg episode reward: [(0, '22.880'), (1, '22.880')] -[2023-10-15 05:21:39,017][88300] Updated weights for policy 1, policy_version 76902 (0.0007) -[2023-10-15 05:21:39,383][88300] Updated weights for policy 1, policy_version 76912 (0.0009) -[2023-10-15 05:21:39,757][88300] Updated weights for policy 1, policy_version 76922 (0.0011) -[2023-10-15 05:21:40,790][88298] Updated weights for policy 0, policy_version 76450 (0.0008) -[2023-10-15 05:21:41,156][88298] Updated weights for policy 0, policy_version 76460 (0.0009) -[2023-10-15 05:21:41,531][88298] Updated weights for policy 0, policy_version 76470 (0.0008) -[2023-10-15 05:21:41,903][88298] Updated weights for policy 0, policy_version 76480 (0.0007) -[2023-10-15 05:21:43,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 157089792. Throughput: 0: 1724.3, 1: 1757.2. Samples: 39284946. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-15 05:21:43,535][87330] Avg episode reward: [(0, '22.780'), (1, '22.910')] -[2023-10-15 05:21:43,613][88300] Updated weights for policy 1, policy_version 76932 (0.0010) -[2023-10-15 05:21:43,979][88300] Updated weights for policy 1, policy_version 76942 (0.0009) -[2023-10-15 05:21:44,338][88300] Updated weights for policy 1, policy_version 76952 (0.0007) -[2023-10-15 05:21:45,853][88298] Updated weights for policy 0, policy_version 76490 (0.0009) -[2023-10-15 05:21:46,224][88298] Updated weights for policy 0, policy_version 76500 (0.0007) -[2023-10-15 05:21:46,592][88298] Updated weights for policy 0, policy_version 76510 (0.0007) -[2023-10-15 05:21:48,254][88300] Updated weights for policy 1, policy_version 76962 (0.0008) -[2023-10-15 05:21:48,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 157155328. Throughput: 0: 1749.8, 1: 1730.6. Samples: 39295428. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-15 05:21:48,535][87330] Avg episode reward: [(0, '22.760'), (1, '22.990')] -[2023-10-15 05:21:48,613][88300] Updated weights for policy 1, policy_version 76972 (0.0011) -[2023-10-15 05:21:48,969][88300] Updated weights for policy 1, policy_version 76982 (0.0011) -[2023-10-15 05:21:49,340][88300] Updated weights for policy 1, policy_version 76992 (0.0011) -[2023-10-15 05:21:50,592][88298] Updated weights for policy 0, policy_version 76520 (0.0010) -[2023-10-15 05:21:50,965][88298] Updated weights for policy 0, policy_version 76530 (0.0009) -[2023-10-15 05:21:51,336][88298] Updated weights for policy 0, policy_version 76540 (0.0008) -[2023-10-15 05:21:53,233][88300] Updated weights for policy 1, policy_version 77002 (0.0008) -[2023-10-15 05:21:53,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 157220864. Throughput: 0: 1720.4, 1: 1755.6. Samples: 39315562. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-15 05:21:53,534][87330] Avg episode reward: [(0, '22.760'), (1, '22.940')] -[2023-10-15 05:21:53,592][88300] Updated weights for policy 1, policy_version 77012 (0.0010) -[2023-10-15 05:21:53,969][88300] Updated weights for policy 1, policy_version 77022 (0.0010) -[2023-10-15 05:21:55,229][88298] Updated weights for policy 0, policy_version 76550 (0.0007) -[2023-10-15 05:21:55,595][88298] Updated weights for policy 0, policy_version 76560 (0.0008) -[2023-10-15 05:21:55,959][88298] Updated weights for policy 0, policy_version 76570 (0.0009) -[2023-10-15 05:21:57,798][88300] Updated weights for policy 1, policy_version 77032 (0.0009) -[2023-10-15 05:21:58,161][88300] Updated weights for policy 1, policy_version 77042 (0.0010) -[2023-10-15 05:21:58,522][88300] Updated weights for policy 1, policy_version 77052 (0.0011) -[2023-10-15 05:21:58,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 157286400. Throughput: 0: 1717.2, 1: 1741.1. Samples: 39336368. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-15 05:21:58,534][87330] Avg episode reward: [(0, '22.750'), (1, '22.960')] -[2023-10-15 05:21:59,902][88298] Updated weights for policy 0, policy_version 76580 (0.0007) -[2023-10-15 05:22:00,290][88298] Updated weights for policy 0, policy_version 76590 (0.0008) -[2023-10-15 05:22:00,667][88298] Updated weights for policy 0, policy_version 76600 (0.0008) -[2023-10-15 05:22:02,433][88300] Updated weights for policy 1, policy_version 77062 (0.0009) -[2023-10-15 05:22:02,803][88300] Updated weights for policy 1, policy_version 77072 (0.0010) -[2023-10-15 05:22:03,173][88300] Updated weights for policy 1, policy_version 77082 (0.0008) -[2023-10-15 05:22:03,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 157384704. Throughput: 0: 1721.2, 1: 1754.3. Samples: 39346996. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-15 05:22:03,534][87330] Avg episode reward: [(0, '22.860'), (1, '22.970')] -[2023-10-15 05:22:04,487][88298] Updated weights for policy 0, policy_version 76610 (0.0009) -[2023-10-15 05:22:04,861][88298] Updated weights for policy 0, policy_version 76620 (0.0008) -[2023-10-15 05:22:05,240][88298] Updated weights for policy 0, policy_version 76630 (0.0008) -[2023-10-15 05:22:05,603][88298] Updated weights for policy 0, policy_version 76640 (0.0007) -[2023-10-15 05:22:07,025][88300] Updated weights for policy 1, policy_version 77092 (0.0009) -[2023-10-15 05:22:07,388][88300] Updated weights for policy 1, policy_version 77102 (0.0008) -[2023-10-15 05:22:07,755][88300] Updated weights for policy 1, policy_version 77112 (0.0008) -[2023-10-15 05:22:08,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 157450240. Throughput: 0: 1713.1, 1: 1757.0. Samples: 39368044. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-15 05:22:08,534][87330] Avg episode reward: [(0, '22.850'), (1, '22.940')] -[2023-10-15 05:22:09,319][88298] Updated weights for policy 0, policy_version 76650 (0.0008) -[2023-10-15 05:22:09,689][88298] Updated weights for policy 0, policy_version 76660 (0.0008) -[2023-10-15 05:22:10,060][88298] Updated weights for policy 0, policy_version 76670 (0.0008) -[2023-10-15 05:22:11,698][88300] Updated weights for policy 1, policy_version 77122 (0.0008) -[2023-10-15 05:22:12,065][88300] Updated weights for policy 1, policy_version 77132 (0.0007) -[2023-10-15 05:22:12,428][88300] Updated weights for policy 1, policy_version 77142 (0.0010) -[2023-10-15 05:22:12,797][88300] Updated weights for policy 1, policy_version 77152 (0.0008) -[2023-10-15 05:22:13,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 157515776. Throughput: 0: 1751.9, 1: 1732.4. Samples: 39389056. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-15 05:22:13,534][87330] Avg episode reward: [(0, '22.990'), (1, '22.810')] -[2023-10-15 05:22:13,981][88298] Updated weights for policy 0, policy_version 76680 (0.0010) -[2023-10-15 05:22:14,342][88298] Updated weights for policy 0, policy_version 76690 (0.0008) -[2023-10-15 05:22:14,709][88298] Updated weights for policy 0, policy_version 76700 (0.0007) -[2023-10-15 05:22:16,653][88300] Updated weights for policy 1, policy_version 77162 (0.0010) -[2023-10-15 05:22:17,022][88300] Updated weights for policy 1, policy_version 77172 (0.0008) -[2023-10-15 05:22:17,392][88300] Updated weights for policy 1, policy_version 77182 (0.0007) -[2023-10-15 05:22:18,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 157581312. Throughput: 0: 1721.8, 1: 1764.2. Samples: 39399894. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-15 05:22:18,535][87330] Avg episode reward: [(0, '22.980'), (1, '22.810')] -[2023-10-15 05:22:18,636][88298] Updated weights for policy 0, policy_version 76710 (0.0007) -[2023-10-15 05:22:19,010][88298] Updated weights for policy 0, policy_version 76720 (0.0011) -[2023-10-15 05:22:19,388][88298] Updated weights for policy 0, policy_version 76730 (0.0011) -[2023-10-15 05:22:21,326][88300] Updated weights for policy 1, policy_version 77192 (0.0009) -[2023-10-15 05:22:21,694][88300] Updated weights for policy 1, policy_version 77202 (0.0010) -[2023-10-15 05:22:22,056][88300] Updated weights for policy 1, policy_version 77212 (0.0011) -[2023-10-15 05:22:23,327][88298] Updated weights for policy 0, policy_version 76740 (0.0009) -[2023-10-15 05:22:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 157646848. Throughput: 0: 1741.2, 1: 1729.6. Samples: 39420024. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-15 05:22:23,534][87330] Avg episode reward: [(0, '22.920'), (1, '22.820')] -[2023-10-15 05:22:23,700][88298] Updated weights for policy 0, policy_version 76750 (0.0008) -[2023-10-15 05:22:24,063][88298] Updated weights for policy 0, policy_version 76760 (0.0009) -[2023-10-15 05:22:26,061][88300] Updated weights for policy 1, policy_version 77222 (0.0008) -[2023-10-15 05:22:26,425][88300] Updated weights for policy 1, policy_version 77232 (0.0009) -[2023-10-15 05:22:26,795][88300] Updated weights for policy 1, policy_version 77242 (0.0007) -[2023-10-15 05:22:28,158][88298] Updated weights for policy 0, policy_version 76770 (0.0009) -[2023-10-15 05:22:28,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 157712384. Throughput: 0: 1745.2, 1: 1730.3. Samples: 39441344. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-15 05:22:28,535][87330] Avg episode reward: [(0, '22.920'), (1, '22.800')] -[2023-10-15 05:22:28,538][88298] Updated weights for policy 0, policy_version 76780 (0.0007) -[2023-10-15 05:22:28,906][88298] Updated weights for policy 0, policy_version 76790 (0.0009) -[2023-10-15 05:22:29,280][88298] Updated weights for policy 0, policy_version 76800 (0.0009) -[2023-10-15 05:22:30,643][88300] Updated weights for policy 1, policy_version 77252 (0.0010) -[2023-10-15 05:22:31,018][88300] Updated weights for policy 1, policy_version 77262 (0.0008) -[2023-10-15 05:22:31,389][88300] Updated weights for policy 1, policy_version 77272 (0.0009) -[2023-10-15 05:22:33,177][88298] Updated weights for policy 0, policy_version 76810 (0.0008) -[2023-10-15 05:22:33,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 157777920. Throughput: 0: 1719.0, 1: 1744.3. Samples: 39451276. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:22:33,534][87330] Avg episode reward: [(0, '22.910'), (1, '22.790')] -[2023-10-15 05:22:33,554][88298] Updated weights for policy 0, policy_version 76820 (0.0007) -[2023-10-15 05:22:33,914][88298] Updated weights for policy 0, policy_version 76830 (0.0008) -[2023-10-15 05:22:35,366][88300] Updated weights for policy 1, policy_version 77282 (0.0009) -[2023-10-15 05:22:35,740][88300] Updated weights for policy 1, policy_version 77292 (0.0010) -[2023-10-15 05:22:36,114][88300] Updated weights for policy 1, policy_version 77302 (0.0008) -[2023-10-15 05:22:36,474][88300] Updated weights for policy 1, policy_version 77312 (0.0009) -[2023-10-15 05:22:37,904][88298] Updated weights for policy 0, policy_version 76840 (0.0009) -[2023-10-15 05:22:38,278][88298] Updated weights for policy 0, policy_version 76850 (0.0008) -[2023-10-15 05:22:38,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 157843456. Throughput: 0: 1743.9, 1: 1732.4. Samples: 39471994. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:22:38,534][87330] Avg episode reward: [(0, '22.900'), (1, '22.770')] -[2023-10-15 05:22:38,654][88298] Updated weights for policy 0, policy_version 76860 (0.0007) -[2023-10-15 05:22:40,466][88300] Updated weights for policy 1, policy_version 77322 (0.0008) -[2023-10-15 05:22:40,825][88300] Updated weights for policy 1, policy_version 77332 (0.0009) -[2023-10-15 05:22:41,198][88300] Updated weights for policy 1, policy_version 77342 (0.0009) -[2023-10-15 05:22:42,568][88298] Updated weights for policy 0, policy_version 76870 (0.0008) -[2023-10-15 05:22:42,930][88298] Updated weights for policy 0, policy_version 76880 (0.0010) -[2023-10-15 05:22:43,294][88298] Updated weights for policy 0, policy_version 76890 (0.0009) -[2023-10-15 05:22:43,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 157941760. Throughput: 0: 1731.6, 1: 1746.6. Samples: 39492888. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:22:43,535][87330] Avg episode reward: [(0, '22.880'), (1, '22.950')] -[2023-10-15 05:22:44,961][88300] Updated weights for policy 1, policy_version 77352 (0.0009) -[2023-10-15 05:22:45,327][88300] Updated weights for policy 1, policy_version 77362 (0.0009) -[2023-10-15 05:22:45,689][88300] Updated weights for policy 1, policy_version 77372 (0.0008) -[2023-10-15 05:22:47,474][88298] Updated weights for policy 0, policy_version 76900 (0.0010) -[2023-10-15 05:22:47,863][88298] Updated weights for policy 0, policy_version 76910 (0.0009) -[2023-10-15 05:22:48,228][88298] Updated weights for policy 0, policy_version 76920 (0.0008) -[2023-10-15 05:22:48,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 158007296. Throughput: 0: 1735.5, 1: 1727.0. Samples: 39502808. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:22:48,534][87330] Avg episode reward: [(0, '22.880'), (1, '22.920')] -[2023-10-15 05:22:49,659][88300] Updated weights for policy 1, policy_version 77382 (0.0009) -[2023-10-15 05:22:50,045][88300] Updated weights for policy 1, policy_version 77392 (0.0009) -[2023-10-15 05:22:50,417][88300] Updated weights for policy 1, policy_version 77402 (0.0009) -[2023-10-15 05:22:52,124][88298] Updated weights for policy 0, policy_version 76930 (0.0009) -[2023-10-15 05:22:52,507][88298] Updated weights for policy 0, policy_version 76940 (0.0009) -[2023-10-15 05:22:52,874][88298] Updated weights for policy 0, policy_version 76950 (0.0009) -[2023-10-15 05:22:53,241][88298] Updated weights for policy 0, policy_version 76960 (0.0008) -[2023-10-15 05:22:53,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 158072832. Throughput: 0: 1739.2, 1: 1729.1. Samples: 39524122. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:22:53,535][87330] Avg episode reward: [(0, '22.900'), (1, '22.930')] -[2023-10-15 05:22:54,104][88300] Updated weights for policy 1, policy_version 77412 (0.0007) -[2023-10-15 05:22:54,474][88300] Updated weights for policy 1, policy_version 77422 (0.0007) -[2023-10-15 05:22:54,846][88300] Updated weights for policy 1, policy_version 77432 (0.0009) -[2023-10-15 05:22:57,055][88298] Updated weights for policy 0, policy_version 76970 (0.0010) -[2023-10-15 05:22:57,425][88298] Updated weights for policy 0, policy_version 76980 (0.0009) -[2023-10-15 05:22:57,797][88298] Updated weights for policy 0, policy_version 76990 (0.0008) -[2023-10-15 05:22:58,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 158138368. Throughput: 0: 1700.1, 1: 1758.5. Samples: 39544696. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:22:58,535][87330] Avg episode reward: [(0, '22.840'), (1, '23.120')] -[2023-10-15 05:22:58,545][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000076992_78839808.pth... -[2023-10-15 05:22:58,580][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000075360_77168640.pth -[2023-10-15 05:22:58,662][88300] Updated weights for policy 1, policy_version 77442 (0.0008) -[2023-10-15 05:22:59,024][88300] Updated weights for policy 1, policy_version 77452 (0.0007) -[2023-10-15 05:22:59,394][88300] Updated weights for policy 1, policy_version 77462 (0.0007) -[2023-10-15 05:22:59,759][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000077472_79331328.pth... -[2023-10-15 05:22:59,761][88300] Updated weights for policy 1, policy_version 77472 (0.0008) -[2023-10-15 05:22:59,788][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000075808_77627392.pth -[2023-10-15 05:23:01,698][88298] Updated weights for policy 0, policy_version 77000 (0.0007) -[2023-10-15 05:23:02,073][88298] Updated weights for policy 0, policy_version 77010 (0.0007) -[2023-10-15 05:23:02,441][88298] Updated weights for policy 0, policy_version 77020 (0.0007) -[2023-10-15 05:23:03,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13995.8). Total num frames: 158203904. Throughput: 0: 1731.9, 1: 1724.9. Samples: 39555452. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:23:03,534][87330] Avg episode reward: [(0, '22.810'), (1, '22.960')] -[2023-10-15 05:23:03,798][88300] Updated weights for policy 1, policy_version 77482 (0.0010) -[2023-10-15 05:23:04,168][88300] Updated weights for policy 1, policy_version 77492 (0.0009) -[2023-10-15 05:23:04,526][88300] Updated weights for policy 1, policy_version 77502 (0.0010) -[2023-10-15 05:23:06,227][88298] Updated weights for policy 0, policy_version 77030 (0.0010) -[2023-10-15 05:23:06,600][88298] Updated weights for policy 0, policy_version 77040 (0.0007) -[2023-10-15 05:23:06,976][88298] Updated weights for policy 0, policy_version 77050 (0.0008) -[2023-10-15 05:23:08,412][88300] Updated weights for policy 1, policy_version 77512 (0.0008) -[2023-10-15 05:23:08,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 158269440. Throughput: 0: 1714.5, 1: 1753.6. Samples: 39576090. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:23:08,535][87330] Avg episode reward: [(0, '22.830'), (1, '22.580')] -[2023-10-15 05:23:08,780][88300] Updated weights for policy 1, policy_version 77522 (0.0007) -[2023-10-15 05:23:09,145][88300] Updated weights for policy 1, policy_version 77532 (0.0007) -[2023-10-15 05:23:10,878][88298] Updated weights for policy 0, policy_version 77060 (0.0007) -[2023-10-15 05:23:11,251][88298] Updated weights for policy 0, policy_version 77070 (0.0009) -[2023-10-15 05:23:11,618][88298] Updated weights for policy 0, policy_version 77080 (0.0010) -[2023-10-15 05:23:13,090][88300] Updated weights for policy 1, policy_version 77542 (0.0008) -[2023-10-15 05:23:13,453][88300] Updated weights for policy 1, policy_version 77552 (0.0008) -[2023-10-15 05:23:13,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 158334976. Throughput: 0: 1714.0, 1: 1748.5. Samples: 39597160. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:23:13,534][87330] Avg episode reward: [(0, '22.820'), (1, '22.550')] -[2023-10-15 05:23:13,816][88300] Updated weights for policy 1, policy_version 77562 (0.0009) -[2023-10-15 05:23:15,423][88298] Updated weights for policy 0, policy_version 77090 (0.0010) -[2023-10-15 05:23:15,802][88298] Updated weights for policy 0, policy_version 77100 (0.0007) -[2023-10-15 05:23:16,168][88298] Updated weights for policy 0, policy_version 77110 (0.0008) -[2023-10-15 05:23:16,531][88298] Updated weights for policy 0, policy_version 77120 (0.0008) -[2023-10-15 05:23:17,730][88300] Updated weights for policy 1, policy_version 77572 (0.0009) -[2023-10-15 05:23:18,104][88300] Updated weights for policy 1, policy_version 77582 (0.0008) -[2023-10-15 05:23:18,462][88300] Updated weights for policy 1, policy_version 77592 (0.0008) -[2023-10-15 05:23:18,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 158400512. Throughput: 0: 1739.6, 1: 1742.0. Samples: 39607948. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:23:18,534][87330] Avg episode reward: [(0, '22.780'), (1, '22.320')] -[2023-10-15 05:23:20,501][88298] Updated weights for policy 0, policy_version 77130 (0.0008) -[2023-10-15 05:23:20,864][88298] Updated weights for policy 0, policy_version 77140 (0.0009) -[2023-10-15 05:23:21,238][88298] Updated weights for policy 0, policy_version 77150 (0.0009) -[2023-10-15 05:23:22,098][88300] Updated weights for policy 1, policy_version 77602 (0.0007) -[2023-10-15 05:23:22,470][88300] Updated weights for policy 1, policy_version 77612 (0.0007) -[2023-10-15 05:23:22,839][88300] Updated weights for policy 1, policy_version 77622 (0.0008) -[2023-10-15 05:23:23,207][88300] Updated weights for policy 1, policy_version 77632 (0.0007) -[2023-10-15 05:23:23,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 158498816. Throughput: 0: 1722.7, 1: 1761.0. Samples: 39628762. Policy #0 lag: (min: 10.0, avg: 12.6, max: 42.0) -[2023-10-15 05:23:23,535][87330] Avg episode reward: [(0, '22.670'), (1, '22.260')] -[2023-10-15 05:23:25,095][88298] Updated weights for policy 0, policy_version 77160 (0.0008) -[2023-10-15 05:23:25,470][88298] Updated weights for policy 0, policy_version 77170 (0.0010) -[2023-10-15 05:23:25,836][88298] Updated weights for policy 0, policy_version 77180 (0.0008) -[2023-10-15 05:23:27,066][88300] Updated weights for policy 1, policy_version 77642 (0.0007) -[2023-10-15 05:23:27,431][88300] Updated weights for policy 1, policy_version 77652 (0.0008) -[2023-10-15 05:23:27,798][88300] Updated weights for policy 1, policy_version 77662 (0.0008) -[2023-10-15 05:23:28,534][87330] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 158564352. Throughput: 0: 1732.6, 1: 1740.6. Samples: 39649182. Policy #0 lag: (min: 10.0, avg: 12.6, max: 42.0) -[2023-10-15 05:23:28,535][87330] Avg episode reward: [(0, '22.680'), (1, '22.210')] -[2023-10-15 05:23:29,714][88298] Updated weights for policy 0, policy_version 77190 (0.0007) -[2023-10-15 05:23:30,092][88298] Updated weights for policy 0, policy_version 77200 (0.0007) -[2023-10-15 05:23:30,461][88298] Updated weights for policy 0, policy_version 77210 (0.0008) -[2023-10-15 05:23:31,742][88300] Updated weights for policy 1, policy_version 77672 (0.0009) -[2023-10-15 05:23:32,108][88300] Updated weights for policy 1, policy_version 77682 (0.0008) -[2023-10-15 05:23:32,475][88300] Updated weights for policy 1, policy_version 77692 (0.0008) -[2023-10-15 05:23:33,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 158629888. Throughput: 0: 1723.2, 1: 1769.4. Samples: 39659976. Policy #0 lag: (min: 10.0, avg: 12.6, max: 42.0) -[2023-10-15 05:23:33,534][87330] Avg episode reward: [(0, '22.830'), (1, '22.040')] -[2023-10-15 05:23:34,470][88298] Updated weights for policy 0, policy_version 77220 (0.0009) -[2023-10-15 05:23:34,832][88298] Updated weights for policy 0, policy_version 77230 (0.0011) -[2023-10-15 05:23:35,197][88298] Updated weights for policy 0, policy_version 77240 (0.0009) -[2023-10-15 05:23:36,437][88300] Updated weights for policy 1, policy_version 77702 (0.0009) -[2023-10-15 05:23:36,812][88300] Updated weights for policy 1, policy_version 77712 (0.0009) -[2023-10-15 05:23:37,182][88300] Updated weights for policy 1, policy_version 77722 (0.0008) -[2023-10-15 05:23:38,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 158695424. Throughput: 0: 1724.3, 1: 1748.5. Samples: 39680400. Policy #0 lag: (min: 10.0, avg: 12.6, max: 42.0) -[2023-10-15 05:23:38,535][87330] Avg episode reward: [(0, '22.860'), (1, '22.180')] -[2023-10-15 05:23:39,172][88298] Updated weights for policy 0, policy_version 77250 (0.0008) -[2023-10-15 05:23:39,552][88298] Updated weights for policy 0, policy_version 77260 (0.0008) -[2023-10-15 05:23:39,924][88298] Updated weights for policy 0, policy_version 77270 (0.0010) -[2023-10-15 05:23:40,300][88298] Updated weights for policy 0, policy_version 77280 (0.0010) -[2023-10-15 05:23:41,079][88300] Updated weights for policy 1, policy_version 77732 (0.0010) -[2023-10-15 05:23:41,449][88300] Updated weights for policy 1, policy_version 77742 (0.0011) -[2023-10-15 05:23:41,820][88300] Updated weights for policy 1, policy_version 77752 (0.0007) -[2023-10-15 05:23:43,534][87330] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 158760960. Throughput: 0: 1753.6, 1: 1736.0. Samples: 39701724. Policy #0 lag: (min: 10.0, avg: 12.6, max: 42.0) -[2023-10-15 05:23:43,535][87330] Avg episode reward: [(0, '22.860'), (1, '22.200')] -[2023-10-15 05:23:44,176][88298] Updated weights for policy 0, policy_version 77290 (0.0009) -[2023-10-15 05:23:44,550][88298] Updated weights for policy 0, policy_version 77300 (0.0007) -[2023-10-15 05:23:44,922][88298] Updated weights for policy 0, policy_version 77310 (0.0010) -[2023-10-15 05:23:45,612][88300] Updated weights for policy 1, policy_version 77762 (0.0009) -[2023-10-15 05:23:45,978][88300] Updated weights for policy 1, policy_version 77772 (0.0007) -[2023-10-15 05:23:46,357][88300] Updated weights for policy 1, policy_version 77782 (0.0007) -[2023-10-15 05:23:46,719][88300] Updated weights for policy 1, policy_version 77792 (0.0008) -[2023-10-15 05:23:48,534][87330] Fps is (10 sec: 13107.8, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 158826496. Throughput: 0: 1723.2, 1: 1754.7. Samples: 39711954. Policy #0 lag: (min: 10.0, avg: 12.6, max: 42.0) -[2023-10-15 05:23:48,534][87330] Avg episode reward: [(0, '22.800'), (1, '22.400')] -[2023-10-15 05:23:48,785][88298] Updated weights for policy 0, policy_version 77320 (0.0007) -[2023-10-15 05:23:49,159][88298] Updated weights for policy 0, policy_version 77330 (0.0007) -[2023-10-15 05:23:49,540][88298] Updated weights for policy 0, policy_version 77340 (0.0009) -[2023-10-15 05:23:50,562][88300] Updated weights for policy 1, policy_version 77802 (0.0010) -[2023-10-15 05:23:50,939][88300] Updated weights for policy 1, policy_version 77812 (0.0007) -[2023-10-15 05:23:51,302][88300] Updated weights for policy 1, policy_version 77822 (0.0010) -[2023-10-15 05:23:53,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 158892032. Throughput: 0: 1739.4, 1: 1743.3. Samples: 39732810. Policy #0 lag: (min: 10.0, avg: 12.6, max: 42.0) -[2023-10-15 05:23:53,534][87330] Avg episode reward: [(0, '22.890'), (1, '22.400')] -[2023-10-15 05:23:53,579][88298] Updated weights for policy 0, policy_version 77350 (0.0011) -[2023-10-15 05:23:53,951][88298] Updated weights for policy 0, policy_version 77360 (0.0009) -[2023-10-15 05:23:54,324][88298] Updated weights for policy 0, policy_version 77370 (0.0009) -[2023-10-15 05:23:55,174][88300] Updated weights for policy 1, policy_version 77832 (0.0008) -[2023-10-15 05:23:55,544][88300] Updated weights for policy 1, policy_version 77842 (0.0010) -[2023-10-15 05:23:55,902][88300] Updated weights for policy 1, policy_version 77852 (0.0008) -[2023-10-15 05:23:58,114][88298] Updated weights for policy 0, policy_version 77380 (0.0009) -[2023-10-15 05:23:58,488][88298] Updated weights for policy 0, policy_version 77390 (0.0009) -[2023-10-15 05:23:58,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 158957568. Throughput: 0: 1746.0, 1: 1753.9. Samples: 39754658. Policy #0 lag: (min: 10.0, avg: 12.6, max: 42.0) -[2023-10-15 05:23:58,534][87330] Avg episode reward: [(0, '22.930'), (1, '22.360')] -[2023-10-15 05:23:58,863][88298] Updated weights for policy 0, policy_version 77400 (0.0010) -[2023-10-15 05:23:59,814][88300] Updated weights for policy 1, policy_version 77862 (0.0009) -[2023-10-15 05:24:00,189][88300] Updated weights for policy 1, policy_version 77872 (0.0010) -[2023-10-15 05:24:00,544][88300] Updated weights for policy 1, policy_version 77882 (0.0010) -[2023-10-15 05:24:02,736][88298] Updated weights for policy 0, policy_version 77410 (0.0008) -[2023-10-15 05:24:03,094][88298] Updated weights for policy 0, policy_version 77420 (0.0009) -[2023-10-15 05:24:03,468][88298] Updated weights for policy 0, policy_version 77430 (0.0007) -[2023-10-15 05:24:03,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 159023104. Throughput: 0: 1723.8, 1: 1748.7. Samples: 39764210. Policy #0 lag: (min: 10.0, avg: 12.6, max: 42.0) -[2023-10-15 05:24:03,535][87330] Avg episode reward: [(0, '22.910'), (1, '22.690')] -[2023-10-15 05:24:03,830][88298] Updated weights for policy 0, policy_version 77440 (0.0008) -[2023-10-15 05:24:04,464][88300] Updated weights for policy 1, policy_version 77892 (0.0010) -[2023-10-15 05:24:04,830][88300] Updated weights for policy 1, policy_version 77902 (0.0009) -[2023-10-15 05:24:05,185][88300] Updated weights for policy 1, policy_version 77912 (0.0007) -[2023-10-15 05:24:07,766][88298] Updated weights for policy 0, policy_version 77450 (0.0007) -[2023-10-15 05:24:08,135][88298] Updated weights for policy 0, policy_version 77460 (0.0007) -[2023-10-15 05:24:08,502][88298] Updated weights for policy 0, policy_version 77470 (0.0007) -[2023-10-15 05:24:08,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 159088640. Throughput: 0: 1748.1, 1: 1741.1. Samples: 39785774. Policy #0 lag: (min: 10.0, avg: 12.6, max: 42.0) -[2023-10-15 05:24:08,534][87330] Avg episode reward: [(0, '22.850'), (1, '22.360')] -[2023-10-15 05:24:08,995][88300] Updated weights for policy 1, policy_version 77922 (0.0008) -[2023-10-15 05:24:09,354][88300] Updated weights for policy 1, policy_version 77932 (0.0007) -[2023-10-15 05:24:09,720][88300] Updated weights for policy 1, policy_version 77942 (0.0007) -[2023-10-15 05:24:10,080][88300] Updated weights for policy 1, policy_version 77952 (0.0008) -[2023-10-15 05:24:12,242][88298] Updated weights for policy 0, policy_version 77480 (0.0009) -[2023-10-15 05:24:12,610][88298] Updated weights for policy 0, policy_version 77490 (0.0007) -[2023-10-15 05:24:12,980][88298] Updated weights for policy 0, policy_version 77500 (0.0010) -[2023-10-15 05:24:13,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 159186944. Throughput: 0: 1736.2, 1: 1766.8. Samples: 39806818. Policy #0 lag: (min: 16.0, avg: 43.7, max: 48.0) -[2023-10-15 05:24:13,535][87330] Avg episode reward: [(0, '22.880'), (1, '22.360')] -[2023-10-15 05:24:13,995][88300] Updated weights for policy 1, policy_version 77962 (0.0010) -[2023-10-15 05:24:14,362][88300] Updated weights for policy 1, policy_version 77972 (0.0009) -[2023-10-15 05:24:14,728][88300] Updated weights for policy 1, policy_version 77982 (0.0009) -[2023-10-15 05:24:16,876][88298] Updated weights for policy 0, policy_version 77510 (0.0008) -[2023-10-15 05:24:17,240][88298] Updated weights for policy 0, policy_version 77520 (0.0007) -[2023-10-15 05:24:17,614][88298] Updated weights for policy 0, policy_version 77530 (0.0009) -[2023-10-15 05:24:18,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 159252480. Throughput: 0: 1758.1, 1: 1736.5. Samples: 39817236. Policy #0 lag: (min: 16.0, avg: 43.7, max: 48.0) -[2023-10-15 05:24:18,534][87330] Avg episode reward: [(0, '22.810'), (1, '22.540')] -[2023-10-15 05:24:18,583][88300] Updated weights for policy 1, policy_version 77992 (0.0009) -[2023-10-15 05:24:18,947][88300] Updated weights for policy 1, policy_version 78002 (0.0007) -[2023-10-15 05:24:19,312][88300] Updated weights for policy 1, policy_version 78012 (0.0007) -[2023-10-15 05:24:21,546][88298] Updated weights for policy 0, policy_version 77540 (0.0010) -[2023-10-15 05:24:21,918][88298] Updated weights for policy 0, policy_version 77550 (0.0010) -[2023-10-15 05:24:22,295][88298] Updated weights for policy 0, policy_version 77560 (0.0008) -[2023-10-15 05:24:23,242][88300] Updated weights for policy 1, policy_version 78022 (0.0008) -[2023-10-15 05:24:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 159318016. Throughput: 0: 1746.4, 1: 1764.1. Samples: 39838374. Policy #0 lag: (min: 16.0, avg: 43.7, max: 48.0) -[2023-10-15 05:24:23,534][87330] Avg episode reward: [(0, '22.830'), (1, '22.400')] -[2023-10-15 05:24:23,597][88300] Updated weights for policy 1, policy_version 78032 (0.0010) -[2023-10-15 05:24:23,958][88300] Updated weights for policy 1, policy_version 78042 (0.0008) -[2023-10-15 05:24:26,281][88298] Updated weights for policy 0, policy_version 77570 (0.0008) -[2023-10-15 05:24:26,696][88298] Updated weights for policy 0, policy_version 77580 (0.0008) -[2023-10-15 05:24:27,073][88298] Updated weights for policy 0, policy_version 77590 (0.0009) -[2023-10-15 05:24:27,442][88298] Updated weights for policy 0, policy_version 77600 (0.0008) -[2023-10-15 05:24:27,787][88300] Updated weights for policy 1, policy_version 78052 (0.0007) -[2023-10-15 05:24:28,151][88300] Updated weights for policy 1, policy_version 78062 (0.0008) -[2023-10-15 05:24:28,520][88300] Updated weights for policy 1, policy_version 78072 (0.0009) -[2023-10-15 05:24:28,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 159383552. Throughput: 0: 1722.1, 1: 1760.9. Samples: 39858460. Policy #0 lag: (min: 16.0, avg: 43.7, max: 48.0) -[2023-10-15 05:24:28,534][87330] Avg episode reward: [(0, '22.640'), (1, '22.280')] -[2023-10-15 05:24:31,386][88298] Updated weights for policy 0, policy_version 77610 (0.0009) -[2023-10-15 05:24:31,747][88298] Updated weights for policy 0, policy_version 77620 (0.0007) -[2023-10-15 05:24:32,116][88298] Updated weights for policy 0, policy_version 77630 (0.0008) -[2023-10-15 05:24:32,431][88300] Updated weights for policy 1, policy_version 78082 (0.0009) -[2023-10-15 05:24:32,812][88300] Updated weights for policy 1, policy_version 78092 (0.0009) -[2023-10-15 05:24:33,179][88300] Updated weights for policy 1, policy_version 78102 (0.0009) -[2023-10-15 05:24:33,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 159449088. Throughput: 0: 1751.5, 1: 1757.9. Samples: 39869878. Policy #0 lag: (min: 16.0, avg: 43.7, max: 48.0) -[2023-10-15 05:24:33,535][87330] Avg episode reward: [(0, '22.410'), (1, '22.270')] -[2023-10-15 05:24:33,551][88300] Updated weights for policy 1, policy_version 78112 (0.0007) -[2023-10-15 05:24:36,056][88298] Updated weights for policy 0, policy_version 77640 (0.0008) -[2023-10-15 05:24:36,420][88298] Updated weights for policy 0, policy_version 77650 (0.0007) -[2023-10-15 05:24:36,787][88298] Updated weights for policy 0, policy_version 77660 (0.0008) -[2023-10-15 05:24:37,421][88300] Updated weights for policy 1, policy_version 78122 (0.0009) -[2023-10-15 05:24:37,784][88300] Updated weights for policy 1, policy_version 78132 (0.0007) -[2023-10-15 05:24:38,147][88300] Updated weights for policy 1, policy_version 78142 (0.0007) -[2023-10-15 05:24:38,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.6, 300 sec: 13995.8). Total num frames: 159547392. Throughput: 0: 1727.2, 1: 1770.8. Samples: 39890222. Policy #0 lag: (min: 16.0, avg: 43.7, max: 48.0) -[2023-10-15 05:24:38,534][87330] Avg episode reward: [(0, '22.420'), (1, '22.590')] -[2023-10-15 05:24:40,737][88298] Updated weights for policy 0, policy_version 77670 (0.0008) -[2023-10-15 05:24:41,107][88298] Updated weights for policy 0, policy_version 77680 (0.0008) -[2023-10-15 05:24:41,482][88298] Updated weights for policy 0, policy_version 77690 (0.0008) -[2023-10-15 05:24:41,916][88300] Updated weights for policy 1, policy_version 78152 (0.0007) -[2023-10-15 05:24:42,280][88300] Updated weights for policy 1, policy_version 78162 (0.0008) -[2023-10-15 05:24:42,654][88300] Updated weights for policy 1, policy_version 78172 (0.0008) -[2023-10-15 05:24:43,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 159612928. Throughput: 0: 1722.0, 1: 1746.8. Samples: 39910754. Policy #0 lag: (min: 16.0, avg: 43.7, max: 48.0) -[2023-10-15 05:24:43,534][87330] Avg episode reward: [(0, '22.320'), (1, '22.460')] -[2023-10-15 05:24:45,589][88298] Updated weights for policy 0, policy_version 77700 (0.0007) -[2023-10-15 05:24:45,959][88298] Updated weights for policy 0, policy_version 77710 (0.0007) -[2023-10-15 05:24:46,326][88298] Updated weights for policy 0, policy_version 77720 (0.0007) -[2023-10-15 05:24:46,568][88300] Updated weights for policy 1, policy_version 78182 (0.0008) -[2023-10-15 05:24:46,944][88300] Updated weights for policy 1, policy_version 78192 (0.0009) -[2023-10-15 05:24:47,307][88300] Updated weights for policy 1, policy_version 78202 (0.0009) -[2023-10-15 05:24:48,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13884.8). Total num frames: 159678464. Throughput: 0: 1739.8, 1: 1771.3. Samples: 39922210. Policy #0 lag: (min: 16.0, avg: 43.7, max: 48.0) -[2023-10-15 05:24:48,534][87330] Avg episode reward: [(0, '22.380'), (1, '22.420')] -[2023-10-15 05:24:50,240][88298] Updated weights for policy 0, policy_version 77730 (0.0007) -[2023-10-15 05:24:50,610][88298] Updated weights for policy 0, policy_version 77740 (0.0007) -[2023-10-15 05:24:50,985][88298] Updated weights for policy 0, policy_version 77750 (0.0007) -[2023-10-15 05:24:51,011][88300] Updated weights for policy 1, policy_version 78212 (0.0007) -[2023-10-15 05:24:51,342][88298] Updated weights for policy 0, policy_version 77760 (0.0009) -[2023-10-15 05:24:51,378][88300] Updated weights for policy 1, policy_version 78222 (0.0010) -[2023-10-15 05:24:51,742][88300] Updated weights for policy 1, policy_version 78232 (0.0010) -[2023-10-15 05:24:53,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 159744000. Throughput: 0: 1715.1, 1: 1742.0. Samples: 39941344. Policy #0 lag: (min: 16.0, avg: 43.7, max: 48.0) -[2023-10-15 05:24:53,534][87330] Avg episode reward: [(0, '22.400'), (1, '22.380')] -[2023-10-15 05:24:55,160][88298] Updated weights for policy 0, policy_version 77770 (0.0009) -[2023-10-15 05:24:55,537][88298] Updated weights for policy 0, policy_version 77780 (0.0008) -[2023-10-15 05:24:55,602][88300] Updated weights for policy 1, policy_version 78242 (0.0011) -[2023-10-15 05:24:55,904][88298] Updated weights for policy 0, policy_version 77790 (0.0008) -[2023-10-15 05:24:55,967][88300] Updated weights for policy 1, policy_version 78252 (0.0007) -[2023-10-15 05:24:56,330][88300] Updated weights for policy 1, policy_version 78262 (0.0008) -[2023-10-15 05:24:56,693][88300] Updated weights for policy 1, policy_version 78272 (0.0009) -[2023-10-15 05:24:58,534][87330] Fps is (10 sec: 13106.5, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 159809536. Throughput: 0: 1735.4, 1: 1742.3. Samples: 39963318. Policy #0 lag: (min: 16.0, avg: 43.7, max: 48.0) -[2023-10-15 05:24:58,536][87330] Avg episode reward: [(0, '22.310'), (1, '22.500')] -[2023-10-15 05:24:58,545][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000077792_79659008.pth... -[2023-10-15 05:24:58,545][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000078272_80150528.pth... -[2023-10-15 05:24:58,585][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000076192_78020608.pth -[2023-10-15 05:24:58,586][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000076640_78479360.pth -[2023-10-15 05:24:59,845][88298] Updated weights for policy 0, policy_version 77800 (0.0011) -[2023-10-15 05:25:00,217][88298] Updated weights for policy 0, policy_version 77810 (0.0009) -[2023-10-15 05:25:00,557][88300] Updated weights for policy 1, policy_version 78282 (0.0007) -[2023-10-15 05:25:00,581][88298] Updated weights for policy 0, policy_version 77820 (0.0007) -[2023-10-15 05:25:00,918][88300] Updated weights for policy 1, policy_version 78292 (0.0008) -[2023-10-15 05:25:01,293][88300] Updated weights for policy 1, policy_version 78302 (0.0008) -[2023-10-15 05:25:03,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 159875072. Throughput: 0: 1709.9, 1: 1747.9. Samples: 39972840. Policy #0 lag: (min: 16.0, avg: 43.7, max: 48.0) -[2023-10-15 05:25:03,535][87330] Avg episode reward: [(0, '22.640'), (1, '22.410')] -[2023-10-15 05:25:04,387][88298] Updated weights for policy 0, policy_version 77830 (0.0007) -[2023-10-15 05:25:04,758][88298] Updated weights for policy 0, policy_version 77840 (0.0007) -[2023-10-15 05:25:05,117][88298] Updated weights for policy 0, policy_version 77850 (0.0007) -[2023-10-15 05:25:05,338][88300] Updated weights for policy 1, policy_version 78312 (0.0009) -[2023-10-15 05:25:05,712][88300] Updated weights for policy 1, policy_version 78322 (0.0008) -[2023-10-15 05:25:06,078][88300] Updated weights for policy 1, policy_version 78332 (0.0009) -[2023-10-15 05:25:08,534][87330] Fps is (10 sec: 13107.7, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 159940608. Throughput: 0: 1725.9, 1: 1735.3. Samples: 39994126. Policy #0 lag: (min: 31.0, avg: 31.8, max: 51.0) -[2023-10-15 05:25:08,535][87330] Avg episode reward: [(0, '22.580'), (1, '22.450')] -[2023-10-15 05:25:09,023][88298] Updated weights for policy 0, policy_version 77860 (0.0007) -[2023-10-15 05:25:09,403][88298] Updated weights for policy 0, policy_version 77870 (0.0009) -[2023-10-15 05:25:09,768][88298] Updated weights for policy 0, policy_version 77880 (0.0010) -[2023-10-15 05:25:10,134][88300] Updated weights for policy 1, policy_version 78342 (0.0009) -[2023-10-15 05:25:10,511][88300] Updated weights for policy 1, policy_version 78352 (0.0009) -[2023-10-15 05:25:10,882][88300] Updated weights for policy 1, policy_version 78362 (0.0007) -[2023-10-15 05:25:13,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 160006144. Throughput: 0: 1749.5, 1: 1738.8. Samples: 40015436. Policy #0 lag: (min: 31.0, avg: 31.8, max: 51.0) -[2023-10-15 05:25:13,535][87330] Avg episode reward: [(0, '22.670'), (1, '22.510')] -[2023-10-15 05:25:13,716][88298] Updated weights for policy 0, policy_version 77890 (0.0009) -[2023-10-15 05:25:14,113][88298] Updated weights for policy 0, policy_version 77900 (0.0009) -[2023-10-15 05:25:14,485][88298] Updated weights for policy 0, policy_version 77910 (0.0009) -[2023-10-15 05:25:14,786][88300] Updated weights for policy 1, policy_version 78372 (0.0007) -[2023-10-15 05:25:14,858][88298] Updated weights for policy 0, policy_version 77920 (0.0009) -[2023-10-15 05:25:15,159][88300] Updated weights for policy 1, policy_version 78382 (0.0007) -[2023-10-15 05:25:15,530][88300] Updated weights for policy 1, policy_version 78392 (0.0008) -[2023-10-15 05:25:18,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 160071680. Throughput: 0: 1718.1, 1: 1724.5. Samples: 40024794. Policy #0 lag: (min: 31.0, avg: 31.8, max: 51.0) -[2023-10-15 05:25:18,534][87330] Avg episode reward: [(0, '22.670'), (1, '22.590')] -[2023-10-15 05:25:18,769][88298] Updated weights for policy 0, policy_version 77930 (0.0007) -[2023-10-15 05:25:19,132][88298] Updated weights for policy 0, policy_version 77940 (0.0007) -[2023-10-15 05:25:19,409][88300] Updated weights for policy 1, policy_version 78402 (0.0008) -[2023-10-15 05:25:19,513][88298] Updated weights for policy 0, policy_version 77950 (0.0008) -[2023-10-15 05:25:19,775][88300] Updated weights for policy 1, policy_version 78412 (0.0009) -[2023-10-15 05:25:20,139][88300] Updated weights for policy 1, policy_version 78422 (0.0009) -[2023-10-15 05:25:20,511][88300] Updated weights for policy 1, policy_version 78432 (0.0008) -[2023-10-15 05:25:23,322][88298] Updated weights for policy 0, policy_version 77960 (0.0009) -[2023-10-15 05:25:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 160137216. Throughput: 0: 1741.1, 1: 1727.3. Samples: 40046302. Policy #0 lag: (min: 31.0, avg: 31.8, max: 51.0) -[2023-10-15 05:25:23,535][87330] Avg episode reward: [(0, '22.710'), (1, '22.670')] -[2023-10-15 05:25:23,685][88298] Updated weights for policy 0, policy_version 77970 (0.0009) -[2023-10-15 05:25:24,059][88298] Updated weights for policy 0, policy_version 77980 (0.0010) -[2023-10-15 05:25:24,537][88300] Updated weights for policy 1, policy_version 78442 (0.0009) -[2023-10-15 05:25:24,901][88300] Updated weights for policy 1, policy_version 78452 (0.0009) -[2023-10-15 05:25:25,264][88300] Updated weights for policy 1, policy_version 78462 (0.0009) -[2023-10-15 05:25:27,941][88298] Updated weights for policy 0, policy_version 77990 (0.0009) -[2023-10-15 05:25:28,317][88298] Updated weights for policy 0, policy_version 78000 (0.0007) -[2023-10-15 05:25:28,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 160202752. Throughput: 0: 1744.9, 1: 1746.1. Samples: 40067850. Policy #0 lag: (min: 31.0, avg: 31.8, max: 51.0) -[2023-10-15 05:25:28,534][87330] Avg episode reward: [(0, '22.800'), (1, '22.870')] -[2023-10-15 05:25:28,696][88298] Updated weights for policy 0, policy_version 78010 (0.0009) -[2023-10-15 05:25:29,044][88300] Updated weights for policy 1, policy_version 78472 (0.0009) -[2023-10-15 05:25:29,422][88300] Updated weights for policy 1, policy_version 78482 (0.0007) -[2023-10-15 05:25:29,782][88300] Updated weights for policy 1, policy_version 78492 (0.0007) -[2023-10-15 05:25:32,689][88298] Updated weights for policy 0, policy_version 78020 (0.0008) -[2023-10-15 05:25:33,055][88298] Updated weights for policy 0, policy_version 78030 (0.0008) -[2023-10-15 05:25:33,429][88298] Updated weights for policy 0, policy_version 78040 (0.0008) -[2023-10-15 05:25:33,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 160268288. Throughput: 0: 1728.8, 1: 1720.7. Samples: 40077436. Policy #0 lag: (min: 31.0, avg: 31.8, max: 51.0) -[2023-10-15 05:25:33,534][87330] Avg episode reward: [(0, '22.730'), (1, '22.930')] -[2023-10-15 05:25:33,604][88300] Updated weights for policy 1, policy_version 78502 (0.0010) -[2023-10-15 05:25:33,973][88300] Updated weights for policy 1, policy_version 78512 (0.0007) -[2023-10-15 05:25:34,337][88300] Updated weights for policy 1, policy_version 78522 (0.0008) -[2023-10-15 05:25:37,334][88298] Updated weights for policy 0, policy_version 78050 (0.0010) -[2023-10-15 05:25:37,699][88298] Updated weights for policy 0, policy_version 78060 (0.0011) -[2023-10-15 05:25:38,055][88298] Updated weights for policy 0, policy_version 78070 (0.0007) -[2023-10-15 05:25:38,303][88300] Updated weights for policy 1, policy_version 78532 (0.0008) -[2023-10-15 05:25:38,428][88298] Updated weights for policy 0, policy_version 78080 (0.0010) -[2023-10-15 05:25:38,534][87330] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 160366592. Throughput: 0: 1749.1, 1: 1751.1. Samples: 40098852. Policy #0 lag: (min: 31.0, avg: 31.8, max: 51.0) -[2023-10-15 05:25:38,535][87330] Avg episode reward: [(0, '22.840'), (1, '22.980')] -[2023-10-15 05:25:38,673][88300] Updated weights for policy 1, policy_version 78542 (0.0008) -[2023-10-15 05:25:39,023][88300] Updated weights for policy 1, policy_version 78552 (0.0007) -[2023-10-15 05:25:42,317][88298] Updated weights for policy 0, policy_version 78090 (0.0008) -[2023-10-15 05:25:42,673][88298] Updated weights for policy 0, policy_version 78100 (0.0009) -[2023-10-15 05:25:42,951][88300] Updated weights for policy 1, policy_version 78562 (0.0008) -[2023-10-15 05:25:43,040][88298] Updated weights for policy 0, policy_version 78110 (0.0010) -[2023-10-15 05:25:43,319][88300] Updated weights for policy 1, policy_version 78572 (0.0008) -[2023-10-15 05:25:43,534][87330] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 160432128. Throughput: 0: 1722.6, 1: 1740.0. Samples: 40119134. Policy #0 lag: (min: 31.0, avg: 31.8, max: 51.0) -[2023-10-15 05:25:43,534][87330] Avg episode reward: [(0, '22.700'), (1, '23.060')] -[2023-10-15 05:25:43,687][88300] Updated weights for policy 1, policy_version 78582 (0.0010) -[2023-10-15 05:25:44,051][88300] Updated weights for policy 1, policy_version 78592 (0.0011) -[2023-10-15 05:25:46,848][88298] Updated weights for policy 0, policy_version 78120 (0.0010) -[2023-10-15 05:25:47,227][88298] Updated weights for policy 0, policy_version 78130 (0.0010) -[2023-10-15 05:25:47,593][88298] Updated weights for policy 0, policy_version 78140 (0.0009) -[2023-10-15 05:25:47,936][88300] Updated weights for policy 1, policy_version 78602 (0.0008) -[2023-10-15 05:25:48,304][88300] Updated weights for policy 1, policy_version 78612 (0.0007) -[2023-10-15 05:25:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 160497664. Throughput: 0: 1746.5, 1: 1741.0. Samples: 40129778. Policy #0 lag: (min: 31.0, avg: 31.8, max: 51.0) -[2023-10-15 05:25:48,535][87330] Avg episode reward: [(0, '22.560'), (1, '23.090')] -[2023-10-15 05:25:48,668][88300] Updated weights for policy 1, policy_version 78622 (0.0009) -[2023-10-15 05:25:51,609][88298] Updated weights for policy 0, policy_version 78150 (0.0010) -[2023-10-15 05:25:51,980][88298] Updated weights for policy 0, policy_version 78160 (0.0007) -[2023-10-15 05:25:52,350][88298] Updated weights for policy 0, policy_version 78170 (0.0009) -[2023-10-15 05:25:52,610][88300] Updated weights for policy 1, policy_version 78632 (0.0009) -[2023-10-15 05:25:52,969][88300] Updated weights for policy 1, policy_version 78642 (0.0010) -[2023-10-15 05:25:53,335][88300] Updated weights for policy 1, policy_version 78652 (0.0008) -[2023-10-15 05:25:53,534][87330] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 160595968. Throughput: 0: 1729.4, 1: 1751.5. Samples: 40150766. Policy #0 lag: (min: 31.0, avg: 31.8, max: 51.0) -[2023-10-15 05:25:53,535][87330] Avg episode reward: [(0, '22.530'), (1, '23.010')] -[2023-10-15 05:25:56,276][88298] Updated weights for policy 0, policy_version 78180 (0.0008) -[2023-10-15 05:25:56,639][88298] Updated weights for policy 0, policy_version 78190 (0.0009) -[2023-10-15 05:25:57,009][88298] Updated weights for policy 0, policy_version 78200 (0.0009) -[2023-10-15 05:25:57,435][88300] Updated weights for policy 1, policy_version 78662 (0.0009) -[2023-10-15 05:25:57,824][88300] Updated weights for policy 1, policy_version 78672 (0.0008) -[2023-10-15 05:25:58,187][88300] Updated weights for policy 1, policy_version 78682 (0.0007) -[2023-10-15 05:25:58,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 160661504. Throughput: 0: 1709.8, 1: 1729.6. Samples: 40170210. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-15 05:25:58,535][87330] Avg episode reward: [(0, '22.580'), (1, '22.960')] -[2023-10-15 05:26:01,075][88298] Updated weights for policy 0, policy_version 78210 (0.0008) -[2023-10-15 05:26:01,451][88298] Updated weights for policy 0, policy_version 78220 (0.0011) -[2023-10-15 05:26:01,821][88298] Updated weights for policy 0, policy_version 78230 (0.0010) -[2023-10-15 05:26:01,944][88300] Updated weights for policy 1, policy_version 78692 (0.0008) -[2023-10-15 05:26:02,184][88298] Updated weights for policy 0, policy_version 78240 (0.0008) -[2023-10-15 05:26:02,309][88300] Updated weights for policy 1, policy_version 78702 (0.0008) -[2023-10-15 05:26:02,675][88300] Updated weights for policy 1, policy_version 78712 (0.0007) -[2023-10-15 05:26:03,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 160727040. Throughput: 0: 1741.1, 1: 1754.4. Samples: 40182088. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-15 05:26:03,534][87330] Avg episode reward: [(0, '22.670'), (1, '22.830')] -[2023-10-15 05:26:06,095][88298] Updated weights for policy 0, policy_version 78250 (0.0011) -[2023-10-15 05:26:06,468][88298] Updated weights for policy 0, policy_version 78260 (0.0010) -[2023-10-15 05:26:06,613][88300] Updated weights for policy 1, policy_version 78722 (0.0007) -[2023-10-15 05:26:06,843][88298] Updated weights for policy 0, policy_version 78270 (0.0009) -[2023-10-15 05:26:06,977][88300] Updated weights for policy 1, policy_version 78732 (0.0008) -[2023-10-15 05:26:07,341][88300] Updated weights for policy 1, policy_version 78742 (0.0009) -[2023-10-15 05:26:07,712][88300] Updated weights for policy 1, policy_version 78752 (0.0008) -[2023-10-15 05:26:08,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 160792576. Throughput: 0: 1717.6, 1: 1737.5. Samples: 40201780. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-15 05:26:08,534][87330] Avg episode reward: [(0, '22.680'), (1, '22.860')] -[2023-10-15 05:26:10,943][88298] Updated weights for policy 0, policy_version 78280 (0.0009) -[2023-10-15 05:26:11,310][88298] Updated weights for policy 0, policy_version 78290 (0.0009) -[2023-10-15 05:26:11,629][88300] Updated weights for policy 1, policy_version 78762 (0.0009) -[2023-10-15 05:26:11,679][88298] Updated weights for policy 0, policy_version 78300 (0.0009) -[2023-10-15 05:26:11,986][88300] Updated weights for policy 1, policy_version 78772 (0.0008) -[2023-10-15 05:26:12,351][88300] Updated weights for policy 1, policy_version 78782 (0.0007) -[2023-10-15 05:26:13,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 160858112. Throughput: 0: 1712.1, 1: 1723.2. Samples: 40222440. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-15 05:26:13,534][87330] Avg episode reward: [(0, '22.490'), (1, '22.880')] -[2023-10-15 05:26:15,588][88298] Updated weights for policy 0, policy_version 78310 (0.0008) -[2023-10-15 05:26:15,956][88298] Updated weights for policy 0, policy_version 78320 (0.0008) -[2023-10-15 05:26:16,207][88300] Updated weights for policy 1, policy_version 78792 (0.0008) -[2023-10-15 05:26:16,326][88298] Updated weights for policy 0, policy_version 78330 (0.0009) -[2023-10-15 05:26:16,571][88300] Updated weights for policy 1, policy_version 78802 (0.0008) -[2023-10-15 05:26:16,936][88300] Updated weights for policy 1, policy_version 78812 (0.0010) -[2023-10-15 05:26:18,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 160923648. Throughput: 0: 1734.2, 1: 1744.6. Samples: 40233984. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-15 05:26:18,535][87330] Avg episode reward: [(0, '22.840'), (1, '22.850')] -[2023-10-15 05:26:20,214][88298] Updated weights for policy 0, policy_version 78340 (0.0009) -[2023-10-15 05:26:20,587][88298] Updated weights for policy 0, policy_version 78350 (0.0010) -[2023-10-15 05:26:20,849][88300] Updated weights for policy 1, policy_version 78822 (0.0009) -[2023-10-15 05:26:20,958][88298] Updated weights for policy 0, policy_version 78360 (0.0009) -[2023-10-15 05:26:21,213][88300] Updated weights for policy 1, policy_version 78832 (0.0008) -[2023-10-15 05:26:21,570][88300] Updated weights for policy 1, policy_version 78842 (0.0010) -[2023-10-15 05:26:23,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 160989184. Throughput: 0: 1716.9, 1: 1722.4. Samples: 40253624. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-15 05:26:23,534][87330] Avg episode reward: [(0, '22.860'), (1, '22.880')] -[2023-10-15 05:26:24,988][88298] Updated weights for policy 0, policy_version 78370 (0.0009) -[2023-10-15 05:26:25,344][88300] Updated weights for policy 1, policy_version 78852 (0.0008) -[2023-10-15 05:26:25,359][88298] Updated weights for policy 0, policy_version 78380 (0.0007) -[2023-10-15 05:26:25,710][88300] Updated weights for policy 1, policy_version 78862 (0.0008) -[2023-10-15 05:26:25,736][88298] Updated weights for policy 0, policy_version 78390 (0.0007) -[2023-10-15 05:26:26,070][88300] Updated weights for policy 1, policy_version 78872 (0.0008) -[2023-10-15 05:26:26,096][88298] Updated weights for policy 0, policy_version 78400 (0.0009) -[2023-10-15 05:26:28,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 161054720. Throughput: 0: 1733.3, 1: 1734.0. Samples: 40275162. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-15 05:26:28,535][87330] Avg episode reward: [(0, '22.860'), (1, '22.920')] -[2023-10-15 05:26:29,795][88300] Updated weights for policy 1, policy_version 78882 (0.0009) -[2023-10-15 05:26:29,944][88298] Updated weights for policy 0, policy_version 78410 (0.0008) -[2023-10-15 05:26:30,162][88300] Updated weights for policy 1, policy_version 78892 (0.0007) -[2023-10-15 05:26:30,314][88298] Updated weights for policy 0, policy_version 78420 (0.0007) -[2023-10-15 05:26:30,530][88300] Updated weights for policy 1, policy_version 78902 (0.0008) -[2023-10-15 05:26:30,683][88298] Updated weights for policy 0, policy_version 78430 (0.0008) -[2023-10-15 05:26:30,894][88300] Updated weights for policy 1, policy_version 78912 (0.0010) -[2023-10-15 05:26:33,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 161120256. Throughput: 0: 1713.2, 1: 1730.7. Samples: 40284752. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-15 05:26:33,535][87330] Avg episode reward: [(0, '22.880'), (1, '23.050')] -[2023-10-15 05:26:34,536][88298] Updated weights for policy 0, policy_version 78440 (0.0007) -[2023-10-15 05:26:34,897][88300] Updated weights for policy 1, policy_version 78922 (0.0009) -[2023-10-15 05:26:34,908][88298] Updated weights for policy 0, policy_version 78450 (0.0007) -[2023-10-15 05:26:35,266][88300] Updated weights for policy 1, policy_version 78932 (0.0009) -[2023-10-15 05:26:35,283][88298] Updated weights for policy 0, policy_version 78460 (0.0007) -[2023-10-15 05:26:35,623][88300] Updated weights for policy 1, policy_version 78942 (0.0008) -[2023-10-15 05:26:38,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 161185792. Throughput: 0: 1724.5, 1: 1732.0. Samples: 40306308. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-15 05:26:38,535][87330] Avg episode reward: [(0, '22.890'), (1, '23.030')] -[2023-10-15 05:26:39,134][88298] Updated weights for policy 0, policy_version 78470 (0.0010) -[2023-10-15 05:26:39,472][88300] Updated weights for policy 1, policy_version 78952 (0.0007) -[2023-10-15 05:26:39,505][88298] Updated weights for policy 0, policy_version 78480 (0.0008) -[2023-10-15 05:26:39,835][88300] Updated weights for policy 1, policy_version 78962 (0.0008) -[2023-10-15 05:26:39,870][88298] Updated weights for policy 0, policy_version 78490 (0.0007) -[2023-10-15 05:26:40,204][88300] Updated weights for policy 1, policy_version 78972 (0.0009) -[2023-10-15 05:26:43,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 161251328. Throughput: 0: 1748.5, 1: 1758.0. Samples: 40328004. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-15 05:26:43,534][87330] Avg episode reward: [(0, '23.090'), (1, '22.960')] -[2023-10-15 05:26:43,789][88298] Updated weights for policy 0, policy_version 78500 (0.0007) -[2023-10-15 05:26:44,151][88298] Updated weights for policy 0, policy_version 78510 (0.0008) -[2023-10-15 05:26:44,214][88300] Updated weights for policy 1, policy_version 78982 (0.0009) -[2023-10-15 05:26:44,516][88298] Updated weights for policy 0, policy_version 78520 (0.0007) -[2023-10-15 05:26:44,590][88300] Updated weights for policy 1, policy_version 78992 (0.0007) -[2023-10-15 05:26:44,961][88300] Updated weights for policy 1, policy_version 79002 (0.0008) -[2023-10-15 05:26:48,304][88298] Updated weights for policy 0, policy_version 78530 (0.0007) -[2023-10-15 05:26:48,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 161316864. Throughput: 0: 1722.2, 1: 1730.3. Samples: 40337450. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-15 05:26:48,535][87330] Avg episode reward: [(0, '23.120'), (1, '22.970')] -[2023-10-15 05:26:48,703][88298] Updated weights for policy 0, policy_version 78540 (0.0009) -[2023-10-15 05:26:48,839][88300] Updated weights for policy 1, policy_version 79012 (0.0008) -[2023-10-15 05:26:49,068][88298] Updated weights for policy 0, policy_version 78550 (0.0010) -[2023-10-15 05:26:49,217][88300] Updated weights for policy 1, policy_version 79022 (0.0008) -[2023-10-15 05:26:49,436][88298] Updated weights for policy 0, policy_version 78560 (0.0008) -[2023-10-15 05:26:49,580][88300] Updated weights for policy 1, policy_version 79032 (0.0009) -[2023-10-15 05:26:53,482][88298] Updated weights for policy 0, policy_version 78570 (0.0009) -[2023-10-15 05:26:53,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13884.7). Total num frames: 161382400. Throughput: 0: 1743.9, 1: 1743.8. Samples: 40358730. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-15 05:26:53,535][88300] Updated weights for policy 1, policy_version 79042 (0.0008) -[2023-10-15 05:26:53,535][87330] Avg episode reward: [(0, '23.110'), (1, '22.890')] -[2023-10-15 05:26:53,856][88298] Updated weights for policy 0, policy_version 78580 (0.0007) -[2023-10-15 05:26:53,901][88300] Updated weights for policy 1, policy_version 79052 (0.0008) -[2023-10-15 05:26:54,218][88298] Updated weights for policy 0, policy_version 78590 (0.0010) -[2023-10-15 05:26:54,263][88300] Updated weights for policy 1, policy_version 79062 (0.0008) -[2023-10-15 05:26:54,639][88300] Updated weights for policy 1, policy_version 79072 (0.0008) -[2023-10-15 05:26:58,154][88298] Updated weights for policy 0, policy_version 78600 (0.0009) -[2023-10-15 05:26:58,480][88300] Updated weights for policy 1, policy_version 79082 (0.0007) -[2023-10-15 05:26:58,520][88298] Updated weights for policy 0, policy_version 78610 (0.0008) -[2023-10-15 05:26:58,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 161447936. Throughput: 0: 1749.1, 1: 1756.0. Samples: 40380168. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-15 05:26:58,534][87330] Avg episode reward: [(0, '23.070'), (1, '22.870')] -[2023-10-15 05:26:58,846][88300] Updated weights for policy 1, policy_version 79092 (0.0007) -[2023-10-15 05:26:58,888][88298] Updated weights for policy 0, policy_version 78620 (0.0007) -[2023-10-15 05:26:59,036][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000078624_80510976.pth... -[2023-10-15 05:26:59,065][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000076992_78839808.pth -[2023-10-15 05:26:59,217][88300] Updated weights for policy 1, policy_version 79102 (0.0007) -[2023-10-15 05:26:59,289][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000079104_81002496.pth... -[2023-10-15 05:26:59,327][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000077472_79331328.pth -[2023-10-15 05:27:02,873][88298] Updated weights for policy 0, policy_version 78630 (0.0007) -[2023-10-15 05:27:03,205][88300] Updated weights for policy 1, policy_version 79112 (0.0009) -[2023-10-15 05:27:03,246][88298] Updated weights for policy 0, policy_version 78640 (0.0010) -[2023-10-15 05:27:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.1, 300 sec: 13773.7). Total num frames: 161513472. Throughput: 0: 1725.7, 1: 1734.8. Samples: 40389704. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-15 05:27:03,535][87330] Avg episode reward: [(0, '23.040'), (1, '22.870')] -[2023-10-15 05:27:03,565][88300] Updated weights for policy 1, policy_version 79122 (0.0008) -[2023-10-15 05:27:03,626][88298] Updated weights for policy 0, policy_version 78650 (0.0010) -[2023-10-15 05:27:03,931][88300] Updated weights for policy 1, policy_version 79132 (0.0007) -[2023-10-15 05:27:07,425][88298] Updated weights for policy 0, policy_version 78660 (0.0008) -[2023-10-15 05:27:07,795][88300] Updated weights for policy 1, policy_version 79142 (0.0009) -[2023-10-15 05:27:07,796][88298] Updated weights for policy 0, policy_version 78670 (0.0008) -[2023-10-15 05:27:08,161][88298] Updated weights for policy 0, policy_version 78680 (0.0007) -[2023-10-15 05:27:08,164][88300] Updated weights for policy 1, policy_version 79152 (0.0007) -[2023-10-15 05:27:08,521][88300] Updated weights for policy 1, policy_version 79162 (0.0010) -[2023-10-15 05:27:08,534][87330] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 161611776. Throughput: 0: 1742.1, 1: 1760.8. Samples: 40411258. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-15 05:27:08,534][87330] Avg episode reward: [(0, '23.040'), (1, '22.640')] -[2023-10-15 05:27:12,160][88298] Updated weights for policy 0, policy_version 78690 (0.0009) -[2023-10-15 05:27:12,522][88298] Updated weights for policy 0, policy_version 78700 (0.0008) -[2023-10-15 05:27:12,578][88300] Updated weights for policy 1, policy_version 79172 (0.0008) -[2023-10-15 05:27:12,897][88298] Updated weights for policy 0, policy_version 78710 (0.0008) -[2023-10-15 05:27:12,941][88300] Updated weights for policy 1, policy_version 79182 (0.0008) -[2023-10-15 05:27:13,252][88298] Updated weights for policy 0, policy_version 78720 (0.0008) -[2023-10-15 05:27:13,303][88300] Updated weights for policy 1, policy_version 79192 (0.0010) -[2023-10-15 05:27:13,534][87330] Fps is (10 sec: 16384.3, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 161677312. Throughput: 0: 1730.8, 1: 1736.0. Samples: 40431166. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-15 05:27:13,534][87330] Avg episode reward: [(0, '22.980'), (1, '22.720')] -[2023-10-15 05:27:17,063][88300] Updated weights for policy 1, policy_version 79202 (0.0010) -[2023-10-15 05:27:17,110][88298] Updated weights for policy 0, policy_version 78730 (0.0008) -[2023-10-15 05:27:17,428][88300] Updated weights for policy 1, policy_version 79212 (0.0008) -[2023-10-15 05:27:17,483][88298] Updated weights for policy 0, policy_version 78740 (0.0008) -[2023-10-15 05:27:17,783][88300] Updated weights for policy 1, policy_version 79222 (0.0008) -[2023-10-15 05:27:17,845][88298] Updated weights for policy 0, policy_version 78750 (0.0008) -[2023-10-15 05:27:18,145][88300] Updated weights for policy 1, policy_version 79232 (0.0009) -[2023-10-15 05:27:18,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 161775616. Throughput: 0: 1752.0, 1: 1751.8. Samples: 40442422. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-15 05:27:18,535][87330] Avg episode reward: [(0, '22.950'), (1, '22.710')] -[2023-10-15 05:27:21,690][88298] Updated weights for policy 0, policy_version 78760 (0.0009) -[2023-10-15 05:27:22,015][88300] Updated weights for policy 1, policy_version 79242 (0.0008) -[2023-10-15 05:27:22,053][88298] Updated weights for policy 0, policy_version 78770 (0.0008) -[2023-10-15 05:27:22,380][88300] Updated weights for policy 1, policy_version 79252 (0.0009) -[2023-10-15 05:27:22,425][88298] Updated weights for policy 0, policy_version 78780 (0.0008) -[2023-10-15 05:27:22,741][88300] Updated weights for policy 1, policy_version 79262 (0.0008) -[2023-10-15 05:27:23,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 161841152. Throughput: 0: 1743.9, 1: 1738.5. Samples: 40463012. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-15 05:27:23,534][87330] Avg episode reward: [(0, '22.950'), (1, '22.700')] -[2023-10-15 05:27:26,369][88298] Updated weights for policy 0, policy_version 78790 (0.0008) -[2023-10-15 05:27:26,729][88300] Updated weights for policy 1, policy_version 79272 (0.0008) -[2023-10-15 05:27:26,730][88298] Updated weights for policy 0, policy_version 78800 (0.0007) -[2023-10-15 05:27:27,098][88298] Updated weights for policy 0, policy_version 78810 (0.0007) -[2023-10-15 05:27:27,099][88300] Updated weights for policy 1, policy_version 79282 (0.0008) -[2023-10-15 05:27:27,461][88300] Updated weights for policy 1, policy_version 79292 (0.0008) -[2023-10-15 05:27:28,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 161906688. Throughput: 0: 1718.8, 1: 1719.2. Samples: 40482710. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-15 05:27:28,534][87330] Avg episode reward: [(0, '22.920'), (1, '22.700')] -[2023-10-15 05:27:31,013][88298] Updated weights for policy 0, policy_version 78820 (0.0008) -[2023-10-15 05:27:31,388][88298] Updated weights for policy 0, policy_version 78830 (0.0010) -[2023-10-15 05:27:31,396][88300] Updated weights for policy 1, policy_version 79302 (0.0009) -[2023-10-15 05:27:31,744][88298] Updated weights for policy 0, policy_version 78840 (0.0007) -[2023-10-15 05:27:31,779][88300] Updated weights for policy 1, policy_version 79312 (0.0007) -[2023-10-15 05:27:32,149][88300] Updated weights for policy 1, policy_version 79322 (0.0008) -[2023-10-15 05:27:33,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 161972224. Throughput: 0: 1744.1, 1: 1750.0. Samples: 40494688. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-15 05:27:33,534][87330] Avg episode reward: [(0, '22.920'), (1, '22.720')] -[2023-10-15 05:27:35,715][88298] Updated weights for policy 0, policy_version 78850 (0.0007) -[2023-10-15 05:27:36,001][88300] Updated weights for policy 1, policy_version 79332 (0.0007) -[2023-10-15 05:27:36,083][88298] Updated weights for policy 0, policy_version 78860 (0.0007) -[2023-10-15 05:27:36,363][88300] Updated weights for policy 1, policy_version 79342 (0.0009) -[2023-10-15 05:27:36,455][88298] Updated weights for policy 0, policy_version 78870 (0.0007) -[2023-10-15 05:27:36,719][88300] Updated weights for policy 1, policy_version 79352 (0.0008) -[2023-10-15 05:27:36,826][88298] Updated weights for policy 0, policy_version 78880 (0.0007) -[2023-10-15 05:27:38,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 162037760. Throughput: 0: 1717.1, 1: 1728.5. Samples: 40513782. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-15 05:27:38,534][87330] Avg episode reward: [(0, '22.880'), (1, '22.710')] -[2023-10-15 05:27:40,622][88300] Updated weights for policy 1, policy_version 79362 (0.0008) -[2023-10-15 05:27:40,807][88298] Updated weights for policy 0, policy_version 78890 (0.0007) -[2023-10-15 05:27:40,985][88300] Updated weights for policy 1, policy_version 79372 (0.0008) -[2023-10-15 05:27:41,168][88298] Updated weights for policy 0, policy_version 78900 (0.0009) -[2023-10-15 05:27:41,342][88300] Updated weights for policy 1, policy_version 79382 (0.0009) -[2023-10-15 05:27:41,544][88298] Updated weights for policy 0, policy_version 78910 (0.0007) -[2023-10-15 05:27:41,705][88300] Updated weights for policy 1, policy_version 79392 (0.0008) -[2023-10-15 05:27:43,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 162103296. Throughput: 0: 1715.9, 1: 1732.9. Samples: 40535364. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-15 05:27:43,534][87330] Avg episode reward: [(0, '22.850'), (1, '22.990')] -[2023-10-15 05:27:45,266][88298] Updated weights for policy 0, policy_version 78920 (0.0010) -[2023-10-15 05:27:45,570][88300] Updated weights for policy 1, policy_version 79402 (0.0008) -[2023-10-15 05:27:45,637][88298] Updated weights for policy 0, policy_version 78930 (0.0009) -[2023-10-15 05:27:45,932][88300] Updated weights for policy 1, policy_version 79412 (0.0008) -[2023-10-15 05:27:45,998][88298] Updated weights for policy 0, policy_version 78940 (0.0007) -[2023-10-15 05:27:46,290][88300] Updated weights for policy 1, policy_version 79422 (0.0008) -[2023-10-15 05:27:48,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 162168832. Throughput: 0: 1727.0, 1: 1734.9. Samples: 40545488. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-15 05:27:48,535][87330] Avg episode reward: [(0, '22.860'), (1, '23.020')] -[2023-10-15 05:27:49,853][88298] Updated weights for policy 0, policy_version 78950 (0.0008) -[2023-10-15 05:27:50,153][88300] Updated weights for policy 1, policy_version 79432 (0.0009) -[2023-10-15 05:27:50,230][88298] Updated weights for policy 0, policy_version 78960 (0.0007) -[2023-10-15 05:27:50,516][88300] Updated weights for policy 1, policy_version 79442 (0.0008) -[2023-10-15 05:27:50,600][88298] Updated weights for policy 0, policy_version 78970 (0.0009) -[2023-10-15 05:27:50,879][88300] Updated weights for policy 1, policy_version 79452 (0.0008) -[2023-10-15 05:27:53,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 162234368. Throughput: 0: 1717.9, 1: 1726.1. Samples: 40566238. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-15 05:27:53,535][87330] Avg episode reward: [(0, '22.850'), (1, '22.920')] -[2023-10-15 05:27:54,530][88298] Updated weights for policy 0, policy_version 78980 (0.0009) -[2023-10-15 05:27:54,845][88300] Updated weights for policy 1, policy_version 79462 (0.0008) -[2023-10-15 05:27:54,900][88298] Updated weights for policy 0, policy_version 78990 (0.0009) -[2023-10-15 05:27:55,216][88300] Updated weights for policy 1, policy_version 79472 (0.0007) -[2023-10-15 05:27:55,271][88298] Updated weights for policy 0, policy_version 79000 (0.0008) -[2023-10-15 05:27:55,580][88300] Updated weights for policy 1, policy_version 79482 (0.0010) -[2023-10-15 05:27:58,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 162299904. Throughput: 0: 1735.0, 1: 1749.6. Samples: 40587976. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-15 05:27:58,534][87330] Avg episode reward: [(0, '22.880'), (1, '23.020')] -[2023-10-15 05:27:59,247][88298] Updated weights for policy 0, policy_version 79010 (0.0008) -[2023-10-15 05:27:59,394][88300] Updated weights for policy 1, policy_version 79492 (0.0011) -[2023-10-15 05:27:59,611][88298] Updated weights for policy 0, policy_version 79020 (0.0008) -[2023-10-15 05:27:59,762][88300] Updated weights for policy 1, policy_version 79502 (0.0009) -[2023-10-15 05:27:59,982][88298] Updated weights for policy 0, policy_version 79030 (0.0008) -[2023-10-15 05:28:00,136][88300] Updated weights for policy 1, policy_version 79512 (0.0008) -[2023-10-15 05:28:00,352][88298] Updated weights for policy 0, policy_version 79040 (0.0009) -[2023-10-15 05:28:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 162365440. Throughput: 0: 1712.7, 1: 1729.2. Samples: 40597308. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-15 05:28:03,535][87330] Avg episode reward: [(0, '22.850'), (1, '22.810')] -[2023-10-15 05:28:04,109][88300] Updated weights for policy 1, policy_version 79522 (0.0007) -[2023-10-15 05:28:04,321][88298] Updated weights for policy 0, policy_version 79050 (0.0008) -[2023-10-15 05:28:04,472][88300] Updated weights for policy 1, policy_version 79532 (0.0008) -[2023-10-15 05:28:04,692][88298] Updated weights for policy 0, policy_version 79060 (0.0008) -[2023-10-15 05:28:04,843][88300] Updated weights for policy 1, policy_version 79542 (0.0010) -[2023-10-15 05:28:05,068][88298] Updated weights for policy 0, policy_version 79070 (0.0007) -[2023-10-15 05:28:05,212][88300] Updated weights for policy 1, policy_version 79552 (0.0009) -[2023-10-15 05:28:08,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 162430976. Throughput: 0: 1723.7, 1: 1737.1. Samples: 40618748. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-15 05:28:08,535][87330] Avg episode reward: [(0, '22.810'), (1, '22.530')] -[2023-10-15 05:28:09,011][88298] Updated weights for policy 0, policy_version 79080 (0.0009) -[2023-10-15 05:28:09,109][88300] Updated weights for policy 1, policy_version 79562 (0.0008) -[2023-10-15 05:28:09,384][88298] Updated weights for policy 0, policy_version 79090 (0.0008) -[2023-10-15 05:28:09,465][88300] Updated weights for policy 1, policy_version 79572 (0.0008) -[2023-10-15 05:28:09,747][88298] Updated weights for policy 0, policy_version 79100 (0.0009) -[2023-10-15 05:28:09,828][88300] Updated weights for policy 1, policy_version 79582 (0.0009) -[2023-10-15 05:28:13,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 162496512. Throughput: 0: 1746.0, 1: 1761.0. Samples: 40640526. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-15 05:28:13,534][87330] Avg episode reward: [(0, '22.840'), (1, '22.540')] -[2023-10-15 05:28:13,591][88298] Updated weights for policy 0, policy_version 79110 (0.0009) -[2023-10-15 05:28:13,755][88300] Updated weights for policy 1, policy_version 79592 (0.0007) -[2023-10-15 05:28:13,969][88298] Updated weights for policy 0, policy_version 79120 (0.0008) -[2023-10-15 05:28:14,114][88300] Updated weights for policy 1, policy_version 79602 (0.0009) -[2023-10-15 05:28:14,328][88298] Updated weights for policy 0, policy_version 79130 (0.0008) -[2023-10-15 05:28:14,489][88300] Updated weights for policy 1, policy_version 79612 (0.0008) -[2023-10-15 05:28:18,365][88298] Updated weights for policy 0, policy_version 79140 (0.0007) -[2023-10-15 05:28:18,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 162562048. Throughput: 0: 1715.6, 1: 1731.5. Samples: 40649808. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-15 05:28:18,534][87330] Avg episode reward: [(0, '22.760'), (1, '22.300')] -[2023-10-15 05:28:18,557][88300] Updated weights for policy 1, policy_version 79622 (0.0009) -[2023-10-15 05:28:18,735][88298] Updated weights for policy 0, policy_version 79150 (0.0008) -[2023-10-15 05:28:18,947][88300] Updated weights for policy 1, policy_version 79632 (0.0009) -[2023-10-15 05:28:19,100][88298] Updated weights for policy 0, policy_version 79160 (0.0009) -[2023-10-15 05:28:19,311][88300] Updated weights for policy 1, policy_version 79642 (0.0007) -[2023-10-15 05:28:23,076][88298] Updated weights for policy 0, policy_version 79170 (0.0009) -[2023-10-15 05:28:23,192][88300] Updated weights for policy 1, policy_version 79652 (0.0008) -[2023-10-15 05:28:23,443][88298] Updated weights for policy 0, policy_version 79180 (0.0008) -[2023-10-15 05:28:23,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 162627584. Throughput: 0: 1747.6, 1: 1750.1. Samples: 40671180. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-15 05:28:23,534][87330] Avg episode reward: [(0, '22.740'), (1, '22.140')] -[2023-10-15 05:28:23,554][88300] Updated weights for policy 1, policy_version 79662 (0.0009) -[2023-10-15 05:28:23,816][88298] Updated weights for policy 0, policy_version 79190 (0.0007) -[2023-10-15 05:28:23,914][88300] Updated weights for policy 1, policy_version 79672 (0.0007) -[2023-10-15 05:28:24,180][88298] Updated weights for policy 0, policy_version 79200 (0.0007) -[2023-10-15 05:28:27,913][88300] Updated weights for policy 1, policy_version 79682 (0.0008) -[2023-10-15 05:28:28,283][88300] Updated weights for policy 1, policy_version 79692 (0.0009) -[2023-10-15 05:28:28,332][88298] Updated weights for policy 0, policy_version 79210 (0.0009) -[2023-10-15 05:28:28,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 162693120. Throughput: 0: 1746.3, 1: 1733.9. Samples: 40691978. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-15 05:28:28,535][87330] Avg episode reward: [(0, '22.700'), (1, '21.900')] -[2023-10-15 05:28:28,654][88300] Updated weights for policy 1, policy_version 79702 (0.0008) -[2023-10-15 05:28:28,710][88298] Updated weights for policy 0, policy_version 79220 (0.0007) -[2023-10-15 05:28:29,021][88300] Updated weights for policy 1, policy_version 79712 (0.0009) -[2023-10-15 05:28:29,081][88298] Updated weights for policy 0, policy_version 79230 (0.0008) -[2023-10-15 05:28:32,885][88300] Updated weights for policy 1, policy_version 79722 (0.0009) -[2023-10-15 05:28:32,907][88298] Updated weights for policy 0, policy_version 79240 (0.0008) -[2023-10-15 05:28:33,246][88300] Updated weights for policy 1, policy_version 79732 (0.0008) -[2023-10-15 05:28:33,281][88298] Updated weights for policy 0, policy_version 79250 (0.0007) -[2023-10-15 05:28:33,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 162758656. Throughput: 0: 1730.9, 1: 1738.5. Samples: 40701610. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-15 05:28:33,534][87330] Avg episode reward: [(0, '22.480'), (1, '21.780')] -[2023-10-15 05:28:33,613][88300] Updated weights for policy 1, policy_version 79742 (0.0009) -[2023-10-15 05:28:33,640][88298] Updated weights for policy 0, policy_version 79260 (0.0007) -[2023-10-15 05:28:37,589][88300] Updated weights for policy 1, policy_version 79752 (0.0008) -[2023-10-15 05:28:37,621][88298] Updated weights for policy 0, policy_version 79270 (0.0008) -[2023-10-15 05:28:37,958][88300] Updated weights for policy 1, policy_version 79762 (0.0008) -[2023-10-15 05:28:37,993][88298] Updated weights for policy 0, policy_version 79280 (0.0009) -[2023-10-15 05:28:38,318][88300] Updated weights for policy 1, policy_version 79772 (0.0008) -[2023-10-15 05:28:38,365][88298] Updated weights for policy 0, policy_version 79290 (0.0009) -[2023-10-15 05:28:38,534][87330] Fps is (10 sec: 16384.4, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 162856960. Throughput: 0: 1741.6, 1: 1743.6. Samples: 40723070. Policy #0 lag: (min: 15.0, avg: 22.8, max: 47.0) -[2023-10-15 05:28:38,534][87330] Avg episode reward: [(0, '22.240'), (1, '22.030')] -[2023-10-15 05:28:42,146][88298] Updated weights for policy 0, policy_version 79300 (0.0009) -[2023-10-15 05:28:42,163][88300] Updated weights for policy 1, policy_version 79782 (0.0009) -[2023-10-15 05:28:42,518][88298] Updated weights for policy 0, policy_version 79310 (0.0007) -[2023-10-15 05:28:42,524][88300] Updated weights for policy 1, policy_version 79792 (0.0008) -[2023-10-15 05:28:42,880][88298] Updated weights for policy 0, policy_version 79320 (0.0007) -[2023-10-15 05:28:42,888][88300] Updated weights for policy 1, policy_version 79802 (0.0007) -[2023-10-15 05:28:43,534][87330] Fps is (10 sec: 19660.2, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 162955264. Throughput: 0: 1715.5, 1: 1711.3. Samples: 40742184. Policy #0 lag: (min: 15.0, avg: 22.8, max: 47.0) -[2023-10-15 05:28:43,535][87330] Avg episode reward: [(0, '22.380'), (1, '22.000')] -[2023-10-15 05:28:46,803][88298] Updated weights for policy 0, policy_version 79330 (0.0009) -[2023-10-15 05:28:46,899][88300] Updated weights for policy 1, policy_version 79812 (0.0007) -[2023-10-15 05:28:47,167][88298] Updated weights for policy 0, policy_version 79340 (0.0007) -[2023-10-15 05:28:47,275][88300] Updated weights for policy 1, policy_version 79822 (0.0008) -[2023-10-15 05:28:47,533][88298] Updated weights for policy 0, policy_version 79350 (0.0008) -[2023-10-15 05:28:47,631][88300] Updated weights for policy 1, policy_version 79832 (0.0007) -[2023-10-15 05:28:47,908][88298] Updated weights for policy 0, policy_version 79360 (0.0009) -[2023-10-15 05:28:48,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 163020800. Throughput: 0: 1734.6, 1: 1739.5. Samples: 40753640. Policy #0 lag: (min: 15.0, avg: 22.8, max: 47.0) -[2023-10-15 05:28:48,534][87330] Avg episode reward: [(0, '22.450'), (1, '22.040')] -[2023-10-15 05:28:51,636][88300] Updated weights for policy 1, policy_version 79842 (0.0008) -[2023-10-15 05:28:51,848][88298] Updated weights for policy 0, policy_version 79370 (0.0007) -[2023-10-15 05:28:52,008][88300] Updated weights for policy 1, policy_version 79852 (0.0008) -[2023-10-15 05:28:52,220][88298] Updated weights for policy 0, policy_version 79380 (0.0009) -[2023-10-15 05:28:52,372][88300] Updated weights for policy 1, policy_version 79862 (0.0007) -[2023-10-15 05:28:52,582][88298] Updated weights for policy 0, policy_version 79390 (0.0007) -[2023-10-15 05:28:52,738][88300] Updated weights for policy 1, policy_version 79872 (0.0007) -[2023-10-15 05:28:53,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 163086336. Throughput: 0: 1725.6, 1: 1724.2. Samples: 40773990. Policy #0 lag: (min: 15.0, avg: 22.8, max: 47.0) -[2023-10-15 05:28:53,535][87330] Avg episode reward: [(0, '22.470'), (1, '22.320')] -[2023-10-15 05:28:56,463][88298] Updated weights for policy 0, policy_version 79400 (0.0007) -[2023-10-15 05:28:56,724][88300] Updated weights for policy 1, policy_version 79882 (0.0009) -[2023-10-15 05:28:56,842][88298] Updated weights for policy 0, policy_version 79410 (0.0009) -[2023-10-15 05:28:57,094][88300] Updated weights for policy 1, policy_version 79892 (0.0007) -[2023-10-15 05:28:57,206][88298] Updated weights for policy 0, policy_version 79420 (0.0009) -[2023-10-15 05:28:57,466][88300] Updated weights for policy 1, policy_version 79902 (0.0008) -[2023-10-15 05:28:58,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 163151872. Throughput: 0: 1700.6, 1: 1704.2. Samples: 40793742. Policy #0 lag: (min: 15.0, avg: 22.8, max: 47.0) -[2023-10-15 05:28:58,534][87330] Avg episode reward: [(0, '22.490'), (1, '22.720')] -[2023-10-15 05:28:58,542][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000079424_81330176.pth... -[2023-10-15 05:28:58,543][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000079904_81821696.pth... -[2023-10-15 05:28:58,572][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000077792_79659008.pth -[2023-10-15 05:28:58,578][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000078272_80150528.pth -[2023-10-15 05:29:01,127][88298] Updated weights for policy 0, policy_version 79430 (0.0007) -[2023-10-15 05:29:01,399][88300] Updated weights for policy 1, policy_version 79912 (0.0008) -[2023-10-15 05:29:01,499][88298] Updated weights for policy 0, policy_version 79440 (0.0008) -[2023-10-15 05:29:01,772][88300] Updated weights for policy 1, policy_version 79922 (0.0010) -[2023-10-15 05:29:01,879][88298] Updated weights for policy 0, policy_version 79450 (0.0008) -[2023-10-15 05:29:02,131][88300] Updated weights for policy 1, policy_version 79932 (0.0008) -[2023-10-15 05:29:03,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 163217408. Throughput: 0: 1732.4, 1: 1732.3. Samples: 40805716. Policy #0 lag: (min: 15.0, avg: 22.8, max: 47.0) -[2023-10-15 05:29:03,534][87330] Avg episode reward: [(0, '22.810'), (1, '22.760')] -[2023-10-15 05:29:05,901][88298] Updated weights for policy 0, policy_version 79460 (0.0007) -[2023-10-15 05:29:06,036][88300] Updated weights for policy 1, policy_version 79942 (0.0008) -[2023-10-15 05:29:06,269][88298] Updated weights for policy 0, policy_version 79470 (0.0008) -[2023-10-15 05:29:06,407][88300] Updated weights for policy 1, policy_version 79952 (0.0008) -[2023-10-15 05:29:06,627][88298] Updated weights for policy 0, policy_version 79480 (0.0008) -[2023-10-15 05:29:06,773][88300] Updated weights for policy 1, policy_version 79962 (0.0007) -[2023-10-15 05:29:08,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 163282944. Throughput: 0: 1704.6, 1: 1706.8. Samples: 40824692. Policy #0 lag: (min: 15.0, avg: 22.8, max: 47.0) -[2023-10-15 05:29:08,534][87330] Avg episode reward: [(0, '22.780'), (1, '22.940')] -[2023-10-15 05:29:10,582][88298] Updated weights for policy 0, policy_version 79490 (0.0008) -[2023-10-15 05:29:10,670][88300] Updated weights for policy 1, policy_version 79972 (0.0007) -[2023-10-15 05:29:10,954][88298] Updated weights for policy 0, policy_version 79500 (0.0007) -[2023-10-15 05:29:11,052][88300] Updated weights for policy 1, policy_version 79982 (0.0007) -[2023-10-15 05:29:11,333][88298] Updated weights for policy 0, policy_version 79510 (0.0011) -[2023-10-15 05:29:11,419][88300] Updated weights for policy 1, policy_version 79992 (0.0008) -[2023-10-15 05:29:11,693][88298] Updated weights for policy 0, policy_version 79520 (0.0009) -[2023-10-15 05:29:13,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 163348480. Throughput: 0: 1700.8, 1: 1719.0. Samples: 40845872. Policy #0 lag: (min: 15.0, avg: 22.8, max: 47.0) -[2023-10-15 05:29:13,535][87330] Avg episode reward: [(0, '22.990'), (1, '22.980')] -[2023-10-15 05:29:15,455][88300] Updated weights for policy 1, policy_version 80002 (0.0007) -[2023-10-15 05:29:15,757][88298] Updated weights for policy 0, policy_version 79530 (0.0007) -[2023-10-15 05:29:15,824][88300] Updated weights for policy 1, policy_version 80012 (0.0007) -[2023-10-15 05:29:16,137][88298] Updated weights for policy 0, policy_version 79540 (0.0009) -[2023-10-15 05:29:16,186][88300] Updated weights for policy 1, policy_version 80022 (0.0008) -[2023-10-15 05:29:16,503][88298] Updated weights for policy 0, policy_version 79550 (0.0009) -[2023-10-15 05:29:16,553][88300] Updated weights for policy 1, policy_version 80032 (0.0007) -[2023-10-15 05:29:18,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 163414016. Throughput: 0: 1721.8, 1: 1716.9. Samples: 40856352. Policy #0 lag: (min: 15.0, avg: 22.8, max: 47.0) -[2023-10-15 05:29:18,535][87330] Avg episode reward: [(0, '22.970'), (1, '23.000')] -[2023-10-15 05:29:20,444][88298] Updated weights for policy 0, policy_version 79560 (0.0007) -[2023-10-15 05:29:20,506][88300] Updated weights for policy 1, policy_version 80042 (0.0010) -[2023-10-15 05:29:20,815][88298] Updated weights for policy 0, policy_version 79570 (0.0007) -[2023-10-15 05:29:20,876][88300] Updated weights for policy 1, policy_version 80052 (0.0009) -[2023-10-15 05:29:21,183][88298] Updated weights for policy 0, policy_version 79580 (0.0007) -[2023-10-15 05:29:21,231][88300] Updated weights for policy 1, policy_version 80062 (0.0009) -[2023-10-15 05:29:23,534][87330] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 163479552. Throughput: 0: 1701.9, 1: 1708.2. Samples: 40876524. Policy #0 lag: (min: 15.0, avg: 22.8, max: 47.0) -[2023-10-15 05:29:23,534][87330] Avg episode reward: [(0, '22.970'), (1, '22.960')] -[2023-10-15 05:29:25,016][88300] Updated weights for policy 1, policy_version 80072 (0.0007) -[2023-10-15 05:29:25,128][88298] Updated weights for policy 0, policy_version 79590 (0.0008) -[2023-10-15 05:29:25,376][88300] Updated weights for policy 1, policy_version 80082 (0.0010) -[2023-10-15 05:29:25,493][88298] Updated weights for policy 0, policy_version 79600 (0.0009) -[2023-10-15 05:29:25,747][88300] Updated weights for policy 1, policy_version 80092 (0.0008) -[2023-10-15 05:29:25,872][88298] Updated weights for policy 0, policy_version 79610 (0.0009) -[2023-10-15 05:29:28,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 163545088. Throughput: 0: 1727.1, 1: 1743.1. Samples: 40898342. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:29:28,534][87330] Avg episode reward: [(0, '22.960'), (1, '22.920')] -[2023-10-15 05:29:29,715][88300] Updated weights for policy 1, policy_version 80102 (0.0008) -[2023-10-15 05:29:29,850][88298] Updated weights for policy 0, policy_version 79620 (0.0008) -[2023-10-15 05:29:30,089][88300] Updated weights for policy 1, policy_version 80112 (0.0008) -[2023-10-15 05:29:30,222][88298] Updated weights for policy 0, policy_version 79630 (0.0008) -[2023-10-15 05:29:30,459][88300] Updated weights for policy 1, policy_version 80122 (0.0007) -[2023-10-15 05:29:30,597][88298] Updated weights for policy 0, policy_version 79640 (0.0008) -[2023-10-15 05:29:33,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 163610624. Throughput: 0: 1710.2, 1: 1716.1. Samples: 40907826. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:29:33,535][87330] Avg episode reward: [(0, '22.990'), (1, '23.080')] -[2023-10-15 05:29:34,477][88300] Updated weights for policy 1, policy_version 80132 (0.0007) -[2023-10-15 05:29:34,627][88298] Updated weights for policy 0, policy_version 79650 (0.0007) -[2023-10-15 05:29:34,847][88300] Updated weights for policy 1, policy_version 80142 (0.0008) -[2023-10-15 05:29:34,996][88298] Updated weights for policy 0, policy_version 79660 (0.0008) -[2023-10-15 05:29:35,202][88300] Updated weights for policy 1, policy_version 80152 (0.0007) -[2023-10-15 05:29:35,370][88298] Updated weights for policy 0, policy_version 79670 (0.0009) -[2023-10-15 05:29:35,731][88298] Updated weights for policy 0, policy_version 79680 (0.0008) -[2023-10-15 05:29:38,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 163676160. Throughput: 0: 1708.0, 1: 1732.8. Samples: 40928826. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:29:38,534][87330] Avg episode reward: [(0, '22.960'), (1, '23.100')] -[2023-10-15 05:29:39,225][88300] Updated weights for policy 1, policy_version 80162 (0.0009) -[2023-10-15 05:29:39,596][88300] Updated weights for policy 1, policy_version 80172 (0.0008) -[2023-10-15 05:29:39,668][88298] Updated weights for policy 0, policy_version 79690 (0.0007) -[2023-10-15 05:29:39,963][88300] Updated weights for policy 1, policy_version 80182 (0.0007) -[2023-10-15 05:29:40,038][88298] Updated weights for policy 0, policy_version 79700 (0.0007) -[2023-10-15 05:29:40,328][88300] Updated weights for policy 1, policy_version 80192 (0.0007) -[2023-10-15 05:29:40,422][88298] Updated weights for policy 0, policy_version 79710 (0.0008) -[2023-10-15 05:29:43,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 163741696. Throughput: 0: 1734.4, 1: 1749.7. Samples: 40950526. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:29:43,534][87330] Avg episode reward: [(0, '23.000'), (1, '23.050')] -[2023-10-15 05:29:44,054][88300] Updated weights for policy 1, policy_version 80202 (0.0007) -[2023-10-15 05:29:44,278][88298] Updated weights for policy 0, policy_version 79720 (0.0009) -[2023-10-15 05:29:44,411][88300] Updated weights for policy 1, policy_version 80212 (0.0007) -[2023-10-15 05:29:44,651][88298] Updated weights for policy 0, policy_version 79730 (0.0008) -[2023-10-15 05:29:44,776][88300] Updated weights for policy 1, policy_version 80222 (0.0007) -[2023-10-15 05:29:45,011][88298] Updated weights for policy 0, policy_version 79740 (0.0009) -[2023-10-15 05:29:48,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 163807232. Throughput: 0: 1705.6, 1: 1724.1. Samples: 40960054. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:29:48,535][87330] Avg episode reward: [(0, '22.990'), (1, '22.760')] -[2023-10-15 05:29:48,693][88300] Updated weights for policy 1, policy_version 80232 (0.0010) -[2023-10-15 05:29:48,994][88298] Updated weights for policy 0, policy_version 79750 (0.0009) -[2023-10-15 05:29:49,047][88300] Updated weights for policy 1, policy_version 80242 (0.0008) -[2023-10-15 05:29:49,361][88298] Updated weights for policy 0, policy_version 79760 (0.0007) -[2023-10-15 05:29:49,418][88300] Updated weights for policy 1, policy_version 80252 (0.0007) -[2023-10-15 05:29:49,729][88298] Updated weights for policy 0, policy_version 79770 (0.0007) -[2023-10-15 05:29:53,202][88300] Updated weights for policy 1, policy_version 80262 (0.0010) -[2023-10-15 05:29:53,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 163872768. Throughput: 0: 1730.5, 1: 1756.3. Samples: 40981598. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:29:53,535][87330] Avg episode reward: [(0, '22.980'), (1, '22.730')] -[2023-10-15 05:29:53,574][88300] Updated weights for policy 1, policy_version 80272 (0.0009) -[2023-10-15 05:29:53,625][88298] Updated weights for policy 0, policy_version 79780 (0.0009) -[2023-10-15 05:29:53,938][88300] Updated weights for policy 1, policy_version 80282 (0.0009) -[2023-10-15 05:29:54,001][88298] Updated weights for policy 0, policy_version 79790 (0.0008) -[2023-10-15 05:29:54,372][88298] Updated weights for policy 0, policy_version 79800 (0.0008) -[2023-10-15 05:29:57,679][88300] Updated weights for policy 1, policy_version 80292 (0.0008) -[2023-10-15 05:29:58,069][88300] Updated weights for policy 1, policy_version 80302 (0.0010) -[2023-10-15 05:29:58,102][88298] Updated weights for policy 0, policy_version 79810 (0.0008) -[2023-10-15 05:29:58,436][88300] Updated weights for policy 1, policy_version 80312 (0.0007) -[2023-10-15 05:29:58,481][88298] Updated weights for policy 0, policy_version 79820 (0.0008) -[2023-10-15 05:29:58,534][87330] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 13773.7). Total num frames: 163938304. Throughput: 0: 1742.9, 1: 1744.6. Samples: 41002808. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:29:58,536][87330] Avg episode reward: [(0, '23.000'), (1, '22.800')] -[2023-10-15 05:29:58,843][88298] Updated weights for policy 0, policy_version 79830 (0.0008) -[2023-10-15 05:29:59,214][88298] Updated weights for policy 0, policy_version 79840 (0.0010) -[2023-10-15 05:30:02,310][88300] Updated weights for policy 1, policy_version 80322 (0.0007) -[2023-10-15 05:30:02,679][88300] Updated weights for policy 1, policy_version 80332 (0.0010) -[2023-10-15 05:30:03,042][88300] Updated weights for policy 1, policy_version 80342 (0.0009) -[2023-10-15 05:30:03,225][88298] Updated weights for policy 0, policy_version 79850 (0.0007) -[2023-10-15 05:30:03,412][88300] Updated weights for policy 1, policy_version 80352 (0.0007) -[2023-10-15 05:30:03,534][87330] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 164036608. Throughput: 0: 1725.1, 1: 1754.8. Samples: 41012946. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:30:03,534][87330] Avg episode reward: [(0, '22.990'), (1, '22.740')] -[2023-10-15 05:30:03,593][88298] Updated weights for policy 0, policy_version 79860 (0.0010) -[2023-10-15 05:30:03,970][88298] Updated weights for policy 0, policy_version 79870 (0.0011) -[2023-10-15 05:30:07,293][88300] Updated weights for policy 1, policy_version 80362 (0.0007) -[2023-10-15 05:30:07,659][88300] Updated weights for policy 1, policy_version 80372 (0.0008) -[2023-10-15 05:30:07,783][88298] Updated weights for policy 0, policy_version 79880 (0.0009) -[2023-10-15 05:30:08,024][88300] Updated weights for policy 1, policy_version 80382 (0.0007) -[2023-10-15 05:30:08,158][88298] Updated weights for policy 0, policy_version 79890 (0.0007) -[2023-10-15 05:30:08,520][88298] Updated weights for policy 0, policy_version 79900 (0.0009) -[2023-10-15 05:30:08,534][87330] Fps is (10 sec: 16384.8, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 164102144. Throughput: 0: 1743.6, 1: 1763.3. Samples: 41034334. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:30:08,534][87330] Avg episode reward: [(0, '22.970'), (1, '22.510')] -[2023-10-15 05:30:12,005][88300] Updated weights for policy 1, policy_version 80392 (0.0008) -[2023-10-15 05:30:12,381][88300] Updated weights for policy 1, policy_version 80402 (0.0008) -[2023-10-15 05:30:12,481][88298] Updated weights for policy 0, policy_version 79910 (0.0008) -[2023-10-15 05:30:12,745][88300] Updated weights for policy 1, policy_version 80412 (0.0007) -[2023-10-15 05:30:12,847][88298] Updated weights for policy 0, policy_version 79920 (0.0008) -[2023-10-15 05:30:13,218][88298] Updated weights for policy 0, policy_version 79930 (0.0009) -[2023-10-15 05:30:13,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 164200448. Throughput: 0: 1731.1, 1: 1731.8. Samples: 41054170. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:30:13,535][87330] Avg episode reward: [(0, '22.990'), (1, '22.530')] -[2023-10-15 05:30:16,633][88300] Updated weights for policy 1, policy_version 80422 (0.0008) -[2023-10-15 05:30:16,999][88300] Updated weights for policy 1, policy_version 80432 (0.0007) -[2023-10-15 05:30:17,291][88298] Updated weights for policy 0, policy_version 79940 (0.0008) -[2023-10-15 05:30:17,368][88300] Updated weights for policy 1, policy_version 80442 (0.0008) -[2023-10-15 05:30:17,657][88298] Updated weights for policy 0, policy_version 79950 (0.0009) -[2023-10-15 05:30:18,022][88298] Updated weights for policy 0, policy_version 79960 (0.0010) -[2023-10-15 05:30:18,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 164265984. Throughput: 0: 1739.0, 1: 1761.1. Samples: 41065332. Policy #0 lag: (min: 23.0, avg: 28.7, max: 55.0) -[2023-10-15 05:30:18,534][87330] Avg episode reward: [(0, '22.990'), (1, '22.780')] -[2023-10-15 05:30:21,411][88300] Updated weights for policy 1, policy_version 80452 (0.0008) -[2023-10-15 05:30:21,777][88300] Updated weights for policy 1, policy_version 80462 (0.0009) -[2023-10-15 05:30:21,993][88298] Updated weights for policy 0, policy_version 79970 (0.0010) -[2023-10-15 05:30:22,136][88300] Updated weights for policy 1, policy_version 80472 (0.0007) -[2023-10-15 05:30:22,368][88298] Updated weights for policy 0, policy_version 79980 (0.0007) -[2023-10-15 05:30:22,737][88298] Updated weights for policy 0, policy_version 79990 (0.0007) -[2023-10-15 05:30:23,100][88298] Updated weights for policy 0, policy_version 80000 (0.0009) -[2023-10-15 05:30:23,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 164331520. Throughput: 0: 1747.9, 1: 1740.4. Samples: 41085802. Policy #0 lag: (min: 23.0, avg: 28.7, max: 55.0) -[2023-10-15 05:30:23,535][87330] Avg episode reward: [(0, '23.000'), (1, '22.850')] -[2023-10-15 05:30:25,946][88300] Updated weights for policy 1, policy_version 80482 (0.0009) -[2023-10-15 05:30:26,302][88300] Updated weights for policy 1, policy_version 80492 (0.0008) -[2023-10-15 05:30:26,677][88300] Updated weights for policy 1, policy_version 80502 (0.0008) -[2023-10-15 05:30:27,032][88298] Updated weights for policy 0, policy_version 80010 (0.0008) -[2023-10-15 05:30:27,038][88300] Updated weights for policy 1, policy_version 80512 (0.0008) -[2023-10-15 05:30:27,398][88298] Updated weights for policy 0, policy_version 80020 (0.0011) -[2023-10-15 05:30:27,779][88298] Updated weights for policy 0, policy_version 80030 (0.0010) -[2023-10-15 05:30:28,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 164397056. Throughput: 0: 1715.6, 1: 1735.6. Samples: 41105826. Policy #0 lag: (min: 23.0, avg: 28.7, max: 55.0) -[2023-10-15 05:30:28,534][87330] Avg episode reward: [(0, '22.990'), (1, '22.900')] -[2023-10-15 05:30:30,742][88300] Updated weights for policy 1, policy_version 80522 (0.0008) -[2023-10-15 05:30:31,106][88300] Updated weights for policy 1, policy_version 80532 (0.0008) -[2023-10-15 05:30:31,477][88300] Updated weights for policy 1, policy_version 80542 (0.0008) -[2023-10-15 05:30:31,754][88298] Updated weights for policy 0, policy_version 80040 (0.0009) -[2023-10-15 05:30:32,118][88298] Updated weights for policy 0, policy_version 80050 (0.0008) -[2023-10-15 05:30:32,491][88298] Updated weights for policy 0, policy_version 80060 (0.0009) -[2023-10-15 05:30:33,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 164462592. Throughput: 0: 1739.5, 1: 1746.6. Samples: 41116930. Policy #0 lag: (min: 23.0, avg: 28.7, max: 55.0) -[2023-10-15 05:30:33,535][87330] Avg episode reward: [(0, '22.980'), (1, '22.960')] -[2023-10-15 05:30:35,535][88300] Updated weights for policy 1, policy_version 80552 (0.0008) -[2023-10-15 05:30:35,899][88300] Updated weights for policy 1, policy_version 80562 (0.0009) -[2023-10-15 05:30:36,270][88300] Updated weights for policy 1, policy_version 80572 (0.0008) -[2023-10-15 05:30:36,438][88298] Updated weights for policy 0, policy_version 80070 (0.0009) -[2023-10-15 05:30:36,808][88298] Updated weights for policy 0, policy_version 80080 (0.0008) -[2023-10-15 05:30:37,166][88298] Updated weights for policy 0, policy_version 80090 (0.0009) -[2023-10-15 05:30:38,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 164528128. Throughput: 0: 1728.7, 1: 1730.8. Samples: 41137276. Policy #0 lag: (min: 23.0, avg: 28.7, max: 55.0) -[2023-10-15 05:30:38,535][87330] Avg episode reward: [(0, '22.980'), (1, '22.700')] -[2023-10-15 05:30:40,015][88300] Updated weights for policy 1, policy_version 80582 (0.0008) -[2023-10-15 05:30:40,392][88300] Updated weights for policy 1, policy_version 80592 (0.0007) -[2023-10-15 05:30:40,747][88300] Updated weights for policy 1, policy_version 80602 (0.0009) -[2023-10-15 05:30:41,150][88298] Updated weights for policy 0, policy_version 80100 (0.0008) -[2023-10-15 05:30:41,524][88298] Updated weights for policy 0, policy_version 80110 (0.0009) -[2023-10-15 05:30:41,890][88298] Updated weights for policy 0, policy_version 80120 (0.0007) -[2023-10-15 05:30:43,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 164593664. Throughput: 0: 1706.0, 1: 1756.2. Samples: 41158606. Policy #0 lag: (min: 23.0, avg: 28.7, max: 55.0) -[2023-10-15 05:30:43,535][87330] Avg episode reward: [(0, '22.970'), (1, '22.840')] -[2023-10-15 05:30:44,673][88300] Updated weights for policy 1, policy_version 80612 (0.0007) -[2023-10-15 05:30:45,084][88300] Updated weights for policy 1, policy_version 80622 (0.0010) -[2023-10-15 05:30:45,448][88300] Updated weights for policy 1, policy_version 80632 (0.0010) -[2023-10-15 05:30:45,901][88298] Updated weights for policy 0, policy_version 80130 (0.0007) -[2023-10-15 05:30:46,270][88298] Updated weights for policy 0, policy_version 80140 (0.0008) -[2023-10-15 05:30:46,644][88298] Updated weights for policy 0, policy_version 80150 (0.0009) -[2023-10-15 05:30:47,004][88298] Updated weights for policy 0, policy_version 80160 (0.0010) -[2023-10-15 05:30:48,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 164659200. Throughput: 0: 1736.1, 1: 1733.8. Samples: 41169092. Policy #0 lag: (min: 23.0, avg: 28.7, max: 55.0) -[2023-10-15 05:30:48,535][87330] Avg episode reward: [(0, '22.980'), (1, '22.850')] -[2023-10-15 05:30:49,335][88300] Updated weights for policy 1, policy_version 80642 (0.0009) -[2023-10-15 05:30:49,694][88300] Updated weights for policy 1, policy_version 80652 (0.0009) -[2023-10-15 05:30:50,058][88300] Updated weights for policy 1, policy_version 80662 (0.0010) -[2023-10-15 05:30:50,419][88300] Updated weights for policy 1, policy_version 80672 (0.0010) -[2023-10-15 05:30:50,901][88298] Updated weights for policy 0, policy_version 80170 (0.0007) -[2023-10-15 05:30:51,274][88298] Updated weights for policy 0, policy_version 80180 (0.0007) -[2023-10-15 05:30:51,640][88298] Updated weights for policy 0, policy_version 80190 (0.0007) -[2023-10-15 05:30:53,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 164724736. Throughput: 0: 1708.0, 1: 1740.3. Samples: 41189508. Policy #0 lag: (min: 23.0, avg: 28.7, max: 55.0) -[2023-10-15 05:30:53,535][87330] Avg episode reward: [(0, '22.990'), (1, '22.630')] -[2023-10-15 05:30:54,245][88300] Updated weights for policy 1, policy_version 80682 (0.0007) -[2023-10-15 05:30:54,612][88300] Updated weights for policy 1, policy_version 80692 (0.0008) -[2023-10-15 05:30:54,988][88300] Updated weights for policy 1, policy_version 80702 (0.0010) -[2023-10-15 05:30:55,474][88298] Updated weights for policy 0, policy_version 80200 (0.0008) -[2023-10-15 05:30:55,845][88298] Updated weights for policy 0, policy_version 80210 (0.0007) -[2023-10-15 05:30:56,206][88298] Updated weights for policy 0, policy_version 80220 (0.0009) -[2023-10-15 05:30:58,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.6, 300 sec: 13773.7). Total num frames: 164790272. Throughput: 0: 1717.8, 1: 1768.7. Samples: 41211062. Policy #0 lag: (min: 23.0, avg: 28.7, max: 55.0) -[2023-10-15 05:30:58,534][87330] Avg episode reward: [(0, '22.970'), (1, '22.620')] -[2023-10-15 05:30:58,543][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000080224_82149376.pth... -[2023-10-15 05:30:58,579][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000078624_80510976.pth -[2023-10-15 05:30:58,693][88300] Updated weights for policy 1, policy_version 80712 (0.0007) -[2023-10-15 05:30:59,055][88300] Updated weights for policy 1, policy_version 80722 (0.0007) -[2023-10-15 05:30:59,416][88300] Updated weights for policy 1, policy_version 80732 (0.0007) -[2023-10-15 05:30:59,559][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000080736_82673664.pth... -[2023-10-15 05:30:59,592][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000079104_81002496.pth -[2023-10-15 05:30:59,921][88298] Updated weights for policy 0, policy_version 80230 (0.0009) -[2023-10-15 05:31:00,293][88298] Updated weights for policy 0, policy_version 80240 (0.0008) -[2023-10-15 05:31:00,662][88298] Updated weights for policy 0, policy_version 80250 (0.0007) -[2023-10-15 05:31:03,256][88300] Updated weights for policy 1, policy_version 80742 (0.0008) -[2023-10-15 05:31:03,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 164855808. Throughput: 0: 1718.4, 1: 1740.6. Samples: 41220986. Policy #0 lag: (min: 23.0, avg: 28.7, max: 55.0) -[2023-10-15 05:31:03,534][87330] Avg episode reward: [(0, '23.000'), (1, '22.580')] -[2023-10-15 05:31:03,625][88300] Updated weights for policy 1, policy_version 80752 (0.0008) -[2023-10-15 05:31:03,992][88300] Updated weights for policy 1, policy_version 80762 (0.0009) -[2023-10-15 05:31:04,604][88298] Updated weights for policy 0, policy_version 80260 (0.0007) -[2023-10-15 05:31:04,976][88298] Updated weights for policy 0, policy_version 80270 (0.0009) -[2023-10-15 05:31:05,341][88298] Updated weights for policy 0, policy_version 80280 (0.0011) -[2023-10-15 05:31:08,067][88300] Updated weights for policy 1, policy_version 80772 (0.0009) -[2023-10-15 05:31:08,438][88300] Updated weights for policy 1, policy_version 80782 (0.0009) -[2023-10-15 05:31:08,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 164921344. Throughput: 0: 1711.2, 1: 1762.1. Samples: 41242100. Policy #0 lag: (min: 23.0, avg: 28.7, max: 55.0) -[2023-10-15 05:31:08,535][87330] Avg episode reward: [(0, '22.910'), (1, '22.760')] -[2023-10-15 05:31:08,807][88300] Updated weights for policy 1, policy_version 80792 (0.0008) -[2023-10-15 05:31:09,321][88298] Updated weights for policy 0, policy_version 80290 (0.0010) -[2023-10-15 05:31:09,691][88298] Updated weights for policy 0, policy_version 80300 (0.0007) -[2023-10-15 05:31:10,054][88298] Updated weights for policy 0, policy_version 80310 (0.0010) -[2023-10-15 05:31:10,425][88298] Updated weights for policy 0, policy_version 80320 (0.0010) -[2023-10-15 05:31:12,785][88300] Updated weights for policy 1, policy_version 80802 (0.0010) -[2023-10-15 05:31:13,148][88300] Updated weights for policy 1, policy_version 80812 (0.0009) -[2023-10-15 05:31:13,519][88300] Updated weights for policy 1, policy_version 80822 (0.0011) -[2023-10-15 05:31:13,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 164986880. Throughput: 0: 1740.0, 1: 1756.2. Samples: 41263154. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-15 05:31:13,535][87330] Avg episode reward: [(0, '22.590'), (1, '22.890')] -[2023-10-15 05:31:13,880][88300] Updated weights for policy 1, policy_version 80832 (0.0007) -[2023-10-15 05:31:14,342][88298] Updated weights for policy 0, policy_version 80330 (0.0007) -[2023-10-15 05:31:14,713][88298] Updated weights for policy 0, policy_version 80340 (0.0008) -[2023-10-15 05:31:15,078][88298] Updated weights for policy 0, policy_version 80350 (0.0009) -[2023-10-15 05:31:17,761][88300] Updated weights for policy 1, policy_version 80842 (0.0009) -[2023-10-15 05:31:18,131][88300] Updated weights for policy 1, policy_version 80852 (0.0009) -[2023-10-15 05:31:18,501][88300] Updated weights for policy 1, policy_version 80862 (0.0008) -[2023-10-15 05:31:18,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.1, 300 sec: 13773.7). Total num frames: 165052416. Throughput: 0: 1714.8, 1: 1757.2. Samples: 41273172. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-15 05:31:18,535][87330] Avg episode reward: [(0, '22.380'), (1, '22.900')] -[2023-10-15 05:31:19,174][88298] Updated weights for policy 0, policy_version 80360 (0.0010) -[2023-10-15 05:31:19,539][88298] Updated weights for policy 0, policy_version 80370 (0.0008) -[2023-10-15 05:31:19,919][88298] Updated weights for policy 0, policy_version 80380 (0.0010) -[2023-10-15 05:31:22,310][88300] Updated weights for policy 1, policy_version 80872 (0.0008) -[2023-10-15 05:31:22,682][88300] Updated weights for policy 1, policy_version 80882 (0.0007) -[2023-10-15 05:31:23,047][88300] Updated weights for policy 1, policy_version 80892 (0.0008) -[2023-10-15 05:31:23,534][87330] Fps is (10 sec: 16384.2, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 165150720. Throughput: 0: 1723.8, 1: 1768.4. Samples: 41294424. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-15 05:31:23,534][87330] Avg episode reward: [(0, '22.380'), (1, '22.950')] -[2023-10-15 05:31:23,803][88298] Updated weights for policy 0, policy_version 80390 (0.0009) -[2023-10-15 05:31:24,176][88298] Updated weights for policy 0, policy_version 80400 (0.0010) -[2023-10-15 05:31:24,544][88298] Updated weights for policy 0, policy_version 80410 (0.0009) -[2023-10-15 05:31:26,882][88300] Updated weights for policy 1, policy_version 80902 (0.0009) -[2023-10-15 05:31:27,247][88300] Updated weights for policy 1, policy_version 80912 (0.0007) -[2023-10-15 05:31:27,608][88300] Updated weights for policy 1, policy_version 80922 (0.0008) -[2023-10-15 05:31:28,521][88298] Updated weights for policy 0, policy_version 80420 (0.0008) -[2023-10-15 05:31:28,534][87330] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 165216256. Throughput: 0: 1748.5, 1: 1729.8. Samples: 41315130. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-15 05:31:28,535][87330] Avg episode reward: [(0, '22.330'), (1, '23.100')] -[2023-10-15 05:31:28,904][88298] Updated weights for policy 0, policy_version 80430 (0.0007) -[2023-10-15 05:31:29,265][88298] Updated weights for policy 0, policy_version 80440 (0.0010) -[2023-10-15 05:31:31,471][88300] Updated weights for policy 1, policy_version 80932 (0.0010) -[2023-10-15 05:31:31,870][88300] Updated weights for policy 1, policy_version 80942 (0.0007) -[2023-10-15 05:31:32,236][88300] Updated weights for policy 1, policy_version 80952 (0.0007) -[2023-10-15 05:31:33,008][88298] Updated weights for policy 0, policy_version 80450 (0.0010) -[2023-10-15 05:31:33,378][88298] Updated weights for policy 0, policy_version 80460 (0.0008) -[2023-10-15 05:31:33,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 165281792. Throughput: 0: 1719.5, 1: 1766.0. Samples: 41325936. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-15 05:31:33,535][87330] Avg episode reward: [(0, '22.110'), (1, '23.150')] -[2023-10-15 05:31:33,537][88033] Saving new best policy, reward=23.150! -[2023-10-15 05:31:33,740][88298] Updated weights for policy 0, policy_version 80470 (0.0007) -[2023-10-15 05:31:34,117][88298] Updated weights for policy 0, policy_version 80480 (0.0007) -[2023-10-15 05:31:36,268][88300] Updated weights for policy 1, policy_version 80962 (0.0007) -[2023-10-15 05:31:36,638][88300] Updated weights for policy 1, policy_version 80972 (0.0007) -[2023-10-15 05:31:37,002][88300] Updated weights for policy 1, policy_version 80982 (0.0007) -[2023-10-15 05:31:37,362][88300] Updated weights for policy 1, policy_version 80992 (0.0010) -[2023-10-15 05:31:38,187][88298] Updated weights for policy 0, policy_version 80490 (0.0009) -[2023-10-15 05:31:38,534][87330] Fps is (10 sec: 13107.7, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 165347328. Throughput: 0: 1749.9, 1: 1729.9. Samples: 41346100. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-15 05:31:38,534][87330] Avg episode reward: [(0, '22.210'), (1, '23.170')] -[2023-10-15 05:31:38,535][88033] Saving new best policy, reward=23.170! -[2023-10-15 05:31:38,547][88298] Updated weights for policy 0, policy_version 80500 (0.0007) -[2023-10-15 05:31:38,914][88298] Updated weights for policy 0, policy_version 80510 (0.0008) -[2023-10-15 05:31:41,185][88300] Updated weights for policy 1, policy_version 81002 (0.0008) -[2023-10-15 05:31:41,549][88300] Updated weights for policy 1, policy_version 81012 (0.0010) -[2023-10-15 05:31:41,911][88300] Updated weights for policy 1, policy_version 81022 (0.0008) -[2023-10-15 05:31:42,852][88298] Updated weights for policy 0, policy_version 80520 (0.0010) -[2023-10-15 05:31:43,223][88298] Updated weights for policy 0, policy_version 80530 (0.0009) -[2023-10-15 05:31:43,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 165412864. Throughput: 0: 1746.8, 1: 1723.7. Samples: 41367234. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-15 05:31:43,534][87330] Avg episode reward: [(0, '22.470'), (1, '23.140')] -[2023-10-15 05:31:43,591][88298] Updated weights for policy 0, policy_version 80540 (0.0008) -[2023-10-15 05:31:45,892][88300] Updated weights for policy 1, policy_version 81032 (0.0007) -[2023-10-15 05:31:46,255][88300] Updated weights for policy 1, policy_version 81042 (0.0009) -[2023-10-15 05:31:46,619][88300] Updated weights for policy 1, policy_version 81052 (0.0010) -[2023-10-15 05:31:47,606][88298] Updated weights for policy 0, policy_version 80550 (0.0007) -[2023-10-15 05:31:47,972][88298] Updated weights for policy 0, policy_version 80560 (0.0009) -[2023-10-15 05:31:48,345][88298] Updated weights for policy 0, policy_version 80570 (0.0008) -[2023-10-15 05:31:48,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 165478400. Throughput: 0: 1736.4, 1: 1736.5. Samples: 41377270. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-15 05:31:48,534][87330] Avg episode reward: [(0, '22.790'), (1, '22.900')] -[2023-10-15 05:31:50,509][88300] Updated weights for policy 1, policy_version 81062 (0.0010) -[2023-10-15 05:31:50,872][88300] Updated weights for policy 1, policy_version 81072 (0.0008) -[2023-10-15 05:31:51,242][88300] Updated weights for policy 1, policy_version 81082 (0.0009) -[2023-10-15 05:31:52,174][88298] Updated weights for policy 0, policy_version 80580 (0.0009) -[2023-10-15 05:31:52,541][88298] Updated weights for policy 0, policy_version 80590 (0.0010) -[2023-10-15 05:31:52,924][88298] Updated weights for policy 0, policy_version 80600 (0.0007) -[2023-10-15 05:31:53,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 165576704. Throughput: 0: 1744.0, 1: 1724.9. Samples: 41398202. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-15 05:31:53,535][87330] Avg episode reward: [(0, '22.620'), (1, '22.910')] -[2023-10-15 05:31:55,199][88300] Updated weights for policy 1, policy_version 81092 (0.0010) -[2023-10-15 05:31:55,572][88300] Updated weights for policy 1, policy_version 81102 (0.0008) -[2023-10-15 05:31:55,935][88300] Updated weights for policy 1, policy_version 81112 (0.0010) -[2023-10-15 05:31:56,969][88298] Updated weights for policy 0, policy_version 80610 (0.0008) -[2023-10-15 05:31:57,337][88298] Updated weights for policy 0, policy_version 80620 (0.0007) -[2023-10-15 05:31:57,712][88298] Updated weights for policy 0, policy_version 80630 (0.0008) -[2023-10-15 05:31:58,073][88298] Updated weights for policy 0, policy_version 80640 (0.0008) -[2023-10-15 05:31:58,534][87330] Fps is (10 sec: 16383.5, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 165642240. Throughput: 0: 1719.2, 1: 1741.4. Samples: 41418882. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-15 05:31:58,535][87330] Avg episode reward: [(0, '22.380'), (1, '22.890')] -[2023-10-15 05:31:59,788][88300] Updated weights for policy 1, policy_version 81122 (0.0008) -[2023-10-15 05:32:00,152][88300] Updated weights for policy 1, policy_version 81132 (0.0008) -[2023-10-15 05:32:00,515][88300] Updated weights for policy 1, policy_version 81142 (0.0007) -[2023-10-15 05:32:00,884][88300] Updated weights for policy 1, policy_version 81152 (0.0007) -[2023-10-15 05:32:01,869][88298] Updated weights for policy 0, policy_version 80650 (0.0008) -[2023-10-15 05:32:02,237][88298] Updated weights for policy 0, policy_version 80660 (0.0010) -[2023-10-15 05:32:02,610][88298] Updated weights for policy 0, policy_version 80670 (0.0009) -[2023-10-15 05:32:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 165707776. Throughput: 0: 1744.8, 1: 1729.8. Samples: 41429532. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-15 05:32:03,535][87330] Avg episode reward: [(0, '22.550'), (1, '22.840')] -[2023-10-15 05:32:04,616][88300] Updated weights for policy 1, policy_version 81162 (0.0007) -[2023-10-15 05:32:04,983][88300] Updated weights for policy 1, policy_version 81172 (0.0007) -[2023-10-15 05:32:05,348][88300] Updated weights for policy 1, policy_version 81182 (0.0007) -[2023-10-15 05:32:06,431][88298] Updated weights for policy 0, policy_version 80680 (0.0009) -[2023-10-15 05:32:06,794][88298] Updated weights for policy 0, policy_version 80690 (0.0008) -[2023-10-15 05:32:07,165][88298] Updated weights for policy 0, policy_version 80700 (0.0010) -[2023-10-15 05:32:08,534][87330] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 165773312. Throughput: 0: 1732.5, 1: 1739.6. Samples: 41450666. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-15 05:32:08,534][87330] Avg episode reward: [(0, '22.150'), (1, '22.820')] -[2023-10-15 05:32:09,149][88300] Updated weights for policy 1, policy_version 81192 (0.0008) -[2023-10-15 05:32:09,520][88300] Updated weights for policy 1, policy_version 81202 (0.0008) -[2023-10-15 05:32:09,889][88300] Updated weights for policy 1, policy_version 81212 (0.0009) -[2023-10-15 05:32:10,992][88298] Updated weights for policy 0, policy_version 80710 (0.0008) -[2023-10-15 05:32:11,363][88298] Updated weights for policy 0, policy_version 80720 (0.0008) -[2023-10-15 05:32:11,736][88298] Updated weights for policy 0, policy_version 80730 (0.0011) -[2023-10-15 05:32:13,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 165838848. Throughput: 0: 1713.6, 1: 1768.7. Samples: 41471832. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-15 05:32:13,534][87330] Avg episode reward: [(0, '22.140'), (1, '22.800')] -[2023-10-15 05:32:13,730][88300] Updated weights for policy 1, policy_version 81222 (0.0009) -[2023-10-15 05:32:14,105][88300] Updated weights for policy 1, policy_version 81232 (0.0008) -[2023-10-15 05:32:14,467][88300] Updated weights for policy 1, policy_version 81242 (0.0009) -[2023-10-15 05:32:15,595][88298] Updated weights for policy 0, policy_version 80740 (0.0010) -[2023-10-15 05:32:15,970][88298] Updated weights for policy 0, policy_version 80750 (0.0010) -[2023-10-15 05:32:16,333][88298] Updated weights for policy 0, policy_version 80760 (0.0011) -[2023-10-15 05:32:18,456][88300] Updated weights for policy 1, policy_version 81252 (0.0009) -[2023-10-15 05:32:18,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 165904384. Throughput: 0: 1738.8, 1: 1739.0. Samples: 41482434. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-15 05:32:18,534][87330] Avg episode reward: [(0, '22.060'), (1, '23.070')] -[2023-10-15 05:32:18,866][88300] Updated weights for policy 1, policy_version 81262 (0.0008) -[2023-10-15 05:32:19,221][88300] Updated weights for policy 1, policy_version 81272 (0.0007) -[2023-10-15 05:32:20,301][88298] Updated weights for policy 0, policy_version 80770 (0.0011) -[2023-10-15 05:32:20,666][88298] Updated weights for policy 0, policy_version 80780 (0.0009) -[2023-10-15 05:32:21,029][88298] Updated weights for policy 0, policy_version 80790 (0.0009) -[2023-10-15 05:32:21,398][88298] Updated weights for policy 0, policy_version 80800 (0.0008) -[2023-10-15 05:32:23,036][88300] Updated weights for policy 1, policy_version 81282 (0.0007) -[2023-10-15 05:32:23,407][88300] Updated weights for policy 1, policy_version 81292 (0.0007) -[2023-10-15 05:32:23,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 165969920. Throughput: 0: 1717.3, 1: 1768.8. Samples: 41502976. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-15 05:32:23,535][87330] Avg episode reward: [(0, '22.240'), (1, '22.700')] -[2023-10-15 05:32:23,779][88300] Updated weights for policy 1, policy_version 81302 (0.0007) -[2023-10-15 05:32:24,132][88300] Updated weights for policy 1, policy_version 81312 (0.0011) -[2023-10-15 05:32:25,394][88298] Updated weights for policy 0, policy_version 80810 (0.0009) -[2023-10-15 05:32:25,778][88298] Updated weights for policy 0, policy_version 80820 (0.0009) -[2023-10-15 05:32:26,141][88298] Updated weights for policy 0, policy_version 80830 (0.0009) -[2023-10-15 05:32:27,997][88300] Updated weights for policy 1, policy_version 81322 (0.0009) -[2023-10-15 05:32:28,366][88300] Updated weights for policy 1, policy_version 81332 (0.0008) -[2023-10-15 05:32:28,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 166035456. Throughput: 0: 1721.8, 1: 1760.0. Samples: 41523914. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-15 05:32:28,534][87330] Avg episode reward: [(0, '22.140'), (1, '22.700')] -[2023-10-15 05:32:28,740][88300] Updated weights for policy 1, policy_version 81342 (0.0008) -[2023-10-15 05:32:30,099][88298] Updated weights for policy 0, policy_version 80840 (0.0011) -[2023-10-15 05:32:30,469][88298] Updated weights for policy 0, policy_version 80850 (0.0010) -[2023-10-15 05:32:30,842][88298] Updated weights for policy 0, policy_version 80860 (0.0007) -[2023-10-15 05:32:32,674][88300] Updated weights for policy 1, policy_version 81352 (0.0010) -[2023-10-15 05:32:33,033][88300] Updated weights for policy 1, policy_version 81362 (0.0010) -[2023-10-15 05:32:33,403][88300] Updated weights for policy 1, policy_version 81372 (0.0008) -[2023-10-15 05:32:33,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 166100992. Throughput: 0: 1729.9, 1: 1760.2. Samples: 41534322. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-15 05:32:33,535][87330] Avg episode reward: [(0, '22.410'), (1, '22.720')] -[2023-10-15 05:32:34,794][88298] Updated weights for policy 0, policy_version 80870 (0.0008) -[2023-10-15 05:32:35,169][88298] Updated weights for policy 0, policy_version 80880 (0.0009) -[2023-10-15 05:32:35,545][88298] Updated weights for policy 0, policy_version 80890 (0.0009) -[2023-10-15 05:32:37,280][88300] Updated weights for policy 1, policy_version 81382 (0.0009) -[2023-10-15 05:32:37,661][88300] Updated weights for policy 1, policy_version 81392 (0.0009) -[2023-10-15 05:32:38,027][88300] Updated weights for policy 1, policy_version 81402 (0.0009) -[2023-10-15 05:32:38,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 166199296. Throughput: 0: 1723.7, 1: 1774.3. Samples: 41555614. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-15 05:32:38,534][87330] Avg episode reward: [(0, '22.660'), (1, '22.760')] -[2023-10-15 05:32:39,361][88298] Updated weights for policy 0, policy_version 80900 (0.0010) -[2023-10-15 05:32:39,740][88298] Updated weights for policy 0, policy_version 80910 (0.0009) -[2023-10-15 05:32:40,115][88298] Updated weights for policy 0, policy_version 80920 (0.0010) -[2023-10-15 05:32:41,842][88300] Updated weights for policy 1, policy_version 81412 (0.0009) -[2023-10-15 05:32:42,209][88300] Updated weights for policy 1, policy_version 81422 (0.0008) -[2023-10-15 05:32:42,581][88300] Updated weights for policy 1, policy_version 81432 (0.0008) -[2023-10-15 05:32:43,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 166264832. Throughput: 0: 1747.3, 1: 1740.4. Samples: 41575824. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-15 05:32:43,534][87330] Avg episode reward: [(0, '22.770'), (1, '22.760')] -[2023-10-15 05:32:44,056][88298] Updated weights for policy 0, policy_version 80930 (0.0010) -[2023-10-15 05:32:44,428][88298] Updated weights for policy 0, policy_version 80940 (0.0010) -[2023-10-15 05:32:44,791][88298] Updated weights for policy 0, policy_version 80950 (0.0009) -[2023-10-15 05:32:45,160][88298] Updated weights for policy 0, policy_version 80960 (0.0009) -[2023-10-15 05:32:46,509][88300] Updated weights for policy 1, policy_version 81442 (0.0008) -[2023-10-15 05:32:46,874][88300] Updated weights for policy 1, policy_version 81452 (0.0008) -[2023-10-15 05:32:47,245][88300] Updated weights for policy 1, policy_version 81462 (0.0008) -[2023-10-15 05:32:47,606][88300] Updated weights for policy 1, policy_version 81472 (0.0010) -[2023-10-15 05:32:48,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 166330368. Throughput: 0: 1723.5, 1: 1768.0. Samples: 41586646. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-15 05:32:48,534][87330] Avg episode reward: [(0, '22.650'), (1, '22.780')] -[2023-10-15 05:32:49,044][88298] Updated weights for policy 0, policy_version 80970 (0.0007) -[2023-10-15 05:32:49,412][88298] Updated weights for policy 0, policy_version 80980 (0.0007) -[2023-10-15 05:32:49,790][88298] Updated weights for policy 0, policy_version 80990 (0.0009) -[2023-10-15 05:32:51,515][88300] Updated weights for policy 1, policy_version 81482 (0.0007) -[2023-10-15 05:32:51,880][88300] Updated weights for policy 1, policy_version 81492 (0.0008) -[2023-10-15 05:32:52,250][88300] Updated weights for policy 1, policy_version 81502 (0.0008) -[2023-10-15 05:32:53,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 166395904. Throughput: 0: 1739.1, 1: 1736.0. Samples: 41607044. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-15 05:32:53,535][87330] Avg episode reward: [(0, '22.660'), (1, '22.750')] -[2023-10-15 05:32:53,686][88298] Updated weights for policy 0, policy_version 81000 (0.0008) -[2023-10-15 05:32:54,065][88298] Updated weights for policy 0, policy_version 81010 (0.0009) -[2023-10-15 05:32:54,431][88298] Updated weights for policy 0, policy_version 81020 (0.0008) -[2023-10-15 05:32:56,130][88300] Updated weights for policy 1, policy_version 81512 (0.0010) -[2023-10-15 05:32:56,498][88300] Updated weights for policy 1, policy_version 81522 (0.0009) -[2023-10-15 05:32:56,860][88300] Updated weights for policy 1, policy_version 81532 (0.0010) -[2023-10-15 05:32:58,323][88298] Updated weights for policy 0, policy_version 81030 (0.0009) -[2023-10-15 05:32:58,534][87330] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 166461440. Throughput: 0: 1747.5, 1: 1729.6. Samples: 41628300. Policy #0 lag: (min: 7.0, avg: 17.8, max: 39.0) -[2023-10-15 05:32:58,535][87330] Avg episode reward: [(0, '22.580'), (1, '22.840')] -[2023-10-15 05:32:58,547][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000081536_83492864.pth... -[2023-10-15 05:32:58,583][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000079904_81821696.pth -[2023-10-15 05:32:58,587][88033] Saving a milestone ./train_atari/atari_seaquest_APPO/checkpoint_p1/milestones/checkpoint_000081536_83492864.pth -[2023-10-15 05:32:58,703][88298] Updated weights for policy 0, policy_version 81040 (0.0009) -[2023-10-15 05:32:59,067][88298] Updated weights for policy 0, policy_version 81050 (0.0009) -[2023-10-15 05:32:59,290][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000081056_83001344.pth... -[2023-10-15 05:32:59,321][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000079424_81330176.pth -[2023-10-15 05:32:59,327][87905] Saving a milestone ./train_atari/atari_seaquest_APPO/checkpoint_p0/milestones/checkpoint_000081056_83001344.pth -[2023-10-15 05:33:00,855][88300] Updated weights for policy 1, policy_version 81542 (0.0008) -[2023-10-15 05:33:01,211][88300] Updated weights for policy 1, policy_version 81552 (0.0009) -[2023-10-15 05:33:01,579][88300] Updated weights for policy 1, policy_version 81562 (0.0010) -[2023-10-15 05:33:02,901][88298] Updated weights for policy 0, policy_version 81060 (0.0009) -[2023-10-15 05:33:03,275][88298] Updated weights for policy 0, policy_version 81070 (0.0008) -[2023-10-15 05:33:03,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 166526976. Throughput: 0: 1721.2, 1: 1743.7. Samples: 41638356. Policy #0 lag: (min: 7.0, avg: 17.8, max: 39.0) -[2023-10-15 05:33:03,534][87330] Avg episode reward: [(0, '22.370'), (1, '22.800')] -[2023-10-15 05:33:03,644][88298] Updated weights for policy 0, policy_version 81080 (0.0007) -[2023-10-15 05:33:05,668][88300] Updated weights for policy 1, policy_version 81572 (0.0010) -[2023-10-15 05:33:06,034][88300] Updated weights for policy 1, policy_version 81582 (0.0009) -[2023-10-15 05:33:06,392][88300] Updated weights for policy 1, policy_version 81592 (0.0010) -[2023-10-15 05:33:07,786][88298] Updated weights for policy 0, policy_version 81090 (0.0008) -[2023-10-15 05:33:08,154][88298] Updated weights for policy 0, policy_version 81100 (0.0008) -[2023-10-15 05:33:08,527][88298] Updated weights for policy 0, policy_version 81110 (0.0009) -[2023-10-15 05:33:08,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 166592512. Throughput: 0: 1744.3, 1: 1723.3. Samples: 41659018. Policy #0 lag: (min: 7.0, avg: 17.8, max: 39.0) -[2023-10-15 05:33:08,535][87330] Avg episode reward: [(0, '22.350'), (1, '22.790')] -[2023-10-15 05:33:08,896][88298] Updated weights for policy 0, policy_version 81120 (0.0010) -[2023-10-15 05:33:10,313][88300] Updated weights for policy 1, policy_version 81602 (0.0010) -[2023-10-15 05:33:10,715][88300] Updated weights for policy 1, policy_version 81612 (0.0009) -[2023-10-15 05:33:11,087][88300] Updated weights for policy 1, policy_version 81622 (0.0009) -[2023-10-15 05:33:11,449][88300] Updated weights for policy 1, policy_version 81632 (0.0009) -[2023-10-15 05:33:12,930][88298] Updated weights for policy 0, policy_version 81130 (0.0007) -[2023-10-15 05:33:13,305][88298] Updated weights for policy 0, policy_version 81140 (0.0008) -[2023-10-15 05:33:13,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 166658048. Throughput: 0: 1731.4, 1: 1739.9. Samples: 41680122. Policy #0 lag: (min: 7.0, avg: 17.8, max: 39.0) -[2023-10-15 05:33:13,535][87330] Avg episode reward: [(0, '22.260'), (1, '22.780')] -[2023-10-15 05:33:13,674][88298] Updated weights for policy 0, policy_version 81150 (0.0007) -[2023-10-15 05:33:15,225][88300] Updated weights for policy 1, policy_version 81642 (0.0010) -[2023-10-15 05:33:15,597][88300] Updated weights for policy 1, policy_version 81652 (0.0007) -[2023-10-15 05:33:15,963][88300] Updated weights for policy 1, policy_version 81662 (0.0011) -[2023-10-15 05:33:17,567][88298] Updated weights for policy 0, policy_version 81160 (0.0010) -[2023-10-15 05:33:17,933][88298] Updated weights for policy 0, policy_version 81170 (0.0008) -[2023-10-15 05:33:18,303][88298] Updated weights for policy 0, policy_version 81180 (0.0010) -[2023-10-15 05:33:18,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 166756352. Throughput: 0: 1729.0, 1: 1726.8. Samples: 41689834. Policy #0 lag: (min: 7.0, avg: 17.8, max: 39.0) -[2023-10-15 05:33:18,535][87330] Avg episode reward: [(0, '22.480'), (1, '22.550')] -[2023-10-15 05:33:19,861][88300] Updated weights for policy 1, policy_version 81672 (0.0010) -[2023-10-15 05:33:20,222][88300] Updated weights for policy 1, policy_version 81682 (0.0009) -[2023-10-15 05:33:20,589][88300] Updated weights for policy 1, policy_version 81692 (0.0010) -[2023-10-15 05:33:22,171][88298] Updated weights for policy 0, policy_version 81190 (0.0010) -[2023-10-15 05:33:22,552][88298] Updated weights for policy 0, policy_version 81200 (0.0008) -[2023-10-15 05:33:22,918][88298] Updated weights for policy 0, policy_version 81210 (0.0007) -[2023-10-15 05:33:23,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 166821888. Throughput: 0: 1734.8, 1: 1724.6. Samples: 41711288. Policy #0 lag: (min: 7.0, avg: 17.8, max: 39.0) -[2023-10-15 05:33:23,534][87330] Avg episode reward: [(0, '22.400'), (1, '22.530')] -[2023-10-15 05:33:24,497][88300] Updated weights for policy 1, policy_version 81702 (0.0010) -[2023-10-15 05:33:24,863][88300] Updated weights for policy 1, policy_version 81712 (0.0008) -[2023-10-15 05:33:25,234][88300] Updated weights for policy 1, policy_version 81722 (0.0009) -[2023-10-15 05:33:26,866][88298] Updated weights for policy 0, policy_version 81220 (0.0009) -[2023-10-15 05:33:27,231][88298] Updated weights for policy 0, policy_version 81230 (0.0009) -[2023-10-15 05:33:27,602][88298] Updated weights for policy 0, policy_version 81240 (0.0011) -[2023-10-15 05:33:28,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 166887424. Throughput: 0: 1707.9, 1: 1760.8. Samples: 41731916. Policy #0 lag: (min: 7.0, avg: 17.8, max: 39.0) -[2023-10-15 05:33:28,535][87330] Avg episode reward: [(0, '22.510'), (1, '22.670')] -[2023-10-15 05:33:28,873][88300] Updated weights for policy 1, policy_version 81732 (0.0007) -[2023-10-15 05:33:29,242][88300] Updated weights for policy 1, policy_version 81742 (0.0007) -[2023-10-15 05:33:29,609][88300] Updated weights for policy 1, policy_version 81752 (0.0008) -[2023-10-15 05:33:31,536][88298] Updated weights for policy 0, policy_version 81250 (0.0010) -[2023-10-15 05:33:31,914][88298] Updated weights for policy 0, policy_version 81260 (0.0007) -[2023-10-15 05:33:32,282][88298] Updated weights for policy 0, policy_version 81270 (0.0007) -[2023-10-15 05:33:32,654][88298] Updated weights for policy 0, policy_version 81280 (0.0008) -[2023-10-15 05:33:33,508][88300] Updated weights for policy 1, policy_version 81762 (0.0009) -[2023-10-15 05:33:33,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 166952960. Throughput: 0: 1735.2, 1: 1729.7. Samples: 41742566. Policy #0 lag: (min: 7.0, avg: 17.8, max: 39.0) -[2023-10-15 05:33:33,535][87330] Avg episode reward: [(0, '22.790'), (1, '22.790')] -[2023-10-15 05:33:33,884][88300] Updated weights for policy 1, policy_version 81772 (0.0007) -[2023-10-15 05:33:34,251][88300] Updated weights for policy 1, policy_version 81782 (0.0007) -[2023-10-15 05:33:34,618][88300] Updated weights for policy 1, policy_version 81792 (0.0007) -[2023-10-15 05:33:36,573][88298] Updated weights for policy 0, policy_version 81290 (0.0007) -[2023-10-15 05:33:36,947][88298] Updated weights for policy 0, policy_version 81300 (0.0008) -[2023-10-15 05:33:37,310][88298] Updated weights for policy 0, policy_version 81310 (0.0007) -[2023-10-15 05:33:38,521][88300] Updated weights for policy 1, policy_version 81802 (0.0007) -[2023-10-15 05:33:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 167018496. Throughput: 0: 1717.5, 1: 1753.7. Samples: 41763246. Policy #0 lag: (min: 7.0, avg: 17.8, max: 39.0) -[2023-10-15 05:33:38,535][87330] Avg episode reward: [(0, '22.900'), (1, '22.550')] -[2023-10-15 05:33:38,889][88300] Updated weights for policy 1, policy_version 81812 (0.0008) -[2023-10-15 05:33:39,263][88300] Updated weights for policy 1, policy_version 81822 (0.0008) -[2023-10-15 05:33:41,003][88298] Updated weights for policy 0, policy_version 81320 (0.0010) -[2023-10-15 05:33:41,366][88298] Updated weights for policy 0, policy_version 81330 (0.0009) -[2023-10-15 05:33:41,745][88298] Updated weights for policy 0, policy_version 81340 (0.0007) -[2023-10-15 05:33:43,288][88300] Updated weights for policy 1, policy_version 81832 (0.0009) -[2023-10-15 05:33:43,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 167084032. Throughput: 0: 1709.9, 1: 1748.1. Samples: 41783910. Policy #0 lag: (min: 7.0, avg: 17.8, max: 39.0) -[2023-10-15 05:33:43,535][87330] Avg episode reward: [(0, '22.900'), (1, '22.580')] -[2023-10-15 05:33:43,654][88300] Updated weights for policy 1, policy_version 81842 (0.0008) -[2023-10-15 05:33:44,019][88300] Updated weights for policy 1, policy_version 81852 (0.0009) -[2023-10-15 05:33:45,725][88298] Updated weights for policy 0, policy_version 81350 (0.0007) -[2023-10-15 05:33:46,104][88298] Updated weights for policy 0, policy_version 81360 (0.0008) -[2023-10-15 05:33:46,474][88298] Updated weights for policy 0, policy_version 81370 (0.0009) -[2023-10-15 05:33:47,927][88300] Updated weights for policy 1, policy_version 81862 (0.0009) -[2023-10-15 05:33:48,288][88300] Updated weights for policy 1, policy_version 81872 (0.0009) -[2023-10-15 05:33:48,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 167149568. Throughput: 0: 1732.9, 1: 1736.8. Samples: 41794490. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:33:48,534][87330] Avg episode reward: [(0, '22.870'), (1, '22.840')] -[2023-10-15 05:33:48,660][88300] Updated weights for policy 1, policy_version 81882 (0.0009) -[2023-10-15 05:33:50,416][88298] Updated weights for policy 0, policy_version 81380 (0.0009) -[2023-10-15 05:33:50,773][88298] Updated weights for policy 0, policy_version 81390 (0.0008) -[2023-10-15 05:33:51,137][88298] Updated weights for policy 0, policy_version 81400 (0.0010) -[2023-10-15 05:33:52,590][88300] Updated weights for policy 1, policy_version 81892 (0.0007) -[2023-10-15 05:33:52,955][88300] Updated weights for policy 1, policy_version 81902 (0.0010) -[2023-10-15 05:33:53,326][88300] Updated weights for policy 1, policy_version 81912 (0.0008) -[2023-10-15 05:33:53,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 167215104. Throughput: 0: 1706.5, 1: 1761.5. Samples: 41815080. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:33:53,534][87330] Avg episode reward: [(0, '22.850'), (1, '22.850')] -[2023-10-15 05:33:54,954][88298] Updated weights for policy 0, policy_version 81410 (0.0009) -[2023-10-15 05:33:55,321][88298] Updated weights for policy 0, policy_version 81420 (0.0011) -[2023-10-15 05:33:55,697][88298] Updated weights for policy 0, policy_version 81430 (0.0011) -[2023-10-15 05:33:56,049][88298] Updated weights for policy 0, policy_version 81440 (0.0010) -[2023-10-15 05:33:57,132][88300] Updated weights for policy 1, policy_version 81922 (0.0008) -[2023-10-15 05:33:57,557][88300] Updated weights for policy 1, policy_version 81932 (0.0010) -[2023-10-15 05:33:57,931][88300] Updated weights for policy 1, policy_version 81942 (0.0007) -[2023-10-15 05:33:58,302][88300] Updated weights for policy 1, policy_version 81952 (0.0007) -[2023-10-15 05:33:58,534][87330] Fps is (10 sec: 16383.5, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 167313408. Throughput: 0: 1722.7, 1: 1729.6. Samples: 41835478. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:33:58,535][87330] Avg episode reward: [(0, '22.970'), (1, '22.860')] -[2023-10-15 05:34:00,175][88298] Updated weights for policy 0, policy_version 81450 (0.0008) -[2023-10-15 05:34:00,544][88298] Updated weights for policy 0, policy_version 81460 (0.0008) -[2023-10-15 05:34:00,910][88298] Updated weights for policy 0, policy_version 81470 (0.0008) -[2023-10-15 05:34:02,161][88300] Updated weights for policy 1, policy_version 81962 (0.0007) -[2023-10-15 05:34:02,526][88300] Updated weights for policy 1, policy_version 81972 (0.0007) -[2023-10-15 05:34:02,891][88300] Updated weights for policy 1, policy_version 81982 (0.0009) -[2023-10-15 05:34:03,534][87330] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 167378944. Throughput: 0: 1721.1, 1: 1755.6. Samples: 41846286. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:34:03,535][87330] Avg episode reward: [(0, '22.900'), (1, '22.480')] -[2023-10-15 05:34:04,834][88298] Updated weights for policy 0, policy_version 81480 (0.0009) -[2023-10-15 05:34:05,206][88298] Updated weights for policy 0, policy_version 81490 (0.0010) -[2023-10-15 05:34:05,573][88298] Updated weights for policy 0, policy_version 81500 (0.0011) -[2023-10-15 05:34:06,751][88300] Updated weights for policy 1, policy_version 81992 (0.0007) -[2023-10-15 05:34:07,114][88300] Updated weights for policy 1, policy_version 82002 (0.0008) -[2023-10-15 05:34:07,480][88300] Updated weights for policy 1, policy_version 82012 (0.0010) -[2023-10-15 05:34:08,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 167444480. Throughput: 0: 1713.5, 1: 1740.3. Samples: 41866708. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:34:08,535][87330] Avg episode reward: [(0, '22.870'), (1, '22.500')] -[2023-10-15 05:34:09,520][88298] Updated weights for policy 0, policy_version 81510 (0.0009) -[2023-10-15 05:34:09,903][88298] Updated weights for policy 0, policy_version 81520 (0.0010) -[2023-10-15 05:34:10,264][88298] Updated weights for policy 0, policy_version 81530 (0.0009) -[2023-10-15 05:34:11,192][88300] Updated weights for policy 1, policy_version 82022 (0.0010) -[2023-10-15 05:34:11,558][88300] Updated weights for policy 1, policy_version 82032 (0.0008) -[2023-10-15 05:34:11,941][88300] Updated weights for policy 1, policy_version 82042 (0.0009) -[2023-10-15 05:34:13,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 167510016. Throughput: 0: 1747.1, 1: 1722.4. Samples: 41888040. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:34:13,534][87330] Avg episode reward: [(0, '22.830'), (1, '22.620')] -[2023-10-15 05:34:14,175][88298] Updated weights for policy 0, policy_version 81540 (0.0007) -[2023-10-15 05:34:14,536][88298] Updated weights for policy 0, policy_version 81550 (0.0008) -[2023-10-15 05:34:14,915][88298] Updated weights for policy 0, policy_version 81560 (0.0009) -[2023-10-15 05:34:15,863][88300] Updated weights for policy 1, policy_version 82052 (0.0008) -[2023-10-15 05:34:16,226][88300] Updated weights for policy 1, policy_version 82062 (0.0007) -[2023-10-15 05:34:16,590][88300] Updated weights for policy 1, policy_version 82072 (0.0008) -[2023-10-15 05:34:18,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 167575552. Throughput: 0: 1718.1, 1: 1745.0. Samples: 41898406. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:34:18,535][87330] Avg episode reward: [(0, '22.740'), (1, '22.560')] -[2023-10-15 05:34:18,811][88298] Updated weights for policy 0, policy_version 81570 (0.0008) -[2023-10-15 05:34:19,179][88298] Updated weights for policy 0, policy_version 81580 (0.0010) -[2023-10-15 05:34:19,549][88298] Updated weights for policy 0, policy_version 81590 (0.0009) -[2023-10-15 05:34:19,906][88298] Updated weights for policy 0, policy_version 81600 (0.0007) -[2023-10-15 05:34:20,446][88300] Updated weights for policy 1, policy_version 82082 (0.0008) -[2023-10-15 05:34:20,805][88300] Updated weights for policy 1, policy_version 82092 (0.0007) -[2023-10-15 05:34:21,179][88300] Updated weights for policy 1, policy_version 82102 (0.0007) -[2023-10-15 05:34:21,540][88300] Updated weights for policy 1, policy_version 82112 (0.0008) -[2023-10-15 05:34:23,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 167641088. Throughput: 0: 1738.5, 1: 1732.1. Samples: 41919422. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:34:23,535][87330] Avg episode reward: [(0, '22.750'), (1, '22.600')] -[2023-10-15 05:34:23,859][88298] Updated weights for policy 0, policy_version 81610 (0.0011) -[2023-10-15 05:34:24,227][88298] Updated weights for policy 0, policy_version 81620 (0.0009) -[2023-10-15 05:34:24,599][88298] Updated weights for policy 0, policy_version 81630 (0.0009) -[2023-10-15 05:34:25,352][88300] Updated weights for policy 1, policy_version 82122 (0.0007) -[2023-10-15 05:34:25,718][88300] Updated weights for policy 1, policy_version 82132 (0.0009) -[2023-10-15 05:34:26,080][88300] Updated weights for policy 1, policy_version 82142 (0.0010) -[2023-10-15 05:34:28,502][88298] Updated weights for policy 0, policy_version 81640 (0.0009) -[2023-10-15 05:34:28,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 167706624. Throughput: 0: 1749.1, 1: 1744.2. Samples: 41941108. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:34:28,535][87330] Avg episode reward: [(0, '22.500'), (1, '22.600')] -[2023-10-15 05:34:28,862][88298] Updated weights for policy 0, policy_version 81650 (0.0009) -[2023-10-15 05:34:29,236][88298] Updated weights for policy 0, policy_version 81660 (0.0008) -[2023-10-15 05:34:29,972][88300] Updated weights for policy 1, policy_version 82152 (0.0008) -[2023-10-15 05:34:30,340][88300] Updated weights for policy 1, policy_version 82162 (0.0008) -[2023-10-15 05:34:30,708][88300] Updated weights for policy 1, policy_version 82172 (0.0009) -[2023-10-15 05:34:33,188][88298] Updated weights for policy 0, policy_version 81670 (0.0008) -[2023-10-15 05:34:33,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 167772160. Throughput: 0: 1726.0, 1: 1741.7. Samples: 41950538. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:34:33,534][87330] Avg episode reward: [(0, '22.480'), (1, '22.990')] -[2023-10-15 05:34:33,561][88298] Updated weights for policy 0, policy_version 81680 (0.0008) -[2023-10-15 05:34:33,934][88298] Updated weights for policy 0, policy_version 81690 (0.0007) -[2023-10-15 05:34:34,717][88300] Updated weights for policy 1, policy_version 82182 (0.0009) -[2023-10-15 05:34:35,087][88300] Updated weights for policy 1, policy_version 82192 (0.0009) -[2023-10-15 05:34:35,444][88300] Updated weights for policy 1, policy_version 82202 (0.0007) -[2023-10-15 05:34:37,934][88298] Updated weights for policy 0, policy_version 81700 (0.0008) -[2023-10-15 05:34:38,294][88298] Updated weights for policy 0, policy_version 81710 (0.0010) -[2023-10-15 05:34:38,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 167837696. Throughput: 0: 1749.6, 1: 1740.8. Samples: 41972150. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:34:38,534][87330] Avg episode reward: [(0, '22.480'), (1, '23.150')] -[2023-10-15 05:34:38,662][88298] Updated weights for policy 0, policy_version 81720 (0.0008) -[2023-10-15 05:34:39,255][88300] Updated weights for policy 1, policy_version 82212 (0.0008) -[2023-10-15 05:34:39,633][88300] Updated weights for policy 1, policy_version 82222 (0.0007) -[2023-10-15 05:34:40,000][88300] Updated weights for policy 1, policy_version 82232 (0.0008) -[2023-10-15 05:34:42,498][88298] Updated weights for policy 0, policy_version 81730 (0.0008) -[2023-10-15 05:34:42,866][88298] Updated weights for policy 0, policy_version 81740 (0.0008) -[2023-10-15 05:34:43,237][88298] Updated weights for policy 0, policy_version 81750 (0.0009) -[2023-10-15 05:34:43,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 167903232. Throughput: 0: 1742.7, 1: 1771.4. Samples: 41993612. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-15 05:34:43,535][87330] Avg episode reward: [(0, '22.500'), (1, '23.160')] -[2023-10-15 05:34:43,607][88298] Updated weights for policy 0, policy_version 81760 (0.0007) -[2023-10-15 05:34:43,807][88300] Updated weights for policy 1, policy_version 82242 (0.0008) -[2023-10-15 05:34:44,230][88300] Updated weights for policy 1, policy_version 82252 (0.0009) -[2023-10-15 05:34:44,597][88300] Updated weights for policy 1, policy_version 82262 (0.0008) -[2023-10-15 05:34:44,965][88300] Updated weights for policy 1, policy_version 82272 (0.0008) -[2023-10-15 05:34:47,482][88298] Updated weights for policy 0, policy_version 81770 (0.0010) -[2023-10-15 05:34:47,855][88298] Updated weights for policy 0, policy_version 81780 (0.0011) -[2023-10-15 05:34:48,220][88298] Updated weights for policy 0, policy_version 81790 (0.0009) -[2023-10-15 05:34:48,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 168001536. Throughput: 0: 1748.5, 1: 1741.6. Samples: 42003344. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-15 05:34:48,535][87330] Avg episode reward: [(0, '22.460'), (1, '23.150')] -[2023-10-15 05:34:48,857][88300] Updated weights for policy 1, policy_version 82282 (0.0009) -[2023-10-15 05:34:49,222][88300] Updated weights for policy 1, policy_version 82292 (0.0007) -[2023-10-15 05:34:49,594][88300] Updated weights for policy 1, policy_version 82302 (0.0010) -[2023-10-15 05:34:52,192][88298] Updated weights for policy 0, policy_version 81800 (0.0009) -[2023-10-15 05:34:52,564][88298] Updated weights for policy 0, policy_version 81810 (0.0008) -[2023-10-15 05:34:52,928][88298] Updated weights for policy 0, policy_version 81820 (0.0009) -[2023-10-15 05:34:53,520][88300] Updated weights for policy 1, policy_version 82312 (0.0010) -[2023-10-15 05:34:53,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 168067072. Throughput: 0: 1749.2, 1: 1757.3. Samples: 42024500. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-15 05:34:53,535][87330] Avg episode reward: [(0, '22.630'), (1, '23.170')] -[2023-10-15 05:34:53,881][88300] Updated weights for policy 1, policy_version 82322 (0.0011) -[2023-10-15 05:34:54,255][88300] Updated weights for policy 1, policy_version 82332 (0.0010) -[2023-10-15 05:34:56,757][88298] Updated weights for policy 0, policy_version 81830 (0.0008) -[2023-10-15 05:34:57,129][88298] Updated weights for policy 0, policy_version 81840 (0.0007) -[2023-10-15 05:34:57,494][88298] Updated weights for policy 0, policy_version 81850 (0.0007) -[2023-10-15 05:34:58,174][88300] Updated weights for policy 1, policy_version 82342 (0.0010) -[2023-10-15 05:34:58,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 168132608. Throughput: 0: 1714.3, 1: 1762.6. Samples: 42044502. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-15 05:34:58,535][87330] Avg episode reward: [(0, '22.740'), (1, '22.950')] -[2023-10-15 05:34:58,545][88300] Updated weights for policy 1, policy_version 82352 (0.0008) -[2023-10-15 05:34:58,546][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000081856_83820544.pth... -[2023-10-15 05:34:58,586][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000080224_82149376.pth -[2023-10-15 05:34:58,920][88300] Updated weights for policy 1, policy_version 82362 (0.0008) -[2023-10-15 05:34:59,139][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000082368_84344832.pth... -[2023-10-15 05:34:59,179][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000080736_82673664.pth -[2023-10-15 05:35:01,397][88298] Updated weights for policy 0, policy_version 81860 (0.0007) -[2023-10-15 05:35:01,769][88298] Updated weights for policy 0, policy_version 81870 (0.0009) -[2023-10-15 05:35:02,139][88298] Updated weights for policy 0, policy_version 81880 (0.0009) -[2023-10-15 05:35:02,896][88300] Updated weights for policy 1, policy_version 82372 (0.0007) -[2023-10-15 05:35:03,263][88300] Updated weights for policy 1, policy_version 82382 (0.0007) -[2023-10-15 05:35:03,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 168198144. Throughput: 0: 1749.6, 1: 1745.3. Samples: 42055676. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-15 05:35:03,534][87330] Avg episode reward: [(0, '22.840'), (1, '22.890')] -[2023-10-15 05:35:03,625][88300] Updated weights for policy 1, policy_version 82392 (0.0007) -[2023-10-15 05:35:06,045][88298] Updated weights for policy 0, policy_version 81890 (0.0007) -[2023-10-15 05:35:06,416][88298] Updated weights for policy 0, policy_version 81900 (0.0009) -[2023-10-15 05:35:06,778][88298] Updated weights for policy 0, policy_version 81910 (0.0008) -[2023-10-15 05:35:07,150][88298] Updated weights for policy 0, policy_version 81920 (0.0010) -[2023-10-15 05:35:07,573][88300] Updated weights for policy 1, policy_version 82402 (0.0009) -[2023-10-15 05:35:07,946][88300] Updated weights for policy 1, policy_version 82412 (0.0010) -[2023-10-15 05:35:08,306][88300] Updated weights for policy 1, policy_version 82422 (0.0009) -[2023-10-15 05:35:08,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 168263680. Throughput: 0: 1728.3, 1: 1762.1. Samples: 42076490. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-15 05:35:08,535][87330] Avg episode reward: [(0, '22.900'), (1, '22.880')] -[2023-10-15 05:35:08,664][88300] Updated weights for policy 1, policy_version 82432 (0.0007) -[2023-10-15 05:35:10,982][88298] Updated weights for policy 0, policy_version 81930 (0.0008) -[2023-10-15 05:35:11,353][88298] Updated weights for policy 0, policy_version 81940 (0.0009) -[2023-10-15 05:35:11,727][88298] Updated weights for policy 0, policy_version 81950 (0.0010) -[2023-10-15 05:35:12,597][88300] Updated weights for policy 1, policy_version 82442 (0.0010) -[2023-10-15 05:35:12,973][88300] Updated weights for policy 1, policy_version 82452 (0.0009) -[2023-10-15 05:35:13,347][88300] Updated weights for policy 1, policy_version 82462 (0.0009) -[2023-10-15 05:35:13,534][87330] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 168361984. Throughput: 0: 1720.5, 1: 1732.0. Samples: 42096470. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-15 05:35:13,535][87330] Avg episode reward: [(0, '22.920'), (1, '22.760')] -[2023-10-15 05:35:15,738][88298] Updated weights for policy 0, policy_version 81960 (0.0011) -[2023-10-15 05:35:16,107][88298] Updated weights for policy 0, policy_version 81970 (0.0007) -[2023-10-15 05:35:16,481][88298] Updated weights for policy 0, policy_version 81980 (0.0009) -[2023-10-15 05:35:17,181][88300] Updated weights for policy 1, policy_version 82472 (0.0011) -[2023-10-15 05:35:17,563][88300] Updated weights for policy 1, policy_version 82482 (0.0009) -[2023-10-15 05:35:17,932][88300] Updated weights for policy 1, policy_version 82492 (0.0008) -[2023-10-15 05:35:18,534][87330] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 168427520. Throughput: 0: 1743.3, 1: 1755.2. Samples: 42107970. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-15 05:35:18,534][87330] Avg episode reward: [(0, '22.960'), (1, '22.770')] -[2023-10-15 05:35:20,327][88298] Updated weights for policy 0, policy_version 81990 (0.0009) -[2023-10-15 05:35:20,707][88298] Updated weights for policy 0, policy_version 82000 (0.0008) -[2023-10-15 05:35:21,081][88298] Updated weights for policy 0, policy_version 82010 (0.0008) -[2023-10-15 05:35:21,875][88300] Updated weights for policy 1, policy_version 82502 (0.0008) -[2023-10-15 05:35:22,242][88300] Updated weights for policy 1, policy_version 82512 (0.0007) -[2023-10-15 05:35:22,613][88300] Updated weights for policy 1, policy_version 82522 (0.0007) -[2023-10-15 05:35:23,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 168493056. Throughput: 0: 1720.6, 1: 1741.3. Samples: 42127938. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-15 05:35:23,534][87330] Avg episode reward: [(0, '22.950'), (1, '22.570')] -[2023-10-15 05:35:25,004][88298] Updated weights for policy 0, policy_version 82020 (0.0009) -[2023-10-15 05:35:25,373][88298] Updated weights for policy 0, policy_version 82030 (0.0008) -[2023-10-15 05:35:25,748][88298] Updated weights for policy 0, policy_version 82040 (0.0007) -[2023-10-15 05:35:26,449][88300] Updated weights for policy 1, policy_version 82532 (0.0008) -[2023-10-15 05:35:26,820][88300] Updated weights for policy 1, policy_version 82542 (0.0009) -[2023-10-15 05:35:27,183][88300] Updated weights for policy 1, policy_version 82552 (0.0007) -[2023-10-15 05:35:28,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 168558592. Throughput: 0: 1723.6, 1: 1723.5. Samples: 42148732. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-15 05:35:28,535][87330] Avg episode reward: [(0, '22.980'), (1, '22.700')] -[2023-10-15 05:35:29,540][88298] Updated weights for policy 0, policy_version 82050 (0.0007) -[2023-10-15 05:35:29,900][88298] Updated weights for policy 0, policy_version 82060 (0.0007) -[2023-10-15 05:35:30,271][88298] Updated weights for policy 0, policy_version 82070 (0.0008) -[2023-10-15 05:35:30,643][88298] Updated weights for policy 0, policy_version 82080 (0.0009) -[2023-10-15 05:35:31,144][88300] Updated weights for policy 1, policy_version 82562 (0.0008) -[2023-10-15 05:35:31,521][88300] Updated weights for policy 1, policy_version 82572 (0.0009) -[2023-10-15 05:35:31,897][88300] Updated weights for policy 1, policy_version 82582 (0.0008) -[2023-10-15 05:35:32,256][88300] Updated weights for policy 1, policy_version 82592 (0.0009) -[2023-10-15 05:35:33,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 168624128. Throughput: 0: 1714.1, 1: 1755.6. Samples: 42159482. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:35:33,535][87330] Avg episode reward: [(0, '22.980'), (1, '22.780')] -[2023-10-15 05:35:34,620][88298] Updated weights for policy 0, policy_version 82090 (0.0007) -[2023-10-15 05:35:34,999][88298] Updated weights for policy 0, policy_version 82100 (0.0008) -[2023-10-15 05:35:35,361][88298] Updated weights for policy 0, policy_version 82110 (0.0008) -[2023-10-15 05:35:36,222][88300] Updated weights for policy 1, policy_version 82602 (0.0007) -[2023-10-15 05:35:36,591][88300] Updated weights for policy 1, policy_version 82612 (0.0008) -[2023-10-15 05:35:36,950][88300] Updated weights for policy 1, policy_version 82622 (0.0007) -[2023-10-15 05:35:38,534][87330] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 168689664. Throughput: 0: 1721.7, 1: 1728.4. Samples: 42179752. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:35:38,534][87330] Avg episode reward: [(0, '22.970'), (1, '22.810')] -[2023-10-15 05:35:39,410][88298] Updated weights for policy 0, policy_version 82120 (0.0007) -[2023-10-15 05:35:39,780][88298] Updated weights for policy 0, policy_version 82130 (0.0007) -[2023-10-15 05:35:40,151][88298] Updated weights for policy 0, policy_version 82140 (0.0007) -[2023-10-15 05:35:40,809][88300] Updated weights for policy 1, policy_version 82632 (0.0008) -[2023-10-15 05:35:41,169][88300] Updated weights for policy 1, policy_version 82642 (0.0008) -[2023-10-15 05:35:41,543][88300] Updated weights for policy 1, policy_version 82652 (0.0009) -[2023-10-15 05:35:43,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 168755200. Throughput: 0: 1751.1, 1: 1731.8. Samples: 42201230. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:35:43,535][87330] Avg episode reward: [(0, '22.970'), (1, '22.940')] -[2023-10-15 05:35:44,104][88298] Updated weights for policy 0, policy_version 82150 (0.0008) -[2023-10-15 05:35:44,475][88298] Updated weights for policy 0, policy_version 82160 (0.0010) -[2023-10-15 05:35:44,847][88298] Updated weights for policy 0, policy_version 82170 (0.0007) -[2023-10-15 05:35:45,408][88300] Updated weights for policy 1, policy_version 82662 (0.0008) -[2023-10-15 05:35:45,783][88300] Updated weights for policy 1, policy_version 82672 (0.0007) -[2023-10-15 05:35:46,143][88300] Updated weights for policy 1, policy_version 82682 (0.0009) -[2023-10-15 05:35:48,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 168820736. Throughput: 0: 1715.7, 1: 1733.8. Samples: 42210904. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:35:48,534][87330] Avg episode reward: [(0, '22.940'), (1, '22.940')] -[2023-10-15 05:35:48,628][88298] Updated weights for policy 0, policy_version 82180 (0.0007) -[2023-10-15 05:35:49,003][88298] Updated weights for policy 0, policy_version 82190 (0.0008) -[2023-10-15 05:35:49,372][88298] Updated weights for policy 0, policy_version 82200 (0.0008) -[2023-10-15 05:35:50,218][88300] Updated weights for policy 1, policy_version 82692 (0.0009) -[2023-10-15 05:35:50,586][88300] Updated weights for policy 1, policy_version 82702 (0.0009) -[2023-10-15 05:35:50,958][88300] Updated weights for policy 1, policy_version 82712 (0.0007) -[2023-10-15 05:35:53,242][88298] Updated weights for policy 0, policy_version 82210 (0.0008) -[2023-10-15 05:35:53,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 168886272. Throughput: 0: 1738.2, 1: 1718.6. Samples: 42232048. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:35:53,534][87330] Avg episode reward: [(0, '22.910'), (1, '23.100')] -[2023-10-15 05:35:53,606][88298] Updated weights for policy 0, policy_version 82220 (0.0008) -[2023-10-15 05:35:53,989][88298] Updated weights for policy 0, policy_version 82230 (0.0007) -[2023-10-15 05:35:54,354][88298] Updated weights for policy 0, policy_version 82240 (0.0007) -[2023-10-15 05:35:54,871][88300] Updated weights for policy 1, policy_version 82722 (0.0011) -[2023-10-15 05:35:55,240][88300] Updated weights for policy 1, policy_version 82732 (0.0009) -[2023-10-15 05:35:55,604][88300] Updated weights for policy 1, policy_version 82742 (0.0007) -[2023-10-15 05:35:55,965][88300] Updated weights for policy 1, policy_version 82752 (0.0009) -[2023-10-15 05:35:58,099][88298] Updated weights for policy 0, policy_version 82250 (0.0008) -[2023-10-15 05:35:58,463][88298] Updated weights for policy 0, policy_version 82260 (0.0007) -[2023-10-15 05:35:58,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 168951808. Throughput: 0: 1746.9, 1: 1752.9. Samples: 42253958. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:35:58,534][87330] Avg episode reward: [(0, '22.920'), (1, '23.080')] -[2023-10-15 05:35:58,829][88298] Updated weights for policy 0, policy_version 82270 (0.0007) -[2023-10-15 05:35:59,767][88300] Updated weights for policy 1, policy_version 82762 (0.0009) -[2023-10-15 05:36:00,135][88300] Updated weights for policy 1, policy_version 82772 (0.0008) -[2023-10-15 05:36:00,500][88300] Updated weights for policy 1, policy_version 82782 (0.0010) -[2023-10-15 05:36:02,823][88298] Updated weights for policy 0, policy_version 82280 (0.0009) -[2023-10-15 05:36:03,201][88298] Updated weights for policy 0, policy_version 82290 (0.0007) -[2023-10-15 05:36:03,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 169017344. Throughput: 0: 1728.4, 1: 1729.3. Samples: 42263568. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:36:03,535][87330] Avg episode reward: [(0, '22.930'), (1, '23.040')] -[2023-10-15 05:36:03,573][88298] Updated weights for policy 0, policy_version 82300 (0.0010) -[2023-10-15 05:36:04,564][88300] Updated weights for policy 1, policy_version 82792 (0.0010) -[2023-10-15 05:36:04,940][88300] Updated weights for policy 1, policy_version 82802 (0.0010) -[2023-10-15 05:36:05,302][88300] Updated weights for policy 1, policy_version 82812 (0.0008) -[2023-10-15 05:36:07,527][88298] Updated weights for policy 0, policy_version 82310 (0.0009) -[2023-10-15 05:36:07,885][88298] Updated weights for policy 0, policy_version 82320 (0.0008) -[2023-10-15 05:36:08,258][88298] Updated weights for policy 0, policy_version 82330 (0.0007) -[2023-10-15 05:36:08,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 169115648. Throughput: 0: 1752.4, 1: 1738.3. Samples: 42285020. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:36:08,534][87330] Avg episode reward: [(0, '22.890'), (1, '22.900')] -[2023-10-15 05:36:09,144][88300] Updated weights for policy 1, policy_version 82822 (0.0007) -[2023-10-15 05:36:09,514][88300] Updated weights for policy 1, policy_version 82832 (0.0009) -[2023-10-15 05:36:09,879][88300] Updated weights for policy 1, policy_version 82842 (0.0010) -[2023-10-15 05:36:11,972][88298] Updated weights for policy 0, policy_version 82340 (0.0008) -[2023-10-15 05:36:12,342][88298] Updated weights for policy 0, policy_version 82350 (0.0008) -[2023-10-15 05:36:12,714][88298] Updated weights for policy 0, policy_version 82360 (0.0008) -[2023-10-15 05:36:13,534][87330] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 169181184. Throughput: 0: 1733.1, 1: 1759.8. Samples: 42305912. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:36:13,535][87330] Avg episode reward: [(0, '22.820'), (1, '22.910')] -[2023-10-15 05:36:13,546][88300] Updated weights for policy 1, policy_version 82852 (0.0008) -[2023-10-15 05:36:13,910][88300] Updated weights for policy 1, policy_version 82862 (0.0009) -[2023-10-15 05:36:14,275][88300] Updated weights for policy 1, policy_version 82872 (0.0008) -[2023-10-15 05:36:16,522][88298] Updated weights for policy 0, policy_version 82370 (0.0008) -[2023-10-15 05:36:16,893][88298] Updated weights for policy 0, policy_version 82380 (0.0009) -[2023-10-15 05:36:17,267][88298] Updated weights for policy 0, policy_version 82390 (0.0008) -[2023-10-15 05:36:17,622][88298] Updated weights for policy 0, policy_version 82400 (0.0009) -[2023-10-15 05:36:18,120][88300] Updated weights for policy 1, policy_version 82882 (0.0007) -[2023-10-15 05:36:18,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 169246720. Throughput: 0: 1759.9, 1: 1730.4. Samples: 42316544. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:36:18,535][87330] Avg episode reward: [(0, '22.850'), (1, '22.900')] -[2023-10-15 05:36:18,542][88300] Updated weights for policy 1, policy_version 82892 (0.0010) -[2023-10-15 05:36:18,901][88300] Updated weights for policy 1, policy_version 82902 (0.0007) -[2023-10-15 05:36:19,268][88300] Updated weights for policy 1, policy_version 82912 (0.0009) -[2023-10-15 05:36:21,493][88298] Updated weights for policy 0, policy_version 82410 (0.0008) -[2023-10-15 05:36:21,864][88298] Updated weights for policy 0, policy_version 82420 (0.0008) -[2023-10-15 05:36:22,225][88298] Updated weights for policy 0, policy_version 82430 (0.0010) -[2023-10-15 05:36:23,007][88300] Updated weights for policy 1, policy_version 82922 (0.0008) -[2023-10-15 05:36:23,380][88300] Updated weights for policy 1, policy_version 82932 (0.0008) -[2023-10-15 05:36:23,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 169312256. Throughput: 0: 1746.5, 1: 1763.0. Samples: 42337678. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:36:23,534][87330] Avg episode reward: [(0, '22.750'), (1, '22.900')] -[2023-10-15 05:36:23,752][88300] Updated weights for policy 1, policy_version 82942 (0.0009) -[2023-10-15 05:36:26,291][88298] Updated weights for policy 0, policy_version 82440 (0.0008) -[2023-10-15 05:36:26,660][88298] Updated weights for policy 0, policy_version 82450 (0.0007) -[2023-10-15 05:36:27,031][88298] Updated weights for policy 0, policy_version 82460 (0.0008) -[2023-10-15 05:36:27,688][88300] Updated weights for policy 1, policy_version 82952 (0.0008) -[2023-10-15 05:36:28,064][88300] Updated weights for policy 1, policy_version 82962 (0.0008) -[2023-10-15 05:36:28,424][88300] Updated weights for policy 1, policy_version 82972 (0.0007) -[2023-10-15 05:36:28,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 169377792. Throughput: 0: 1733.4, 1: 1746.1. Samples: 42357806. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:36:28,535][87330] Avg episode reward: [(0, '22.690'), (1, '22.910')] -[2023-10-15 05:36:30,981][88298] Updated weights for policy 0, policy_version 82470 (0.0007) -[2023-10-15 05:36:31,349][88298] Updated weights for policy 0, policy_version 82480 (0.0009) -[2023-10-15 05:36:31,722][88298] Updated weights for policy 0, policy_version 82490 (0.0008) -[2023-10-15 05:36:32,227][88300] Updated weights for policy 1, policy_version 82982 (0.0008) -[2023-10-15 05:36:32,600][88300] Updated weights for policy 1, policy_version 82992 (0.0009) -[2023-10-15 05:36:32,966][88300] Updated weights for policy 1, policy_version 83002 (0.0009) -[2023-10-15 05:36:33,534][87330] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 169476096. Throughput: 0: 1763.8, 1: 1763.2. Samples: 42369616. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:36:33,535][87330] Avg episode reward: [(0, '22.670'), (1, '22.980')] -[2023-10-15 05:36:35,551][88298] Updated weights for policy 0, policy_version 82500 (0.0009) -[2023-10-15 05:36:35,923][88298] Updated weights for policy 0, policy_version 82510 (0.0010) -[2023-10-15 05:36:36,292][88298] Updated weights for policy 0, policy_version 82520 (0.0010) -[2023-10-15 05:36:36,895][88300] Updated weights for policy 1, policy_version 83012 (0.0007) -[2023-10-15 05:36:37,263][88300] Updated weights for policy 1, policy_version 83022 (0.0007) -[2023-10-15 05:36:37,627][88300] Updated weights for policy 1, policy_version 83032 (0.0009) -[2023-10-15 05:36:38,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 169541632. Throughput: 0: 1733.1, 1: 1765.2. Samples: 42389470. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:36:38,535][87330] Avg episode reward: [(0, '22.560'), (1, '22.950')] -[2023-10-15 05:36:40,305][88298] Updated weights for policy 0, policy_version 82530 (0.0010) -[2023-10-15 05:36:40,674][88298] Updated weights for policy 0, policy_version 82540 (0.0007) -[2023-10-15 05:36:41,051][88298] Updated weights for policy 0, policy_version 82550 (0.0007) -[2023-10-15 05:36:41,243][88300] Updated weights for policy 1, policy_version 83042 (0.0008) -[2023-10-15 05:36:41,419][88298] Updated weights for policy 0, policy_version 82560 (0.0007) -[2023-10-15 05:36:41,618][88300] Updated weights for policy 1, policy_version 83052 (0.0011) -[2023-10-15 05:36:41,975][88300] Updated weights for policy 1, policy_version 83062 (0.0011) -[2023-10-15 05:36:42,342][88300] Updated weights for policy 1, policy_version 83072 (0.0011) -[2023-10-15 05:36:43,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 169607168. Throughput: 0: 1730.0, 1: 1746.7. Samples: 42410408. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:36:43,534][87330] Avg episode reward: [(0, '22.600'), (1, '23.100')] -[2023-10-15 05:36:45,238][88298] Updated weights for policy 0, policy_version 82570 (0.0007) -[2023-10-15 05:36:45,609][88298] Updated weights for policy 0, policy_version 82580 (0.0007) -[2023-10-15 05:36:45,989][88298] Updated weights for policy 0, policy_version 82590 (0.0008) -[2023-10-15 05:36:46,175][88300] Updated weights for policy 1, policy_version 83082 (0.0007) -[2023-10-15 05:36:46,551][88300] Updated weights for policy 1, policy_version 83092 (0.0009) -[2023-10-15 05:36:46,918][88300] Updated weights for policy 1, policy_version 83102 (0.0011) -[2023-10-15 05:36:48,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 169672704. Throughput: 0: 1737.9, 1: 1767.3. Samples: 42421302. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:36:48,534][87330] Avg episode reward: [(0, '22.630'), (1, '22.930')] -[2023-10-15 05:36:49,831][88298] Updated weights for policy 0, policy_version 82600 (0.0008) -[2023-10-15 05:36:50,199][88298] Updated weights for policy 0, policy_version 82610 (0.0008) -[2023-10-15 05:36:50,561][88298] Updated weights for policy 0, policy_version 82620 (0.0007) -[2023-10-15 05:36:50,779][88300] Updated weights for policy 1, policy_version 83112 (0.0008) -[2023-10-15 05:36:51,146][88300] Updated weights for policy 1, policy_version 83122 (0.0007) -[2023-10-15 05:36:51,507][88300] Updated weights for policy 1, policy_version 83132 (0.0008) -[2023-10-15 05:36:53,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13884.8). Total num frames: 169738240. Throughput: 0: 1733.0, 1: 1747.4. Samples: 42441640. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:36:53,535][87330] Avg episode reward: [(0, '22.620'), (1, '22.910')] -[2023-10-15 05:36:54,460][88298] Updated weights for policy 0, policy_version 82630 (0.0008) -[2023-10-15 05:36:54,831][88298] Updated weights for policy 0, policy_version 82640 (0.0010) -[2023-10-15 05:36:55,199][88298] Updated weights for policy 0, policy_version 82650 (0.0007) -[2023-10-15 05:36:55,569][88300] Updated weights for policy 1, policy_version 83142 (0.0008) -[2023-10-15 05:36:55,935][88300] Updated weights for policy 1, policy_version 83152 (0.0009) -[2023-10-15 05:36:56,301][88300] Updated weights for policy 1, policy_version 83162 (0.0009) -[2023-10-15 05:36:58,534][87330] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 169803776. Throughput: 0: 1748.8, 1: 1739.4. Samples: 42462880. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:36:58,535][87330] Avg episode reward: [(0, '22.810'), (1, '22.930')] -[2023-10-15 05:36:58,546][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000082656_84639744.pth... -[2023-10-15 05:36:58,546][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000083168_85164032.pth... -[2023-10-15 05:36:58,583][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000081056_83001344.pth -[2023-10-15 05:36:58,583][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000081536_83492864.pth -[2023-10-15 05:36:59,258][88298] Updated weights for policy 0, policy_version 82660 (0.0007) -[2023-10-15 05:36:59,630][88298] Updated weights for policy 0, policy_version 82670 (0.0009) -[2023-10-15 05:37:00,004][88298] Updated weights for policy 0, policy_version 82680 (0.0011) -[2023-10-15 05:37:00,326][88300] Updated weights for policy 1, policy_version 83172 (0.0008) -[2023-10-15 05:37:00,695][88300] Updated weights for policy 1, policy_version 83182 (0.0008) -[2023-10-15 05:37:01,061][88300] Updated weights for policy 1, policy_version 83192 (0.0011) -[2023-10-15 05:37:03,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 169869312. Throughput: 0: 1720.5, 1: 1746.0. Samples: 42472536. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:37:03,534][87330] Avg episode reward: [(0, '22.860'), (1, '22.910')] -[2023-10-15 05:37:04,099][88298] Updated weights for policy 0, policy_version 82690 (0.0009) -[2023-10-15 05:37:04,478][88298] Updated weights for policy 0, policy_version 82700 (0.0011) -[2023-10-15 05:37:04,701][88300] Updated weights for policy 1, policy_version 83202 (0.0009) -[2023-10-15 05:37:04,837][88298] Updated weights for policy 0, policy_version 82710 (0.0009) -[2023-10-15 05:37:05,056][88300] Updated weights for policy 1, policy_version 83212 (0.0008) -[2023-10-15 05:37:05,216][88298] Updated weights for policy 0, policy_version 82720 (0.0008) -[2023-10-15 05:37:05,428][88300] Updated weights for policy 1, policy_version 83222 (0.0008) -[2023-10-15 05:37:05,788][88300] Updated weights for policy 1, policy_version 83232 (0.0007) -[2023-10-15 05:37:08,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 169934848. Throughput: 0: 1730.8, 1: 1738.3. Samples: 42493788. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:37:08,535][87330] Avg episode reward: [(0, '22.880'), (1, '22.940')] -[2023-10-15 05:37:09,124][88298] Updated weights for policy 0, policy_version 82730 (0.0008) -[2023-10-15 05:37:09,487][88298] Updated weights for policy 0, policy_version 82740 (0.0007) -[2023-10-15 05:37:09,863][88298] Updated weights for policy 0, policy_version 82750 (0.0008) -[2023-10-15 05:37:09,966][88300] Updated weights for policy 1, policy_version 83242 (0.0008) -[2023-10-15 05:37:10,343][88300] Updated weights for policy 1, policy_version 83252 (0.0010) -[2023-10-15 05:37:10,704][88300] Updated weights for policy 1, policy_version 83262 (0.0008) -[2023-10-15 05:37:13,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 170000384. Throughput: 0: 1747.3, 1: 1750.1. Samples: 42515192. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:37:13,535][87330] Avg episode reward: [(0, '22.950'), (1, '22.940')] -[2023-10-15 05:37:13,817][88298] Updated weights for policy 0, policy_version 82760 (0.0011) -[2023-10-15 05:37:14,199][88298] Updated weights for policy 0, policy_version 82770 (0.0008) -[2023-10-15 05:37:14,556][88298] Updated weights for policy 0, policy_version 82780 (0.0009) -[2023-10-15 05:37:14,667][88300] Updated weights for policy 1, policy_version 83272 (0.0009) -[2023-10-15 05:37:15,023][88300] Updated weights for policy 1, policy_version 83282 (0.0009) -[2023-10-15 05:37:15,387][88300] Updated weights for policy 1, policy_version 83292 (0.0011) -[2023-10-15 05:37:18,471][88298] Updated weights for policy 0, policy_version 82790 (0.0007) -[2023-10-15 05:37:18,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 170065920. Throughput: 0: 1714.4, 1: 1726.2. Samples: 42524440. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:37:18,535][87330] Avg episode reward: [(0, '22.850'), (1, '23.070')] -[2023-10-15 05:37:18,846][88298] Updated weights for policy 0, policy_version 82800 (0.0007) -[2023-10-15 05:37:19,212][88298] Updated weights for policy 0, policy_version 82810 (0.0007) -[2023-10-15 05:37:19,318][88300] Updated weights for policy 1, policy_version 83302 (0.0008) -[2023-10-15 05:37:19,679][88300] Updated weights for policy 1, policy_version 83312 (0.0008) -[2023-10-15 05:37:20,039][88300] Updated weights for policy 1, policy_version 83322 (0.0008) -[2023-10-15 05:37:23,116][88298] Updated weights for policy 0, policy_version 82820 (0.0007) -[2023-10-15 05:37:23,484][88298] Updated weights for policy 0, policy_version 82830 (0.0007) -[2023-10-15 05:37:23,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 170131456. Throughput: 0: 1745.1, 1: 1731.2. Samples: 42545900. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:37:23,534][87330] Avg episode reward: [(0, '22.840'), (1, '23.090')] -[2023-10-15 05:37:23,856][88298] Updated weights for policy 0, policy_version 82840 (0.0008) -[2023-10-15 05:37:24,034][88300] Updated weights for policy 1, policy_version 83332 (0.0009) -[2023-10-15 05:37:24,400][88300] Updated weights for policy 1, policy_version 83342 (0.0010) -[2023-10-15 05:37:24,766][88300] Updated weights for policy 1, policy_version 83352 (0.0009) -[2023-10-15 05:37:27,907][88298] Updated weights for policy 0, policy_version 82850 (0.0008) -[2023-10-15 05:37:28,273][88298] Updated weights for policy 0, policy_version 82860 (0.0007) -[2023-10-15 05:37:28,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 170196992. Throughput: 0: 1745.4, 1: 1743.8. Samples: 42567424. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:37:28,534][87330] Avg episode reward: [(0, '22.730'), (1, '23.080')] -[2023-10-15 05:37:28,547][88300] Updated weights for policy 1, policy_version 83362 (0.0007) -[2023-10-15 05:37:28,647][88298] Updated weights for policy 0, policy_version 82870 (0.0007) -[2023-10-15 05:37:28,907][88300] Updated weights for policy 1, policy_version 83372 (0.0008) -[2023-10-15 05:37:29,009][88298] Updated weights for policy 0, policy_version 82880 (0.0007) -[2023-10-15 05:37:29,268][88300] Updated weights for policy 1, policy_version 83382 (0.0007) -[2023-10-15 05:37:29,639][88300] Updated weights for policy 1, policy_version 83392 (0.0010) -[2023-10-15 05:37:32,803][88298] Updated weights for policy 0, policy_version 82890 (0.0009) -[2023-10-15 05:37:33,167][88298] Updated weights for policy 0, policy_version 82900 (0.0008) -[2023-10-15 05:37:33,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 170262528. Throughput: 0: 1735.7, 1: 1722.5. Samples: 42576924. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:37:33,534][87330] Avg episode reward: [(0, '22.550'), (1, '23.090')] -[2023-10-15 05:37:33,539][88298] Updated weights for policy 0, policy_version 82910 (0.0009) -[2023-10-15 05:37:33,607][88300] Updated weights for policy 1, policy_version 83402 (0.0008) -[2023-10-15 05:37:33,966][88300] Updated weights for policy 1, policy_version 83412 (0.0007) -[2023-10-15 05:37:34,336][88300] Updated weights for policy 1, policy_version 83422 (0.0008) -[2023-10-15 05:37:37,538][88298] Updated weights for policy 0, policy_version 82920 (0.0008) -[2023-10-15 05:37:37,908][88298] Updated weights for policy 0, policy_version 82930 (0.0008) -[2023-10-15 05:37:38,269][88300] Updated weights for policy 1, policy_version 83432 (0.0008) -[2023-10-15 05:37:38,282][88298] Updated weights for policy 0, policy_version 82940 (0.0008) -[2023-10-15 05:37:38,534][87330] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 170360832. Throughput: 0: 1737.7, 1: 1745.5. Samples: 42598386. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:37:38,534][87330] Avg episode reward: [(0, '22.510'), (1, '23.050')] -[2023-10-15 05:37:38,631][88300] Updated weights for policy 1, policy_version 83442 (0.0007) -[2023-10-15 05:37:39,004][88300] Updated weights for policy 1, policy_version 83452 (0.0009) -[2023-10-15 05:37:42,105][88298] Updated weights for policy 0, policy_version 82950 (0.0008) -[2023-10-15 05:37:42,471][88298] Updated weights for policy 0, policy_version 82960 (0.0007) -[2023-10-15 05:37:42,748][88300] Updated weights for policy 1, policy_version 83462 (0.0007) -[2023-10-15 05:37:42,836][88298] Updated weights for policy 0, policy_version 82970 (0.0007) -[2023-10-15 05:37:43,117][88300] Updated weights for policy 1, policy_version 83472 (0.0007) -[2023-10-15 05:37:43,476][88300] Updated weights for policy 1, policy_version 83482 (0.0007) -[2023-10-15 05:37:43,534][87330] Fps is (10 sec: 16383.6, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 170426368. Throughput: 0: 1720.8, 1: 1739.3. Samples: 42618586. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:37:43,535][87330] Avg episode reward: [(0, '22.540'), (1, '23.000')] -[2023-10-15 05:37:46,823][88298] Updated weights for policy 0, policy_version 82980 (0.0008) -[2023-10-15 05:37:47,195][88298] Updated weights for policy 0, policy_version 82990 (0.0008) -[2023-10-15 05:37:47,226][88300] Updated weights for policy 1, policy_version 83492 (0.0008) -[2023-10-15 05:37:47,560][88298] Updated weights for policy 0, policy_version 83000 (0.0008) -[2023-10-15 05:37:47,586][88300] Updated weights for policy 1, policy_version 83502 (0.0009) -[2023-10-15 05:37:47,952][88300] Updated weights for policy 1, policy_version 83512 (0.0007) -[2023-10-15 05:37:48,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 170524672. Throughput: 0: 1744.1, 1: 1754.0. Samples: 42629952. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:37:48,534][87330] Avg episode reward: [(0, '22.650'), (1, '22.910')] -[2023-10-15 05:37:51,542][88298] Updated weights for policy 0, policy_version 83010 (0.0008) -[2023-10-15 05:37:51,908][88298] Updated weights for policy 0, policy_version 83020 (0.0007) -[2023-10-15 05:37:52,015][88300] Updated weights for policy 1, policy_version 83522 (0.0008) -[2023-10-15 05:37:52,267][88298] Updated weights for policy 0, policy_version 83030 (0.0007) -[2023-10-15 05:37:52,378][88300] Updated weights for policy 1, policy_version 83532 (0.0009) -[2023-10-15 05:37:52,644][88298] Updated weights for policy 0, policy_version 83040 (0.0008) -[2023-10-15 05:37:52,733][88300] Updated weights for policy 1, policy_version 83542 (0.0008) -[2023-10-15 05:37:53,096][88300] Updated weights for policy 1, policy_version 83552 (0.0009) -[2023-10-15 05:37:53,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 170590208. Throughput: 0: 1736.0, 1: 1748.4. Samples: 42650588. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:37:53,535][87330] Avg episode reward: [(0, '22.730'), (1, '22.930')] -[2023-10-15 05:37:56,538][88298] Updated weights for policy 0, policy_version 83050 (0.0009) -[2023-10-15 05:37:56,918][88298] Updated weights for policy 0, policy_version 83060 (0.0008) -[2023-10-15 05:37:57,027][88300] Updated weights for policy 1, policy_version 83562 (0.0008) -[2023-10-15 05:37:57,284][88298] Updated weights for policy 0, policy_version 83070 (0.0007) -[2023-10-15 05:37:57,393][88300] Updated weights for policy 1, policy_version 83572 (0.0009) -[2023-10-15 05:37:57,761][88300] Updated weights for policy 1, policy_version 83582 (0.0007) -[2023-10-15 05:37:58,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 170655744. Throughput: 0: 1708.6, 1: 1726.4. Samples: 42669768. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:37:58,534][87330] Avg episode reward: [(0, '22.860'), (1, '22.910')] -[2023-10-15 05:38:01,345][88298] Updated weights for policy 0, policy_version 83080 (0.0009) -[2023-10-15 05:38:01,574][88300] Updated weights for policy 1, policy_version 83592 (0.0008) -[2023-10-15 05:38:01,719][88298] Updated weights for policy 0, policy_version 83090 (0.0009) -[2023-10-15 05:38:01,942][88300] Updated weights for policy 1, policy_version 83602 (0.0010) -[2023-10-15 05:38:02,087][88298] Updated weights for policy 0, policy_version 83100 (0.0007) -[2023-10-15 05:38:02,299][88300] Updated weights for policy 1, policy_version 83612 (0.0010) -[2023-10-15 05:38:03,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 170721280. Throughput: 0: 1744.0, 1: 1759.5. Samples: 42682098. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:38:03,535][87330] Avg episode reward: [(0, '22.890'), (1, '22.930')] -[2023-10-15 05:38:05,888][88298] Updated weights for policy 0, policy_version 83110 (0.0008) -[2023-10-15 05:38:06,094][88300] Updated weights for policy 1, policy_version 83622 (0.0009) -[2023-10-15 05:38:06,250][88298] Updated weights for policy 0, policy_version 83120 (0.0007) -[2023-10-15 05:38:06,454][88300] Updated weights for policy 1, policy_version 83632 (0.0009) -[2023-10-15 05:38:06,613][88298] Updated weights for policy 0, policy_version 83130 (0.0008) -[2023-10-15 05:38:06,831][88300] Updated weights for policy 1, policy_version 83642 (0.0008) -[2023-10-15 05:38:08,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 170786816. Throughput: 0: 1711.2, 1: 1734.9. Samples: 42700976. Policy #0 lag: (min: 12.0, avg: 19.7, max: 44.0) -[2023-10-15 05:38:08,534][87330] Avg episode reward: [(0, '23.100'), (1, '22.940')] -[2023-10-15 05:38:10,338][88298] Updated weights for policy 0, policy_version 83140 (0.0007) -[2023-10-15 05:38:10,715][88298] Updated weights for policy 0, policy_version 83150 (0.0009) -[2023-10-15 05:38:10,843][88300] Updated weights for policy 1, policy_version 83652 (0.0009) -[2023-10-15 05:38:11,073][88298] Updated weights for policy 0, policy_version 83160 (0.0009) -[2023-10-15 05:38:11,209][88300] Updated weights for policy 1, policy_version 83662 (0.0008) -[2023-10-15 05:38:11,584][88300] Updated weights for policy 1, policy_version 83672 (0.0009) -[2023-10-15 05:38:13,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 170852352. Throughput: 0: 1707.9, 1: 1735.9. Samples: 42722396. Policy #0 lag: (min: 12.0, avg: 19.7, max: 44.0) -[2023-10-15 05:38:13,535][87330] Avg episode reward: [(0, '23.080'), (1, '22.960')] -[2023-10-15 05:38:15,076][88298] Updated weights for policy 0, policy_version 83170 (0.0008) -[2023-10-15 05:38:15,447][88298] Updated weights for policy 0, policy_version 83180 (0.0008) -[2023-10-15 05:38:15,542][88300] Updated weights for policy 1, policy_version 83682 (0.0009) -[2023-10-15 05:38:15,815][88298] Updated weights for policy 0, policy_version 83190 (0.0007) -[2023-10-15 05:38:15,905][88300] Updated weights for policy 1, policy_version 83692 (0.0007) -[2023-10-15 05:38:16,176][88298] Updated weights for policy 0, policy_version 83200 (0.0009) -[2023-10-15 05:38:16,269][88300] Updated weights for policy 1, policy_version 83702 (0.0009) -[2023-10-15 05:38:16,629][88300] Updated weights for policy 1, policy_version 83712 (0.0011) -[2023-10-15 05:38:18,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 170917888. Throughput: 0: 1716.9, 1: 1745.9. Samples: 42732752. Policy #0 lag: (min: 12.0, avg: 19.7, max: 44.0) -[2023-10-15 05:38:18,534][87330] Avg episode reward: [(0, '23.080'), (1, '22.980')] -[2023-10-15 05:38:20,224][88298] Updated weights for policy 0, policy_version 83210 (0.0009) -[2023-10-15 05:38:20,458][88300] Updated weights for policy 1, policy_version 83722 (0.0009) -[2023-10-15 05:38:20,608][88298] Updated weights for policy 0, policy_version 83220 (0.0007) -[2023-10-15 05:38:20,829][88300] Updated weights for policy 1, policy_version 83732 (0.0009) -[2023-10-15 05:38:20,978][88298] Updated weights for policy 0, policy_version 83230 (0.0007) -[2023-10-15 05:38:21,192][88300] Updated weights for policy 1, policy_version 83742 (0.0008) -[2023-10-15 05:38:23,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 170983424. Throughput: 0: 1706.8, 1: 1729.7. Samples: 42753028. Policy #0 lag: (min: 12.0, avg: 19.7, max: 44.0) -[2023-10-15 05:38:23,535][87330] Avg episode reward: [(0, '23.090'), (1, '22.950')] -[2023-10-15 05:38:25,033][88298] Updated weights for policy 0, policy_version 83240 (0.0008) -[2023-10-15 05:38:25,155][88300] Updated weights for policy 1, policy_version 83752 (0.0008) -[2023-10-15 05:38:25,404][88298] Updated weights for policy 0, policy_version 83250 (0.0008) -[2023-10-15 05:38:25,519][88300] Updated weights for policy 1, policy_version 83762 (0.0007) -[2023-10-15 05:38:25,767][88298] Updated weights for policy 0, policy_version 83260 (0.0010) -[2023-10-15 05:38:25,880][88300] Updated weights for policy 1, policy_version 83772 (0.0008) -[2023-10-15 05:38:28,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.8). Total num frames: 171048960. Throughput: 0: 1721.1, 1: 1735.6. Samples: 42774134. Policy #0 lag: (min: 12.0, avg: 19.7, max: 44.0) -[2023-10-15 05:38:28,534][87330] Avg episode reward: [(0, '23.110'), (1, '22.960')] -[2023-10-15 05:38:29,721][88298] Updated weights for policy 0, policy_version 83270 (0.0009) -[2023-10-15 05:38:29,899][88300] Updated weights for policy 1, policy_version 83782 (0.0009) -[2023-10-15 05:38:30,080][88298] Updated weights for policy 0, policy_version 83280 (0.0009) -[2023-10-15 05:38:30,269][88300] Updated weights for policy 1, policy_version 83792 (0.0009) -[2023-10-15 05:38:30,455][88298] Updated weights for policy 0, policy_version 83290 (0.0007) -[2023-10-15 05:38:30,628][88300] Updated weights for policy 1, policy_version 83802 (0.0009) -[2023-10-15 05:38:33,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 13884.8). Total num frames: 171114496. Throughput: 0: 1700.6, 1: 1713.9. Samples: 42783604. Policy #0 lag: (min: 12.0, avg: 19.7, max: 44.0) -[2023-10-15 05:38:33,534][87330] Avg episode reward: [(0, '22.920'), (1, '22.940')] -[2023-10-15 05:38:34,446][88298] Updated weights for policy 0, policy_version 83300 (0.0010) -[2023-10-15 05:38:34,723][88300] Updated weights for policy 1, policy_version 83812 (0.0008) -[2023-10-15 05:38:34,816][88298] Updated weights for policy 0, policy_version 83310 (0.0007) -[2023-10-15 05:38:35,091][88300] Updated weights for policy 1, policy_version 83822 (0.0007) -[2023-10-15 05:38:35,181][88298] Updated weights for policy 0, policy_version 83320 (0.0007) -[2023-10-15 05:38:35,449][88300] Updated weights for policy 1, policy_version 83832 (0.0009) -[2023-10-15 05:38:38,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 171180032. Throughput: 0: 1708.0, 1: 1720.0. Samples: 42804848. Policy #0 lag: (min: 12.0, avg: 19.7, max: 44.0) -[2023-10-15 05:38:38,534][87330] Avg episode reward: [(0, '22.900'), (1, '22.820')] -[2023-10-15 05:38:39,001][88298] Updated weights for policy 0, policy_version 83330 (0.0007) -[2023-10-15 05:38:39,284][88300] Updated weights for policy 1, policy_version 83842 (0.0009) -[2023-10-15 05:38:39,373][88298] Updated weights for policy 0, policy_version 83340 (0.0008) -[2023-10-15 05:38:39,647][88300] Updated weights for policy 1, policy_version 83852 (0.0008) -[2023-10-15 05:38:39,737][88298] Updated weights for policy 0, policy_version 83350 (0.0009) -[2023-10-15 05:38:40,016][88300] Updated weights for policy 1, policy_version 83862 (0.0008) -[2023-10-15 05:38:40,099][88298] Updated weights for policy 0, policy_version 83360 (0.0007) -[2023-10-15 05:38:40,382][88300] Updated weights for policy 1, policy_version 83872 (0.0008) -[2023-10-15 05:38:43,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 171245568. Throughput: 0: 1734.5, 1: 1746.7. Samples: 42826420. Policy #0 lag: (min: 12.0, avg: 19.7, max: 44.0) -[2023-10-15 05:38:43,534][87330] Avg episode reward: [(0, '22.910'), (1, '22.840')] -[2023-10-15 05:38:43,978][88298] Updated weights for policy 0, policy_version 83370 (0.0007) -[2023-10-15 05:38:44,345][88298] Updated weights for policy 0, policy_version 83380 (0.0007) -[2023-10-15 05:38:44,423][88300] Updated weights for policy 1, policy_version 83882 (0.0009) -[2023-10-15 05:38:44,718][88298] Updated weights for policy 0, policy_version 83390 (0.0008) -[2023-10-15 05:38:44,791][88300] Updated weights for policy 1, policy_version 83892 (0.0009) -[2023-10-15 05:38:45,159][88300] Updated weights for policy 1, policy_version 83902 (0.0009) -[2023-10-15 05:38:48,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13884.7). Total num frames: 171311104. Throughput: 0: 1705.0, 1: 1708.3. Samples: 42835696. Policy #0 lag: (min: 12.0, avg: 19.7, max: 44.0) -[2023-10-15 05:38:48,535][87330] Avg episode reward: [(0, '22.900'), (1, '22.740')] -[2023-10-15 05:38:48,567][88298] Updated weights for policy 0, policy_version 83400 (0.0009) -[2023-10-15 05:38:48,944][88298] Updated weights for policy 0, policy_version 83410 (0.0009) -[2023-10-15 05:38:49,039][88300] Updated weights for policy 1, policy_version 83912 (0.0008) -[2023-10-15 05:38:49,320][88298] Updated weights for policy 0, policy_version 83420 (0.0007) -[2023-10-15 05:38:49,392][88300] Updated weights for policy 1, policy_version 83922 (0.0008) -[2023-10-15 05:38:49,763][88300] Updated weights for policy 1, policy_version 83932 (0.0007) -[2023-10-15 05:38:53,114][88298] Updated weights for policy 0, policy_version 83430 (0.0007) -[2023-10-15 05:38:53,483][88298] Updated weights for policy 0, policy_version 83440 (0.0008) -[2023-10-15 05:38:53,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 171376640. Throughput: 0: 1730.7, 1: 1738.2. Samples: 42857076. Policy #0 lag: (min: 12.0, avg: 19.7, max: 44.0) -[2023-10-15 05:38:53,534][87330] Avg episode reward: [(0, '22.850'), (1, '22.850')] -[2023-10-15 05:38:53,703][88300] Updated weights for policy 1, policy_version 83942 (0.0008) -[2023-10-15 05:38:53,854][88298] Updated weights for policy 0, policy_version 83450 (0.0007) -[2023-10-15 05:38:54,066][88300] Updated weights for policy 1, policy_version 83952 (0.0009) -[2023-10-15 05:38:54,432][88300] Updated weights for policy 1, policy_version 83962 (0.0009) -[2023-10-15 05:38:57,757][88298] Updated weights for policy 0, policy_version 83460 (0.0009) -[2023-10-15 05:38:58,126][88298] Updated weights for policy 0, policy_version 83470 (0.0007) -[2023-10-15 05:38:58,353][88300] Updated weights for policy 1, policy_version 83972 (0.0009) -[2023-10-15 05:38:58,492][88298] Updated weights for policy 0, policy_version 83480 (0.0007) -[2023-10-15 05:38:58,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 171442176. Throughput: 0: 1735.2, 1: 1736.3. Samples: 42878610. Policy #0 lag: (min: 12.0, avg: 19.7, max: 44.0) -[2023-10-15 05:38:58,534][87330] Avg episode reward: [(0, '22.810'), (1, '22.850')] -[2023-10-15 05:38:58,722][88300] Updated weights for policy 1, policy_version 83982 (0.0010) -[2023-10-15 05:38:58,789][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000083488_85491712.pth... -[2023-10-15 05:38:58,817][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000081856_83820544.pth -[2023-10-15 05:38:59,088][88300] Updated weights for policy 1, policy_version 83992 (0.0009) -[2023-10-15 05:38:59,377][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000084000_86016000.pth... -[2023-10-15 05:38:59,405][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000082368_84344832.pth -[2023-10-15 05:39:02,482][88298] Updated weights for policy 0, policy_version 83490 (0.0007) -[2023-10-15 05:39:02,854][88298] Updated weights for policy 0, policy_version 83500 (0.0009) -[2023-10-15 05:39:03,021][88300] Updated weights for policy 1, policy_version 84002 (0.0009) -[2023-10-15 05:39:03,218][88298] Updated weights for policy 0, policy_version 83510 (0.0009) -[2023-10-15 05:39:03,398][88300] Updated weights for policy 1, policy_version 84012 (0.0008) -[2023-10-15 05:39:03,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 171507712. Throughput: 0: 1730.9, 1: 1725.7. Samples: 42888302. Policy #0 lag: (min: 10.0, avg: 13.2, max: 42.0) -[2023-10-15 05:39:03,534][87330] Avg episode reward: [(0, '22.790'), (1, '22.850')] -[2023-10-15 05:39:03,595][88298] Updated weights for policy 0, policy_version 83520 (0.0008) -[2023-10-15 05:39:03,755][88300] Updated weights for policy 1, policy_version 84022 (0.0008) -[2023-10-15 05:39:04,125][88300] Updated weights for policy 1, policy_version 84032 (0.0007) -[2023-10-15 05:39:07,536][88298] Updated weights for policy 0, policy_version 83530 (0.0009) -[2023-10-15 05:39:07,911][88298] Updated weights for policy 0, policy_version 83540 (0.0009) -[2023-10-15 05:39:08,108][88300] Updated weights for policy 1, policy_version 84042 (0.0008) -[2023-10-15 05:39:08,292][88298] Updated weights for policy 0, policy_version 83550 (0.0009) -[2023-10-15 05:39:08,473][88300] Updated weights for policy 1, policy_version 84052 (0.0008) -[2023-10-15 05:39:08,534][87330] Fps is (10 sec: 16384.2, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 171606016. Throughput: 0: 1742.1, 1: 1740.2. Samples: 42909730. Policy #0 lag: (min: 10.0, avg: 13.2, max: 42.0) -[2023-10-15 05:39:08,534][87330] Avg episode reward: [(0, '22.970'), (1, '22.970')] -[2023-10-15 05:39:08,844][88300] Updated weights for policy 1, policy_version 84062 (0.0008) -[2023-10-15 05:39:12,274][88298] Updated weights for policy 0, policy_version 83560 (0.0009) -[2023-10-15 05:39:12,644][88298] Updated weights for policy 0, policy_version 83570 (0.0008) -[2023-10-15 05:39:12,662][88300] Updated weights for policy 1, policy_version 84072 (0.0009) -[2023-10-15 05:39:13,022][88300] Updated weights for policy 1, policy_version 84082 (0.0008) -[2023-10-15 05:39:13,023][88298] Updated weights for policy 0, policy_version 83580 (0.0008) -[2023-10-15 05:39:13,392][88300] Updated weights for policy 1, policy_version 84092 (0.0008) -[2023-10-15 05:39:13,534][87330] Fps is (10 sec: 19659.7, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 171704320. Throughput: 0: 1726.4, 1: 1717.8. Samples: 42929126. Policy #0 lag: (min: 10.0, avg: 13.2, max: 42.0) -[2023-10-15 05:39:13,535][87330] Avg episode reward: [(0, '23.010'), (1, '22.930')] -[2023-10-15 05:39:17,107][88298] Updated weights for policy 0, policy_version 83590 (0.0008) -[2023-10-15 05:39:17,331][88300] Updated weights for policy 1, policy_version 84102 (0.0008) -[2023-10-15 05:39:17,485][88298] Updated weights for policy 0, policy_version 83600 (0.0007) -[2023-10-15 05:39:17,696][88300] Updated weights for policy 1, policy_version 84112 (0.0007) -[2023-10-15 05:39:17,853][88298] Updated weights for policy 0, policy_version 83610 (0.0008) -[2023-10-15 05:39:18,063][88300] Updated weights for policy 1, policy_version 84122 (0.0008) -[2023-10-15 05:39:18,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 171769856. Throughput: 0: 1741.3, 1: 1738.5. Samples: 42940196. Policy #0 lag: (min: 10.0, avg: 13.2, max: 42.0) -[2023-10-15 05:39:18,534][87330] Avg episode reward: [(0, '23.010'), (1, '22.940')] -[2023-10-15 05:39:21,888][88298] Updated weights for policy 0, policy_version 83620 (0.0007) -[2023-10-15 05:39:22,184][88300] Updated weights for policy 1, policy_version 84132 (0.0009) -[2023-10-15 05:39:22,258][88298] Updated weights for policy 0, policy_version 83630 (0.0009) -[2023-10-15 05:39:22,544][88300] Updated weights for policy 1, policy_version 84142 (0.0008) -[2023-10-15 05:39:22,632][88298] Updated weights for policy 0, policy_version 83640 (0.0007) -[2023-10-15 05:39:22,915][88300] Updated weights for policy 1, policy_version 84152 (0.0008) -[2023-10-15 05:39:23,534][87330] Fps is (10 sec: 13108.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 171835392. Throughput: 0: 1740.4, 1: 1736.4. Samples: 42961300. Policy #0 lag: (min: 10.0, avg: 13.2, max: 42.0) -[2023-10-15 05:39:23,534][87330] Avg episode reward: [(0, '23.040'), (1, '22.810')] -[2023-10-15 05:39:26,629][88298] Updated weights for policy 0, policy_version 83650 (0.0007) -[2023-10-15 05:39:26,947][88300] Updated weights for policy 1, policy_version 84162 (0.0007) -[2023-10-15 05:39:27,003][88298] Updated weights for policy 0, policy_version 83660 (0.0008) -[2023-10-15 05:39:27,304][88300] Updated weights for policy 1, policy_version 84172 (0.0010) -[2023-10-15 05:39:27,364][88298] Updated weights for policy 0, policy_version 83670 (0.0007) -[2023-10-15 05:39:27,668][88300] Updated weights for policy 1, policy_version 84182 (0.0009) -[2023-10-15 05:39:27,737][88298] Updated weights for policy 0, policy_version 83680 (0.0008) -[2023-10-15 05:39:28,038][88300] Updated weights for policy 1, policy_version 84192 (0.0008) -[2023-10-15 05:39:28,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 171900928. Throughput: 0: 1709.5, 1: 1710.2. Samples: 42980310. Policy #0 lag: (min: 10.0, avg: 13.2, max: 42.0) -[2023-10-15 05:39:28,535][87330] Avg episode reward: [(0, '23.050'), (1, '22.780')] -[2023-10-15 05:39:31,629][88298] Updated weights for policy 0, policy_version 83690 (0.0008) -[2023-10-15 05:39:31,949][88300] Updated weights for policy 1, policy_version 84202 (0.0007) -[2023-10-15 05:39:31,994][88298] Updated weights for policy 0, policy_version 83700 (0.0008) -[2023-10-15 05:39:32,326][88300] Updated weights for policy 1, policy_version 84212 (0.0007) -[2023-10-15 05:39:32,360][88298] Updated weights for policy 0, policy_version 83710 (0.0007) -[2023-10-15 05:39:32,695][88300] Updated weights for policy 1, policy_version 84222 (0.0008) -[2023-10-15 05:39:33,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 171966464. Throughput: 0: 1739.9, 1: 1745.9. Samples: 42992558. Policy #0 lag: (min: 10.0, avg: 13.2, max: 42.0) -[2023-10-15 05:39:33,535][87330] Avg episode reward: [(0, '23.070'), (1, '22.540')] -[2023-10-15 05:39:36,316][88298] Updated weights for policy 0, policy_version 83720 (0.0008) -[2023-10-15 05:39:36,550][88300] Updated weights for policy 1, policy_version 84232 (0.0009) -[2023-10-15 05:39:36,686][88298] Updated weights for policy 0, policy_version 83730 (0.0009) -[2023-10-15 05:39:36,915][88300] Updated weights for policy 1, policy_version 84242 (0.0008) -[2023-10-15 05:39:37,062][88298] Updated weights for policy 0, policy_version 83740 (0.0007) -[2023-10-15 05:39:37,276][88300] Updated weights for policy 1, policy_version 84252 (0.0008) -[2023-10-15 05:39:38,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 172032000. Throughput: 0: 1720.6, 1: 1721.0. Samples: 43011950. Policy #0 lag: (min: 10.0, avg: 13.2, max: 42.0) -[2023-10-15 05:39:38,534][87330] Avg episode reward: [(0, '23.030'), (1, '22.240')] -[2023-10-15 05:39:40,890][88298] Updated weights for policy 0, policy_version 83750 (0.0007) -[2023-10-15 05:39:41,102][88300] Updated weights for policy 1, policy_version 84262 (0.0008) -[2023-10-15 05:39:41,258][88298] Updated weights for policy 0, policy_version 83760 (0.0008) -[2023-10-15 05:39:41,460][88300] Updated weights for policy 1, policy_version 84272 (0.0008) -[2023-10-15 05:39:41,623][88298] Updated weights for policy 0, policy_version 83770 (0.0008) -[2023-10-15 05:39:41,833][88300] Updated weights for policy 1, policy_version 84282 (0.0007) -[2023-10-15 05:39:43,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 172097536. Throughput: 0: 1714.9, 1: 1711.4. Samples: 43032794. Policy #0 lag: (min: 10.0, avg: 13.2, max: 42.0) -[2023-10-15 05:39:43,534][87330] Avg episode reward: [(0, '22.890'), (1, '22.170')] -[2023-10-15 05:39:45,308][88298] Updated weights for policy 0, policy_version 83780 (0.0007) -[2023-10-15 05:39:45,686][88298] Updated weights for policy 0, policy_version 83790 (0.0009) -[2023-10-15 05:39:45,898][88300] Updated weights for policy 1, policy_version 84292 (0.0009) -[2023-10-15 05:39:46,051][88298] Updated weights for policy 0, policy_version 83800 (0.0007) -[2023-10-15 05:39:46,264][88300] Updated weights for policy 1, policy_version 84302 (0.0010) -[2023-10-15 05:39:46,619][88300] Updated weights for policy 1, policy_version 84312 (0.0008) -[2023-10-15 05:39:48,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.8). Total num frames: 172163072. Throughput: 0: 1724.0, 1: 1728.5. Samples: 43043666. Policy #0 lag: (min: 10.0, avg: 13.2, max: 42.0) -[2023-10-15 05:39:48,534][87330] Avg episode reward: [(0, '22.830'), (1, '22.200')] -[2023-10-15 05:39:50,088][88298] Updated weights for policy 0, policy_version 83810 (0.0007) -[2023-10-15 05:39:50,390][88300] Updated weights for policy 1, policy_version 84322 (0.0007) -[2023-10-15 05:39:50,458][88298] Updated weights for policy 0, policy_version 83820 (0.0007) -[2023-10-15 05:39:50,759][88300] Updated weights for policy 1, policy_version 84332 (0.0007) -[2023-10-15 05:39:50,833][88298] Updated weights for policy 0, policy_version 83830 (0.0007) -[2023-10-15 05:39:51,120][88300] Updated weights for policy 1, policy_version 84342 (0.0009) -[2023-10-15 05:39:51,204][88298] Updated weights for policy 0, policy_version 83840 (0.0007) -[2023-10-15 05:39:51,492][88300] Updated weights for policy 1, policy_version 84352 (0.0010) -[2023-10-15 05:39:53,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13884.8). Total num frames: 172228608. Throughput: 0: 1706.6, 1: 1711.0. Samples: 43063522. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:39:53,535][87330] Avg episode reward: [(0, '22.810'), (1, '22.360')] -[2023-10-15 05:39:55,196][88298] Updated weights for policy 0, policy_version 83850 (0.0009) -[2023-10-15 05:39:55,418][88300] Updated weights for policy 1, policy_version 84362 (0.0007) -[2023-10-15 05:39:55,578][88298] Updated weights for policy 0, policy_version 83860 (0.0010) -[2023-10-15 05:39:55,781][88300] Updated weights for policy 1, policy_version 84372 (0.0007) -[2023-10-15 05:39:55,939][88298] Updated weights for policy 0, policy_version 83870 (0.0008) -[2023-10-15 05:39:56,155][88300] Updated weights for policy 1, policy_version 84382 (0.0008) -[2023-10-15 05:39:58,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 172294144. Throughput: 0: 1728.1, 1: 1735.2. Samples: 43084972. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:39:58,534][87330] Avg episode reward: [(0, '22.750'), (1, '22.360')] -[2023-10-15 05:39:59,902][88298] Updated weights for policy 0, policy_version 83880 (0.0008) -[2023-10-15 05:40:00,116][88300] Updated weights for policy 1, policy_version 84392 (0.0007) -[2023-10-15 05:40:00,270][88298] Updated weights for policy 0, policy_version 83890 (0.0007) -[2023-10-15 05:40:00,486][88300] Updated weights for policy 1, policy_version 84402 (0.0007) -[2023-10-15 05:40:00,637][88298] Updated weights for policy 0, policy_version 83900 (0.0007) -[2023-10-15 05:40:00,856][88300] Updated weights for policy 1, policy_version 84412 (0.0007) -[2023-10-15 05:40:03,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 172359680. Throughput: 0: 1709.8, 1: 1715.2. Samples: 43094322. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:40:03,535][87330] Avg episode reward: [(0, '22.740'), (1, '22.590')] -[2023-10-15 05:40:04,697][88298] Updated weights for policy 0, policy_version 83910 (0.0007) -[2023-10-15 05:40:04,723][88300] Updated weights for policy 1, policy_version 84422 (0.0007) -[2023-10-15 05:40:05,062][88298] Updated weights for policy 0, policy_version 83920 (0.0007) -[2023-10-15 05:40:05,086][88300] Updated weights for policy 1, policy_version 84432 (0.0008) -[2023-10-15 05:40:05,424][88298] Updated weights for policy 0, policy_version 83930 (0.0007) -[2023-10-15 05:40:05,449][88300] Updated weights for policy 1, policy_version 84442 (0.0007) -[2023-10-15 05:40:08,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 172425216. Throughput: 0: 1710.0, 1: 1717.6. Samples: 43115544. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:40:08,535][87330] Avg episode reward: [(0, '22.760'), (1, '22.730')] -[2023-10-15 05:40:09,270][88300] Updated weights for policy 1, policy_version 84452 (0.0008) -[2023-10-15 05:40:09,310][88298] Updated weights for policy 0, policy_version 83940 (0.0008) -[2023-10-15 05:40:09,626][88300] Updated weights for policy 1, policy_version 84462 (0.0009) -[2023-10-15 05:40:09,676][88298] Updated weights for policy 0, policy_version 83950 (0.0008) -[2023-10-15 05:40:09,988][88300] Updated weights for policy 1, policy_version 84472 (0.0008) -[2023-10-15 05:40:10,045][88298] Updated weights for policy 0, policy_version 83960 (0.0008) -[2023-10-15 05:40:13,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.3, 300 sec: 13773.7). Total num frames: 172490752. Throughput: 0: 1738.4, 1: 1747.6. Samples: 43137176. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:40:13,535][87330] Avg episode reward: [(0, '22.730'), (1, '22.940')] -[2023-10-15 05:40:13,801][88300] Updated weights for policy 1, policy_version 84482 (0.0008) -[2023-10-15 05:40:13,965][88298] Updated weights for policy 0, policy_version 83970 (0.0008) -[2023-10-15 05:40:14,162][88300] Updated weights for policy 1, policy_version 84492 (0.0009) -[2023-10-15 05:40:14,337][88298] Updated weights for policy 0, policy_version 83980 (0.0007) -[2023-10-15 05:40:14,533][88300] Updated weights for policy 1, policy_version 84502 (0.0007) -[2023-10-15 05:40:14,700][88298] Updated weights for policy 0, policy_version 83990 (0.0007) -[2023-10-15 05:40:14,894][88300] Updated weights for policy 1, policy_version 84512 (0.0007) -[2023-10-15 05:40:15,070][88298] Updated weights for policy 0, policy_version 84000 (0.0009) -[2023-10-15 05:40:18,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 172556288. Throughput: 0: 1702.3, 1: 1720.3. Samples: 43146572. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:40:18,534][87330] Avg episode reward: [(0, '22.670'), (1, '22.970')] -[2023-10-15 05:40:18,975][88300] Updated weights for policy 1, policy_version 84522 (0.0007) -[2023-10-15 05:40:19,075][88298] Updated weights for policy 0, policy_version 84010 (0.0007) -[2023-10-15 05:40:19,352][88300] Updated weights for policy 1, policy_version 84532 (0.0010) -[2023-10-15 05:40:19,446][88298] Updated weights for policy 0, policy_version 84020 (0.0007) -[2023-10-15 05:40:19,718][88300] Updated weights for policy 1, policy_version 84542 (0.0009) -[2023-10-15 05:40:19,814][88298] Updated weights for policy 0, policy_version 84030 (0.0007) -[2023-10-15 05:40:23,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 172621824. Throughput: 0: 1724.4, 1: 1741.2. Samples: 43167902. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:40:23,534][87330] Avg episode reward: [(0, '22.520'), (1, '22.750')] -[2023-10-15 05:40:23,624][88300] Updated weights for policy 1, policy_version 84552 (0.0007) -[2023-10-15 05:40:23,811][88298] Updated weights for policy 0, policy_version 84040 (0.0008) -[2023-10-15 05:40:23,988][88300] Updated weights for policy 1, policy_version 84562 (0.0009) -[2023-10-15 05:40:24,187][88298] Updated weights for policy 0, policy_version 84050 (0.0010) -[2023-10-15 05:40:24,354][88300] Updated weights for policy 1, policy_version 84572 (0.0007) -[2023-10-15 05:40:24,554][88298] Updated weights for policy 0, policy_version 84060 (0.0008) -[2023-10-15 05:40:28,351][88300] Updated weights for policy 1, policy_version 84582 (0.0007) -[2023-10-15 05:40:28,439][88298] Updated weights for policy 0, policy_version 84070 (0.0008) -[2023-10-15 05:40:28,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 172687360. Throughput: 0: 1722.5, 1: 1749.6. Samples: 43189040. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:40:28,534][87330] Avg episode reward: [(0, '22.210'), (1, '22.800')] -[2023-10-15 05:40:28,709][88300] Updated weights for policy 1, policy_version 84592 (0.0009) -[2023-10-15 05:40:28,809][88298] Updated weights for policy 0, policy_version 84080 (0.0009) -[2023-10-15 05:40:29,080][88300] Updated weights for policy 1, policy_version 84602 (0.0008) -[2023-10-15 05:40:29,182][88298] Updated weights for policy 0, policy_version 84090 (0.0008) -[2023-10-15 05:40:33,049][88300] Updated weights for policy 1, policy_version 84612 (0.0010) -[2023-10-15 05:40:33,157][88298] Updated weights for policy 0, policy_version 84100 (0.0009) -[2023-10-15 05:40:33,416][88300] Updated weights for policy 1, policy_version 84622 (0.0007) -[2023-10-15 05:40:33,533][88298] Updated weights for policy 0, policy_version 84110 (0.0007) -[2023-10-15 05:40:33,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 172752896. Throughput: 0: 1709.4, 1: 1730.6. Samples: 43198466. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:40:33,534][87330] Avg episode reward: [(0, '22.050'), (1, '22.490')] -[2023-10-15 05:40:33,799][88300] Updated weights for policy 1, policy_version 84632 (0.0009) -[2023-10-15 05:40:33,894][88298] Updated weights for policy 0, policy_version 84120 (0.0007) -[2023-10-15 05:40:37,843][88300] Updated weights for policy 1, policy_version 84642 (0.0009) -[2023-10-15 05:40:37,939][88298] Updated weights for policy 0, policy_version 84130 (0.0008) -[2023-10-15 05:40:38,208][88300] Updated weights for policy 1, policy_version 84652 (0.0008) -[2023-10-15 05:40:38,305][88298] Updated weights for policy 0, policy_version 84140 (0.0008) -[2023-10-15 05:40:38,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 172818432. Throughput: 0: 1726.5, 1: 1751.4. Samples: 43220028. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:40:38,535][87330] Avg episode reward: [(0, '22.000'), (1, '22.310')] -[2023-10-15 05:40:38,579][88300] Updated weights for policy 1, policy_version 84662 (0.0008) -[2023-10-15 05:40:38,669][88298] Updated weights for policy 0, policy_version 84150 (0.0009) -[2023-10-15 05:40:38,945][88300] Updated weights for policy 1, policy_version 84672 (0.0007) -[2023-10-15 05:40:39,034][88298] Updated weights for policy 0, policy_version 84160 (0.0007) -[2023-10-15 05:40:42,856][88300] Updated weights for policy 1, policy_version 84682 (0.0008) -[2023-10-15 05:40:42,880][88298] Updated weights for policy 0, policy_version 84170 (0.0009) -[2023-10-15 05:40:43,213][88300] Updated weights for policy 1, policy_version 84692 (0.0009) -[2023-10-15 05:40:43,252][88298] Updated weights for policy 0, policy_version 84180 (0.0007) -[2023-10-15 05:40:43,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 172883968. Throughput: 0: 1721.3, 1: 1733.3. Samples: 43240428. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:40:43,534][87330] Avg episode reward: [(0, '22.010'), (1, '22.340')] -[2023-10-15 05:40:43,584][88300] Updated weights for policy 1, policy_version 84702 (0.0007) -[2023-10-15 05:40:43,614][88298] Updated weights for policy 0, policy_version 84190 (0.0008) -[2023-10-15 05:40:47,315][88298] Updated weights for policy 0, policy_version 84200 (0.0008) -[2023-10-15 05:40:47,624][88300] Updated weights for policy 1, policy_version 84712 (0.0007) -[2023-10-15 05:40:47,683][88298] Updated weights for policy 0, policy_version 84210 (0.0008) -[2023-10-15 05:40:47,992][88300] Updated weights for policy 1, policy_version 84722 (0.0009) -[2023-10-15 05:40:48,057][88298] Updated weights for policy 0, policy_version 84220 (0.0009) -[2023-10-15 05:40:48,368][88300] Updated weights for policy 1, policy_version 84732 (0.0008) -[2023-10-15 05:40:48,534][87330] Fps is (10 sec: 19661.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 173015040. Throughput: 0: 1729.6, 1: 1747.5. Samples: 43250792. Policy #0 lag: (min: 31.0, avg: 33.2, max: 62.0) -[2023-10-15 05:40:48,535][87330] Avg episode reward: [(0, '22.040'), (1, '22.350')] -[2023-10-15 05:40:52,126][88298] Updated weights for policy 0, policy_version 84230 (0.0009) -[2023-10-15 05:40:52,155][88300] Updated weights for policy 1, policy_version 84742 (0.0009) -[2023-10-15 05:40:52,494][88298] Updated weights for policy 0, policy_version 84240 (0.0008) -[2023-10-15 05:40:52,515][88300] Updated weights for policy 1, policy_version 84752 (0.0007) -[2023-10-15 05:40:52,851][88298] Updated weights for policy 0, policy_version 84250 (0.0007) -[2023-10-15 05:40:52,879][88300] Updated weights for policy 1, policy_version 84762 (0.0008) -[2023-10-15 05:40:53,534][87330] Fps is (10 sec: 19660.7, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 173080576. Throughput: 0: 1730.4, 1: 1748.5. Samples: 43272094. Policy #0 lag: (min: 31.0, avg: 33.2, max: 62.0) -[2023-10-15 05:40:53,534][87330] Avg episode reward: [(0, '22.240'), (1, '22.390')] -[2023-10-15 05:40:56,725][88300] Updated weights for policy 1, policy_version 84772 (0.0007) -[2023-10-15 05:40:56,777][88298] Updated weights for policy 0, policy_version 84260 (0.0008) -[2023-10-15 05:40:57,096][88300] Updated weights for policy 1, policy_version 84782 (0.0008) -[2023-10-15 05:40:57,140][88298] Updated weights for policy 0, policy_version 84270 (0.0008) -[2023-10-15 05:40:57,456][88300] Updated weights for policy 1, policy_version 84792 (0.0008) -[2023-10-15 05:40:57,507][88298] Updated weights for policy 0, policy_version 84280 (0.0008) -[2023-10-15 05:40:58,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 173146112. Throughput: 0: 1704.8, 1: 1722.8. Samples: 43291414. Policy #0 lag: (min: 31.0, avg: 33.2, max: 62.0) -[2023-10-15 05:40:58,534][87330] Avg episode reward: [(0, '22.480'), (1, '22.590')] -[2023-10-15 05:40:58,543][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000084288_86310912.pth... -[2023-10-15 05:40:58,543][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000084800_86835200.pth... -[2023-10-15 05:40:58,579][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000083168_85164032.pth -[2023-10-15 05:40:58,587][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000082656_84639744.pth -[2023-10-15 05:41:01,440][88300] Updated weights for policy 1, policy_version 84802 (0.0008) -[2023-10-15 05:41:01,517][88298] Updated weights for policy 0, policy_version 84290 (0.0007) -[2023-10-15 05:41:01,807][88300] Updated weights for policy 1, policy_version 84812 (0.0009) -[2023-10-15 05:41:01,884][88298] Updated weights for policy 0, policy_version 84300 (0.0007) -[2023-10-15 05:41:02,163][88300] Updated weights for policy 1, policy_version 84822 (0.0007) -[2023-10-15 05:41:02,257][88298] Updated weights for policy 0, policy_version 84310 (0.0009) -[2023-10-15 05:41:02,530][88300] Updated weights for policy 1, policy_version 84832 (0.0008) -[2023-10-15 05:41:02,616][88298] Updated weights for policy 0, policy_version 84320 (0.0009) -[2023-10-15 05:41:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 173211648. Throughput: 0: 1735.0, 1: 1749.9. Samples: 43303394. Policy #0 lag: (min: 31.0, avg: 33.2, max: 62.0) -[2023-10-15 05:41:03,534][87330] Avg episode reward: [(0, '22.890'), (1, '22.580')] -[2023-10-15 05:41:06,433][88300] Updated weights for policy 1, policy_version 84842 (0.0009) -[2023-10-15 05:41:06,601][88298] Updated weights for policy 0, policy_version 84330 (0.0008) -[2023-10-15 05:41:06,798][88300] Updated weights for policy 1, policy_version 84852 (0.0007) -[2023-10-15 05:41:06,972][88298] Updated weights for policy 0, policy_version 84340 (0.0007) -[2023-10-15 05:41:07,165][88300] Updated weights for policy 1, policy_version 84862 (0.0007) -[2023-10-15 05:41:07,339][88298] Updated weights for policy 0, policy_version 84350 (0.0007) -[2023-10-15 05:41:08,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 173277184. Throughput: 0: 1723.0, 1: 1722.8. Samples: 43322960. Policy #0 lag: (min: 31.0, avg: 33.2, max: 62.0) -[2023-10-15 05:41:08,534][87330] Avg episode reward: [(0, '22.970'), (1, '23.110')] -[2023-10-15 05:41:11,096][88300] Updated weights for policy 1, policy_version 84872 (0.0009) -[2023-10-15 05:41:11,360][88298] Updated weights for policy 0, policy_version 84360 (0.0009) -[2023-10-15 05:41:11,465][88300] Updated weights for policy 1, policy_version 84882 (0.0009) -[2023-10-15 05:41:11,732][88298] Updated weights for policy 0, policy_version 84370 (0.0008) -[2023-10-15 05:41:11,822][88300] Updated weights for policy 1, policy_version 84892 (0.0009) -[2023-10-15 05:41:12,102][88298] Updated weights for policy 0, policy_version 84380 (0.0008) -[2023-10-15 05:41:13,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 173342720. Throughput: 0: 1710.1, 1: 1723.5. Samples: 43343552. Policy #0 lag: (min: 31.0, avg: 33.2, max: 62.0) -[2023-10-15 05:41:13,535][87330] Avg episode reward: [(0, '23.060'), (1, '23.110')] -[2023-10-15 05:41:15,629][88300] Updated weights for policy 1, policy_version 84902 (0.0010) -[2023-10-15 05:41:15,995][88300] Updated weights for policy 1, policy_version 84912 (0.0008) -[2023-10-15 05:41:16,073][88298] Updated weights for policy 0, policy_version 84390 (0.0008) -[2023-10-15 05:41:16,356][88300] Updated weights for policy 1, policy_version 84922 (0.0008) -[2023-10-15 05:41:16,443][88298] Updated weights for policy 0, policy_version 84400 (0.0009) -[2023-10-15 05:41:16,813][88298] Updated weights for policy 0, policy_version 84410 (0.0009) -[2023-10-15 05:41:18,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 173408256. Throughput: 0: 1737.0, 1: 1733.9. Samples: 43354658. Policy #0 lag: (min: 31.0, avg: 33.2, max: 62.0) -[2023-10-15 05:41:18,534][87330] Avg episode reward: [(0, '23.050'), (1, '23.010')] -[2023-10-15 05:41:20,150][88300] Updated weights for policy 1, policy_version 84932 (0.0008) -[2023-10-15 05:41:20,519][88300] Updated weights for policy 1, policy_version 84942 (0.0010) -[2023-10-15 05:41:20,802][88298] Updated weights for policy 0, policy_version 84420 (0.0007) -[2023-10-15 05:41:20,893][88300] Updated weights for policy 1, policy_version 84952 (0.0009) -[2023-10-15 05:41:21,171][88298] Updated weights for policy 0, policy_version 84430 (0.0007) -[2023-10-15 05:41:21,537][88298] Updated weights for policy 0, policy_version 84440 (0.0008) -[2023-10-15 05:41:23,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 173473792. Throughput: 0: 1713.7, 1: 1723.5. Samples: 43374700. Policy #0 lag: (min: 31.0, avg: 33.2, max: 62.0) -[2023-10-15 05:41:23,535][87330] Avg episode reward: [(0, '23.040'), (1, '22.980')] -[2023-10-15 05:41:24,962][88300] Updated weights for policy 1, policy_version 84962 (0.0009) -[2023-10-15 05:41:25,313][88298] Updated weights for policy 0, policy_version 84450 (0.0008) -[2023-10-15 05:41:25,323][88300] Updated weights for policy 1, policy_version 84972 (0.0009) -[2023-10-15 05:41:25,680][88298] Updated weights for policy 0, policy_version 84460 (0.0007) -[2023-10-15 05:41:25,686][88300] Updated weights for policy 1, policy_version 84982 (0.0008) -[2023-10-15 05:41:26,047][88298] Updated weights for policy 0, policy_version 84470 (0.0008) -[2023-10-15 05:41:26,049][88300] Updated weights for policy 1, policy_version 84992 (0.0008) -[2023-10-15 05:41:26,423][88298] Updated weights for policy 0, policy_version 84480 (0.0009) -[2023-10-15 05:41:28,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 173539328. Throughput: 0: 1719.2, 1: 1736.8. Samples: 43395948. Policy #0 lag: (min: 31.0, avg: 33.2, max: 62.0) -[2023-10-15 05:41:28,534][87330] Avg episode reward: [(0, '22.940'), (1, '22.980')] -[2023-10-15 05:41:29,814][88300] Updated weights for policy 1, policy_version 85002 (0.0008) -[2023-10-15 05:41:30,187][88300] Updated weights for policy 1, policy_version 85012 (0.0009) -[2023-10-15 05:41:30,334][88298] Updated weights for policy 0, policy_version 84490 (0.0007) -[2023-10-15 05:41:30,559][88300] Updated weights for policy 1, policy_version 85022 (0.0009) -[2023-10-15 05:41:30,717][88298] Updated weights for policy 0, policy_version 84500 (0.0008) -[2023-10-15 05:41:31,077][88298] Updated weights for policy 0, policy_version 84510 (0.0010) -[2023-10-15 05:41:33,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 173604864. Throughput: 0: 1722.6, 1: 1723.8. Samples: 43405880. Policy #0 lag: (min: 31.0, avg: 33.2, max: 62.0) -[2023-10-15 05:41:33,534][87330] Avg episode reward: [(0, '22.970'), (1, '22.980')] -[2023-10-15 05:41:34,456][88300] Updated weights for policy 1, policy_version 85032 (0.0009) -[2023-10-15 05:41:34,822][88300] Updated weights for policy 1, policy_version 85042 (0.0008) -[2023-10-15 05:41:34,944][88298] Updated weights for policy 0, policy_version 84520 (0.0009) -[2023-10-15 05:41:35,191][88300] Updated weights for policy 1, policy_version 85052 (0.0009) -[2023-10-15 05:41:35,313][88298] Updated weights for policy 0, policy_version 84530 (0.0008) -[2023-10-15 05:41:35,695][88298] Updated weights for policy 0, policy_version 84540 (0.0008) -[2023-10-15 05:41:38,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 173670400. Throughput: 0: 1713.9, 1: 1725.6. Samples: 43426870. Policy #0 lag: (min: 31.0, avg: 33.2, max: 62.0) -[2023-10-15 05:41:38,535][87330] Avg episode reward: [(0, '22.990'), (1, '22.880')] -[2023-10-15 05:41:39,197][88300] Updated weights for policy 1, policy_version 85062 (0.0008) -[2023-10-15 05:41:39,558][88300] Updated weights for policy 1, policy_version 85072 (0.0008) -[2023-10-15 05:41:39,718][88298] Updated weights for policy 0, policy_version 84550 (0.0008) -[2023-10-15 05:41:39,926][88300] Updated weights for policy 1, policy_version 85082 (0.0008) -[2023-10-15 05:41:40,091][88298] Updated weights for policy 0, policy_version 84560 (0.0007) -[2023-10-15 05:41:40,466][88298] Updated weights for policy 0, policy_version 84570 (0.0008) -[2023-10-15 05:41:43,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 173735936. Throughput: 0: 1743.6, 1: 1749.1. Samples: 43448586. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:41:43,535][87330] Avg episode reward: [(0, '22.890'), (1, '22.850')] -[2023-10-15 05:41:43,823][88300] Updated weights for policy 1, policy_version 85092 (0.0008) -[2023-10-15 05:41:44,195][88300] Updated weights for policy 1, policy_version 85102 (0.0009) -[2023-10-15 05:41:44,314][88298] Updated weights for policy 0, policy_version 84580 (0.0009) -[2023-10-15 05:41:44,560][88300] Updated weights for policy 1, policy_version 85112 (0.0008) -[2023-10-15 05:41:44,679][88298] Updated weights for policy 0, policy_version 84590 (0.0007) -[2023-10-15 05:41:45,050][88298] Updated weights for policy 0, policy_version 84600 (0.0008) -[2023-10-15 05:41:48,334][88300] Updated weights for policy 1, policy_version 85122 (0.0008) -[2023-10-15 05:41:48,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 173801472. Throughput: 0: 1715.5, 1: 1720.5. Samples: 43458016. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:41:48,534][87330] Avg episode reward: [(0, '22.930'), (1, '22.820')] -[2023-10-15 05:41:48,705][88300] Updated weights for policy 1, policy_version 85132 (0.0010) -[2023-10-15 05:41:48,934][88298] Updated weights for policy 0, policy_version 84610 (0.0008) -[2023-10-15 05:41:49,060][88300] Updated weights for policy 1, policy_version 85142 (0.0008) -[2023-10-15 05:41:49,302][88298] Updated weights for policy 0, policy_version 84620 (0.0008) -[2023-10-15 05:41:49,431][88300] Updated weights for policy 1, policy_version 85152 (0.0008) -[2023-10-15 05:41:49,672][88298] Updated weights for policy 0, policy_version 84630 (0.0007) -[2023-10-15 05:41:50,042][88298] Updated weights for policy 0, policy_version 84640 (0.0008) -[2023-10-15 05:41:53,405][88300] Updated weights for policy 1, policy_version 85162 (0.0009) -[2023-10-15 05:41:53,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 173867008. Throughput: 0: 1728.0, 1: 1751.0. Samples: 43479512. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:41:53,535][87330] Avg episode reward: [(0, '22.900'), (1, '22.930')] -[2023-10-15 05:41:53,775][88300] Updated weights for policy 1, policy_version 85172 (0.0008) -[2023-10-15 05:41:53,842][88298] Updated weights for policy 0, policy_version 84650 (0.0007) -[2023-10-15 05:41:54,136][88300] Updated weights for policy 1, policy_version 85182 (0.0007) -[2023-10-15 05:41:54,207][88298] Updated weights for policy 0, policy_version 84660 (0.0010) -[2023-10-15 05:41:54,583][88298] Updated weights for policy 0, policy_version 84670 (0.0010) -[2023-10-15 05:41:58,057][88300] Updated weights for policy 1, policy_version 85192 (0.0008) -[2023-10-15 05:41:58,434][88300] Updated weights for policy 1, policy_version 85202 (0.0009) -[2023-10-15 05:41:58,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 173932544. Throughput: 0: 1752.2, 1: 1740.2. Samples: 43500710. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:41:58,534][87330] Avg episode reward: [(0, '23.040'), (1, '22.890')] -[2023-10-15 05:41:58,581][88298] Updated weights for policy 0, policy_version 84680 (0.0007) -[2023-10-15 05:41:58,806][88300] Updated weights for policy 1, policy_version 85212 (0.0008) -[2023-10-15 05:41:58,959][88298] Updated weights for policy 0, policy_version 84690 (0.0008) -[2023-10-15 05:41:59,326][88298] Updated weights for policy 0, policy_version 84700 (0.0008) -[2023-10-15 05:42:02,596][88300] Updated weights for policy 1, policy_version 85222 (0.0009) -[2023-10-15 05:42:02,961][88300] Updated weights for policy 1, policy_version 85232 (0.0010) -[2023-10-15 05:42:03,137][88298] Updated weights for policy 0, policy_version 84710 (0.0007) -[2023-10-15 05:42:03,325][88300] Updated weights for policy 1, policy_version 85242 (0.0009) -[2023-10-15 05:42:03,502][88298] Updated weights for policy 0, policy_version 84720 (0.0008) -[2023-10-15 05:42:03,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 173998080. Throughput: 0: 1721.7, 1: 1742.9. Samples: 43510566. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:42:03,534][87330] Avg episode reward: [(0, '22.700'), (1, '22.870')] -[2023-10-15 05:42:03,867][88298] Updated weights for policy 0, policy_version 84730 (0.0010) -[2023-10-15 05:42:07,473][88300] Updated weights for policy 1, policy_version 85252 (0.0010) -[2023-10-15 05:42:07,832][88300] Updated weights for policy 1, policy_version 85262 (0.0009) -[2023-10-15 05:42:07,875][88298] Updated weights for policy 0, policy_version 84740 (0.0007) -[2023-10-15 05:42:08,197][88300] Updated weights for policy 1, policy_version 85272 (0.0007) -[2023-10-15 05:42:08,245][88298] Updated weights for policy 0, policy_version 84750 (0.0007) -[2023-10-15 05:42:08,534][87330] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 174096384. Throughput: 0: 1745.2, 1: 1748.0. Samples: 43531892. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:42:08,534][87330] Avg episode reward: [(0, '22.630'), (1, '22.800')] -[2023-10-15 05:42:08,614][88298] Updated weights for policy 0, policy_version 84760 (0.0008) -[2023-10-15 05:42:12,095][88300] Updated weights for policy 1, policy_version 85282 (0.0008) -[2023-10-15 05:42:12,466][88300] Updated weights for policy 1, policy_version 85292 (0.0007) -[2023-10-15 05:42:12,469][88298] Updated weights for policy 0, policy_version 84770 (0.0010) -[2023-10-15 05:42:12,830][88300] Updated weights for policy 1, policy_version 85302 (0.0008) -[2023-10-15 05:42:12,838][88298] Updated weights for policy 0, policy_version 84780 (0.0008) -[2023-10-15 05:42:13,190][88300] Updated weights for policy 1, policy_version 85312 (0.0008) -[2023-10-15 05:42:13,202][88298] Updated weights for policy 0, policy_version 84790 (0.0007) -[2023-10-15 05:42:13,534][87330] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 174161920. Throughput: 0: 1737.8, 1: 1725.1. Samples: 43551778. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:42:13,534][87330] Avg episode reward: [(0, '22.620'), (1, '22.370')] -[2023-10-15 05:42:13,567][88298] Updated weights for policy 0, policy_version 84800 (0.0007) -[2023-10-15 05:42:17,178][88300] Updated weights for policy 1, policy_version 85322 (0.0010) -[2023-10-15 05:42:17,544][88300] Updated weights for policy 1, policy_version 85332 (0.0007) -[2023-10-15 05:42:17,747][88298] Updated weights for policy 0, policy_version 84810 (0.0009) -[2023-10-15 05:42:17,919][88300] Updated weights for policy 1, policy_version 85342 (0.0008) -[2023-10-15 05:42:18,119][88298] Updated weights for policy 0, policy_version 84820 (0.0008) -[2023-10-15 05:42:18,492][88298] Updated weights for policy 0, policy_version 84830 (0.0007) -[2023-10-15 05:42:18,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 174227456. Throughput: 0: 1735.7, 1: 1754.7. Samples: 43562950. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:42:18,534][87330] Avg episode reward: [(0, '22.610'), (1, '22.220')] -[2023-10-15 05:42:21,776][88300] Updated weights for policy 1, policy_version 85352 (0.0008) -[2023-10-15 05:42:22,156][88300] Updated weights for policy 1, policy_version 85362 (0.0010) -[2023-10-15 05:42:22,515][88298] Updated weights for policy 0, policy_version 84840 (0.0007) -[2023-10-15 05:42:22,524][88300] Updated weights for policy 1, policy_version 85372 (0.0009) -[2023-10-15 05:42:22,881][88298] Updated weights for policy 0, policy_version 84850 (0.0010) -[2023-10-15 05:42:23,248][88298] Updated weights for policy 0, policy_version 84860 (0.0007) -[2023-10-15 05:42:23,534][87330] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 174325760. Throughput: 0: 1744.8, 1: 1733.4. Samples: 43583388. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:42:23,535][87330] Avg episode reward: [(0, '22.470'), (1, '22.240')] -[2023-10-15 05:42:26,371][88300] Updated weights for policy 1, policy_version 85382 (0.0008) -[2023-10-15 05:42:26,737][88300] Updated weights for policy 1, policy_version 85392 (0.0011) -[2023-10-15 05:42:27,099][88300] Updated weights for policy 1, policy_version 85402 (0.0008) -[2023-10-15 05:42:27,308][88298] Updated weights for policy 0, policy_version 84870 (0.0008) -[2023-10-15 05:42:27,681][88298] Updated weights for policy 0, policy_version 84880 (0.0009) -[2023-10-15 05:42:28,056][88298] Updated weights for policy 0, policy_version 84890 (0.0008) -[2023-10-15 05:42:28,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 174391296. Throughput: 0: 1722.6, 1: 1720.5. Samples: 43603524. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:42:28,534][87330] Avg episode reward: [(0, '22.400'), (1, '22.290')] -[2023-10-15 05:42:31,045][88300] Updated weights for policy 1, policy_version 85412 (0.0007) -[2023-10-15 05:42:31,398][88300] Updated weights for policy 1, policy_version 85422 (0.0009) -[2023-10-15 05:42:31,783][88300] Updated weights for policy 1, policy_version 85432 (0.0008) -[2023-10-15 05:42:32,003][88298] Updated weights for policy 0, policy_version 84900 (0.0007) -[2023-10-15 05:42:32,367][88298] Updated weights for policy 0, policy_version 84910 (0.0009) -[2023-10-15 05:42:32,744][88298] Updated weights for policy 0, policy_version 84920 (0.0007) -[2023-10-15 05:42:33,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 174456832. Throughput: 0: 1740.5, 1: 1740.7. Samples: 43614670. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:42:33,535][87330] Avg episode reward: [(0, '22.360'), (1, '22.280')] -[2023-10-15 05:42:35,667][88300] Updated weights for policy 1, policy_version 85442 (0.0009) -[2023-10-15 05:42:36,031][88300] Updated weights for policy 1, policy_version 85452 (0.0011) -[2023-10-15 05:42:36,394][88300] Updated weights for policy 1, policy_version 85462 (0.0009) -[2023-10-15 05:42:36,672][88298] Updated weights for policy 0, policy_version 84930 (0.0008) -[2023-10-15 05:42:36,760][88300] Updated weights for policy 1, policy_version 85472 (0.0009) -[2023-10-15 05:42:37,040][88298] Updated weights for policy 0, policy_version 84940 (0.0009) -[2023-10-15 05:42:37,413][88298] Updated weights for policy 0, policy_version 84950 (0.0008) -[2023-10-15 05:42:37,785][88298] Updated weights for policy 0, policy_version 84960 (0.0009) -[2023-10-15 05:42:38,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 174522368. Throughput: 0: 1735.7, 1: 1722.6. Samples: 43635134. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-15 05:42:38,534][87330] Avg episode reward: [(0, '22.660'), (1, '22.340')] -[2023-10-15 05:42:40,663][88300] Updated weights for policy 1, policy_version 85482 (0.0007) -[2023-10-15 05:42:41,030][88300] Updated weights for policy 1, policy_version 85492 (0.0011) -[2023-10-15 05:42:41,389][88300] Updated weights for policy 1, policy_version 85502 (0.0009) -[2023-10-15 05:42:41,647][88298] Updated weights for policy 0, policy_version 84970 (0.0009) -[2023-10-15 05:42:42,006][88298] Updated weights for policy 0, policy_version 84980 (0.0007) -[2023-10-15 05:42:42,380][88298] Updated weights for policy 0, policy_version 84990 (0.0010) -[2023-10-15 05:42:43,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 174587904. Throughput: 0: 1710.6, 1: 1734.5. Samples: 43655738. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-15 05:42:43,535][87330] Avg episode reward: [(0, '22.710'), (1, '22.710')] -[2023-10-15 05:42:45,354][88300] Updated weights for policy 1, policy_version 85512 (0.0007) -[2023-10-15 05:42:45,718][88300] Updated weights for policy 1, policy_version 85522 (0.0007) -[2023-10-15 05:42:46,077][88300] Updated weights for policy 1, policy_version 85532 (0.0009) -[2023-10-15 05:42:46,368][88298] Updated weights for policy 0, policy_version 85000 (0.0010) -[2023-10-15 05:42:46,732][88298] Updated weights for policy 0, policy_version 85010 (0.0007) -[2023-10-15 05:42:47,100][88298] Updated weights for policy 0, policy_version 85020 (0.0007) -[2023-10-15 05:42:48,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 174653440. Throughput: 0: 1743.6, 1: 1724.5. Samples: 43666634. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-15 05:42:48,535][87330] Avg episode reward: [(0, '22.350'), (1, '22.800')] -[2023-10-15 05:42:50,041][88300] Updated weights for policy 1, policy_version 85542 (0.0008) -[2023-10-15 05:42:50,402][88300] Updated weights for policy 1, policy_version 85552 (0.0008) -[2023-10-15 05:42:50,761][88300] Updated weights for policy 1, policy_version 85562 (0.0008) -[2023-10-15 05:42:50,885][88298] Updated weights for policy 0, policy_version 85030 (0.0008) -[2023-10-15 05:42:51,260][88298] Updated weights for policy 0, policy_version 85040 (0.0008) -[2023-10-15 05:42:51,635][88298] Updated weights for policy 0, policy_version 85050 (0.0009) -[2023-10-15 05:42:53,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 174718976. Throughput: 0: 1715.1, 1: 1727.0. Samples: 43686786. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-15 05:42:53,535][87330] Avg episode reward: [(0, '22.360'), (1, '22.810')] -[2023-10-15 05:42:54,673][88300] Updated weights for policy 1, policy_version 85572 (0.0008) -[2023-10-15 05:42:55,041][88300] Updated weights for policy 1, policy_version 85582 (0.0009) -[2023-10-15 05:42:55,403][88300] Updated weights for policy 1, policy_version 85592 (0.0010) -[2023-10-15 05:42:55,487][88298] Updated weights for policy 0, policy_version 85060 (0.0008) -[2023-10-15 05:42:55,858][88298] Updated weights for policy 0, policy_version 85070 (0.0008) -[2023-10-15 05:42:56,227][88298] Updated weights for policy 0, policy_version 85080 (0.0010) -[2023-10-15 05:42:58,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 174784512. Throughput: 0: 1722.2, 1: 1756.1. Samples: 43708304. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-15 05:42:58,535][87330] Avg episode reward: [(0, '22.510'), (1, '22.750')] -[2023-10-15 05:42:58,546][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000085600_87654400.pth... -[2023-10-15 05:42:58,546][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000085088_87130112.pth... -[2023-10-15 05:42:58,578][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000083488_85491712.pth -[2023-10-15 05:42:58,586][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000084000_86016000.pth -[2023-10-15 05:42:59,129][88300] Updated weights for policy 1, policy_version 85602 (0.0008) -[2023-10-15 05:42:59,494][88300] Updated weights for policy 1, policy_version 85612 (0.0009) -[2023-10-15 05:42:59,856][88300] Updated weights for policy 1, policy_version 85622 (0.0010) -[2023-10-15 05:43:00,229][88300] Updated weights for policy 1, policy_version 85632 (0.0009) -[2023-10-15 05:43:00,244][88298] Updated weights for policy 0, policy_version 85090 (0.0007) -[2023-10-15 05:43:00,608][88298] Updated weights for policy 0, policy_version 85100 (0.0007) -[2023-10-15 05:43:00,968][88298] Updated weights for policy 0, policy_version 85110 (0.0007) -[2023-10-15 05:43:01,342][88298] Updated weights for policy 0, policy_version 85120 (0.0008) -[2023-10-15 05:43:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 174850048. Throughput: 0: 1727.8, 1: 1725.5. Samples: 43718350. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-15 05:43:03,535][87330] Avg episode reward: [(0, '22.660'), (1, '22.710')] -[2023-10-15 05:43:04,225][88300] Updated weights for policy 1, policy_version 85642 (0.0008) -[2023-10-15 05:43:04,597][88300] Updated weights for policy 1, policy_version 85652 (0.0007) -[2023-10-15 05:43:04,956][88300] Updated weights for policy 1, policy_version 85662 (0.0008) -[2023-10-15 05:43:05,210][88298] Updated weights for policy 0, policy_version 85130 (0.0008) -[2023-10-15 05:43:05,581][88298] Updated weights for policy 0, policy_version 85140 (0.0007) -[2023-10-15 05:43:05,946][88298] Updated weights for policy 0, policy_version 85150 (0.0008) -[2023-10-15 05:43:08,534][87330] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 174915584. Throughput: 0: 1715.2, 1: 1745.7. Samples: 43739126. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-15 05:43:08,534][87330] Avg episode reward: [(0, '22.470'), (1, '22.480')] -[2023-10-15 05:43:08,853][88300] Updated weights for policy 1, policy_version 85672 (0.0010) -[2023-10-15 05:43:09,215][88300] Updated weights for policy 1, policy_version 85682 (0.0008) -[2023-10-15 05:43:09,575][88300] Updated weights for policy 1, policy_version 85692 (0.0008) -[2023-10-15 05:43:09,845][88298] Updated weights for policy 0, policy_version 85160 (0.0009) -[2023-10-15 05:43:10,214][88298] Updated weights for policy 0, policy_version 85170 (0.0007) -[2023-10-15 05:43:10,580][88298] Updated weights for policy 0, policy_version 85180 (0.0007) -[2023-10-15 05:43:13,380][88300] Updated weights for policy 1, policy_version 85702 (0.0007) -[2023-10-15 05:43:13,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 174981120. Throughput: 0: 1735.2, 1: 1759.0. Samples: 43760762. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-15 05:43:13,534][87330] Avg episode reward: [(0, '22.480'), (1, '22.530')] -[2023-10-15 05:43:13,748][88300] Updated weights for policy 1, policy_version 85712 (0.0009) -[2023-10-15 05:43:14,109][88300] Updated weights for policy 1, policy_version 85722 (0.0008) -[2023-10-15 05:43:14,373][88298] Updated weights for policy 0, policy_version 85190 (0.0007) -[2023-10-15 05:43:14,744][88298] Updated weights for policy 0, policy_version 85200 (0.0009) -[2023-10-15 05:43:15,120][88298] Updated weights for policy 0, policy_version 85210 (0.0010) -[2023-10-15 05:43:18,052][88300] Updated weights for policy 1, policy_version 85732 (0.0009) -[2023-10-15 05:43:18,418][88300] Updated weights for policy 1, policy_version 85742 (0.0008) -[2023-10-15 05:43:18,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 175046656. Throughput: 0: 1719.2, 1: 1741.4. Samples: 43770394. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-15 05:43:18,534][87330] Avg episode reward: [(0, '22.660'), (1, '22.340')] -[2023-10-15 05:43:18,782][88300] Updated weights for policy 1, policy_version 85752 (0.0010) -[2023-10-15 05:43:18,999][88298] Updated weights for policy 0, policy_version 85220 (0.0009) -[2023-10-15 05:43:19,378][88298] Updated weights for policy 0, policy_version 85230 (0.0008) -[2023-10-15 05:43:19,751][88298] Updated weights for policy 0, policy_version 85240 (0.0009) -[2023-10-15 05:43:22,793][88300] Updated weights for policy 1, policy_version 85762 (0.0008) -[2023-10-15 05:43:23,152][88300] Updated weights for policy 1, policy_version 85772 (0.0009) -[2023-10-15 05:43:23,514][88298] Updated weights for policy 0, policy_version 85250 (0.0007) -[2023-10-15 05:43:23,524][88300] Updated weights for policy 1, policy_version 85782 (0.0010) -[2023-10-15 05:43:23,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 175112192. Throughput: 0: 1726.3, 1: 1759.4. Samples: 43791990. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-15 05:43:23,534][87330] Avg episode reward: [(0, '22.480'), (1, '22.540')] -[2023-10-15 05:43:23,883][88300] Updated weights for policy 1, policy_version 85792 (0.0007) -[2023-10-15 05:43:23,886][88298] Updated weights for policy 0, policy_version 85260 (0.0007) -[2023-10-15 05:43:24,254][88298] Updated weights for policy 0, policy_version 85270 (0.0008) -[2023-10-15 05:43:24,626][88298] Updated weights for policy 0, policy_version 85280 (0.0007) -[2023-10-15 05:43:27,685][88300] Updated weights for policy 1, policy_version 85802 (0.0007) -[2023-10-15 05:43:28,059][88300] Updated weights for policy 1, policy_version 85812 (0.0007) -[2023-10-15 05:43:28,422][88300] Updated weights for policy 1, policy_version 85822 (0.0009) -[2023-10-15 05:43:28,534][87330] Fps is (10 sec: 16383.6, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 175210496. Throughput: 0: 1747.7, 1: 1739.7. Samples: 43812672. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-15 05:43:28,535][87330] Avg episode reward: [(0, '22.330'), (1, '22.470')] -[2023-10-15 05:43:28,606][88298] Updated weights for policy 0, policy_version 85290 (0.0007) -[2023-10-15 05:43:28,970][88298] Updated weights for policy 0, policy_version 85300 (0.0008) -[2023-10-15 05:43:29,338][88298] Updated weights for policy 0, policy_version 85310 (0.0008) -[2023-10-15 05:43:32,108][88300] Updated weights for policy 1, policy_version 85832 (0.0008) -[2023-10-15 05:43:32,470][88300] Updated weights for policy 1, policy_version 85842 (0.0007) -[2023-10-15 05:43:32,836][88300] Updated weights for policy 1, policy_version 85852 (0.0007) -[2023-10-15 05:43:33,257][88298] Updated weights for policy 0, policy_version 85320 (0.0009) -[2023-10-15 05:43:33,534][87330] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 175276032. Throughput: 0: 1716.6, 1: 1765.2. Samples: 43823318. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-15 05:43:33,535][87330] Avg episode reward: [(0, '22.300'), (1, '22.370')] -[2023-10-15 05:43:33,631][88298] Updated weights for policy 0, policy_version 85330 (0.0009) -[2023-10-15 05:43:34,000][88298] Updated weights for policy 0, policy_version 85340 (0.0008) -[2023-10-15 05:43:36,898][88300] Updated weights for policy 1, policy_version 85862 (0.0009) -[2023-10-15 05:43:37,259][88300] Updated weights for policy 1, policy_version 85872 (0.0009) -[2023-10-15 05:43:37,623][88300] Updated weights for policy 1, policy_version 85882 (0.0008) -[2023-10-15 05:43:37,845][88298] Updated weights for policy 0, policy_version 85350 (0.0009) -[2023-10-15 05:43:38,202][88298] Updated weights for policy 0, policy_version 85360 (0.0010) -[2023-10-15 05:43:38,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 175341568. Throughput: 0: 1746.1, 1: 1755.1. Samples: 43844340. Policy #0 lag: (min: 23.0, avg: 28.7, max: 55.0) -[2023-10-15 05:43:38,534][87330] Avg episode reward: [(0, '22.470'), (1, '22.430')] -[2023-10-15 05:43:38,573][88298] Updated weights for policy 0, policy_version 85370 (0.0009) -[2023-10-15 05:43:41,488][88300] Updated weights for policy 1, policy_version 85892 (0.0008) -[2023-10-15 05:43:41,852][88300] Updated weights for policy 1, policy_version 85902 (0.0007) -[2023-10-15 05:43:42,219][88300] Updated weights for policy 1, policy_version 85912 (0.0009) -[2023-10-15 05:43:42,552][88298] Updated weights for policy 0, policy_version 85380 (0.0009) -[2023-10-15 05:43:42,932][88298] Updated weights for policy 0, policy_version 85390 (0.0007) -[2023-10-15 05:43:43,301][88298] Updated weights for policy 0, policy_version 85400 (0.0009) -[2023-10-15 05:43:43,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 175407104. Throughput: 0: 1739.4, 1: 1736.0. Samples: 43864694. Policy #0 lag: (min: 23.0, avg: 28.7, max: 55.0) -[2023-10-15 05:43:43,534][87330] Avg episode reward: [(0, '22.560'), (1, '22.590')] -[2023-10-15 05:43:46,145][88300] Updated weights for policy 1, policy_version 85922 (0.0008) -[2023-10-15 05:43:46,506][88300] Updated weights for policy 1, policy_version 85932 (0.0007) -[2023-10-15 05:43:46,887][88300] Updated weights for policy 1, policy_version 85942 (0.0009) -[2023-10-15 05:43:47,243][88300] Updated weights for policy 1, policy_version 85952 (0.0010) -[2023-10-15 05:43:47,271][88298] Updated weights for policy 0, policy_version 85410 (0.0007) -[2023-10-15 05:43:47,644][88298] Updated weights for policy 0, policy_version 85420 (0.0010) -[2023-10-15 05:43:48,012][88298] Updated weights for policy 0, policy_version 85430 (0.0010) -[2023-10-15 05:43:48,392][88298] Updated weights for policy 0, policy_version 85440 (0.0008) -[2023-10-15 05:43:48,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 175505408. Throughput: 0: 1734.3, 1: 1760.1. Samples: 43875598. Policy #0 lag: (min: 23.0, avg: 28.7, max: 55.0) -[2023-10-15 05:43:48,534][87330] Avg episode reward: [(0, '22.570'), (1, '22.550')] -[2023-10-15 05:43:51,131][88300] Updated weights for policy 1, policy_version 85962 (0.0009) -[2023-10-15 05:43:51,503][88300] Updated weights for policy 1, policy_version 85972 (0.0008) -[2023-10-15 05:43:51,865][88300] Updated weights for policy 1, policy_version 85982 (0.0007) -[2023-10-15 05:43:52,406][88298] Updated weights for policy 0, policy_version 85450 (0.0007) -[2023-10-15 05:43:52,783][88298] Updated weights for policy 0, policy_version 85460 (0.0008) -[2023-10-15 05:43:53,153][88298] Updated weights for policy 0, policy_version 85470 (0.0007) -[2023-10-15 05:43:53,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 175570944. Throughput: 0: 1751.1, 1: 1733.3. Samples: 43895924. Policy #0 lag: (min: 23.0, avg: 28.7, max: 55.0) -[2023-10-15 05:43:53,535][87330] Avg episode reward: [(0, '22.630'), (1, '22.720')] -[2023-10-15 05:43:55,807][88300] Updated weights for policy 1, policy_version 85992 (0.0007) -[2023-10-15 05:43:56,173][88300] Updated weights for policy 1, policy_version 86002 (0.0008) -[2023-10-15 05:43:56,536][88300] Updated weights for policy 1, policy_version 86012 (0.0007) -[2023-10-15 05:43:57,097][88298] Updated weights for policy 0, policy_version 85480 (0.0008) -[2023-10-15 05:43:57,465][88298] Updated weights for policy 0, policy_version 85490 (0.0007) -[2023-10-15 05:43:57,829][88298] Updated weights for policy 0, policy_version 85500 (0.0010) -[2023-10-15 05:43:58,534][87330] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 175636480. Throughput: 0: 1727.0, 1: 1731.5. Samples: 43916398. Policy #0 lag: (min: 23.0, avg: 28.7, max: 55.0) -[2023-10-15 05:43:58,535][87330] Avg episode reward: [(0, '22.850'), (1, '22.730')] -[2023-10-15 05:44:00,462][88300] Updated weights for policy 1, policy_version 86022 (0.0009) -[2023-10-15 05:44:00,827][88300] Updated weights for policy 1, policy_version 86032 (0.0007) -[2023-10-15 05:44:01,188][88300] Updated weights for policy 1, policy_version 86042 (0.0008) -[2023-10-15 05:44:01,793][88298] Updated weights for policy 0, policy_version 85510 (0.0009) -[2023-10-15 05:44:02,168][88298] Updated weights for policy 0, policy_version 85520 (0.0007) -[2023-10-15 05:44:02,543][88298] Updated weights for policy 0, policy_version 85530 (0.0009) -[2023-10-15 05:44:03,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 175702016. Throughput: 0: 1748.3, 1: 1736.3. Samples: 43927200. Policy #0 lag: (min: 23.0, avg: 28.7, max: 55.0) -[2023-10-15 05:44:03,534][87330] Avg episode reward: [(0, '23.010'), (1, '22.750')] -[2023-10-15 05:44:05,008][88300] Updated weights for policy 1, policy_version 86052 (0.0008) -[2023-10-15 05:44:05,379][88300] Updated weights for policy 1, policy_version 86062 (0.0008) -[2023-10-15 05:44:05,742][88300] Updated weights for policy 1, policy_version 86072 (0.0008) -[2023-10-15 05:44:06,210][88298] Updated weights for policy 0, policy_version 85540 (0.0007) -[2023-10-15 05:44:06,580][88298] Updated weights for policy 0, policy_version 85550 (0.0007) -[2023-10-15 05:44:06,960][88298] Updated weights for policy 0, policy_version 85560 (0.0010) -[2023-10-15 05:44:08,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 175767552. Throughput: 0: 1730.1, 1: 1730.8. Samples: 43947730. Policy #0 lag: (min: 23.0, avg: 28.7, max: 55.0) -[2023-10-15 05:44:08,534][87330] Avg episode reward: [(0, '22.760'), (1, '22.830')] -[2023-10-15 05:44:09,616][88300] Updated weights for policy 1, policy_version 86082 (0.0010) -[2023-10-15 05:44:09,974][88300] Updated weights for policy 1, policy_version 86092 (0.0009) -[2023-10-15 05:44:10,345][88300] Updated weights for policy 1, policy_version 86102 (0.0008) -[2023-10-15 05:44:10,714][88300] Updated weights for policy 1, policy_version 86112 (0.0009) -[2023-10-15 05:44:10,730][88298] Updated weights for policy 0, policy_version 85570 (0.0008) -[2023-10-15 05:44:11,114][88298] Updated weights for policy 0, policy_version 85580 (0.0011) -[2023-10-15 05:44:11,474][88298] Updated weights for policy 0, policy_version 85590 (0.0009) -[2023-10-15 05:44:11,841][88298] Updated weights for policy 0, policy_version 85600 (0.0009) -[2023-10-15 05:44:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 175833088. Throughput: 0: 1717.8, 1: 1753.9. Samples: 43968898. Policy #0 lag: (min: 23.0, avg: 28.7, max: 55.0) -[2023-10-15 05:44:13,534][87330] Avg episode reward: [(0, '22.750'), (1, '22.830')] -[2023-10-15 05:44:14,689][88300] Updated weights for policy 1, policy_version 86122 (0.0007) -[2023-10-15 05:44:15,066][88300] Updated weights for policy 1, policy_version 86132 (0.0008) -[2023-10-15 05:44:15,435][88300] Updated weights for policy 1, policy_version 86142 (0.0008) -[2023-10-15 05:44:15,948][88298] Updated weights for policy 0, policy_version 85610 (0.0008) -[2023-10-15 05:44:16,320][88298] Updated weights for policy 0, policy_version 85620 (0.0010) -[2023-10-15 05:44:16,689][88298] Updated weights for policy 0, policy_version 85630 (0.0010) -[2023-10-15 05:44:18,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 175898624. Throughput: 0: 1741.3, 1: 1724.6. Samples: 43979282. Policy #0 lag: (min: 23.0, avg: 28.7, max: 55.0) -[2023-10-15 05:44:18,535][87330] Avg episode reward: [(0, '22.550'), (1, '22.850')] -[2023-10-15 05:44:19,173][88300] Updated weights for policy 1, policy_version 86152 (0.0008) -[2023-10-15 05:44:19,531][88300] Updated weights for policy 1, policy_version 86162 (0.0009) -[2023-10-15 05:44:19,910][88300] Updated weights for policy 1, policy_version 86172 (0.0009) -[2023-10-15 05:44:20,754][88298] Updated weights for policy 0, policy_version 85640 (0.0011) -[2023-10-15 05:44:21,130][88298] Updated weights for policy 0, policy_version 85650 (0.0009) -[2023-10-15 05:44:21,486][88298] Updated weights for policy 0, policy_version 85660 (0.0009) -[2023-10-15 05:44:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 175964160. Throughput: 0: 1709.8, 1: 1737.6. Samples: 43999472. Policy #0 lag: (min: 23.0, avg: 28.7, max: 55.0) -[2023-10-15 05:44:23,534][87330] Avg episode reward: [(0, '22.590'), (1, '22.880')] -[2023-10-15 05:44:23,797][88300] Updated weights for policy 1, policy_version 86182 (0.0007) -[2023-10-15 05:44:24,157][88300] Updated weights for policy 1, policy_version 86192 (0.0007) -[2023-10-15 05:44:24,520][88300] Updated weights for policy 1, policy_version 86202 (0.0007) -[2023-10-15 05:44:25,430][88298] Updated weights for policy 0, policy_version 85670 (0.0009) -[2023-10-15 05:44:25,793][88298] Updated weights for policy 0, policy_version 85680 (0.0010) -[2023-10-15 05:44:26,156][88298] Updated weights for policy 0, policy_version 85690 (0.0007) -[2023-10-15 05:44:28,425][88300] Updated weights for policy 1, policy_version 86212 (0.0009) -[2023-10-15 05:44:28,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 176029696. Throughput: 0: 1718.8, 1: 1756.6. Samples: 44021086. Policy #0 lag: (min: 23.0, avg: 28.7, max: 55.0) -[2023-10-15 05:44:28,535][87330] Avg episode reward: [(0, '22.400'), (1, '22.860')] -[2023-10-15 05:44:28,790][88300] Updated weights for policy 1, policy_version 86222 (0.0007) -[2023-10-15 05:44:29,163][88300] Updated weights for policy 1, policy_version 86232 (0.0007) -[2023-10-15 05:44:30,088][88298] Updated weights for policy 0, policy_version 85700 (0.0008) -[2023-10-15 05:44:30,459][88298] Updated weights for policy 0, policy_version 85710 (0.0007) -[2023-10-15 05:44:30,833][88298] Updated weights for policy 0, policy_version 85720 (0.0010) -[2023-10-15 05:44:33,110][88300] Updated weights for policy 1, policy_version 86242 (0.0007) -[2023-10-15 05:44:33,474][88300] Updated weights for policy 1, policy_version 86252 (0.0008) -[2023-10-15 05:44:33,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 176095232. Throughput: 0: 1722.0, 1: 1734.8. Samples: 44031152. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-15 05:44:33,534][87330] Avg episode reward: [(0, '22.460'), (1, '22.940')] -[2023-10-15 05:44:33,846][88300] Updated weights for policy 1, policy_version 86262 (0.0008) -[2023-10-15 05:44:34,216][88300] Updated weights for policy 1, policy_version 86272 (0.0009) -[2023-10-15 05:44:34,884][88298] Updated weights for policy 0, policy_version 85730 (0.0007) -[2023-10-15 05:44:35,262][88298] Updated weights for policy 0, policy_version 85740 (0.0008) -[2023-10-15 05:44:35,629][88298] Updated weights for policy 0, policy_version 85750 (0.0007) -[2023-10-15 05:44:35,990][88298] Updated weights for policy 0, policy_version 85760 (0.0009) -[2023-10-15 05:44:38,215][88300] Updated weights for policy 1, policy_version 86282 (0.0010) -[2023-10-15 05:44:38,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 176160768. Throughput: 0: 1709.7, 1: 1759.7. Samples: 44052044. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-15 05:44:38,534][87330] Avg episode reward: [(0, '22.580'), (1, '22.960')] -[2023-10-15 05:44:38,588][88300] Updated weights for policy 1, policy_version 86292 (0.0007) -[2023-10-15 05:44:38,950][88300] Updated weights for policy 1, policy_version 86302 (0.0009) -[2023-10-15 05:44:39,820][88298] Updated weights for policy 0, policy_version 85770 (0.0008) -[2023-10-15 05:44:40,184][88298] Updated weights for policy 0, policy_version 85780 (0.0007) -[2023-10-15 05:44:40,554][88298] Updated weights for policy 0, policy_version 85790 (0.0009) -[2023-10-15 05:44:42,784][88300] Updated weights for policy 1, policy_version 86312 (0.0008) -[2023-10-15 05:44:43,140][88300] Updated weights for policy 1, policy_version 86322 (0.0010) -[2023-10-15 05:44:43,504][88300] Updated weights for policy 1, policy_version 86332 (0.0008) -[2023-10-15 05:44:43,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 176226304. Throughput: 0: 1737.6, 1: 1744.1. Samples: 44073072. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-15 05:44:43,535][87330] Avg episode reward: [(0, '22.740'), (1, '22.940')] -[2023-10-15 05:44:44,335][88298] Updated weights for policy 0, policy_version 85800 (0.0009) -[2023-10-15 05:44:44,697][88298] Updated weights for policy 0, policy_version 85810 (0.0009) -[2023-10-15 05:44:45,074][88298] Updated weights for policy 0, policy_version 85820 (0.0007) -[2023-10-15 05:44:47,389][88300] Updated weights for policy 1, policy_version 86342 (0.0008) -[2023-10-15 05:44:47,755][88300] Updated weights for policy 1, policy_version 86352 (0.0009) -[2023-10-15 05:44:48,116][88300] Updated weights for policy 1, policy_version 86362 (0.0012) -[2023-10-15 05:44:48,534][87330] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 176324608. Throughput: 0: 1718.3, 1: 1753.0. Samples: 44083410. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-15 05:44:48,535][87330] Avg episode reward: [(0, '22.730'), (1, '22.870')] -[2023-10-15 05:44:48,981][88298] Updated weights for policy 0, policy_version 85830 (0.0007) -[2023-10-15 05:44:49,356][88298] Updated weights for policy 0, policy_version 85840 (0.0007) -[2023-10-15 05:44:49,721][88298] Updated weights for policy 0, policy_version 85850 (0.0007) -[2023-10-15 05:44:51,968][88300] Updated weights for policy 1, policy_version 86372 (0.0010) -[2023-10-15 05:44:52,325][88300] Updated weights for policy 1, policy_version 86382 (0.0007) -[2023-10-15 05:44:52,691][88300] Updated weights for policy 1, policy_version 86392 (0.0010) -[2023-10-15 05:44:53,370][88298] Updated weights for policy 0, policy_version 85860 (0.0008) -[2023-10-15 05:44:53,534][87330] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 176390144. Throughput: 0: 1735.9, 1: 1750.9. Samples: 44104638. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-15 05:44:53,535][87330] Avg episode reward: [(0, '22.790'), (1, '22.890')] -[2023-10-15 05:44:53,743][88298] Updated weights for policy 0, policy_version 85870 (0.0009) -[2023-10-15 05:44:54,108][88298] Updated weights for policy 0, policy_version 85880 (0.0010) -[2023-10-15 05:44:56,498][88300] Updated weights for policy 1, policy_version 86402 (0.0008) -[2023-10-15 05:44:56,862][88300] Updated weights for policy 1, policy_version 86412 (0.0008) -[2023-10-15 05:44:57,231][88300] Updated weights for policy 1, policy_version 86422 (0.0007) -[2023-10-15 05:44:57,590][88300] Updated weights for policy 1, policy_version 86432 (0.0007) -[2023-10-15 05:44:58,064][88298] Updated weights for policy 0, policy_version 85890 (0.0008) -[2023-10-15 05:44:58,440][88298] Updated weights for policy 0, policy_version 85900 (0.0007) -[2023-10-15 05:44:58,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 176455680. Throughput: 0: 1754.7, 1: 1726.1. Samples: 44125538. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-15 05:44:58,535][87330] Avg episode reward: [(0, '22.940'), (1, '22.850')] -[2023-10-15 05:44:58,545][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000086432_88506368.pth... -[2023-10-15 05:44:58,583][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000084800_86835200.pth -[2023-10-15 05:44:58,808][88298] Updated weights for policy 0, policy_version 85910 (0.0007) -[2023-10-15 05:44:59,166][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000085920_87982080.pth... -[2023-10-15 05:44:59,170][88298] Updated weights for policy 0, policy_version 85920 (0.0008) -[2023-10-15 05:44:59,194][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000084288_86310912.pth -[2023-10-15 05:45:01,618][88300] Updated weights for policy 1, policy_version 86442 (0.0007) -[2023-10-15 05:45:01,993][88300] Updated weights for policy 1, policy_version 86452 (0.0009) -[2023-10-15 05:45:02,357][88300] Updated weights for policy 1, policy_version 86462 (0.0010) -[2023-10-15 05:45:03,030][88298] Updated weights for policy 0, policy_version 85930 (0.0007) -[2023-10-15 05:45:03,402][88298] Updated weights for policy 0, policy_version 85940 (0.0009) -[2023-10-15 05:45:03,534][87330] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 176521216. Throughput: 0: 1731.3, 1: 1757.6. Samples: 44136278. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-15 05:45:03,534][87330] Avg episode reward: [(0, '22.880'), (1, '22.780')] -[2023-10-15 05:45:03,762][88298] Updated weights for policy 0, policy_version 85950 (0.0009) -[2023-10-15 05:45:06,219][88300] Updated weights for policy 1, policy_version 86472 (0.0008) -[2023-10-15 05:45:06,584][88300] Updated weights for policy 1, policy_version 86482 (0.0011) -[2023-10-15 05:45:06,943][88300] Updated weights for policy 1, policy_version 86492 (0.0010) -[2023-10-15 05:45:07,800][88298] Updated weights for policy 0, policy_version 85960 (0.0010) -[2023-10-15 05:45:08,180][88298] Updated weights for policy 0, policy_version 85970 (0.0009) -[2023-10-15 05:45:08,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 176586752. Throughput: 0: 1764.6, 1: 1726.2. Samples: 44156558. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-15 05:45:08,534][87330] Avg episode reward: [(0, '22.880'), (1, '22.690')] -[2023-10-15 05:45:08,560][88298] Updated weights for policy 0, policy_version 85980 (0.0008) -[2023-10-15 05:45:10,724][88300] Updated weights for policy 1, policy_version 86502 (0.0008) -[2023-10-15 05:45:11,083][88300] Updated weights for policy 1, policy_version 86512 (0.0007) -[2023-10-15 05:45:11,451][88300] Updated weights for policy 1, policy_version 86522 (0.0007) -[2023-10-15 05:45:12,407][88298] Updated weights for policy 0, policy_version 85990 (0.0007) -[2023-10-15 05:45:12,791][88298] Updated weights for policy 0, policy_version 86000 (0.0008) -[2023-10-15 05:45:13,164][88298] Updated weights for policy 0, policy_version 86010 (0.0007) -[2023-10-15 05:45:13,534][87330] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 176685056. Throughput: 0: 1747.7, 1: 1731.6. Samples: 44177652. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-15 05:45:13,535][87330] Avg episode reward: [(0, '22.820'), (1, '22.540')] -[2023-10-15 05:45:15,388][88300] Updated weights for policy 1, policy_version 86532 (0.0008) -[2023-10-15 05:45:15,753][88300] Updated weights for policy 1, policy_version 86542 (0.0009) -[2023-10-15 05:45:16,121][88300] Updated weights for policy 1, policy_version 86552 (0.0007) -[2023-10-15 05:45:16,991][88298] Updated weights for policy 0, policy_version 86020 (0.0008) -[2023-10-15 05:45:17,369][88298] Updated weights for policy 0, policy_version 86030 (0.0009) -[2023-10-15 05:45:17,731][88298] Updated weights for policy 0, policy_version 86040 (0.0007) -[2023-10-15 05:45:18,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 176750592. Throughput: 0: 1752.1, 1: 1735.2. Samples: 44188082. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-15 05:45:18,534][87330] Avg episode reward: [(0, '22.870'), (1, '22.650')] -[2023-10-15 05:45:20,117][88300] Updated weights for policy 1, policy_version 86562 (0.0008) -[2023-10-15 05:45:20,489][88300] Updated weights for policy 1, policy_version 86572 (0.0007) -[2023-10-15 05:45:20,860][88300] Updated weights for policy 1, policy_version 86582 (0.0007) -[2023-10-15 05:45:21,224][88300] Updated weights for policy 1, policy_version 86592 (0.0008) -[2023-10-15 05:45:21,552][88298] Updated weights for policy 0, policy_version 86050 (0.0007) -[2023-10-15 05:45:21,914][88298] Updated weights for policy 0, policy_version 86060 (0.0007) -[2023-10-15 05:45:22,285][88298] Updated weights for policy 0, policy_version 86070 (0.0007) -[2023-10-15 05:45:22,652][88298] Updated weights for policy 0, policy_version 86080 (0.0007) -[2023-10-15 05:45:23,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 176816128. Throughput: 0: 1758.2, 1: 1736.3. Samples: 44209296. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-15 05:45:23,534][87330] Avg episode reward: [(0, '22.830'), (1, '22.700')] -[2023-10-15 05:45:25,249][88300] Updated weights for policy 1, policy_version 86602 (0.0008) -[2023-10-15 05:45:25,617][88300] Updated weights for policy 1, policy_version 86612 (0.0008) -[2023-10-15 05:45:25,986][88300] Updated weights for policy 1, policy_version 86622 (0.0009) -[2023-10-15 05:45:26,539][88298] Updated weights for policy 0, policy_version 86090 (0.0007) -[2023-10-15 05:45:26,907][88298] Updated weights for policy 0, policy_version 86100 (0.0009) -[2023-10-15 05:45:27,280][88298] Updated weights for policy 0, policy_version 86110 (0.0010) -[2023-10-15 05:45:28,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 176881664. Throughput: 0: 1731.4, 1: 1754.1. Samples: 44229920. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:45:28,535][87330] Avg episode reward: [(0, '22.860'), (1, '22.650')] -[2023-10-15 05:45:29,532][88300] Updated weights for policy 1, policy_version 86632 (0.0009) -[2023-10-15 05:45:29,903][88300] Updated weights for policy 1, policy_version 86642 (0.0009) -[2023-10-15 05:45:30,268][88300] Updated weights for policy 1, policy_version 86652 (0.0009) -[2023-10-15 05:45:31,475][88298] Updated weights for policy 0, policy_version 86120 (0.0009) -[2023-10-15 05:45:31,838][88298] Updated weights for policy 0, policy_version 86130 (0.0007) -[2023-10-15 05:45:32,215][88298] Updated weights for policy 0, policy_version 86140 (0.0007) -[2023-10-15 05:45:33,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 176947200. Throughput: 0: 1759.2, 1: 1738.4. Samples: 44240800. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:45:33,534][87330] Avg episode reward: [(0, '22.870'), (1, '22.600')] -[2023-10-15 05:45:34,226][88300] Updated weights for policy 1, policy_version 86662 (0.0008) -[2023-10-15 05:45:34,603][88300] Updated weights for policy 1, policy_version 86672 (0.0007) -[2023-10-15 05:45:34,973][88300] Updated weights for policy 1, policy_version 86682 (0.0008) -[2023-10-15 05:45:36,105][88298] Updated weights for policy 0, policy_version 86150 (0.0008) -[2023-10-15 05:45:36,472][88298] Updated weights for policy 0, policy_version 86160 (0.0010) -[2023-10-15 05:45:36,839][88298] Updated weights for policy 0, policy_version 86170 (0.0009) -[2023-10-15 05:45:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 177012736. Throughput: 0: 1738.0, 1: 1746.1. Samples: 44261424. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:45:38,535][87330] Avg episode reward: [(0, '22.900'), (1, '22.660')] -[2023-10-15 05:45:38,915][88300] Updated weights for policy 1, policy_version 86692 (0.0009) -[2023-10-15 05:45:39,293][88300] Updated weights for policy 1, policy_version 86702 (0.0007) -[2023-10-15 05:45:39,658][88300] Updated weights for policy 1, policy_version 86712 (0.0010) -[2023-10-15 05:45:40,589][88298] Updated weights for policy 0, policy_version 86180 (0.0010) -[2023-10-15 05:45:40,955][88298] Updated weights for policy 0, policy_version 86190 (0.0008) -[2023-10-15 05:45:41,327][88298] Updated weights for policy 0, policy_version 86200 (0.0008) -[2023-10-15 05:45:43,523][88300] Updated weights for policy 1, policy_version 86722 (0.0007) -[2023-10-15 05:45:43,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 177078272. Throughput: 0: 1725.2, 1: 1766.3. Samples: 44282656. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:45:43,535][87330] Avg episode reward: [(0, '22.930'), (1, '22.770')] -[2023-10-15 05:45:43,900][88300] Updated weights for policy 1, policy_version 86732 (0.0008) -[2023-10-15 05:45:44,257][88300] Updated weights for policy 1, policy_version 86742 (0.0009) -[2023-10-15 05:45:44,628][88300] Updated weights for policy 1, policy_version 86752 (0.0007) -[2023-10-15 05:45:45,217][88298] Updated weights for policy 0, policy_version 86210 (0.0009) -[2023-10-15 05:45:45,590][88298] Updated weights for policy 0, policy_version 86220 (0.0010) -[2023-10-15 05:45:45,958][88298] Updated weights for policy 0, policy_version 86230 (0.0007) -[2023-10-15 05:45:46,334][88298] Updated weights for policy 0, policy_version 86240 (0.0010) -[2023-10-15 05:45:48,493][88300] Updated weights for policy 1, policy_version 86762 (0.0010) -[2023-10-15 05:45:48,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 177143808. Throughput: 0: 1741.0, 1: 1739.6. Samples: 44292902. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:45:48,534][87330] Avg episode reward: [(0, '22.940'), (1, '22.750')] -[2023-10-15 05:45:48,859][88300] Updated weights for policy 1, policy_version 86772 (0.0008) -[2023-10-15 05:45:49,219][88300] Updated weights for policy 1, policy_version 86782 (0.0009) -[2023-10-15 05:45:50,092][88298] Updated weights for policy 0, policy_version 86250 (0.0008) -[2023-10-15 05:45:50,464][88298] Updated weights for policy 0, policy_version 86260 (0.0010) -[2023-10-15 05:45:50,836][88298] Updated weights for policy 0, policy_version 86270 (0.0007) -[2023-10-15 05:45:53,054][88300] Updated weights for policy 1, policy_version 86792 (0.0008) -[2023-10-15 05:45:53,421][88300] Updated weights for policy 1, policy_version 86802 (0.0008) -[2023-10-15 05:45:53,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 177209344. Throughput: 0: 1723.4, 1: 1768.4. Samples: 44313690. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:45:53,535][87330] Avg episode reward: [(0, '22.970'), (1, '22.720')] -[2023-10-15 05:45:53,795][88300] Updated weights for policy 1, policy_version 86812 (0.0008) -[2023-10-15 05:45:54,690][88298] Updated weights for policy 0, policy_version 86280 (0.0009) -[2023-10-15 05:45:55,064][88298] Updated weights for policy 0, policy_version 86290 (0.0010) -[2023-10-15 05:45:55,419][88298] Updated weights for policy 0, policy_version 86300 (0.0011) -[2023-10-15 05:45:57,744][88300] Updated weights for policy 1, policy_version 86822 (0.0008) -[2023-10-15 05:45:58,103][88300] Updated weights for policy 1, policy_version 86832 (0.0010) -[2023-10-15 05:45:58,466][88300] Updated weights for policy 1, policy_version 86842 (0.0011) -[2023-10-15 05:45:58,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 177274880. Throughput: 0: 1740.2, 1: 1745.7. Samples: 44334518. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:45:58,534][87330] Avg episode reward: [(0, '23.040'), (1, '22.610')] -[2023-10-15 05:45:59,305][88298] Updated weights for policy 0, policy_version 86310 (0.0009) -[2023-10-15 05:45:59,670][88298] Updated weights for policy 0, policy_version 86320 (0.0007) -[2023-10-15 05:46:00,032][88298] Updated weights for policy 0, policy_version 86330 (0.0008) -[2023-10-15 05:46:02,398][88300] Updated weights for policy 1, policy_version 86852 (0.0008) -[2023-10-15 05:46:02,768][88300] Updated weights for policy 1, policy_version 86862 (0.0007) -[2023-10-15 05:46:03,149][88300] Updated weights for policy 1, policy_version 86872 (0.0008) -[2023-10-15 05:46:03,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 177373184. Throughput: 0: 1725.3, 1: 1758.0. Samples: 44344832. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:46:03,534][87330] Avg episode reward: [(0, '23.050'), (1, '22.700')] -[2023-10-15 05:46:04,025][88298] Updated weights for policy 0, policy_version 86340 (0.0008) -[2023-10-15 05:46:04,394][88298] Updated weights for policy 0, policy_version 86350 (0.0007) -[2023-10-15 05:46:04,761][88298] Updated weights for policy 0, policy_version 86360 (0.0008) -[2023-10-15 05:46:07,139][88300] Updated weights for policy 1, policy_version 86882 (0.0008) -[2023-10-15 05:46:07,503][88300] Updated weights for policy 1, policy_version 86892 (0.0011) -[2023-10-15 05:46:07,872][88300] Updated weights for policy 1, policy_version 86902 (0.0011) -[2023-10-15 05:46:08,231][88300] Updated weights for policy 1, policy_version 86912 (0.0011) -[2023-10-15 05:46:08,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 177438720. Throughput: 0: 1730.4, 1: 1753.1. Samples: 44366052. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:46:08,534][87330] Avg episode reward: [(0, '23.070'), (1, '22.730')] -[2023-10-15 05:46:08,705][88298] Updated weights for policy 0, policy_version 86370 (0.0007) -[2023-10-15 05:46:09,070][88298] Updated weights for policy 0, policy_version 86380 (0.0011) -[2023-10-15 05:46:09,449][88298] Updated weights for policy 0, policy_version 86390 (0.0011) -[2023-10-15 05:46:09,810][88298] Updated weights for policy 0, policy_version 86400 (0.0009) -[2023-10-15 05:46:12,139][88300] Updated weights for policy 1, policy_version 86922 (0.0010) -[2023-10-15 05:46:12,510][88300] Updated weights for policy 1, policy_version 86932 (0.0008) -[2023-10-15 05:46:12,878][88300] Updated weights for policy 1, policy_version 86942 (0.0007) -[2023-10-15 05:46:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 177504256. Throughput: 0: 1753.1, 1: 1725.3. Samples: 44386446. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:46:13,534][87330] Avg episode reward: [(0, '23.070'), (1, '22.810')] -[2023-10-15 05:46:13,853][88298] Updated weights for policy 0, policy_version 86410 (0.0008) -[2023-10-15 05:46:14,229][88298] Updated weights for policy 0, policy_version 86420 (0.0011) -[2023-10-15 05:46:14,594][88298] Updated weights for policy 0, policy_version 86430 (0.0010) -[2023-10-15 05:46:16,567][88300] Updated weights for policy 1, policy_version 86952 (0.0010) -[2023-10-15 05:46:16,941][88300] Updated weights for policy 1, policy_version 86962 (0.0009) -[2023-10-15 05:46:17,308][88300] Updated weights for policy 1, policy_version 86972 (0.0009) -[2023-10-15 05:46:18,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 177569792. Throughput: 0: 1718.3, 1: 1762.0. Samples: 44397414. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:46:18,535][87330] Avg episode reward: [(0, '23.030'), (1, '22.710')] -[2023-10-15 05:46:18,578][88298] Updated weights for policy 0, policy_version 86440 (0.0009) -[2023-10-15 05:46:18,957][88298] Updated weights for policy 0, policy_version 86450 (0.0008) -[2023-10-15 05:46:19,324][88298] Updated weights for policy 0, policy_version 86460 (0.0007) -[2023-10-15 05:46:21,105][88300] Updated weights for policy 1, policy_version 86982 (0.0010) -[2023-10-15 05:46:21,474][88300] Updated weights for policy 1, policy_version 86992 (0.0008) -[2023-10-15 05:46:21,833][88300] Updated weights for policy 1, policy_version 87002 (0.0008) -[2023-10-15 05:46:23,407][88298] Updated weights for policy 0, policy_version 86470 (0.0008) -[2023-10-15 05:46:23,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 177635328. Throughput: 0: 1735.9, 1: 1734.3. Samples: 44417582. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:46:23,534][87330] Avg episode reward: [(0, '22.760'), (1, '22.670')] -[2023-10-15 05:46:23,793][88298] Updated weights for policy 0, policy_version 86480 (0.0010) -[2023-10-15 05:46:24,157][88298] Updated weights for policy 0, policy_version 86490 (0.0011) -[2023-10-15 05:46:25,642][88300] Updated weights for policy 1, policy_version 87012 (0.0009) -[2023-10-15 05:46:26,007][88300] Updated weights for policy 1, policy_version 87022 (0.0008) -[2023-10-15 05:46:26,372][88300] Updated weights for policy 1, policy_version 87032 (0.0009) -[2023-10-15 05:46:28,125][88298] Updated weights for policy 0, policy_version 86500 (0.0008) -[2023-10-15 05:46:28,493][88298] Updated weights for policy 0, policy_version 86510 (0.0008) -[2023-10-15 05:46:28,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 177700864. Throughput: 0: 1741.9, 1: 1738.1. Samples: 44439256. Policy #0 lag: (min: 7.0, avg: 7.3, max: 18.0) -[2023-10-15 05:46:28,534][87330] Avg episode reward: [(0, '22.810'), (1, '22.790')] -[2023-10-15 05:46:28,866][88298] Updated weights for policy 0, policy_version 86520 (0.0008) -[2023-10-15 05:46:30,280][88300] Updated weights for policy 1, policy_version 87042 (0.0009) -[2023-10-15 05:46:30,637][88300] Updated weights for policy 1, policy_version 87052 (0.0009) -[2023-10-15 05:46:31,005][88300] Updated weights for policy 1, policy_version 87062 (0.0007) -[2023-10-15 05:46:31,372][88300] Updated weights for policy 1, policy_version 87072 (0.0009) -[2023-10-15 05:46:32,534][88298] Updated weights for policy 0, policy_version 86530 (0.0007) -[2023-10-15 05:46:32,915][88298] Updated weights for policy 0, policy_version 86540 (0.0008) -[2023-10-15 05:46:33,287][88298] Updated weights for policy 0, policy_version 86550 (0.0008) -[2023-10-15 05:46:33,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 177766400. Throughput: 0: 1726.3, 1: 1744.4. Samples: 44449080. Policy #0 lag: (min: 7.0, avg: 7.3, max: 18.0) -[2023-10-15 05:46:33,534][87330] Avg episode reward: [(0, '22.850'), (1, '22.770')] -[2023-10-15 05:46:33,649][88298] Updated weights for policy 0, policy_version 86560 (0.0009) -[2023-10-15 05:46:35,259][88300] Updated weights for policy 1, policy_version 87082 (0.0008) -[2023-10-15 05:46:35,626][88300] Updated weights for policy 1, policy_version 87092 (0.0007) -[2023-10-15 05:46:35,989][88300] Updated weights for policy 1, policy_version 87102 (0.0007) -[2023-10-15 05:46:37,569][88298] Updated weights for policy 0, policy_version 86570 (0.0009) -[2023-10-15 05:46:37,933][88298] Updated weights for policy 0, policy_version 86580 (0.0009) -[2023-10-15 05:46:38,298][88298] Updated weights for policy 0, policy_version 86590 (0.0008) -[2023-10-15 05:46:38,534][87330] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 177864704. Throughput: 0: 1744.8, 1: 1736.1. Samples: 44470330. Policy #0 lag: (min: 7.0, avg: 7.3, max: 18.0) -[2023-10-15 05:46:38,535][87330] Avg episode reward: [(0, '22.860'), (1, '22.790')] -[2023-10-15 05:46:40,017][88300] Updated weights for policy 1, policy_version 87112 (0.0009) -[2023-10-15 05:46:40,388][88300] Updated weights for policy 1, policy_version 87122 (0.0009) -[2023-10-15 05:46:40,753][88300] Updated weights for policy 1, policy_version 87132 (0.0008) -[2023-10-15 05:46:42,311][88298] Updated weights for policy 0, policy_version 86600 (0.0007) -[2023-10-15 05:46:42,683][88298] Updated weights for policy 0, policy_version 86610 (0.0007) -[2023-10-15 05:46:43,049][88298] Updated weights for policy 0, policy_version 86620 (0.0008) -[2023-10-15 05:46:43,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 177930240. Throughput: 0: 1723.0, 1: 1756.3. Samples: 44491086. Policy #0 lag: (min: 7.0, avg: 7.3, max: 18.0) -[2023-10-15 05:46:43,534][87330] Avg episode reward: [(0, '22.760'), (1, '22.750')] -[2023-10-15 05:46:44,677][88300] Updated weights for policy 1, policy_version 87142 (0.0009) -[2023-10-15 05:46:45,047][88300] Updated weights for policy 1, policy_version 87152 (0.0007) -[2023-10-15 05:46:45,411][88300] Updated weights for policy 1, policy_version 87162 (0.0008) -[2023-10-15 05:46:46,860][88298] Updated weights for policy 0, policy_version 86630 (0.0008) -[2023-10-15 05:46:47,220][88298] Updated weights for policy 0, policy_version 86640 (0.0007) -[2023-10-15 05:46:47,591][88298] Updated weights for policy 0, policy_version 86650 (0.0009) -[2023-10-15 05:46:48,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 177995776. Throughput: 0: 1742.8, 1: 1737.0. Samples: 44501424. Policy #0 lag: (min: 7.0, avg: 7.3, max: 18.0) -[2023-10-15 05:46:48,534][87330] Avg episode reward: [(0, '22.780'), (1, '22.870')] -[2023-10-15 05:46:49,366][88300] Updated weights for policy 1, policy_version 87172 (0.0011) -[2023-10-15 05:46:49,728][88300] Updated weights for policy 1, policy_version 87182 (0.0007) -[2023-10-15 05:46:50,095][88300] Updated weights for policy 1, policy_version 87192 (0.0008) -[2023-10-15 05:46:51,593][88298] Updated weights for policy 0, policy_version 86660 (0.0009) -[2023-10-15 05:46:51,960][88298] Updated weights for policy 0, policy_version 86670 (0.0008) -[2023-10-15 05:46:52,322][88298] Updated weights for policy 0, policy_version 86680 (0.0007) -[2023-10-15 05:46:53,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 178061312. Throughput: 0: 1734.7, 1: 1743.2. Samples: 44522558. Policy #0 lag: (min: 7.0, avg: 7.3, max: 18.0) -[2023-10-15 05:46:53,535][87330] Avg episode reward: [(0, '23.050'), (1, '22.930')] -[2023-10-15 05:46:53,971][88300] Updated weights for policy 1, policy_version 87202 (0.0009) -[2023-10-15 05:46:54,343][88300] Updated weights for policy 1, policy_version 87212 (0.0009) -[2023-10-15 05:46:54,714][88300] Updated weights for policy 1, policy_version 87222 (0.0009) -[2023-10-15 05:46:55,075][88300] Updated weights for policy 1, policy_version 87232 (0.0008) -[2023-10-15 05:46:56,186][88298] Updated weights for policy 0, policy_version 86690 (0.0009) -[2023-10-15 05:46:56,558][88298] Updated weights for policy 0, policy_version 86700 (0.0009) -[2023-10-15 05:46:56,926][88298] Updated weights for policy 0, policy_version 86710 (0.0009) -[2023-10-15 05:46:57,294][88298] Updated weights for policy 0, policy_version 86720 (0.0008) -[2023-10-15 05:46:58,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 178126848. Throughput: 0: 1711.9, 1: 1771.2. Samples: 44543186. Policy #0 lag: (min: 7.0, avg: 7.3, max: 18.0) -[2023-10-15 05:46:58,534][87330] Avg episode reward: [(0, '23.090'), (1, '22.820')] -[2023-10-15 05:46:58,544][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000086720_88801280.pth... -[2023-10-15 05:46:58,580][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000085088_87130112.pth -[2023-10-15 05:46:58,995][88300] Updated weights for policy 1, policy_version 87242 (0.0007) -[2023-10-15 05:46:59,359][88300] Updated weights for policy 1, policy_version 87252 (0.0007) -[2023-10-15 05:46:59,722][88300] Updated weights for policy 1, policy_version 87262 (0.0008) -[2023-10-15 05:46:59,796][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000087264_89358336.pth... -[2023-10-15 05:46:59,834][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000085600_87654400.pth -[2023-10-15 05:47:01,138][88298] Updated weights for policy 0, policy_version 86730 (0.0008) -[2023-10-15 05:47:01,506][88298] Updated weights for policy 0, policy_version 86740 (0.0007) -[2023-10-15 05:47:01,888][88298] Updated weights for policy 0, policy_version 86750 (0.0008) -[2023-10-15 05:47:03,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 178192384. Throughput: 0: 1747.7, 1: 1733.9. Samples: 44554086. Policy #0 lag: (min: 7.0, avg: 7.3, max: 18.0) -[2023-10-15 05:47:03,535][87330] Avg episode reward: [(0, '23.080'), (1, '22.860')] -[2023-10-15 05:47:03,601][88300] Updated weights for policy 1, policy_version 87272 (0.0009) -[2023-10-15 05:47:03,964][88300] Updated weights for policy 1, policy_version 87282 (0.0009) -[2023-10-15 05:47:04,338][88300] Updated weights for policy 1, policy_version 87292 (0.0010) -[2023-10-15 05:47:05,944][88298] Updated weights for policy 0, policy_version 86760 (0.0009) -[2023-10-15 05:47:06,313][88298] Updated weights for policy 0, policy_version 86770 (0.0009) -[2023-10-15 05:47:06,682][88298] Updated weights for policy 0, policy_version 86780 (0.0008) -[2023-10-15 05:47:08,364][88300] Updated weights for policy 1, policy_version 87302 (0.0011) -[2023-10-15 05:47:08,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 178257920. Throughput: 0: 1716.9, 1: 1763.0. Samples: 44574178. Policy #0 lag: (min: 7.0, avg: 7.3, max: 18.0) -[2023-10-15 05:47:08,534][87330] Avg episode reward: [(0, '23.040'), (1, '22.840')] -[2023-10-15 05:47:08,725][88300] Updated weights for policy 1, policy_version 87312 (0.0008) -[2023-10-15 05:47:09,087][88300] Updated weights for policy 1, policy_version 87322 (0.0009) -[2023-10-15 05:47:10,545][88298] Updated weights for policy 0, policy_version 86790 (0.0008) -[2023-10-15 05:47:10,911][88298] Updated weights for policy 0, policy_version 86800 (0.0007) -[2023-10-15 05:47:11,281][88298] Updated weights for policy 0, policy_version 86810 (0.0009) -[2023-10-15 05:47:13,022][88300] Updated weights for policy 1, policy_version 87332 (0.0008) -[2023-10-15 05:47:13,397][88300] Updated weights for policy 1, policy_version 87342 (0.0007) -[2023-10-15 05:47:13,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 178323456. Throughput: 0: 1715.3, 1: 1747.6. Samples: 44595088. Policy #0 lag: (min: 7.0, avg: 7.3, max: 18.0) -[2023-10-15 05:47:13,534][87330] Avg episode reward: [(0, '23.120'), (1, '22.880')] -[2023-10-15 05:47:13,775][88300] Updated weights for policy 1, policy_version 87352 (0.0007) -[2023-10-15 05:47:15,180][88298] Updated weights for policy 0, policy_version 86820 (0.0009) -[2023-10-15 05:47:15,559][88298] Updated weights for policy 0, policy_version 86830 (0.0007) -[2023-10-15 05:47:15,930][88298] Updated weights for policy 0, policy_version 86840 (0.0007) -[2023-10-15 05:47:17,600][88300] Updated weights for policy 1, policy_version 87362 (0.0009) -[2023-10-15 05:47:17,973][88300] Updated weights for policy 1, policy_version 87372 (0.0010) -[2023-10-15 05:47:18,343][88300] Updated weights for policy 1, policy_version 87382 (0.0007) -[2023-10-15 05:47:18,534][87330] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 178388992. Throughput: 0: 1727.7, 1: 1745.6. Samples: 44605380. Policy #0 lag: (min: 7.0, avg: 7.3, max: 18.0) -[2023-10-15 05:47:18,535][87330] Avg episode reward: [(0, '23.090'), (1, '22.850')] -[2023-10-15 05:47:18,715][88300] Updated weights for policy 1, policy_version 87392 (0.0007) -[2023-10-15 05:47:19,868][88298] Updated weights for policy 0, policy_version 86850 (0.0008) -[2023-10-15 05:47:20,237][88298] Updated weights for policy 0, policy_version 86860 (0.0009) -[2023-10-15 05:47:20,608][88298] Updated weights for policy 0, policy_version 86870 (0.0010) -[2023-10-15 05:47:20,981][88298] Updated weights for policy 0, policy_version 86880 (0.0008) -[2023-10-15 05:47:22,685][88300] Updated weights for policy 1, policy_version 87402 (0.0007) -[2023-10-15 05:47:23,050][88300] Updated weights for policy 1, policy_version 87412 (0.0008) -[2023-10-15 05:47:23,413][88300] Updated weights for policy 1, policy_version 87422 (0.0009) -[2023-10-15 05:47:23,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 178487296. Throughput: 0: 1717.3, 1: 1755.6. Samples: 44626608. Policy #0 lag: (min: 30.0, avg: 37.5, max: 62.0) -[2023-10-15 05:47:23,534][87330] Avg episode reward: [(0, '23.060'), (1, '22.840')] -[2023-10-15 05:47:24,836][88298] Updated weights for policy 0, policy_version 86890 (0.0008) -[2023-10-15 05:47:25,209][88298] Updated weights for policy 0, policy_version 86900 (0.0008) -[2023-10-15 05:47:25,579][88298] Updated weights for policy 0, policy_version 86910 (0.0007) -[2023-10-15 05:47:27,393][88300] Updated weights for policy 1, policy_version 87432 (0.0008) -[2023-10-15 05:47:27,765][88300] Updated weights for policy 1, policy_version 87442 (0.0008) -[2023-10-15 05:47:28,134][88300] Updated weights for policy 1, policy_version 87452 (0.0007) -[2023-10-15 05:47:28,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 178552832. Throughput: 0: 1748.8, 1: 1721.9. Samples: 44647268. Policy #0 lag: (min: 30.0, avg: 37.5, max: 62.0) -[2023-10-15 05:47:28,535][87330] Avg episode reward: [(0, '23.030'), (1, '23.000')] -[2023-10-15 05:47:29,343][88298] Updated weights for policy 0, policy_version 86920 (0.0008) -[2023-10-15 05:47:29,707][88298] Updated weights for policy 0, policy_version 86930 (0.0009) -[2023-10-15 05:47:30,082][88298] Updated weights for policy 0, policy_version 86940 (0.0007) -[2023-10-15 05:47:31,955][88300] Updated weights for policy 1, policy_version 87462 (0.0009) -[2023-10-15 05:47:32,322][88300] Updated weights for policy 1, policy_version 87472 (0.0008) -[2023-10-15 05:47:32,698][88300] Updated weights for policy 1, policy_version 87482 (0.0008) -[2023-10-15 05:47:33,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 178618368. Throughput: 0: 1727.4, 1: 1752.1. Samples: 44658002. Policy #0 lag: (min: 30.0, avg: 37.5, max: 62.0) -[2023-10-15 05:47:33,534][87330] Avg episode reward: [(0, '23.020'), (1, '22.880')] -[2023-10-15 05:47:33,965][88298] Updated weights for policy 0, policy_version 86950 (0.0010) -[2023-10-15 05:47:34,347][88298] Updated weights for policy 0, policy_version 86960 (0.0010) -[2023-10-15 05:47:34,717][88298] Updated weights for policy 0, policy_version 86970 (0.0010) -[2023-10-15 05:47:36,689][88300] Updated weights for policy 1, policy_version 87492 (0.0010) -[2023-10-15 05:47:37,052][88300] Updated weights for policy 1, policy_version 87502 (0.0007) -[2023-10-15 05:47:37,410][88300] Updated weights for policy 1, policy_version 87512 (0.0009) -[2023-10-15 05:47:38,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 178683904. Throughput: 0: 1738.5, 1: 1734.7. Samples: 44678852. Policy #0 lag: (min: 30.0, avg: 37.5, max: 62.0) -[2023-10-15 05:47:38,534][87330] Avg episode reward: [(0, '23.060'), (1, '22.910')] -[2023-10-15 05:47:38,661][88298] Updated weights for policy 0, policy_version 86980 (0.0007) -[2023-10-15 05:47:39,026][88298] Updated weights for policy 0, policy_version 86990 (0.0010) -[2023-10-15 05:47:39,396][88298] Updated weights for policy 0, policy_version 87000 (0.0011) -[2023-10-15 05:47:41,146][88300] Updated weights for policy 1, policy_version 87522 (0.0010) -[2023-10-15 05:47:41,506][88300] Updated weights for policy 1, policy_version 87532 (0.0008) -[2023-10-15 05:47:41,874][88300] Updated weights for policy 1, policy_version 87542 (0.0008) -[2023-10-15 05:47:42,242][88300] Updated weights for policy 1, policy_version 87552 (0.0007) -[2023-10-15 05:47:43,453][88298] Updated weights for policy 0, policy_version 87010 (0.0010) -[2023-10-15 05:47:43,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 178749440. Throughput: 0: 1759.9, 1: 1727.7. Samples: 44700126. Policy #0 lag: (min: 30.0, avg: 37.5, max: 62.0) -[2023-10-15 05:47:43,535][87330] Avg episode reward: [(0, '23.060'), (1, '22.900')] -[2023-10-15 05:47:43,821][88298] Updated weights for policy 0, policy_version 87020 (0.0007) -[2023-10-15 05:47:44,182][88298] Updated weights for policy 0, policy_version 87030 (0.0008) -[2023-10-15 05:47:44,547][88298] Updated weights for policy 0, policy_version 87040 (0.0007) -[2023-10-15 05:47:45,936][88300] Updated weights for policy 1, policy_version 87562 (0.0007) -[2023-10-15 05:47:46,303][88300] Updated weights for policy 1, policy_version 87572 (0.0007) -[2023-10-15 05:47:46,673][88300] Updated weights for policy 1, policy_version 87582 (0.0008) -[2023-10-15 05:47:48,401][88298] Updated weights for policy 0, policy_version 87050 (0.0008) -[2023-10-15 05:47:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 178814976. Throughput: 0: 1725.1, 1: 1745.0. Samples: 44710240. Policy #0 lag: (min: 30.0, avg: 37.5, max: 62.0) -[2023-10-15 05:47:48,534][87330] Avg episode reward: [(0, '22.880'), (1, '22.910')] -[2023-10-15 05:47:48,775][88298] Updated weights for policy 0, policy_version 87060 (0.0008) -[2023-10-15 05:47:49,136][88298] Updated weights for policy 0, policy_version 87070 (0.0007) -[2023-10-15 05:47:50,584][88300] Updated weights for policy 1, policy_version 87592 (0.0008) -[2023-10-15 05:47:50,954][88300] Updated weights for policy 1, policy_version 87602 (0.0007) -[2023-10-15 05:47:51,315][88300] Updated weights for policy 1, policy_version 87612 (0.0010) -[2023-10-15 05:47:52,967][88298] Updated weights for policy 0, policy_version 87080 (0.0009) -[2023-10-15 05:47:53,339][88298] Updated weights for policy 0, policy_version 87090 (0.0008) -[2023-10-15 05:47:53,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 178880512. Throughput: 0: 1757.3, 1: 1728.9. Samples: 44731060. Policy #0 lag: (min: 30.0, avg: 37.5, max: 62.0) -[2023-10-15 05:47:53,535][87330] Avg episode reward: [(0, '22.890'), (1, '22.800')] -[2023-10-15 05:47:53,714][88298] Updated weights for policy 0, policy_version 87100 (0.0008) -[2023-10-15 05:47:55,069][88300] Updated weights for policy 1, policy_version 87622 (0.0009) -[2023-10-15 05:47:55,428][88300] Updated weights for policy 1, policy_version 87632 (0.0008) -[2023-10-15 05:47:55,798][88300] Updated weights for policy 1, policy_version 87642 (0.0008) -[2023-10-15 05:47:57,775][88298] Updated weights for policy 0, policy_version 87110 (0.0009) -[2023-10-15 05:47:58,145][88298] Updated weights for policy 0, policy_version 87120 (0.0008) -[2023-10-15 05:47:58,509][88298] Updated weights for policy 0, policy_version 87130 (0.0008) -[2023-10-15 05:47:58,534][87330] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 178946048. Throughput: 0: 1752.4, 1: 1746.9. Samples: 44752556. Policy #0 lag: (min: 30.0, avg: 37.5, max: 62.0) -[2023-10-15 05:47:58,535][87330] Avg episode reward: [(0, '22.830'), (1, '22.800')] -[2023-10-15 05:47:59,649][88300] Updated weights for policy 1, policy_version 87652 (0.0007) -[2023-10-15 05:48:00,016][88300] Updated weights for policy 1, policy_version 87662 (0.0008) -[2023-10-15 05:48:00,376][88300] Updated weights for policy 1, policy_version 87672 (0.0007) -[2023-10-15 05:48:02,439][88298] Updated weights for policy 0, policy_version 87140 (0.0009) -[2023-10-15 05:48:02,812][88298] Updated weights for policy 0, policy_version 87150 (0.0010) -[2023-10-15 05:48:03,187][88298] Updated weights for policy 0, policy_version 87160 (0.0010) -[2023-10-15 05:48:03,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 179044352. Throughput: 0: 1746.2, 1: 1740.2. Samples: 44762270. Policy #0 lag: (min: 30.0, avg: 37.5, max: 62.0) -[2023-10-15 05:48:03,534][87330] Avg episode reward: [(0, '22.820'), (1, '22.900')] -[2023-10-15 05:48:04,159][88300] Updated weights for policy 1, policy_version 87682 (0.0008) -[2023-10-15 05:48:04,530][88300] Updated weights for policy 1, policy_version 87692 (0.0008) -[2023-10-15 05:48:04,892][88300] Updated weights for policy 1, policy_version 87702 (0.0008) -[2023-10-15 05:48:05,256][88300] Updated weights for policy 1, policy_version 87712 (0.0009) -[2023-10-15 05:48:07,113][88298] Updated weights for policy 0, policy_version 87170 (0.0008) -[2023-10-15 05:48:07,481][88298] Updated weights for policy 0, policy_version 87180 (0.0009) -[2023-10-15 05:48:07,849][88298] Updated weights for policy 0, policy_version 87190 (0.0007) -[2023-10-15 05:48:08,218][88298] Updated weights for policy 0, policy_version 87200 (0.0008) -[2023-10-15 05:48:08,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 179109888. Throughput: 0: 1749.9, 1: 1745.6. Samples: 44783910. Policy #0 lag: (min: 30.0, avg: 37.5, max: 62.0) -[2023-10-15 05:48:08,535][87330] Avg episode reward: [(0, '22.810'), (1, '22.730')] -[2023-10-15 05:48:09,066][88300] Updated weights for policy 1, policy_version 87722 (0.0008) -[2023-10-15 05:48:09,430][88300] Updated weights for policy 1, policy_version 87732 (0.0009) -[2023-10-15 05:48:09,801][88300] Updated weights for policy 1, policy_version 87742 (0.0008) -[2023-10-15 05:48:12,182][88298] Updated weights for policy 0, policy_version 87210 (0.0007) -[2023-10-15 05:48:12,553][88298] Updated weights for policy 0, policy_version 87220 (0.0009) -[2023-10-15 05:48:12,909][88298] Updated weights for policy 0, policy_version 87230 (0.0008) -[2023-10-15 05:48:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 179175424. Throughput: 0: 1713.7, 1: 1784.0. Samples: 44804662. Policy #0 lag: (min: 30.0, avg: 37.5, max: 62.0) -[2023-10-15 05:48:13,534][87330] Avg episode reward: [(0, '22.790'), (1, '22.460')] -[2023-10-15 05:48:13,742][88300] Updated weights for policy 1, policy_version 87752 (0.0010) -[2023-10-15 05:48:14,113][88300] Updated weights for policy 1, policy_version 87762 (0.0011) -[2023-10-15 05:48:14,474][88300] Updated weights for policy 1, policy_version 87772 (0.0007) -[2023-10-15 05:48:17,060][88298] Updated weights for policy 0, policy_version 87240 (0.0009) -[2023-10-15 05:48:17,433][88298] Updated weights for policy 0, policy_version 87250 (0.0009) -[2023-10-15 05:48:17,794][88298] Updated weights for policy 0, policy_version 87260 (0.0008) -[2023-10-15 05:48:18,209][88300] Updated weights for policy 1, policy_version 87782 (0.0008) -[2023-10-15 05:48:18,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 179240960. Throughput: 0: 1738.6, 1: 1753.2. Samples: 44815134. Policy #0 lag: (min: 11.0, avg: 14.0, max: 43.0) -[2023-10-15 05:48:18,535][87330] Avg episode reward: [(0, '22.860'), (1, '22.360')] -[2023-10-15 05:48:18,576][88300] Updated weights for policy 1, policy_version 87792 (0.0008) -[2023-10-15 05:48:18,946][88300] Updated weights for policy 1, policy_version 87802 (0.0007) -[2023-10-15 05:48:21,689][88298] Updated weights for policy 0, policy_version 87270 (0.0009) -[2023-10-15 05:48:22,060][88298] Updated weights for policy 0, policy_version 87280 (0.0008) -[2023-10-15 05:48:22,428][88298] Updated weights for policy 0, policy_version 87290 (0.0009) -[2023-10-15 05:48:22,781][88300] Updated weights for policy 1, policy_version 87812 (0.0008) -[2023-10-15 05:48:23,145][88300] Updated weights for policy 1, policy_version 87822 (0.0009) -[2023-10-15 05:48:23,517][88300] Updated weights for policy 1, policy_version 87832 (0.0008) -[2023-10-15 05:48:23,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 179306496. Throughput: 0: 1723.9, 1: 1775.3. Samples: 44836314. Policy #0 lag: (min: 11.0, avg: 14.0, max: 43.0) -[2023-10-15 05:48:23,535][87330] Avg episode reward: [(0, '22.870'), (1, '22.350')] -[2023-10-15 05:48:26,338][88298] Updated weights for policy 0, policy_version 87300 (0.0009) -[2023-10-15 05:48:26,706][88298] Updated weights for policy 0, policy_version 87310 (0.0010) -[2023-10-15 05:48:27,074][88298] Updated weights for policy 0, policy_version 87320 (0.0009) -[2023-10-15 05:48:27,378][88300] Updated weights for policy 1, policy_version 87842 (0.0009) -[2023-10-15 05:48:27,741][88300] Updated weights for policy 1, policy_version 87852 (0.0009) -[2023-10-15 05:48:28,108][88300] Updated weights for policy 1, policy_version 87862 (0.0008) -[2023-10-15 05:48:28,474][88300] Updated weights for policy 1, policy_version 87872 (0.0007) -[2023-10-15 05:48:28,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 179404800. Throughput: 0: 1701.9, 1: 1762.3. Samples: 44856014. Policy #0 lag: (min: 11.0, avg: 14.0, max: 43.0) -[2023-10-15 05:48:28,535][87330] Avg episode reward: [(0, '22.890'), (1, '22.500')] -[2023-10-15 05:48:30,931][88298] Updated weights for policy 0, policy_version 87330 (0.0007) -[2023-10-15 05:48:31,303][88298] Updated weights for policy 0, policy_version 87340 (0.0008) -[2023-10-15 05:48:31,670][88298] Updated weights for policy 0, policy_version 87350 (0.0009) -[2023-10-15 05:48:32,044][88298] Updated weights for policy 0, policy_version 87360 (0.0008) -[2023-10-15 05:48:32,301][88300] Updated weights for policy 1, policy_version 87882 (0.0009) -[2023-10-15 05:48:32,676][88300] Updated weights for policy 1, policy_version 87892 (0.0008) -[2023-10-15 05:48:33,048][88300] Updated weights for policy 1, policy_version 87902 (0.0007) -[2023-10-15 05:48:33,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 179470336. Throughput: 0: 1739.0, 1: 1768.7. Samples: 44868086. Policy #0 lag: (min: 11.0, avg: 14.0, max: 43.0) -[2023-10-15 05:48:33,535][87330] Avg episode reward: [(0, '22.910'), (1, '22.360')] -[2023-10-15 05:48:35,924][88298] Updated weights for policy 0, policy_version 87370 (0.0008) -[2023-10-15 05:48:36,301][88298] Updated weights for policy 0, policy_version 87380 (0.0009) -[2023-10-15 05:48:36,659][88298] Updated weights for policy 0, policy_version 87390 (0.0010) -[2023-10-15 05:48:36,954][88300] Updated weights for policy 1, policy_version 87912 (0.0009) -[2023-10-15 05:48:37,320][88300] Updated weights for policy 1, policy_version 87922 (0.0010) -[2023-10-15 05:48:37,695][88300] Updated weights for policy 1, policy_version 87932 (0.0008) -[2023-10-15 05:48:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 179535872. Throughput: 0: 1711.7, 1: 1777.9. Samples: 44888090. Policy #0 lag: (min: 11.0, avg: 14.0, max: 43.0) -[2023-10-15 05:48:38,535][87330] Avg episode reward: [(0, '22.970'), (1, '22.550')] -[2023-10-15 05:48:40,330][88298] Updated weights for policy 0, policy_version 87400 (0.0007) -[2023-10-15 05:48:40,706][88298] Updated weights for policy 0, policy_version 87410 (0.0008) -[2023-10-15 05:48:41,074][88298] Updated weights for policy 0, policy_version 87420 (0.0008) -[2023-10-15 05:48:41,472][88300] Updated weights for policy 1, policy_version 87942 (0.0008) -[2023-10-15 05:48:41,840][88300] Updated weights for policy 1, policy_version 87952 (0.0009) -[2023-10-15 05:48:42,204][88300] Updated weights for policy 1, policy_version 87962 (0.0010) -[2023-10-15 05:48:43,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 179601408. Throughput: 0: 1720.8, 1: 1758.4. Samples: 44909122. Policy #0 lag: (min: 11.0, avg: 14.0, max: 43.0) -[2023-10-15 05:48:43,535][87330] Avg episode reward: [(0, '22.930'), (1, '22.810')] -[2023-10-15 05:48:45,076][88298] Updated weights for policy 0, policy_version 87430 (0.0010) -[2023-10-15 05:48:45,445][88298] Updated weights for policy 0, policy_version 87440 (0.0008) -[2023-10-15 05:48:45,820][88298] Updated weights for policy 0, policy_version 87450 (0.0009) -[2023-10-15 05:48:46,112][88300] Updated weights for policy 1, policy_version 87972 (0.0009) -[2023-10-15 05:48:46,472][88300] Updated weights for policy 1, policy_version 87982 (0.0009) -[2023-10-15 05:48:46,837][88300] Updated weights for policy 1, policy_version 87992 (0.0007) -[2023-10-15 05:48:48,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 179666944. Throughput: 0: 1722.2, 1: 1786.1. Samples: 44920144. Policy #0 lag: (min: 11.0, avg: 14.0, max: 43.0) -[2023-10-15 05:48:48,534][87330] Avg episode reward: [(0, '22.970'), (1, '22.920')] -[2023-10-15 05:48:49,768][88298] Updated weights for policy 0, policy_version 87460 (0.0009) -[2023-10-15 05:48:50,146][88298] Updated weights for policy 0, policy_version 87470 (0.0007) -[2023-10-15 05:48:50,524][88298] Updated weights for policy 0, policy_version 87480 (0.0009) -[2023-10-15 05:48:50,731][88300] Updated weights for policy 1, policy_version 88002 (0.0007) -[2023-10-15 05:48:51,098][88300] Updated weights for policy 1, policy_version 88012 (0.0007) -[2023-10-15 05:48:51,464][88300] Updated weights for policy 1, policy_version 88022 (0.0007) -[2023-10-15 05:48:51,834][88300] Updated weights for policy 1, policy_version 88032 (0.0007) -[2023-10-15 05:48:53,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13884.8). Total num frames: 179732480. Throughput: 0: 1719.7, 1: 1756.2. Samples: 44940324. Policy #0 lag: (min: 11.0, avg: 14.0, max: 43.0) -[2023-10-15 05:48:53,535][87330] Avg episode reward: [(0, '23.110'), (1, '22.970')] -[2023-10-15 05:48:54,327][88298] Updated weights for policy 0, policy_version 87490 (0.0009) -[2023-10-15 05:48:54,695][88298] Updated weights for policy 0, policy_version 87500 (0.0007) -[2023-10-15 05:48:55,060][88298] Updated weights for policy 0, policy_version 87510 (0.0008) -[2023-10-15 05:48:55,436][88298] Updated weights for policy 0, policy_version 87520 (0.0009) -[2023-10-15 05:48:55,790][88300] Updated weights for policy 1, policy_version 88042 (0.0007) -[2023-10-15 05:48:56,160][88300] Updated weights for policy 1, policy_version 88052 (0.0007) -[2023-10-15 05:48:56,530][88300] Updated weights for policy 1, policy_version 88062 (0.0008) -[2023-10-15 05:48:58,534][87330] Fps is (10 sec: 13106.7, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 179798016. Throughput: 0: 1748.6, 1: 1748.0. Samples: 44962010. Policy #0 lag: (min: 11.0, avg: 14.0, max: 43.0) -[2023-10-15 05:48:58,535][87330] Avg episode reward: [(0, '23.190'), (1, '22.920')] -[2023-10-15 05:48:58,547][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000088064_90177536.pth... -[2023-10-15 05:48:58,547][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000087520_89620480.pth... -[2023-10-15 05:48:58,583][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000085920_87982080.pth -[2023-10-15 05:48:58,586][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000086432_88506368.pth -[2023-10-15 05:48:59,291][88298] Updated weights for policy 0, policy_version 87530 (0.0008) -[2023-10-15 05:48:59,664][88298] Updated weights for policy 0, policy_version 87540 (0.0009) -[2023-10-15 05:49:00,033][88298] Updated weights for policy 0, policy_version 87550 (0.0007) -[2023-10-15 05:49:00,402][88300] Updated weights for policy 1, policy_version 88072 (0.0009) -[2023-10-15 05:49:00,778][88300] Updated weights for policy 1, policy_version 88082 (0.0010) -[2023-10-15 05:49:01,148][88300] Updated weights for policy 1, policy_version 88092 (0.0010) -[2023-10-15 05:49:03,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 179863552. Throughput: 0: 1725.8, 1: 1753.2. Samples: 44971686. Policy #0 lag: (min: 11.0, avg: 14.0, max: 43.0) -[2023-10-15 05:49:03,535][87330] Avg episode reward: [(0, '22.940'), (1, '22.850')] -[2023-10-15 05:49:04,038][88298] Updated weights for policy 0, policy_version 87560 (0.0007) -[2023-10-15 05:49:04,411][88298] Updated weights for policy 0, policy_version 87570 (0.0007) -[2023-10-15 05:49:04,785][88298] Updated weights for policy 0, policy_version 87580 (0.0007) -[2023-10-15 05:49:05,127][88300] Updated weights for policy 1, policy_version 88102 (0.0010) -[2023-10-15 05:49:05,487][88300] Updated weights for policy 1, policy_version 88112 (0.0008) -[2023-10-15 05:49:05,856][88300] Updated weights for policy 1, policy_version 88122 (0.0008) -[2023-10-15 05:49:08,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 179929088. Throughput: 0: 1738.7, 1: 1743.5. Samples: 44993012. Policy #0 lag: (min: 11.0, avg: 14.0, max: 43.0) -[2023-10-15 05:49:08,535][87330] Avg episode reward: [(0, '22.830'), (1, '22.710')] -[2023-10-15 05:49:08,582][88298] Updated weights for policy 0, policy_version 87590 (0.0007) -[2023-10-15 05:49:08,956][88298] Updated weights for policy 0, policy_version 87600 (0.0007) -[2023-10-15 05:49:09,325][88298] Updated weights for policy 0, policy_version 87610 (0.0008) -[2023-10-15 05:49:09,747][88300] Updated weights for policy 1, policy_version 88132 (0.0008) -[2023-10-15 05:49:10,113][88300] Updated weights for policy 1, policy_version 88142 (0.0007) -[2023-10-15 05:49:10,476][88300] Updated weights for policy 1, policy_version 88152 (0.0007) -[2023-10-15 05:49:13,273][88298] Updated weights for policy 0, policy_version 87620 (0.0009) -[2023-10-15 05:49:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 179994624. Throughput: 0: 1761.1, 1: 1764.0. Samples: 45014640. Policy #0 lag: (min: 11.0, avg: 14.0, max: 43.0) -[2023-10-15 05:49:13,535][87330] Avg episode reward: [(0, '22.620'), (1, '22.550')] -[2023-10-15 05:49:13,654][88298] Updated weights for policy 0, policy_version 87630 (0.0008) -[2023-10-15 05:49:14,022][88298] Updated weights for policy 0, policy_version 87640 (0.0007) -[2023-10-15 05:49:14,228][88300] Updated weights for policy 1, policy_version 88162 (0.0010) -[2023-10-15 05:49:14,598][88300] Updated weights for policy 1, policy_version 88172 (0.0010) -[2023-10-15 05:49:14,956][88300] Updated weights for policy 1, policy_version 88182 (0.0011) -[2023-10-15 05:49:15,326][88300] Updated weights for policy 1, policy_version 88192 (0.0010) -[2023-10-15 05:49:17,879][88298] Updated weights for policy 0, policy_version 87650 (0.0007) -[2023-10-15 05:49:18,253][88298] Updated weights for policy 0, policy_version 87660 (0.0008) -[2023-10-15 05:49:18,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 180060160. Throughput: 0: 1728.2, 1: 1739.6. Samples: 45024136. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-15 05:49:18,534][87330] Avg episode reward: [(0, '22.570'), (1, '22.540')] -[2023-10-15 05:49:18,627][88298] Updated weights for policy 0, policy_version 87670 (0.0009) -[2023-10-15 05:49:19,006][88298] Updated weights for policy 0, policy_version 87680 (0.0009) -[2023-10-15 05:49:19,264][88300] Updated weights for policy 1, policy_version 88202 (0.0010) -[2023-10-15 05:49:19,623][88300] Updated weights for policy 1, policy_version 88212 (0.0009) -[2023-10-15 05:49:20,003][88300] Updated weights for policy 1, policy_version 88222 (0.0008) -[2023-10-15 05:49:23,083][88298] Updated weights for policy 0, policy_version 87690 (0.0010) -[2023-10-15 05:49:23,452][88298] Updated weights for policy 0, policy_version 87700 (0.0009) -[2023-10-15 05:49:23,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 180125696. Throughput: 0: 1755.7, 1: 1747.1. Samples: 45045714. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-15 05:49:23,534][87330] Avg episode reward: [(0, '22.380'), (1, '22.530')] -[2023-10-15 05:49:23,821][88298] Updated weights for policy 0, policy_version 87710 (0.0007) -[2023-10-15 05:49:23,848][88300] Updated weights for policy 1, policy_version 88232 (0.0009) -[2023-10-15 05:49:24,221][88300] Updated weights for policy 1, policy_version 88242 (0.0007) -[2023-10-15 05:49:24,585][88300] Updated weights for policy 1, policy_version 88252 (0.0009) -[2023-10-15 05:49:27,633][88298] Updated weights for policy 0, policy_version 87720 (0.0008) -[2023-10-15 05:49:28,010][88298] Updated weights for policy 0, policy_version 87730 (0.0010) -[2023-10-15 05:49:28,377][88298] Updated weights for policy 0, policy_version 87740 (0.0007) -[2023-10-15 05:49:28,395][88300] Updated weights for policy 1, policy_version 88262 (0.0008) -[2023-10-15 05:49:28,534][87330] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13995.8). Total num frames: 180224000. Throughput: 0: 1741.0, 1: 1764.9. Samples: 45066888. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-15 05:49:28,534][87330] Avg episode reward: [(0, '22.320'), (1, '22.510')] -[2023-10-15 05:49:28,765][88300] Updated weights for policy 1, policy_version 88272 (0.0009) -[2023-10-15 05:49:29,139][88300] Updated weights for policy 1, policy_version 88282 (0.0010) -[2023-10-15 05:49:32,262][88298] Updated weights for policy 0, policy_version 87750 (0.0007) -[2023-10-15 05:49:32,631][88298] Updated weights for policy 0, policy_version 87760 (0.0008) -[2023-10-15 05:49:32,983][88300] Updated weights for policy 1, policy_version 88292 (0.0007) -[2023-10-15 05:49:33,004][88298] Updated weights for policy 0, policy_version 87770 (0.0009) -[2023-10-15 05:49:33,349][88300] Updated weights for policy 1, policy_version 88302 (0.0009) -[2023-10-15 05:49:33,534][87330] Fps is (10 sec: 16383.6, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 180289536. Throughput: 0: 1745.2, 1: 1736.7. Samples: 45076830. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-15 05:49:33,535][87330] Avg episode reward: [(0, '22.400'), (1, '22.530')] -[2023-10-15 05:49:33,714][88300] Updated weights for policy 1, policy_version 88312 (0.0010) -[2023-10-15 05:49:36,805][88298] Updated weights for policy 0, policy_version 87780 (0.0009) -[2023-10-15 05:49:37,173][88298] Updated weights for policy 0, policy_version 87790 (0.0009) -[2023-10-15 05:49:37,540][88298] Updated weights for policy 0, policy_version 87800 (0.0008) -[2023-10-15 05:49:37,648][88300] Updated weights for policy 1, policy_version 88322 (0.0008) -[2023-10-15 05:49:38,012][88300] Updated weights for policy 1, policy_version 88332 (0.0008) -[2023-10-15 05:49:38,382][88300] Updated weights for policy 1, policy_version 88342 (0.0007) -[2023-10-15 05:49:38,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13995.8). Total num frames: 180355072. Throughput: 0: 1748.2, 1: 1760.1. Samples: 45098198. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-15 05:49:38,534][87330] Avg episode reward: [(0, '22.500'), (1, '22.840')] -[2023-10-15 05:49:38,741][88300] Updated weights for policy 1, policy_version 88352 (0.0007) -[2023-10-15 05:49:41,530][88298] Updated weights for policy 0, policy_version 87810 (0.0009) -[2023-10-15 05:49:41,907][88298] Updated weights for policy 0, policy_version 87820 (0.0009) -[2023-10-15 05:49:42,284][88298] Updated weights for policy 0, policy_version 87830 (0.0010) -[2023-10-15 05:49:42,546][88300] Updated weights for policy 1, policy_version 88362 (0.0008) -[2023-10-15 05:49:42,653][88298] Updated weights for policy 0, policy_version 87840 (0.0008) -[2023-10-15 05:49:42,913][88300] Updated weights for policy 1, policy_version 88372 (0.0007) -[2023-10-15 05:49:43,284][88300] Updated weights for policy 1, policy_version 88382 (0.0008) -[2023-10-15 05:49:43,534][87330] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 180453376. Throughput: 0: 1717.7, 1: 1735.2. Samples: 45117388. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-15 05:49:43,534][87330] Avg episode reward: [(0, '22.830'), (1, '22.810')] -[2023-10-15 05:49:46,563][88298] Updated weights for policy 0, policy_version 87850 (0.0011) -[2023-10-15 05:49:46,935][88298] Updated weights for policy 0, policy_version 87860 (0.0010) -[2023-10-15 05:49:47,307][88298] Updated weights for policy 0, policy_version 87870 (0.0008) -[2023-10-15 05:49:47,427][88300] Updated weights for policy 1, policy_version 88392 (0.0008) -[2023-10-15 05:49:47,804][88300] Updated weights for policy 1, policy_version 88402 (0.0010) -[2023-10-15 05:49:48,167][88300] Updated weights for policy 1, policy_version 88412 (0.0008) -[2023-10-15 05:49:48,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 180518912. Throughput: 0: 1747.5, 1: 1754.9. Samples: 45129294. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-15 05:49:48,534][87330] Avg episode reward: [(0, '22.910'), (1, '23.020')] -[2023-10-15 05:49:51,297][88298] Updated weights for policy 0, policy_version 87880 (0.0009) -[2023-10-15 05:49:51,674][88298] Updated weights for policy 0, policy_version 87890 (0.0010) -[2023-10-15 05:49:52,046][88298] Updated weights for policy 0, policy_version 87900 (0.0008) -[2023-10-15 05:49:52,092][88300] Updated weights for policy 1, policy_version 88422 (0.0009) -[2023-10-15 05:49:52,457][88300] Updated weights for policy 1, policy_version 88432 (0.0010) -[2023-10-15 05:49:52,825][88300] Updated weights for policy 1, policy_version 88442 (0.0008) -[2023-10-15 05:49:53,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 180584448. Throughput: 0: 1724.3, 1: 1745.2. Samples: 45149140. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-15 05:49:53,534][87330] Avg episode reward: [(0, '23.130'), (1, '22.860')] -[2023-10-15 05:49:55,910][88298] Updated weights for policy 0, policy_version 87910 (0.0008) -[2023-10-15 05:49:56,284][88298] Updated weights for policy 0, policy_version 87920 (0.0009) -[2023-10-15 05:49:56,650][88298] Updated weights for policy 0, policy_version 87930 (0.0008) -[2023-10-15 05:49:56,862][88300] Updated weights for policy 1, policy_version 88452 (0.0010) -[2023-10-15 05:49:57,227][88300] Updated weights for policy 1, policy_version 88462 (0.0007) -[2023-10-15 05:49:57,594][88300] Updated weights for policy 1, policy_version 88472 (0.0009) -[2023-10-15 05:49:58,534][87330] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 180649984. Throughput: 0: 1713.9, 1: 1716.1. Samples: 45168990. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-15 05:49:58,535][87330] Avg episode reward: [(0, '23.170'), (1, '22.900')] -[2023-10-15 05:50:00,506][88298] Updated weights for policy 0, policy_version 87940 (0.0008) -[2023-10-15 05:50:00,882][88298] Updated weights for policy 0, policy_version 87950 (0.0010) -[2023-10-15 05:50:01,245][88298] Updated weights for policy 0, policy_version 87960 (0.0010) -[2023-10-15 05:50:01,250][88300] Updated weights for policy 1, policy_version 88482 (0.0009) -[2023-10-15 05:50:01,611][88300] Updated weights for policy 1, policy_version 88492 (0.0008) -[2023-10-15 05:50:01,971][88300] Updated weights for policy 1, policy_version 88502 (0.0009) -[2023-10-15 05:50:02,340][88300] Updated weights for policy 1, policy_version 88512 (0.0009) -[2023-10-15 05:50:03,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 180715520. Throughput: 0: 1735.6, 1: 1752.0. Samples: 45181080. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-15 05:50:03,534][87330] Avg episode reward: [(0, '23.060'), (1, '22.700')] -[2023-10-15 05:50:05,247][88298] Updated weights for policy 0, policy_version 87970 (0.0009) -[2023-10-15 05:50:05,625][88298] Updated weights for policy 0, policy_version 87980 (0.0011) -[2023-10-15 05:50:06,000][88298] Updated weights for policy 0, policy_version 87990 (0.0011) -[2023-10-15 05:50:06,360][88300] Updated weights for policy 1, policy_version 88522 (0.0008) -[2023-10-15 05:50:06,371][88298] Updated weights for policy 0, policy_version 88000 (0.0008) -[2023-10-15 05:50:06,729][88300] Updated weights for policy 1, policy_version 88532 (0.0009) -[2023-10-15 05:50:07,103][88300] Updated weights for policy 1, policy_version 88542 (0.0009) -[2023-10-15 05:50:08,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 180781056. Throughput: 0: 1715.0, 1: 1719.7. Samples: 45200278. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-15 05:50:08,534][87330] Avg episode reward: [(0, '23.060'), (1, '22.730')] -[2023-10-15 05:50:10,158][88298] Updated weights for policy 0, policy_version 88010 (0.0008) -[2023-10-15 05:50:10,536][88298] Updated weights for policy 0, policy_version 88020 (0.0007) -[2023-10-15 05:50:10,867][88300] Updated weights for policy 1, policy_version 88552 (0.0007) -[2023-10-15 05:50:10,893][88298] Updated weights for policy 0, policy_version 88030 (0.0008) -[2023-10-15 05:50:11,227][88300] Updated weights for policy 1, policy_version 88562 (0.0008) -[2023-10-15 05:50:11,597][88300] Updated weights for policy 1, policy_version 88572 (0.0010) -[2023-10-15 05:50:13,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 180846592. Throughput: 0: 1733.9, 1: 1714.8. Samples: 45222080. Policy #0 lag: (min: 15.0, avg: 15.2, max: 24.0) -[2023-10-15 05:50:13,535][87330] Avg episode reward: [(0, '23.060'), (1, '22.740')] -[2023-10-15 05:50:14,730][88298] Updated weights for policy 0, policy_version 88040 (0.0009) -[2023-10-15 05:50:15,097][88298] Updated weights for policy 0, policy_version 88050 (0.0010) -[2023-10-15 05:50:15,465][88298] Updated weights for policy 0, policy_version 88060 (0.0009) -[2023-10-15 05:50:15,493][88300] Updated weights for policy 1, policy_version 88582 (0.0008) -[2023-10-15 05:50:15,858][88300] Updated weights for policy 1, policy_version 88592 (0.0007) -[2023-10-15 05:50:16,228][88300] Updated weights for policy 1, policy_version 88602 (0.0010) -[2023-10-15 05:50:18,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 180912128. Throughput: 0: 1720.7, 1: 1726.0. Samples: 45231932. Policy #0 lag: (min: 15.0, avg: 15.2, max: 24.0) -[2023-10-15 05:50:18,534][87330] Avg episode reward: [(0, '22.930'), (1, '22.540')] -[2023-10-15 05:50:19,310][88298] Updated weights for policy 0, policy_version 88070 (0.0010) -[2023-10-15 05:50:19,679][88298] Updated weights for policy 0, policy_version 88080 (0.0011) -[2023-10-15 05:50:20,051][88298] Updated weights for policy 0, policy_version 88090 (0.0007) -[2023-10-15 05:50:20,187][88300] Updated weights for policy 1, policy_version 88612 (0.0009) -[2023-10-15 05:50:20,562][88300] Updated weights for policy 1, policy_version 88622 (0.0008) -[2023-10-15 05:50:20,936][88300] Updated weights for policy 1, policy_version 88632 (0.0007) -[2023-10-15 05:50:23,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 180977664. Throughput: 0: 1729.5, 1: 1719.3. Samples: 45253398. Policy #0 lag: (min: 15.0, avg: 15.2, max: 24.0) -[2023-10-15 05:50:23,535][87330] Avg episode reward: [(0, '22.910'), (1, '22.640')] -[2023-10-15 05:50:23,904][88298] Updated weights for policy 0, policy_version 88100 (0.0008) -[2023-10-15 05:50:24,274][88298] Updated weights for policy 0, policy_version 88110 (0.0010) -[2023-10-15 05:50:24,650][88298] Updated weights for policy 0, policy_version 88120 (0.0009) -[2023-10-15 05:50:24,713][88300] Updated weights for policy 1, policy_version 88642 (0.0009) -[2023-10-15 05:50:25,071][88300] Updated weights for policy 1, policy_version 88652 (0.0008) -[2023-10-15 05:50:25,440][88300] Updated weights for policy 1, policy_version 88662 (0.0007) -[2023-10-15 05:50:25,799][88300] Updated weights for policy 1, policy_version 88672 (0.0007) -[2023-10-15 05:50:28,518][88298] Updated weights for policy 0, policy_version 88130 (0.0008) -[2023-10-15 05:50:28,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 181043200. Throughput: 0: 1756.0, 1: 1750.8. Samples: 45275196. Policy #0 lag: (min: 15.0, avg: 15.2, max: 24.0) -[2023-10-15 05:50:28,534][87330] Avg episode reward: [(0, '22.920'), (1, '22.640')] -[2023-10-15 05:50:28,887][88298] Updated weights for policy 0, policy_version 88140 (0.0007) -[2023-10-15 05:50:29,256][88298] Updated weights for policy 0, policy_version 88150 (0.0009) -[2023-10-15 05:50:29,620][88298] Updated weights for policy 0, policy_version 88160 (0.0008) -[2023-10-15 05:50:29,703][88300] Updated weights for policy 1, policy_version 88682 (0.0009) -[2023-10-15 05:50:30,081][88300] Updated weights for policy 1, policy_version 88692 (0.0009) -[2023-10-15 05:50:30,451][88300] Updated weights for policy 1, policy_version 88702 (0.0010) -[2023-10-15 05:50:33,534][87330] Fps is (10 sec: 13107.7, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 181108736. Throughput: 0: 1725.6, 1: 1727.9. Samples: 45284700. Policy #0 lag: (min: 15.0, avg: 15.2, max: 24.0) -[2023-10-15 05:50:33,534][87330] Avg episode reward: [(0, '23.020'), (1, '22.800')] -[2023-10-15 05:50:33,688][88298] Updated weights for policy 0, policy_version 88170 (0.0009) -[2023-10-15 05:50:34,061][88298] Updated weights for policy 0, policy_version 88180 (0.0011) -[2023-10-15 05:50:34,430][88298] Updated weights for policy 0, policy_version 88190 (0.0007) -[2023-10-15 05:50:34,448][88300] Updated weights for policy 1, policy_version 88712 (0.0007) -[2023-10-15 05:50:34,816][88300] Updated weights for policy 1, policy_version 88722 (0.0009) -[2023-10-15 05:50:35,181][88300] Updated weights for policy 1, policy_version 88732 (0.0008) -[2023-10-15 05:50:38,526][88298] Updated weights for policy 0, policy_version 88200 (0.0009) -[2023-10-15 05:50:38,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 181174272. Throughput: 0: 1747.7, 1: 1744.2. Samples: 45306276. Policy #0 lag: (min: 15.0, avg: 15.2, max: 24.0) -[2023-10-15 05:50:38,534][87330] Avg episode reward: [(0, '22.930'), (1, '22.750')] -[2023-10-15 05:50:38,883][88298] Updated weights for policy 0, policy_version 88210 (0.0010) -[2023-10-15 05:50:39,074][88300] Updated weights for policy 1, policy_version 88742 (0.0009) -[2023-10-15 05:50:39,246][88298] Updated weights for policy 0, policy_version 88220 (0.0009) -[2023-10-15 05:50:39,468][88300] Updated weights for policy 1, policy_version 88752 (0.0007) -[2023-10-15 05:50:39,832][88300] Updated weights for policy 1, policy_version 88762 (0.0008) -[2023-10-15 05:50:43,316][88298] Updated weights for policy 0, policy_version 88230 (0.0009) -[2023-10-15 05:50:43,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13884.7). Total num frames: 181239808. Throughput: 0: 1750.3, 1: 1772.0. Samples: 45327496. Policy #0 lag: (min: 15.0, avg: 15.2, max: 24.0) -[2023-10-15 05:50:43,535][87330] Avg episode reward: [(0, '22.890'), (1, '22.750')] -[2023-10-15 05:50:43,636][88300] Updated weights for policy 1, policy_version 88772 (0.0008) -[2023-10-15 05:50:43,690][88298] Updated weights for policy 0, policy_version 88240 (0.0009) -[2023-10-15 05:50:43,997][88300] Updated weights for policy 1, policy_version 88782 (0.0007) -[2023-10-15 05:50:44,064][88298] Updated weights for policy 0, policy_version 88250 (0.0007) -[2023-10-15 05:50:44,361][88300] Updated weights for policy 1, policy_version 88792 (0.0011) -[2023-10-15 05:50:47,929][88298] Updated weights for policy 0, policy_version 88260 (0.0009) -[2023-10-15 05:50:48,285][88300] Updated weights for policy 1, policy_version 88802 (0.0010) -[2023-10-15 05:50:48,298][88298] Updated weights for policy 0, policy_version 88270 (0.0009) -[2023-10-15 05:50:48,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13884.8). Total num frames: 181305344. Throughput: 0: 1728.2, 1: 1733.8. Samples: 45336868. Policy #0 lag: (min: 15.0, avg: 15.2, max: 24.0) -[2023-10-15 05:50:48,534][87330] Avg episode reward: [(0, '22.940'), (1, '22.910')] -[2023-10-15 05:50:48,656][88300] Updated weights for policy 1, policy_version 88812 (0.0008) -[2023-10-15 05:50:48,667][88298] Updated weights for policy 0, policy_version 88280 (0.0011) -[2023-10-15 05:50:49,026][88300] Updated weights for policy 1, policy_version 88822 (0.0009) -[2023-10-15 05:50:49,381][88300] Updated weights for policy 1, policy_version 88832 (0.0009) -[2023-10-15 05:50:52,617][88298] Updated weights for policy 0, policy_version 88290 (0.0009) -[2023-10-15 05:50:52,984][88298] Updated weights for policy 0, policy_version 88300 (0.0008) -[2023-10-15 05:50:53,357][88298] Updated weights for policy 0, policy_version 88310 (0.0007) -[2023-10-15 05:50:53,391][88300] Updated weights for policy 1, policy_version 88842 (0.0009) -[2023-10-15 05:50:53,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13884.8). Total num frames: 181370880. Throughput: 0: 1748.4, 1: 1761.1. Samples: 45358202. Policy #0 lag: (min: 15.0, avg: 15.2, max: 24.0) -[2023-10-15 05:50:53,534][87330] Avg episode reward: [(0, '22.940'), (1, '22.910')] -[2023-10-15 05:50:53,726][88298] Updated weights for policy 0, policy_version 88320 (0.0007) -[2023-10-15 05:50:53,747][88300] Updated weights for policy 1, policy_version 88852 (0.0009) -[2023-10-15 05:50:54,108][88300] Updated weights for policy 1, policy_version 88862 (0.0008) -[2023-10-15 05:50:57,573][88298] Updated weights for policy 0, policy_version 88330 (0.0010) -[2023-10-15 05:50:57,935][88298] Updated weights for policy 0, policy_version 88340 (0.0007) -[2023-10-15 05:50:58,036][88300] Updated weights for policy 1, policy_version 88872 (0.0008) -[2023-10-15 05:50:58,310][88298] Updated weights for policy 0, policy_version 88350 (0.0008) -[2023-10-15 05:50:58,396][88300] Updated weights for policy 1, policy_version 88882 (0.0008) -[2023-10-15 05:50:58,534][87330] Fps is (10 sec: 16383.4, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 181469184. Throughput: 0: 1729.5, 1: 1742.0. Samples: 45378296. Policy #0 lag: (min: 15.0, avg: 15.2, max: 24.0) -[2023-10-15 05:50:58,535][87330] Avg episode reward: [(0, '22.900'), (1, '22.940')] -[2023-10-15 05:50:58,546][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000088352_90472448.pth... -[2023-10-15 05:50:58,575][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000086720_88801280.pth -[2023-10-15 05:50:58,762][88300] Updated weights for policy 1, policy_version 88892 (0.0007) -[2023-10-15 05:50:58,898][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000088896_91029504.pth... -[2023-10-15 05:50:58,931][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000087264_89358336.pth -[2023-10-15 05:51:02,127][88298] Updated weights for policy 0, policy_version 88360 (0.0007) -[2023-10-15 05:51:02,510][88298] Updated weights for policy 0, policy_version 88370 (0.0007) -[2023-10-15 05:51:02,639][88300] Updated weights for policy 1, policy_version 88902 (0.0007) -[2023-10-15 05:51:02,872][88298] Updated weights for policy 0, policy_version 88380 (0.0007) -[2023-10-15 05:51:03,005][88300] Updated weights for policy 1, policy_version 88912 (0.0007) -[2023-10-15 05:51:03,369][88300] Updated weights for policy 1, policy_version 88922 (0.0007) -[2023-10-15 05:51:03,534][87330] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 181534720. Throughput: 0: 1743.2, 1: 1745.0. Samples: 45388900. Policy #0 lag: (min: 15.0, avg: 15.2, max: 24.0) -[2023-10-15 05:51:03,534][87330] Avg episode reward: [(0, '22.710'), (1, '22.930')] -[2023-10-15 05:51:06,918][88298] Updated weights for policy 0, policy_version 88390 (0.0009) -[2023-10-15 05:51:07,280][88298] Updated weights for policy 0, policy_version 88400 (0.0007) -[2023-10-15 05:51:07,329][88300] Updated weights for policy 1, policy_version 88932 (0.0008) -[2023-10-15 05:51:07,653][88298] Updated weights for policy 0, policy_version 88410 (0.0007) -[2023-10-15 05:51:07,690][88300] Updated weights for policy 1, policy_version 88942 (0.0010) -[2023-10-15 05:51:08,061][88300] Updated weights for policy 1, policy_version 88952 (0.0008) -[2023-10-15 05:51:08,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 181633024. Throughput: 0: 1732.8, 1: 1752.6. Samples: 45410240. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:51:08,535][87330] Avg episode reward: [(0, '22.760'), (1, '23.000')] -[2023-10-15 05:51:11,665][88298] Updated weights for policy 0, policy_version 88420 (0.0007) -[2023-10-15 05:51:11,934][88300] Updated weights for policy 1, policy_version 88962 (0.0009) -[2023-10-15 05:51:12,033][88298] Updated weights for policy 0, policy_version 88430 (0.0008) -[2023-10-15 05:51:12,303][88300] Updated weights for policy 1, policy_version 88972 (0.0009) -[2023-10-15 05:51:12,394][88298] Updated weights for policy 0, policy_version 88440 (0.0009) -[2023-10-15 05:51:12,660][88300] Updated weights for policy 1, policy_version 88982 (0.0008) -[2023-10-15 05:51:13,027][88300] Updated weights for policy 1, policy_version 88992 (0.0009) -[2023-10-15 05:51:13,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 181698560. Throughput: 0: 1704.0, 1: 1717.6. Samples: 45429166. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:51:13,534][87330] Avg episode reward: [(0, '22.740'), (1, '22.980')] -[2023-10-15 05:51:16,265][88298] Updated weights for policy 0, policy_version 88450 (0.0008) -[2023-10-15 05:51:16,632][88298] Updated weights for policy 0, policy_version 88460 (0.0007) -[2023-10-15 05:51:17,003][88298] Updated weights for policy 0, policy_version 88470 (0.0008) -[2023-10-15 05:51:17,094][88300] Updated weights for policy 1, policy_version 89002 (0.0007) -[2023-10-15 05:51:17,370][88298] Updated weights for policy 0, policy_version 88480 (0.0009) -[2023-10-15 05:51:17,460][88300] Updated weights for policy 1, policy_version 89012 (0.0009) -[2023-10-15 05:51:17,833][88300] Updated weights for policy 1, policy_version 89022 (0.0008) -[2023-10-15 05:51:18,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 181764096. Throughput: 0: 1735.7, 1: 1743.8. Samples: 45441280. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:51:18,535][87330] Avg episode reward: [(0, '22.690'), (1, '22.970')] -[2023-10-15 05:51:21,237][88298] Updated weights for policy 0, policy_version 88490 (0.0009) -[2023-10-15 05:51:21,610][88298] Updated weights for policy 0, policy_version 88500 (0.0008) -[2023-10-15 05:51:21,739][88300] Updated weights for policy 1, policy_version 89032 (0.0008) -[2023-10-15 05:51:21,980][88298] Updated weights for policy 0, policy_version 88510 (0.0007) -[2023-10-15 05:51:22,106][88300] Updated weights for policy 1, policy_version 89042 (0.0009) -[2023-10-15 05:51:22,474][88300] Updated weights for policy 1, policy_version 89052 (0.0010) -[2023-10-15 05:51:23,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 181829632. Throughput: 0: 1717.3, 1: 1726.2. Samples: 45461236. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:51:23,535][87330] Avg episode reward: [(0, '22.660'), (1, '22.990')] -[2023-10-15 05:51:25,880][88298] Updated weights for policy 0, policy_version 88520 (0.0009) -[2023-10-15 05:51:26,251][88298] Updated weights for policy 0, policy_version 88530 (0.0008) -[2023-10-15 05:51:26,444][88300] Updated weights for policy 1, policy_version 89062 (0.0009) -[2023-10-15 05:51:26,628][88298] Updated weights for policy 0, policy_version 88540 (0.0008) -[2023-10-15 05:51:26,842][88300] Updated weights for policy 1, policy_version 89072 (0.0011) -[2023-10-15 05:51:27,204][88300] Updated weights for policy 1, policy_version 89082 (0.0011) -[2023-10-15 05:51:28,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 181895168. Throughput: 0: 1717.7, 1: 1707.5. Samples: 45481628. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:51:28,535][87330] Avg episode reward: [(0, '22.600'), (1, '23.000')] -[2023-10-15 05:51:30,512][88298] Updated weights for policy 0, policy_version 88550 (0.0010) -[2023-10-15 05:51:30,887][88298] Updated weights for policy 0, policy_version 88560 (0.0009) -[2023-10-15 05:51:31,219][88300] Updated weights for policy 1, policy_version 89092 (0.0010) -[2023-10-15 05:51:31,253][88298] Updated weights for policy 0, policy_version 88570 (0.0010) -[2023-10-15 05:51:31,592][88300] Updated weights for policy 1, policy_version 89102 (0.0008) -[2023-10-15 05:51:31,963][88300] Updated weights for policy 1, policy_version 89112 (0.0011) -[2023-10-15 05:51:33,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 181960704. Throughput: 0: 1734.6, 1: 1736.5. Samples: 45493068. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:51:33,535][87330] Avg episode reward: [(0, '22.620'), (1, '22.980')] -[2023-10-15 05:51:35,237][88298] Updated weights for policy 0, policy_version 88580 (0.0009) -[2023-10-15 05:51:35,611][88298] Updated weights for policy 0, policy_version 88590 (0.0010) -[2023-10-15 05:51:35,792][88300] Updated weights for policy 1, policy_version 89122 (0.0009) -[2023-10-15 05:51:35,984][88298] Updated weights for policy 0, policy_version 88600 (0.0007) -[2023-10-15 05:51:36,160][88300] Updated weights for policy 1, policy_version 89132 (0.0008) -[2023-10-15 05:51:36,533][88300] Updated weights for policy 1, policy_version 89142 (0.0011) -[2023-10-15 05:51:36,902][88300] Updated weights for policy 1, policy_version 89152 (0.0009) -[2023-10-15 05:51:38,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 182026240. Throughput: 0: 1716.3, 1: 1710.8. Samples: 45512420. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:51:38,535][87330] Avg episode reward: [(0, '22.500'), (1, '22.970')] -[2023-10-15 05:51:39,947][88298] Updated weights for policy 0, policy_version 88610 (0.0007) -[2023-10-15 05:51:40,315][88298] Updated weights for policy 0, policy_version 88620 (0.0008) -[2023-10-15 05:51:40,690][88298] Updated weights for policy 0, policy_version 88630 (0.0007) -[2023-10-15 05:51:40,773][88300] Updated weights for policy 1, policy_version 89162 (0.0007) -[2023-10-15 05:51:41,058][88298] Updated weights for policy 0, policy_version 88640 (0.0007) -[2023-10-15 05:51:41,140][88300] Updated weights for policy 1, policy_version 89172 (0.0007) -[2023-10-15 05:51:41,510][88300] Updated weights for policy 1, policy_version 89182 (0.0008) -[2023-10-15 05:51:43,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 182091776. Throughput: 0: 1725.1, 1: 1730.8. Samples: 45533810. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:51:43,534][87330] Avg episode reward: [(0, '22.520'), (1, '22.820')] -[2023-10-15 05:51:45,072][88298] Updated weights for policy 0, policy_version 88650 (0.0009) -[2023-10-15 05:51:45,361][88300] Updated weights for policy 1, policy_version 89192 (0.0007) -[2023-10-15 05:51:45,446][88298] Updated weights for policy 0, policy_version 88660 (0.0007) -[2023-10-15 05:51:45,733][88300] Updated weights for policy 1, policy_version 89202 (0.0008) -[2023-10-15 05:51:45,813][88298] Updated weights for policy 0, policy_version 88670 (0.0008) -[2023-10-15 05:51:46,098][88300] Updated weights for policy 1, policy_version 89212 (0.0008) -[2023-10-15 05:51:48,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 182157312. Throughput: 0: 1714.3, 1: 1719.2. Samples: 45543410. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:51:48,534][87330] Avg episode reward: [(0, '22.560'), (1, '22.760')] -[2023-10-15 05:51:49,730][88298] Updated weights for policy 0, policy_version 88680 (0.0009) -[2023-10-15 05:51:49,852][88300] Updated weights for policy 1, policy_version 89222 (0.0008) -[2023-10-15 05:51:50,105][88298] Updated weights for policy 0, policy_version 88690 (0.0007) -[2023-10-15 05:51:50,221][88300] Updated weights for policy 1, policy_version 89232 (0.0009) -[2023-10-15 05:51:50,473][88298] Updated weights for policy 0, policy_version 88700 (0.0007) -[2023-10-15 05:51:50,586][88300] Updated weights for policy 1, policy_version 89242 (0.0008) -[2023-10-15 05:51:53,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 182222848. Throughput: 0: 1712.3, 1: 1720.9. Samples: 45564734. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:51:53,534][87330] Avg episode reward: [(0, '22.610'), (1, '22.590')] -[2023-10-15 05:51:54,527][88298] Updated weights for policy 0, policy_version 88710 (0.0007) -[2023-10-15 05:51:54,602][88300] Updated weights for policy 1, policy_version 89252 (0.0008) -[2023-10-15 05:51:54,886][88298] Updated weights for policy 0, policy_version 88720 (0.0009) -[2023-10-15 05:51:54,960][88300] Updated weights for policy 1, policy_version 89262 (0.0007) -[2023-10-15 05:51:55,259][88298] Updated weights for policy 0, policy_version 88730 (0.0009) -[2023-10-15 05:51:55,330][88300] Updated weights for policy 1, policy_version 89272 (0.0009) -[2023-10-15 05:51:58,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 182288384. Throughput: 0: 1741.6, 1: 1749.1. Samples: 45586248. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:51:58,534][87330] Avg episode reward: [(0, '22.560'), (1, '22.370')] -[2023-10-15 05:51:59,132][88298] Updated weights for policy 0, policy_version 88740 (0.0009) -[2023-10-15 05:51:59,252][88300] Updated weights for policy 1, policy_version 89282 (0.0008) -[2023-10-15 05:51:59,505][88298] Updated weights for policy 0, policy_version 88750 (0.0008) -[2023-10-15 05:51:59,624][88300] Updated weights for policy 1, policy_version 89292 (0.0008) -[2023-10-15 05:51:59,872][88298] Updated weights for policy 0, policy_version 88760 (0.0007) -[2023-10-15 05:51:59,994][88300] Updated weights for policy 1, policy_version 89302 (0.0007) -[2023-10-15 05:52:00,363][88300] Updated weights for policy 1, policy_version 89312 (0.0007) -[2023-10-15 05:52:03,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 182353920. Throughput: 0: 1709.4, 1: 1724.5. Samples: 45595806. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:52:03,535][87330] Avg episode reward: [(0, '22.540'), (1, '22.370')] -[2023-10-15 05:52:03,741][88298] Updated weights for policy 0, policy_version 88770 (0.0008) -[2023-10-15 05:52:04,111][88298] Updated weights for policy 0, policy_version 88780 (0.0008) -[2023-10-15 05:52:04,139][88300] Updated weights for policy 1, policy_version 89322 (0.0007) -[2023-10-15 05:52:04,482][88298] Updated weights for policy 0, policy_version 88790 (0.0007) -[2023-10-15 05:52:04,494][88300] Updated weights for policy 1, policy_version 89332 (0.0009) -[2023-10-15 05:52:04,847][88298] Updated weights for policy 0, policy_version 88800 (0.0007) -[2023-10-15 05:52:04,864][88300] Updated weights for policy 1, policy_version 89342 (0.0008) -[2023-10-15 05:52:08,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13884.7). Total num frames: 182419456. Throughput: 0: 1725.1, 1: 1747.0. Samples: 45617482. Policy #0 lag: (min: 12.0, avg: 19.5, max: 44.0) -[2023-10-15 05:52:08,535][87330] Avg episode reward: [(0, '22.510'), (1, '22.370')] -[2023-10-15 05:52:08,684][88300] Updated weights for policy 1, policy_version 89352 (0.0008) -[2023-10-15 05:52:08,889][88298] Updated weights for policy 0, policy_version 88810 (0.0009) -[2023-10-15 05:52:09,049][88300] Updated weights for policy 1, policy_version 89362 (0.0008) -[2023-10-15 05:52:09,255][88298] Updated weights for policy 0, policy_version 88820 (0.0009) -[2023-10-15 05:52:09,420][88300] Updated weights for policy 1, policy_version 89372 (0.0007) -[2023-10-15 05:52:09,629][88298] Updated weights for policy 0, policy_version 88830 (0.0007) -[2023-10-15 05:52:13,522][88300] Updated weights for policy 1, policy_version 89382 (0.0009) -[2023-10-15 05:52:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13884.8). Total num frames: 182484992. Throughput: 0: 1731.0, 1: 1765.0. Samples: 45638948. Policy #0 lag: (min: 12.0, avg: 19.5, max: 44.0) -[2023-10-15 05:52:13,534][87330] Avg episode reward: [(0, '22.520'), (1, '22.580')] -[2023-10-15 05:52:13,750][88298] Updated weights for policy 0, policy_version 88840 (0.0008) -[2023-10-15 05:52:13,910][88300] Updated weights for policy 1, policy_version 89392 (0.0008) -[2023-10-15 05:52:14,119][88298] Updated weights for policy 0, policy_version 88850 (0.0008) -[2023-10-15 05:52:14,280][88300] Updated weights for policy 1, policy_version 89402 (0.0009) -[2023-10-15 05:52:14,477][88298] Updated weights for policy 0, policy_version 88860 (0.0009) -[2023-10-15 05:52:18,123][88300] Updated weights for policy 1, policy_version 89412 (0.0009) -[2023-10-15 05:52:18,438][88298] Updated weights for policy 0, policy_version 88870 (0.0008) -[2023-10-15 05:52:18,480][88300] Updated weights for policy 1, policy_version 89422 (0.0009) -[2023-10-15 05:52:18,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 182550528. Throughput: 0: 1709.5, 1: 1736.4. Samples: 45648132. Policy #0 lag: (min: 12.0, avg: 19.5, max: 44.0) -[2023-10-15 05:52:18,534][87330] Avg episode reward: [(0, '22.610'), (1, '22.610')] -[2023-10-15 05:52:18,805][88298] Updated weights for policy 0, policy_version 88880 (0.0007) -[2023-10-15 05:52:18,843][88300] Updated weights for policy 1, policy_version 89432 (0.0008) -[2023-10-15 05:52:19,175][88298] Updated weights for policy 0, policy_version 88890 (0.0008) -[2023-10-15 05:52:22,829][88300] Updated weights for policy 1, policy_version 89442 (0.0009) -[2023-10-15 05:52:23,132][88298] Updated weights for policy 0, policy_version 88900 (0.0010) -[2023-10-15 05:52:23,198][88300] Updated weights for policy 1, policy_version 89452 (0.0008) -[2023-10-15 05:52:23,502][88298] Updated weights for policy 0, policy_version 88910 (0.0008) -[2023-10-15 05:52:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 182616064. Throughput: 0: 1722.2, 1: 1761.7. Samples: 45669196. Policy #0 lag: (min: 12.0, avg: 19.5, max: 44.0) -[2023-10-15 05:52:23,534][87330] Avg episode reward: [(0, '22.610'), (1, '22.840')] -[2023-10-15 05:52:23,572][88300] Updated weights for policy 1, policy_version 89462 (0.0008) -[2023-10-15 05:52:23,876][88298] Updated weights for policy 0, policy_version 88920 (0.0008) -[2023-10-15 05:52:23,931][88300] Updated weights for policy 1, policy_version 89472 (0.0007) -[2023-10-15 05:52:27,667][88300] Updated weights for policy 1, policy_version 89482 (0.0008) -[2023-10-15 05:52:27,765][88298] Updated weights for policy 0, policy_version 88930 (0.0009) -[2023-10-15 05:52:28,034][88300] Updated weights for policy 1, policy_version 89492 (0.0009) -[2023-10-15 05:52:28,136][88298] Updated weights for policy 0, policy_version 88940 (0.0009) -[2023-10-15 05:52:28,395][88300] Updated weights for policy 1, policy_version 89502 (0.0009) -[2023-10-15 05:52:28,512][88298] Updated weights for policy 0, policy_version 88950 (0.0007) -[2023-10-15 05:52:28,534][87330] Fps is (10 sec: 16383.6, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 182714368. Throughput: 0: 1721.6, 1: 1744.1. Samples: 45689768. Policy #0 lag: (min: 12.0, avg: 19.5, max: 44.0) -[2023-10-15 05:52:28,535][87330] Avg episode reward: [(0, '22.630'), (1, '22.850')] -[2023-10-15 05:52:28,885][88298] Updated weights for policy 0, policy_version 88960 (0.0011) -[2023-10-15 05:52:32,238][88300] Updated weights for policy 1, policy_version 89512 (0.0011) -[2023-10-15 05:52:32,602][88300] Updated weights for policy 1, policy_version 89522 (0.0008) -[2023-10-15 05:52:32,688][88298] Updated weights for policy 0, policy_version 88970 (0.0007) -[2023-10-15 05:52:32,974][88300] Updated weights for policy 1, policy_version 89532 (0.0008) -[2023-10-15 05:52:33,059][88298] Updated weights for policy 0, policy_version 88980 (0.0008) -[2023-10-15 05:52:33,431][88298] Updated weights for policy 0, policy_version 88990 (0.0007) -[2023-10-15 05:52:33,534][87330] Fps is (10 sec: 19660.7, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 182812672. Throughput: 0: 1719.6, 1: 1764.8. Samples: 45700204. Policy #0 lag: (min: 12.0, avg: 19.5, max: 44.0) -[2023-10-15 05:52:33,535][87330] Avg episode reward: [(0, '22.580'), (1, '23.060')] -[2023-10-15 05:52:36,926][88300] Updated weights for policy 1, policy_version 89542 (0.0008) -[2023-10-15 05:52:37,287][88300] Updated weights for policy 1, policy_version 89552 (0.0008) -[2023-10-15 05:52:37,319][88298] Updated weights for policy 0, policy_version 89000 (0.0008) -[2023-10-15 05:52:37,645][88300] Updated weights for policy 1, policy_version 89562 (0.0007) -[2023-10-15 05:52:37,696][88298] Updated weights for policy 0, policy_version 89010 (0.0008) -[2023-10-15 05:52:38,068][88298] Updated weights for policy 0, policy_version 89020 (0.0008) -[2023-10-15 05:52:38,534][87330] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 182878208. Throughput: 0: 1726.0, 1: 1749.7. Samples: 45721144. Policy #0 lag: (min: 12.0, avg: 19.5, max: 44.0) -[2023-10-15 05:52:38,534][87330] Avg episode reward: [(0, '22.630'), (1, '23.030')] -[2023-10-15 05:52:41,454][88300] Updated weights for policy 1, policy_version 89572 (0.0007) -[2023-10-15 05:52:41,816][88300] Updated weights for policy 1, policy_version 89582 (0.0007) -[2023-10-15 05:52:42,182][88300] Updated weights for policy 1, policy_version 89592 (0.0008) -[2023-10-15 05:52:42,230][88298] Updated weights for policy 0, policy_version 89030 (0.0009) -[2023-10-15 05:52:42,608][88298] Updated weights for policy 0, policy_version 89040 (0.0007) -[2023-10-15 05:52:42,980][88298] Updated weights for policy 0, policy_version 89050 (0.0008) -[2023-10-15 05:52:43,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 182943744. Throughput: 0: 1704.7, 1: 1737.2. Samples: 45741132. Policy #0 lag: (min: 12.0, avg: 19.5, max: 44.0) -[2023-10-15 05:52:43,535][87330] Avg episode reward: [(0, '22.670'), (1, '22.810')] -[2023-10-15 05:52:46,121][88300] Updated weights for policy 1, policy_version 89602 (0.0008) -[2023-10-15 05:52:46,493][88300] Updated weights for policy 1, policy_version 89612 (0.0010) -[2023-10-15 05:52:46,856][88300] Updated weights for policy 1, policy_version 89622 (0.0008) -[2023-10-15 05:52:46,882][88298] Updated weights for policy 0, policy_version 89060 (0.0009) -[2023-10-15 05:52:47,214][88300] Updated weights for policy 1, policy_version 89632 (0.0007) -[2023-10-15 05:52:47,254][88298] Updated weights for policy 0, policy_version 89070 (0.0008) -[2023-10-15 05:52:47,619][88298] Updated weights for policy 0, policy_version 89080 (0.0007) -[2023-10-15 05:52:48,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 183009280. Throughput: 0: 1725.7, 1: 1761.2. Samples: 45752716. Policy #0 lag: (min: 12.0, avg: 19.5, max: 44.0) -[2023-10-15 05:52:48,534][87330] Avg episode reward: [(0, '22.930'), (1, '22.780')] -[2023-10-15 05:52:51,142][88300] Updated weights for policy 1, policy_version 89642 (0.0008) -[2023-10-15 05:52:51,421][88298] Updated weights for policy 0, policy_version 89090 (0.0008) -[2023-10-15 05:52:51,498][88300] Updated weights for policy 1, policy_version 89652 (0.0008) -[2023-10-15 05:52:51,792][88298] Updated weights for policy 0, policy_version 89100 (0.0007) -[2023-10-15 05:52:51,865][88300] Updated weights for policy 1, policy_version 89662 (0.0008) -[2023-10-15 05:52:52,154][88298] Updated weights for policy 0, policy_version 89110 (0.0009) -[2023-10-15 05:52:52,526][88298] Updated weights for policy 0, policy_version 89120 (0.0010) -[2023-10-15 05:52:53,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 183074816. Throughput: 0: 1721.0, 1: 1725.6. Samples: 45772580. Policy #0 lag: (min: 12.0, avg: 19.5, max: 44.0) -[2023-10-15 05:52:53,535][87330] Avg episode reward: [(0, '22.920'), (1, '22.560')] -[2023-10-15 05:52:55,710][88300] Updated weights for policy 1, policy_version 89672 (0.0009) -[2023-10-15 05:52:56,074][88300] Updated weights for policy 1, policy_version 89682 (0.0007) -[2023-10-15 05:52:56,434][88298] Updated weights for policy 0, policy_version 89130 (0.0009) -[2023-10-15 05:52:56,440][88300] Updated weights for policy 1, policy_version 89692 (0.0009) -[2023-10-15 05:52:56,811][88298] Updated weights for policy 0, policy_version 89140 (0.0007) -[2023-10-15 05:52:57,174][88298] Updated weights for policy 0, policy_version 89150 (0.0007) -[2023-10-15 05:52:58,534][87330] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 183140352. Throughput: 0: 1702.2, 1: 1725.8. Samples: 45793206. Policy #0 lag: (min: 12.0, avg: 19.5, max: 44.0) -[2023-10-15 05:52:58,535][87330] Avg episode reward: [(0, '22.910'), (1, '22.550')] -[2023-10-15 05:52:58,546][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000089152_91291648.pth... -[2023-10-15 05:52:58,546][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000089696_91848704.pth... -[2023-10-15 05:52:58,578][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000087520_89620480.pth -[2023-10-15 05:52:58,582][87905] Saving a milestone ./train_atari/atari_seaquest_APPO/checkpoint_p0/milestones/checkpoint_000089152_91291648.pth -[2023-10-15 05:52:58,583][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000088064_90177536.pth -[2023-10-15 05:52:58,587][88033] Saving a milestone ./train_atari/atari_seaquest_APPO/checkpoint_p1/milestones/checkpoint_000089696_91848704.pth -[2023-10-15 05:53:00,437][88300] Updated weights for policy 1, policy_version 89702 (0.0008) -[2023-10-15 05:53:00,821][88300] Updated weights for policy 1, policy_version 89712 (0.0010) -[2023-10-15 05:53:01,183][88300] Updated weights for policy 1, policy_version 89722 (0.0008) -[2023-10-15 05:53:01,336][88298] Updated weights for policy 0, policy_version 89160 (0.0008) -[2023-10-15 05:53:01,707][88298] Updated weights for policy 0, policy_version 89170 (0.0009) -[2023-10-15 05:53:02,082][88298] Updated weights for policy 0, policy_version 89180 (0.0008) -[2023-10-15 05:53:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 183205888. Throughput: 0: 1734.7, 1: 1729.4. Samples: 45804016. Policy #0 lag: (min: 18.0, avg: 19.0, max: 39.0) -[2023-10-15 05:53:03,535][87330] Avg episode reward: [(0, '23.020'), (1, '22.320')] -[2023-10-15 05:53:04,986][88300] Updated weights for policy 1, policy_version 89732 (0.0009) -[2023-10-15 05:53:05,360][88300] Updated weights for policy 1, policy_version 89742 (0.0007) -[2023-10-15 05:53:05,722][88300] Updated weights for policy 1, policy_version 89752 (0.0008) -[2023-10-15 05:53:05,940][88298] Updated weights for policy 0, policy_version 89190 (0.0008) -[2023-10-15 05:53:06,298][88298] Updated weights for policy 0, policy_version 89200 (0.0011) -[2023-10-15 05:53:06,671][88298] Updated weights for policy 0, policy_version 89210 (0.0011) -[2023-10-15 05:53:08,534][87330] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 183271424. Throughput: 0: 1714.1, 1: 1729.0. Samples: 45824136. Policy #0 lag: (min: 18.0, avg: 19.0, max: 39.0) -[2023-10-15 05:53:08,534][87330] Avg episode reward: [(0, '23.000'), (1, '22.370')] -[2023-10-15 05:53:09,624][88300] Updated weights for policy 1, policy_version 89762 (0.0008) -[2023-10-15 05:53:09,992][88300] Updated weights for policy 1, policy_version 89772 (0.0007) -[2023-10-15 05:53:10,353][88300] Updated weights for policy 1, policy_version 89782 (0.0007) -[2023-10-15 05:53:10,451][88298] Updated weights for policy 0, policy_version 89220 (0.0010) -[2023-10-15 05:53:10,719][88300] Updated weights for policy 1, policy_version 89792 (0.0008) -[2023-10-15 05:53:10,824][88298] Updated weights for policy 0, policy_version 89230 (0.0009) -[2023-10-15 05:53:11,196][88298] Updated weights for policy 0, policy_version 89240 (0.0010) -[2023-10-15 05:53:13,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 183336960. Throughput: 0: 1718.5, 1: 1748.2. Samples: 45845770. Policy #0 lag: (min: 18.0, avg: 19.0, max: 39.0) -[2023-10-15 05:53:13,534][87330] Avg episode reward: [(0, '22.930'), (1, '22.550')] -[2023-10-15 05:53:14,473][88300] Updated weights for policy 1, policy_version 89802 (0.0010) -[2023-10-15 05:53:14,839][88300] Updated weights for policy 1, policy_version 89812 (0.0008) -[2023-10-15 05:53:15,199][88300] Updated weights for policy 1, policy_version 89822 (0.0008) -[2023-10-15 05:53:15,219][88298] Updated weights for policy 0, policy_version 89250 (0.0009) -[2023-10-15 05:53:15,586][88298] Updated weights for policy 0, policy_version 89260 (0.0010) -[2023-10-15 05:53:15,963][88298] Updated weights for policy 0, policy_version 89270 (0.0010) -[2023-10-15 05:53:16,326][88298] Updated weights for policy 0, policy_version 89280 (0.0010) -[2023-10-15 05:53:18,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 183402496. Throughput: 0: 1733.8, 1: 1729.8. Samples: 45856066. Policy #0 lag: (min: 18.0, avg: 19.0, max: 39.0) -[2023-10-15 05:53:18,535][87330] Avg episode reward: [(0, '22.910'), (1, '22.590')] -[2023-10-15 05:53:19,143][88300] Updated weights for policy 1, policy_version 89832 (0.0008) -[2023-10-15 05:53:19,521][88300] Updated weights for policy 1, policy_version 89842 (0.0010) -[2023-10-15 05:53:19,885][88300] Updated weights for policy 1, policy_version 89852 (0.0008) -[2023-10-15 05:53:20,318][88298] Updated weights for policy 0, policy_version 89290 (0.0008) -[2023-10-15 05:53:20,691][88298] Updated weights for policy 0, policy_version 89300 (0.0009) -[2023-10-15 05:53:21,062][88298] Updated weights for policy 0, policy_version 89310 (0.0009) -[2023-10-15 05:53:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 183468032. Throughput: 0: 1714.8, 1: 1741.6. Samples: 45876684. Policy #0 lag: (min: 18.0, avg: 19.0, max: 39.0) -[2023-10-15 05:53:23,534][87330] Avg episode reward: [(0, '22.720'), (1, '22.810')] -[2023-10-15 05:53:23,837][88300] Updated weights for policy 1, policy_version 89862 (0.0008) -[2023-10-15 05:53:24,196][88300] Updated weights for policy 1, policy_version 89872 (0.0008) -[2023-10-15 05:53:24,560][88300] Updated weights for policy 1, policy_version 89882 (0.0010) -[2023-10-15 05:53:24,943][88298] Updated weights for policy 0, policy_version 89320 (0.0008) -[2023-10-15 05:53:25,320][88298] Updated weights for policy 0, policy_version 89330 (0.0007) -[2023-10-15 05:53:25,688][88298] Updated weights for policy 0, policy_version 89340 (0.0009) -[2023-10-15 05:53:28,264][88300] Updated weights for policy 1, policy_version 89892 (0.0008) -[2023-10-15 05:53:28,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 183533568. Throughput: 0: 1734.0, 1: 1755.3. Samples: 45898150. Policy #0 lag: (min: 18.0, avg: 19.0, max: 39.0) -[2023-10-15 05:53:28,534][87330] Avg episode reward: [(0, '22.640'), (1, '22.830')] -[2023-10-15 05:53:28,627][88300] Updated weights for policy 1, policy_version 89902 (0.0007) -[2023-10-15 05:53:28,990][88300] Updated weights for policy 1, policy_version 89912 (0.0007) -[2023-10-15 05:53:29,584][88298] Updated weights for policy 0, policy_version 89350 (0.0010) -[2023-10-15 05:53:29,964][88298] Updated weights for policy 0, policy_version 89360 (0.0010) -[2023-10-15 05:53:30,327][88298] Updated weights for policy 0, policy_version 89370 (0.0011) -[2023-10-15 05:53:32,795][88300] Updated weights for policy 1, policy_version 89922 (0.0010) -[2023-10-15 05:53:33,155][88300] Updated weights for policy 1, policy_version 89932 (0.0009) -[2023-10-15 05:53:33,522][88300] Updated weights for policy 1, policy_version 89942 (0.0009) -[2023-10-15 05:53:33,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 183599104. Throughput: 0: 1712.0, 1: 1736.1. Samples: 45907882. Policy #0 lag: (min: 18.0, avg: 19.0, max: 39.0) -[2023-10-15 05:53:33,534][87330] Avg episode reward: [(0, '22.630'), (1, '22.690')] -[2023-10-15 05:53:33,875][88300] Updated weights for policy 1, policy_version 89952 (0.0009) -[2023-10-15 05:53:34,159][88298] Updated weights for policy 0, policy_version 89380 (0.0009) -[2023-10-15 05:53:34,525][88298] Updated weights for policy 0, policy_version 89390 (0.0007) -[2023-10-15 05:53:34,892][88298] Updated weights for policy 0, policy_version 89400 (0.0007) -[2023-10-15 05:53:37,838][88300] Updated weights for policy 1, policy_version 89962 (0.0009) -[2023-10-15 05:53:38,207][88300] Updated weights for policy 1, policy_version 89972 (0.0009) -[2023-10-15 05:53:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 183664640. Throughput: 0: 1722.7, 1: 1769.4. Samples: 45929722. Policy #0 lag: (min: 18.0, avg: 19.0, max: 39.0) -[2023-10-15 05:53:38,534][87330] Avg episode reward: [(0, '22.720'), (1, '22.850')] -[2023-10-15 05:53:38,577][88300] Updated weights for policy 1, policy_version 89982 (0.0007) -[2023-10-15 05:53:38,795][88298] Updated weights for policy 0, policy_version 89410 (0.0007) -[2023-10-15 05:53:39,166][88298] Updated weights for policy 0, policy_version 89420 (0.0008) -[2023-10-15 05:53:39,525][88298] Updated weights for policy 0, policy_version 89430 (0.0008) -[2023-10-15 05:53:39,904][88298] Updated weights for policy 0, policy_version 89440 (0.0009) -[2023-10-15 05:53:42,503][88300] Updated weights for policy 1, policy_version 89992 (0.0007) -[2023-10-15 05:53:42,869][88300] Updated weights for policy 1, policy_version 90002 (0.0007) -[2023-10-15 05:53:43,234][88300] Updated weights for policy 1, policy_version 90012 (0.0007) -[2023-10-15 05:53:43,534][87330] Fps is (10 sec: 16383.8, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 183762944. Throughput: 0: 1746.1, 1: 1748.5. Samples: 45950460. Policy #0 lag: (min: 18.0, avg: 19.0, max: 39.0) -[2023-10-15 05:53:43,534][87330] Avg episode reward: [(0, '22.790'), (1, '22.820')] -[2023-10-15 05:53:43,783][88298] Updated weights for policy 0, policy_version 89450 (0.0009) -[2023-10-15 05:53:44,142][88298] Updated weights for policy 0, policy_version 89460 (0.0007) -[2023-10-15 05:53:44,510][88298] Updated weights for policy 0, policy_version 89470 (0.0009) -[2023-10-15 05:53:47,252][88300] Updated weights for policy 1, policy_version 90022 (0.0007) -[2023-10-15 05:53:47,641][88300] Updated weights for policy 1, policy_version 90032 (0.0008) -[2023-10-15 05:53:48,012][88300] Updated weights for policy 1, policy_version 90042 (0.0007) -[2023-10-15 05:53:48,526][88298] Updated weights for policy 0, policy_version 89480 (0.0008) -[2023-10-15 05:53:48,534][87330] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 183828480. Throughput: 0: 1718.7, 1: 1771.7. Samples: 45961082. Policy #0 lag: (min: 18.0, avg: 19.0, max: 39.0) -[2023-10-15 05:53:48,534][87330] Avg episode reward: [(0, '22.790'), (1, '22.770')] -[2023-10-15 05:53:48,906][88298] Updated weights for policy 0, policy_version 89490 (0.0008) -[2023-10-15 05:53:49,273][88298] Updated weights for policy 0, policy_version 89500 (0.0008) -[2023-10-15 05:53:51,753][88300] Updated weights for policy 1, policy_version 90052 (0.0009) -[2023-10-15 05:53:52,122][88300] Updated weights for policy 1, policy_version 90062 (0.0009) -[2023-10-15 05:53:52,498][88300] Updated weights for policy 1, policy_version 90072 (0.0007) -[2023-10-15 05:53:53,320][88298] Updated weights for policy 0, policy_version 89510 (0.0008) -[2023-10-15 05:53:53,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 183894016. Throughput: 0: 1739.8, 1: 1762.6. Samples: 45981744. Policy #0 lag: (min: 18.0, avg: 19.0, max: 39.0) -[2023-10-15 05:53:53,535][87330] Avg episode reward: [(0, '22.790'), (1, '22.800')] -[2023-10-15 05:53:53,685][88298] Updated weights for policy 0, policy_version 89520 (0.0008) -[2023-10-15 05:53:54,051][88298] Updated weights for policy 0, policy_version 89530 (0.0009) -[2023-10-15 05:53:56,555][88300] Updated weights for policy 1, policy_version 90082 (0.0007) -[2023-10-15 05:53:56,913][88300] Updated weights for policy 1, policy_version 90092 (0.0010) -[2023-10-15 05:53:57,282][88300] Updated weights for policy 1, policy_version 90102 (0.0007) -[2023-10-15 05:53:57,647][88300] Updated weights for policy 1, policy_version 90112 (0.0007) -[2023-10-15 05:53:57,842][88298] Updated weights for policy 0, policy_version 89540 (0.0008) -[2023-10-15 05:53:58,204][88298] Updated weights for policy 0, policy_version 89550 (0.0009) -[2023-10-15 05:53:58,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 183959552. Throughput: 0: 1740.4, 1: 1744.0. Samples: 46002568. Policy #0 lag: (min: 18.0, avg: 19.0, max: 39.0) -[2023-10-15 05:53:58,535][87330] Avg episode reward: [(0, '22.970'), (1, '22.780')] -[2023-10-15 05:53:58,567][88298] Updated weights for policy 0, policy_version 89560 (0.0008) -[2023-10-15 05:54:01,670][88300] Updated weights for policy 1, policy_version 90122 (0.0008) -[2023-10-15 05:54:02,043][88300] Updated weights for policy 1, policy_version 90132 (0.0008) -[2023-10-15 05:54:02,406][88300] Updated weights for policy 1, policy_version 90142 (0.0007) -[2023-10-15 05:54:02,491][88298] Updated weights for policy 0, policy_version 89570 (0.0010) -[2023-10-15 05:54:02,858][88298] Updated weights for policy 0, policy_version 89580 (0.0008) -[2023-10-15 05:54:03,231][88298] Updated weights for policy 0, policy_version 89590 (0.0007) -[2023-10-15 05:54:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 184025088. Throughput: 0: 1727.5, 1: 1770.8. Samples: 46013490. Policy #0 lag: (min: 25.0, avg: 42.2, max: 57.0) -[2023-10-15 05:54:03,535][87330] Avg episode reward: [(0, '23.070'), (1, '22.650')] -[2023-10-15 05:54:03,603][88298] Updated weights for policy 0, policy_version 89600 (0.0008) -[2023-10-15 05:54:06,171][88300] Updated weights for policy 1, policy_version 90152 (0.0008) -[2023-10-15 05:54:06,542][88300] Updated weights for policy 1, policy_version 90162 (0.0010) -[2023-10-15 05:54:06,904][88300] Updated weights for policy 1, policy_version 90172 (0.0008) -[2023-10-15 05:54:07,356][88298] Updated weights for policy 0, policy_version 89610 (0.0007) -[2023-10-15 05:54:07,713][88298] Updated weights for policy 0, policy_version 89620 (0.0008) -[2023-10-15 05:54:08,090][88298] Updated weights for policy 0, policy_version 89630 (0.0008) -[2023-10-15 05:54:08,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 184123392. Throughput: 0: 1751.3, 1: 1739.7. Samples: 46033780. Policy #0 lag: (min: 25.0, avg: 42.2, max: 57.0) -[2023-10-15 05:54:08,534][87330] Avg episode reward: [(0, '23.020'), (1, '22.790')] -[2023-10-15 05:54:10,670][88300] Updated weights for policy 1, policy_version 90182 (0.0008) -[2023-10-15 05:54:11,034][88300] Updated weights for policy 1, policy_version 90192 (0.0009) -[2023-10-15 05:54:11,404][88300] Updated weights for policy 1, policy_version 90202 (0.0008) -[2023-10-15 05:54:11,952][88298] Updated weights for policy 0, policy_version 89640 (0.0008) -[2023-10-15 05:54:12,327][88298] Updated weights for policy 0, policy_version 89650 (0.0011) -[2023-10-15 05:54:12,684][88298] Updated weights for policy 0, policy_version 89660 (0.0009) -[2023-10-15 05:54:13,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 184188928. Throughput: 0: 1731.0, 1: 1745.9. Samples: 46054612. Policy #0 lag: (min: 25.0, avg: 42.2, max: 57.0) -[2023-10-15 05:54:13,534][87330] Avg episode reward: [(0, '23.010'), (1, '22.730')] -[2023-10-15 05:54:15,191][88300] Updated weights for policy 1, policy_version 90212 (0.0010) -[2023-10-15 05:54:15,553][88300] Updated weights for policy 1, policy_version 90222 (0.0009) -[2023-10-15 05:54:15,922][88300] Updated weights for policy 1, policy_version 90232 (0.0009) -[2023-10-15 05:54:16,555][88298] Updated weights for policy 0, policy_version 89670 (0.0008) -[2023-10-15 05:54:16,931][88298] Updated weights for policy 0, policy_version 89680 (0.0009) -[2023-10-15 05:54:17,306][88298] Updated weights for policy 0, policy_version 89690 (0.0008) -[2023-10-15 05:54:18,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 184254464. Throughput: 0: 1759.0, 1: 1744.0. Samples: 46065518. Policy #0 lag: (min: 25.0, avg: 42.2, max: 57.0) -[2023-10-15 05:54:18,535][87330] Avg episode reward: [(0, '23.030'), (1, '22.740')] -[2023-10-15 05:54:19,863][88300] Updated weights for policy 1, policy_version 90242 (0.0007) -[2023-10-15 05:54:20,215][88300] Updated weights for policy 1, policy_version 90252 (0.0011) -[2023-10-15 05:54:20,578][88300] Updated weights for policy 1, policy_version 90262 (0.0010) -[2023-10-15 05:54:20,955][88300] Updated weights for policy 1, policy_version 90272 (0.0008) -[2023-10-15 05:54:21,174][88298] Updated weights for policy 0, policy_version 89700 (0.0009) -[2023-10-15 05:54:21,542][88298] Updated weights for policy 0, policy_version 89710 (0.0007) -[2023-10-15 05:54:21,918][88298] Updated weights for policy 0, policy_version 89720 (0.0007) -[2023-10-15 05:54:23,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 184320000. Throughput: 0: 1748.1, 1: 1738.6. Samples: 46086622. Policy #0 lag: (min: 25.0, avg: 42.2, max: 57.0) -[2023-10-15 05:54:23,534][87330] Avg episode reward: [(0, '23.100'), (1, '22.690')] -[2023-10-15 05:54:24,784][88300] Updated weights for policy 1, policy_version 90282 (0.0008) -[2023-10-15 05:54:25,152][88300] Updated weights for policy 1, policy_version 90292 (0.0007) -[2023-10-15 05:54:25,523][88300] Updated weights for policy 1, policy_version 90302 (0.0009) -[2023-10-15 05:54:25,930][88298] Updated weights for policy 0, policy_version 89730 (0.0008) -[2023-10-15 05:54:26,299][88298] Updated weights for policy 0, policy_version 89740 (0.0009) -[2023-10-15 05:54:26,666][88298] Updated weights for policy 0, policy_version 89750 (0.0009) -[2023-10-15 05:54:27,034][88298] Updated weights for policy 0, policy_version 89760 (0.0008) -[2023-10-15 05:54:28,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 184385536. Throughput: 0: 1733.7, 1: 1771.0. Samples: 46108174. Policy #0 lag: (min: 25.0, avg: 42.2, max: 57.0) -[2023-10-15 05:54:28,535][87330] Avg episode reward: [(0, '23.080'), (1, '22.560')] -[2023-10-15 05:54:29,121][88300] Updated weights for policy 1, policy_version 90312 (0.0007) -[2023-10-15 05:54:29,492][88300] Updated weights for policy 1, policy_version 90322 (0.0007) -[2023-10-15 05:54:29,856][88300] Updated weights for policy 1, policy_version 90332 (0.0008) -[2023-10-15 05:54:30,726][88298] Updated weights for policy 0, policy_version 89770 (0.0008) -[2023-10-15 05:54:31,086][88298] Updated weights for policy 0, policy_version 89780 (0.0007) -[2023-10-15 05:54:31,461][88298] Updated weights for policy 0, policy_version 89790 (0.0009) -[2023-10-15 05:54:33,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 184451072. Throughput: 0: 1750.0, 1: 1750.9. Samples: 46118626. Policy #0 lag: (min: 25.0, avg: 42.2, max: 57.0) -[2023-10-15 05:54:33,534][87330] Avg episode reward: [(0, '23.050'), (1, '22.530')] -[2023-10-15 05:54:33,795][88300] Updated weights for policy 1, policy_version 90342 (0.0011) -[2023-10-15 05:54:34,163][88300] Updated weights for policy 1, policy_version 90352 (0.0009) -[2023-10-15 05:54:34,530][88300] Updated weights for policy 1, policy_version 90362 (0.0007) -[2023-10-15 05:54:35,377][88298] Updated weights for policy 0, policy_version 89800 (0.0009) -[2023-10-15 05:54:35,753][88298] Updated weights for policy 0, policy_version 89810 (0.0008) -[2023-10-15 05:54:36,119][88298] Updated weights for policy 0, policy_version 89820 (0.0007) -[2023-10-15 05:54:38,466][88300] Updated weights for policy 1, policy_version 90372 (0.0008) -[2023-10-15 05:54:38,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 184516608. Throughput: 0: 1738.3, 1: 1762.1. Samples: 46139262. Policy #0 lag: (min: 25.0, avg: 42.2, max: 57.0) -[2023-10-15 05:54:38,534][87330] Avg episode reward: [(0, '23.020'), (1, '22.670')] -[2023-10-15 05:54:38,824][88300] Updated weights for policy 1, policy_version 90382 (0.0008) -[2023-10-15 05:54:39,197][88300] Updated weights for policy 1, policy_version 90392 (0.0009) -[2023-10-15 05:54:40,007][88298] Updated weights for policy 0, policy_version 89830 (0.0008) -[2023-10-15 05:54:40,394][88298] Updated weights for policy 0, policy_version 89840 (0.0008) -[2023-10-15 05:54:40,764][88298] Updated weights for policy 0, policy_version 89850 (0.0007) -[2023-10-15 05:54:43,154][88300] Updated weights for policy 1, policy_version 90402 (0.0009) -[2023-10-15 05:54:43,524][88300] Updated weights for policy 1, policy_version 90412 (0.0011) -[2023-10-15 05:54:43,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 184582144. Throughput: 0: 1737.6, 1: 1774.2. Samples: 46160600. Policy #0 lag: (min: 25.0, avg: 42.2, max: 57.0) -[2023-10-15 05:54:43,534][87330] Avg episode reward: [(0, '23.110'), (1, '22.690')] -[2023-10-15 05:54:43,882][88300] Updated weights for policy 1, policy_version 90422 (0.0012) -[2023-10-15 05:54:44,247][88300] Updated weights for policy 1, policy_version 90432 (0.0007) -[2023-10-15 05:54:44,696][88298] Updated weights for policy 0, policy_version 89860 (0.0009) -[2023-10-15 05:54:45,070][88298] Updated weights for policy 0, policy_version 89870 (0.0009) -[2023-10-15 05:54:45,444][88298] Updated weights for policy 0, policy_version 89880 (0.0007) -[2023-10-15 05:54:48,105][88300] Updated weights for policy 1, policy_version 90442 (0.0008) -[2023-10-15 05:54:48,465][88300] Updated weights for policy 1, policy_version 90452 (0.0009) -[2023-10-15 05:54:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 184647680. Throughput: 0: 1732.3, 1: 1749.3. Samples: 46170160. Policy #0 lag: (min: 25.0, avg: 42.2, max: 57.0) -[2023-10-15 05:54:48,534][87330] Avg episode reward: [(0, '22.960'), (1, '22.840')] -[2023-10-15 05:54:48,828][88300] Updated weights for policy 1, policy_version 90462 (0.0009) -[2023-10-15 05:54:49,243][88298] Updated weights for policy 0, policy_version 89890 (0.0008) -[2023-10-15 05:54:49,617][88298] Updated weights for policy 0, policy_version 89900 (0.0010) -[2023-10-15 05:54:49,982][88298] Updated weights for policy 0, policy_version 89910 (0.0008) -[2023-10-15 05:54:50,361][88298] Updated weights for policy 0, policy_version 89920 (0.0007) -[2023-10-15 05:54:52,643][88300] Updated weights for policy 1, policy_version 90472 (0.0009) -[2023-10-15 05:54:53,018][88300] Updated weights for policy 1, policy_version 90482 (0.0007) -[2023-10-15 05:54:53,385][88300] Updated weights for policy 1, policy_version 90492 (0.0007) -[2023-10-15 05:54:53,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 184745984. Throughput: 0: 1729.7, 1: 1784.4. Samples: 46191912. Policy #0 lag: (min: 25.0, avg: 42.2, max: 57.0) -[2023-10-15 05:54:53,534][87330] Avg episode reward: [(0, '22.940'), (1, '22.850')] -[2023-10-15 05:54:54,437][88298] Updated weights for policy 0, policy_version 89930 (0.0008) -[2023-10-15 05:54:54,796][88298] Updated weights for policy 0, policy_version 89940 (0.0008) -[2023-10-15 05:54:55,175][88298] Updated weights for policy 0, policy_version 89950 (0.0008) -[2023-10-15 05:54:57,195][88300] Updated weights for policy 1, policy_version 90502 (0.0008) -[2023-10-15 05:54:57,553][88300] Updated weights for policy 1, policy_version 90512 (0.0008) -[2023-10-15 05:54:57,930][88300] Updated weights for policy 1, policy_version 90522 (0.0007) -[2023-10-15 05:54:58,534][87330] Fps is (10 sec: 16383.4, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 184811520. Throughput: 0: 1756.9, 1: 1749.2. Samples: 46212388. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-15 05:54:58,535][87330] Avg episode reward: [(0, '22.940'), (1, '22.970')] -[2023-10-15 05:54:58,546][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000089952_92110848.pth... -[2023-10-15 05:54:58,546][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000090528_92700672.pth... -[2023-10-15 05:54:58,578][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000088896_91029504.pth -[2023-10-15 05:54:58,588][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000088352_90472448.pth -[2023-10-15 05:54:59,015][88298] Updated weights for policy 0, policy_version 89960 (0.0007) -[2023-10-15 05:54:59,387][88298] Updated weights for policy 0, policy_version 89970 (0.0010) -[2023-10-15 05:54:59,755][88298] Updated weights for policy 0, policy_version 89980 (0.0008) -[2023-10-15 05:55:01,818][88300] Updated weights for policy 1, policy_version 90532 (0.0007) -[2023-10-15 05:55:02,190][88300] Updated weights for policy 1, policy_version 90542 (0.0008) -[2023-10-15 05:55:02,563][88300] Updated weights for policy 1, policy_version 90552 (0.0008) -[2023-10-15 05:55:03,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 184877056. Throughput: 0: 1730.4, 1: 1775.0. Samples: 46223260. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-15 05:55:03,535][87330] Avg episode reward: [(0, '22.970'), (1, '22.970')] -[2023-10-15 05:55:03,696][88298] Updated weights for policy 0, policy_version 89990 (0.0009) -[2023-10-15 05:55:04,065][88298] Updated weights for policy 0, policy_version 90000 (0.0011) -[2023-10-15 05:55:04,435][88298] Updated weights for policy 0, policy_version 90010 (0.0008) -[2023-10-15 05:55:06,293][88300] Updated weights for policy 1, policy_version 90562 (0.0007) -[2023-10-15 05:55:06,669][88300] Updated weights for policy 1, policy_version 90572 (0.0009) -[2023-10-15 05:55:07,029][88300] Updated weights for policy 1, policy_version 90582 (0.0008) -[2023-10-15 05:55:07,404][88300] Updated weights for policy 1, policy_version 90592 (0.0009) -[2023-10-15 05:55:08,385][88298] Updated weights for policy 0, policy_version 90020 (0.0007) -[2023-10-15 05:55:08,534][87330] Fps is (10 sec: 13107.6, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 184942592. Throughput: 0: 1737.5, 1: 1753.8. Samples: 46243728. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-15 05:55:08,534][87330] Avg episode reward: [(0, '23.010'), (1, '22.940')] -[2023-10-15 05:55:08,759][88298] Updated weights for policy 0, policy_version 90030 (0.0008) -[2023-10-15 05:55:09,125][88298] Updated weights for policy 0, policy_version 90040 (0.0008) -[2023-10-15 05:55:11,230][88300] Updated weights for policy 1, policy_version 90602 (0.0011) -[2023-10-15 05:55:11,600][88300] Updated weights for policy 1, policy_version 90612 (0.0009) -[2023-10-15 05:55:11,973][88300] Updated weights for policy 1, policy_version 90622 (0.0007) -[2023-10-15 05:55:13,038][88298] Updated weights for policy 0, policy_version 90050 (0.0007) -[2023-10-15 05:55:13,402][88298] Updated weights for policy 0, policy_version 90060 (0.0007) -[2023-10-15 05:55:13,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 185008128. Throughput: 0: 1753.0, 1: 1735.6. Samples: 46265162. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-15 05:55:13,535][87330] Avg episode reward: [(0, '22.950'), (1, '22.970')] -[2023-10-15 05:55:13,781][88298] Updated weights for policy 0, policy_version 90070 (0.0007) -[2023-10-15 05:55:14,140][88298] Updated weights for policy 0, policy_version 90080 (0.0009) -[2023-10-15 05:55:15,983][88300] Updated weights for policy 1, policy_version 90632 (0.0008) -[2023-10-15 05:55:16,340][88300] Updated weights for policy 1, policy_version 90642 (0.0010) -[2023-10-15 05:55:16,711][88300] Updated weights for policy 1, policy_version 90652 (0.0009) -[2023-10-15 05:55:17,881][88298] Updated weights for policy 0, policy_version 90090 (0.0007) -[2023-10-15 05:55:18,245][88298] Updated weights for policy 0, policy_version 90100 (0.0009) -[2023-10-15 05:55:18,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 185073664. Throughput: 0: 1734.6, 1: 1748.7. Samples: 46275376. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-15 05:55:18,535][87330] Avg episode reward: [(0, '23.040'), (1, '22.940')] -[2023-10-15 05:55:18,619][88298] Updated weights for policy 0, policy_version 90110 (0.0008) -[2023-10-15 05:55:20,697][88300] Updated weights for policy 1, policy_version 90662 (0.0008) -[2023-10-15 05:55:21,096][88300] Updated weights for policy 1, policy_version 90672 (0.0010) -[2023-10-15 05:55:21,450][88300] Updated weights for policy 1, policy_version 90682 (0.0010) -[2023-10-15 05:55:22,366][88298] Updated weights for policy 0, policy_version 90120 (0.0009) -[2023-10-15 05:55:22,729][88298] Updated weights for policy 0, policy_version 90130 (0.0010) -[2023-10-15 05:55:23,103][88298] Updated weights for policy 0, policy_version 90140 (0.0007) -[2023-10-15 05:55:23,534][87330] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 185171968. Throughput: 0: 1758.4, 1: 1731.0. Samples: 46296284. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-15 05:55:23,534][87330] Avg episode reward: [(0, '23.060'), (1, '22.950')] -[2023-10-15 05:55:25,119][88300] Updated weights for policy 1, policy_version 90692 (0.0009) -[2023-10-15 05:55:25,480][88300] Updated weights for policy 1, policy_version 90702 (0.0008) -[2023-10-15 05:55:25,845][88300] Updated weights for policy 1, policy_version 90712 (0.0007) -[2023-10-15 05:55:27,112][88298] Updated weights for policy 0, policy_version 90150 (0.0010) -[2023-10-15 05:55:27,487][88298] Updated weights for policy 0, policy_version 90160 (0.0009) -[2023-10-15 05:55:27,856][88298] Updated weights for policy 0, policy_version 90170 (0.0008) -[2023-10-15 05:55:28,534][87330] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 185237504. Throughput: 0: 1733.4, 1: 1744.7. Samples: 46317114. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-15 05:55:28,535][87330] Avg episode reward: [(0, '23.070'), (1, '23.030')] -[2023-10-15 05:55:29,690][88300] Updated weights for policy 1, policy_version 90722 (0.0010) -[2023-10-15 05:55:30,055][88300] Updated weights for policy 1, policy_version 90732 (0.0010) -[2023-10-15 05:55:30,421][88300] Updated weights for policy 1, policy_version 90742 (0.0008) -[2023-10-15 05:55:30,785][88300] Updated weights for policy 1, policy_version 90752 (0.0008) -[2023-10-15 05:55:31,770][88298] Updated weights for policy 0, policy_version 90180 (0.0010) -[2023-10-15 05:55:32,133][88298] Updated weights for policy 0, policy_version 90190 (0.0010) -[2023-10-15 05:55:32,502][88298] Updated weights for policy 0, policy_version 90200 (0.0008) -[2023-10-15 05:55:33,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 185303040. Throughput: 0: 1762.7, 1: 1739.6. Samples: 46327764. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-15 05:55:33,535][87330] Avg episode reward: [(0, '23.030'), (1, '23.010')] -[2023-10-15 05:55:34,849][88300] Updated weights for policy 1, policy_version 90762 (0.0010) -[2023-10-15 05:55:35,211][88300] Updated weights for policy 1, policy_version 90772 (0.0010) -[2023-10-15 05:55:35,579][88300] Updated weights for policy 1, policy_version 90782 (0.0010) -[2023-10-15 05:55:36,399][88298] Updated weights for policy 0, policy_version 90210 (0.0009) -[2023-10-15 05:55:36,766][88298] Updated weights for policy 0, policy_version 90220 (0.0009) -[2023-10-15 05:55:37,130][88298] Updated weights for policy 0, policy_version 90230 (0.0011) -[2023-10-15 05:55:37,492][88298] Updated weights for policy 0, policy_version 90240 (0.0011) -[2023-10-15 05:55:38,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 185368576. Throughput: 0: 1745.0, 1: 1735.4. Samples: 46348530. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-15 05:55:38,534][87330] Avg episode reward: [(0, '23.030'), (1, '23.000')] -[2023-10-15 05:55:39,404][88300] Updated weights for policy 1, policy_version 90792 (0.0009) -[2023-10-15 05:55:39,778][88300] Updated weights for policy 1, policy_version 90802 (0.0008) -[2023-10-15 05:55:40,138][88300] Updated weights for policy 1, policy_version 90812 (0.0007) -[2023-10-15 05:55:41,480][88298] Updated weights for policy 0, policy_version 90250 (0.0009) -[2023-10-15 05:55:41,851][88298] Updated weights for policy 0, policy_version 90260 (0.0007) -[2023-10-15 05:55:42,229][88298] Updated weights for policy 0, policy_version 90270 (0.0008) -[2023-10-15 05:55:43,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 185434112. Throughput: 0: 1722.4, 1: 1768.7. Samples: 46369488. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-15 05:55:43,534][87330] Avg episode reward: [(0, '23.070'), (1, '23.010')] -[2023-10-15 05:55:43,923][88300] Updated weights for policy 1, policy_version 90822 (0.0009) -[2023-10-15 05:55:44,295][88300] Updated weights for policy 1, policy_version 90832 (0.0007) -[2023-10-15 05:55:44,672][88300] Updated weights for policy 1, policy_version 90842 (0.0008) -[2023-10-15 05:55:46,171][88298] Updated weights for policy 0, policy_version 90280 (0.0009) -[2023-10-15 05:55:46,535][88298] Updated weights for policy 0, policy_version 90290 (0.0009) -[2023-10-15 05:55:46,910][88298] Updated weights for policy 0, policy_version 90300 (0.0010) -[2023-10-15 05:55:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 185499648. Throughput: 0: 1753.1, 1: 1735.3. Samples: 46380236. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-15 05:55:48,534][87330] Avg episode reward: [(0, '23.100'), (1, '23.020')] -[2023-10-15 05:55:48,672][88300] Updated weights for policy 1, policy_version 90852 (0.0010) -[2023-10-15 05:55:49,045][88300] Updated weights for policy 1, policy_version 90862 (0.0008) -[2023-10-15 05:55:49,414][88300] Updated weights for policy 1, policy_version 90872 (0.0008) -[2023-10-15 05:55:50,882][88298] Updated weights for policy 0, policy_version 90310 (0.0007) -[2023-10-15 05:55:51,245][88298] Updated weights for policy 0, policy_version 90320 (0.0007) -[2023-10-15 05:55:51,617][88298] Updated weights for policy 0, policy_version 90330 (0.0008) -[2023-10-15 05:55:53,235][88300] Updated weights for policy 1, policy_version 90882 (0.0010) -[2023-10-15 05:55:53,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 185565184. Throughput: 0: 1727.2, 1: 1755.3. Samples: 46400442. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:55:53,535][87330] Avg episode reward: [(0, '23.090'), (1, '22.830')] -[2023-10-15 05:55:53,605][88300] Updated weights for policy 1, policy_version 90892 (0.0011) -[2023-10-15 05:55:53,981][88300] Updated weights for policy 1, policy_version 90902 (0.0008) -[2023-10-15 05:55:54,348][88300] Updated weights for policy 1, policy_version 90912 (0.0008) -[2023-10-15 05:55:55,673][88298] Updated weights for policy 0, policy_version 90340 (0.0008) -[2023-10-15 05:55:56,054][88298] Updated weights for policy 0, policy_version 90350 (0.0007) -[2023-10-15 05:55:56,423][88298] Updated weights for policy 0, policy_version 90360 (0.0008) -[2023-10-15 05:55:58,111][88300] Updated weights for policy 1, policy_version 90922 (0.0011) -[2023-10-15 05:55:58,477][88300] Updated weights for policy 1, policy_version 90932 (0.0008) -[2023-10-15 05:55:58,534][87330] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 185630720. Throughput: 0: 1718.8, 1: 1754.3. Samples: 46421452. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:55:58,535][87330] Avg episode reward: [(0, '23.070'), (1, '22.730')] -[2023-10-15 05:55:58,850][88300] Updated weights for policy 1, policy_version 90942 (0.0009) -[2023-10-15 05:56:00,183][88298] Updated weights for policy 0, policy_version 90370 (0.0009) -[2023-10-15 05:56:00,549][88298] Updated weights for policy 0, policy_version 90380 (0.0009) -[2023-10-15 05:56:00,926][88298] Updated weights for policy 0, policy_version 90390 (0.0008) -[2023-10-15 05:56:01,285][88298] Updated weights for policy 0, policy_version 90400 (0.0007) -[2023-10-15 05:56:02,897][88300] Updated weights for policy 1, policy_version 90952 (0.0009) -[2023-10-15 05:56:03,268][88300] Updated weights for policy 1, policy_version 90962 (0.0007) -[2023-10-15 05:56:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 185696256. Throughput: 0: 1734.9, 1: 1746.0. Samples: 46432014. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:56:03,535][87330] Avg episode reward: [(0, '23.080'), (1, '22.720')] -[2023-10-15 05:56:03,627][88300] Updated weights for policy 1, policy_version 90972 (0.0009) -[2023-10-15 05:56:05,203][88298] Updated weights for policy 0, policy_version 90410 (0.0011) -[2023-10-15 05:56:05,568][88298] Updated weights for policy 0, policy_version 90420 (0.0007) -[2023-10-15 05:56:05,936][88298] Updated weights for policy 0, policy_version 90430 (0.0007) -[2023-10-15 05:56:07,505][88300] Updated weights for policy 1, policy_version 90982 (0.0009) -[2023-10-15 05:56:07,866][88300] Updated weights for policy 1, policy_version 90992 (0.0008) -[2023-10-15 05:56:08,241][88300] Updated weights for policy 1, policy_version 91002 (0.0010) -[2023-10-15 05:56:08,534][87330] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 185794560. Throughput: 0: 1715.4, 1: 1767.6. Samples: 46453022. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:56:08,534][87330] Avg episode reward: [(0, '23.050'), (1, '22.710')] -[2023-10-15 05:56:09,829][88298] Updated weights for policy 0, policy_version 90440 (0.0010) -[2023-10-15 05:56:10,204][88298] Updated weights for policy 0, policy_version 90450 (0.0008) -[2023-10-15 05:56:10,580][88298] Updated weights for policy 0, policy_version 90460 (0.0010) -[2023-10-15 05:56:12,036][88300] Updated weights for policy 1, policy_version 91012 (0.0007) -[2023-10-15 05:56:12,397][88300] Updated weights for policy 1, policy_version 91022 (0.0008) -[2023-10-15 05:56:12,767][88300] Updated weights for policy 1, policy_version 91032 (0.0007) -[2023-10-15 05:56:13,534][87330] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 185860096. Throughput: 0: 1739.9, 1: 1730.4. Samples: 46473276. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:56:13,534][87330] Avg episode reward: [(0, '23.050'), (1, '22.720')] -[2023-10-15 05:56:14,606][88298] Updated weights for policy 0, policy_version 90470 (0.0008) -[2023-10-15 05:56:14,987][88298] Updated weights for policy 0, policy_version 90480 (0.0007) -[2023-10-15 05:56:15,358][88298] Updated weights for policy 0, policy_version 90490 (0.0008) -[2023-10-15 05:56:16,697][88300] Updated weights for policy 1, policy_version 91042 (0.0008) -[2023-10-15 05:56:17,067][88300] Updated weights for policy 1, policy_version 91052 (0.0008) -[2023-10-15 05:56:17,434][88300] Updated weights for policy 1, policy_version 91062 (0.0009) -[2023-10-15 05:56:17,797][88300] Updated weights for policy 1, policy_version 91072 (0.0007) -[2023-10-15 05:56:18,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 185925632. Throughput: 0: 1710.9, 1: 1763.6. Samples: 46484114. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:56:18,534][87330] Avg episode reward: [(0, '23.030'), (1, '22.720')] -[2023-10-15 05:56:19,221][88298] Updated weights for policy 0, policy_version 90500 (0.0008) -[2023-10-15 05:56:19,589][88298] Updated weights for policy 0, policy_version 90510 (0.0008) -[2023-10-15 05:56:19,965][88298] Updated weights for policy 0, policy_version 90520 (0.0009) -[2023-10-15 05:56:21,521][88300] Updated weights for policy 1, policy_version 91082 (0.0008) -[2023-10-15 05:56:21,891][88300] Updated weights for policy 1, policy_version 91092 (0.0011) -[2023-10-15 05:56:22,251][88300] Updated weights for policy 1, policy_version 91102 (0.0010) -[2023-10-15 05:56:23,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 185991168. Throughput: 0: 1725.6, 1: 1746.8. Samples: 46504784. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:56:23,534][87330] Avg episode reward: [(0, '23.080'), (1, '22.730')] -[2023-10-15 05:56:23,859][88298] Updated weights for policy 0, policy_version 90530 (0.0008) -[2023-10-15 05:56:24,232][88298] Updated weights for policy 0, policy_version 90540 (0.0010) -[2023-10-15 05:56:24,606][88298] Updated weights for policy 0, policy_version 90550 (0.0008) -[2023-10-15 05:56:24,967][88298] Updated weights for policy 0, policy_version 90560 (0.0008) -[2023-10-15 05:56:26,138][88300] Updated weights for policy 1, policy_version 91112 (0.0009) -[2023-10-15 05:56:26,498][88300] Updated weights for policy 1, policy_version 91122 (0.0008) -[2023-10-15 05:56:26,864][88300] Updated weights for policy 1, policy_version 91132 (0.0009) -[2023-10-15 05:56:28,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 186056704. Throughput: 0: 1749.9, 1: 1734.6. Samples: 46526290. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:56:28,535][87330] Avg episode reward: [(0, '23.140'), (1, '22.990')] -[2023-10-15 05:56:28,687][88298] Updated weights for policy 0, policy_version 90570 (0.0009) -[2023-10-15 05:56:29,052][88298] Updated weights for policy 0, policy_version 90580 (0.0007) -[2023-10-15 05:56:29,425][88298] Updated weights for policy 0, policy_version 90590 (0.0007) -[2023-10-15 05:56:30,730][88300] Updated weights for policy 1, policy_version 91142 (0.0007) -[2023-10-15 05:56:31,099][88300] Updated weights for policy 1, policy_version 91152 (0.0007) -[2023-10-15 05:56:31,461][88300] Updated weights for policy 1, policy_version 91162 (0.0007) -[2023-10-15 05:56:33,252][88298] Updated weights for policy 0, policy_version 90600 (0.0008) -[2023-10-15 05:56:33,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 186122240. Throughput: 0: 1716.3, 1: 1750.7. Samples: 46536252. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:56:33,535][87330] Avg episode reward: [(0, '23.160'), (1, '23.000')] -[2023-10-15 05:56:33,628][88298] Updated weights for policy 0, policy_version 90610 (0.0010) -[2023-10-15 05:56:34,001][88298] Updated weights for policy 0, policy_version 90620 (0.0009) -[2023-10-15 05:56:35,480][88300] Updated weights for policy 1, policy_version 91172 (0.0009) -[2023-10-15 05:56:35,852][88300] Updated weights for policy 1, policy_version 91182 (0.0010) -[2023-10-15 05:56:36,219][88300] Updated weights for policy 1, policy_version 91192 (0.0010) -[2023-10-15 05:56:37,954][88298] Updated weights for policy 0, policy_version 90630 (0.0010) -[2023-10-15 05:56:38,317][88298] Updated weights for policy 0, policy_version 90640 (0.0011) -[2023-10-15 05:56:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 186187776. Throughput: 0: 1746.3, 1: 1738.4. Samples: 46557256. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:56:38,535][87330] Avg episode reward: [(0, '23.160'), (1, '23.040')] -[2023-10-15 05:56:38,701][88298] Updated weights for policy 0, policy_version 90650 (0.0010) -[2023-10-15 05:56:40,102][88300] Updated weights for policy 1, policy_version 91202 (0.0010) -[2023-10-15 05:56:40,464][88300] Updated weights for policy 1, policy_version 91212 (0.0008) -[2023-10-15 05:56:40,828][88300] Updated weights for policy 1, policy_version 91222 (0.0010) -[2023-10-15 05:56:41,197][88300] Updated weights for policy 1, policy_version 91232 (0.0009) -[2023-10-15 05:56:42,493][88298] Updated weights for policy 0, policy_version 90660 (0.0010) -[2023-10-15 05:56:42,860][88298] Updated weights for policy 0, policy_version 90670 (0.0009) -[2023-10-15 05:56:43,227][88298] Updated weights for policy 0, policy_version 90680 (0.0010) -[2023-10-15 05:56:43,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 186286080. Throughput: 0: 1739.6, 1: 1747.0. Samples: 46578348. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:56:43,535][87330] Avg episode reward: [(0, '23.150'), (1, '23.020')] -[2023-10-15 05:56:45,379][88300] Updated weights for policy 1, policy_version 91242 (0.0009) -[2023-10-15 05:56:45,746][88300] Updated weights for policy 1, policy_version 91252 (0.0007) -[2023-10-15 05:56:46,114][88300] Updated weights for policy 1, policy_version 91262 (0.0008) -[2023-10-15 05:56:47,250][88298] Updated weights for policy 0, policy_version 90690 (0.0007) -[2023-10-15 05:56:47,623][88298] Updated weights for policy 0, policy_version 90700 (0.0007) -[2023-10-15 05:56:47,991][88298] Updated weights for policy 0, policy_version 90710 (0.0008) -[2023-10-15 05:56:48,366][88298] Updated weights for policy 0, policy_version 90720 (0.0008) -[2023-10-15 05:56:48,534][87330] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 186351616. Throughput: 0: 1735.7, 1: 1736.3. Samples: 46588256. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:56:48,534][87330] Avg episode reward: [(0, '23.170'), (1, '22.910')] -[2023-10-15 05:56:49,900][88300] Updated weights for policy 1, policy_version 91272 (0.0008) -[2023-10-15 05:56:50,266][88300] Updated weights for policy 1, policy_version 91282 (0.0008) -[2023-10-15 05:56:50,630][88300] Updated weights for policy 1, policy_version 91292 (0.0009) -[2023-10-15 05:56:52,227][88298] Updated weights for policy 0, policy_version 90730 (0.0010) -[2023-10-15 05:56:52,601][88298] Updated weights for policy 0, policy_version 90740 (0.0009) -[2023-10-15 05:56:52,970][88298] Updated weights for policy 0, policy_version 90750 (0.0008) -[2023-10-15 05:56:53,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 186417152. Throughput: 0: 1752.7, 1: 1733.4. Samples: 46609896. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:56:53,534][87330] Avg episode reward: [(0, '23.150'), (1, '22.910')] -[2023-10-15 05:56:54,620][88300] Updated weights for policy 1, policy_version 91302 (0.0007) -[2023-10-15 05:56:55,006][88300] Updated weights for policy 1, policy_version 91312 (0.0007) -[2023-10-15 05:56:55,374][88300] Updated weights for policy 1, policy_version 91322 (0.0007) -[2023-10-15 05:56:56,982][88298] Updated weights for policy 0, policy_version 90760 (0.0011) -[2023-10-15 05:56:57,350][88298] Updated weights for policy 0, policy_version 90770 (0.0010) -[2023-10-15 05:56:57,720][88298] Updated weights for policy 0, policy_version 90780 (0.0009) -[2023-10-15 05:56:58,534][87330] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 186482688. Throughput: 0: 1723.3, 1: 1763.6. Samples: 46630190. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:56:58,535][87330] Avg episode reward: [(0, '23.130'), (1, '22.870')] -[2023-10-15 05:56:58,547][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000090784_92962816.pth... -[2023-10-15 05:56:58,547][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000091328_93519872.pth... -[2023-10-15 05:56:58,584][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000089152_91291648.pth -[2023-10-15 05:56:58,584][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000089696_91848704.pth -[2023-10-15 05:56:59,396][88300] Updated weights for policy 1, policy_version 91332 (0.0009) -[2023-10-15 05:56:59,751][88300] Updated weights for policy 1, policy_version 91342 (0.0008) -[2023-10-15 05:57:00,115][88300] Updated weights for policy 1, policy_version 91352 (0.0008) -[2023-10-15 05:57:01,578][88298] Updated weights for policy 0, policy_version 90790 (0.0009) -[2023-10-15 05:57:01,949][88298] Updated weights for policy 0, policy_version 90800 (0.0011) -[2023-10-15 05:57:02,322][88298] Updated weights for policy 0, policy_version 90810 (0.0008) -[2023-10-15 05:57:03,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 186548224. Throughput: 0: 1756.4, 1: 1729.4. Samples: 46640976. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:57:03,535][87330] Avg episode reward: [(0, '23.140'), (1, '22.870')] -[2023-10-15 05:57:03,946][88300] Updated weights for policy 1, policy_version 91362 (0.0008) -[2023-10-15 05:57:04,316][88300] Updated weights for policy 1, policy_version 91372 (0.0007) -[2023-10-15 05:57:04,694][88300] Updated weights for policy 1, policy_version 91382 (0.0008) -[2023-10-15 05:57:05,050][88300] Updated weights for policy 1, policy_version 91392 (0.0010) -[2023-10-15 05:57:06,393][88298] Updated weights for policy 0, policy_version 90820 (0.0009) -[2023-10-15 05:57:06,765][88298] Updated weights for policy 0, policy_version 90830 (0.0008) -[2023-10-15 05:57:07,135][88298] Updated weights for policy 0, policy_version 90840 (0.0007) -[2023-10-15 05:57:08,534][87330] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13995.8). Total num frames: 186613760. Throughput: 0: 1739.8, 1: 1751.8. Samples: 46661904. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:57:08,534][87330] Avg episode reward: [(0, '23.110'), (1, '22.880')] -[2023-10-15 05:57:08,809][88300] Updated weights for policy 1, policy_version 91402 (0.0008) -[2023-10-15 05:57:09,182][88300] Updated weights for policy 1, policy_version 91412 (0.0007) -[2023-10-15 05:57:09,549][88300] Updated weights for policy 1, policy_version 91422 (0.0009) -[2023-10-15 05:57:10,877][88298] Updated weights for policy 0, policy_version 90850 (0.0007) -[2023-10-15 05:57:11,242][88298] Updated weights for policy 0, policy_version 90860 (0.0008) -[2023-10-15 05:57:11,605][88298] Updated weights for policy 0, policy_version 90870 (0.0009) -[2023-10-15 05:57:11,975][88298] Updated weights for policy 0, policy_version 90880 (0.0008) -[2023-10-15 05:57:13,325][88300] Updated weights for policy 1, policy_version 91432 (0.0010) -[2023-10-15 05:57:13,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 186679296. Throughput: 0: 1720.2, 1: 1758.0. Samples: 46682810. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:57:13,534][87330] Avg episode reward: [(0, '22.990'), (1, '22.680')] -[2023-10-15 05:57:13,691][88300] Updated weights for policy 1, policy_version 91442 (0.0010) -[2023-10-15 05:57:14,060][88300] Updated weights for policy 1, policy_version 91452 (0.0008) -[2023-10-15 05:57:15,991][88298] Updated weights for policy 0, policy_version 90890 (0.0008) -[2023-10-15 05:57:16,356][88298] Updated weights for policy 0, policy_version 90900 (0.0011) -[2023-10-15 05:57:16,728][88298] Updated weights for policy 0, policy_version 90910 (0.0008) -[2023-10-15 05:57:17,704][88300] Updated weights for policy 1, policy_version 91462 (0.0008) -[2023-10-15 05:57:18,076][88300] Updated weights for policy 1, policy_version 91472 (0.0007) -[2023-10-15 05:57:18,434][88300] Updated weights for policy 1, policy_version 91482 (0.0010) -[2023-10-15 05:57:18,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 186744832. Throughput: 0: 1749.9, 1: 1752.9. Samples: 46693880. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:57:18,535][87330] Avg episode reward: [(0, '22.720'), (1, '22.650')] -[2023-10-15 05:57:20,603][88298] Updated weights for policy 0, policy_version 90920 (0.0008) -[2023-10-15 05:57:20,974][88298] Updated weights for policy 0, policy_version 90930 (0.0008) -[2023-10-15 05:57:21,345][88298] Updated weights for policy 0, policy_version 90940 (0.0008) -[2023-10-15 05:57:22,211][88300] Updated weights for policy 1, policy_version 91492 (0.0007) -[2023-10-15 05:57:22,585][88300] Updated weights for policy 1, policy_version 91502 (0.0007) -[2023-10-15 05:57:22,949][88300] Updated weights for policy 1, policy_version 91512 (0.0008) -[2023-10-15 05:57:23,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 186843136. Throughput: 0: 1720.5, 1: 1770.3. Samples: 46714340. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:57:23,534][87330] Avg episode reward: [(0, '22.710'), (1, '22.790')] -[2023-10-15 05:57:25,233][88298] Updated weights for policy 0, policy_version 90950 (0.0009) -[2023-10-15 05:57:25,604][88298] Updated weights for policy 0, policy_version 90960 (0.0008) -[2023-10-15 05:57:25,978][88298] Updated weights for policy 0, policy_version 90970 (0.0008) -[2023-10-15 05:57:27,015][88300] Updated weights for policy 1, policy_version 91522 (0.0008) -[2023-10-15 05:57:27,388][88300] Updated weights for policy 1, policy_version 91532 (0.0009) -[2023-10-15 05:57:27,751][88300] Updated weights for policy 1, policy_version 91542 (0.0010) -[2023-10-15 05:57:28,114][88300] Updated weights for policy 1, policy_version 91552 (0.0007) -[2023-10-15 05:57:28,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 186908672. Throughput: 0: 1733.2, 1: 1739.1. Samples: 46734600. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:57:28,534][87330] Avg episode reward: [(0, '22.630'), (1, '22.830')] -[2023-10-15 05:57:29,818][88298] Updated weights for policy 0, policy_version 90980 (0.0008) -[2023-10-15 05:57:30,183][88298] Updated weights for policy 0, policy_version 90990 (0.0009) -[2023-10-15 05:57:30,557][88298] Updated weights for policy 0, policy_version 91000 (0.0008) -[2023-10-15 05:57:32,069][88300] Updated weights for policy 1, policy_version 91562 (0.0007) -[2023-10-15 05:57:32,430][88300] Updated weights for policy 1, policy_version 91572 (0.0007) -[2023-10-15 05:57:32,800][88300] Updated weights for policy 1, policy_version 91582 (0.0007) -[2023-10-15 05:57:33,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 186974208. Throughput: 0: 1725.0, 1: 1773.5. Samples: 46745688. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:57:33,535][87330] Avg episode reward: [(0, '22.650'), (1, '22.700')] -[2023-10-15 05:57:34,415][88298] Updated weights for policy 0, policy_version 91010 (0.0008) -[2023-10-15 05:57:34,786][88298] Updated weights for policy 0, policy_version 91020 (0.0010) -[2023-10-15 05:57:35,168][88298] Updated weights for policy 0, policy_version 91030 (0.0008) -[2023-10-15 05:57:35,538][88298] Updated weights for policy 0, policy_version 91040 (0.0008) -[2023-10-15 05:57:36,527][88300] Updated weights for policy 1, policy_version 91592 (0.0010) -[2023-10-15 05:57:36,894][88300] Updated weights for policy 1, policy_version 91602 (0.0008) -[2023-10-15 05:57:37,268][88300] Updated weights for policy 1, policy_version 91612 (0.0007) -[2023-10-15 05:57:38,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 187039744. Throughput: 0: 1720.3, 1: 1755.2. Samples: 46766298. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:57:38,535][87330] Avg episode reward: [(0, '22.620'), (1, '22.710')] -[2023-10-15 05:57:39,515][88298] Updated weights for policy 0, policy_version 91050 (0.0008) -[2023-10-15 05:57:39,888][88298] Updated weights for policy 0, policy_version 91060 (0.0007) -[2023-10-15 05:57:40,254][88298] Updated weights for policy 0, policy_version 91070 (0.0007) -[2023-10-15 05:57:41,331][88300] Updated weights for policy 1, policy_version 91622 (0.0009) -[2023-10-15 05:57:41,699][88300] Updated weights for policy 1, policy_version 91632 (0.0007) -[2023-10-15 05:57:42,065][88300] Updated weights for policy 1, policy_version 91642 (0.0010) -[2023-10-15 05:57:43,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 187105280. Throughput: 0: 1744.9, 1: 1745.8. Samples: 46787272. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:57:43,535][87330] Avg episode reward: [(0, '22.760'), (1, '22.900')] -[2023-10-15 05:57:44,297][88298] Updated weights for policy 0, policy_version 91080 (0.0007) -[2023-10-15 05:57:44,675][88298] Updated weights for policy 0, policy_version 91090 (0.0007) -[2023-10-15 05:57:45,050][88298] Updated weights for policy 0, policy_version 91100 (0.0007) -[2023-10-15 05:57:45,944][88300] Updated weights for policy 1, policy_version 91652 (0.0010) -[2023-10-15 05:57:46,315][88300] Updated weights for policy 1, policy_version 91662 (0.0011) -[2023-10-15 05:57:46,673][88300] Updated weights for policy 1, policy_version 91672 (0.0009) -[2023-10-15 05:57:48,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 187170816. Throughput: 0: 1711.9, 1: 1767.5. Samples: 46797550. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-15 05:57:48,534][87330] Avg episode reward: [(0, '23.050'), (1, '22.720')] -[2023-10-15 05:57:49,197][88298] Updated weights for policy 0, policy_version 91110 (0.0010) -[2023-10-15 05:57:49,574][88298] Updated weights for policy 0, policy_version 91120 (0.0007) -[2023-10-15 05:57:49,946][88298] Updated weights for policy 0, policy_version 91130 (0.0008) -[2023-10-15 05:57:50,619][88300] Updated weights for policy 1, policy_version 91682 (0.0009) -[2023-10-15 05:57:50,984][88300] Updated weights for policy 1, policy_version 91692 (0.0008) -[2023-10-15 05:57:51,356][88300] Updated weights for policy 1, policy_version 91702 (0.0009) -[2023-10-15 05:57:51,718][88300] Updated weights for policy 1, policy_version 91712 (0.0008) -[2023-10-15 05:57:53,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 187236352. Throughput: 0: 1726.9, 1: 1741.9. Samples: 46817998. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-15 05:57:53,535][87330] Avg episode reward: [(0, '23.060'), (1, '22.750')] -[2023-10-15 05:57:53,731][88298] Updated weights for policy 0, policy_version 91140 (0.0009) -[2023-10-15 05:57:54,093][88298] Updated weights for policy 0, policy_version 91150 (0.0009) -[2023-10-15 05:57:54,463][88298] Updated weights for policy 0, policy_version 91160 (0.0009) -[2023-10-15 05:57:55,521][88300] Updated weights for policy 1, policy_version 91722 (0.0010) -[2023-10-15 05:57:55,886][88300] Updated weights for policy 1, policy_version 91732 (0.0007) -[2023-10-15 05:57:56,251][88300] Updated weights for policy 1, policy_version 91742 (0.0008) -[2023-10-15 05:57:58,350][88298] Updated weights for policy 0, policy_version 91170 (0.0007) -[2023-10-15 05:57:58,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 187301888. Throughput: 0: 1741.6, 1: 1742.4. Samples: 46839590. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-15 05:57:58,534][87330] Avg episode reward: [(0, '23.130'), (1, '22.710')] -[2023-10-15 05:57:58,720][88298] Updated weights for policy 0, policy_version 91180 (0.0008) -[2023-10-15 05:57:59,081][88298] Updated weights for policy 0, policy_version 91190 (0.0009) -[2023-10-15 05:57:59,448][88298] Updated weights for policy 0, policy_version 91200 (0.0008) -[2023-10-15 05:58:00,015][88300] Updated weights for policy 1, policy_version 91752 (0.0007) -[2023-10-15 05:58:00,388][88300] Updated weights for policy 1, policy_version 91762 (0.0008) -[2023-10-15 05:58:00,763][88300] Updated weights for policy 1, policy_version 91772 (0.0009) -[2023-10-15 05:58:03,284][88298] Updated weights for policy 0, policy_version 91210 (0.0008) -[2023-10-15 05:58:03,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 187367424. Throughput: 0: 1713.7, 1: 1734.6. Samples: 46849054. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-15 05:58:03,534][87330] Avg episode reward: [(0, '23.120'), (1, '22.710')] -[2023-10-15 05:58:03,650][88298] Updated weights for policy 0, policy_version 91220 (0.0010) -[2023-10-15 05:58:04,027][88298] Updated weights for policy 0, policy_version 91230 (0.0010) -[2023-10-15 05:58:04,663][88300] Updated weights for policy 1, policy_version 91782 (0.0008) -[2023-10-15 05:58:05,039][88300] Updated weights for policy 1, policy_version 91792 (0.0008) -[2023-10-15 05:58:05,401][88300] Updated weights for policy 1, policy_version 91802 (0.0007) -[2023-10-15 05:58:08,026][88298] Updated weights for policy 0, policy_version 91240 (0.0008) -[2023-10-15 05:58:08,397][88298] Updated weights for policy 0, policy_version 91250 (0.0007) -[2023-10-15 05:58:08,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 187432960. Throughput: 0: 1739.5, 1: 1730.1. Samples: 46870470. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-15 05:58:08,535][87330] Avg episode reward: [(0, '23.150'), (1, '22.870')] -[2023-10-15 05:58:08,774][88298] Updated weights for policy 0, policy_version 91260 (0.0007) -[2023-10-15 05:58:09,291][88300] Updated weights for policy 1, policy_version 91812 (0.0007) -[2023-10-15 05:58:09,661][88300] Updated weights for policy 1, policy_version 91822 (0.0009) -[2023-10-15 05:58:10,029][88300] Updated weights for policy 1, policy_version 91832 (0.0008) -[2023-10-15 05:58:12,585][88298] Updated weights for policy 0, policy_version 91270 (0.0007) -[2023-10-15 05:58:12,955][88298] Updated weights for policy 0, policy_version 91280 (0.0007) -[2023-10-15 05:58:13,323][88298] Updated weights for policy 0, policy_version 91290 (0.0007) -[2023-10-15 05:58:13,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 187498496. Throughput: 0: 1728.8, 1: 1766.8. Samples: 46891900. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-15 05:58:13,535][87330] Avg episode reward: [(0, '23.130'), (1, '22.870')] -[2023-10-15 05:58:13,881][88300] Updated weights for policy 1, policy_version 91842 (0.0008) -[2023-10-15 05:58:14,254][88300] Updated weights for policy 1, policy_version 91852 (0.0011) -[2023-10-15 05:58:14,611][88300] Updated weights for policy 1, policy_version 91862 (0.0009) -[2023-10-15 05:58:14,977][88300] Updated weights for policy 1, policy_version 91872 (0.0008) -[2023-10-15 05:58:17,333][88298] Updated weights for policy 0, policy_version 91300 (0.0007) -[2023-10-15 05:58:17,710][88298] Updated weights for policy 0, policy_version 91310 (0.0008) -[2023-10-15 05:58:18,082][88298] Updated weights for policy 0, policy_version 91320 (0.0007) -[2023-10-15 05:58:18,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 187596800. Throughput: 0: 1735.5, 1: 1733.4. Samples: 46901790. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-15 05:58:18,535][87330] Avg episode reward: [(0, '23.090'), (1, '22.910')] -[2023-10-15 05:58:18,926][88300] Updated weights for policy 1, policy_version 91882 (0.0011) -[2023-10-15 05:58:19,301][88300] Updated weights for policy 1, policy_version 91892 (0.0008) -[2023-10-15 05:58:19,668][88300] Updated weights for policy 1, policy_version 91902 (0.0008) -[2023-10-15 05:58:21,906][88298] Updated weights for policy 0, policy_version 91330 (0.0007) -[2023-10-15 05:58:22,269][88298] Updated weights for policy 0, policy_version 91340 (0.0009) -[2023-10-15 05:58:22,641][88298] Updated weights for policy 0, policy_version 91350 (0.0010) -[2023-10-15 05:58:23,011][88298] Updated weights for policy 0, policy_version 91360 (0.0008) -[2023-10-15 05:58:23,422][88300] Updated weights for policy 1, policy_version 91912 (0.0010) -[2023-10-15 05:58:23,534][87330] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 187662336. Throughput: 0: 1738.6, 1: 1751.4. Samples: 46923348. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-15 05:58:23,535][87330] Avg episode reward: [(0, '23.050'), (1, '23.070')] -[2023-10-15 05:58:23,793][88300] Updated weights for policy 1, policy_version 91922 (0.0010) -[2023-10-15 05:58:24,162][88300] Updated weights for policy 1, policy_version 91932 (0.0007) -[2023-10-15 05:58:27,121][88298] Updated weights for policy 0, policy_version 91370 (0.0010) -[2023-10-15 05:58:27,487][88298] Updated weights for policy 0, policy_version 91380 (0.0009) -[2023-10-15 05:58:27,864][88298] Updated weights for policy 0, policy_version 91390 (0.0008) -[2023-10-15 05:58:28,229][88300] Updated weights for policy 1, policy_version 91942 (0.0008) -[2023-10-15 05:58:28,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 187727872. Throughput: 0: 1716.8, 1: 1747.8. Samples: 46943180. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-15 05:58:28,534][87330] Avg episode reward: [(0, '23.060'), (1, '23.060')] -[2023-10-15 05:58:28,618][88300] Updated weights for policy 1, policy_version 91952 (0.0010) -[2023-10-15 05:58:28,981][88300] Updated weights for policy 1, policy_version 91962 (0.0009) -[2023-10-15 05:58:31,907][88298] Updated weights for policy 0, policy_version 91400 (0.0008) -[2023-10-15 05:58:32,276][88298] Updated weights for policy 0, policy_version 91410 (0.0008) -[2023-10-15 05:58:32,644][88298] Updated weights for policy 0, policy_version 91420 (0.0009) -[2023-10-15 05:58:32,849][88300] Updated weights for policy 1, policy_version 91972 (0.0008) -[2023-10-15 05:58:33,215][88300] Updated weights for policy 1, policy_version 91982 (0.0011) -[2023-10-15 05:58:33,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13995.8). Total num frames: 187793408. Throughput: 0: 1741.9, 1: 1730.4. Samples: 46953802. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-15 05:58:33,534][87330] Avg episode reward: [(0, '23.030'), (1, '23.060')] -[2023-10-15 05:58:33,592][88300] Updated weights for policy 1, policy_version 91992 (0.0008) -[2023-10-15 05:58:36,792][88298] Updated weights for policy 0, policy_version 91430 (0.0009) -[2023-10-15 05:58:37,169][88298] Updated weights for policy 0, policy_version 91440 (0.0011) -[2023-10-15 05:58:37,539][88298] Updated weights for policy 0, policy_version 91450 (0.0010) -[2023-10-15 05:58:37,576][88300] Updated weights for policy 1, policy_version 92002 (0.0008) -[2023-10-15 05:58:37,951][88300] Updated weights for policy 1, policy_version 92012 (0.0008) -[2023-10-15 05:58:38,313][88300] Updated weights for policy 1, policy_version 92022 (0.0007) -[2023-10-15 05:58:38,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 187858944. Throughput: 0: 1734.0, 1: 1756.9. Samples: 46975088. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-15 05:58:38,535][87330] Avg episode reward: [(0, '22.990'), (1, '22.880')] -[2023-10-15 05:58:38,679][88300] Updated weights for policy 1, policy_version 92032 (0.0008) -[2023-10-15 05:58:41,418][88298] Updated weights for policy 0, policy_version 91460 (0.0009) -[2023-10-15 05:58:41,791][88298] Updated weights for policy 0, policy_version 91470 (0.0009) -[2023-10-15 05:58:42,166][88298] Updated weights for policy 0, policy_version 91480 (0.0010) -[2023-10-15 05:58:42,622][88300] Updated weights for policy 1, policy_version 92042 (0.0009) -[2023-10-15 05:58:42,981][88300] Updated weights for policy 1, policy_version 92052 (0.0011) -[2023-10-15 05:58:43,346][88300] Updated weights for policy 1, policy_version 92062 (0.0010) -[2023-10-15 05:58:43,534][87330] Fps is (10 sec: 16383.5, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 187957248. Throughput: 0: 1703.8, 1: 1735.8. Samples: 46994372. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:58:43,535][87330] Avg episode reward: [(0, '22.570'), (1, '22.650')] -[2023-10-15 05:58:46,114][88298] Updated weights for policy 0, policy_version 91490 (0.0011) -[2023-10-15 05:58:46,482][88298] Updated weights for policy 0, policy_version 91500 (0.0009) -[2023-10-15 05:58:46,843][88298] Updated weights for policy 0, policy_version 91510 (0.0011) -[2023-10-15 05:58:47,129][88300] Updated weights for policy 1, policy_version 92072 (0.0008) -[2023-10-15 05:58:47,209][88298] Updated weights for policy 0, policy_version 91520 (0.0007) -[2023-10-15 05:58:47,493][88300] Updated weights for policy 1, policy_version 92082 (0.0009) -[2023-10-15 05:58:47,859][88300] Updated weights for policy 1, policy_version 92092 (0.0011) -[2023-10-15 05:58:48,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 188022784. Throughput: 0: 1733.4, 1: 1758.8. Samples: 47006206. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:58:48,534][87330] Avg episode reward: [(0, '22.620'), (1, '22.630')] -[2023-10-15 05:58:51,125][88298] Updated weights for policy 0, policy_version 91530 (0.0008) -[2023-10-15 05:58:51,486][88298] Updated weights for policy 0, policy_version 91540 (0.0009) -[2023-10-15 05:58:51,607][88300] Updated weights for policy 1, policy_version 92102 (0.0009) -[2023-10-15 05:58:51,867][88298] Updated weights for policy 0, policy_version 91550 (0.0007) -[2023-10-15 05:58:51,985][88300] Updated weights for policy 1, policy_version 92112 (0.0007) -[2023-10-15 05:58:52,357][88300] Updated weights for policy 1, policy_version 92122 (0.0009) -[2023-10-15 05:58:53,534][87330] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 188088320. Throughput: 0: 1709.2, 1: 1746.7. Samples: 47025982. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:58:53,534][87330] Avg episode reward: [(0, '22.650'), (1, '22.620')] -[2023-10-15 05:58:55,626][88298] Updated weights for policy 0, policy_version 91560 (0.0009) -[2023-10-15 05:58:56,001][88298] Updated weights for policy 0, policy_version 91570 (0.0010) -[2023-10-15 05:58:56,169][88300] Updated weights for policy 1, policy_version 92132 (0.0009) -[2023-10-15 05:58:56,361][88298] Updated weights for policy 0, policy_version 91580 (0.0010) -[2023-10-15 05:58:56,533][88300] Updated weights for policy 1, policy_version 92142 (0.0007) -[2023-10-15 05:58:56,897][88300] Updated weights for policy 1, policy_version 92152 (0.0009) -[2023-10-15 05:58:58,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 188153856. Throughput: 0: 1713.3, 1: 1728.8. Samples: 47046796. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:58:58,534][87330] Avg episode reward: [(0, '22.670'), (1, '22.620')] -[2023-10-15 05:58:58,542][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000091584_93782016.pth... -[2023-10-15 05:58:58,542][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000092160_94371840.pth... -[2023-10-15 05:58:58,580][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000089952_92110848.pth -[2023-10-15 05:58:58,582][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000090528_92700672.pth -[2023-10-15 05:59:00,262][88298] Updated weights for policy 0, policy_version 91590 (0.0009) -[2023-10-15 05:59:00,642][88298] Updated weights for policy 0, policy_version 91600 (0.0009) -[2023-10-15 05:59:00,815][88300] Updated weights for policy 1, policy_version 92162 (0.0008) -[2023-10-15 05:59:01,006][88298] Updated weights for policy 0, policy_version 91610 (0.0009) -[2023-10-15 05:59:01,178][88300] Updated weights for policy 1, policy_version 92172 (0.0008) -[2023-10-15 05:59:01,545][88300] Updated weights for policy 1, policy_version 92182 (0.0008) -[2023-10-15 05:59:01,918][88300] Updated weights for policy 1, policy_version 92192 (0.0008) -[2023-10-15 05:59:03,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 188219392. Throughput: 0: 1716.4, 1: 1749.9. Samples: 47057772. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:59:03,534][87330] Avg episode reward: [(0, '22.640'), (1, '22.610')] -[2023-10-15 05:59:05,018][88298] Updated weights for policy 0, policy_version 91620 (0.0007) -[2023-10-15 05:59:05,380][88298] Updated weights for policy 0, policy_version 91630 (0.0011) -[2023-10-15 05:59:05,751][88298] Updated weights for policy 0, policy_version 91640 (0.0007) -[2023-10-15 05:59:05,839][88300] Updated weights for policy 1, policy_version 92202 (0.0008) -[2023-10-15 05:59:06,194][88300] Updated weights for policy 1, policy_version 92212 (0.0007) -[2023-10-15 05:59:06,569][88300] Updated weights for policy 1, policy_version 92222 (0.0007) -[2023-10-15 05:59:08,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 188284928. Throughput: 0: 1706.8, 1: 1729.6. Samples: 47077988. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:59:08,535][87330] Avg episode reward: [(0, '22.700'), (1, '22.660')] -[2023-10-15 05:59:09,704][88298] Updated weights for policy 0, policy_version 91650 (0.0008) -[2023-10-15 05:59:10,070][88298] Updated weights for policy 0, policy_version 91660 (0.0009) -[2023-10-15 05:59:10,443][88298] Updated weights for policy 0, policy_version 91670 (0.0009) -[2023-10-15 05:59:10,472][88300] Updated weights for policy 1, policy_version 92232 (0.0008) -[2023-10-15 05:59:10,802][88298] Updated weights for policy 0, policy_version 91680 (0.0008) -[2023-10-15 05:59:10,836][88300] Updated weights for policy 1, policy_version 92242 (0.0007) -[2023-10-15 05:59:11,207][88300] Updated weights for policy 1, policy_version 92252 (0.0008) -[2023-10-15 05:59:13,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 188350464. Throughput: 0: 1734.5, 1: 1741.1. Samples: 47099580. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:59:13,534][87330] Avg episode reward: [(0, '23.150'), (1, '22.870')] -[2023-10-15 05:59:14,637][88298] Updated weights for policy 0, policy_version 91690 (0.0009) -[2023-10-15 05:59:15,016][88298] Updated weights for policy 0, policy_version 91700 (0.0010) -[2023-10-15 05:59:15,247][88300] Updated weights for policy 1, policy_version 92262 (0.0007) -[2023-10-15 05:59:15,377][88298] Updated weights for policy 0, policy_version 91710 (0.0008) -[2023-10-15 05:59:15,623][88300] Updated weights for policy 1, policy_version 92272 (0.0009) -[2023-10-15 05:59:15,989][88300] Updated weights for policy 1, policy_version 92282 (0.0010) -[2023-10-15 05:59:18,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 188416000. Throughput: 0: 1710.6, 1: 1736.9. Samples: 47108940. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:59:18,534][87330] Avg episode reward: [(0, '22.960'), (1, '22.860')] -[2023-10-15 05:59:19,308][88298] Updated weights for policy 0, policy_version 91720 (0.0007) -[2023-10-15 05:59:19,677][88298] Updated weights for policy 0, policy_version 91730 (0.0007) -[2023-10-15 05:59:19,807][88300] Updated weights for policy 1, policy_version 92292 (0.0008) -[2023-10-15 05:59:20,048][88298] Updated weights for policy 0, policy_version 91740 (0.0009) -[2023-10-15 05:59:20,184][88300] Updated weights for policy 1, policy_version 92302 (0.0008) -[2023-10-15 05:59:20,548][88300] Updated weights for policy 1, policy_version 92312 (0.0008) -[2023-10-15 05:59:23,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 188481536. Throughput: 0: 1723.5, 1: 1729.3. Samples: 47130464. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:59:23,534][87330] Avg episode reward: [(0, '22.880'), (1, '22.860')] -[2023-10-15 05:59:23,874][88298] Updated weights for policy 0, policy_version 91750 (0.0007) -[2023-10-15 05:59:24,249][88298] Updated weights for policy 0, policy_version 91760 (0.0011) -[2023-10-15 05:59:24,562][88300] Updated weights for policy 1, policy_version 92322 (0.0009) -[2023-10-15 05:59:24,615][88298] Updated weights for policy 0, policy_version 91770 (0.0008) -[2023-10-15 05:59:24,927][88300] Updated weights for policy 1, policy_version 92332 (0.0007) -[2023-10-15 05:59:25,298][88300] Updated weights for policy 1, policy_version 92342 (0.0011) -[2023-10-15 05:59:25,660][88300] Updated weights for policy 1, policy_version 92352 (0.0011) -[2023-10-15 05:59:28,534][87330] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 188547072. Throughput: 0: 1754.0, 1: 1753.0. Samples: 47152186. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:59:28,535][87330] Avg episode reward: [(0, '22.860'), (1, '22.860')] -[2023-10-15 05:59:28,558][88298] Updated weights for policy 0, policy_version 91780 (0.0009) -[2023-10-15 05:59:28,923][88298] Updated weights for policy 0, policy_version 91790 (0.0008) -[2023-10-15 05:59:29,296][88298] Updated weights for policy 0, policy_version 91800 (0.0010) -[2023-10-15 05:59:29,447][88300] Updated weights for policy 1, policy_version 92362 (0.0008) -[2023-10-15 05:59:29,814][88300] Updated weights for policy 1, policy_version 92372 (0.0007) -[2023-10-15 05:59:30,186][88300] Updated weights for policy 1, policy_version 92382 (0.0007) -[2023-10-15 05:59:33,278][88298] Updated weights for policy 0, policy_version 91810 (0.0009) -[2023-10-15 05:59:33,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 188612608. Throughput: 0: 1722.8, 1: 1730.9. Samples: 47161624. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:59:33,534][87330] Avg episode reward: [(0, '22.860'), (1, '22.860')] -[2023-10-15 05:59:33,655][88298] Updated weights for policy 0, policy_version 91820 (0.0008) -[2023-10-15 05:59:34,019][88298] Updated weights for policy 0, policy_version 91830 (0.0007) -[2023-10-15 05:59:34,190][88300] Updated weights for policy 1, policy_version 92392 (0.0007) -[2023-10-15 05:59:34,391][88298] Updated weights for policy 0, policy_version 91840 (0.0009) -[2023-10-15 05:59:34,556][88300] Updated weights for policy 1, policy_version 92402 (0.0008) -[2023-10-15 05:59:34,916][88300] Updated weights for policy 1, policy_version 92412 (0.0008) -[2023-10-15 05:59:38,361][88298] Updated weights for policy 0, policy_version 91850 (0.0008) -[2023-10-15 05:59:38,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 188678144. Throughput: 0: 1747.0, 1: 1737.7. Samples: 47182794. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 05:59:38,534][87330] Avg episode reward: [(0, '22.860'), (1, '22.970')] -[2023-10-15 05:59:38,726][88298] Updated weights for policy 0, policy_version 91860 (0.0007) -[2023-10-15 05:59:38,903][88300] Updated weights for policy 1, policy_version 92422 (0.0008) -[2023-10-15 05:59:39,089][88298] Updated weights for policy 0, policy_version 91870 (0.0009) -[2023-10-15 05:59:39,259][88300] Updated weights for policy 1, policy_version 92432 (0.0009) -[2023-10-15 05:59:39,621][88300] Updated weights for policy 1, policy_version 92442 (0.0009) -[2023-10-15 05:59:42,901][88298] Updated weights for policy 0, policy_version 91880 (0.0009) -[2023-10-15 05:59:43,282][88298] Updated weights for policy 0, policy_version 91890 (0.0009) -[2023-10-15 05:59:43,467][88300] Updated weights for policy 1, policy_version 92452 (0.0009) -[2023-10-15 05:59:43,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13884.7). Total num frames: 188743680. Throughput: 0: 1750.0, 1: 1751.3. Samples: 47204354. Policy #0 lag: (min: 8.0, avg: 34.4, max: 40.0) -[2023-10-15 05:59:43,535][87330] Avg episode reward: [(0, '22.860'), (1, '22.940')] -[2023-10-15 05:59:43,655][88298] Updated weights for policy 0, policy_version 91900 (0.0008) -[2023-10-15 05:59:43,829][88300] Updated weights for policy 1, policy_version 92462 (0.0008) -[2023-10-15 05:59:44,203][88300] Updated weights for policy 1, policy_version 92472 (0.0009) -[2023-10-15 05:59:47,611][88298] Updated weights for policy 0, policy_version 91910 (0.0009) -[2023-10-15 05:59:47,980][88298] Updated weights for policy 0, policy_version 91920 (0.0010) -[2023-10-15 05:59:48,013][88300] Updated weights for policy 1, policy_version 92482 (0.0009) -[2023-10-15 05:59:48,350][88298] Updated weights for policy 0, policy_version 91930 (0.0010) -[2023-10-15 05:59:48,375][88300] Updated weights for policy 1, policy_version 92492 (0.0007) -[2023-10-15 05:59:48,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 188809216. Throughput: 0: 1736.8, 1: 1730.1. Samples: 47213784. Policy #0 lag: (min: 8.0, avg: 34.4, max: 40.0) -[2023-10-15 05:59:48,534][87330] Avg episode reward: [(0, '22.840'), (1, '22.780')] -[2023-10-15 05:59:48,751][88300] Updated weights for policy 1, policy_version 92502 (0.0008) -[2023-10-15 05:59:49,115][88300] Updated weights for policy 1, policy_version 92512 (0.0009) -[2023-10-15 05:59:52,216][88298] Updated weights for policy 0, policy_version 91940 (0.0009) -[2023-10-15 05:59:52,590][88298] Updated weights for policy 0, policy_version 91950 (0.0008) -[2023-10-15 05:59:52,949][88300] Updated weights for policy 1, policy_version 92522 (0.0009) -[2023-10-15 05:59:52,961][88298] Updated weights for policy 0, policy_version 91960 (0.0007) -[2023-10-15 05:59:53,321][88300] Updated weights for policy 1, policy_version 92532 (0.0008) -[2023-10-15 05:59:53,534][87330] Fps is (10 sec: 16384.3, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 188907520. Throughput: 0: 1745.1, 1: 1755.9. Samples: 47235534. Policy #0 lag: (min: 8.0, avg: 34.4, max: 40.0) -[2023-10-15 05:59:53,535][87330] Avg episode reward: [(0, '23.000'), (1, '22.600')] -[2023-10-15 05:59:53,692][88300] Updated weights for policy 1, policy_version 92542 (0.0007) -[2023-10-15 05:59:56,828][88298] Updated weights for policy 0, policy_version 91970 (0.0007) -[2023-10-15 05:59:57,196][88298] Updated weights for policy 0, policy_version 91980 (0.0008) -[2023-10-15 05:59:57,498][88300] Updated weights for policy 1, policy_version 92552 (0.0008) -[2023-10-15 05:59:57,559][88298] Updated weights for policy 0, policy_version 91990 (0.0008) -[2023-10-15 05:59:57,855][88300] Updated weights for policy 1, policy_version 92562 (0.0008) -[2023-10-15 05:59:57,930][88298] Updated weights for policy 0, policy_version 92000 (0.0008) -[2023-10-15 05:59:58,227][88300] Updated weights for policy 1, policy_version 92572 (0.0010) -[2023-10-15 05:59:58,534][87330] Fps is (10 sec: 19661.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 189005824. Throughput: 0: 1718.0, 1: 1734.1. Samples: 47254928. Policy #0 lag: (min: 8.0, avg: 34.4, max: 40.0) -[2023-10-15 05:59:58,534][87330] Avg episode reward: [(0, '23.020'), (1, '22.610')] -[2023-10-15 06:00:01,986][88298] Updated weights for policy 0, policy_version 92010 (0.0010) -[2023-10-15 06:00:02,341][88298] Updated weights for policy 0, policy_version 92020 (0.0009) -[2023-10-15 06:00:02,361][88300] Updated weights for policy 1, policy_version 92582 (0.0009) -[2023-10-15 06:00:02,715][88298] Updated weights for policy 0, policy_version 92030 (0.0008) -[2023-10-15 06:00:02,744][88300] Updated weights for policy 1, policy_version 92592 (0.0008) -[2023-10-15 06:00:03,111][88300] Updated weights for policy 1, policy_version 92602 (0.0007) -[2023-10-15 06:00:03,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 189071360. Throughput: 0: 1746.3, 1: 1750.8. Samples: 47266308. Policy #0 lag: (min: 8.0, avg: 34.4, max: 40.0) -[2023-10-15 06:00:03,535][87330] Avg episode reward: [(0, '22.970'), (1, '22.620')] -[2023-10-15 06:00:06,635][88298] Updated weights for policy 0, policy_version 92040 (0.0008) -[2023-10-15 06:00:07,006][88300] Updated weights for policy 1, policy_version 92612 (0.0007) -[2023-10-15 06:00:07,009][88298] Updated weights for policy 0, policy_version 92050 (0.0007) -[2023-10-15 06:00:07,371][88298] Updated weights for policy 0, policy_version 92060 (0.0009) -[2023-10-15 06:00:07,376][88300] Updated weights for policy 1, policy_version 92622 (0.0008) -[2023-10-15 06:00:07,742][88300] Updated weights for policy 1, policy_version 92632 (0.0007) -[2023-10-15 06:00:08,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 189136896. Throughput: 0: 1732.4, 1: 1743.0. Samples: 47286856. Policy #0 lag: (min: 8.0, avg: 34.4, max: 40.0) -[2023-10-15 06:00:08,535][87330] Avg episode reward: [(0, '22.940'), (1, '22.610')] -[2023-10-15 06:00:11,400][88298] Updated weights for policy 0, policy_version 92070 (0.0008) -[2023-10-15 06:00:11,496][88300] Updated weights for policy 1, policy_version 92642 (0.0011) -[2023-10-15 06:00:11,783][88298] Updated weights for policy 0, policy_version 92080 (0.0008) -[2023-10-15 06:00:11,857][88300] Updated weights for policy 1, policy_version 92652 (0.0007) -[2023-10-15 06:00:12,150][88298] Updated weights for policy 0, policy_version 92090 (0.0009) -[2023-10-15 06:00:12,229][88300] Updated weights for policy 1, policy_version 92662 (0.0008) -[2023-10-15 06:00:12,592][88300] Updated weights for policy 1, policy_version 92672 (0.0008) -[2023-10-15 06:00:13,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 189202432. Throughput: 0: 1704.4, 1: 1724.8. Samples: 47306500. Policy #0 lag: (min: 8.0, avg: 34.4, max: 40.0) -[2023-10-15 06:00:13,535][87330] Avg episode reward: [(0, '22.930'), (1, '22.650')] -[2023-10-15 06:00:16,194][88298] Updated weights for policy 0, policy_version 92100 (0.0007) -[2023-10-15 06:00:16,362][88300] Updated weights for policy 1, policy_version 92682 (0.0008) -[2023-10-15 06:00:16,557][88298] Updated weights for policy 0, policy_version 92110 (0.0009) -[2023-10-15 06:00:16,734][88300] Updated weights for policy 1, policy_version 92692 (0.0009) -[2023-10-15 06:00:16,915][88298] Updated weights for policy 0, policy_version 92120 (0.0008) -[2023-10-15 06:00:17,091][88300] Updated weights for policy 1, policy_version 92702 (0.0010) -[2023-10-15 06:00:18,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 189267968. Throughput: 0: 1730.8, 1: 1751.1. Samples: 47318312. Policy #0 lag: (min: 8.0, avg: 34.4, max: 40.0) -[2023-10-15 06:00:18,535][87330] Avg episode reward: [(0, '22.890'), (1, '22.660')] -[2023-10-15 06:00:20,982][88298] Updated weights for policy 0, policy_version 92130 (0.0009) -[2023-10-15 06:00:21,075][88300] Updated weights for policy 1, policy_version 92712 (0.0008) -[2023-10-15 06:00:21,341][88298] Updated weights for policy 0, policy_version 92140 (0.0008) -[2023-10-15 06:00:21,438][88300] Updated weights for policy 1, policy_version 92722 (0.0007) -[2023-10-15 06:00:21,710][88298] Updated weights for policy 0, policy_version 92150 (0.0008) -[2023-10-15 06:00:21,802][88300] Updated weights for policy 1, policy_version 92732 (0.0007) -[2023-10-15 06:00:22,078][88298] Updated weights for policy 0, policy_version 92160 (0.0007) -[2023-10-15 06:00:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 189333504. Throughput: 0: 1710.1, 1: 1734.4. Samples: 47337798. Policy #0 lag: (min: 8.0, avg: 34.4, max: 40.0) -[2023-10-15 06:00:23,534][87330] Avg episode reward: [(0, '22.900'), (1, '22.980')] -[2023-10-15 06:00:25,682][88300] Updated weights for policy 1, policy_version 92742 (0.0009) -[2023-10-15 06:00:26,014][88298] Updated weights for policy 0, policy_version 92170 (0.0007) -[2023-10-15 06:00:26,042][88300] Updated weights for policy 1, policy_version 92752 (0.0008) -[2023-10-15 06:00:26,384][88298] Updated weights for policy 0, policy_version 92180 (0.0008) -[2023-10-15 06:00:26,416][88300] Updated weights for policy 1, policy_version 92762 (0.0007) -[2023-10-15 06:00:26,744][88298] Updated weights for policy 0, policy_version 92190 (0.0009) -[2023-10-15 06:00:28,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 189399040. Throughput: 0: 1705.4, 1: 1734.1. Samples: 47359132. Policy #0 lag: (min: 8.0, avg: 34.4, max: 40.0) -[2023-10-15 06:00:28,534][87330] Avg episode reward: [(0, '22.900'), (1, '22.890')] -[2023-10-15 06:00:30,253][88300] Updated weights for policy 1, policy_version 92772 (0.0008) -[2023-10-15 06:00:30,583][88298] Updated weights for policy 0, policy_version 92200 (0.0007) -[2023-10-15 06:00:30,617][88300] Updated weights for policy 1, policy_version 92782 (0.0007) -[2023-10-15 06:00:30,949][88298] Updated weights for policy 0, policy_version 92210 (0.0009) -[2023-10-15 06:00:30,988][88300] Updated weights for policy 1, policy_version 92792 (0.0008) -[2023-10-15 06:00:31,322][88298] Updated weights for policy 0, policy_version 92220 (0.0009) -[2023-10-15 06:00:33,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 189464576. Throughput: 0: 1724.4, 1: 1736.6. Samples: 47369528. Policy #0 lag: (min: 8.0, avg: 34.4, max: 40.0) -[2023-10-15 06:00:33,534][87330] Avg episode reward: [(0, '22.960'), (1, '22.860')] -[2023-10-15 06:00:34,903][88300] Updated weights for policy 1, policy_version 92802 (0.0009) -[2023-10-15 06:00:35,102][88298] Updated weights for policy 0, policy_version 92230 (0.0008) -[2023-10-15 06:00:35,269][88300] Updated weights for policy 1, policy_version 92812 (0.0008) -[2023-10-15 06:00:35,476][88298] Updated weights for policy 0, policy_version 92240 (0.0007) -[2023-10-15 06:00:35,636][88300] Updated weights for policy 1, policy_version 92822 (0.0008) -[2023-10-15 06:00:35,837][88298] Updated weights for policy 0, policy_version 92250 (0.0007) -[2023-10-15 06:00:35,997][88300] Updated weights for policy 1, policy_version 92832 (0.0008) -[2023-10-15 06:00:38,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 189530112. Throughput: 0: 1704.2, 1: 1723.1. Samples: 47389766. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-15 06:00:38,535][87330] Avg episode reward: [(0, '23.000'), (1, '22.870')] -[2023-10-15 06:00:39,682][88298] Updated weights for policy 0, policy_version 92260 (0.0007) -[2023-10-15 06:00:39,989][88300] Updated weights for policy 1, policy_version 92842 (0.0008) -[2023-10-15 06:00:40,051][88298] Updated weights for policy 0, policy_version 92270 (0.0008) -[2023-10-15 06:00:40,355][88300] Updated weights for policy 1, policy_version 92852 (0.0008) -[2023-10-15 06:00:40,415][88298] Updated weights for policy 0, policy_version 92280 (0.0007) -[2023-10-15 06:00:40,722][88300] Updated weights for policy 1, policy_version 92862 (0.0007) -[2023-10-15 06:00:43,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 189595648. Throughput: 0: 1736.3, 1: 1747.2. Samples: 47411682. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-15 06:00:43,534][87330] Avg episode reward: [(0, '23.030'), (1, '22.890')] -[2023-10-15 06:00:44,404][88298] Updated weights for policy 0, policy_version 92290 (0.0007) -[2023-10-15 06:00:44,593][88300] Updated weights for policy 1, policy_version 92872 (0.0008) -[2023-10-15 06:00:44,774][88298] Updated weights for policy 0, policy_version 92300 (0.0009) -[2023-10-15 06:00:44,971][88300] Updated weights for policy 1, policy_version 92882 (0.0007) -[2023-10-15 06:00:45,150][88298] Updated weights for policy 0, policy_version 92310 (0.0010) -[2023-10-15 06:00:45,339][88300] Updated weights for policy 1, policy_version 92892 (0.0008) -[2023-10-15 06:00:45,519][88298] Updated weights for policy 0, policy_version 92320 (0.0007) -[2023-10-15 06:00:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 189661184. Throughput: 0: 1710.1, 1: 1727.3. Samples: 47420992. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-15 06:00:48,535][87330] Avg episode reward: [(0, '23.070'), (1, '22.930')] -[2023-10-15 06:00:49,335][88298] Updated weights for policy 0, policy_version 92330 (0.0007) -[2023-10-15 06:00:49,530][88300] Updated weights for policy 1, policy_version 92902 (0.0007) -[2023-10-15 06:00:49,713][88298] Updated weights for policy 0, policy_version 92340 (0.0009) -[2023-10-15 06:00:49,913][88300] Updated weights for policy 1, policy_version 92912 (0.0007) -[2023-10-15 06:00:50,085][88298] Updated weights for policy 0, policy_version 92350 (0.0008) -[2023-10-15 06:00:50,285][88300] Updated weights for policy 1, policy_version 92922 (0.0007) -[2023-10-15 06:00:53,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 189726720. Throughput: 0: 1724.1, 1: 1733.9. Samples: 47442466. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-15 06:00:53,534][87330] Avg episode reward: [(0, '23.050'), (1, '22.900')] -[2023-10-15 06:00:53,897][88298] Updated weights for policy 0, policy_version 92360 (0.0009) -[2023-10-15 06:00:54,014][88300] Updated weights for policy 1, policy_version 92932 (0.0008) -[2023-10-15 06:00:54,259][88298] Updated weights for policy 0, policy_version 92370 (0.0010) -[2023-10-15 06:00:54,378][88300] Updated weights for policy 1, policy_version 92942 (0.0008) -[2023-10-15 06:00:54,629][88298] Updated weights for policy 0, policy_version 92380 (0.0008) -[2023-10-15 06:00:54,742][88300] Updated weights for policy 1, policy_version 92952 (0.0008) -[2023-10-15 06:00:58,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13884.7). Total num frames: 189792256. Throughput: 0: 1750.8, 1: 1752.1. Samples: 47464134. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-15 06:00:58,535][87330] Avg episode reward: [(0, '23.050'), (1, '23.010')] -[2023-10-15 06:00:58,692][88300] Updated weights for policy 1, policy_version 92962 (0.0008) -[2023-10-15 06:00:58,777][88298] Updated weights for policy 0, policy_version 92390 (0.0008) -[2023-10-15 06:00:59,054][88300] Updated weights for policy 1, policy_version 92972 (0.0007) -[2023-10-15 06:00:59,157][88298] Updated weights for policy 0, policy_version 92400 (0.0009) -[2023-10-15 06:00:59,422][88300] Updated weights for policy 1, policy_version 92982 (0.0007) -[2023-10-15 06:00:59,526][88298] Updated weights for policy 0, policy_version 92410 (0.0007) -[2023-10-15 06:00:59,737][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000092416_94633984.pth... -[2023-10-15 06:00:59,767][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000090784_92962816.pth -[2023-10-15 06:00:59,783][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000092992_95223808.pth... -[2023-10-15 06:00:59,787][88300] Updated weights for policy 1, policy_version 92992 (0.0009) -[2023-10-15 06:00:59,821][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000091328_93519872.pth -[2023-10-15 06:01:03,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 189857792. Throughput: 0: 1722.8, 1: 1725.4. Samples: 47473480. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-15 06:01:03,535][87330] Avg episode reward: [(0, '23.040'), (1, '22.990')] -[2023-10-15 06:01:03,702][88298] Updated weights for policy 0, policy_version 92420 (0.0007) -[2023-10-15 06:01:03,762][88300] Updated weights for policy 1, policy_version 93002 (0.0007) -[2023-10-15 06:01:04,080][88298] Updated weights for policy 0, policy_version 92430 (0.0009) -[2023-10-15 06:01:04,134][88300] Updated weights for policy 1, policy_version 93012 (0.0009) -[2023-10-15 06:01:04,451][88298] Updated weights for policy 0, policy_version 92440 (0.0008) -[2023-10-15 06:01:04,509][88300] Updated weights for policy 1, policy_version 93022 (0.0008) -[2023-10-15 06:01:08,247][88298] Updated weights for policy 0, policy_version 92450 (0.0008) -[2023-10-15 06:01:08,437][88300] Updated weights for policy 1, policy_version 93032 (0.0009) -[2023-10-15 06:01:08,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13107.3, 300 sec: 13773.7). Total num frames: 189923328. Throughput: 0: 1742.2, 1: 1745.5. Samples: 47494746. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-15 06:01:08,534][87330] Avg episode reward: [(0, '23.000'), (1, '23.020')] -[2023-10-15 06:01:08,608][88298] Updated weights for policy 0, policy_version 92460 (0.0007) -[2023-10-15 06:01:08,791][88300] Updated weights for policy 1, policy_version 93042 (0.0008) -[2023-10-15 06:01:08,988][88298] Updated weights for policy 0, policy_version 92470 (0.0008) -[2023-10-15 06:01:09,160][88300] Updated weights for policy 1, policy_version 93052 (0.0009) -[2023-10-15 06:01:09,355][88298] Updated weights for policy 0, policy_version 92480 (0.0008) -[2023-10-15 06:01:13,084][88300] Updated weights for policy 1, policy_version 93062 (0.0010) -[2023-10-15 06:01:13,119][88298] Updated weights for policy 0, policy_version 92490 (0.0010) -[2023-10-15 06:01:13,441][88300] Updated weights for policy 1, policy_version 93072 (0.0007) -[2023-10-15 06:01:13,494][88298] Updated weights for policy 0, policy_version 92500 (0.0008) -[2023-10-15 06:01:13,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 189988864. Throughput: 0: 1746.9, 1: 1734.8. Samples: 47515808. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-15 06:01:13,534][87330] Avg episode reward: [(0, '23.060'), (1, '23.000')] -[2023-10-15 06:01:13,806][88300] Updated weights for policy 1, policy_version 93082 (0.0007) -[2023-10-15 06:01:13,849][88298] Updated weights for policy 0, policy_version 92510 (0.0007) -[2023-10-15 06:01:17,788][88300] Updated weights for policy 1, policy_version 93092 (0.0007) -[2023-10-15 06:01:18,015][88298] Updated weights for policy 0, policy_version 92520 (0.0008) -[2023-10-15 06:01:18,155][88300] Updated weights for policy 1, policy_version 93102 (0.0007) -[2023-10-15 06:01:18,390][88298] Updated weights for policy 0, policy_version 92530 (0.0008) -[2023-10-15 06:01:18,523][88300] Updated weights for policy 1, policy_version 93112 (0.0007) -[2023-10-15 06:01:18,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 190054400. Throughput: 0: 1726.0, 1: 1742.8. Samples: 47525620. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-15 06:01:18,534][87330] Avg episode reward: [(0, '23.080'), (1, '23.000')] -[2023-10-15 06:01:18,755][88298] Updated weights for policy 0, policy_version 92540 (0.0007) -[2023-10-15 06:01:22,427][88300] Updated weights for policy 1, policy_version 93122 (0.0008) -[2023-10-15 06:01:22,793][88300] Updated weights for policy 1, policy_version 93132 (0.0008) -[2023-10-15 06:01:22,806][88298] Updated weights for policy 0, policy_version 92550 (0.0007) -[2023-10-15 06:01:23,165][88300] Updated weights for policy 1, policy_version 93142 (0.0007) -[2023-10-15 06:01:23,175][88298] Updated weights for policy 0, policy_version 92560 (0.0007) -[2023-10-15 06:01:23,526][88300] Updated weights for policy 1, policy_version 93152 (0.0009) -[2023-10-15 06:01:23,534][87330] Fps is (10 sec: 16384.2, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 190152704. Throughput: 0: 1740.9, 1: 1748.8. Samples: 47546800. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-15 06:01:23,534][87330] Avg episode reward: [(0, '23.070'), (1, '23.030')] -[2023-10-15 06:01:23,542][88298] Updated weights for policy 0, policy_version 92570 (0.0007) -[2023-10-15 06:01:27,347][88298] Updated weights for policy 0, policy_version 92580 (0.0008) -[2023-10-15 06:01:27,523][88300] Updated weights for policy 1, policy_version 93162 (0.0009) -[2023-10-15 06:01:27,718][88298] Updated weights for policy 0, policy_version 92590 (0.0008) -[2023-10-15 06:01:27,890][88300] Updated weights for policy 1, policy_version 93172 (0.0008) -[2023-10-15 06:01:28,086][88298] Updated weights for policy 0, policy_version 92600 (0.0008) -[2023-10-15 06:01:28,253][88300] Updated weights for policy 1, policy_version 93182 (0.0007) -[2023-10-15 06:01:28,534][87330] Fps is (10 sec: 19660.7, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 190251008. Throughput: 0: 1722.5, 1: 1716.7. Samples: 47566446. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-15 06:01:28,534][87330] Avg episode reward: [(0, '23.100'), (1, '23.010')] -[2023-10-15 06:01:32,090][88298] Updated weights for policy 0, policy_version 92610 (0.0008) -[2023-10-15 06:01:32,199][88300] Updated weights for policy 1, policy_version 93192 (0.0009) -[2023-10-15 06:01:32,453][88298] Updated weights for policy 0, policy_version 92620 (0.0007) -[2023-10-15 06:01:32,559][88300] Updated weights for policy 1, policy_version 93202 (0.0010) -[2023-10-15 06:01:32,830][88298] Updated weights for policy 0, policy_version 92630 (0.0009) -[2023-10-15 06:01:32,928][88300] Updated weights for policy 1, policy_version 93212 (0.0010) -[2023-10-15 06:01:33,192][88298] Updated weights for policy 0, policy_version 92640 (0.0008) -[2023-10-15 06:01:33,534][87330] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 190316544. Throughput: 0: 1734.2, 1: 1744.0. Samples: 47577512. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-15 06:01:33,535][87330] Avg episode reward: [(0, '23.080'), (1, '23.050')] -[2023-10-15 06:01:37,030][88300] Updated weights for policy 1, policy_version 93222 (0.0009) -[2023-10-15 06:01:37,244][88298] Updated weights for policy 0, policy_version 92650 (0.0008) -[2023-10-15 06:01:37,422][88300] Updated weights for policy 1, policy_version 93232 (0.0009) -[2023-10-15 06:01:37,609][88298] Updated weights for policy 0, policy_version 92660 (0.0010) -[2023-10-15 06:01:37,787][88300] Updated weights for policy 1, policy_version 93242 (0.0008) -[2023-10-15 06:01:37,974][88298] Updated weights for policy 0, policy_version 92670 (0.0007) -[2023-10-15 06:01:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 190382080. Throughput: 0: 1725.9, 1: 1733.4. Samples: 47598136. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-15 06:01:38,534][87330] Avg episode reward: [(0, '23.090'), (1, '22.920')] -[2023-10-15 06:01:41,678][88300] Updated weights for policy 1, policy_version 93252 (0.0008) -[2023-10-15 06:01:41,863][88298] Updated weights for policy 0, policy_version 92680 (0.0009) -[2023-10-15 06:01:42,036][88300] Updated weights for policy 1, policy_version 93262 (0.0007) -[2023-10-15 06:01:42,236][88298] Updated weights for policy 0, policy_version 92690 (0.0009) -[2023-10-15 06:01:42,404][88300] Updated weights for policy 1, policy_version 93272 (0.0007) -[2023-10-15 06:01:42,596][88298] Updated weights for policy 0, policy_version 92700 (0.0010) -[2023-10-15 06:01:43,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 190447616. Throughput: 0: 1695.7, 1: 1706.6. Samples: 47617234. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-15 06:01:43,534][87330] Avg episode reward: [(0, '23.050'), (1, '22.920')] -[2023-10-15 06:01:46,253][88300] Updated weights for policy 1, policy_version 93282 (0.0007) -[2023-10-15 06:01:46,592][88298] Updated weights for policy 0, policy_version 92710 (0.0009) -[2023-10-15 06:01:46,624][88300] Updated weights for policy 1, policy_version 93292 (0.0007) -[2023-10-15 06:01:46,974][88298] Updated weights for policy 0, policy_version 92720 (0.0008) -[2023-10-15 06:01:46,990][88300] Updated weights for policy 1, policy_version 93302 (0.0008) -[2023-10-15 06:01:47,339][88298] Updated weights for policy 0, policy_version 92730 (0.0008) -[2023-10-15 06:01:47,354][88300] Updated weights for policy 1, policy_version 93312 (0.0008) -[2023-10-15 06:01:48,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 190513152. Throughput: 0: 1729.8, 1: 1739.6. Samples: 47629604. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-15 06:01:48,534][87330] Avg episode reward: [(0, '22.980'), (1, '22.910')] -[2023-10-15 06:01:51,109][88298] Updated weights for policy 0, policy_version 92740 (0.0009) -[2023-10-15 06:01:51,137][88300] Updated weights for policy 1, policy_version 93322 (0.0008) -[2023-10-15 06:01:51,472][88298] Updated weights for policy 0, policy_version 92750 (0.0008) -[2023-10-15 06:01:51,493][88300] Updated weights for policy 1, policy_version 93332 (0.0009) -[2023-10-15 06:01:51,845][88298] Updated weights for policy 0, policy_version 92760 (0.0007) -[2023-10-15 06:01:51,855][88300] Updated weights for policy 1, policy_version 93342 (0.0007) -[2023-10-15 06:01:53,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13884.8). Total num frames: 190578688. Throughput: 0: 1709.5, 1: 1716.8. Samples: 47648928. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-15 06:01:53,535][87330] Avg episode reward: [(0, '23.000'), (1, '22.890')] -[2023-10-15 06:01:55,709][88300] Updated weights for policy 1, policy_version 93352 (0.0009) -[2023-10-15 06:01:55,739][88298] Updated weights for policy 0, policy_version 92770 (0.0007) -[2023-10-15 06:01:56,065][88300] Updated weights for policy 1, policy_version 93362 (0.0007) -[2023-10-15 06:01:56,115][88298] Updated weights for policy 0, policy_version 92780 (0.0008) -[2023-10-15 06:01:56,431][88300] Updated weights for policy 1, policy_version 93372 (0.0009) -[2023-10-15 06:01:56,477][88298] Updated weights for policy 0, policy_version 92790 (0.0008) -[2023-10-15 06:01:56,853][88298] Updated weights for policy 0, policy_version 92800 (0.0008) -[2023-10-15 06:01:58,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 190644224. Throughput: 0: 1703.2, 1: 1726.7. Samples: 47670154. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-15 06:01:58,534][87330] Avg episode reward: [(0, '22.780'), (1, '22.920')] -[2023-10-15 06:02:00,413][88300] Updated weights for policy 1, policy_version 93382 (0.0007) -[2023-10-15 06:02:00,682][88298] Updated weights for policy 0, policy_version 92810 (0.0007) -[2023-10-15 06:02:00,780][88300] Updated weights for policy 1, policy_version 93392 (0.0008) -[2023-10-15 06:02:01,051][88298] Updated weights for policy 0, policy_version 92820 (0.0008) -[2023-10-15 06:02:01,152][88300] Updated weights for policy 1, policy_version 93402 (0.0009) -[2023-10-15 06:02:01,423][88298] Updated weights for policy 0, policy_version 92830 (0.0009) -[2023-10-15 06:02:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 190709760. Throughput: 0: 1727.1, 1: 1720.3. Samples: 47680750. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-15 06:02:03,535][87330] Avg episode reward: [(0, '22.780'), (1, '22.830')] -[2023-10-15 06:02:04,910][88300] Updated weights for policy 1, policy_version 93412 (0.0009) -[2023-10-15 06:02:05,277][88300] Updated weights for policy 1, policy_version 93422 (0.0007) -[2023-10-15 06:02:05,323][88298] Updated weights for policy 0, policy_version 92840 (0.0009) -[2023-10-15 06:02:05,653][88300] Updated weights for policy 1, policy_version 93432 (0.0008) -[2023-10-15 06:02:05,693][88298] Updated weights for policy 0, policy_version 92850 (0.0009) -[2023-10-15 06:02:06,063][88298] Updated weights for policy 0, policy_version 92860 (0.0009) -[2023-10-15 06:02:08,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 190775296. Throughput: 0: 1710.8, 1: 1724.3. Samples: 47701378. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-15 06:02:08,534][87330] Avg episode reward: [(0, '22.820'), (1, '22.980')] -[2023-10-15 06:02:09,625][88300] Updated weights for policy 1, policy_version 93442 (0.0009) -[2023-10-15 06:02:09,983][88300] Updated weights for policy 1, policy_version 93452 (0.0009) -[2023-10-15 06:02:10,020][88298] Updated weights for policy 0, policy_version 92870 (0.0008) -[2023-10-15 06:02:10,344][88300] Updated weights for policy 1, policy_version 93462 (0.0009) -[2023-10-15 06:02:10,381][88298] Updated weights for policy 0, policy_version 92880 (0.0008) -[2023-10-15 06:02:10,713][88300] Updated weights for policy 1, policy_version 93472 (0.0007) -[2023-10-15 06:02:10,746][88298] Updated weights for policy 0, policy_version 92890 (0.0008) -[2023-10-15 06:02:13,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 190840832. Throughput: 0: 1733.5, 1: 1755.2. Samples: 47723434. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-15 06:02:13,535][87330] Avg episode reward: [(0, '22.880'), (1, '22.970')] -[2023-10-15 06:02:14,548][88298] Updated weights for policy 0, policy_version 92900 (0.0008) -[2023-10-15 06:02:14,680][88300] Updated weights for policy 1, policy_version 93482 (0.0009) -[2023-10-15 06:02:14,920][88298] Updated weights for policy 0, policy_version 92910 (0.0008) -[2023-10-15 06:02:15,044][88300] Updated weights for policy 1, policy_version 93492 (0.0008) -[2023-10-15 06:02:15,294][88298] Updated weights for policy 0, policy_version 92920 (0.0008) -[2023-10-15 06:02:15,408][88300] Updated weights for policy 1, policy_version 93502 (0.0009) -[2023-10-15 06:02:18,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 190906368. Throughput: 0: 1721.5, 1: 1732.1. Samples: 47732922. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-15 06:02:18,535][87330] Avg episode reward: [(0, '22.790'), (1, '22.970')] -[2023-10-15 06:02:19,026][88298] Updated weights for policy 0, policy_version 92930 (0.0009) -[2023-10-15 06:02:19,266][88300] Updated weights for policy 1, policy_version 93512 (0.0008) -[2023-10-15 06:02:19,401][88298] Updated weights for policy 0, policy_version 92940 (0.0008) -[2023-10-15 06:02:19,625][88300] Updated weights for policy 1, policy_version 93522 (0.0008) -[2023-10-15 06:02:19,754][88298] Updated weights for policy 0, policy_version 92950 (0.0007) -[2023-10-15 06:02:19,997][88300] Updated weights for policy 1, policy_version 93532 (0.0007) -[2023-10-15 06:02:20,127][88298] Updated weights for policy 0, policy_version 92960 (0.0008) -[2023-10-15 06:02:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 190971904. Throughput: 0: 1730.7, 1: 1751.7. Samples: 47754842. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-15 06:02:23,534][87330] Avg episode reward: [(0, '22.790'), (1, '22.990')] -[2023-10-15 06:02:23,835][88300] Updated weights for policy 1, policy_version 93542 (0.0008) -[2023-10-15 06:02:23,936][88298] Updated weights for policy 0, policy_version 92970 (0.0008) -[2023-10-15 06:02:24,208][88300] Updated weights for policy 1, policy_version 93552 (0.0009) -[2023-10-15 06:02:24,308][88298] Updated weights for policy 0, policy_version 92980 (0.0008) -[2023-10-15 06:02:24,567][88300] Updated weights for policy 1, policy_version 93562 (0.0008) -[2023-10-15 06:02:24,668][88298] Updated weights for policy 0, policy_version 92990 (0.0007) -[2023-10-15 06:02:28,305][88300] Updated weights for policy 1, policy_version 93572 (0.0009) -[2023-10-15 06:02:28,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 191037440. Throughput: 0: 1768.6, 1: 1774.3. Samples: 47776662. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-15 06:02:28,534][87330] Avg episode reward: [(0, '22.850'), (1, '23.000')] -[2023-10-15 06:02:28,652][88298] Updated weights for policy 0, policy_version 93000 (0.0008) -[2023-10-15 06:02:28,678][88300] Updated weights for policy 1, policy_version 93582 (0.0007) -[2023-10-15 06:02:29,029][88298] Updated weights for policy 0, policy_version 93010 (0.0008) -[2023-10-15 06:02:29,046][88300] Updated weights for policy 1, policy_version 93592 (0.0007) -[2023-10-15 06:02:29,399][88298] Updated weights for policy 0, policy_version 93020 (0.0007) -[2023-10-15 06:02:32,853][88300] Updated weights for policy 1, policy_version 93602 (0.0007) -[2023-10-15 06:02:33,218][88300] Updated weights for policy 1, policy_version 93612 (0.0007) -[2023-10-15 06:02:33,454][88298] Updated weights for policy 0, policy_version 93030 (0.0009) -[2023-10-15 06:02:33,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 13773.7). Total num frames: 191102976. Throughput: 0: 1734.8, 1: 1741.3. Samples: 47786032. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-15 06:02:33,534][87330] Avg episode reward: [(0, '23.050'), (1, '23.070')] -[2023-10-15 06:02:33,584][88300] Updated weights for policy 1, policy_version 93622 (0.0007) -[2023-10-15 06:02:33,822][88298] Updated weights for policy 0, policy_version 93040 (0.0009) -[2023-10-15 06:02:33,952][88300] Updated weights for policy 1, policy_version 93632 (0.0007) -[2023-10-15 06:02:34,187][88298] Updated weights for policy 0, policy_version 93050 (0.0008) -[2023-10-15 06:02:37,796][88300] Updated weights for policy 1, policy_version 93642 (0.0011) -[2023-10-15 06:02:38,120][88298] Updated weights for policy 0, policy_version 93060 (0.0008) -[2023-10-15 06:02:38,163][88300] Updated weights for policy 1, policy_version 93652 (0.0007) -[2023-10-15 06:02:38,477][88298] Updated weights for policy 0, policy_version 93070 (0.0007) -[2023-10-15 06:02:38,531][88300] Updated weights for policy 1, policy_version 93662 (0.0008) -[2023-10-15 06:02:38,534][87330] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 13773.7). Total num frames: 191168512. Throughput: 0: 1749.3, 1: 1770.0. Samples: 47807296. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:02:38,535][87330] Avg episode reward: [(0, '23.030'), (1, '23.080')] -[2023-10-15 06:02:38,855][88298] Updated weights for policy 0, policy_version 93080 (0.0009) -[2023-10-15 06:02:42,448][88300] Updated weights for policy 1, policy_version 93672 (0.0010) -[2023-10-15 06:02:42,762][88298] Updated weights for policy 0, policy_version 93090 (0.0010) -[2023-10-15 06:02:42,812][88300] Updated weights for policy 1, policy_version 93682 (0.0007) -[2023-10-15 06:02:43,138][88298] Updated weights for policy 0, policy_version 93100 (0.0007) -[2023-10-15 06:02:43,187][88300] Updated weights for policy 1, policy_version 93692 (0.0008) -[2023-10-15 06:02:43,503][88298] Updated weights for policy 0, policy_version 93110 (0.0009) -[2023-10-15 06:02:43,534][87330] Fps is (10 sec: 16383.5, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 191266816. Throughput: 0: 1755.4, 1: 1742.7. Samples: 47827572. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:02:43,535][87330] Avg episode reward: [(0, '23.020'), (1, '23.060')] -[2023-10-15 06:02:43,871][88298] Updated weights for policy 0, policy_version 93120 (0.0007) -[2023-10-15 06:02:47,047][88300] Updated weights for policy 1, policy_version 93702 (0.0007) -[2023-10-15 06:02:47,411][88300] Updated weights for policy 1, policy_version 93712 (0.0009) -[2023-10-15 06:02:47,772][88300] Updated weights for policy 1, policy_version 93722 (0.0009) -[2023-10-15 06:02:47,818][88298] Updated weights for policy 0, policy_version 93130 (0.0007) -[2023-10-15 06:02:48,195][88298] Updated weights for policy 0, policy_version 93140 (0.0007) -[2023-10-15 06:02:48,534][87330] Fps is (10 sec: 16384.4, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 191332352. Throughput: 0: 1733.6, 1: 1766.0. Samples: 47838228. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:02:48,534][87330] Avg episode reward: [(0, '23.110'), (1, '23.060')] -[2023-10-15 06:02:48,558][88298] Updated weights for policy 0, policy_version 93150 (0.0008) -[2023-10-15 06:02:51,797][88300] Updated weights for policy 1, policy_version 93732 (0.0009) -[2023-10-15 06:02:52,153][88300] Updated weights for policy 1, policy_version 93742 (0.0009) -[2023-10-15 06:02:52,513][88298] Updated weights for policy 0, policy_version 93160 (0.0007) -[2023-10-15 06:02:52,515][88300] Updated weights for policy 1, policy_version 93752 (0.0008) -[2023-10-15 06:02:52,884][88298] Updated weights for policy 0, policy_version 93170 (0.0008) -[2023-10-15 06:02:53,246][88298] Updated weights for policy 0, policy_version 93180 (0.0010) -[2023-10-15 06:02:53,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 191430656. Throughput: 0: 1757.6, 1: 1751.8. Samples: 47859302. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:02:53,535][87330] Avg episode reward: [(0, '23.130'), (1, '23.070')] -[2023-10-15 06:02:56,266][88300] Updated weights for policy 1, policy_version 93762 (0.0007) -[2023-10-15 06:02:56,633][88300] Updated weights for policy 1, policy_version 93772 (0.0011) -[2023-10-15 06:02:56,993][88300] Updated weights for policy 1, policy_version 93782 (0.0009) -[2023-10-15 06:02:57,066][88298] Updated weights for policy 0, policy_version 93190 (0.0007) -[2023-10-15 06:02:57,361][88300] Updated weights for policy 1, policy_version 93792 (0.0009) -[2023-10-15 06:02:57,437][88298] Updated weights for policy 0, policy_version 93200 (0.0009) -[2023-10-15 06:02:57,815][88298] Updated weights for policy 0, policy_version 93210 (0.0008) -[2023-10-15 06:02:58,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 191496192. Throughput: 0: 1726.0, 1: 1739.3. Samples: 47879372. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:02:58,534][87330] Avg episode reward: [(0, '23.150'), (1, '23.080')] -[2023-10-15 06:02:58,543][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000093792_96043008.pth... -[2023-10-15 06:02:58,543][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000093216_95453184.pth... -[2023-10-15 06:02:58,578][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000091584_93782016.pth -[2023-10-15 06:02:58,580][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000092160_94371840.pth -[2023-10-15 06:03:01,305][88300] Updated weights for policy 1, policy_version 93802 (0.0008) -[2023-10-15 06:03:01,669][88300] Updated weights for policy 1, policy_version 93812 (0.0010) -[2023-10-15 06:03:01,694][88298] Updated weights for policy 0, policy_version 93220 (0.0007) -[2023-10-15 06:03:02,040][88300] Updated weights for policy 1, policy_version 93822 (0.0008) -[2023-10-15 06:03:02,063][88298] Updated weights for policy 0, policy_version 93230 (0.0007) -[2023-10-15 06:03:02,431][88298] Updated weights for policy 0, policy_version 93240 (0.0008) -[2023-10-15 06:03:03,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 191561728. Throughput: 0: 1748.4, 1: 1767.7. Samples: 47891144. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:03:03,535][87330] Avg episode reward: [(0, '23.090'), (1, '23.060')] -[2023-10-15 06:03:05,955][88300] Updated weights for policy 1, policy_version 93832 (0.0008) -[2023-10-15 06:03:06,244][88298] Updated weights for policy 0, policy_version 93250 (0.0008) -[2023-10-15 06:03:06,319][88300] Updated weights for policy 1, policy_version 93842 (0.0008) -[2023-10-15 06:03:06,615][88298] Updated weights for policy 0, policy_version 93260 (0.0008) -[2023-10-15 06:03:06,683][88300] Updated weights for policy 1, policy_version 93852 (0.0008) -[2023-10-15 06:03:06,975][88298] Updated weights for policy 0, policy_version 93270 (0.0008) -[2023-10-15 06:03:07,346][88298] Updated weights for policy 0, policy_version 93280 (0.0008) -[2023-10-15 06:03:08,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 191627264. Throughput: 0: 1735.1, 1: 1735.8. Samples: 47911032. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:03:08,534][87330] Avg episode reward: [(0, '23.030'), (1, '23.090')] -[2023-10-15 06:03:10,625][88300] Updated weights for policy 1, policy_version 93862 (0.0007) -[2023-10-15 06:03:11,021][88300] Updated weights for policy 1, policy_version 93872 (0.0007) -[2023-10-15 06:03:11,192][88298] Updated weights for policy 0, policy_version 93290 (0.0008) -[2023-10-15 06:03:11,387][88300] Updated weights for policy 1, policy_version 93882 (0.0008) -[2023-10-15 06:03:11,561][88298] Updated weights for policy 0, policy_version 93300 (0.0007) -[2023-10-15 06:03:11,933][88298] Updated weights for policy 0, policy_version 93310 (0.0009) -[2023-10-15 06:03:13,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 191692800. Throughput: 0: 1716.5, 1: 1739.1. Samples: 47932166. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:03:13,535][87330] Avg episode reward: [(0, '22.980'), (1, '23.090')] -[2023-10-15 06:03:15,298][88300] Updated weights for policy 1, policy_version 93892 (0.0008) -[2023-10-15 06:03:15,663][88300] Updated weights for policy 1, policy_version 93902 (0.0008) -[2023-10-15 06:03:15,840][88298] Updated weights for policy 0, policy_version 93320 (0.0010) -[2023-10-15 06:03:16,036][88300] Updated weights for policy 1, policy_version 93912 (0.0008) -[2023-10-15 06:03:16,210][88298] Updated weights for policy 0, policy_version 93330 (0.0008) -[2023-10-15 06:03:16,570][88298] Updated weights for policy 0, policy_version 93340 (0.0009) -[2023-10-15 06:03:18,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 191758336. Throughput: 0: 1741.3, 1: 1743.4. Samples: 47942846. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:03:18,534][87330] Avg episode reward: [(0, '23.040'), (1, '23.090')] -[2023-10-15 06:03:19,914][88300] Updated weights for policy 1, policy_version 93922 (0.0008) -[2023-10-15 06:03:20,277][88300] Updated weights for policy 1, policy_version 93932 (0.0009) -[2023-10-15 06:03:20,543][88298] Updated weights for policy 0, policy_version 93350 (0.0007) -[2023-10-15 06:03:20,644][88300] Updated weights for policy 1, policy_version 93942 (0.0007) -[2023-10-15 06:03:20,916][88298] Updated weights for policy 0, policy_version 93360 (0.0007) -[2023-10-15 06:03:21,008][88300] Updated weights for policy 1, policy_version 93952 (0.0007) -[2023-10-15 06:03:21,285][88298] Updated weights for policy 0, policy_version 93370 (0.0009) -[2023-10-15 06:03:23,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 191823872. Throughput: 0: 1727.3, 1: 1734.0. Samples: 47963052. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:03:23,535][87330] Avg episode reward: [(0, '23.040'), (1, '23.040')] -[2023-10-15 06:03:24,969][88300] Updated weights for policy 1, policy_version 93962 (0.0009) -[2023-10-15 06:03:25,020][88298] Updated weights for policy 0, policy_version 93380 (0.0007) -[2023-10-15 06:03:25,330][88300] Updated weights for policy 1, policy_version 93972 (0.0009) -[2023-10-15 06:03:25,388][88298] Updated weights for policy 0, policy_version 93390 (0.0007) -[2023-10-15 06:03:25,697][88300] Updated weights for policy 1, policy_version 93982 (0.0010) -[2023-10-15 06:03:25,760][88298] Updated weights for policy 0, policy_version 93400 (0.0007) -[2023-10-15 06:03:28,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 191889408. Throughput: 0: 1732.2, 1: 1760.5. Samples: 47984740. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:03:28,534][87330] Avg episode reward: [(0, '22.890'), (1, '22.840')] -[2023-10-15 06:03:29,604][88300] Updated weights for policy 1, policy_version 93992 (0.0009) -[2023-10-15 06:03:29,842][88298] Updated weights for policy 0, policy_version 93410 (0.0008) -[2023-10-15 06:03:29,970][88300] Updated weights for policy 1, policy_version 94002 (0.0008) -[2023-10-15 06:03:30,207][88298] Updated weights for policy 0, policy_version 93420 (0.0009) -[2023-10-15 06:03:30,333][88300] Updated weights for policy 1, policy_version 94012 (0.0008) -[2023-10-15 06:03:30,569][88298] Updated weights for policy 0, policy_version 93430 (0.0008) -[2023-10-15 06:03:30,944][88298] Updated weights for policy 0, policy_version 93440 (0.0007) -[2023-10-15 06:03:33,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 13884.8). Total num frames: 191954944. Throughput: 0: 1737.0, 1: 1732.9. Samples: 47994376. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:03:33,534][87330] Avg episode reward: [(0, '22.840'), (1, '22.820')] -[2023-10-15 06:03:34,316][88300] Updated weights for policy 1, policy_version 94022 (0.0008) -[2023-10-15 06:03:34,679][88300] Updated weights for policy 1, policy_version 94032 (0.0009) -[2023-10-15 06:03:34,719][88298] Updated weights for policy 0, policy_version 93450 (0.0008) -[2023-10-15 06:03:35,044][88300] Updated weights for policy 1, policy_version 94042 (0.0008) -[2023-10-15 06:03:35,087][88298] Updated weights for policy 0, policy_version 93460 (0.0008) -[2023-10-15 06:03:35,449][88298] Updated weights for policy 0, policy_version 93470 (0.0009) -[2023-10-15 06:03:38,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 192020480. Throughput: 0: 1728.5, 1: 1743.7. Samples: 48015550. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:03:38,534][87330] Avg episode reward: [(0, '22.840'), (1, '22.670')] -[2023-10-15 06:03:38,840][88300] Updated weights for policy 1, policy_version 94052 (0.0010) -[2023-10-15 06:03:39,200][88300] Updated weights for policy 1, policy_version 94062 (0.0008) -[2023-10-15 06:03:39,351][88298] Updated weights for policy 0, policy_version 93480 (0.0007) -[2023-10-15 06:03:39,570][88300] Updated weights for policy 1, policy_version 94072 (0.0009) -[2023-10-15 06:03:39,708][88298] Updated weights for policy 0, policy_version 93490 (0.0008) -[2023-10-15 06:03:40,079][88298] Updated weights for policy 0, policy_version 93500 (0.0008) -[2023-10-15 06:03:43,443][88300] Updated weights for policy 1, policy_version 94082 (0.0009) -[2023-10-15 06:03:43,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 192086016. Throughput: 0: 1748.8, 1: 1756.3. Samples: 48037100. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:03:43,534][87330] Avg episode reward: [(0, '22.840'), (1, '22.650')] -[2023-10-15 06:03:43,810][88300] Updated weights for policy 1, policy_version 94092 (0.0008) -[2023-10-15 06:03:44,076][88298] Updated weights for policy 0, policy_version 93510 (0.0008) -[2023-10-15 06:03:44,178][88300] Updated weights for policy 1, policy_version 94102 (0.0009) -[2023-10-15 06:03:44,450][88298] Updated weights for policy 0, policy_version 93520 (0.0008) -[2023-10-15 06:03:44,536][88300] Updated weights for policy 1, policy_version 94112 (0.0008) -[2023-10-15 06:03:44,813][88298] Updated weights for policy 0, policy_version 93530 (0.0010) -[2023-10-15 06:03:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13773.7). Total num frames: 192151552. Throughput: 0: 1726.8, 1: 1727.3. Samples: 48046576. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:03:48,534][87330] Avg episode reward: [(0, '22.870'), (1, '22.410')] -[2023-10-15 06:03:48,560][88300] Updated weights for policy 1, policy_version 94122 (0.0010) -[2023-10-15 06:03:48,828][88298] Updated weights for policy 0, policy_version 93540 (0.0009) -[2023-10-15 06:03:48,919][88300] Updated weights for policy 1, policy_version 94132 (0.0008) -[2023-10-15 06:03:49,199][88298] Updated weights for policy 0, policy_version 93550 (0.0007) -[2023-10-15 06:03:49,284][88300] Updated weights for policy 1, policy_version 94142 (0.0007) -[2023-10-15 06:03:49,569][88298] Updated weights for policy 0, policy_version 93560 (0.0008) -[2023-10-15 06:03:53,179][88300] Updated weights for policy 1, policy_version 94152 (0.0007) -[2023-10-15 06:03:53,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 192217088. Throughput: 0: 1731.7, 1: 1753.3. Samples: 48067856. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:03:53,534][87330] Avg episode reward: [(0, '22.820'), (1, '22.400')] -[2023-10-15 06:03:53,549][88300] Updated weights for policy 1, policy_version 94162 (0.0009) -[2023-10-15 06:03:53,626][88298] Updated weights for policy 0, policy_version 93570 (0.0007) -[2023-10-15 06:03:53,910][88300] Updated weights for policy 1, policy_version 94172 (0.0007) -[2023-10-15 06:03:54,001][88298] Updated weights for policy 0, policy_version 93580 (0.0007) -[2023-10-15 06:03:54,364][88298] Updated weights for policy 0, policy_version 93590 (0.0008) -[2023-10-15 06:03:54,737][88298] Updated weights for policy 0, policy_version 93600 (0.0011) -[2023-10-15 06:03:58,016][88300] Updated weights for policy 1, policy_version 94182 (0.0009) -[2023-10-15 06:03:58,399][88300] Updated weights for policy 1, policy_version 94192 (0.0009) -[2023-10-15 06:03:58,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 192282624. Throughput: 0: 1744.7, 1: 1735.4. Samples: 48088770. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:03:58,534][87330] Avg episode reward: [(0, '22.860'), (1, '22.520')] -[2023-10-15 06:03:58,755][88298] Updated weights for policy 0, policy_version 93610 (0.0008) -[2023-10-15 06:03:58,772][88300] Updated weights for policy 1, policy_version 94202 (0.0008) -[2023-10-15 06:03:59,126][88298] Updated weights for policy 0, policy_version 93620 (0.0007) -[2023-10-15 06:03:59,493][88298] Updated weights for policy 0, policy_version 93630 (0.0007) -[2023-10-15 06:04:02,554][88300] Updated weights for policy 1, policy_version 94212 (0.0007) -[2023-10-15 06:04:02,911][88300] Updated weights for policy 1, policy_version 94222 (0.0007) -[2023-10-15 06:04:03,278][88300] Updated weights for policy 1, policy_version 94232 (0.0009) -[2023-10-15 06:04:03,399][88298] Updated weights for policy 0, policy_version 93640 (0.0007) -[2023-10-15 06:04:03,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13773.7). Total num frames: 192348160. Throughput: 0: 1724.0, 1: 1741.1. Samples: 48098776. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:04:03,535][87330] Avg episode reward: [(0, '22.960'), (1, '22.520')] -[2023-10-15 06:04:03,760][88298] Updated weights for policy 0, policy_version 93650 (0.0009) -[2023-10-15 06:04:04,129][88298] Updated weights for policy 0, policy_version 93660 (0.0007) -[2023-10-15 06:04:07,057][88300] Updated weights for policy 1, policy_version 94242 (0.0008) -[2023-10-15 06:04:07,422][88300] Updated weights for policy 1, policy_version 94252 (0.0008) -[2023-10-15 06:04:07,782][88300] Updated weights for policy 1, policy_version 94262 (0.0008) -[2023-10-15 06:04:08,155][88300] Updated weights for policy 1, policy_version 94272 (0.0008) -[2023-10-15 06:04:08,167][88298] Updated weights for policy 0, policy_version 93670 (0.0009) -[2023-10-15 06:04:08,534][87330] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 192446464. Throughput: 0: 1745.2, 1: 1740.1. Samples: 48119888. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:04:08,535][87330] Avg episode reward: [(0, '22.960'), (1, '22.450')] -[2023-10-15 06:04:08,552][88298] Updated weights for policy 0, policy_version 93680 (0.0008) -[2023-10-15 06:04:08,927][88298] Updated weights for policy 0, policy_version 93690 (0.0008) -[2023-10-15 06:04:12,087][88300] Updated weights for policy 1, policy_version 94282 (0.0008) -[2023-10-15 06:04:12,459][88300] Updated weights for policy 1, policy_version 94292 (0.0007) -[2023-10-15 06:04:12,800][88298] Updated weights for policy 0, policy_version 93700 (0.0009) -[2023-10-15 06:04:12,820][88300] Updated weights for policy 1, policy_version 94302 (0.0008) -[2023-10-15 06:04:13,170][88298] Updated weights for policy 0, policy_version 93710 (0.0007) -[2023-10-15 06:04:13,534][87330] Fps is (10 sec: 16384.2, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 192512000. Throughput: 0: 1734.8, 1: 1715.3. Samples: 48139996. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:04:13,534][87330] Avg episode reward: [(0, '23.010'), (1, '22.430')] -[2023-10-15 06:04:13,541][88298] Updated weights for policy 0, policy_version 93720 (0.0009) -[2023-10-15 06:04:16,655][88300] Updated weights for policy 1, policy_version 94312 (0.0008) -[2023-10-15 06:04:17,024][88300] Updated weights for policy 1, policy_version 94322 (0.0009) -[2023-10-15 06:04:17,403][88300] Updated weights for policy 1, policy_version 94332 (0.0008) -[2023-10-15 06:04:17,451][88298] Updated weights for policy 0, policy_version 93730 (0.0008) -[2023-10-15 06:04:17,828][88298] Updated weights for policy 0, policy_version 93740 (0.0011) -[2023-10-15 06:04:18,197][88298] Updated weights for policy 0, policy_version 93750 (0.0009) -[2023-10-15 06:04:18,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 192577536. Throughput: 0: 1730.2, 1: 1749.0. Samples: 48150940. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:04:18,535][87330] Avg episode reward: [(0, '22.970'), (1, '22.680')] -[2023-10-15 06:04:18,573][88298] Updated weights for policy 0, policy_version 93760 (0.0008) -[2023-10-15 06:04:21,360][88300] Updated weights for policy 1, policy_version 94342 (0.0009) -[2023-10-15 06:04:21,725][88300] Updated weights for policy 1, policy_version 94352 (0.0008) -[2023-10-15 06:04:22,085][88300] Updated weights for policy 1, policy_version 94362 (0.0009) -[2023-10-15 06:04:22,248][88298] Updated weights for policy 0, policy_version 93770 (0.0007) -[2023-10-15 06:04:22,617][88298] Updated weights for policy 0, policy_version 93780 (0.0007) -[2023-10-15 06:04:22,994][88298] Updated weights for policy 0, policy_version 93790 (0.0007) -[2023-10-15 06:04:23,534][87330] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 192675840. Throughput: 0: 1740.8, 1: 1725.3. Samples: 48171526. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:04:23,535][87330] Avg episode reward: [(0, '22.980'), (1, '22.750')] -[2023-10-15 06:04:25,913][88300] Updated weights for policy 1, policy_version 94372 (0.0008) -[2023-10-15 06:04:26,280][88300] Updated weights for policy 1, policy_version 94382 (0.0008) -[2023-10-15 06:04:26,646][88300] Updated weights for policy 1, policy_version 94392 (0.0008) -[2023-10-15 06:04:26,912][88298] Updated weights for policy 0, policy_version 93800 (0.0007) -[2023-10-15 06:04:27,277][88298] Updated weights for policy 0, policy_version 93810 (0.0008) -[2023-10-15 06:04:27,647][88298] Updated weights for policy 0, policy_version 93820 (0.0008) -[2023-10-15 06:04:28,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 192741376. Throughput: 0: 1716.8, 1: 1725.4. Samples: 48191996. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:04:28,534][87330] Avg episode reward: [(0, '22.880'), (1, '22.770')] -[2023-10-15 06:04:30,411][88300] Updated weights for policy 1, policy_version 94402 (0.0008) -[2023-10-15 06:04:30,778][88300] Updated weights for policy 1, policy_version 94412 (0.0008) -[2023-10-15 06:04:31,148][88300] Updated weights for policy 1, policy_version 94422 (0.0008) -[2023-10-15 06:04:31,480][88298] Updated weights for policy 0, policy_version 93830 (0.0008) -[2023-10-15 06:04:31,514][88300] Updated weights for policy 1, policy_version 94432 (0.0008) -[2023-10-15 06:04:31,853][88298] Updated weights for policy 0, policy_version 93840 (0.0009) -[2023-10-15 06:04:32,228][88298] Updated weights for policy 0, policy_version 93850 (0.0008) -[2023-10-15 06:04:33,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 192806912. Throughput: 0: 1747.2, 1: 1735.0. Samples: 48203276. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:04:33,535][87330] Avg episode reward: [(0, '22.860'), (1, '22.770')] -[2023-10-15 06:04:35,340][88300] Updated weights for policy 1, policy_version 94442 (0.0010) -[2023-10-15 06:04:35,706][88300] Updated weights for policy 1, policy_version 94452 (0.0010) -[2023-10-15 06:04:36,072][88300] Updated weights for policy 1, policy_version 94462 (0.0010) -[2023-10-15 06:04:36,158][88298] Updated weights for policy 0, policy_version 93860 (0.0009) -[2023-10-15 06:04:36,529][88298] Updated weights for policy 0, policy_version 93870 (0.0007) -[2023-10-15 06:04:36,892][88298] Updated weights for policy 0, policy_version 93880 (0.0008) -[2023-10-15 06:04:38,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 192872448. Throughput: 0: 1733.1, 1: 1730.1. Samples: 48223700. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-15 06:04:38,534][87330] Avg episode reward: [(0, '22.930'), (1, '22.760')] -[2023-10-15 06:04:40,043][88300] Updated weights for policy 1, policy_version 94472 (0.0008) -[2023-10-15 06:04:40,416][88300] Updated weights for policy 1, policy_version 94482 (0.0007) -[2023-10-15 06:04:40,782][88300] Updated weights for policy 1, policy_version 94492 (0.0008) -[2023-10-15 06:04:40,834][88298] Updated weights for policy 0, policy_version 93890 (0.0009) -[2023-10-15 06:04:41,201][88298] Updated weights for policy 0, policy_version 93900 (0.0011) -[2023-10-15 06:04:41,572][88298] Updated weights for policy 0, policy_version 93910 (0.0010) -[2023-10-15 06:04:41,938][88298] Updated weights for policy 0, policy_version 93920 (0.0007) -[2023-10-15 06:04:43,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 192937984. Throughput: 0: 1719.5, 1: 1748.3. Samples: 48244824. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-15 06:04:43,535][87330] Avg episode reward: [(0, '22.960'), (1, '22.920')] -[2023-10-15 06:04:44,781][88300] Updated weights for policy 1, policy_version 94502 (0.0009) -[2023-10-15 06:04:45,141][88300] Updated weights for policy 1, policy_version 94512 (0.0008) -[2023-10-15 06:04:45,515][88300] Updated weights for policy 1, policy_version 94522 (0.0008) -[2023-10-15 06:04:45,736][88298] Updated weights for policy 0, policy_version 93930 (0.0008) -[2023-10-15 06:04:46,093][88298] Updated weights for policy 0, policy_version 93940 (0.0009) -[2023-10-15 06:04:46,469][88298] Updated weights for policy 0, policy_version 93950 (0.0009) -[2023-10-15 06:04:48,534][87330] Fps is (10 sec: 13106.6, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 193003520. Throughput: 0: 1739.3, 1: 1736.5. Samples: 48255186. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-15 06:04:48,535][87330] Avg episode reward: [(0, '22.950'), (1, '22.790')] -[2023-10-15 06:04:49,421][88300] Updated weights for policy 1, policy_version 94532 (0.0010) -[2023-10-15 06:04:49,795][88300] Updated weights for policy 1, policy_version 94542 (0.0009) -[2023-10-15 06:04:50,166][88300] Updated weights for policy 1, policy_version 94552 (0.0009) -[2023-10-15 06:04:50,466][88298] Updated weights for policy 0, policy_version 93960 (0.0009) -[2023-10-15 06:04:50,837][88298] Updated weights for policy 0, policy_version 93970 (0.0009) -[2023-10-15 06:04:51,213][88298] Updated weights for policy 0, policy_version 93980 (0.0007) -[2023-10-15 06:04:53,534][87330] Fps is (10 sec: 13107.6, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 193069056. Throughput: 0: 1718.0, 1: 1746.0. Samples: 48275772. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-15 06:04:53,534][87330] Avg episode reward: [(0, '23.000'), (1, '22.610')] -[2023-10-15 06:04:53,954][88300] Updated weights for policy 1, policy_version 94562 (0.0008) -[2023-10-15 06:04:54,321][88300] Updated weights for policy 1, policy_version 94572 (0.0008) -[2023-10-15 06:04:54,686][88300] Updated weights for policy 1, policy_version 94582 (0.0008) -[2023-10-15 06:04:55,054][88300] Updated weights for policy 1, policy_version 94592 (0.0007) -[2023-10-15 06:04:55,094][88298] Updated weights for policy 0, policy_version 93990 (0.0007) -[2023-10-15 06:04:55,487][88298] Updated weights for policy 0, policy_version 94000 (0.0009) -[2023-10-15 06:04:55,859][88298] Updated weights for policy 0, policy_version 94010 (0.0009) -[2023-10-15 06:04:58,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13773.7). Total num frames: 193134592. Throughput: 0: 1726.7, 1: 1770.8. Samples: 48297386. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-15 06:04:58,535][87330] Avg episode reward: [(0, '23.040'), (1, '22.720')] -[2023-10-15 06:04:58,548][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000094592_96862208.pth... -[2023-10-15 06:04:58,548][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000094016_96272384.pth... -[2023-10-15 06:04:58,587][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000092992_95223808.pth -[2023-10-15 06:04:58,591][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000092416_94633984.pth -[2023-10-15 06:04:59,105][88300] Updated weights for policy 1, policy_version 94602 (0.0007) -[2023-10-15 06:04:59,472][88300] Updated weights for policy 1, policy_version 94612 (0.0007) -[2023-10-15 06:04:59,835][88300] Updated weights for policy 1, policy_version 94622 (0.0008) -[2023-10-15 06:04:59,954][88298] Updated weights for policy 0, policy_version 94020 (0.0008) -[2023-10-15 06:05:00,316][88298] Updated weights for policy 0, policy_version 94030 (0.0011) -[2023-10-15 06:05:00,688][88298] Updated weights for policy 0, policy_version 94040 (0.0007) -[2023-10-15 06:05:03,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13773.7). Total num frames: 193200128. Throughput: 0: 1729.2, 1: 1742.0. Samples: 48307148. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-15 06:05:03,534][87330] Avg episode reward: [(0, '23.050'), (1, '22.720')] -[2023-10-15 06:05:03,694][88300] Updated weights for policy 1, policy_version 94632 (0.0007) -[2023-10-15 06:05:04,064][88300] Updated weights for policy 1, policy_version 94642 (0.0008) -[2023-10-15 06:05:04,431][88300] Updated weights for policy 1, policy_version 94652 (0.0007) -[2023-10-15 06:05:04,534][88298] Updated weights for policy 0, policy_version 94050 (0.0009) -[2023-10-15 06:05:04,909][88298] Updated weights for policy 0, policy_version 94060 (0.0008) -[2023-10-15 06:05:05,276][88298] Updated weights for policy 0, policy_version 94070 (0.0007) -[2023-10-15 06:05:05,643][88298] Updated weights for policy 0, policy_version 94080 (0.0009) -[2023-10-15 06:05:08,211][88300] Updated weights for policy 1, policy_version 94662 (0.0009) -[2023-10-15 06:05:08,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 193265664. Throughput: 0: 1716.1, 1: 1772.6. Samples: 48328516. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-15 06:05:08,535][87330] Avg episode reward: [(0, '23.020'), (1, '22.520')] -[2023-10-15 06:05:08,569][88300] Updated weights for policy 1, policy_version 94672 (0.0007) -[2023-10-15 06:05:08,942][88300] Updated weights for policy 1, policy_version 94682 (0.0007) -[2023-10-15 06:05:09,525][88298] Updated weights for policy 0, policy_version 94090 (0.0010) -[2023-10-15 06:05:09,899][88298] Updated weights for policy 0, policy_version 94100 (0.0010) -[2023-10-15 06:05:10,265][88298] Updated weights for policy 0, policy_version 94110 (0.0008) -[2023-10-15 06:05:12,770][88300] Updated weights for policy 1, policy_version 94692 (0.0007) -[2023-10-15 06:05:13,140][88300] Updated weights for policy 1, policy_version 94702 (0.0008) -[2023-10-15 06:05:13,504][88300] Updated weights for policy 1, policy_version 94712 (0.0010) -[2023-10-15 06:05:13,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 193331200. Throughput: 0: 1735.8, 1: 1758.9. Samples: 48349258. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-15 06:05:13,535][87330] Avg episode reward: [(0, '22.860'), (1, '22.570')] -[2023-10-15 06:05:14,333][88298] Updated weights for policy 0, policy_version 94120 (0.0009) -[2023-10-15 06:05:14,711][88298] Updated weights for policy 0, policy_version 94130 (0.0010) -[2023-10-15 06:05:15,085][88298] Updated weights for policy 0, policy_version 94140 (0.0011) -[2023-10-15 06:05:17,143][88300] Updated weights for policy 1, policy_version 94722 (0.0009) -[2023-10-15 06:05:17,504][88300] Updated weights for policy 1, policy_version 94732 (0.0009) -[2023-10-15 06:05:17,866][88300] Updated weights for policy 1, policy_version 94742 (0.0007) -[2023-10-15 06:05:18,223][88300] Updated weights for policy 1, policy_version 94752 (0.0011) -[2023-10-15 06:05:18,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 193429504. Throughput: 0: 1708.5, 1: 1765.0. Samples: 48359582. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-15 06:05:18,534][87330] Avg episode reward: [(0, '22.900'), (1, '22.550')] -[2023-10-15 06:05:18,892][88298] Updated weights for policy 0, policy_version 94150 (0.0008) -[2023-10-15 06:05:19,267][88298] Updated weights for policy 0, policy_version 94160 (0.0007) -[2023-10-15 06:05:19,627][88298] Updated weights for policy 0, policy_version 94170 (0.0008) -[2023-10-15 06:05:22,154][88300] Updated weights for policy 1, policy_version 94762 (0.0008) -[2023-10-15 06:05:22,526][88300] Updated weights for policy 1, policy_version 94772 (0.0008) -[2023-10-15 06:05:22,892][88300] Updated weights for policy 1, policy_version 94782 (0.0008) -[2023-10-15 06:05:23,346][88298] Updated weights for policy 0, policy_version 94180 (0.0009) -[2023-10-15 06:05:23,534][87330] Fps is (10 sec: 16384.2, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 193495040. Throughput: 0: 1736.0, 1: 1761.0. Samples: 48381066. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-15 06:05:23,534][87330] Avg episode reward: [(0, '22.860'), (1, '22.730')] -[2023-10-15 06:05:23,714][88298] Updated weights for policy 0, policy_version 94190 (0.0009) -[2023-10-15 06:05:24,084][88298] Updated weights for policy 0, policy_version 94200 (0.0007) -[2023-10-15 06:05:26,689][88300] Updated weights for policy 1, policy_version 94792 (0.0008) -[2023-10-15 06:05:27,066][88300] Updated weights for policy 1, policy_version 94802 (0.0008) -[2023-10-15 06:05:27,429][88300] Updated weights for policy 1, policy_version 94812 (0.0008) -[2023-10-15 06:05:27,793][88298] Updated weights for policy 0, policy_version 94210 (0.0008) -[2023-10-15 06:05:28,166][88298] Updated weights for policy 0, policy_version 94220 (0.0007) -[2023-10-15 06:05:28,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 193560576. Throughput: 0: 1756.1, 1: 1739.4. Samples: 48402122. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-15 06:05:28,534][87330] Avg episode reward: [(0, '22.860'), (1, '22.870')] -[2023-10-15 06:05:28,546][88298] Updated weights for policy 0, policy_version 94230 (0.0007) -[2023-10-15 06:05:28,913][88298] Updated weights for policy 0, policy_version 94240 (0.0008) -[2023-10-15 06:05:31,193][88300] Updated weights for policy 1, policy_version 94822 (0.0008) -[2023-10-15 06:05:31,558][88300] Updated weights for policy 1, policy_version 94832 (0.0010) -[2023-10-15 06:05:31,936][88300] Updated weights for policy 1, policy_version 94842 (0.0011) -[2023-10-15 06:05:32,774][88298] Updated weights for policy 0, policy_version 94250 (0.0008) -[2023-10-15 06:05:33,151][88298] Updated weights for policy 0, policy_version 94260 (0.0008) -[2023-10-15 06:05:33,523][88298] Updated weights for policy 0, policy_version 94270 (0.0008) -[2023-10-15 06:05:33,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 193626112. Throughput: 0: 1737.7, 1: 1766.9. Samples: 48412894. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-15 06:05:33,534][87330] Avg episode reward: [(0, '22.880'), (1, '22.860')] -[2023-10-15 06:05:36,068][88300] Updated weights for policy 1, policy_version 94852 (0.0009) -[2023-10-15 06:05:36,433][88300] Updated weights for policy 1, policy_version 94862 (0.0011) -[2023-10-15 06:05:36,800][88300] Updated weights for policy 1, policy_version 94872 (0.0011) -[2023-10-15 06:05:37,493][88298] Updated weights for policy 0, policy_version 94280 (0.0008) -[2023-10-15 06:05:37,863][88298] Updated weights for policy 0, policy_version 94290 (0.0009) -[2023-10-15 06:05:38,241][88298] Updated weights for policy 0, policy_version 94300 (0.0008) -[2023-10-15 06:05:38,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 193724416. Throughput: 0: 1759.0, 1: 1739.0. Samples: 48433180. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:05:38,534][87330] Avg episode reward: [(0, '22.790'), (1, '22.730')] -[2023-10-15 06:05:40,548][88300] Updated weights for policy 1, policy_version 94882 (0.0009) -[2023-10-15 06:05:40,915][88300] Updated weights for policy 1, policy_version 94892 (0.0008) -[2023-10-15 06:05:41,282][88300] Updated weights for policy 1, policy_version 94902 (0.0008) -[2023-10-15 06:05:41,650][88300] Updated weights for policy 1, policy_version 94912 (0.0007) -[2023-10-15 06:05:42,289][88298] Updated weights for policy 0, policy_version 94310 (0.0008) -[2023-10-15 06:05:42,664][88298] Updated weights for policy 0, policy_version 94320 (0.0007) -[2023-10-15 06:05:43,043][88298] Updated weights for policy 0, policy_version 94330 (0.0007) -[2023-10-15 06:05:43,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 193789952. Throughput: 0: 1741.7, 1: 1746.2. Samples: 48454344. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:05:43,534][87330] Avg episode reward: [(0, '22.940'), (1, '22.730')] -[2023-10-15 06:05:45,589][88300] Updated weights for policy 1, policy_version 94922 (0.0011) -[2023-10-15 06:05:45,955][88300] Updated weights for policy 1, policy_version 94932 (0.0007) -[2023-10-15 06:05:46,313][88300] Updated weights for policy 1, policy_version 94942 (0.0008) -[2023-10-15 06:05:46,810][88298] Updated weights for policy 0, policy_version 94340 (0.0007) -[2023-10-15 06:05:47,175][88298] Updated weights for policy 0, policy_version 94350 (0.0007) -[2023-10-15 06:05:47,542][88298] Updated weights for policy 0, policy_version 94360 (0.0007) -[2023-10-15 06:05:48,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 193855488. Throughput: 0: 1755.7, 1: 1749.9. Samples: 48464900. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:05:48,535][87330] Avg episode reward: [(0, '22.930'), (1, '22.720')] -[2023-10-15 06:05:50,266][88300] Updated weights for policy 1, policy_version 94952 (0.0009) -[2023-10-15 06:05:50,645][88300] Updated weights for policy 1, policy_version 94962 (0.0008) -[2023-10-15 06:05:51,015][88300] Updated weights for policy 1, policy_version 94972 (0.0010) -[2023-10-15 06:05:51,515][88298] Updated weights for policy 0, policy_version 94370 (0.0007) -[2023-10-15 06:05:51,881][88298] Updated weights for policy 0, policy_version 94380 (0.0010) -[2023-10-15 06:05:52,251][88298] Updated weights for policy 0, policy_version 94390 (0.0008) -[2023-10-15 06:05:52,619][88298] Updated weights for policy 0, policy_version 94400 (0.0008) -[2023-10-15 06:05:53,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 193921024. Throughput: 0: 1753.0, 1: 1741.5. Samples: 48485770. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:05:53,535][87330] Avg episode reward: [(0, '22.970'), (1, '22.710')] -[2023-10-15 06:05:54,762][88300] Updated weights for policy 1, policy_version 94982 (0.0009) -[2023-10-15 06:05:55,122][88300] Updated weights for policy 1, policy_version 94992 (0.0011) -[2023-10-15 06:05:55,496][88300] Updated weights for policy 1, policy_version 95002 (0.0008) -[2023-10-15 06:05:56,548][88298] Updated weights for policy 0, policy_version 94410 (0.0010) -[2023-10-15 06:05:56,919][88298] Updated weights for policy 0, policy_version 94420 (0.0010) -[2023-10-15 06:05:57,301][88298] Updated weights for policy 0, policy_version 94430 (0.0010) -[2023-10-15 06:05:58,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 193986560. Throughput: 0: 1738.8, 1: 1753.1. Samples: 48506396. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:05:58,535][87330] Avg episode reward: [(0, '22.940'), (1, '22.720')] -[2023-10-15 06:05:59,382][88300] Updated weights for policy 1, policy_version 95012 (0.0007) -[2023-10-15 06:05:59,752][88300] Updated weights for policy 1, policy_version 95022 (0.0007) -[2023-10-15 06:06:00,108][88300] Updated weights for policy 1, policy_version 95032 (0.0011) -[2023-10-15 06:06:01,292][88298] Updated weights for policy 0, policy_version 94440 (0.0008) -[2023-10-15 06:06:01,662][88298] Updated weights for policy 0, policy_version 94450 (0.0009) -[2023-10-15 06:06:02,036][88298] Updated weights for policy 0, policy_version 94460 (0.0007) -[2023-10-15 06:06:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 194052096. Throughput: 0: 1764.0, 1: 1738.3. Samples: 48517184. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:06:03,535][87330] Avg episode reward: [(0, '22.980'), (1, '22.710')] -[2023-10-15 06:06:03,956][88300] Updated weights for policy 1, policy_version 95042 (0.0008) -[2023-10-15 06:06:04,324][88300] Updated weights for policy 1, policy_version 95052 (0.0007) -[2023-10-15 06:06:04,688][88300] Updated weights for policy 1, policy_version 95062 (0.0008) -[2023-10-15 06:06:05,059][88300] Updated weights for policy 1, policy_version 95072 (0.0007) -[2023-10-15 06:06:05,816][88298] Updated weights for policy 0, policy_version 94470 (0.0008) -[2023-10-15 06:06:06,186][88298] Updated weights for policy 0, policy_version 94480 (0.0009) -[2023-10-15 06:06:06,551][88298] Updated weights for policy 0, policy_version 94490 (0.0008) -[2023-10-15 06:06:08,534][87330] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 194117632. Throughput: 0: 1730.3, 1: 1748.5. Samples: 48537614. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:06:08,534][87330] Avg episode reward: [(0, '22.930'), (1, '22.820')] -[2023-10-15 06:06:09,038][88300] Updated weights for policy 1, policy_version 95082 (0.0007) -[2023-10-15 06:06:09,399][88300] Updated weights for policy 1, policy_version 95092 (0.0007) -[2023-10-15 06:06:09,778][88300] Updated weights for policy 1, policy_version 95102 (0.0008) -[2023-10-15 06:06:10,441][88298] Updated weights for policy 0, policy_version 94500 (0.0007) -[2023-10-15 06:06:10,819][88298] Updated weights for policy 0, policy_version 94510 (0.0007) -[2023-10-15 06:06:11,192][88298] Updated weights for policy 0, policy_version 94520 (0.0008) -[2023-10-15 06:06:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 194183168. Throughput: 0: 1722.7, 1: 1765.3. Samples: 48559082. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:06:13,535][87330] Avg episode reward: [(0, '23.050'), (1, '23.000')] -[2023-10-15 06:06:13,684][88300] Updated weights for policy 1, policy_version 95112 (0.0008) -[2023-10-15 06:06:14,043][88300] Updated weights for policy 1, policy_version 95122 (0.0009) -[2023-10-15 06:06:14,404][88300] Updated weights for policy 1, policy_version 95132 (0.0007) -[2023-10-15 06:06:15,049][88298] Updated weights for policy 0, policy_version 94530 (0.0009) -[2023-10-15 06:06:15,419][88298] Updated weights for policy 0, policy_version 94540 (0.0007) -[2023-10-15 06:06:15,789][88298] Updated weights for policy 0, policy_version 94550 (0.0008) -[2023-10-15 06:06:16,158][88298] Updated weights for policy 0, policy_version 94560 (0.0007) -[2023-10-15 06:06:18,403][88300] Updated weights for policy 1, policy_version 95142 (0.0008) -[2023-10-15 06:06:18,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 194248704. Throughput: 0: 1732.8, 1: 1740.4. Samples: 48569190. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:06:18,534][87330] Avg episode reward: [(0, '23.030'), (1, '22.720')] -[2023-10-15 06:06:18,781][88300] Updated weights for policy 1, policy_version 95152 (0.0007) -[2023-10-15 06:06:19,152][88300] Updated weights for policy 1, policy_version 95162 (0.0008) -[2023-10-15 06:06:20,192][88298] Updated weights for policy 0, policy_version 94570 (0.0007) -[2023-10-15 06:06:20,561][88298] Updated weights for policy 0, policy_version 94580 (0.0007) -[2023-10-15 06:06:20,929][88298] Updated weights for policy 0, policy_version 94590 (0.0009) -[2023-10-15 06:06:23,068][88300] Updated weights for policy 1, policy_version 95172 (0.0007) -[2023-10-15 06:06:23,430][88300] Updated weights for policy 1, policy_version 95182 (0.0009) -[2023-10-15 06:06:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 194314240. Throughput: 0: 1723.6, 1: 1765.8. Samples: 48590200. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:06:23,535][87330] Avg episode reward: [(0, '22.980'), (1, '22.720')] -[2023-10-15 06:06:23,800][88300] Updated weights for policy 1, policy_version 95192 (0.0008) -[2023-10-15 06:06:24,819][88298] Updated weights for policy 0, policy_version 94600 (0.0010) -[2023-10-15 06:06:25,178][88298] Updated weights for policy 0, policy_version 94610 (0.0009) -[2023-10-15 06:06:25,554][88298] Updated weights for policy 0, policy_version 94620 (0.0007) -[2023-10-15 06:06:27,776][88300] Updated weights for policy 1, policy_version 95202 (0.0008) -[2023-10-15 06:06:28,136][88300] Updated weights for policy 1, policy_version 95212 (0.0010) -[2023-10-15 06:06:28,502][88300] Updated weights for policy 1, policy_version 95222 (0.0009) -[2023-10-15 06:06:28,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 194379776. Throughput: 0: 1741.6, 1: 1742.8. Samples: 48611142. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:06:28,534][87330] Avg episode reward: [(0, '22.850'), (1, '22.730')] -[2023-10-15 06:06:28,871][88300] Updated weights for policy 1, policy_version 95232 (0.0009) -[2023-10-15 06:06:29,568][88298] Updated weights for policy 0, policy_version 94630 (0.0008) -[2023-10-15 06:06:29,954][88298] Updated weights for policy 0, policy_version 94640 (0.0011) -[2023-10-15 06:06:30,325][88298] Updated weights for policy 0, policy_version 94650 (0.0009) -[2023-10-15 06:06:32,684][88300] Updated weights for policy 1, policy_version 95242 (0.0008) -[2023-10-15 06:06:33,048][88300] Updated weights for policy 1, policy_version 95252 (0.0007) -[2023-10-15 06:06:33,419][88300] Updated weights for policy 1, policy_version 95262 (0.0007) -[2023-10-15 06:06:33,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 194478080. Throughput: 0: 1720.0, 1: 1749.4. Samples: 48621022. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:06:33,535][87330] Avg episode reward: [(0, '22.810'), (1, '22.670')] -[2023-10-15 06:06:34,115][88298] Updated weights for policy 0, policy_version 94660 (0.0010) -[2023-10-15 06:06:34,474][88298] Updated weights for policy 0, policy_version 94670 (0.0008) -[2023-10-15 06:06:34,849][88298] Updated weights for policy 0, policy_version 94680 (0.0010) -[2023-10-15 06:06:37,446][88300] Updated weights for policy 1, policy_version 95272 (0.0008) -[2023-10-15 06:06:37,814][88300] Updated weights for policy 1, policy_version 95282 (0.0008) -[2023-10-15 06:06:38,183][88300] Updated weights for policy 1, policy_version 95292 (0.0008) -[2023-10-15 06:06:38,534][87330] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 194543616. Throughput: 0: 1736.4, 1: 1747.2. Samples: 48642532. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:06:38,534][87330] Avg episode reward: [(0, '22.840'), (1, '22.700')] -[2023-10-15 06:06:38,549][88298] Updated weights for policy 0, policy_version 94690 (0.0008) -[2023-10-15 06:06:38,920][88298] Updated weights for policy 0, policy_version 94700 (0.0009) -[2023-10-15 06:06:39,277][88298] Updated weights for policy 0, policy_version 94710 (0.0008) -[2023-10-15 06:06:39,651][88298] Updated weights for policy 0, policy_version 94720 (0.0008) -[2023-10-15 06:06:42,034][88300] Updated weights for policy 1, policy_version 95302 (0.0007) -[2023-10-15 06:06:42,399][88300] Updated weights for policy 1, policy_version 95312 (0.0007) -[2023-10-15 06:06:42,775][88300] Updated weights for policy 1, policy_version 95322 (0.0009) -[2023-10-15 06:06:43,398][88298] Updated weights for policy 0, policy_version 94730 (0.0009) -[2023-10-15 06:06:43,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 194609152. Throughput: 0: 1765.0, 1: 1717.0. Samples: 48663086. Policy #0 lag: (min: 8.0, avg: 34.1, max: 40.0) -[2023-10-15 06:06:43,534][87330] Avg episode reward: [(0, '22.850'), (1, '22.680')] -[2023-10-15 06:06:43,775][88298] Updated weights for policy 0, policy_version 94740 (0.0007) -[2023-10-15 06:06:44,138][88298] Updated weights for policy 0, policy_version 94750 (0.0009) -[2023-10-15 06:06:46,723][88300] Updated weights for policy 1, policy_version 95332 (0.0008) -[2023-10-15 06:06:47,089][88300] Updated weights for policy 1, policy_version 95342 (0.0008) -[2023-10-15 06:06:47,453][88300] Updated weights for policy 1, policy_version 95352 (0.0009) -[2023-10-15 06:06:47,980][88298] Updated weights for policy 0, policy_version 94760 (0.0009) -[2023-10-15 06:06:48,354][88298] Updated weights for policy 0, policy_version 94770 (0.0008) -[2023-10-15 06:06:48,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 194674688. Throughput: 0: 1736.5, 1: 1745.9. Samples: 48673890. Policy #0 lag: (min: 8.0, avg: 34.1, max: 40.0) -[2023-10-15 06:06:48,534][87330] Avg episode reward: [(0, '22.850'), (1, '22.880')] -[2023-10-15 06:06:48,716][88298] Updated weights for policy 0, policy_version 94780 (0.0008) -[2023-10-15 06:06:51,400][88300] Updated weights for policy 1, policy_version 95362 (0.0008) -[2023-10-15 06:06:51,755][88300] Updated weights for policy 1, policy_version 95372 (0.0010) -[2023-10-15 06:06:52,129][88300] Updated weights for policy 1, policy_version 95382 (0.0008) -[2023-10-15 06:06:52,504][88300] Updated weights for policy 1, policy_version 95392 (0.0007) -[2023-10-15 06:06:52,870][88298] Updated weights for policy 0, policy_version 94790 (0.0007) -[2023-10-15 06:06:53,238][88298] Updated weights for policy 0, policy_version 94800 (0.0007) -[2023-10-15 06:06:53,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 194740224. Throughput: 0: 1758.0, 1: 1723.0. Samples: 48694260. Policy #0 lag: (min: 8.0, avg: 34.1, max: 40.0) -[2023-10-15 06:06:53,535][87330] Avg episode reward: [(0, '22.860'), (1, '22.990')] -[2023-10-15 06:06:53,616][88298] Updated weights for policy 0, policy_version 94810 (0.0008) -[2023-10-15 06:06:56,262][88300] Updated weights for policy 1, policy_version 95402 (0.0007) -[2023-10-15 06:06:56,633][88300] Updated weights for policy 1, policy_version 95412 (0.0007) -[2023-10-15 06:06:57,003][88300] Updated weights for policy 1, policy_version 95422 (0.0007) -[2023-10-15 06:06:57,520][88298] Updated weights for policy 0, policy_version 94820 (0.0009) -[2023-10-15 06:06:57,881][88298] Updated weights for policy 0, policy_version 94830 (0.0010) -[2023-10-15 06:06:58,259][88298] Updated weights for policy 0, policy_version 94840 (0.0008) -[2023-10-15 06:06:58,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 194805760. Throughput: 0: 1750.9, 1: 1721.6. Samples: 48715342. Policy #0 lag: (min: 8.0, avg: 34.1, max: 40.0) -[2023-10-15 06:06:58,534][87330] Avg episode reward: [(0, '22.900'), (1, '22.780')] -[2023-10-15 06:06:58,543][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000095424_97714176.pth... -[2023-10-15 06:06:58,545][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000094848_97124352.pth... -[2023-10-15 06:06:58,574][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000093216_95453184.pth -[2023-10-15 06:06:58,581][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000093792_96043008.pth -[2023-10-15 06:07:00,858][88300] Updated weights for policy 1, policy_version 95432 (0.0008) -[2023-10-15 06:07:01,223][88300] Updated weights for policy 1, policy_version 95442 (0.0008) -[2023-10-15 06:07:01,590][88300] Updated weights for policy 1, policy_version 95452 (0.0008) -[2023-10-15 06:07:02,109][88298] Updated weights for policy 0, policy_version 94850 (0.0007) -[2023-10-15 06:07:02,477][88298] Updated weights for policy 0, policy_version 94860 (0.0007) -[2023-10-15 06:07:02,838][88298] Updated weights for policy 0, policy_version 94870 (0.0008) -[2023-10-15 06:07:03,213][88298] Updated weights for policy 0, policy_version 94880 (0.0008) -[2023-10-15 06:07:03,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 194904064. Throughput: 0: 1749.9, 1: 1732.9. Samples: 48725920. Policy #0 lag: (min: 8.0, avg: 34.1, max: 40.0) -[2023-10-15 06:07:03,535][87330] Avg episode reward: [(0, '23.070'), (1, '22.740')] -[2023-10-15 06:07:05,591][88300] Updated weights for policy 1, policy_version 95462 (0.0007) -[2023-10-15 06:07:05,959][88300] Updated weights for policy 1, policy_version 95472 (0.0008) -[2023-10-15 06:07:06,325][88300] Updated weights for policy 1, policy_version 95482 (0.0009) -[2023-10-15 06:07:07,146][88298] Updated weights for policy 0, policy_version 94890 (0.0007) -[2023-10-15 06:07:07,509][88298] Updated weights for policy 0, policy_version 94900 (0.0007) -[2023-10-15 06:07:07,877][88298] Updated weights for policy 0, policy_version 94910 (0.0009) -[2023-10-15 06:07:08,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 194969600. Throughput: 0: 1761.3, 1: 1718.3. Samples: 48746784. Policy #0 lag: (min: 8.0, avg: 34.1, max: 40.0) -[2023-10-15 06:07:08,534][87330] Avg episode reward: [(0, '23.090'), (1, '22.880')] -[2023-10-15 06:07:10,387][88300] Updated weights for policy 1, policy_version 95492 (0.0010) -[2023-10-15 06:07:10,749][88300] Updated weights for policy 1, policy_version 95502 (0.0008) -[2023-10-15 06:07:11,117][88300] Updated weights for policy 1, policy_version 95512 (0.0008) -[2023-10-15 06:07:11,703][88298] Updated weights for policy 0, policy_version 94920 (0.0007) -[2023-10-15 06:07:12,073][88298] Updated weights for policy 0, policy_version 94930 (0.0007) -[2023-10-15 06:07:12,439][88298] Updated weights for policy 0, policy_version 94940 (0.0008) -[2023-10-15 06:07:13,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 195035136. Throughput: 0: 1731.9, 1: 1732.1. Samples: 48767020. Policy #0 lag: (min: 8.0, avg: 34.1, max: 40.0) -[2023-10-15 06:07:13,534][87330] Avg episode reward: [(0, '23.060'), (1, '22.880')] -[2023-10-15 06:07:14,768][88300] Updated weights for policy 1, policy_version 95522 (0.0007) -[2023-10-15 06:07:15,132][88300] Updated weights for policy 1, policy_version 95532 (0.0008) -[2023-10-15 06:07:15,503][88300] Updated weights for policy 1, policy_version 95542 (0.0008) -[2023-10-15 06:07:15,869][88300] Updated weights for policy 1, policy_version 95552 (0.0009) -[2023-10-15 06:07:16,379][88298] Updated weights for policy 0, policy_version 94950 (0.0007) -[2023-10-15 06:07:16,763][88298] Updated weights for policy 0, policy_version 94960 (0.0007) -[2023-10-15 06:07:17,142][88298] Updated weights for policy 0, policy_version 94970 (0.0010) -[2023-10-15 06:07:18,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 195100672. Throughput: 0: 1767.6, 1: 1716.3. Samples: 48777796. Policy #0 lag: (min: 8.0, avg: 34.1, max: 40.0) -[2023-10-15 06:07:18,535][87330] Avg episode reward: [(0, '23.100'), (1, '22.900')] -[2023-10-15 06:07:19,879][88300] Updated weights for policy 1, policy_version 95562 (0.0010) -[2023-10-15 06:07:20,259][88300] Updated weights for policy 1, policy_version 95572 (0.0008) -[2023-10-15 06:07:20,626][88300] Updated weights for policy 1, policy_version 95582 (0.0008) -[2023-10-15 06:07:20,967][88298] Updated weights for policy 0, policy_version 94980 (0.0009) -[2023-10-15 06:07:21,337][88298] Updated weights for policy 0, policy_version 94990 (0.0009) -[2023-10-15 06:07:21,705][88298] Updated weights for policy 0, policy_version 95000 (0.0007) -[2023-10-15 06:07:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 195166208. Throughput: 0: 1735.9, 1: 1725.5. Samples: 48798294. Policy #0 lag: (min: 8.0, avg: 34.1, max: 40.0) -[2023-10-15 06:07:23,534][87330] Avg episode reward: [(0, '23.120'), (1, '22.900')] -[2023-10-15 06:07:24,483][88300] Updated weights for policy 1, policy_version 95592 (0.0008) -[2023-10-15 06:07:24,853][88300] Updated weights for policy 1, policy_version 95602 (0.0007) -[2023-10-15 06:07:25,212][88300] Updated weights for policy 1, policy_version 95612 (0.0007) -[2023-10-15 06:07:25,651][88298] Updated weights for policy 0, policy_version 95010 (0.0007) -[2023-10-15 06:07:26,016][88298] Updated weights for policy 0, policy_version 95020 (0.0009) -[2023-10-15 06:07:26,395][88298] Updated weights for policy 0, policy_version 95030 (0.0008) -[2023-10-15 06:07:26,760][88298] Updated weights for policy 0, policy_version 95040 (0.0008) -[2023-10-15 06:07:28,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 195231744. Throughput: 0: 1717.7, 1: 1763.4. Samples: 48819736. Policy #0 lag: (min: 8.0, avg: 34.1, max: 40.0) -[2023-10-15 06:07:28,534][87330] Avg episode reward: [(0, '23.100'), (1, '22.980')] -[2023-10-15 06:07:28,958][88300] Updated weights for policy 1, policy_version 95622 (0.0008) -[2023-10-15 06:07:29,333][88300] Updated weights for policy 1, policy_version 95632 (0.0008) -[2023-10-15 06:07:29,699][88300] Updated weights for policy 1, policy_version 95642 (0.0009) -[2023-10-15 06:07:30,633][88298] Updated weights for policy 0, policy_version 95050 (0.0008) -[2023-10-15 06:07:31,001][88298] Updated weights for policy 0, policy_version 95060 (0.0008) -[2023-10-15 06:07:31,376][88298] Updated weights for policy 0, policy_version 95070 (0.0009) -[2023-10-15 06:07:33,501][88300] Updated weights for policy 1, policy_version 95652 (0.0010) -[2023-10-15 06:07:33,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 195297280. Throughput: 0: 1739.8, 1: 1734.3. Samples: 48830228. Policy #0 lag: (min: 8.0, avg: 34.1, max: 40.0) -[2023-10-15 06:07:33,535][87330] Avg episode reward: [(0, '23.040'), (1, '22.930')] -[2023-10-15 06:07:33,859][88300] Updated weights for policy 1, policy_version 95662 (0.0008) -[2023-10-15 06:07:34,231][88300] Updated weights for policy 1, policy_version 95672 (0.0009) -[2023-10-15 06:07:35,308][88298] Updated weights for policy 0, policy_version 95080 (0.0008) -[2023-10-15 06:07:35,678][88298] Updated weights for policy 0, policy_version 95090 (0.0009) -[2023-10-15 06:07:36,048][88298] Updated weights for policy 0, policy_version 95100 (0.0008) -[2023-10-15 06:07:38,062][88300] Updated weights for policy 1, policy_version 95682 (0.0009) -[2023-10-15 06:07:38,430][88300] Updated weights for policy 1, policy_version 95692 (0.0009) -[2023-10-15 06:07:38,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 195362816. Throughput: 0: 1726.2, 1: 1759.0. Samples: 48851094. Policy #0 lag: (min: 8.0, avg: 34.1, max: 40.0) -[2023-10-15 06:07:38,534][87330] Avg episode reward: [(0, '23.030'), (1, '22.940')] -[2023-10-15 06:07:38,791][88300] Updated weights for policy 1, policy_version 95702 (0.0009) -[2023-10-15 06:07:39,161][88300] Updated weights for policy 1, policy_version 95712 (0.0007) -[2023-10-15 06:07:39,900][88298] Updated weights for policy 0, policy_version 95110 (0.0009) -[2023-10-15 06:07:40,257][88298] Updated weights for policy 0, policy_version 95120 (0.0010) -[2023-10-15 06:07:40,627][88298] Updated weights for policy 0, policy_version 95130 (0.0010) -[2023-10-15 06:07:43,135][88300] Updated weights for policy 1, policy_version 95722 (0.0007) -[2023-10-15 06:07:43,507][88300] Updated weights for policy 1, policy_version 95732 (0.0008) -[2023-10-15 06:07:43,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 195428352. Throughput: 0: 1736.0, 1: 1748.1. Samples: 48872126. Policy #0 lag: (min: 19.0, avg: 24.0, max: 51.0) -[2023-10-15 06:07:43,534][87330] Avg episode reward: [(0, '23.030'), (1, '22.950')] -[2023-10-15 06:07:43,871][88300] Updated weights for policy 1, policy_version 95742 (0.0009) -[2023-10-15 06:07:44,621][88298] Updated weights for policy 0, policy_version 95140 (0.0009) -[2023-10-15 06:07:44,997][88298] Updated weights for policy 0, policy_version 95150 (0.0011) -[2023-10-15 06:07:45,375][88298] Updated weights for policy 0, policy_version 95160 (0.0007) -[2023-10-15 06:07:47,841][88300] Updated weights for policy 1, policy_version 95752 (0.0010) -[2023-10-15 06:07:48,207][88300] Updated weights for policy 1, policy_version 95762 (0.0008) -[2023-10-15 06:07:48,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13773.7). Total num frames: 195493888. Throughput: 0: 1727.0, 1: 1745.3. Samples: 48882170. Policy #0 lag: (min: 19.0, avg: 24.0, max: 51.0) -[2023-10-15 06:07:48,534][87330] Avg episode reward: [(0, '23.050'), (1, '22.930')] -[2023-10-15 06:07:48,579][88300] Updated weights for policy 1, policy_version 95772 (0.0009) -[2023-10-15 06:07:49,402][88298] Updated weights for policy 0, policy_version 95170 (0.0009) -[2023-10-15 06:07:49,773][88298] Updated weights for policy 0, policy_version 95180 (0.0008) -[2023-10-15 06:07:50,141][88298] Updated weights for policy 0, policy_version 95190 (0.0008) -[2023-10-15 06:07:50,503][88298] Updated weights for policy 0, policy_version 95200 (0.0007) -[2023-10-15 06:07:52,470][88300] Updated weights for policy 1, policy_version 95782 (0.0007) -[2023-10-15 06:07:52,830][88300] Updated weights for policy 1, policy_version 95792 (0.0008) -[2023-10-15 06:07:53,205][88300] Updated weights for policy 1, policy_version 95802 (0.0009) -[2023-10-15 06:07:53,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 195592192. Throughput: 0: 1721.9, 1: 1762.7. Samples: 48903592. Policy #0 lag: (min: 19.0, avg: 24.0, max: 51.0) -[2023-10-15 06:07:53,535][87330] Avg episode reward: [(0, '23.010'), (1, '22.930')] -[2023-10-15 06:07:54,398][88298] Updated weights for policy 0, policy_version 95210 (0.0010) -[2023-10-15 06:07:54,757][88298] Updated weights for policy 0, policy_version 95220 (0.0009) -[2023-10-15 06:07:55,128][88298] Updated weights for policy 0, policy_version 95230 (0.0010) -[2023-10-15 06:07:57,188][88300] Updated weights for policy 1, policy_version 95812 (0.0008) -[2023-10-15 06:07:57,588][88300] Updated weights for policy 1, policy_version 95822 (0.0010) -[2023-10-15 06:07:57,958][88300] Updated weights for policy 1, policy_version 95832 (0.0010) -[2023-10-15 06:07:58,534][87330] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 195657728. Throughput: 0: 1749.8, 1: 1730.3. Samples: 48923626. Policy #0 lag: (min: 19.0, avg: 24.0, max: 51.0) -[2023-10-15 06:07:58,535][87330] Avg episode reward: [(0, '23.030'), (1, '22.960')] -[2023-10-15 06:07:59,012][88298] Updated weights for policy 0, policy_version 95240 (0.0008) -[2023-10-15 06:07:59,382][88298] Updated weights for policy 0, policy_version 95250 (0.0008) -[2023-10-15 06:07:59,759][88298] Updated weights for policy 0, policy_version 95260 (0.0009) -[2023-10-15 06:08:01,844][88300] Updated weights for policy 1, policy_version 95842 (0.0008) -[2023-10-15 06:08:02,213][88300] Updated weights for policy 1, policy_version 95852 (0.0008) -[2023-10-15 06:08:02,588][88300] Updated weights for policy 1, policy_version 95862 (0.0007) -[2023-10-15 06:08:02,961][88300] Updated weights for policy 1, policy_version 95872 (0.0008) -[2023-10-15 06:08:03,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 195723264. Throughput: 0: 1717.2, 1: 1761.7. Samples: 48934344. Policy #0 lag: (min: 19.0, avg: 24.0, max: 51.0) -[2023-10-15 06:08:03,534][87330] Avg episode reward: [(0, '23.110'), (1, '23.040')] -[2023-10-15 06:08:03,743][88298] Updated weights for policy 0, policy_version 95270 (0.0010) -[2023-10-15 06:08:04,113][88298] Updated weights for policy 0, policy_version 95280 (0.0008) -[2023-10-15 06:08:04,496][88298] Updated weights for policy 0, policy_version 95290 (0.0008) -[2023-10-15 06:08:06,766][88300] Updated weights for policy 1, policy_version 95882 (0.0010) -[2023-10-15 06:08:07,131][88300] Updated weights for policy 1, policy_version 95892 (0.0008) -[2023-10-15 06:08:07,494][88300] Updated weights for policy 1, policy_version 95902 (0.0007) -[2023-10-15 06:08:08,335][88298] Updated weights for policy 0, policy_version 95300 (0.0008) -[2023-10-15 06:08:08,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 195788800. Throughput: 0: 1737.2, 1: 1742.2. Samples: 48954868. Policy #0 lag: (min: 19.0, avg: 24.0, max: 51.0) -[2023-10-15 06:08:08,535][87330] Avg episode reward: [(0, '23.120'), (1, '23.100')] -[2023-10-15 06:08:08,702][88298] Updated weights for policy 0, policy_version 95310 (0.0010) -[2023-10-15 06:08:09,069][88298] Updated weights for policy 0, policy_version 95320 (0.0008) -[2023-10-15 06:08:11,559][88300] Updated weights for policy 1, policy_version 95912 (0.0009) -[2023-10-15 06:08:11,926][88300] Updated weights for policy 1, policy_version 95922 (0.0010) -[2023-10-15 06:08:12,301][88300] Updated weights for policy 1, policy_version 95932 (0.0010) -[2023-10-15 06:08:12,920][88298] Updated weights for policy 0, policy_version 95330 (0.0008) -[2023-10-15 06:08:13,285][88298] Updated weights for policy 0, policy_version 95340 (0.0009) -[2023-10-15 06:08:13,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 195854336. Throughput: 0: 1750.8, 1: 1721.0. Samples: 48975966. Policy #0 lag: (min: 19.0, avg: 24.0, max: 51.0) -[2023-10-15 06:08:13,536][87330] Avg episode reward: [(0, '23.010'), (1, '23.090')] -[2023-10-15 06:08:13,658][88298] Updated weights for policy 0, policy_version 95350 (0.0009) -[2023-10-15 06:08:14,020][88298] Updated weights for policy 0, policy_version 95360 (0.0008) -[2023-10-15 06:08:16,196][88300] Updated weights for policy 1, policy_version 95942 (0.0009) -[2023-10-15 06:08:16,569][88300] Updated weights for policy 1, policy_version 95952 (0.0008) -[2023-10-15 06:08:16,938][88300] Updated weights for policy 1, policy_version 95962 (0.0009) -[2023-10-15 06:08:18,172][88298] Updated weights for policy 0, policy_version 95370 (0.0007) -[2023-10-15 06:08:18,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 195919872. Throughput: 0: 1725.4, 1: 1749.3. Samples: 48986590. Policy #0 lag: (min: 19.0, avg: 24.0, max: 51.0) -[2023-10-15 06:08:18,534][87330] Avg episode reward: [(0, '22.950'), (1, '23.100')] -[2023-10-15 06:08:18,540][88298] Updated weights for policy 0, policy_version 95380 (0.0007) -[2023-10-15 06:08:18,913][88298] Updated weights for policy 0, policy_version 95390 (0.0008) -[2023-10-15 06:08:20,665][88300] Updated weights for policy 1, policy_version 95972 (0.0008) -[2023-10-15 06:08:21,029][88300] Updated weights for policy 1, policy_version 95982 (0.0009) -[2023-10-15 06:08:21,391][88300] Updated weights for policy 1, policy_version 95992 (0.0008) -[2023-10-15 06:08:22,718][88298] Updated weights for policy 0, policy_version 95400 (0.0008) -[2023-10-15 06:08:23,094][88298] Updated weights for policy 0, policy_version 95410 (0.0007) -[2023-10-15 06:08:23,474][88298] Updated weights for policy 0, policy_version 95420 (0.0010) -[2023-10-15 06:08:23,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 195985408. Throughput: 0: 1746.7, 1: 1727.9. Samples: 49007452. Policy #0 lag: (min: 19.0, avg: 24.0, max: 51.0) -[2023-10-15 06:08:23,535][87330] Avg episode reward: [(0, '22.920'), (1, '23.090')] -[2023-10-15 06:08:25,420][88300] Updated weights for policy 1, policy_version 96002 (0.0008) -[2023-10-15 06:08:25,780][88300] Updated weights for policy 1, policy_version 96012 (0.0008) -[2023-10-15 06:08:26,151][88300] Updated weights for policy 1, policy_version 96022 (0.0009) -[2023-10-15 06:08:26,521][88300] Updated weights for policy 1, policy_version 96032 (0.0008) -[2023-10-15 06:08:27,358][88298] Updated weights for policy 0, policy_version 95430 (0.0009) -[2023-10-15 06:08:27,717][88298] Updated weights for policy 0, policy_version 95440 (0.0008) -[2023-10-15 06:08:28,090][88298] Updated weights for policy 0, policy_version 95450 (0.0008) -[2023-10-15 06:08:28,534][87330] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 196083712. Throughput: 0: 1726.6, 1: 1744.8. Samples: 49028340. Policy #0 lag: (min: 19.0, avg: 24.0, max: 51.0) -[2023-10-15 06:08:28,535][87330] Avg episode reward: [(0, '22.930'), (1, '23.040')] -[2023-10-15 06:08:30,490][88300] Updated weights for policy 1, policy_version 96042 (0.0007) -[2023-10-15 06:08:30,854][88300] Updated weights for policy 1, policy_version 96052 (0.0007) -[2023-10-15 06:08:31,213][88300] Updated weights for policy 1, policy_version 96062 (0.0008) -[2023-10-15 06:08:31,779][88298] Updated weights for policy 0, policy_version 95460 (0.0008) -[2023-10-15 06:08:32,160][88298] Updated weights for policy 0, policy_version 95470 (0.0008) -[2023-10-15 06:08:32,531][88298] Updated weights for policy 0, policy_version 95480 (0.0009) -[2023-10-15 06:08:33,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 196149248. Throughput: 0: 1742.4, 1: 1738.1. Samples: 49038790. Policy #0 lag: (min: 19.0, avg: 24.0, max: 51.0) -[2023-10-15 06:08:33,534][87330] Avg episode reward: [(0, '22.940'), (1, '22.890')] -[2023-10-15 06:08:34,982][88300] Updated weights for policy 1, policy_version 96072 (0.0011) -[2023-10-15 06:08:35,357][88300] Updated weights for policy 1, policy_version 96082 (0.0008) -[2023-10-15 06:08:35,719][88300] Updated weights for policy 1, policy_version 96092 (0.0009) -[2023-10-15 06:08:36,467][88298] Updated weights for policy 0, policy_version 95490 (0.0008) -[2023-10-15 06:08:36,829][88298] Updated weights for policy 0, policy_version 95500 (0.0008) -[2023-10-15 06:08:37,209][88298] Updated weights for policy 0, policy_version 95510 (0.0007) -[2023-10-15 06:08:37,576][88298] Updated weights for policy 0, policy_version 95520 (0.0007) -[2023-10-15 06:08:38,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 196214784. Throughput: 0: 1737.3, 1: 1729.9. Samples: 49059614. Policy #0 lag: (min: 19.0, avg: 24.0, max: 51.0) -[2023-10-15 06:08:38,534][87330] Avg episode reward: [(0, '22.940'), (1, '22.880')] -[2023-10-15 06:08:39,595][88300] Updated weights for policy 1, policy_version 96102 (0.0008) -[2023-10-15 06:08:39,953][88300] Updated weights for policy 1, policy_version 96112 (0.0010) -[2023-10-15 06:08:40,329][88300] Updated weights for policy 1, policy_version 96122 (0.0009) -[2023-10-15 06:08:41,441][88298] Updated weights for policy 0, policy_version 95530 (0.0010) -[2023-10-15 06:08:41,804][88298] Updated weights for policy 0, policy_version 95540 (0.0010) -[2023-10-15 06:08:42,179][88298] Updated weights for policy 0, policy_version 95550 (0.0007) -[2023-10-15 06:08:43,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 196280320. Throughput: 0: 1724.9, 1: 1769.1. Samples: 49080854. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:08:43,534][87330] Avg episode reward: [(0, '22.840'), (1, '22.890')] -[2023-10-15 06:08:44,264][88300] Updated weights for policy 1, policy_version 96132 (0.0009) -[2023-10-15 06:08:44,660][88300] Updated weights for policy 1, policy_version 96142 (0.0011) -[2023-10-15 06:08:45,024][88300] Updated weights for policy 1, policy_version 96152 (0.0011) -[2023-10-15 06:08:45,980][88298] Updated weights for policy 0, policy_version 95560 (0.0007) -[2023-10-15 06:08:46,342][88298] Updated weights for policy 0, policy_version 95570 (0.0009) -[2023-10-15 06:08:46,724][88298] Updated weights for policy 0, policy_version 95580 (0.0009) -[2023-10-15 06:08:48,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 196345856. Throughput: 0: 1757.8, 1: 1737.2. Samples: 49091620. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:08:48,534][87330] Avg episode reward: [(0, '22.800'), (1, '22.920')] -[2023-10-15 06:08:48,980][88300] Updated weights for policy 1, policy_version 96162 (0.0007) -[2023-10-15 06:08:49,352][88300] Updated weights for policy 1, policy_version 96172 (0.0008) -[2023-10-15 06:08:49,724][88300] Updated weights for policy 1, policy_version 96182 (0.0009) -[2023-10-15 06:08:50,094][88300] Updated weights for policy 1, policy_version 96192 (0.0008) -[2023-10-15 06:08:50,713][88298] Updated weights for policy 0, policy_version 95590 (0.0008) -[2023-10-15 06:08:51,086][88298] Updated weights for policy 0, policy_version 95600 (0.0007) -[2023-10-15 06:08:51,459][88298] Updated weights for policy 0, policy_version 95610 (0.0009) -[2023-10-15 06:08:53,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13995.8). Total num frames: 196411392. Throughput: 0: 1734.5, 1: 1753.2. Samples: 49111818. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:08:53,534][87330] Avg episode reward: [(0, '22.930'), (1, '22.880')] -[2023-10-15 06:08:53,833][88300] Updated weights for policy 1, policy_version 96202 (0.0007) -[2023-10-15 06:08:54,194][88300] Updated weights for policy 1, policy_version 96212 (0.0007) -[2023-10-15 06:08:54,556][88300] Updated weights for policy 1, policy_version 96222 (0.0007) -[2023-10-15 06:08:55,327][88298] Updated weights for policy 0, policy_version 95620 (0.0008) -[2023-10-15 06:08:55,698][88298] Updated weights for policy 0, policy_version 95630 (0.0007) -[2023-10-15 06:08:56,079][88298] Updated weights for policy 0, policy_version 95640 (0.0007) -[2023-10-15 06:08:58,452][88300] Updated weights for policy 1, policy_version 96232 (0.0008) -[2023-10-15 06:08:58,534][87330] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 196476928. Throughput: 0: 1735.2, 1: 1764.7. Samples: 49133464. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:08:58,535][87330] Avg episode reward: [(0, '22.930'), (1, '22.960')] -[2023-10-15 06:08:58,544][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000095648_97943552.pth... -[2023-10-15 06:08:58,579][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000094016_96272384.pth -[2023-10-15 06:08:58,820][88300] Updated weights for policy 1, policy_version 96242 (0.0008) -[2023-10-15 06:08:59,173][88300] Updated weights for policy 1, policy_version 96252 (0.0009) -[2023-10-15 06:08:59,318][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000096256_98566144.pth... -[2023-10-15 06:08:59,347][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000094592_96862208.pth -[2023-10-15 06:08:59,955][88298] Updated weights for policy 0, policy_version 95650 (0.0010) -[2023-10-15 06:09:00,319][88298] Updated weights for policy 0, policy_version 95660 (0.0010) -[2023-10-15 06:09:00,691][88298] Updated weights for policy 0, policy_version 95670 (0.0009) -[2023-10-15 06:09:01,059][88298] Updated weights for policy 0, policy_version 95680 (0.0010) -[2023-10-15 06:09:03,123][88300] Updated weights for policy 1, policy_version 96262 (0.0010) -[2023-10-15 06:09:03,488][88300] Updated weights for policy 1, policy_version 96272 (0.0007) -[2023-10-15 06:09:03,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 196542464. Throughput: 0: 1751.1, 1: 1738.2. Samples: 49143610. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:09:03,535][87330] Avg episode reward: [(0, '22.910'), (1, '23.000')] -[2023-10-15 06:09:03,849][88300] Updated weights for policy 1, policy_version 96282 (0.0010) -[2023-10-15 06:09:04,951][88298] Updated weights for policy 0, policy_version 95690 (0.0008) -[2023-10-15 06:09:05,323][88298] Updated weights for policy 0, policy_version 95700 (0.0008) -[2023-10-15 06:09:05,698][88298] Updated weights for policy 0, policy_version 95710 (0.0008) -[2023-10-15 06:09:07,718][88300] Updated weights for policy 1, policy_version 96292 (0.0009) -[2023-10-15 06:09:08,090][88300] Updated weights for policy 1, policy_version 96302 (0.0009) -[2023-10-15 06:09:08,459][88300] Updated weights for policy 1, policy_version 96312 (0.0009) -[2023-10-15 06:09:08,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 196608000. Throughput: 0: 1735.7, 1: 1758.0. Samples: 49164670. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:09:08,535][87330] Avg episode reward: [(0, '22.850'), (1, '23.210')] -[2023-10-15 06:09:08,740][88033] Saving new best policy, reward=23.210! -[2023-10-15 06:09:09,437][88298] Updated weights for policy 0, policy_version 95720 (0.0008) -[2023-10-15 06:09:09,813][88298] Updated weights for policy 0, policy_version 95730 (0.0008) -[2023-10-15 06:09:10,181][88298] Updated weights for policy 0, policy_version 95740 (0.0008) -[2023-10-15 06:09:12,402][88300] Updated weights for policy 1, policy_version 96322 (0.0009) -[2023-10-15 06:09:12,770][88300] Updated weights for policy 1, policy_version 96332 (0.0009) -[2023-10-15 06:09:13,127][88300] Updated weights for policy 1, policy_version 96342 (0.0007) -[2023-10-15 06:09:13,491][88300] Updated weights for policy 1, policy_version 96352 (0.0009) -[2023-10-15 06:09:13,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 196706304. Throughput: 0: 1754.4, 1: 1732.6. Samples: 49185254. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:09:13,534][87330] Avg episode reward: [(0, '23.080'), (1, '23.220')] -[2023-10-15 06:09:13,544][88033] Saving new best policy, reward=23.220! -[2023-10-15 06:09:14,196][88298] Updated weights for policy 0, policy_version 95750 (0.0008) -[2023-10-15 06:09:14,570][88298] Updated weights for policy 0, policy_version 95760 (0.0008) -[2023-10-15 06:09:14,951][88298] Updated weights for policy 0, policy_version 95770 (0.0009) -[2023-10-15 06:09:17,439][88300] Updated weights for policy 1, policy_version 96362 (0.0008) -[2023-10-15 06:09:17,803][88300] Updated weights for policy 1, policy_version 96372 (0.0008) -[2023-10-15 06:09:18,165][88300] Updated weights for policy 1, policy_version 96382 (0.0009) -[2023-10-15 06:09:18,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 196771840. Throughput: 0: 1732.7, 1: 1753.3. Samples: 49195660. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:09:18,535][87330] Avg episode reward: [(0, '23.060'), (1, '23.210')] -[2023-10-15 06:09:18,943][88298] Updated weights for policy 0, policy_version 95780 (0.0007) -[2023-10-15 06:09:19,308][88298] Updated weights for policy 0, policy_version 95790 (0.0007) -[2023-10-15 06:09:19,676][88298] Updated weights for policy 0, policy_version 95800 (0.0008) -[2023-10-15 06:09:22,114][88300] Updated weights for policy 1, policy_version 96392 (0.0008) -[2023-10-15 06:09:22,480][88300] Updated weights for policy 1, policy_version 96402 (0.0010) -[2023-10-15 06:09:22,846][88300] Updated weights for policy 1, policy_version 96412 (0.0007) -[2023-10-15 06:09:23,509][88298] Updated weights for policy 0, policy_version 95810 (0.0007) -[2023-10-15 06:09:23,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 196837376. Throughput: 0: 1745.2, 1: 1749.4. Samples: 49216872. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:09:23,534][87330] Avg episode reward: [(0, '23.060'), (1, '23.230')] -[2023-10-15 06:09:23,535][88033] Saving new best policy, reward=23.230! -[2023-10-15 06:09:23,887][88298] Updated weights for policy 0, policy_version 95820 (0.0008) -[2023-10-15 06:09:24,261][88298] Updated weights for policy 0, policy_version 95830 (0.0009) -[2023-10-15 06:09:24,638][88298] Updated weights for policy 0, policy_version 95840 (0.0008) -[2023-10-15 06:09:26,748][88300] Updated weights for policy 1, policy_version 96422 (0.0008) -[2023-10-15 06:09:27,112][88300] Updated weights for policy 1, policy_version 96432 (0.0010) -[2023-10-15 06:09:27,475][88300] Updated weights for policy 1, policy_version 96442 (0.0010) -[2023-10-15 06:09:28,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 196902912. Throughput: 0: 1761.6, 1: 1723.2. Samples: 49237668. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:09:28,535][87330] Avg episode reward: [(0, '22.960'), (1, '23.230')] -[2023-10-15 06:09:28,546][88298] Updated weights for policy 0, policy_version 95850 (0.0009) -[2023-10-15 06:09:28,909][88298] Updated weights for policy 0, policy_version 95860 (0.0011) -[2023-10-15 06:09:29,281][88298] Updated weights for policy 0, policy_version 95870 (0.0009) -[2023-10-15 06:09:31,276][88300] Updated weights for policy 1, policy_version 96452 (0.0007) -[2023-10-15 06:09:31,677][88300] Updated weights for policy 1, policy_version 96462 (0.0007) -[2023-10-15 06:09:32,043][88300] Updated weights for policy 1, policy_version 96472 (0.0007) -[2023-10-15 06:09:33,045][88298] Updated weights for policy 0, policy_version 95880 (0.0008) -[2023-10-15 06:09:33,415][88298] Updated weights for policy 0, policy_version 95890 (0.0008) -[2023-10-15 06:09:33,534][87330] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 196968448. Throughput: 0: 1730.0, 1: 1755.2. Samples: 49248454. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:09:33,535][87330] Avg episode reward: [(0, '22.950'), (1, '23.120')] -[2023-10-15 06:09:33,796][88298] Updated weights for policy 0, policy_version 95900 (0.0009) -[2023-10-15 06:09:35,808][88300] Updated weights for policy 1, policy_version 96482 (0.0007) -[2023-10-15 06:09:36,166][88300] Updated weights for policy 1, policy_version 96492 (0.0008) -[2023-10-15 06:09:36,541][88300] Updated weights for policy 1, policy_version 96502 (0.0008) -[2023-10-15 06:09:36,896][88300] Updated weights for policy 1, policy_version 96512 (0.0010) -[2023-10-15 06:09:37,688][88298] Updated weights for policy 0, policy_version 95910 (0.0008) -[2023-10-15 06:09:38,073][88298] Updated weights for policy 0, policy_version 95920 (0.0009) -[2023-10-15 06:09:38,438][88298] Updated weights for policy 0, policy_version 95930 (0.0008) -[2023-10-15 06:09:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 197033984. Throughput: 0: 1764.7, 1: 1729.5. Samples: 49269056. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:09:38,534][87330] Avg episode reward: [(0, '22.980'), (1, '23.130')] -[2023-10-15 06:09:40,732][88300] Updated weights for policy 1, policy_version 96522 (0.0007) -[2023-10-15 06:09:41,093][88300] Updated weights for policy 1, policy_version 96532 (0.0007) -[2023-10-15 06:09:41,457][88300] Updated weights for policy 1, policy_version 96542 (0.0008) -[2023-10-15 06:09:42,262][88298] Updated weights for policy 0, policy_version 95940 (0.0007) -[2023-10-15 06:09:42,635][88298] Updated weights for policy 0, policy_version 95950 (0.0008) -[2023-10-15 06:09:43,010][88298] Updated weights for policy 0, policy_version 95960 (0.0009) -[2023-10-15 06:09:43,534][87330] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 197132288. Throughput: 0: 1740.1, 1: 1736.6. Samples: 49289914. Policy #0 lag: (min: 14.0, avg: 36.8, max: 40.0) -[2023-10-15 06:09:43,534][87330] Avg episode reward: [(0, '23.040'), (1, '23.140')] -[2023-10-15 06:09:45,290][88300] Updated weights for policy 1, policy_version 96552 (0.0009) -[2023-10-15 06:09:45,653][88300] Updated weights for policy 1, policy_version 96562 (0.0010) -[2023-10-15 06:09:46,025][88300] Updated weights for policy 1, policy_version 96572 (0.0010) -[2023-10-15 06:09:47,058][88298] Updated weights for policy 0, policy_version 95970 (0.0008) -[2023-10-15 06:09:47,427][88298] Updated weights for policy 0, policy_version 95980 (0.0008) -[2023-10-15 06:09:47,798][88298] Updated weights for policy 0, policy_version 95990 (0.0010) -[2023-10-15 06:09:48,171][88298] Updated weights for policy 0, policy_version 96000 (0.0009) -[2023-10-15 06:09:48,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 197197824. Throughput: 0: 1743.6, 1: 1734.5. Samples: 49300126. Policy #0 lag: (min: 14.0, avg: 36.8, max: 40.0) -[2023-10-15 06:09:48,535][87330] Avg episode reward: [(0, '23.090'), (1, '23.120')] -[2023-10-15 06:09:49,947][88300] Updated weights for policy 1, policy_version 96582 (0.0010) -[2023-10-15 06:09:50,312][88300] Updated weights for policy 1, policy_version 96592 (0.0010) -[2023-10-15 06:09:50,672][88300] Updated weights for policy 1, policy_version 96602 (0.0009) -[2023-10-15 06:09:51,821][88298] Updated weights for policy 0, policy_version 96010 (0.0008) -[2023-10-15 06:09:52,204][88298] Updated weights for policy 0, policy_version 96020 (0.0011) -[2023-10-15 06:09:52,570][88298] Updated weights for policy 0, policy_version 96030 (0.0007) -[2023-10-15 06:09:53,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 197263360. Throughput: 0: 1749.7, 1: 1736.0. Samples: 49321522. Policy #0 lag: (min: 14.0, avg: 36.8, max: 40.0) -[2023-10-15 06:09:53,534][87330] Avg episode reward: [(0, '23.080'), (1, '22.920')] -[2023-10-15 06:09:54,442][88300] Updated weights for policy 1, policy_version 96612 (0.0008) -[2023-10-15 06:09:54,807][88300] Updated weights for policy 1, policy_version 96622 (0.0008) -[2023-10-15 06:09:55,177][88300] Updated weights for policy 1, policy_version 96632 (0.0008) -[2023-10-15 06:09:56,668][88298] Updated weights for policy 0, policy_version 96040 (0.0010) -[2023-10-15 06:09:57,039][88298] Updated weights for policy 0, policy_version 96050 (0.0007) -[2023-10-15 06:09:57,403][88298] Updated weights for policy 0, policy_version 96060 (0.0007) -[2023-10-15 06:09:58,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 197328896. Throughput: 0: 1721.7, 1: 1764.4. Samples: 49342128. Policy #0 lag: (min: 14.0, avg: 36.8, max: 40.0) -[2023-10-15 06:09:58,535][87330] Avg episode reward: [(0, '23.110'), (1, '22.960')] -[2023-10-15 06:09:58,980][88300] Updated weights for policy 1, policy_version 96642 (0.0007) -[2023-10-15 06:09:59,354][88300] Updated weights for policy 1, policy_version 96652 (0.0008) -[2023-10-15 06:09:59,721][88300] Updated weights for policy 1, policy_version 96662 (0.0009) -[2023-10-15 06:10:00,089][88300] Updated weights for policy 1, policy_version 96672 (0.0009) -[2023-10-15 06:10:01,401][88298] Updated weights for policy 0, policy_version 96070 (0.0010) -[2023-10-15 06:10:01,768][88298] Updated weights for policy 0, policy_version 96080 (0.0009) -[2023-10-15 06:10:02,148][88298] Updated weights for policy 0, policy_version 96090 (0.0007) -[2023-10-15 06:10:03,534][87330] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 197394432. Throughput: 0: 1755.8, 1: 1739.3. Samples: 49352938. Policy #0 lag: (min: 14.0, avg: 36.8, max: 40.0) -[2023-10-15 06:10:03,535][87330] Avg episode reward: [(0, '23.190'), (1, '23.040')] -[2023-10-15 06:10:04,067][88300] Updated weights for policy 1, policy_version 96682 (0.0009) -[2023-10-15 06:10:04,432][88300] Updated weights for policy 1, policy_version 96692 (0.0010) -[2023-10-15 06:10:04,806][88300] Updated weights for policy 1, policy_version 96702 (0.0009) -[2023-10-15 06:10:06,169][88298] Updated weights for policy 0, policy_version 96100 (0.0009) -[2023-10-15 06:10:06,540][88298] Updated weights for policy 0, policy_version 96110 (0.0009) -[2023-10-15 06:10:06,918][88298] Updated weights for policy 0, policy_version 96120 (0.0010) -[2023-10-15 06:10:08,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 197459968. Throughput: 0: 1730.4, 1: 1751.9. Samples: 49373580. Policy #0 lag: (min: 14.0, avg: 36.8, max: 40.0) -[2023-10-15 06:10:08,535][87330] Avg episode reward: [(0, '23.180'), (1, '22.860')] -[2023-10-15 06:10:08,700][88300] Updated weights for policy 1, policy_version 96712 (0.0010) -[2023-10-15 06:10:09,069][88300] Updated weights for policy 1, policy_version 96722 (0.0009) -[2023-10-15 06:10:09,438][88300] Updated weights for policy 1, policy_version 96732 (0.0010) -[2023-10-15 06:10:10,726][88298] Updated weights for policy 0, policy_version 96130 (0.0010) -[2023-10-15 06:10:11,087][88298] Updated weights for policy 0, policy_version 96140 (0.0008) -[2023-10-15 06:10:11,453][88298] Updated weights for policy 0, policy_version 96150 (0.0009) -[2023-10-15 06:10:11,824][88298] Updated weights for policy 0, policy_version 96160 (0.0007) -[2023-10-15 06:10:13,311][88300] Updated weights for policy 1, policy_version 96742 (0.0009) -[2023-10-15 06:10:13,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 197525504. Throughput: 0: 1717.8, 1: 1773.2. Samples: 49394762. Policy #0 lag: (min: 14.0, avg: 36.8, max: 40.0) -[2023-10-15 06:10:13,534][87330] Avg episode reward: [(0, '23.200'), (1, '22.860')] -[2023-10-15 06:10:13,681][88300] Updated weights for policy 1, policy_version 96752 (0.0007) -[2023-10-15 06:10:14,043][88300] Updated weights for policy 1, policy_version 96762 (0.0009) -[2023-10-15 06:10:15,760][88298] Updated weights for policy 0, policy_version 96170 (0.0010) -[2023-10-15 06:10:16,130][88298] Updated weights for policy 0, policy_version 96180 (0.0009) -[2023-10-15 06:10:16,511][88298] Updated weights for policy 0, policy_version 96190 (0.0008) -[2023-10-15 06:10:17,954][88300] Updated weights for policy 1, policy_version 96772 (0.0009) -[2023-10-15 06:10:18,358][88300] Updated weights for policy 1, policy_version 96782 (0.0008) -[2023-10-15 06:10:18,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 197591040. Throughput: 0: 1738.9, 1: 1748.5. Samples: 49405382. Policy #0 lag: (min: 14.0, avg: 36.8, max: 40.0) -[2023-10-15 06:10:18,534][87330] Avg episode reward: [(0, '23.160'), (1, '22.680')] -[2023-10-15 06:10:18,730][88300] Updated weights for policy 1, policy_version 96792 (0.0008) -[2023-10-15 06:10:20,395][88298] Updated weights for policy 0, policy_version 96200 (0.0008) -[2023-10-15 06:10:20,772][88298] Updated weights for policy 0, policy_version 96210 (0.0008) -[2023-10-15 06:10:21,151][88298] Updated weights for policy 0, policy_version 96220 (0.0011) -[2023-10-15 06:10:22,664][88300] Updated weights for policy 1, policy_version 96802 (0.0009) -[2023-10-15 06:10:23,031][88300] Updated weights for policy 1, policy_version 96812 (0.0011) -[2023-10-15 06:10:23,394][88300] Updated weights for policy 1, policy_version 96822 (0.0010) -[2023-10-15 06:10:23,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 197656576. Throughput: 0: 1716.0, 1: 1771.7. Samples: 49426004. Policy #0 lag: (min: 14.0, avg: 36.8, max: 40.0) -[2023-10-15 06:10:23,535][87330] Avg episode reward: [(0, '23.160'), (1, '22.690')] -[2023-10-15 06:10:23,769][88300] Updated weights for policy 1, policy_version 96832 (0.0009) -[2023-10-15 06:10:24,841][88298] Updated weights for policy 0, policy_version 96230 (0.0009) -[2023-10-15 06:10:25,214][88298] Updated weights for policy 0, policy_version 96240 (0.0008) -[2023-10-15 06:10:25,588][88298] Updated weights for policy 0, policy_version 96250 (0.0007) -[2023-10-15 06:10:27,721][88300] Updated weights for policy 1, policy_version 96842 (0.0008) -[2023-10-15 06:10:28,098][88300] Updated weights for policy 1, policy_version 96852 (0.0007) -[2023-10-15 06:10:28,473][88300] Updated weights for policy 1, policy_version 96862 (0.0007) -[2023-10-15 06:10:28,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 197722112. Throughput: 0: 1736.3, 1: 1745.3. Samples: 49446584. Policy #0 lag: (min: 14.0, avg: 36.8, max: 40.0) -[2023-10-15 06:10:28,534][87330] Avg episode reward: [(0, '23.170'), (1, '22.610')] -[2023-10-15 06:10:29,474][88298] Updated weights for policy 0, policy_version 96260 (0.0008) -[2023-10-15 06:10:29,837][88298] Updated weights for policy 0, policy_version 96270 (0.0010) -[2023-10-15 06:10:30,205][88298] Updated weights for policy 0, policy_version 96280 (0.0011) -[2023-10-15 06:10:32,354][88300] Updated weights for policy 1, policy_version 96872 (0.0008) -[2023-10-15 06:10:32,716][88300] Updated weights for policy 1, policy_version 96882 (0.0008) -[2023-10-15 06:10:33,083][88300] Updated weights for policy 1, policy_version 96892 (0.0009) -[2023-10-15 06:10:33,534][87330] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 197820416. Throughput: 0: 1718.3, 1: 1763.1. Samples: 49456788. Policy #0 lag: (min: 14.0, avg: 36.8, max: 40.0) -[2023-10-15 06:10:33,535][87330] Avg episode reward: [(0, '23.180'), (1, '22.540')] -[2023-10-15 06:10:33,960][88298] Updated weights for policy 0, policy_version 96290 (0.0011) -[2023-10-15 06:10:34,327][88298] Updated weights for policy 0, policy_version 96300 (0.0009) -[2023-10-15 06:10:34,698][88298] Updated weights for policy 0, policy_version 96310 (0.0010) -[2023-10-15 06:10:35,068][88298] Updated weights for policy 0, policy_version 96320 (0.0009) -[2023-10-15 06:10:36,984][88300] Updated weights for policy 1, policy_version 96902 (0.0008) -[2023-10-15 06:10:37,343][88300] Updated weights for policy 1, policy_version 96912 (0.0007) -[2023-10-15 06:10:37,706][88300] Updated weights for policy 1, policy_version 96922 (0.0010) -[2023-10-15 06:10:38,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 197885952. Throughput: 0: 1722.6, 1: 1751.5. Samples: 49477856. Policy #0 lag: (min: 14.0, avg: 36.8, max: 40.0) -[2023-10-15 06:10:38,534][87330] Avg episode reward: [(0, '23.250'), (1, '22.740')] -[2023-10-15 06:10:38,535][87905] Saving new best policy, reward=23.250! -[2023-10-15 06:10:39,249][88298] Updated weights for policy 0, policy_version 96330 (0.0009) -[2023-10-15 06:10:39,624][88298] Updated weights for policy 0, policy_version 96340 (0.0008) -[2023-10-15 06:10:40,000][88298] Updated weights for policy 0, policy_version 96350 (0.0007) -[2023-10-15 06:10:41,590][88300] Updated weights for policy 1, policy_version 96932 (0.0009) -[2023-10-15 06:10:41,963][88300] Updated weights for policy 1, policy_version 96942 (0.0010) -[2023-10-15 06:10:42,324][88300] Updated weights for policy 1, policy_version 96952 (0.0009) -[2023-10-15 06:10:43,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 197951488. Throughput: 0: 1747.4, 1: 1727.7. Samples: 49498504. Policy #0 lag: (min: 14.0, avg: 36.8, max: 40.0) -[2023-10-15 06:10:43,535][87330] Avg episode reward: [(0, '22.900'), (1, '22.720')] -[2023-10-15 06:10:43,951][88298] Updated weights for policy 0, policy_version 96360 (0.0008) -[2023-10-15 06:10:44,335][88298] Updated weights for policy 0, policy_version 96370 (0.0009) -[2023-10-15 06:10:44,705][88298] Updated weights for policy 0, policy_version 96380 (0.0008) -[2023-10-15 06:10:46,360][88300] Updated weights for policy 1, policy_version 96962 (0.0008) -[2023-10-15 06:10:46,722][88300] Updated weights for policy 1, policy_version 96972 (0.0011) -[2023-10-15 06:10:47,088][88300] Updated weights for policy 1, policy_version 96982 (0.0011) -[2023-10-15 06:10:47,457][88300] Updated weights for policy 1, policy_version 96992 (0.0011) -[2023-10-15 06:10:48,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 198017024. Throughput: 0: 1715.6, 1: 1758.0. Samples: 49509248. Policy #0 lag: (min: 0.0, avg: 23.4, max: 32.0) -[2023-10-15 06:10:48,534][87330] Avg episode reward: [(0, '22.910'), (1, '22.680')] -[2023-10-15 06:10:48,601][88298] Updated weights for policy 0, policy_version 96390 (0.0008) -[2023-10-15 06:10:48,966][88298] Updated weights for policy 0, policy_version 96400 (0.0009) -[2023-10-15 06:10:49,342][88298] Updated weights for policy 0, policy_version 96410 (0.0011) -[2023-10-15 06:10:51,412][88300] Updated weights for policy 1, policy_version 97002 (0.0009) -[2023-10-15 06:10:51,788][88300] Updated weights for policy 1, policy_version 97012 (0.0008) -[2023-10-15 06:10:52,158][88300] Updated weights for policy 1, policy_version 97022 (0.0008) -[2023-10-15 06:10:53,350][88298] Updated weights for policy 0, policy_version 96420 (0.0007) -[2023-10-15 06:10:53,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 198082560. Throughput: 0: 1739.0, 1: 1725.4. Samples: 49529478. Policy #0 lag: (min: 0.0, avg: 23.4, max: 32.0) -[2023-10-15 06:10:53,535][87330] Avg episode reward: [(0, '22.830'), (1, '22.820')] -[2023-10-15 06:10:53,723][88298] Updated weights for policy 0, policy_version 96430 (0.0007) -[2023-10-15 06:10:54,101][88298] Updated weights for policy 0, policy_version 96440 (0.0008) -[2023-10-15 06:10:55,991][88300] Updated weights for policy 1, policy_version 97032 (0.0009) -[2023-10-15 06:10:56,357][88300] Updated weights for policy 1, policy_version 97042 (0.0009) -[2023-10-15 06:10:56,716][88300] Updated weights for policy 1, policy_version 97052 (0.0008) -[2023-10-15 06:10:57,999][88298] Updated weights for policy 0, policy_version 96450 (0.0007) -[2023-10-15 06:10:58,365][88298] Updated weights for policy 0, policy_version 96460 (0.0007) -[2023-10-15 06:10:58,534][87330] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 198148096. Throughput: 0: 1751.0, 1: 1723.7. Samples: 49551122. Policy #0 lag: (min: 0.0, avg: 23.4, max: 32.0) -[2023-10-15 06:10:58,535][87330] Avg episode reward: [(0, '22.640'), (1, '22.850')] -[2023-10-15 06:10:58,547][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000097056_99385344.pth... -[2023-10-15 06:10:58,583][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000095424_97714176.pth -[2023-10-15 06:10:58,730][88298] Updated weights for policy 0, policy_version 96470 (0.0007) -[2023-10-15 06:10:59,104][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000096480_98795520.pth... -[2023-10-15 06:10:59,108][88298] Updated weights for policy 0, policy_version 96480 (0.0007) -[2023-10-15 06:10:59,133][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000094848_97124352.pth -[2023-10-15 06:11:00,633][88300] Updated weights for policy 1, policy_version 97062 (0.0008) -[2023-10-15 06:11:00,994][88300] Updated weights for policy 1, policy_version 97072 (0.0010) -[2023-10-15 06:11:01,368][88300] Updated weights for policy 1, policy_version 97082 (0.0010) -[2023-10-15 06:11:02,987][88298] Updated weights for policy 0, policy_version 96490 (0.0007) -[2023-10-15 06:11:03,371][88298] Updated weights for policy 0, policy_version 96500 (0.0008) -[2023-10-15 06:11:03,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13884.7). Total num frames: 198213632. Throughput: 0: 1728.3, 1: 1728.0. Samples: 49560916. Policy #0 lag: (min: 0.0, avg: 23.4, max: 32.0) -[2023-10-15 06:11:03,534][87330] Avg episode reward: [(0, '22.610'), (1, '23.120')] -[2023-10-15 06:11:03,734][88298] Updated weights for policy 0, policy_version 96510 (0.0007) -[2023-10-15 06:11:05,197][88300] Updated weights for policy 1, policy_version 97092 (0.0008) -[2023-10-15 06:11:05,562][88300] Updated weights for policy 1, policy_version 97102 (0.0007) -[2023-10-15 06:11:05,927][88300] Updated weights for policy 1, policy_version 97112 (0.0008) -[2023-10-15 06:11:07,791][88298] Updated weights for policy 0, policy_version 96520 (0.0008) -[2023-10-15 06:11:08,166][88298] Updated weights for policy 0, policy_version 96530 (0.0007) -[2023-10-15 06:11:08,534][87330] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 198279168. Throughput: 0: 1746.5, 1: 1723.1. Samples: 49582134. Policy #0 lag: (min: 0.0, avg: 23.4, max: 32.0) -[2023-10-15 06:11:08,535][88298] Updated weights for policy 0, policy_version 96540 (0.0007) -[2023-10-15 06:11:08,535][87330] Avg episode reward: [(0, '22.620'), (1, '23.170')] -[2023-10-15 06:11:09,661][88300] Updated weights for policy 1, policy_version 97122 (0.0008) -[2023-10-15 06:11:10,040][88300] Updated weights for policy 1, policy_version 97132 (0.0010) -[2023-10-15 06:11:10,399][88300] Updated weights for policy 1, policy_version 97142 (0.0007) -[2023-10-15 06:11:10,771][88300] Updated weights for policy 1, policy_version 97152 (0.0007) -[2023-10-15 06:11:12,374][88298] Updated weights for policy 0, policy_version 96550 (0.0008) -[2023-10-15 06:11:12,764][88298] Updated weights for policy 0, policy_version 96560 (0.0008) -[2023-10-15 06:11:13,140][88298] Updated weights for policy 0, policy_version 96570 (0.0007) -[2023-10-15 06:11:13,534][87330] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 198377472. Throughput: 0: 1733.1, 1: 1747.1. Samples: 49603190. Policy #0 lag: (min: 0.0, avg: 23.4, max: 32.0) -[2023-10-15 06:11:13,535][87330] Avg episode reward: [(0, '22.550'), (1, '23.190')] -[2023-10-15 06:11:14,688][88300] Updated weights for policy 1, policy_version 97162 (0.0010) -[2023-10-15 06:11:15,048][88300] Updated weights for policy 1, policy_version 97172 (0.0009) -[2023-10-15 06:11:15,418][88300] Updated weights for policy 1, policy_version 97182 (0.0009) -[2023-10-15 06:11:16,952][88298] Updated weights for policy 0, policy_version 96580 (0.0009) -[2023-10-15 06:11:17,327][88298] Updated weights for policy 0, policy_version 96590 (0.0010) -[2023-10-15 06:11:17,701][88298] Updated weights for policy 0, policy_version 96600 (0.0011) -[2023-10-15 06:11:18,534][87330] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 198443008. Throughput: 0: 1752.0, 1: 1727.5. Samples: 49613366. Policy #0 lag: (min: 0.0, avg: 23.4, max: 32.0) -[2023-10-15 06:11:18,535][87330] Avg episode reward: [(0, '22.910'), (1, '23.240')] -[2023-10-15 06:11:18,536][88033] Saving new best policy, reward=23.240! -[2023-10-15 06:11:19,275][88300] Updated weights for policy 1, policy_version 97192 (0.0009) -[2023-10-15 06:11:19,639][88300] Updated weights for policy 1, policy_version 97202 (0.0011) -[2023-10-15 06:11:20,009][88300] Updated weights for policy 1, policy_version 97212 (0.0012) -[2023-10-15 06:11:21,669][88298] Updated weights for policy 0, policy_version 96610 (0.0007) -[2023-10-15 06:11:22,031][88298] Updated weights for policy 0, policy_version 96620 (0.0008) -[2023-10-15 06:11:22,398][88298] Updated weights for policy 0, policy_version 96630 (0.0009) -[2023-10-15 06:11:22,773][88298] Updated weights for policy 0, policy_version 96640 (0.0009) -[2023-10-15 06:11:23,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 198508544. Throughput: 0: 1746.0, 1: 1743.7. Samples: 49634892. Policy #0 lag: (min: 0.0, avg: 23.4, max: 32.0) -[2023-10-15 06:11:23,535][87330] Avg episode reward: [(0, '23.010'), (1, '23.310')] -[2023-10-15 06:11:23,835][88300] Updated weights for policy 1, policy_version 97222 (0.0008) -[2023-10-15 06:11:24,200][88300] Updated weights for policy 1, policy_version 97232 (0.0007) -[2023-10-15 06:11:24,571][88300] Updated weights for policy 1, policy_version 97242 (0.0007) -[2023-10-15 06:11:24,784][88033] Saving new best policy, reward=23.310! -[2023-10-15 06:11:26,741][88298] Updated weights for policy 0, policy_version 96650 (0.0010) -[2023-10-15 06:11:27,115][88298] Updated weights for policy 0, policy_version 96660 (0.0008) -[2023-10-15 06:11:27,483][88298] Updated weights for policy 0, policy_version 96670 (0.0009) -[2023-10-15 06:11:28,458][88300] Updated weights for policy 1, policy_version 97252 (0.0008) -[2023-10-15 06:11:28,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 198574080. Throughput: 0: 1722.4, 1: 1766.6. Samples: 49655512. Policy #0 lag: (min: 0.0, avg: 23.4, max: 32.0) -[2023-10-15 06:11:28,534][87330] Avg episode reward: [(0, '23.230'), (1, '23.290')] -[2023-10-15 06:11:28,821][88300] Updated weights for policy 1, policy_version 97262 (0.0008) -[2023-10-15 06:11:29,189][88300] Updated weights for policy 1, policy_version 97272 (0.0009) -[2023-10-15 06:11:31,413][88298] Updated weights for policy 0, policy_version 96680 (0.0009) -[2023-10-15 06:11:31,782][88298] Updated weights for policy 0, policy_version 96690 (0.0008) -[2023-10-15 06:11:32,159][88298] Updated weights for policy 0, policy_version 96700 (0.0008) -[2023-10-15 06:11:32,921][88300] Updated weights for policy 1, policy_version 97282 (0.0008) -[2023-10-15 06:11:33,282][88300] Updated weights for policy 1, policy_version 97292 (0.0009) -[2023-10-15 06:11:33,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 198639616. Throughput: 0: 1753.4, 1: 1737.6. Samples: 49666344. Policy #0 lag: (min: 0.0, avg: 23.4, max: 32.0) -[2023-10-15 06:11:33,535][87330] Avg episode reward: [(0, '23.240'), (1, '23.100')] -[2023-10-15 06:11:33,657][88300] Updated weights for policy 1, policy_version 97302 (0.0011) -[2023-10-15 06:11:34,021][88300] Updated weights for policy 1, policy_version 97312 (0.0010) -[2023-10-15 06:11:36,117][88298] Updated weights for policy 0, policy_version 96710 (0.0008) -[2023-10-15 06:11:36,486][88298] Updated weights for policy 0, policy_version 96720 (0.0008) -[2023-10-15 06:11:36,858][88298] Updated weights for policy 0, policy_version 96730 (0.0007) -[2023-10-15 06:11:38,005][88300] Updated weights for policy 1, policy_version 97322 (0.0009) -[2023-10-15 06:11:38,374][88300] Updated weights for policy 1, policy_version 97332 (0.0009) -[2023-10-15 06:11:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 198705152. Throughput: 0: 1730.3, 1: 1767.7. Samples: 49686884. Policy #0 lag: (min: 0.0, avg: 23.4, max: 32.0) -[2023-10-15 06:11:38,534][87330] Avg episode reward: [(0, '23.250'), (1, '23.110')] -[2023-10-15 06:11:38,747][88300] Updated weights for policy 1, policy_version 97342 (0.0008) -[2023-10-15 06:11:40,514][88298] Updated weights for policy 0, policy_version 96740 (0.0008) -[2023-10-15 06:11:40,888][88298] Updated weights for policy 0, policy_version 96750 (0.0008) -[2023-10-15 06:11:41,248][88298] Updated weights for policy 0, policy_version 96760 (0.0008) -[2023-10-15 06:11:42,555][88300] Updated weights for policy 1, policy_version 97352 (0.0008) -[2023-10-15 06:11:42,923][88300] Updated weights for policy 1, policy_version 97362 (0.0008) -[2023-10-15 06:11:43,295][88300] Updated weights for policy 1, policy_version 97372 (0.0008) -[2023-10-15 06:11:43,534][87330] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 198803456. Throughput: 0: 1722.5, 1: 1748.1. Samples: 49707300. Policy #0 lag: (min: 0.0, avg: 23.4, max: 32.0) -[2023-10-15 06:11:43,534][87330] Avg episode reward: [(0, '23.300'), (1, '23.100')] -[2023-10-15 06:11:43,544][87905] Saving new best policy, reward=23.300! -[2023-10-15 06:11:45,129][88298] Updated weights for policy 0, policy_version 96770 (0.0007) -[2023-10-15 06:11:45,498][88298] Updated weights for policy 0, policy_version 96780 (0.0007) -[2023-10-15 06:11:45,858][88298] Updated weights for policy 0, policy_version 96790 (0.0009) -[2023-10-15 06:11:46,226][88298] Updated weights for policy 0, policy_version 96800 (0.0011) -[2023-10-15 06:11:47,140][88300] Updated weights for policy 1, policy_version 97382 (0.0007) -[2023-10-15 06:11:47,517][88300] Updated weights for policy 1, policy_version 97392 (0.0007) -[2023-10-15 06:11:47,876][88300] Updated weights for policy 1, policy_version 97402 (0.0010) -[2023-10-15 06:11:48,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 198868992. Throughput: 0: 1738.8, 1: 1761.4. Samples: 49718424. Policy #0 lag: (min: 1.0, avg: 9.4, max: 33.0) -[2023-10-15 06:11:48,534][87330] Avg episode reward: [(0, '23.280'), (1, '23.100')] -[2023-10-15 06:11:50,227][88298] Updated weights for policy 0, policy_version 96810 (0.0010) -[2023-10-15 06:11:50,593][88298] Updated weights for policy 0, policy_version 96820 (0.0008) -[2023-10-15 06:11:50,974][88298] Updated weights for policy 0, policy_version 96830 (0.0007) -[2023-10-15 06:11:51,894][88300] Updated weights for policy 1, policy_version 97412 (0.0008) -[2023-10-15 06:11:52,256][88300] Updated weights for policy 1, policy_version 97422 (0.0008) -[2023-10-15 06:11:52,630][88300] Updated weights for policy 1, policy_version 97432 (0.0009) -[2023-10-15 06:11:53,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 198934528. Throughput: 0: 1719.0, 1: 1761.1. Samples: 49738738. Policy #0 lag: (min: 1.0, avg: 9.4, max: 33.0) -[2023-10-15 06:11:53,535][87330] Avg episode reward: [(0, '23.260'), (1, '23.020')] -[2023-10-15 06:11:54,889][88298] Updated weights for policy 0, policy_version 96840 (0.0009) -[2023-10-15 06:11:55,270][88298] Updated weights for policy 0, policy_version 96850 (0.0011) -[2023-10-15 06:11:55,636][88298] Updated weights for policy 0, policy_version 96860 (0.0009) -[2023-10-15 06:11:56,361][88300] Updated weights for policy 1, policy_version 97442 (0.0009) -[2023-10-15 06:11:56,756][88300] Updated weights for policy 1, policy_version 97452 (0.0009) -[2023-10-15 06:11:57,124][88300] Updated weights for policy 1, policy_version 97462 (0.0008) -[2023-10-15 06:11:57,487][88300] Updated weights for policy 1, policy_version 97472 (0.0007) -[2023-10-15 06:11:58,534][87330] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 199000064. Throughput: 0: 1734.3, 1: 1750.7. Samples: 49760016. Policy #0 lag: (min: 1.0, avg: 9.4, max: 33.0) -[2023-10-15 06:11:58,535][87330] Avg episode reward: [(0, '23.290'), (1, '23.030')] -[2023-10-15 06:11:59,435][88298] Updated weights for policy 0, policy_version 96870 (0.0008) -[2023-10-15 06:11:59,819][88298] Updated weights for policy 0, policy_version 96880 (0.0008) -[2023-10-15 06:12:00,199][88298] Updated weights for policy 0, policy_version 96890 (0.0010) -[2023-10-15 06:12:01,317][88300] Updated weights for policy 1, policy_version 97482 (0.0007) -[2023-10-15 06:12:01,679][88300] Updated weights for policy 1, policy_version 97492 (0.0008) -[2023-10-15 06:12:02,051][88300] Updated weights for policy 1, policy_version 97502 (0.0009) -[2023-10-15 06:12:03,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 199065600. Throughput: 0: 1714.0, 1: 1779.8. Samples: 49770584. Policy #0 lag: (min: 1.0, avg: 9.4, max: 33.0) -[2023-10-15 06:12:03,535][87330] Avg episode reward: [(0, '23.300'), (1, '22.960')] -[2023-10-15 06:12:04,239][88298] Updated weights for policy 0, policy_version 96900 (0.0010) -[2023-10-15 06:12:04,611][88298] Updated weights for policy 0, policy_version 96910 (0.0010) -[2023-10-15 06:12:04,980][88298] Updated weights for policy 0, policy_version 96920 (0.0010) -[2023-10-15 06:12:05,849][88300] Updated weights for policy 1, policy_version 97512 (0.0010) -[2023-10-15 06:12:06,228][88300] Updated weights for policy 1, policy_version 97522 (0.0011) -[2023-10-15 06:12:06,584][88300] Updated weights for policy 1, policy_version 97532 (0.0011) -[2023-10-15 06:12:08,534][87330] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 13884.7). Total num frames: 199131136. Throughput: 0: 1720.5, 1: 1748.3. Samples: 49790988. Policy #0 lag: (min: 1.0, avg: 9.4, max: 33.0) -[2023-10-15 06:12:08,535][87330] Avg episode reward: [(0, '23.300'), (1, '22.920')] -[2023-10-15 06:12:08,835][88298] Updated weights for policy 0, policy_version 96930 (0.0010) -[2023-10-15 06:12:09,190][88298] Updated weights for policy 0, policy_version 96940 (0.0009) -[2023-10-15 06:12:09,564][88298] Updated weights for policy 0, policy_version 96950 (0.0008) -[2023-10-15 06:12:09,928][88298] Updated weights for policy 0, policy_version 96960 (0.0009) -[2023-10-15 06:12:10,399][88300] Updated weights for policy 1, policy_version 97542 (0.0012) -[2023-10-15 06:12:10,766][88300] Updated weights for policy 1, policy_version 97552 (0.0008) -[2023-10-15 06:12:11,129][88300] Updated weights for policy 1, policy_version 97562 (0.0007) -[2023-10-15 06:12:13,534][87330] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 199196672. Throughput: 0: 1747.2, 1: 1753.0. Samples: 49813022. Policy #0 lag: (min: 1.0, avg: 9.4, max: 33.0) -[2023-10-15 06:12:13,534][87330] Avg episode reward: [(0, '23.290'), (1, '22.870')] -[2023-10-15 06:12:13,888][88298] Updated weights for policy 0, policy_version 96970 (0.0007) -[2023-10-15 06:12:14,255][88298] Updated weights for policy 0, policy_version 96980 (0.0010) -[2023-10-15 06:12:14,634][88298] Updated weights for policy 0, policy_version 96990 (0.0007) -[2023-10-15 06:12:14,949][88300] Updated weights for policy 1, policy_version 97572 (0.0009) -[2023-10-15 06:12:15,313][88300] Updated weights for policy 1, policy_version 97582 (0.0007) -[2023-10-15 06:12:15,692][88300] Updated weights for policy 1, policy_version 97592 (0.0007) -[2023-10-15 06:12:18,389][88298] Updated weights for policy 0, policy_version 97000 (0.0008) -[2023-10-15 06:12:18,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 199262208. Throughput: 0: 1717.6, 1: 1754.9. Samples: 49822610. Policy #0 lag: (min: 1.0, avg: 9.4, max: 33.0) -[2023-10-15 06:12:18,535][87330] Avg episode reward: [(0, '23.200'), (1, '22.720')] -[2023-10-15 06:12:18,762][88298] Updated weights for policy 0, policy_version 97010 (0.0008) -[2023-10-15 06:12:19,132][88298] Updated weights for policy 0, policy_version 97020 (0.0007) -[2023-10-15 06:12:19,551][88300] Updated weights for policy 1, policy_version 97602 (0.0008) -[2023-10-15 06:12:19,915][88300] Updated weights for policy 1, policy_version 97612 (0.0009) -[2023-10-15 06:12:20,289][88300] Updated weights for policy 1, policy_version 97622 (0.0011) -[2023-10-15 06:12:20,652][88300] Updated weights for policy 1, policy_version 97632 (0.0009) -[2023-10-15 06:12:23,136][88298] Updated weights for policy 0, policy_version 97030 (0.0007) -[2023-10-15 06:12:23,505][88298] Updated weights for policy 0, policy_version 97040 (0.0007) -[2023-10-15 06:12:23,534][87330] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 199327744. Throughput: 0: 1739.5, 1: 1752.7. Samples: 49844036. Policy #0 lag: (min: 1.0, avg: 9.4, max: 33.0) -[2023-10-15 06:12:23,535][87330] Avg episode reward: [(0, '23.210'), (1, '22.780')] -[2023-10-15 06:12:23,877][88298] Updated weights for policy 0, policy_version 97050 (0.0007) -[2023-10-15 06:12:24,515][88300] Updated weights for policy 1, policy_version 97642 (0.0008) -[2023-10-15 06:12:24,884][88300] Updated weights for policy 1, policy_version 97652 (0.0011) -[2023-10-15 06:12:25,251][88300] Updated weights for policy 1, policy_version 97662 (0.0009) -[2023-10-15 06:12:27,917][88298] Updated weights for policy 0, policy_version 97060 (0.0009) -[2023-10-15 06:12:28,286][88298] Updated weights for policy 0, policy_version 97070 (0.0007) -[2023-10-15 06:12:28,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 199393280. Throughput: 0: 1738.3, 1: 1775.6. Samples: 49865426. Policy #0 lag: (min: 1.0, avg: 9.4, max: 33.0) -[2023-10-15 06:12:28,534][87330] Avg episode reward: [(0, '23.240'), (1, '22.760')] -[2023-10-15 06:12:28,651][88298] Updated weights for policy 0, policy_version 97080 (0.0007) -[2023-10-15 06:12:29,127][88300] Updated weights for policy 1, policy_version 97672 (0.0007) -[2023-10-15 06:12:29,487][88300] Updated weights for policy 1, policy_version 97682 (0.0009) -[2023-10-15 06:12:29,851][88300] Updated weights for policy 1, policy_version 97692 (0.0009) -[2023-10-15 06:12:32,570][88298] Updated weights for policy 0, policy_version 97090 (0.0009) -[2023-10-15 06:12:32,954][88298] Updated weights for policy 0, policy_version 97100 (0.0008) -[2023-10-15 06:12:33,325][88298] Updated weights for policy 0, policy_version 97110 (0.0008) -[2023-10-15 06:12:33,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 199458816. Throughput: 0: 1726.3, 1: 1753.1. Samples: 49875000. Policy #0 lag: (min: 1.0, avg: 9.4, max: 33.0) -[2023-10-15 06:12:33,535][87330] Avg episode reward: [(0, '23.260'), (1, '22.940')] -[2023-10-15 06:12:33,687][88298] Updated weights for policy 0, policy_version 97120 (0.0007) -[2023-10-15 06:12:33,721][88300] Updated weights for policy 1, policy_version 97702 (0.0007) -[2023-10-15 06:12:34,090][88300] Updated weights for policy 1, policy_version 97712 (0.0008) -[2023-10-15 06:12:34,458][88300] Updated weights for policy 1, policy_version 97722 (0.0008) -[2023-10-15 06:12:37,541][88298] Updated weights for policy 0, policy_version 97130 (0.0009) -[2023-10-15 06:12:37,911][88298] Updated weights for policy 0, policy_version 97140 (0.0008) -[2023-10-15 06:12:38,122][88300] Updated weights for policy 1, policy_version 97732 (0.0008) -[2023-10-15 06:12:38,273][88298] Updated weights for policy 0, policy_version 97150 (0.0007) -[2023-10-15 06:12:38,488][88300] Updated weights for policy 1, policy_version 97742 (0.0009) -[2023-10-15 06:12:38,534][87330] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 199557120. Throughput: 0: 1745.7, 1: 1768.4. Samples: 49896872. Policy #0 lag: (min: 1.0, avg: 9.4, max: 33.0) -[2023-10-15 06:12:38,534][87330] Avg episode reward: [(0, '23.180'), (1, '23.000')] -[2023-10-15 06:12:38,847][88300] Updated weights for policy 1, policy_version 97752 (0.0010) -[2023-10-15 06:12:42,200][88298] Updated weights for policy 0, policy_version 97160 (0.0007) -[2023-10-15 06:12:42,576][88298] Updated weights for policy 0, policy_version 97170 (0.0008) -[2023-10-15 06:12:42,744][88300] Updated weights for policy 1, policy_version 97762 (0.0007) -[2023-10-15 06:12:42,933][88298] Updated weights for policy 0, policy_version 97180 (0.0008) -[2023-10-15 06:12:43,164][88300] Updated weights for policy 1, policy_version 97772 (0.0008) -[2023-10-15 06:12:43,534][87330] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 199622656. Throughput: 0: 1724.4, 1: 1765.3. Samples: 49917050. Policy #0 lag: (min: 1.0, avg: 9.4, max: 33.0) -[2023-10-15 06:12:43,535][87330] Avg episode reward: [(0, '22.940'), (1, '23.010')] -[2023-10-15 06:12:43,537][88300] Updated weights for policy 1, policy_version 97782 (0.0007) -[2023-10-15 06:12:43,897][88300] Updated weights for policy 1, policy_version 97792 (0.0007) -[2023-10-15 06:12:47,012][88298] Updated weights for policy 0, policy_version 97190 (0.0007) -[2023-10-15 06:12:47,393][88298] Updated weights for policy 0, policy_version 97200 (0.0009) -[2023-10-15 06:12:47,758][88298] Updated weights for policy 0, policy_version 97210 (0.0008) -[2023-10-15 06:12:47,777][88300] Updated weights for policy 1, policy_version 97802 (0.0008) -[2023-10-15 06:12:48,137][88300] Updated weights for policy 1, policy_version 97812 (0.0009) -[2023-10-15 06:12:48,501][88300] Updated weights for policy 1, policy_version 97822 (0.0008) -[2023-10-15 06:12:48,534][87330] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13884.8). Total num frames: 199688192. Throughput: 0: 1748.8, 1: 1751.2. Samples: 49928084. Policy #0 lag: (min: 28.0, avg: 32.6, max: 60.0) -[2023-10-15 06:12:48,534][87330] Avg episode reward: [(0, '22.980'), (1, '23.200')] -[2023-10-15 06:12:51,665][88298] Updated weights for policy 0, policy_version 97220 (0.0008) -[2023-10-15 06:12:52,045][88298] Updated weights for policy 0, policy_version 97230 (0.0008) -[2023-10-15 06:12:52,408][88298] Updated weights for policy 0, policy_version 97240 (0.0007) -[2023-10-15 06:12:52,426][88300] Updated weights for policy 1, policy_version 97832 (0.0008) -[2023-10-15 06:12:52,784][88300] Updated weights for policy 1, policy_version 97842 (0.0007) -[2023-10-15 06:12:53,148][88300] Updated weights for policy 1, policy_version 97852 (0.0011) -[2023-10-15 06:12:53,534][87330] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 199786496. Throughput: 0: 1740.1, 1: 1777.2. Samples: 49949264. Policy #0 lag: (min: 28.0, avg: 32.6, max: 60.0) -[2023-10-15 06:12:53,534][87330] Avg episode reward: [(0, '22.930'), (1, '23.170')] -[2023-10-15 06:12:56,298][88298] Updated weights for policy 0, policy_version 97250 (0.0008) -[2023-10-15 06:12:56,660][88298] Updated weights for policy 0, policy_version 97260 (0.0008) -[2023-10-15 06:12:57,027][88298] Updated weights for policy 0, policy_version 97270 (0.0007) -[2023-10-15 06:12:57,280][88300] Updated weights for policy 1, policy_version 97862 (0.0009) -[2023-10-15 06:12:57,397][88298] Updated weights for policy 0, policy_version 97280 (0.0008) -[2023-10-15 06:12:57,649][88300] Updated weights for policy 1, policy_version 97872 (0.0009) -[2023-10-15 06:12:58,016][88300] Updated weights for policy 1, policy_version 97882 (0.0008) -[2023-10-15 06:12:58,534][87330] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 199852032. Throughput: 0: 1718.2, 1: 1735.9. Samples: 49968458. Policy #0 lag: (min: 28.0, avg: 32.6, max: 60.0) -[2023-10-15 06:12:58,534][87330] Avg episode reward: [(0, '22.850'), (1, '23.190')] -[2023-10-15 06:12:58,543][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000097888_100237312.pth... -[2023-10-15 06:12:58,543][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000097280_99614720.pth... -[2023-10-15 06:12:58,572][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000096256_98566144.pth -[2023-10-15 06:12:58,576][88033] Saving a milestone ./train_atari/atari_seaquest_APPO/checkpoint_p1/milestones/checkpoint_000097888_100237312.pth -[2023-10-15 06:12:58,580][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000095648_97943552.pth -[2023-10-15 06:12:58,583][87905] Saving a milestone ./train_atari/atari_seaquest_APPO/checkpoint_p0/milestones/checkpoint_000097280_99614720.pth -[2023-10-15 06:13:01,155][88298] Updated weights for policy 0, policy_version 97290 (0.0010) -[2023-10-15 06:13:01,525][88298] Updated weights for policy 0, policy_version 97300 (0.0011) -[2023-10-15 06:13:01,890][88298] Updated weights for policy 0, policy_version 97310 (0.0009) -[2023-10-15 06:13:01,962][88300] Updated weights for policy 1, policy_version 97892 (0.0008) -[2023-10-15 06:13:02,336][88300] Updated weights for policy 1, policy_version 97902 (0.0007) -[2023-10-15 06:13:02,698][88300] Updated weights for policy 1, policy_version 97912 (0.0010) -[2023-10-15 06:13:03,534][87330] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 199917568. Throughput: 0: 1751.3, 1: 1761.9. Samples: 49980704. Policy #0 lag: (min: 28.0, avg: 32.6, max: 60.0) -[2023-10-15 06:13:03,535][87330] Avg episode reward: [(0, '22.850'), (1, '23.170')] -[2023-10-15 06:13:05,598][88298] Updated weights for policy 0, policy_version 97320 (0.0008) -[2023-10-15 06:13:05,976][88298] Updated weights for policy 0, policy_version 97330 (0.0008) -[2023-10-15 06:13:06,340][88298] Updated weights for policy 0, policy_version 97340 (0.0010) -[2023-10-15 06:13:06,628][88300] Updated weights for policy 1, policy_version 97922 (0.0010) -[2023-10-15 06:13:06,998][88300] Updated weights for policy 1, policy_version 97932 (0.0010) -[2023-10-15 06:13:07,366][88300] Updated weights for policy 1, policy_version 97942 (0.0007) -[2023-10-15 06:13:07,729][88300] Updated weights for policy 1, policy_version 97952 (0.0011) -[2023-10-15 06:13:08,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 199983104. Throughput: 0: 1724.1, 1: 1746.2. Samples: 50000198. Policy #0 lag: (min: 28.0, avg: 32.6, max: 60.0) -[2023-10-15 06:13:08,535][87330] Avg episode reward: [(0, '22.830'), (1, '23.020')] -[2023-10-15 06:13:10,234][88298] Updated weights for policy 0, policy_version 97350 (0.0010) -[2023-10-15 06:13:10,599][88298] Updated weights for policy 0, policy_version 97360 (0.0009) -[2023-10-15 06:13:10,970][88298] Updated weights for policy 0, policy_version 97370 (0.0007) -[2023-10-15 06:13:11,457][88300] Updated weights for policy 1, policy_version 97962 (0.0010) -[2023-10-15 06:13:11,821][88300] Updated weights for policy 1, policy_version 97972 (0.0008) -[2023-10-15 06:13:12,190][88300] Updated weights for policy 1, policy_version 97982 (0.0009) -[2023-10-15 06:13:13,534][87330] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 200048640. Throughput: 0: 1729.5, 1: 1731.1. Samples: 50021150. Policy #0 lag: (min: 28.0, avg: 32.6, max: 60.0) -[2023-10-15 06:13:13,534][87330] Avg episode reward: [(0, '23.030'), (1, '23.000')] -[2023-10-15 06:13:14,909][88298] Updated weights for policy 0, policy_version 97380 (0.0008) -[2023-10-15 06:13:15,287][88298] Updated weights for policy 0, policy_version 97390 (0.0007) -[2023-10-15 06:13:15,645][88298] Updated weights for policy 0, policy_version 97400 (0.0008) -[2023-10-15 06:13:16,016][88300] Updated weights for policy 1, policy_version 97992 (0.0008) -[2023-10-15 06:13:16,385][88300] Updated weights for policy 1, policy_version 98002 (0.0010) -[2023-10-15 06:13:16,756][88300] Updated weights for policy 1, policy_version 98012 (0.0009) -[2023-10-15 06:13:18,534][87330] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 200114176. Throughput: 0: 1731.2, 1: 1753.4. Samples: 50031806. Policy #0 lag: (min: 28.0, avg: 32.6, max: 60.0) -[2023-10-15 06:13:18,534][87330] Avg episode reward: [(0, '23.090'), (1, '22.970')] -[2023-10-15 06:13:19,693][88298] Updated weights for policy 0, policy_version 97410 (0.0008) -[2023-10-15 06:13:20,064][88298] Updated weights for policy 0, policy_version 97420 (0.0007) -[2023-10-15 06:13:20,436][88298] Updated weights for policy 0, policy_version 97430 (0.0009) -[2023-10-15 06:13:20,471][88300] Updated weights for policy 1, policy_version 98022 (0.0009) -[2023-10-15 06:13:20,800][88298] Updated weights for policy 0, policy_version 97440 (0.0008) -[2023-10-15 06:13:20,838][88300] Updated weights for policy 1, policy_version 98032 (0.0007) -[2023-10-15 06:13:21,207][88300] Updated weights for policy 1, policy_version 98042 (0.0009) -[2023-10-15 06:13:23,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13884.8). Total num frames: 200179712. Throughput: 0: 1725.7, 1: 1727.8. Samples: 50052278. Policy #0 lag: (min: 28.0, avg: 32.6, max: 60.0) -[2023-10-15 06:13:23,535][87330] Avg episode reward: [(0, '23.140'), (1, '22.990')] -[2023-10-15 06:13:24,811][88298] Updated weights for policy 0, policy_version 97450 (0.0008) -[2023-10-15 06:13:25,173][88298] Updated weights for policy 0, policy_version 97460 (0.0007) -[2023-10-15 06:13:25,206][88300] Updated weights for policy 1, policy_version 98052 (0.0009) -[2023-10-15 06:13:25,538][88298] Updated weights for policy 0, policy_version 97470 (0.0009) -[2023-10-15 06:13:25,577][88300] Updated weights for policy 1, policy_version 98062 (0.0009) -[2023-10-15 06:13:25,941][88300] Updated weights for policy 1, policy_version 98072 (0.0007) -[2023-10-15 06:13:28,534][87330] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 200245248. Throughput: 0: 1742.5, 1: 1733.7. Samples: 50073480. Policy #0 lag: (min: 28.0, avg: 32.6, max: 60.0) -[2023-10-15 06:13:28,534][87330] Avg episode reward: [(0, '23.100'), (1, '22.950')] -[2023-10-15 06:13:29,388][88298] Updated weights for policy 0, policy_version 97480 (0.0009) -[2023-10-15 06:13:29,762][88298] Updated weights for policy 0, policy_version 97490 (0.0009) -[2023-10-15 06:13:29,948][88300] Updated weights for policy 1, policy_version 98082 (0.0008) -[2023-10-15 06:13:30,123][88298] Updated weights for policy 0, policy_version 97500 (0.0008) -[2023-10-15 06:13:30,365][88300] Updated weights for policy 1, policy_version 98092 (0.0009) -[2023-10-15 06:13:30,733][88300] Updated weights for policy 1, policy_version 98102 (0.0010) -[2023-10-15 06:13:31,095][88300] Updated weights for policy 1, policy_version 98112 (0.0010) -[2023-10-15 06:13:33,534][87330] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13884.7). Total num frames: 200310784. Throughput: 0: 1721.8, 1: 1717.6. Samples: 50082858. Policy #0 lag: (min: 28.0, avg: 32.6, max: 60.0) -[2023-10-15 06:13:33,535][87330] Avg episode reward: [(0, '23.080'), (1, '22.960')] -[2023-10-15 06:13:34,019][88298] Updated weights for policy 0, policy_version 97510 (0.0010) -[2023-10-15 06:13:34,386][88298] Updated weights for policy 0, policy_version 97520 (0.0011) -[2023-10-15 06:13:34,753][88298] Updated weights for policy 0, policy_version 97530 (0.0009) -[2023-10-15 06:13:34,964][88300] Updated weights for policy 1, policy_version 98122 (0.0009) -[2023-10-15 06:13:35,320][88300] Updated weights for policy 1, policy_version 98132 (0.0007) -[2023-10-15 06:13:35,689][88300] Updated weights for policy 1, policy_version 98142 (0.0008) -[2023-10-15 06:13:38,534][87330] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 200376320. Throughput: 0: 1733.2, 1: 1717.1. Samples: 50104526. Policy #0 lag: (min: 28.0, avg: 32.6, max: 60.0) -[2023-10-15 06:13:38,534][87330] Avg episode reward: [(0, '23.080'), (1, '23.160')] -[2023-10-15 06:13:38,655][88298] Updated weights for policy 0, policy_version 97540 (0.0010) -[2023-10-15 06:13:39,012][88298] Updated weights for policy 0, policy_version 97550 (0.0008) -[2023-10-15 06:13:39,391][88298] Updated weights for policy 0, policy_version 97560 (0.0007) -[2023-10-15 06:13:39,573][88300] Updated weights for policy 1, policy_version 98152 (0.0008) -[2023-10-15 06:13:39,942][88300] Updated weights for policy 1, policy_version 98162 (0.0008) -[2023-10-15 06:13:40,310][88300] Updated weights for policy 1, policy_version 98172 (0.0008) -[2023-10-15 06:13:43,310][88298] Updated weights for policy 0, policy_version 97570 (0.0009) -[2023-10-15 06:13:43,534][87330] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13884.7). Total num frames: 200441856. Throughput: 0: 1753.6, 1: 1750.9. Samples: 50126162. Policy #0 lag: (min: 28.0, avg: 32.6, max: 60.0) -[2023-10-15 06:13:43,535][87330] Avg episode reward: [(0, '23.060'), (1, '22.910')] -[2023-10-15 06:13:43,678][88298] Updated weights for policy 0, policy_version 97580 (0.0008) -[2023-10-15 06:13:44,053][88298] Updated weights for policy 0, policy_version 97590 (0.0010) -[2023-10-15 06:13:44,304][88300] Updated weights for policy 1, policy_version 98182 (0.0008) -[2023-10-15 06:13:44,422][88298] Updated weights for policy 0, policy_version 97600 (0.0009) -[2023-10-15 06:13:44,668][88300] Updated weights for policy 1, policy_version 98192 (0.0008) -[2023-10-15 06:13:45,044][88300] Updated weights for policy 1, policy_version 98202 (0.0009) -[2023-10-15 06:13:48,261][88298] Updated weights for policy 0, policy_version 97610 (0.0010) -[2023-10-15 06:13:48,534][87330] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13884.8). Total num frames: 200507392. Throughput: 0: 1720.6, 1: 1721.5. Samples: 50135600. Policy #0 lag: (min: 28.0, avg: 32.6, max: 60.0) -[2023-10-15 06:13:48,534][87330] Avg episode reward: [(0, '23.080'), (1, '22.950')] -[2023-10-15 06:13:48,631][88298] Updated weights for policy 0, policy_version 97620 (0.0010) -[2023-10-15 06:13:49,001][88298] Updated weights for policy 0, policy_version 97630 (0.0009) -[2023-10-15 06:13:49,032][88300] Updated weights for policy 1, policy_version 98212 (0.0009) -[2023-10-15 06:13:49,393][88300] Updated weights for policy 1, policy_version 98222 (0.0011) -[2023-10-15 06:13:49,760][88300] Updated weights for policy 1, policy_version 98232 (0.0010) -[2023-10-15 06:13:52,926][88298] Updated weights for policy 0, policy_version 97640 (0.0007) -[2023-10-15 06:13:53,288][88298] Updated weights for policy 0, policy_version 97650 (0.0008) -[2023-10-15 06:13:53,534][87330] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13884.8). Total num frames: 200572928. Throughput: 0: 1748.6, 1: 1735.9. Samples: 50157002. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-15 06:13:53,534][87330] Avg episode reward: [(0, '23.040'), (1, '22.910')] -[2023-10-15 06:13:53,610][88300] Updated weights for policy 1, policy_version 98242 (0.0011) -[2023-10-15 06:13:53,661][88298] Updated weights for policy 0, policy_version 97660 (0.0007) -[2023-10-15 06:13:53,976][88300] Updated weights for policy 1, policy_version 98252 (0.0010) -[2023-10-15 06:13:54,347][88300] Updated weights for policy 1, policy_version 98262 (0.0009) -[2023-10-15 06:13:54,712][88300] Updated weights for policy 1, policy_version 98272 (0.0010) -[2023-10-15 06:13:54,712][88351] Stopping RolloutWorker_w12... -[2023-10-15 06:13:54,712][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000097664_100007936.pth... -[2023-10-15 06:13:54,712][88344] Stopping RolloutWorker_w6... -[2023-10-15 06:13:54,712][88306] Stopping RolloutWorker_w1... -[2023-10-15 06:13:54,712][88351] Loop rollout_proc12_evt_loop terminating... -[2023-10-15 06:13:54,712][88348] Stopping RolloutWorker_w9... -[2023-10-15 06:13:54,712][88305] Stopping RolloutWorker_w0... -[2023-10-15 06:13:54,713][88306] Loop rollout_proc1_evt_loop terminating... -[2023-10-15 06:13:54,713][88344] Loop rollout_proc6_evt_loop terminating... -[2023-10-15 06:13:54,713][88348] Loop rollout_proc9_evt_loop terminating... -[2023-10-15 06:13:54,713][88311] Stopping RolloutWorker_w2... -[2023-10-15 06:13:54,713][88305] Loop rollout_proc0_evt_loop terminating... -[2023-10-15 06:13:54,713][88311] Loop rollout_proc2_evt_loop terminating... -[2023-10-15 06:13:54,713][88341] Stopping RolloutWorker_w4... -[2023-10-15 06:13:54,713][87330] Component RolloutWorker_w12 stopped! -[2023-10-15 06:13:54,712][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000098272_100630528.pth... -[2023-10-15 06:13:54,713][88341] Loop rollout_proc4_evt_loop terminating... -[2023-10-15 06:13:54,713][87330] Component Batcher_0 stopped! -[2023-10-15 06:13:54,714][87330] Component RolloutWorker_w1 stopped! -[2023-10-15 06:13:54,715][87330] Component RolloutWorker_w6 stopped! -[2023-10-15 06:13:54,715][88350] Stopping RolloutWorker_w10... -[2023-10-15 06:13:54,715][88350] Loop rollout_proc10_evt_loop terminating... -[2023-10-15 06:13:54,715][87330] Component RolloutWorker_w9 stopped! -[2023-10-15 06:13:54,716][88948] Stopping RolloutWorker_w14... -[2023-10-15 06:13:54,716][87330] Component RolloutWorker_w0 stopped! -[2023-10-15 06:13:54,716][88948] Loop rollout_proc14_evt_loop terminating... -[2023-10-15 06:13:54,716][88347] Stopping RolloutWorker_w7... -[2023-10-15 06:13:54,716][88346] Stopping RolloutWorker_w5... -[2023-10-15 06:13:54,716][88347] Loop rollout_proc7_evt_loop terminating... -[2023-10-15 06:13:54,716][87330] Component RolloutWorker_w2 stopped! -[2023-10-15 06:13:54,716][88346] Loop rollout_proc5_evt_loop terminating... -[2023-10-15 06:13:54,717][87330] Component RolloutWorker_w4 stopped! -[2023-10-15 06:13:54,717][87330] Component Batcher_1 stopped! -[2023-10-15 06:13:54,717][88345] Stopping RolloutWorker_w8... -[2023-10-15 06:13:54,717][88980] Stopping RolloutWorker_w15... -[2023-10-15 06:13:54,717][87330] Component RolloutWorker_w10 stopped! -[2023-10-15 06:13:54,717][88345] Loop rollout_proc8_evt_loop terminating... -[2023-10-15 06:13:54,718][88980] Loop rollout_proc15_evt_loop terminating... -[2023-10-15 06:13:54,718][88349] Stopping RolloutWorker_w11... -[2023-10-15 06:13:54,718][88342] Stopping RolloutWorker_w3... -[2023-10-15 06:13:54,712][87905] Stopping Batcher_0... -[2023-10-15 06:13:54,718][87330] Component RolloutWorker_w14 stopped! -[2023-10-15 06:13:54,718][88342] Loop rollout_proc3_evt_loop terminating... -[2023-10-15 06:13:54,718][88349] Loop rollout_proc11_evt_loop terminating... -[2023-10-15 06:13:54,718][87330] Component RolloutWorker_w7 stopped! -[2023-10-15 06:13:54,719][87330] Component RolloutWorker_w5 stopped! -[2023-10-15 06:13:54,719][88352] Stopping RolloutWorker_w13... -[2023-10-15 06:13:54,713][88033] Stopping Batcher_1... -[2023-10-15 06:13:54,719][87330] Component RolloutWorker_w8 stopped! -[2023-10-15 06:13:54,719][88352] Loop rollout_proc13_evt_loop terminating... -[2023-10-15 06:13:54,720][87330] Component RolloutWorker_w15 stopped! -[2023-10-15 06:13:54,720][87330] Component RolloutWorker_w11 stopped! -[2023-10-15 06:13:54,721][87330] Component RolloutWorker_w3 stopped! -[2023-10-15 06:13:54,721][87330] Component RolloutWorker_w13 stopped! -[2023-10-15 06:13:54,731][88298] Weights refcount: 2 0 -[2023-10-15 06:13:54,733][88298] Stopping InferenceWorker_p0-w0... -[2023-10-15 06:13:54,733][88298] Loop inference_proc0-0_evt_loop terminating... -[2023-10-15 06:13:54,733][87330] Component InferenceWorker_p0-w0 stopped! -[2023-10-15 06:13:54,743][88300] Weights refcount: 2 0 -[2023-10-15 06:13:54,744][88300] Stopping InferenceWorker_p1-w0... -[2023-10-15 06:13:54,745][88300] Loop inference_proc1-0_evt_loop terminating... -[2023-10-15 06:13:54,745][87330] Component InferenceWorker_p1-w0 stopped! -[2023-10-15 06:13:54,733][88033] Loop batcher_evt_loop terminating... -[2023-10-15 06:13:54,733][87905] Loop batcher_evt_loop terminating... -[2023-10-15 06:13:54,762][88033] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000097056_99385344.pth -[2023-10-15 06:13:54,762][87905] Removing ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000096480_98795520.pth -[2023-10-15 06:13:54,768][88033] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p1/checkpoint_000098272_100630528.pth... -[2023-10-15 06:13:54,768][87905] Saving ./train_atari/atari_seaquest_APPO/checkpoint_p0/checkpoint_000097664_100007936.pth... -[2023-10-15 06:13:54,829][88033] Stopping LearnerWorker_p1... -[2023-10-15 06:13:54,830][88033] Loop learner_proc1_evt_loop terminating... -[2023-10-15 06:13:54,829][87330] Component LearnerWorker_p1 stopped! -[2023-10-15 06:13:54,830][87905] Stopping LearnerWorker_p0... -[2023-10-15 06:13:54,831][87905] Loop learner_proc0_evt_loop terminating... -[2023-10-15 06:13:54,831][87330] Component LearnerWorker_p0 stopped! -[2023-10-15 06:13:54,831][87330] Waiting for process learner_proc0 to stop... -[2023-10-15 06:13:55,721][87330] Waiting for process learner_proc1 to stop... -[2023-10-15 06:13:55,752][87330] Waiting for process inference_proc0-0 to join... -[2023-10-15 06:13:55,753][87330] Waiting for process inference_proc1-0 to join... -[2023-10-15 06:13:55,754][87330] Waiting for process rollout_proc0 to join... -[2023-10-15 06:13:55,754][87330] Waiting for process rollout_proc1 to join... -[2023-10-15 06:13:55,755][87330] Waiting for process rollout_proc2 to join... -[2023-10-15 06:13:55,756][87330] Waiting for process rollout_proc3 to join... -[2023-10-15 06:13:55,756][87330] Waiting for process rollout_proc4 to join... -[2023-10-15 06:13:55,757][87330] Waiting for process rollout_proc5 to join... -[2023-10-15 06:13:55,758][87330] Waiting for process rollout_proc6 to join... -[2023-10-15 06:13:55,759][87330] Waiting for process rollout_proc7 to join... -[2023-10-15 06:13:55,760][87330] Waiting for process rollout_proc8 to join... -[2023-10-15 06:13:55,760][87330] Waiting for process rollout_proc9 to join... -[2023-10-15 06:13:55,761][87330] Waiting for process rollout_proc10 to join... -[2023-10-15 06:13:55,762][87330] Waiting for process rollout_proc11 to join... -[2023-10-15 06:13:55,762][87330] Waiting for process rollout_proc12 to join... -[2023-10-15 06:13:55,763][87330] Waiting for process rollout_proc13 to join... -[2023-10-15 06:13:55,763][87330] Waiting for process rollout_proc14 to join... -[2023-10-15 06:13:55,764][87330] Waiting for process rollout_proc15 to join... -[2023-10-15 06:13:55,764][87330] Batcher 0 profile tree view: -batching: 170.6026, releasing_batches: 0.0902 -[2023-10-15 06:13:55,764][87330] Batcher 1 profile tree view: -batching: 170.6530, releasing_batches: 0.0948 -[2023-10-15 06:13:55,765][87330] InferenceWorker_p0-w0 profile tree view: -wait_policy: 0.0000 - wait_policy_total: 2231.6545 -update_model: 200.7035 - weight_update: 0.0007 -one_step: 0.0019 - handle_policy_step: 11323.8745 - deserialize: 63.6281, stack: 192.0024, obs_to_device_normalize: 2514.8339, forward: 5141.3310, prepare_outputs: 2451.0864, send_messages: 464.7167 -[2023-10-15 06:13:55,765][87330] InferenceWorker_p1-w0 profile tree view: -wait_policy: 0.0002 - wait_policy_total: 2244.7999 -update_model: 201.0398 - weight_update: 0.0010 -one_step: 0.0025 - handle_policy_step: 11313.1699 - deserialize: 64.1632, stack: 194.4284, obs_to_device_normalize: 2514.3958, forward: 5101.1109, prepare_outputs: 2481.9226, send_messages: 466.7674 -[2023-10-15 06:13:55,766][87330] Learner 0 profile tree view: -misc: 0.0184, prepare_batch: 268.8250 -train: 3631.5470 - epoch_init: 0.1827, minibatch_init: 13.3094, losses_postprocess: 896.5686, kl_divergence: 32.2272, update: 384.1278, after_optimizer: 2119.8538 - calculate_losses: 168.3982 - losses_init: 0.3979, forward_head: 58.7129, bptt_initial: 1.3950, bptt: 1.7716, tail: 37.9703, advantages_returns: 10.9466, losses: 43.6193 -[2023-10-15 06:13:55,766][87330] Learner 1 profile tree view: -misc: 0.0188, prepare_batch: 269.9074 -train: 3624.2720 - epoch_init: 0.1857, minibatch_init: 13.1077, losses_postprocess: 896.9835, kl_divergence: 31.8924, update: 386.7111, after_optimizer: 2108.4285 - calculate_losses: 170.2488 - losses_init: 0.3873, forward_head: 60.0771, bptt_initial: 1.4419, bptt: 1.8046, tail: 38.1421, advantages_returns: 11.1128, losses: 43.5887 -[2023-10-15 06:13:55,766][87330] RolloutWorker_w0 profile tree view: -wait_for_trajectories: 1.2134, enqueue_policy_requests: 404.1246, process_policy_outputs: 190.0800, env_step: 7144.1441, finalize_trajectories: 3.4137, complete_rollouts: 2.9198 -post_env_step: 371.0546 - process_env_step: 83.2717 -[2023-10-15 06:13:55,767][87330] RolloutWorker_w15 profile tree view: -wait_for_trajectories: 1.2377, enqueue_policy_requests: 409.2172, process_policy_outputs: 193.1441, env_step: 7079.7668, finalize_trajectories: 3.5119, complete_rollouts: 2.9829 -post_env_step: 380.1136 - process_env_step: 84.2577 -[2023-10-15 06:13:55,769][87330] Loop Runner_EvtLoop terminating... -[2023-10-15 06:13:55,769][87330] Runner profile tree view: -main_loop: 14452.6851 -[2023-10-15 06:13:55,770][87330] Collected {0: 100007936, 1: 100630528}, FPS: 13882.4 +version https://git-lfs.github.com/spec/v1 +oid sha256:2f230d198bff568759245af957c474166b5bd9226e77999564790708f8f1de4a +size 49083929